summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig114
-rw-r--r--arch/x86/Kconfig.debug10
-rw-r--r--arch/x86/Makefile8
-rw-r--r--arch/x86/boot/Makefile3
-rw-r--r--arch/x86/boot/boot.h1
-rw-r--r--arch/x86/boot/compressed/eboot.c789
-rw-r--r--arch/x86/boot/compressed/eboot.h9
-rw-r--r--arch/x86/boot/compressed/head_32.S31
-rw-r--r--arch/x86/boot/compressed/head_64.S1
-rw-r--r--arch/x86/boot/compressed/misc.c77
-rw-r--r--arch/x86/boot/compressed/mkpiggy.c16
-rw-r--r--arch/x86/boot/printf.c2
-rw-r--r--arch/x86/boot/tools/build.c40
-rw-r--r--arch/x86/configs/i386_defconfig2
-rw-r--r--arch/x86/configs/x86_64_defconfig2
-rw-r--r--arch/x86/crypto/Makefile2
-rw-r--r--arch/x86/crypto/camellia_glue.c64
-rw-r--r--arch/x86/crypto/crct10dif-pcl-asm_64.S643
-rw-r--r--arch/x86/crypto/crct10dif-pclmul_glue.c151
-rw-r--r--arch/x86/ia32/ia32_signal.c2
-rw-r--r--arch/x86/ia32/ia32entry.S2
-rw-r--r--arch/x86/include/asm/acpi.h2
-rw-r--r--arch/x86/include/asm/alternative.h14
-rw-r--r--arch/x86/include/asm/apic.h2
-rw-r--r--arch/x86/include/asm/asm.h6
-rw-r--r--arch/x86/include/asm/atomic.h29
-rw-r--r--arch/x86/include/asm/atomic64_64.h28
-rw-r--r--arch/x86/include/asm/bitops.h70
-rw-r--r--arch/x86/include/asm/calling.h50
-rw-r--r--arch/x86/include/asm/checksum_32.h22
-rw-r--r--arch/x86/include/asm/checksum_64.h2
-rw-r--r--arch/x86/include/asm/cpufeature.h23
-rw-r--r--arch/x86/include/asm/dma-contiguous.h1
-rw-r--r--arch/x86/include/asm/e820.h2
-rw-r--r--arch/x86/include/asm/efi.h2
-rw-r--r--arch/x86/include/asm/hw_irq.h120
-rw-r--r--arch/x86/include/asm/hypervisor.h2
-rw-r--r--arch/x86/include/asm/intel-mid.h113
-rw-r--r--arch/x86/include/asm/intel_mid_vrtc.h (renamed from arch/x86/include/asm/mrst-vrtc.h)4
-rw-r--r--arch/x86/include/asm/irq.h2
-rw-r--r--arch/x86/include/asm/jump_label.h11
-rw-r--r--arch/x86/include/asm/kprobes.h10
-rw-r--r--arch/x86/include/asm/kvm_host.h14
-rw-r--r--arch/x86/include/asm/kvm_para.h38
-rw-r--r--arch/x86/include/asm/local.h28
-rw-r--r--arch/x86/include/asm/mce.h17
-rw-r--r--arch/x86/include/asm/misc.h6
-rw-r--r--arch/x86/include/asm/mmu_context.h20
-rw-r--r--arch/x86/include/asm/mrst.h81
-rw-r--r--arch/x86/include/asm/mutex_64.h30
-rw-r--r--arch/x86/include/asm/page_32_types.h2
-rw-r--r--arch/x86/include/asm/page_64_types.h5
-rw-r--r--arch/x86/include/asm/page_types.h5
-rw-r--r--arch/x86/include/asm/paravirt.h32
-rw-r--r--arch/x86/include/asm/paravirt_types.h17
-rw-r--r--arch/x86/include/asm/pci.h30
-rw-r--r--arch/x86/include/asm/percpu.h3
-rw-r--r--arch/x86/include/asm/pgtable.h37
-rw-r--r--arch/x86/include/asm/pgtable_types.h3
-rw-r--r--arch/x86/include/asm/preempt.h100
-rw-r--r--arch/x86/include/asm/processor.h34
-rw-r--r--arch/x86/include/asm/pvclock.h1
-rw-r--r--arch/x86/include/asm/rmwcc.h41
-rw-r--r--arch/x86/include/asm/setup.h12
-rw-r--r--arch/x86/include/asm/special_insns.h2
-rw-r--r--arch/x86/include/asm/spinlock.h133
-rw-r--r--arch/x86/include/asm/spinlock_types.h16
-rw-r--r--arch/x86/include/asm/switch_to.h4
-rw-r--r--arch/x86/include/asm/sync_bitops.h24
-rw-r--r--arch/x86/include/asm/syscall.h3
-rw-r--r--arch/x86/include/asm/syscalls.h6
-rw-r--r--arch/x86/include/asm/sysfb.h98
-rw-r--r--arch/x86/include/asm/thread_info.h5
-rw-r--r--arch/x86/include/asm/tlbflush.h37
-rw-r--r--arch/x86/include/asm/topology.h3
-rw-r--r--arch/x86/include/asm/traps.h6
-rw-r--r--arch/x86/include/asm/tsc.h1
-rw-r--r--arch/x86/include/asm/uaccess.h105
-rw-r--r--arch/x86/include/asm/uaccess_32.h29
-rw-r--r--arch/x86/include/asm/uaccess_64.h28
-rw-r--r--arch/x86/include/asm/uprobes.h12
-rw-r--r--arch/x86/include/asm/vmx.h2
-rw-r--r--arch/x86/include/asm/vvar.h2
-rw-r--r--arch/x86/include/asm/xen/events.h1
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h16
-rw-r--r--arch/x86/include/asm/xen/page.h31
-rw-r--r--arch/x86/include/asm/xor_avx.h4
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h2
-rw-r--r--arch/x86/include/uapi/asm/hyperv.h19
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h1
-rw-r--r--arch/x86/include/uapi/asm/vmx.h6
-rw-r--r--arch/x86/kernel/Makefile5
-rw-r--r--arch/x86/kernel/acpi/boot.c25
-rw-r--r--arch/x86/kernel/alternative.c155
-rw-r--r--arch/x86/kernel/amd_nb.c13
-rw-r--r--arch/x86/kernel/apb_timer.c10
-rw-r--r--arch/x86/kernel/apic/apic.c12
-rw-r--r--arch/x86/kernel/apic/io_apic.c14
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c2
-rw-r--r--arch/x86/kernel/apm_32.c2
-rw-r--r--arch/x86/kernel/asm-offsets.c1
-rw-r--r--arch/x86/kernel/cpu/amd.c10
-rw-r--r--arch/x86/kernel/cpu/centaur.c8
-rw-r--r--arch/x86/kernel/cpu/common.c21
-rw-r--r--arch/x86/kernel/cpu/cpu.h20
-rw-r--r--arch/x86/kernel/cpu/hypervisor.c15
-rw-r--r--arch/x86/kernel/cpu/intel.c12
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-apei.c3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-internal.h3
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c28
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c42
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c40
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c2
-rw-r--r--arch/x86/kernel/cpu/perf_event.c27
-rw-r--r--arch/x86/kernel/cpu/perf_event.h8
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c3
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c260
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c236
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c31
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c402
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.h10
-rw-r--r--arch/x86/kernel/cpu/proc.c15
-rw-r--r--arch/x86/kernel/cpu/umc.c4
-rw-r--r--arch/x86/kernel/cpu/vmware.c8
-rw-r--r--arch/x86/kernel/crash.c6
-rw-r--r--arch/x86/kernel/devicetree.c3
-rw-r--r--arch/x86/kernel/e820.c5
-rw-r--r--arch/x86/kernel/early-quirks.c154
-rw-r--r--arch/x86/kernel/early_printk.c9
-rw-r--r--arch/x86/kernel/entry_32.S10
-rw-r--r--arch/x86/kernel/entry_64.S23
-rw-r--r--arch/x86/kernel/head32.c6
-rw-r--r--arch/x86/kernel/head64.c2
-rw-r--r--arch/x86/kernel/head_32.S2
-rw-r--r--arch/x86/kernel/i386_ksyms_32.c7
-rw-r--r--arch/x86/kernel/i8259.c3
-rw-r--r--arch/x86/kernel/irq.c8
-rw-r--r--arch/x86/kernel/irq_32.c34
-rw-r--r--arch/x86/kernel/irq_64.c21
-rw-r--r--arch/x86/kernel/irq_work.c4
-rw-r--r--arch/x86/kernel/jump_label.c84
-rw-r--r--arch/x86/kernel/kprobes/common.h5
-rw-r--r--arch/x86/kernel/kprobes/core.c4
-rw-r--r--arch/x86/kernel/kprobes/opt.c115
-rw-r--r--arch/x86/kernel/kvm.c279
-rw-r--r--arch/x86/kernel/microcode_amd.c1
-rw-r--r--arch/x86/kernel/msr.c2
-rw-r--r--arch/x86/kernel/nmi.c4
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c18
-rw-r--r--arch/x86/kernel/paravirt.c9
-rw-r--r--arch/x86/kernel/preempt.S25
-rw-r--r--arch/x86/kernel/process.c8
-rw-r--r--arch/x86/kernel/process_32.c10
-rw-r--r--arch/x86/kernel/process_64.c12
-rw-r--r--arch/x86/kernel/pvclock.c44
-rw-r--r--arch/x86/kernel/reboot.c285
-rw-r--r--arch/x86/kernel/rtc.c12
-rw-r--r--arch/x86/kernel/setup.c28
-rw-r--r--arch/x86/kernel/signal.c12
-rw-r--r--arch/x86/kernel/smp.c12
-rw-r--r--arch/x86/kernel/smpboot.c36
-rw-r--r--arch/x86/kernel/syscall_32.c2
-rw-r--r--arch/x86/kernel/syscall_64.c5
-rw-r--r--arch/x86/kernel/sysfb.c74
-rw-r--r--arch/x86/kernel/sysfb_efi.c214
-rw-r--r--arch/x86/kernel/sysfb_simplefb.c95
-rw-r--r--arch/x86/kernel/tboot.c10
-rw-r--r--arch/x86/kernel/traps.c8
-rw-r--r--arch/x86/kernel/tsc.c6
-rw-r--r--arch/x86/kernel/vmlinux.lds.S9
-rw-r--r--arch/x86/kernel/x8664_ksyms_64.c7
-rw-r--r--arch/x86/kernel/x86_init.c24
-rw-r--r--arch/x86/kvm/cpuid.c3
-rw-r--r--arch/x86/kvm/emulate.c14
-rw-r--r--arch/x86/kvm/lapic.c38
-rw-r--r--arch/x86/kvm/mmu.c206
-rw-r--r--arch/x86/kvm/mmu.h2
-rw-r--r--arch/x86/kvm/paging_tmpl.h198
-rw-r--r--arch/x86/kvm/pmu.c25
-rw-r--r--arch/x86/kvm/vmx.c472
-rw-r--r--arch/x86/kvm/x86.c224
-rw-r--r--arch/x86/lguest/boot.c10
-rw-r--r--arch/x86/lib/Makefile2
-rw-r--r--arch/x86/lib/csum-wrappers_64.c12
-rw-r--r--arch/x86/lib/misc.c21
-rw-r--r--arch/x86/lib/usercopy.c43
-rw-r--r--arch/x86/lib/usercopy_32.c8
-rw-r--r--arch/x86/lib/usercopy_64.c2
-rw-r--r--arch/x86/lib/x86-opcode-map.txt42
-rw-r--r--arch/x86/mm/fault.c82
-rw-r--r--arch/x86/mm/hugetlbpage.c8
-rw-r--r--arch/x86/mm/init.c23
-rw-r--r--arch/x86/mm/ioremap.c5
-rw-r--r--arch/x86/mm/srat.c11
-rw-r--r--arch/x86/mm/tlb.c14
-rw-r--r--arch/x86/net/bpf_jit_comp.c18
-rw-r--r--arch/x86/oprofile/backtrace.c4
-rw-r--r--arch/x86/oprofile/nmi_int.c18
-rw-r--r--arch/x86/oprofile/op_model_amd.c24
-rw-r--r--arch/x86/pci/Makefile2
-rw-r--r--arch/x86/pci/acpi.c9
-rw-r--r--arch/x86/pci/i386.c4
-rw-r--r--arch/x86/pci/intel_mid_pci.c (renamed from arch/x86/pci/mrst.c)59
-rw-r--r--arch/x86/platform/Makefile2
-rw-r--r--arch/x86/platform/efi/Makefile1
-rw-r--r--arch/x86/platform/efi/early_printk.c191
-rw-r--r--arch/x86/platform/efi/efi.c137
-rw-r--r--arch/x86/platform/geode/alix.c2
-rw-r--r--arch/x86/platform/geode/geos.c2
-rw-r--r--arch/x86/platform/geode/net5501.c2
-rw-r--r--arch/x86/platform/intel-mid/Makefile7
-rw-r--r--arch/x86/platform/intel-mid/device_libs/Makefile22
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_bma023.c20
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_emc1403.c41
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c83
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_ipc.c68
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_ipc.h17
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_lis331.c39
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_max3111.c35
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_max7315.c79
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c36
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic.c87
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic.h19
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c47
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c37
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c48
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c49
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c36
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c37
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c54
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c36
-rw-r--r--arch/x86/platform/intel-mid/device_libs/platform_tca6416.c57
-rw-r--r--arch/x86/platform/intel-mid/early_printk_intel_mid.c (renamed from arch/x86/platform/mrst/early_printk_mrst.c)11
-rw-r--r--arch/x86/platform/intel-mid/intel-mid.c213
-rw-r--r--arch/x86/platform/intel-mid/intel_mid_vrtc.c (renamed from arch/x86/platform/mrst/vrtc.c)19
-rw-r--r--arch/x86/platform/intel-mid/sfi.c488
-rw-r--r--arch/x86/platform/mrst/Makefile3
-rw-r--r--arch/x86/platform/mrst/mrst.c1052
-rw-r--r--arch/x86/power/cpu.c8
-rw-r--r--arch/x86/power/hibernate_64.c12
-rw-r--r--arch/x86/tools/gen-insn-attr-x86.awk4
-rw-r--r--arch/x86/um/os-Linux/prctl.c2
-rw-r--r--arch/x86/vdso/vclock_gettime.c16
-rw-r--r--arch/x86/xen/enlighten.c25
-rw-r--r--arch/x86/xen/irq.c25
-rw-r--r--arch/x86/xen/p2m.c36
-rw-r--r--arch/x86/xen/setup.c29
-rw-r--r--arch/x86/xen/smp.c45
-rw-r--r--arch/x86/xen/spinlock.c450
-rw-r--r--arch/x86/xen/xen-ops.h16
250 files changed, 7968 insertions, 4219 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b32ebf92b0c..725e1573ea8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -16,6 +16,7 @@ config X86_64
def_bool y
depends on 64BIT
select X86_DEV_DMA_OPS
+ select ARCH_USE_CMPXCHG_LOCKREF
### Arch settings
config X86
@@ -81,8 +82,6 @@ config X86
select HAVE_USER_RETURN_NOTIFIER
select ARCH_BINFMT_ELF_RANDOMIZE_PIE
select HAVE_ARCH_JUMP_LABEL
- select HAVE_TEXT_POKE_SMP
- select HAVE_GENERIC_HARDIRQS
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select SPARSE_IRQ
select GENERIC_FIND_FIRST_BIT
@@ -124,6 +123,7 @@ config X86
select COMPAT_OLD_SIGACTION if IA32_EMULATION
select RTC_LIB
select HAVE_DEBUG_STACKOVERFLOW
+ select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
config INSTRUCTION_DECODER
def_bool y
@@ -482,11 +482,12 @@ config X86_INTEL_LPSS
bool "Intel Low Power Subsystem Support"
depends on ACPI
select COMMON_CLK
+ select PINCTRL
---help---
Select to build support for Intel Low Power Subsystem such as
found on Intel Lynxpoint PCH. Selecting this option enables
- things like clock tree (common clock framework) which are needed
- by the LPSS peripheral drivers.
+ things like clock tree (common clock framework) and pincontrol
+ which are needed by the LPSS peripheral drivers.
config X86_RDC321X
bool "RDC R-321x SoC"
@@ -632,6 +633,7 @@ config PARAVIRT_DEBUG
config PARAVIRT_SPINLOCKS
bool "Paravirtualization layer for spinlocks"
depends on PARAVIRT && SMP
+ select UNINLINE_SPIN_UNLOCK
---help---
Paravirtualized spinlocks allow a pvops backend to replace the
spinlock implementation with something virtualization-friendly
@@ -656,6 +658,15 @@ config KVM_GUEST
underlying device model, the host provides the guest with
timing infrastructure such as time of day, and system time
+config KVM_DEBUG_FS
+ bool "Enable debug information for KVM Guests in debugfs"
+ depends on KVM_GUEST && DEBUG_FS
+ default n
+ ---help---
+ This option enables collection of various statistics for KVM guest.
+ Statistics are displayed in debugfs filesystem. Enabling this option
+ may incur significant overhead.
+
source "arch/x86/lguest/Kconfig"
config PARAVIRT_TIME_ACCOUNTING
@@ -746,20 +757,25 @@ config DMI
BIOS code.
config GART_IOMMU
- bool "GART IOMMU support" if EXPERT
- default y
+ bool "Old AMD GART IOMMU support"
select SWIOTLB
depends on X86_64 && PCI && AMD_NB
---help---
- Support for full DMA access of devices with 32bit memory access only
- on systems with more than 3GB. This is usually needed for USB,
- sound, many IDE/SATA chipsets and some other devices.
- Provides a driver for the AMD Athlon64/Opteron/Turion/Sempron GART
- based hardware IOMMU and a software bounce buffer based IOMMU used
- on Intel systems and as fallback.
- The code is only active when needed (enough memory and limited
- device) unless CONFIG_IOMMU_DEBUG or iommu=force is specified
- too.
+ Provides a driver for older AMD Athlon64/Opteron/Turion/Sempron
+ GART based hardware IOMMUs.
+
+ The GART supports full DMA access for devices with 32-bit access
+ limitations, on systems with more than 3 GB. This is usually needed
+ for USB, sound, many IDE/SATA chipsets and some other devices.
+
+ Newer systems typically have a modern AMD IOMMU, supported via
+ the CONFIG_AMD_IOMMU=y config option.
+
+ In normal configurations this driver is only active when needed:
+ there's more than 3 GB of memory and the system contains a
+ 32-bit limited device.
+
+ If unsure, say Y.
config CALGARY_IOMMU
bool "IBM Calgary IOMMU support"
@@ -815,14 +831,16 @@ config MAXSMP
config NR_CPUS
int "Maximum number of CPUs" if SMP && !MAXSMP
range 2 8 if SMP && X86_32 && !X86_BIGSMP
- range 2 512 if SMP && !MAXSMP
+ range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK
+ range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64
default "1" if !SMP
- default "4096" if MAXSMP
+ default "8192" if MAXSMP
default "32" if SMP && (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP || X86_ES7000)
default "8" if SMP
---help---
This allows you to specify the maximum number of CPUs which this
- kernel will support. The maximum supported value is 512 and the
+ kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum
+ supported value is 4096, otherwise the maximum value is 512. The
minimum value which makes sense is 2.
This is purely to save memory - each supported CPU adds
@@ -850,7 +868,7 @@ source "kernel/Kconfig.preempt"
config X86_UP_APIC
bool "Local APIC support on uniprocessors"
- depends on X86_32 && !SMP && !X86_32_NON_STANDARD
+ depends on X86_32 && !SMP && !X86_32_NON_STANDARD && !PCI_MSI
---help---
A local APIC (Advanced Programmable Interrupt Controller) is an
integrated interrupt controller in the CPU. If you have a single-CPU
@@ -875,11 +893,11 @@ config X86_UP_IOAPIC
config X86_LOCAL_APIC
def_bool y
- depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC
+ depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
config X86_IO_APIC
def_bool y
- depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC
+ depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI
config X86_VISWS_APIC
def_bool y
@@ -1023,6 +1041,7 @@ config X86_REBOOTFIXUPS
config MICROCODE
tristate "CPU microcode loading support"
+ depends on CPU_SUP_AMD || CPU_SUP_INTEL
select FW_LOADER
---help---
@@ -1344,8 +1363,12 @@ config ARCH_SELECT_MEMORY_MODEL
depends on ARCH_SPARSEMEM_ENABLE
config ARCH_MEMORY_PROBE
- def_bool y
+ bool "Enable sysfs memory/probe interface"
depends on X86_64 && MEMORY_HOTPLUG
+ help
+ This option enables a sysfs memory/probe interface for testing.
+ See Documentation/memory-hotplug.txt for more information.
+ If you are unsure how to answer this question, answer N.
config ARCH_PROC_KCORE_TEXT
def_bool y
@@ -1579,7 +1602,7 @@ config EFI_STUB
This kernel feature allows a bzImage to be loaded directly
by EFI firmware without the use of a bootloader.
- See Documentation/x86/efi-stub.txt for more information.
+ See Documentation/efi-stub.txt for more information.
config SECCOMP
def_bool y
@@ -1627,9 +1650,9 @@ config KEXEC
It is an ongoing process to be certain the hardware in a machine
is properly shutdown, so do not be surprised if this code does not
- initially work for you. It may help to enable device hotplugging
- support. As of this writing the exact hardware interface is
- strongly in flux, so no good recommendation can be made.
+ initially work for you. As of this writing the exact hardware
+ interface is strongly in flux, so no good recommendation can be
+ made.
config CRASH_DUMP
bool "kernel crash dumps"
@@ -1716,9 +1739,10 @@ config X86_NEED_RELOCS
depends on X86_32 && RELOCATABLE
config PHYSICAL_ALIGN
- hex "Alignment value to which kernel should be aligned" if X86_32
+ hex "Alignment value to which kernel should be aligned"
default "0x1000000"
- range 0x2000 0x1000000
+ range 0x2000 0x1000000 if X86_32
+ range 0x200000 0x1000000 if X86_64
---help---
This value puts the alignment restrictions on physical address
where kernel is loaded and run from. Kernel is compiled for an
@@ -1736,6 +1760,9 @@ config PHYSICAL_ALIGN
end result is that kernel runs from a physical address meeting
above alignment restrictions.
+ On 32-bit this value must be a multiple of 0x2000. On 64-bit
+ this value must be a multiple of 0x200000.
+
Don't change this unless you know what you are doing.
config HOTPLUG_CPU
@@ -2014,7 +2041,6 @@ menu "Bus options (PCI etc.)"
config PCI
bool "PCI support"
default y
- select ARCH_SUPPORTS_MSI if (X86_LOCAL_APIC && X86_IO_APIC)
---help---
Find out whether you have a PCI motherboard. PCI is the name of a
bus system, i.e. the way the CPU talks to the other stuff inside
@@ -2270,6 +2296,32 @@ config RAPIDIO
source "drivers/rapidio/Kconfig"
+config X86_SYSFB
+ bool "Mark VGA/VBE/EFI FB as generic system framebuffer"
+ help
+ Firmwares often provide initial graphics framebuffers so the BIOS,
+ bootloader or kernel can show basic video-output during boot for
+ user-guidance and debugging. Historically, x86 used the VESA BIOS
+ Extensions and EFI-framebuffers for this, which are mostly limited
+ to x86.
+ This option, if enabled, marks VGA/VBE/EFI framebuffers as generic
+ framebuffers so the new generic system-framebuffer drivers can be
+ used on x86. If the framebuffer is not compatible with the generic
+ modes, it is adverticed as fallback platform framebuffer so legacy
+ drivers like efifb, vesafb and uvesafb can pick it up.
+ If this option is not selected, all system framebuffers are always
+ marked as fallback platform framebuffers as usual.
+
+ Note: Legacy fbdev drivers, including vesafb, efifb, uvesafb, will
+ not be able to pick up generic system framebuffers if this option
+ is selected. You are highly encouraged to enable simplefb as
+ replacement if you select this option. simplefb can correctly deal
+ with generic system framebuffers. But you should still keep vesafb
+ and others enabled as fallback if a system framebuffer is
+ incompatible with simplefb.
+
+ If unsure, say Y.
+
endmenu
@@ -2332,10 +2384,6 @@ config HAVE_ATOMIC_IOMAP
def_bool y
depends on X86_32
-config HAVE_TEXT_POKE_SMP
- bool
- select STOP_MACHINE if SMP
-
config X86_DEV_DMA_OPS
bool
depends on X86_64 || STA2X11
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 78d91afb8e5..0f3621ed1db 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -59,6 +59,16 @@ config EARLY_PRINTK_DBGP
with klogd/syslogd or the X server. You should normally N here,
unless you want to debug such a crash. You need usb debug device.
+config EARLY_PRINTK_EFI
+ bool "Early printk via the EFI framebuffer"
+ depends on EFI && EARLY_PRINTK
+ select FONT_SUPPORT
+ ---help---
+ Write kernel log output directly into the EFI framebuffer.
+
+ This is useful for kernel debugging when your machine crashes very
+ early before the console code is initialized.
+
config X86_PTDUMP
bool "Export kernel pagetable layout to userspace via debugfs"
depends on DEBUG_KERNEL
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 07639c656fc..41250fb3398 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -16,6 +16,10 @@ endif
# e.g.: obj-y += foo_$(BITS).o
export BITS
+ifdef CONFIG_X86_NEED_RELOCS
+ LDFLAGS_vmlinux := --emit-relocs
+endif
+
ifeq ($(CONFIG_X86_32),y)
BITS := 32
UTS_MACHINE := i386
@@ -25,10 +29,6 @@ ifeq ($(CONFIG_X86_32),y)
KBUILD_AFLAGS += $(biarch)
KBUILD_CFLAGS += $(biarch)
- ifdef CONFIG_RELOCATABLE
- LDFLAGS_vmlinux := --emit-relocs
- endif
-
KBUILD_CFLAGS += -msoft-float -mregparm=3 -freg-struct-return
# Never want PIC in a 32-bit kernel, prevent breakage with GCC built
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 379814bc41e..dce69a25689 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -71,7 +71,8 @@ GCOV_PROFILE := n
$(obj)/bzImage: asflags-y := $(SVGA_MODE)
quiet_cmd_image = BUILD $@
-cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/zoffset.h > $@
+cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \
+ $(obj)/zoffset.h $@
$(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE
$(call if_changed,image)
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 5b7531966b8..ef72baeff48 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -355,6 +355,7 @@ int strncmp(const char *cs, const char *ct, size_t count);
size_t strnlen(const char *s, size_t maxlen);
unsigned int atou(const char *s);
unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base);
+size_t strlen(const char *s);
/* tty.c */
void puts(const char *);
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index b7388a425f0..a7677babf94 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -19,214 +19,10 @@
static efi_system_table_t *sys_table;
-static void efi_char16_printk(efi_char16_t *str)
-{
- struct efi_simple_text_output_protocol *out;
-
- out = (struct efi_simple_text_output_protocol *)sys_table->con_out;
- efi_call_phys2(out->output_string, out, str);
-}
-
-static void efi_printk(char *str)
-{
- char *s8;
-
- for (s8 = str; *s8; s8++) {
- efi_char16_t ch[2] = { 0 };
-
- ch[0] = *s8;
- if (*s8 == '\n') {
- efi_char16_t nl[2] = { '\r', 0 };
- efi_char16_printk(nl);
- }
-
- efi_char16_printk(ch);
- }
-}
-
-static efi_status_t __get_map(efi_memory_desc_t **map, unsigned long *map_size,
- unsigned long *desc_size)
-{
- efi_memory_desc_t *m = NULL;
- efi_status_t status;
- unsigned long key;
- u32 desc_version;
-
- *map_size = sizeof(*m) * 32;
-again:
- /*
- * Add an additional efi_memory_desc_t because we're doing an
- * allocation which may be in a new descriptor region.
- */
- *map_size += sizeof(*m);
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, *map_size, (void **)&m);
- if (status != EFI_SUCCESS)
- goto fail;
-
- status = efi_call_phys5(sys_table->boottime->get_memory_map, map_size,
- m, &key, desc_size, &desc_version);
- if (status == EFI_BUFFER_TOO_SMALL) {
- efi_call_phys1(sys_table->boottime->free_pool, m);
- goto again;
- }
-
- if (status != EFI_SUCCESS)
- efi_call_phys1(sys_table->boottime->free_pool, m);
-fail:
- *map = m;
- return status;
-}
-
-/*
- * Allocate at the highest possible address that is not above 'max'.
- */
-static efi_status_t high_alloc(unsigned long size, unsigned long align,
- unsigned long *addr, unsigned long max)
-{
- unsigned long map_size, desc_size;
- efi_memory_desc_t *map;
- efi_status_t status;
- unsigned long nr_pages;
- u64 max_addr = 0;
- int i;
-
- status = __get_map(&map, &map_size, &desc_size);
- if (status != EFI_SUCCESS)
- goto fail;
-
- nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
-again:
- for (i = 0; i < map_size / desc_size; i++) {
- efi_memory_desc_t *desc;
- unsigned long m = (unsigned long)map;
- u64 start, end;
-
- desc = (efi_memory_desc_t *)(m + (i * desc_size));
- if (desc->type != EFI_CONVENTIONAL_MEMORY)
- continue;
-
- if (desc->num_pages < nr_pages)
- continue;
+#include "../../../../drivers/firmware/efi/efi-stub-helper.c"
- start = desc->phys_addr;
- end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
- if ((start + size) > end || (start + size) > max)
- continue;
-
- if (end - size > max)
- end = max;
-
- if (round_down(end - size, align) < start)
- continue;
-
- start = round_down(end - size, align);
-
- /*
- * Don't allocate at 0x0. It will confuse code that
- * checks pointers against NULL.
- */
- if (start == 0x0)
- continue;
-
- if (start > max_addr)
- max_addr = start;
- }
-
- if (!max_addr)
- status = EFI_NOT_FOUND;
- else {
- status = efi_call_phys4(sys_table->boottime->allocate_pages,
- EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
- nr_pages, &max_addr);
- if (status != EFI_SUCCESS) {
- max = max_addr;
- max_addr = 0;
- goto again;
- }
-
- *addr = max_addr;
- }
-
-free_pool:
- efi_call_phys1(sys_table->boottime->free_pool, map);
-
-fail:
- return status;
-}
-
-/*
- * Allocate at the lowest possible address.
- */
-static efi_status_t low_alloc(unsigned long size, unsigned long align,
- unsigned long *addr)
-{
- unsigned long map_size, desc_size;
- efi_memory_desc_t *map;
- efi_status_t status;
- unsigned long nr_pages;
- int i;
-
- status = __get_map(&map, &map_size, &desc_size);
- if (status != EFI_SUCCESS)
- goto fail;
-
- nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
- for (i = 0; i < map_size / desc_size; i++) {
- efi_memory_desc_t *desc;
- unsigned long m = (unsigned long)map;
- u64 start, end;
-
- desc = (efi_memory_desc_t *)(m + (i * desc_size));
-
- if (desc->type != EFI_CONVENTIONAL_MEMORY)
- continue;
-
- if (desc->num_pages < nr_pages)
- continue;
-
- start = desc->phys_addr;
- end = start + desc->num_pages * (1UL << EFI_PAGE_SHIFT);
-
- /*
- * Don't allocate at 0x0. It will confuse code that
- * checks pointers against NULL. Skip the first 8
- * bytes so we start at a nice even number.
- */
- if (start == 0x0)
- start += 8;
-
- start = round_up(start, align);
- if ((start + size) > end)
- continue;
-
- status = efi_call_phys4(sys_table->boottime->allocate_pages,
- EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
- nr_pages, &start);
- if (status == EFI_SUCCESS) {
- *addr = start;
- break;
- }
- }
-
- if (i == map_size / desc_size)
- status = EFI_NOT_FOUND;
-
-free_pool:
- efi_call_phys1(sys_table->boottime->free_pool, map);
-fail:
- return status;
-}
-
-static void low_free(unsigned long size, unsigned long addr)
-{
- unsigned long nr_pages;
-
- nr_pages = round_up(size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
- efi_call_phys2(sys_table->boottime->free_pages, addr, nr_pages);
-}
static void find_bits(unsigned long mask, u8 *pos, u8 *size)
{
@@ -624,242 +420,6 @@ void setup_graphics(struct boot_params *boot_params)
}
}
-struct initrd {
- efi_file_handle_t *handle;
- u64 size;
-};
-
-/*
- * Check the cmdline for a LILO-style initrd= arguments.
- *
- * We only support loading an initrd from the same filesystem as the
- * kernel image.
- */
-static efi_status_t handle_ramdisks(efi_loaded_image_t *image,
- struct setup_header *hdr)
-{
- struct initrd *initrds;
- unsigned long initrd_addr;
- efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
- u64 initrd_total;
- efi_file_io_interface_t *io;
- efi_file_handle_t *fh;
- efi_status_t status;
- int nr_initrds;
- char *str;
- int i, j, k;
-
- initrd_addr = 0;
- initrd_total = 0;
-
- str = (char *)(unsigned long)hdr->cmd_line_ptr;
-
- j = 0; /* See close_handles */
-
- if (!str || !*str)
- return EFI_SUCCESS;
-
- for (nr_initrds = 0; *str; nr_initrds++) {
- str = strstr(str, "initrd=");
- if (!str)
- break;
-
- str += 7;
-
- /* Skip any leading slashes */
- while (*str == '/' || *str == '\\')
- str++;
-
- while (*str && *str != ' ' && *str != '\n')
- str++;
- }
-
- if (!nr_initrds)
- return EFI_SUCCESS;
-
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA,
- nr_initrds * sizeof(*initrds),
- &initrds);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for initrds\n");
- goto fail;
- }
-
- str = (char *)(unsigned long)hdr->cmd_line_ptr;
- for (i = 0; i < nr_initrds; i++) {
- struct initrd *initrd;
- efi_file_handle_t *h;
- efi_file_info_t *info;
- efi_char16_t filename_16[256];
- unsigned long info_sz;
- efi_guid_t info_guid = EFI_FILE_INFO_ID;
- efi_char16_t *p;
- u64 file_sz;
-
- str = strstr(str, "initrd=");
- if (!str)
- break;
-
- str += 7;
-
- initrd = &initrds[i];
- p = filename_16;
-
- /* Skip any leading slashes */
- while (*str == '/' || *str == '\\')
- str++;
-
- while (*str && *str != ' ' && *str != '\n') {
- if ((u8 *)p >= (u8 *)filename_16 + sizeof(filename_16))
- break;
-
- if (*str == '/') {
- *p++ = '\\';
- *str++;
- } else {
- *p++ = *str++;
- }
- }
-
- *p = '\0';
-
- /* Only open the volume once. */
- if (!i) {
- efi_boot_services_t *boottime;
-
- boottime = sys_table->boottime;
-
- status = efi_call_phys3(boottime->handle_protocol,
- image->device_handle, &fs_proto, &io);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to handle fs_proto\n");
- goto free_initrds;
- }
-
- status = efi_call_phys2(io->open_volume, io, &fh);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to open volume\n");
- goto free_initrds;
- }
- }
-
- status = efi_call_phys5(fh->open, fh, &h, filename_16,
- EFI_FILE_MODE_READ, (u64)0);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to open initrd file: ");
- efi_char16_printk(filename_16);
- efi_printk("\n");
- goto close_handles;
- }
-
- initrd->handle = h;
-
- info_sz = 0;
- status = efi_call_phys4(h->get_info, h, &info_guid,
- &info_sz, NULL);
- if (status != EFI_BUFFER_TOO_SMALL) {
- efi_printk("Failed to get initrd info size\n");
- goto close_handles;
- }
-
-grow:
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, info_sz, &info);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for initrd info\n");
- goto close_handles;
- }
-
- status = efi_call_phys4(h->get_info, h, &info_guid,
- &info_sz, info);
- if (status == EFI_BUFFER_TOO_SMALL) {
- efi_call_phys1(sys_table->boottime->free_pool, info);
- goto grow;
- }
-
- file_sz = info->file_size;
- efi_call_phys1(sys_table->boottime->free_pool, info);
-
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to get initrd info\n");
- goto close_handles;
- }
-
- initrd->size = file_sz;
- initrd_total += file_sz;
- }
-
- if (initrd_total) {
- unsigned long addr;
-
- /*
- * Multiple initrd's need to be at consecutive
- * addresses in memory, so allocate enough memory for
- * all the initrd's.
- */
- status = high_alloc(initrd_total, 0x1000,
- &initrd_addr, hdr->initrd_addr_max);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc highmem for initrds\n");
- goto close_handles;
- }
-
- /* We've run out of free low memory. */
- if (initrd_addr > hdr->initrd_addr_max) {
- efi_printk("We've run out of free low memory\n");
- status = EFI_INVALID_PARAMETER;
- goto free_initrd_total;
- }
-
- addr = initrd_addr;
- for (j = 0; j < nr_initrds; j++) {
- u64 size;
-
- size = initrds[j].size;
- while (size) {
- u64 chunksize;
- if (size > EFI_READ_CHUNK_SIZE)
- chunksize = EFI_READ_CHUNK_SIZE;
- else
- chunksize = size;
- status = efi_call_phys3(fh->read,
- initrds[j].handle,
- &chunksize, addr);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to read initrd\n");
- goto free_initrd_total;
- }
- addr += chunksize;
- size -= chunksize;
- }
-
- efi_call_phys1(fh->close, initrds[j].handle);
- }
-
- }
-
- efi_call_phys1(sys_table->boottime->free_pool, initrds);
-
- hdr->ramdisk_image = initrd_addr;
- hdr->ramdisk_size = initrd_total;
-
- return status;
-
-free_initrd_total:
- low_free(initrd_total, initrd_addr);
-
-close_handles:
- for (k = j; k < i; k++)
- efi_call_phys1(fh->close, initrds[k].handle);
-free_initrds:
- efi_call_phys1(sys_table->boottime->free_pool, initrds);
-fail:
- hdr->ramdisk_image = 0;
- hdr->ramdisk_size = 0;
-
- return status;
-}
/*
* Because the x86 boot code expects to be passed a boot_params we
@@ -875,14 +435,15 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
struct efi_info *efi;
efi_loaded_image_t *image;
void *options;
- u32 load_options_size;
efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
int options_size = 0;
efi_status_t status;
- unsigned long cmdline;
+ char *cmdline_ptr;
u16 *s2;
u8 *s1;
int i;
+ unsigned long ramdisk_addr;
+ unsigned long ramdisk_size;
sys_table = _table;
@@ -893,13 +454,14 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
status = efi_call_phys3(sys_table->boottime->handle_protocol,
handle, &proto, (void *)&image);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
+ efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
return NULL;
}
- status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
+ status = efi_low_alloc(sys_table, 0x4000, 1,
+ (unsigned long *)&boot_params);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc lowmem for boot params\n");
+ efi_printk(sys_table, "Failed to alloc lowmem for boot params\n");
return NULL;
}
@@ -926,40 +488,11 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
hdr->type_of_loader = 0x21;
/* Convert unicode cmdline to ascii */
- options = image->load_options;
- load_options_size = image->load_options_size / 2; /* ASCII */
- cmdline = 0;
- s2 = (u16 *)options;
-
- if (s2) {
- while (*s2 && *s2 != '\n' && options_size < load_options_size) {
- s2++;
- options_size++;
- }
-
- if (options_size) {
- if (options_size > hdr->cmdline_size)
- options_size = hdr->cmdline_size;
-
- options_size++; /* NUL termination */
-
- status = low_alloc(options_size, 1, &cmdline);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for cmdline\n");
- goto fail;
- }
-
- s1 = (u8 *)(unsigned long)cmdline;
- s2 = (u16 *)options;
-
- for (i = 0; i < options_size - 1; i++)
- *s1++ = *s2++;
-
- *s1 = '\0';
- }
- }
-
- hdr->cmd_line_ptr = cmdline;
+ cmdline_ptr = efi_convert_cmdline_to_ascii(sys_table, image,
+ &options_size);
+ if (!cmdline_ptr)
+ goto fail;
+ hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
hdr->ramdisk_image = 0;
hdr->ramdisk_size = 0;
@@ -969,96 +502,64 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
memset(sdt, 0, sizeof(*sdt));
- status = handle_ramdisks(image, hdr);
+ status = handle_cmdline_files(sys_table, image,
+ (char *)(unsigned long)hdr->cmd_line_ptr,
+ "initrd=", hdr->initrd_addr_max,
+ &ramdisk_addr, &ramdisk_size);
if (status != EFI_SUCCESS)
goto fail2;
+ hdr->ramdisk_image = ramdisk_addr;
+ hdr->ramdisk_size = ramdisk_size;
return boot_params;
fail2:
- if (options_size)
- low_free(options_size, hdr->cmd_line_ptr);
+ efi_free(sys_table, options_size, hdr->cmd_line_ptr);
fail:
- low_free(0x4000, (unsigned long)boot_params);
+ efi_free(sys_table, 0x4000, (unsigned long)boot_params);
return NULL;
}
-static efi_status_t exit_boot(struct boot_params *boot_params,
- void *handle)
+static void add_e820ext(struct boot_params *params,
+ struct setup_data *e820ext, u32 nr_entries)
{
- struct efi_info *efi = &boot_params->efi_info;
- struct e820entry *e820_map = &boot_params->e820_map[0];
- struct e820entry *prev = NULL;
- unsigned long size, key, desc_size, _size;
- efi_memory_desc_t *mem_map;
+ struct setup_data *data;
efi_status_t status;
- __u32 desc_version;
- bool called_exit = false;
- u8 nr_entries;
- int i;
-
- size = sizeof(*mem_map) * 32;
-
-again:
- size += sizeof(*mem_map) * 2;
- _size = size;
- status = low_alloc(size, 1, (unsigned long *)&mem_map);
- if (status != EFI_SUCCESS)
- return status;
-
-get_map:
- status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
- mem_map, &key, &desc_size, &desc_version);
- if (status == EFI_BUFFER_TOO_SMALL) {
- low_free(_size, (unsigned long)mem_map);
- goto again;
- }
+ unsigned long size;
- if (status != EFI_SUCCESS)
- goto free_mem_map;
+ e820ext->type = SETUP_E820_EXT;
+ e820ext->len = nr_entries * sizeof(struct e820entry);
+ e820ext->next = 0;
- memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
- efi->efi_systab = (unsigned long)sys_table;
- efi->efi_memdesc_size = desc_size;
- efi->efi_memdesc_version = desc_version;
- efi->efi_memmap = (unsigned long)mem_map;
- efi->efi_memmap_size = size;
-
-#ifdef CONFIG_X86_64
- efi->efi_systab_hi = (unsigned long)sys_table >> 32;
- efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
-#endif
+ data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
- /* Might as well exit boot services now */
- status = efi_call_phys2(sys_table->boottime->exit_boot_services,
- handle, key);
- if (status != EFI_SUCCESS) {
- /*
- * ExitBootServices() will fail if any of the event
- * handlers change the memory map. In which case, we
- * must be prepared to retry, but only once so that
- * we're guaranteed to exit on repeated failures instead
- * of spinning forever.
- */
- if (called_exit)
- goto free_mem_map;
+ while (data && data->next)
+ data = (struct setup_data *)(unsigned long)data->next;
- called_exit = true;
- goto get_map;
- }
+ if (data)
+ data->next = (unsigned long)e820ext;
+ else
+ params->hdr.setup_data = (unsigned long)e820ext;
+}
- /* Historic? */
- boot_params->alt_mem_k = 32 * 1024;
+static efi_status_t setup_e820(struct boot_params *params,
+ struct setup_data *e820ext, u32 e820ext_size)
+{
+ struct e820entry *e820_map = &params->e820_map[0];
+ struct efi_info *efi = &params->efi_info;
+ struct e820entry *prev = NULL;
+ u32 nr_entries;
+ u32 nr_desc;
+ int i;
- /*
- * Convert the EFI memory map to E820.
- */
nr_entries = 0;
- for (i = 0; i < size / desc_size; i++) {
+ nr_desc = efi->efi_memmap_size / efi->efi_memdesc_size;
+
+ for (i = 0; i < nr_desc; i++) {
efi_memory_desc_t *d;
unsigned int e820_type = 0;
- unsigned long m = (unsigned long)mem_map;
+ unsigned long m = efi->efi_memmap;
- d = (efi_memory_desc_t *)(m + (i * desc_size));
+ d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
switch (d->type) {
case EFI_RESERVED_TYPE:
case EFI_RUNTIME_SERVICES_CODE:
@@ -1095,61 +596,151 @@ get_map:
/* Merge adjacent mappings */
if (prev && prev->type == e820_type &&
- (prev->addr + prev->size) == d->phys_addr)
+ (prev->addr + prev->size) == d->phys_addr) {
prev->size += d->num_pages << 12;
- else {
- e820_map->addr = d->phys_addr;
- e820_map->size = d->num_pages << 12;
- e820_map->type = e820_type;
- prev = e820_map++;
- nr_entries++;
+ continue;
+ }
+
+ if (nr_entries == ARRAY_SIZE(params->e820_map)) {
+ u32 need = (nr_desc - i) * sizeof(struct e820entry) +
+ sizeof(struct setup_data);
+
+ if (!e820ext || e820ext_size < need)
+ return EFI_BUFFER_TOO_SMALL;
+
+ /* boot_params map full, switch to e820 extended */
+ e820_map = (struct e820entry *)e820ext->data;
}
+
+ e820_map->addr = d->phys_addr;
+ e820_map->size = d->num_pages << PAGE_SHIFT;
+ e820_map->type = e820_type;
+ prev = e820_map++;
+ nr_entries++;
}
- boot_params->e820_entries = nr_entries;
+ if (nr_entries > ARRAY_SIZE(params->e820_map)) {
+ u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_map);
+
+ add_e820ext(params, e820ext, nr_e820ext);
+ nr_entries -= nr_e820ext;
+ }
+
+ params->e820_entries = (u8)nr_entries;
return EFI_SUCCESS;
+}
+
+static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
+ u32 *e820ext_size)
+{
+ efi_status_t status;
+ unsigned long size;
+
+ size = sizeof(struct setup_data) +
+ sizeof(struct e820entry) * nr_desc;
+
+ if (*e820ext) {
+ efi_call_phys1(sys_table->boottime->free_pool, *e820ext);
+ *e820ext = NULL;
+ *e820ext_size = 0;
+ }
+
+ status = efi_call_phys3(sys_table->boottime->allocate_pool,
+ EFI_LOADER_DATA, size, e820ext);
+
+ if (status == EFI_SUCCESS)
+ *e820ext_size = size;
-free_mem_map:
- low_free(_size, (unsigned long)mem_map);
return status;
}
-static efi_status_t relocate_kernel(struct setup_header *hdr)
+static efi_status_t exit_boot(struct boot_params *boot_params,
+ void *handle)
{
- unsigned long start, nr_pages;
+ struct efi_info *efi = &boot_params->efi_info;
+ unsigned long map_sz, key, desc_size;
+ efi_memory_desc_t *mem_map;
+ struct setup_data *e820ext;
+ __u32 e820ext_size;
+ __u32 nr_desc, prev_nr_desc;
efi_status_t status;
+ __u32 desc_version;
+ bool called_exit = false;
+ u8 nr_entries;
+ int i;
- /*
- * The EFI firmware loader could have placed the kernel image
- * anywhere in memory, but the kernel has various restrictions
- * on the max physical address it can run at. Attempt to move
- * the kernel to boot_params.pref_address, or as low as
- * possible.
- */
- start = hdr->pref_address;
- nr_pages = round_up(hdr->init_size, EFI_PAGE_SIZE) / EFI_PAGE_SIZE;
+ nr_desc = 0;
+ e820ext = NULL;
+ e820ext_size = 0;
- status = efi_call_phys4(sys_table->boottime->allocate_pages,
- EFI_ALLOCATE_ADDRESS, EFI_LOADER_DATA,
- nr_pages, &start);
- if (status != EFI_SUCCESS) {
- status = low_alloc(hdr->init_size, hdr->kernel_alignment,
- &start);
+get_map:
+ status = efi_get_memory_map(sys_table, &mem_map, &map_sz, &desc_size,
+ &desc_version, &key);
+
+ if (status != EFI_SUCCESS)
+ return status;
+
+ prev_nr_desc = nr_desc;
+ nr_desc = map_sz / desc_size;
+ if (nr_desc > prev_nr_desc &&
+ nr_desc > ARRAY_SIZE(boot_params->e820_map)) {
+ u32 nr_e820ext = nr_desc - ARRAY_SIZE(boot_params->e820_map);
+
+ status = alloc_e820ext(nr_e820ext, &e820ext, &e820ext_size);
if (status != EFI_SUCCESS)
- efi_printk("Failed to alloc mem for kernel\n");
+ goto free_mem_map;
+
+ efi_call_phys1(sys_table->boottime->free_pool, mem_map);
+ goto get_map; /* Allocated memory, get map again */
}
- if (status == EFI_SUCCESS)
- memcpy((void *)start, (void *)(unsigned long)hdr->code32_start,
- hdr->init_size);
+ memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
+ efi->efi_systab = (unsigned long)sys_table;
+ efi->efi_memdesc_size = desc_size;
+ efi->efi_memdesc_version = desc_version;
+ efi->efi_memmap = (unsigned long)mem_map;
+ efi->efi_memmap_size = map_sz;
+
+#ifdef CONFIG_X86_64
+ efi->efi_systab_hi = (unsigned long)sys_table >> 32;
+ efi->efi_memmap_hi = (unsigned long)mem_map >> 32;
+#endif
- hdr->pref_address = hdr->code32_start;
- hdr->code32_start = (__u32)start;
+ /* Might as well exit boot services now */
+ status = efi_call_phys2(sys_table->boottime->exit_boot_services,
+ handle, key);
+ if (status != EFI_SUCCESS) {
+ /*
+ * ExitBootServices() will fail if any of the event
+ * handlers change the memory map. In which case, we
+ * must be prepared to retry, but only once so that
+ * we're guaranteed to exit on repeated failures instead
+ * of spinning forever.
+ */
+ if (called_exit)
+ goto free_mem_map;
+ called_exit = true;
+ efi_call_phys1(sys_table->boottime->free_pool, mem_map);
+ goto get_map;
+ }
+
+ /* Historic? */
+ boot_params->alt_mem_k = 32 * 1024;
+
+ status = setup_e820(boot_params, e820ext, e820ext_size);
+ if (status != EFI_SUCCESS)
+ return status;
+
+ return EFI_SUCCESS;
+
+free_mem_map:
+ efi_call_phys1(sys_table->boottime->free_pool, mem_map);
return status;
}
+
/*
* On success we return a pointer to a boot_params structure, and NULL
* on failure.
@@ -1157,7 +748,7 @@ static efi_status_t relocate_kernel(struct setup_header *hdr)
struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
struct boot_params *boot_params)
{
- struct desc_ptr *gdt, *idt;
+ struct desc_ptr *gdt;
efi_loaded_image_t *image;
struct setup_header *hdr = &boot_params->hdr;
efi_status_t status;
@@ -1177,37 +768,33 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
EFI_LOADER_DATA, sizeof(*gdt),
(void **)&gdt);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for gdt structure\n");
+ efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
goto fail;
}
gdt->size = 0x800;
- status = low_alloc(gdt->size, 8, (unsigned long *)&gdt->address);
- if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for gdt\n");
- goto fail;
- }
-
- status = efi_call_phys3(sys_table->boottime->allocate_pool,
- EFI_LOADER_DATA, sizeof(*idt),
- (void **)&idt);
+ status = efi_low_alloc(sys_table, gdt->size, 8,
+ (unsigned long *)&gdt->address);
if (status != EFI_SUCCESS) {
- efi_printk("Failed to alloc mem for idt structure\n");
+ efi_printk(sys_table, "Failed to alloc mem for gdt\n");
goto fail;
}
- idt->size = 0;
- idt->address = 0;
-
/*
* If the kernel isn't already loaded at the preferred load
* address, relocate it.
*/
if (hdr->pref_address != hdr->code32_start) {
- status = relocate_kernel(hdr);
-
+ unsigned long bzimage_addr = hdr->code32_start;
+ status = efi_relocate_kernel(sys_table, &bzimage_addr,
+ hdr->init_size, hdr->init_size,
+ hdr->pref_address,
+ hdr->kernel_alignment);
if (status != EFI_SUCCESS)
goto fail;
+
+ hdr->pref_address = hdr->code32_start;
+ hdr->code32_start = bzimage_addr;
}
status = exit_boot(boot_params, handle);
@@ -1267,10 +854,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
desc->base2 = 0x00;
#endif /* CONFIG_X86_64 */
- asm volatile ("lidt %0" : : "m" (*idt));
- asm volatile ("lgdt %0" : : "m" (*gdt));
-
asm volatile("cli");
+ asm volatile ("lgdt %0" : : "m" (*gdt));
return boot_params;
fail:
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index e5b0a8f91c5..81b6b652b46 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -11,9 +11,6 @@
#define DESC_TYPE_CODE_DATA (1 << 0)
-#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)
@@ -62,10 +59,4 @@ struct efi_uga_draw_protocol {
void *blt;
};
-struct efi_simple_text_output_protocol {
- void *reset;
- void *output_string;
- void *test_string;
-};
-
#endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 1e3184f6072..5d6f6891b18 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -181,8 +181,9 @@ relocated:
/*
* Do the decompression, and jump to the new kernel..
*/
- leal z_extract_offset_negative(%ebx), %ebp
/* push arguments for decompress_kernel: */
+ pushl $z_output_len /* decompressed length */
+ leal z_extract_offset_negative(%ebx), %ebp
pushl %ebp /* output address */
pushl $z_input_len /* input_len */
leal input_data(%ebx), %eax
@@ -191,33 +192,7 @@ relocated:
pushl %eax /* heap area */
pushl %esi /* real mode pointer */
call decompress_kernel
- addl $20, %esp
-
-#if CONFIG_RELOCATABLE
-/*
- * Find the address of the relocations.
- */
- leal z_output_len(%ebp), %edi
-
-/*
- * Calculate the delta between where vmlinux was compiled to run
- * and where it was actually loaded.
- */
- movl %ebp, %ebx
- subl $LOAD_PHYSICAL_ADDR, %ebx
- jz 2f /* Nothing to be done if loaded at compiled addr. */
-/*
- * Process relocations.
- */
-
-1: subl $4, %edi
- movl (%edi), %ecx
- testl %ecx, %ecx
- jz 2f
- addl %ebx, -__PAGE_OFFSET(%ebx, %ecx)
- jmp 1b
-2:
-#endif
+ addl $24, %esp
/*
* Jump to the decompressed kernel.
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 06e71c2c16b..c337422b575 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -338,6 +338,7 @@ relocated:
leaq input_data(%rip), %rdx /* input_data */
movl $z_input_len, %ecx /* input_len */
movq %rbp, %r8 /* output target address */
+ movq $z_output_len, %r9 /* decompressed length */
call decompress_kernel
popq %rsi
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 0319c88290a..434f077d2c4 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -271,6 +271,79 @@ static void error(char *x)
asm("hlt");
}
+#if CONFIG_X86_NEED_RELOCS
+static void handle_relocations(void *output, unsigned long output_len)
+{
+ int *reloc;
+ unsigned long delta, map, ptr;
+ unsigned long min_addr = (unsigned long)output;
+ unsigned long max_addr = min_addr + output_len;
+
+ /*
+ * Calculate the delta between where vmlinux was linked to load
+ * and where it was actually loaded.
+ */
+ delta = min_addr - LOAD_PHYSICAL_ADDR;
+ if (!delta) {
+ debug_putstr("No relocation needed... ");
+ return;
+ }
+ debug_putstr("Performing relocations... ");
+
+ /*
+ * The kernel contains a table of relocation addresses. Those
+ * addresses have the final load address of the kernel in virtual
+ * memory. We are currently working in the self map. So we need to
+ * create an adjustment for kernel memory addresses to the self map.
+ * This will involve subtracting out the base address of the kernel.
+ */
+ map = delta - __START_KERNEL_map;
+
+ /*
+ * Process relocations: 32 bit relocations first then 64 bit after.
+ * Two sets of binary relocations are added to the end of the kernel
+ * before compression. Each relocation table entry is the kernel
+ * address of the location which needs to be updated stored as a
+ * 32-bit value which is sign extended to 64 bits.
+ *
+ * Format is:
+ *
+ * kernel bits...
+ * 0 - zero terminator for 64 bit relocations
+ * 64 bit relocation repeated
+ * 0 - zero terminator for 32 bit relocations
+ * 32 bit relocation repeated
+ *
+ * So we work backwards from the end of the decompressed image.
+ */
+ for (reloc = output + output_len - sizeof(*reloc); *reloc; reloc--) {
+ int extended = *reloc;
+ extended += map;
+
+ ptr = (unsigned long)extended;
+ if (ptr < min_addr || ptr > max_addr)
+ error("32-bit relocation outside of kernel!\n");
+
+ *(uint32_t *)ptr += delta;
+ }
+#ifdef CONFIG_X86_64
+ for (reloc--; *reloc; reloc--) {
+ long extended = *reloc;
+ extended += map;
+
+ ptr = (unsigned long)extended;
+ if (ptr < min_addr || ptr > max_addr)
+ error("64-bit relocation outside of kernel!\n");
+
+ *(uint64_t *)ptr += delta;
+ }
+#endif
+}
+#else
+static inline void handle_relocations(void *output, unsigned long output_len)
+{ }
+#endif
+
static void parse_elf(void *output)
{
#ifdef CONFIG_X86_64
@@ -325,7 +398,8 @@ static void parse_elf(void *output)
asmlinkage void decompress_kernel(void *rmode, memptr heap,
unsigned char *input_data,
unsigned long input_len,
- unsigned char *output)
+ unsigned char *output,
+ unsigned long output_len)
{
real_mode = rmode;
@@ -365,6 +439,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
debug_putstr("\nDecompressing Linux... ");
decompress(input_data, input_len, NULL, NULL, output, NULL, error);
parse_elf(output);
+ handle_relocations(output, output_len);
debug_putstr("done.\nBooting the kernel.\n");
return;
}
diff --git a/arch/x86/boot/compressed/mkpiggy.c b/arch/x86/boot/compressed/mkpiggy.c
index 958a641483d..b669ab65bf6 100644
--- a/arch/x86/boot/compressed/mkpiggy.c
+++ b/arch/x86/boot/compressed/mkpiggy.c
@@ -36,11 +36,12 @@ int main(int argc, char *argv[])
uint32_t olen;
long ilen;
unsigned long offs;
- FILE *f;
+ FILE *f = NULL;
+ int retval = 1;
if (argc < 2) {
fprintf(stderr, "Usage: %s compressed_file\n", argv[0]);
- return 1;
+ goto bail;
}
/* Get the information for the compressed kernel image first */
@@ -48,7 +49,7 @@ int main(int argc, char *argv[])
f = fopen(argv[1], "r");
if (!f) {
perror(argv[1]);
- return 1;
+ goto bail;
}
@@ -58,12 +59,11 @@ int main(int argc, char *argv[])
if (fread(&olen, sizeof(olen), 1, f) != 1) {
perror(argv[1]);
- return 1;
+ goto bail;
}
ilen = ftell(f);
olen = get_unaligned_le32(&olen);
- fclose(f);
/*
* Now we have the input (compressed) and output (uncompressed)
@@ -91,5 +91,9 @@ int main(int argc, char *argv[])
printf(".incbin \"%s\"\n", argv[1]);
printf("input_data_end:\n");
- return 0;
+ retval = 0;
+bail:
+ if (f)
+ fclose(f);
+ return retval;
}
diff --git a/arch/x86/boot/printf.c b/arch/x86/boot/printf.c
index cdac91ca55d..565083c16e5 100644
--- a/arch/x86/boot/printf.c
+++ b/arch/x86/boot/printf.c
@@ -55,7 +55,7 @@ static char *number(char *str, long num, int base, int size, int precision,
locase = (type & SMALL);
if (type & LEFT)
type &= ~ZEROPAD;
- if (base < 2 || base > 36)
+ if (base < 2 || base > 16)
return NULL;
c = (type & ZEROPAD) ? '0' : ' ';
sign = 0;
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index c941d6a8887..8e15b22391f 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -5,14 +5,15 @@
*/
/*
- * This file builds a disk-image from two different files:
+ * This file builds a disk-image from three different files:
*
* - setup: 8086 machine code, sets up system parm
* - system: 80386 code for actual system
+ * - zoffset.h: header with ZO_* defines
*
- * It does some checking that all files are of the correct type, and
- * just writes the result to stdout, removing headers and padding to
- * the right amount. It also writes some system data to stderr.
+ * It does some checking that all files are of the correct type, and writes
+ * the result to the specified destination, removing headers and padding to
+ * the right amount. It also writes some system data to stdout.
*/
/*
@@ -136,7 +137,7 @@ static void die(const char * str, ...)
static void usage(void)
{
- die("Usage: build setup system [zoffset.h] [> image]");
+ die("Usage: build setup system zoffset.h image");
}
#ifdef CONFIG_EFI_STUB
@@ -265,7 +266,7 @@ int main(int argc, char ** argv)
int c;
u32 sys_size;
struct stat sb;
- FILE *file;
+ FILE *file, *dest;
int fd;
void *kernel;
u32 crc = 0xffffffffUL;
@@ -280,10 +281,13 @@ int main(int argc, char ** argv)
startup_64 = 0x200;
#endif
- if (argc == 4)
- parse_zoffset(argv[3]);
- else if (argc != 3)
+ if (argc != 5)
usage();
+ parse_zoffset(argv[3]);
+
+ dest = fopen(argv[4], "w");
+ if (!dest)
+ die("Unable to write `%s': %m", argv[4]);
/* Copy the setup code */
file = fopen(argv[1], "r");
@@ -318,7 +322,7 @@ int main(int argc, char ** argv)
/* Set the default root device */
put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
- fprintf(stderr, "Setup is %d bytes (padded to %d bytes).\n", c, i);
+ printf("Setup is %d bytes (padded to %d bytes).\n", c, i);
/* Open and stat the kernel file */
fd = open(argv[2], O_RDONLY);
@@ -327,7 +331,7 @@ int main(int argc, char ** argv)
if (fstat(fd, &sb))
die("Unable to stat `%s': %m", argv[2]);
sz = sb.st_size;
- fprintf (stderr, "System is %d kB\n", (sz+1023)/1024);
+ printf("System is %d kB\n", (sz+1023)/1024);
kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
if (kernel == MAP_FAILED)
die("Unable to mmap '%s': %m", argv[2]);
@@ -348,27 +352,31 @@ int main(int argc, char ** argv)
#endif
crc = partial_crc32(buf, i, crc);
- if (fwrite(buf, 1, i, stdout) != i)
+ if (fwrite(buf, 1, i, dest) != i)
die("Writing setup failed");
/* Copy the kernel code */
crc = partial_crc32(kernel, sz, crc);
- if (fwrite(kernel, 1, sz, stdout) != sz)
+ if (fwrite(kernel, 1, sz, dest) != sz)
die("Writing kernel failed");
/* Add padding leaving 4 bytes for the checksum */
while (sz++ < (sys_size*16) - 4) {
crc = partial_crc32_one('\0', crc);
- if (fwrite("\0", 1, 1, stdout) != 1)
+ if (fwrite("\0", 1, 1, dest) != 1)
die("Writing padding failed");
}
/* Write the CRC */
- fprintf(stderr, "CRC %x\n", crc);
+ printf("CRC %x\n", crc);
put_unaligned_le32(crc, buf);
- if (fwrite(buf, 1, 4, stdout) != 4)
+ if (fwrite(buf, 1, 4, dest) != 4)
die("Writing CRC failed");
+ /* Catch any delayed write failures */
+ if (fclose(dest))
+ die("Writing image failed");
+
close(fd);
/* Everything is OK */
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 94447086e55..a7fef2621cc 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -142,6 +142,8 @@ CONFIG_MAC80211=y
CONFIG_MAC80211_LEDS=y
CONFIG_RFKILL=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
CONFIG_DEBUG_DEVRES=y
CONFIG_CONNECTOR=y
CONFIG_BLK_DEV_LOOP=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 671524d0f6c..c1119d4c128 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -141,6 +141,8 @@ CONFIG_MAC80211=y
CONFIG_MAC80211_LEDS=y
CONFIG_RFKILL=y
CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
CONFIG_DEBUG_DEVRES=y
CONFIG_CONNECTOR=y
CONFIG_BLK_DEV_LOOP=y
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 6c63c358a7e..7d6ba9db1be 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
obj-$(CONFIG_CRYPTO_CRC32_PCLMUL) += crc32-pclmul.o
obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF_PCLMUL) += crct10dif-pclmul.o
# These modules require assembler to support AVX.
ifeq ($(avx_supported),yes)
@@ -81,3 +82,4 @@ crc32c-intel-$(CONFIG_64BIT) += crc32c-pcl-intel-asm_64.o
crc32-pclmul-y := crc32-pclmul_asm.o crc32-pclmul_glue.o
sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
+crct10dif-pclmul-y := crct10dif-pcl-asm_64.o crct10dif-pclmul_glue.o
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index 5cb86ccd4ac..c171dcbf192 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -62,7 +62,7 @@ static void camellia_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
}
/* camellia sboxes */
-const u64 camellia_sp10011110[256] = {
+__visible const u64 camellia_sp10011110[256] = {
0x7000007070707000ULL, 0x8200008282828200ULL, 0x2c00002c2c2c2c00ULL,
0xec0000ecececec00ULL, 0xb30000b3b3b3b300ULL, 0x2700002727272700ULL,
0xc00000c0c0c0c000ULL, 0xe50000e5e5e5e500ULL, 0xe40000e4e4e4e400ULL,
@@ -151,7 +151,7 @@ const u64 camellia_sp10011110[256] = {
0x9e00009e9e9e9e00ULL,
};
-const u64 camellia_sp22000222[256] = {
+__visible const u64 camellia_sp22000222[256] = {
0xe0e0000000e0e0e0ULL, 0x0505000000050505ULL, 0x5858000000585858ULL,
0xd9d9000000d9d9d9ULL, 0x6767000000676767ULL, 0x4e4e0000004e4e4eULL,
0x8181000000818181ULL, 0xcbcb000000cbcbcbULL, 0xc9c9000000c9c9c9ULL,
@@ -240,7 +240,7 @@ const u64 camellia_sp22000222[256] = {
0x3d3d0000003d3d3dULL,
};
-const u64 camellia_sp03303033[256] = {
+__visible const u64 camellia_sp03303033[256] = {
0x0038380038003838ULL, 0x0041410041004141ULL, 0x0016160016001616ULL,
0x0076760076007676ULL, 0x00d9d900d900d9d9ULL, 0x0093930093009393ULL,
0x0060600060006060ULL, 0x00f2f200f200f2f2ULL, 0x0072720072007272ULL,
@@ -329,7 +329,7 @@ const u64 camellia_sp03303033[256] = {
0x004f4f004f004f4fULL,
};
-const u64 camellia_sp00444404[256] = {
+__visible const u64 camellia_sp00444404[256] = {
0x0000707070700070ULL, 0x00002c2c2c2c002cULL, 0x0000b3b3b3b300b3ULL,
0x0000c0c0c0c000c0ULL, 0x0000e4e4e4e400e4ULL, 0x0000575757570057ULL,
0x0000eaeaeaea00eaULL, 0x0000aeaeaeae00aeULL, 0x0000232323230023ULL,
@@ -418,7 +418,7 @@ const u64 camellia_sp00444404[256] = {
0x00009e9e9e9e009eULL,
};
-const u64 camellia_sp02220222[256] = {
+__visible const u64 camellia_sp02220222[256] = {
0x00e0e0e000e0e0e0ULL, 0x0005050500050505ULL, 0x0058585800585858ULL,
0x00d9d9d900d9d9d9ULL, 0x0067676700676767ULL, 0x004e4e4e004e4e4eULL,
0x0081818100818181ULL, 0x00cbcbcb00cbcbcbULL, 0x00c9c9c900c9c9c9ULL,
@@ -507,7 +507,7 @@ const u64 camellia_sp02220222[256] = {
0x003d3d3d003d3d3dULL,
};
-const u64 camellia_sp30333033[256] = {
+__visible const u64 camellia_sp30333033[256] = {
0x3800383838003838ULL, 0x4100414141004141ULL, 0x1600161616001616ULL,
0x7600767676007676ULL, 0xd900d9d9d900d9d9ULL, 0x9300939393009393ULL,
0x6000606060006060ULL, 0xf200f2f2f200f2f2ULL, 0x7200727272007272ULL,
@@ -596,7 +596,7 @@ const u64 camellia_sp30333033[256] = {
0x4f004f4f4f004f4fULL,
};
-const u64 camellia_sp44044404[256] = {
+__visible const u64 camellia_sp44044404[256] = {
0x7070007070700070ULL, 0x2c2c002c2c2c002cULL, 0xb3b300b3b3b300b3ULL,
0xc0c000c0c0c000c0ULL, 0xe4e400e4e4e400e4ULL, 0x5757005757570057ULL,
0xeaea00eaeaea00eaULL, 0xaeae00aeaeae00aeULL, 0x2323002323230023ULL,
@@ -685,7 +685,7 @@ const u64 camellia_sp44044404[256] = {
0x9e9e009e9e9e009eULL,
};
-const u64 camellia_sp11101110[256] = {
+__visible const u64 camellia_sp11101110[256] = {
0x7070700070707000ULL, 0x8282820082828200ULL, 0x2c2c2c002c2c2c00ULL,
0xececec00ececec00ULL, 0xb3b3b300b3b3b300ULL, 0x2727270027272700ULL,
0xc0c0c000c0c0c000ULL, 0xe5e5e500e5e5e500ULL, 0xe4e4e400e4e4e400ULL,
@@ -828,8 +828,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
subRL[1] ^= (subRL[1] & ~subRL[9]) << 32;
/* modified for FLinv(kl2) */
- dw = (subRL[1] & subRL[9]) >> 32,
- subRL[1] ^= rol32(dw, 1);
+ dw = (subRL[1] & subRL[9]) >> 32;
+ subRL[1] ^= rol32(dw, 1);
/* round 8 */
subRL[11] ^= subRL[1];
@@ -840,8 +840,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
subRL[1] ^= (subRL[1] & ~subRL[17]) << 32;
/* modified for FLinv(kl4) */
- dw = (subRL[1] & subRL[17]) >> 32,
- subRL[1] ^= rol32(dw, 1);
+ dw = (subRL[1] & subRL[17]) >> 32;
+ subRL[1] ^= rol32(dw, 1);
/* round 14 */
subRL[19] ^= subRL[1];
@@ -859,8 +859,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
} else {
subRL[1] ^= (subRL[1] & ~subRL[25]) << 32;
/* modified for FLinv(kl6) */
- dw = (subRL[1] & subRL[25]) >> 32,
- subRL[1] ^= rol32(dw, 1);
+ dw = (subRL[1] & subRL[25]) >> 32;
+ subRL[1] ^= rol32(dw, 1);
/* round 20 */
subRL[27] ^= subRL[1];
@@ -882,8 +882,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
kw4 ^= (kw4 & ~subRL[24]) << 32;
/* modified for FL(kl5) */
- dw = (kw4 & subRL[24]) >> 32,
- kw4 ^= rol32(dw, 1);
+ dw = (kw4 & subRL[24]) >> 32;
+ kw4 ^= rol32(dw, 1);
}
/* round 17 */
@@ -895,8 +895,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
kw4 ^= (kw4 & ~subRL[16]) << 32;
/* modified for FL(kl3) */
- dw = (kw4 & subRL[16]) >> 32,
- kw4 ^= rol32(dw, 1);
+ dw = (kw4 & subRL[16]) >> 32;
+ kw4 ^= rol32(dw, 1);
/* round 11 */
subRL[14] ^= kw4;
@@ -907,8 +907,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
kw4 ^= (kw4 & ~subRL[8]) << 32;
/* modified for FL(kl1) */
- dw = (kw4 & subRL[8]) >> 32,
- kw4 ^= rol32(dw, 1);
+ dw = (kw4 & subRL[8]) >> 32;
+ kw4 ^= rol32(dw, 1);
/* round 5 */
subRL[6] ^= kw4;
@@ -928,8 +928,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(6, subRL[5] ^ subRL[7]); /* round 5 */
tl = (subRL[10] >> 32) ^ (subRL[10] & ~subRL[8]);
- dw = tl & (subRL[8] >> 32), /* FL(kl1) */
- tr = subRL[10] ^ rol32(dw, 1);
+ dw = tl & (subRL[8] >> 32); /* FL(kl1) */
+ tr = subRL[10] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(7, subRL[6] ^ tt); /* round 6 */
@@ -937,8 +937,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(9, subRL[9]); /* FLinv(kl2) */
tl = (subRL[7] >> 32) ^ (subRL[7] & ~subRL[9]);
- dw = tl & (subRL[9] >> 32), /* FLinv(kl2) */
- tr = subRL[7] ^ rol32(dw, 1);
+ dw = tl & (subRL[9] >> 32); /* FLinv(kl2) */
+ tr = subRL[7] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(10, subRL[11] ^ tt); /* round 7 */
@@ -948,8 +948,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(14, subRL[13] ^ subRL[15]); /* round 11 */
tl = (subRL[18] >> 32) ^ (subRL[18] & ~subRL[16]);
- dw = tl & (subRL[16] >> 32), /* FL(kl3) */
- tr = subRL[18] ^ rol32(dw, 1);
+ dw = tl & (subRL[16] >> 32); /* FL(kl3) */
+ tr = subRL[18] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(15, subRL[14] ^ tt); /* round 12 */
@@ -957,8 +957,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(17, subRL[17]); /* FLinv(kl4) */
tl = (subRL[15] >> 32) ^ (subRL[15] & ~subRL[17]);
- dw = tl & (subRL[17] >> 32), /* FLinv(kl4) */
- tr = subRL[15] ^ rol32(dw, 1);
+ dw = tl & (subRL[17] >> 32); /* FLinv(kl4) */
+ tr = subRL[15] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(18, subRL[19] ^ tt); /* round 13 */
@@ -972,8 +972,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(24, subRL[24] ^ subRL[23]); /* kw3 */
} else {
tl = (subRL[26] >> 32) ^ (subRL[26] & ~subRL[24]);
- dw = tl & (subRL[24] >> 32), /* FL(kl5) */
- tr = subRL[26] ^ rol32(dw, 1);
+ dw = tl & (subRL[24] >> 32); /* FL(kl5) */
+ tr = subRL[26] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(23, subRL[22] ^ tt); /* round 18 */
@@ -981,8 +981,8 @@ static void camellia_setup_tail(u64 *subkey, u64 *subRL, int max)
SET_SUBKEY_LR(25, subRL[25]); /* FLinv(kl6) */
tl = (subRL[23] >> 32) ^ (subRL[23] & ~subRL[25]);
- dw = tl & (subRL[25] >> 32), /* FLinv(kl6) */
- tr = subRL[23] ^ rol32(dw, 1);
+ dw = tl & (subRL[25] >> 32); /* FLinv(kl6) */
+ tr = subRL[23] ^ rol32(dw, 1);
tt = (tr | ((u64)tl << 32));
SET_SUBKEY_LR(26, subRL[27] ^ tt); /* round 19 */
diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S
new file mode 100644
index 00000000000..35e97569d05
--- /dev/null
+++ b/arch/x86/crypto/crct10dif-pcl-asm_64.S
@@ -0,0 +1,643 @@
+########################################################################
+# Implement fast CRC-T10DIF computation with SSE and PCLMULQDQ instructions
+#
+# Copyright (c) 2013, Intel Corporation
+#
+# Authors:
+# Erdinc Ozturk <erdinc.ozturk@intel.com>
+# Vinodh Gopal <vinodh.gopal@intel.com>
+# James Guilford <james.guilford@intel.com>
+# Tim Chen <tim.c.chen@linux.intel.com>
+#
+# This software is available to you under a choice of one of two
+# licenses. You may choose to be licensed under the terms of the GNU
+# General Public License (GPL) Version 2, available from the file
+# COPYING in the main directory of this source tree, or the
+# OpenIB.org BSD license below:
+#
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are
+# met:
+#
+# * Redistributions of source code must retain the above copyright
+# notice, this list of conditions and the following disclaimer.
+#
+# * Redistributions in binary form must reproduce the above copyright
+# notice, this list of conditions and the following disclaimer in the
+# documentation and/or other materials provided with the
+# distribution.
+#
+# * Neither the name of the Intel Corporation nor the names of its
+# contributors may be used to endorse or promote products derived from
+# this software without specific prior written permission.
+#
+#
+# THIS SOFTWARE IS PROVIDED BY INTEL CORPORATION ""AS IS"" AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL INTEL CORPORATION OR
+# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
+# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
+# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
+# PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+# LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+# NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+# SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+########################################################################
+# Function API:
+# UINT16 crc_t10dif_pcl(
+# UINT16 init_crc, //initial CRC value, 16 bits
+# const unsigned char *buf, //buffer pointer to calculate CRC on
+# UINT64 len //buffer length in bytes (64-bit data)
+# );
+#
+# Reference paper titled "Fast CRC Computation for Generic
+# Polynomials Using PCLMULQDQ Instruction"
+# URL: http://www.intel.com/content/dam/www/public/us/en/documents
+# /white-papers/fast-crc-computation-generic-polynomials-pclmulqdq-paper.pdf
+#
+#
+
+#include <linux/linkage.h>
+
+.text
+
+#define arg1 %rdi
+#define arg2 %rsi
+#define arg3 %rdx
+
+#define arg1_low32 %edi
+
+ENTRY(crc_t10dif_pcl)
+.align 16
+
+ # adjust the 16-bit initial_crc value, scale it to 32 bits
+ shl $16, arg1_low32
+
+ # Allocate Stack Space
+ mov %rsp, %rcx
+ sub $16*2, %rsp
+ # align stack to 16 byte boundary
+ and $~(0x10 - 1), %rsp
+
+ # check if smaller than 256
+ cmp $256, arg3
+
+ # for sizes less than 128, we can't fold 64B at a time...
+ jl _less_than_128
+
+
+ # load the initial crc value
+ movd arg1_low32, %xmm10 # initial crc
+
+ # crc value does not need to be byte-reflected, but it needs
+ # to be moved to the high part of the register.
+ # because data will be byte-reflected and will align with
+ # initial crc at correct place.
+ pslldq $12, %xmm10
+
+ movdqa SHUF_MASK(%rip), %xmm11
+ # receive the initial 64B data, xor the initial crc value
+ movdqu 16*0(arg2), %xmm0
+ movdqu 16*1(arg2), %xmm1
+ movdqu 16*2(arg2), %xmm2
+ movdqu 16*3(arg2), %xmm3
+ movdqu 16*4(arg2), %xmm4
+ movdqu 16*5(arg2), %xmm5
+ movdqu 16*6(arg2), %xmm6
+ movdqu 16*7(arg2), %xmm7
+
+ pshufb %xmm11, %xmm0
+ # XOR the initial_crc value
+ pxor %xmm10, %xmm0
+ pshufb %xmm11, %xmm1
+ pshufb %xmm11, %xmm2
+ pshufb %xmm11, %xmm3
+ pshufb %xmm11, %xmm4
+ pshufb %xmm11, %xmm5
+ pshufb %xmm11, %xmm6
+ pshufb %xmm11, %xmm7
+
+ movdqa rk3(%rip), %xmm10 #xmm10 has rk3 and rk4
+ #imm value of pclmulqdq instruction
+ #will determine which constant to use
+
+ #################################################################
+ # we subtract 256 instead of 128 to save one instruction from the loop
+ sub $256, arg3
+
+ # at this section of the code, there is 64*x+y (0<=y<64) bytes of
+ # buffer. The _fold_64_B_loop will fold 64B at a time
+ # until we have 64+y Bytes of buffer
+
+
+ # fold 64B at a time. This section of the code folds 4 xmm
+ # registers in parallel
+_fold_64_B_loop:
+
+ # update the buffer pointer
+ add $128, arg2 # buf += 64#
+
+ movdqu 16*0(arg2), %xmm9
+ movdqu 16*1(arg2), %xmm12
+ pshufb %xmm11, %xmm9
+ pshufb %xmm11, %xmm12
+ movdqa %xmm0, %xmm8
+ movdqa %xmm1, %xmm13
+ pclmulqdq $0x0 , %xmm10, %xmm0
+ pclmulqdq $0x11, %xmm10, %xmm8
+ pclmulqdq $0x0 , %xmm10, %xmm1
+ pclmulqdq $0x11, %xmm10, %xmm13
+ pxor %xmm9 , %xmm0
+ xorps %xmm8 , %xmm0
+ pxor %xmm12, %xmm1
+ xorps %xmm13, %xmm1
+
+ movdqu 16*2(arg2), %xmm9
+ movdqu 16*3(arg2), %xmm12
+ pshufb %xmm11, %xmm9
+ pshufb %xmm11, %xmm12
+ movdqa %xmm2, %xmm8
+ movdqa %xmm3, %xmm13
+ pclmulqdq $0x0, %xmm10, %xmm2
+ pclmulqdq $0x11, %xmm10, %xmm8
+ pclmulqdq $0x0, %xmm10, %xmm3
+ pclmulqdq $0x11, %xmm10, %xmm13
+ pxor %xmm9 , %xmm2
+ xorps %xmm8 , %xmm2
+ pxor %xmm12, %xmm3
+ xorps %xmm13, %xmm3
+
+ movdqu 16*4(arg2), %xmm9
+ movdqu 16*5(arg2), %xmm12
+ pshufb %xmm11, %xmm9
+ pshufb %xmm11, %xmm12
+ movdqa %xmm4, %xmm8
+ movdqa %xmm5, %xmm13
+ pclmulqdq $0x0, %xmm10, %xmm4
+ pclmulqdq $0x11, %xmm10, %xmm8
+ pclmulqdq $0x0, %xmm10, %xmm5
+ pclmulqdq $0x11, %xmm10, %xmm13
+ pxor %xmm9 , %xmm4
+ xorps %xmm8 , %xmm4
+ pxor %xmm12, %xmm5
+ xorps %xmm13, %xmm5
+
+ movdqu 16*6(arg2), %xmm9
+ movdqu 16*7(arg2), %xmm12
+ pshufb %xmm11, %xmm9
+ pshufb %xmm11, %xmm12
+ movdqa %xmm6 , %xmm8
+ movdqa %xmm7 , %xmm13
+ pclmulqdq $0x0 , %xmm10, %xmm6
+ pclmulqdq $0x11, %xmm10, %xmm8
+ pclmulqdq $0x0 , %xmm10, %xmm7
+ pclmulqdq $0x11, %xmm10, %xmm13
+ pxor %xmm9 , %xmm6
+ xorps %xmm8 , %xmm6
+ pxor %xmm12, %xmm7
+ xorps %xmm13, %xmm7
+
+ sub $128, arg3
+
+ # check if there is another 64B in the buffer to be able to fold
+ jge _fold_64_B_loop
+ ##################################################################
+
+
+ add $128, arg2
+ # at this point, the buffer pointer is pointing at the last y Bytes
+ # of the buffer the 64B of folded data is in 4 of the xmm
+ # registers: xmm0, xmm1, xmm2, xmm3
+
+
+ # fold the 8 xmm registers to 1 xmm register with different constants
+
+ movdqa rk9(%rip), %xmm10
+ movdqa %xmm0, %xmm8
+ pclmulqdq $0x11, %xmm10, %xmm0
+ pclmulqdq $0x0 , %xmm10, %xmm8
+ pxor %xmm8, %xmm7
+ xorps %xmm0, %xmm7
+
+ movdqa rk11(%rip), %xmm10
+ movdqa %xmm1, %xmm8
+ pclmulqdq $0x11, %xmm10, %xmm1
+ pclmulqdq $0x0 , %xmm10, %xmm8
+ pxor %xmm8, %xmm7
+ xorps %xmm1, %xmm7
+
+ movdqa rk13(%rip), %xmm10
+ movdqa %xmm2, %xmm8
+ pclmulqdq $0x11, %xmm10, %xmm2
+ pclmulqdq $0x0 , %xmm10, %xmm8
+ pxor %xmm8, %xmm7
+ pxor %xmm2, %xmm7
+
+ movdqa rk15(%rip), %xmm10
+ movdqa %xmm3, %xmm8
+ pclmulqdq $0x11, %xmm10, %xmm3
+ pclmulqdq $0x0 , %xmm10, %xmm8
+ pxor %xmm8, %xmm7
+ xorps %xmm3, %xmm7
+
+ movdqa rk17(%rip), %xmm10
+ movdqa %xmm4, %xmm8
+ pclmulqdq $0x11, %xmm10, %xmm4
+ pclmulqdq $0x0 , %xmm10, %xmm8
+ pxor %xmm8, %xmm7
+ pxor %xmm4, %xmm7
+
+ movdqa rk19(%rip), %xmm10
+ movdqa %xmm5, %xmm8
+ pclmulqdq $0x11, %xmm10, %xmm5
+ pclmulqdq $0x0 , %xmm10, %xmm8
+ pxor %xmm8, %xmm7
+ xorps %xmm5, %xmm7
+
+ movdqa rk1(%rip), %xmm10 #xmm10 has rk1 and rk2
+ #imm value of pclmulqdq instruction
+ #will determine which constant to use
+ movdqa %xmm6, %xmm8
+ pclmulqdq $0x11, %xmm10, %xmm6
+ pclmulqdq $0x0 , %xmm10, %xmm8
+ pxor %xmm8, %xmm7
+ pxor %xmm6, %xmm7
+
+
+ # instead of 64, we add 48 to the loop counter to save 1 instruction
+ # from the loop instead of a cmp instruction, we use the negative
+ # flag with the jl instruction
+ add $128-16, arg3
+ jl _final_reduction_for_128
+
+ # now we have 16+y bytes left to reduce. 16 Bytes is in register xmm7
+ # and the rest is in memory. We can fold 16 bytes at a time if y>=16
+ # continue folding 16B at a time
+
+_16B_reduction_loop:
+ movdqa %xmm7, %xmm8
+ pclmulqdq $0x11, %xmm10, %xmm7
+ pclmulqdq $0x0 , %xmm10, %xmm8
+ pxor %xmm8, %xmm7
+ movdqu (arg2), %xmm0
+ pshufb %xmm11, %xmm0
+ pxor %xmm0 , %xmm7
+ add $16, arg2
+ sub $16, arg3
+ # instead of a cmp instruction, we utilize the flags with the
+ # jge instruction equivalent of: cmp arg3, 16-16
+ # check if there is any more 16B in the buffer to be able to fold
+ jge _16B_reduction_loop
+
+ #now we have 16+z bytes left to reduce, where 0<= z < 16.
+ #first, we reduce the data in the xmm7 register
+
+
+_final_reduction_for_128:
+ # check if any more data to fold. If not, compute the CRC of
+ # the final 128 bits
+ add $16, arg3
+ je _128_done
+
+ # here we are getting data that is less than 16 bytes.
+ # since we know that there was data before the pointer, we can
+ # offset the input pointer before the actual point, to receive
+ # exactly 16 bytes. after that the registers need to be adjusted.
+_get_last_two_xmms:
+ movdqa %xmm7, %xmm2
+
+ movdqu -16(arg2, arg3), %xmm1
+ pshufb %xmm11, %xmm1
+
+ # get rid of the extra data that was loaded before
+ # load the shift constant
+ lea pshufb_shf_table+16(%rip), %rax
+ sub arg3, %rax
+ movdqu (%rax), %xmm0
+
+ # shift xmm2 to the left by arg3 bytes
+ pshufb %xmm0, %xmm2
+
+ # shift xmm7 to the right by 16-arg3 bytes
+ pxor mask1(%rip), %xmm0
+ pshufb %xmm0, %xmm7
+ pblendvb %xmm2, %xmm1 #xmm0 is implicit
+
+ # fold 16 Bytes
+ movdqa %xmm1, %xmm2
+ movdqa %xmm7, %xmm8
+ pclmulqdq $0x11, %xmm10, %xmm7
+ pclmulqdq $0x0 , %xmm10, %xmm8
+ pxor %xmm8, %xmm7
+ pxor %xmm2, %xmm7
+
+_128_done:
+ # compute crc of a 128-bit value
+ movdqa rk5(%rip), %xmm10 # rk5 and rk6 in xmm10
+ movdqa %xmm7, %xmm0
+
+ #64b fold
+ pclmulqdq $0x1, %xmm10, %xmm7
+ pslldq $8 , %xmm0
+ pxor %xmm0, %xmm7
+
+ #32b fold
+ movdqa %xmm7, %xmm0
+
+ pand mask2(%rip), %xmm0
+
+ psrldq $12, %xmm7
+ pclmulqdq $0x10, %xmm10, %xmm7
+ pxor %xmm0, %xmm7
+
+ #barrett reduction
+_barrett:
+ movdqa rk7(%rip), %xmm10 # rk7 and rk8 in xmm10
+ movdqa %xmm7, %xmm0
+ pclmulqdq $0x01, %xmm10, %xmm7
+ pslldq $4, %xmm7
+ pclmulqdq $0x11, %xmm10, %xmm7
+
+ pslldq $4, %xmm7
+ pxor %xmm0, %xmm7
+ pextrd $1, %xmm7, %eax
+
+_cleanup:
+ # scale the result back to 16 bits
+ shr $16, %eax
+ mov %rcx, %rsp
+ ret
+
+########################################################################
+
+.align 16
+_less_than_128:
+
+ # check if there is enough buffer to be able to fold 16B at a time
+ cmp $32, arg3
+ jl _less_than_32
+ movdqa SHUF_MASK(%rip), %xmm11
+
+ # now if there is, load the constants
+ movdqa rk1(%rip), %xmm10 # rk1 and rk2 in xmm10
+
+ movd arg1_low32, %xmm0 # get the initial crc value
+ pslldq $12, %xmm0 # align it to its correct place
+ movdqu (arg2), %xmm7 # load the plaintext
+ pshufb %xmm11, %xmm7 # byte-reflect the plaintext
+ pxor %xmm0, %xmm7
+
+
+ # update the buffer pointer
+ add $16, arg2
+
+ # update the counter. subtract 32 instead of 16 to save one
+ # instruction from the loop
+ sub $32, arg3
+
+ jmp _16B_reduction_loop
+
+
+.align 16
+_less_than_32:
+ # mov initial crc to the return value. this is necessary for
+ # zero-length buffers.
+ mov arg1_low32, %eax
+ test arg3, arg3
+ je _cleanup
+
+ movdqa SHUF_MASK(%rip), %xmm11
+
+ movd arg1_low32, %xmm0 # get the initial crc value
+ pslldq $12, %xmm0 # align it to its correct place
+
+ cmp $16, arg3
+ je _exact_16_left
+ jl _less_than_16_left
+
+ movdqu (arg2), %xmm7 # load the plaintext
+ pshufb %xmm11, %xmm7 # byte-reflect the plaintext
+ pxor %xmm0 , %xmm7 # xor the initial crc value
+ add $16, arg2
+ sub $16, arg3
+ movdqa rk1(%rip), %xmm10 # rk1 and rk2 in xmm10
+ jmp _get_last_two_xmms
+
+
+.align 16
+_less_than_16_left:
+ # use stack space to load data less than 16 bytes, zero-out
+ # the 16B in memory first.
+
+ pxor %xmm1, %xmm1
+ mov %rsp, %r11
+ movdqa %xmm1, (%r11)
+
+ cmp $4, arg3
+ jl _only_less_than_4
+
+ # backup the counter value
+ mov arg3, %r9
+ cmp $8, arg3
+ jl _less_than_8_left
+
+ # load 8 Bytes
+ mov (arg2), %rax
+ mov %rax, (%r11)
+ add $8, %r11
+ sub $8, arg3
+ add $8, arg2
+_less_than_8_left:
+
+ cmp $4, arg3
+ jl _less_than_4_left
+
+ # load 4 Bytes
+ mov (arg2), %eax
+ mov %eax, (%r11)
+ add $4, %r11
+ sub $4, arg3
+ add $4, arg2
+_less_than_4_left:
+
+ cmp $2, arg3
+ jl _less_than_2_left
+
+ # load 2 Bytes
+ mov (arg2), %ax
+ mov %ax, (%r11)
+ add $2, %r11
+ sub $2, arg3
+ add $2, arg2
+_less_than_2_left:
+ cmp $1, arg3
+ jl _zero_left
+
+ # load 1 Byte
+ mov (arg2), %al
+ mov %al, (%r11)
+_zero_left:
+ movdqa (%rsp), %xmm7
+ pshufb %xmm11, %xmm7
+ pxor %xmm0 , %xmm7 # xor the initial crc value
+
+ # shl r9, 4
+ lea pshufb_shf_table+16(%rip), %rax
+ sub %r9, %rax
+ movdqu (%rax), %xmm0
+ pxor mask1(%rip), %xmm0
+
+ pshufb %xmm0, %xmm7
+ jmp _128_done
+
+.align 16
+_exact_16_left:
+ movdqu (arg2), %xmm7
+ pshufb %xmm11, %xmm7
+ pxor %xmm0 , %xmm7 # xor the initial crc value
+
+ jmp _128_done
+
+_only_less_than_4:
+ cmp $3, arg3
+ jl _only_less_than_3
+
+ # load 3 Bytes
+ mov (arg2), %al
+ mov %al, (%r11)
+
+ mov 1(arg2), %al
+ mov %al, 1(%r11)
+
+ mov 2(arg2), %al
+ mov %al, 2(%r11)
+
+ movdqa (%rsp), %xmm7
+ pshufb %xmm11, %xmm7
+ pxor %xmm0 , %xmm7 # xor the initial crc value
+
+ psrldq $5, %xmm7
+
+ jmp _barrett
+_only_less_than_3:
+ cmp $2, arg3
+ jl _only_less_than_2
+
+ # load 2 Bytes
+ mov (arg2), %al
+ mov %al, (%r11)
+
+ mov 1(arg2), %al
+ mov %al, 1(%r11)
+
+ movdqa (%rsp), %xmm7
+ pshufb %xmm11, %xmm7
+ pxor %xmm0 , %xmm7 # xor the initial crc value
+
+ psrldq $6, %xmm7
+
+ jmp _barrett
+_only_less_than_2:
+
+ # load 1 Byte
+ mov (arg2), %al
+ mov %al, (%r11)
+
+ movdqa (%rsp), %xmm7
+ pshufb %xmm11, %xmm7
+ pxor %xmm0 , %xmm7 # xor the initial crc value
+
+ psrldq $7, %xmm7
+
+ jmp _barrett
+
+ENDPROC(crc_t10dif_pcl)
+
+.data
+
+# precomputed constants
+# these constants are precomputed from the poly:
+# 0x8bb70000 (0x8bb7 scaled to 32 bits)
+.align 16
+# Q = 0x18BB70000
+# rk1 = 2^(32*3) mod Q << 32
+# rk2 = 2^(32*5) mod Q << 32
+# rk3 = 2^(32*15) mod Q << 32
+# rk4 = 2^(32*17) mod Q << 32
+# rk5 = 2^(32*3) mod Q << 32
+# rk6 = 2^(32*2) mod Q << 32
+# rk7 = floor(2^64/Q)
+# rk8 = Q
+rk1:
+.quad 0x2d56000000000000
+rk2:
+.quad 0x06df000000000000
+rk3:
+.quad 0x9d9d000000000000
+rk4:
+.quad 0x7cf5000000000000
+rk5:
+.quad 0x2d56000000000000
+rk6:
+.quad 0x1368000000000000
+rk7:
+.quad 0x00000001f65a57f8
+rk8:
+.quad 0x000000018bb70000
+
+rk9:
+.quad 0xceae000000000000
+rk10:
+.quad 0xbfd6000000000000
+rk11:
+.quad 0x1e16000000000000
+rk12:
+.quad 0x713c000000000000
+rk13:
+.quad 0xf7f9000000000000
+rk14:
+.quad 0x80a6000000000000
+rk15:
+.quad 0x044c000000000000
+rk16:
+.quad 0xe658000000000000
+rk17:
+.quad 0xad18000000000000
+rk18:
+.quad 0xa497000000000000
+rk19:
+.quad 0x6ee3000000000000
+rk20:
+.quad 0xe7b5000000000000
+
+
+
+mask1:
+.octa 0x80808080808080808080808080808080
+mask2:
+.octa 0x00000000FFFFFFFFFFFFFFFFFFFFFFFF
+
+SHUF_MASK:
+.octa 0x000102030405060708090A0B0C0D0E0F
+
+pshufb_shf_table:
+# use these values for shift constants for the pshufb instruction
+# different alignments result in values as shown:
+# DDQ 0x008f8e8d8c8b8a898887868584838281 # shl 15 (16-1) / shr1
+# DDQ 0x01008f8e8d8c8b8a8988878685848382 # shl 14 (16-3) / shr2
+# DDQ 0x0201008f8e8d8c8b8a89888786858483 # shl 13 (16-4) / shr3
+# DDQ 0x030201008f8e8d8c8b8a898887868584 # shl 12 (16-4) / shr4
+# DDQ 0x04030201008f8e8d8c8b8a8988878685 # shl 11 (16-5) / shr5
+# DDQ 0x0504030201008f8e8d8c8b8a89888786 # shl 10 (16-6) / shr6
+# DDQ 0x060504030201008f8e8d8c8b8a898887 # shl 9 (16-7) / shr7
+# DDQ 0x07060504030201008f8e8d8c8b8a8988 # shl 8 (16-8) / shr8
+# DDQ 0x0807060504030201008f8e8d8c8b8a89 # shl 7 (16-9) / shr9
+# DDQ 0x090807060504030201008f8e8d8c8b8a # shl 6 (16-10) / shr10
+# DDQ 0x0a090807060504030201008f8e8d8c8b # shl 5 (16-11) / shr11
+# DDQ 0x0b0a090807060504030201008f8e8d8c # shl 4 (16-12) / shr12
+# DDQ 0x0c0b0a090807060504030201008f8e8d # shl 3 (16-13) / shr13
+# DDQ 0x0d0c0b0a090807060504030201008f8e # shl 2 (16-14) / shr14
+# DDQ 0x0e0d0c0b0a090807060504030201008f # shl 1 (16-15) / shr15
+.octa 0x8f8e8d8c8b8a89888786858483828100
+.octa 0x000e0d0c0b0a09080706050403020100
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
new file mode 100644
index 00000000000..7845d7fd54c
--- /dev/null
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -0,0 +1,151 @@
+/*
+ * Cryptographic API.
+ *
+ * T10 Data Integrity Field CRC16 Crypto Transform using PCLMULQDQ Instructions
+ *
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc-t10dif.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+#include <asm/i387.h>
+#include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
+
+asmlinkage __u16 crc_t10dif_pcl(__u16 crc, const unsigned char *buf,
+ size_t len);
+
+struct chksum_desc_ctx {
+ __u16 crc;
+};
+
+/*
+ * Steps through buffer one byte at at time, calculates reflected
+ * crc using table.
+ */
+
+static int chksum_init(struct shash_desc *desc)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ ctx->crc = 0;
+
+ return 0;
+}
+
+static int chksum_update(struct shash_desc *desc, const u8 *data,
+ unsigned int length)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ if (irq_fpu_usable()) {
+ kernel_fpu_begin();
+ ctx->crc = crc_t10dif_pcl(ctx->crc, data, length);
+ kernel_fpu_end();
+ } else
+ ctx->crc = crc_t10dif_generic(ctx->crc, data, length);
+ return 0;
+}
+
+static int chksum_final(struct shash_desc *desc, u8 *out)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ *(__u16 *)out = ctx->crc;
+ return 0;
+}
+
+static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
+ u8 *out)
+{
+ if (irq_fpu_usable()) {
+ kernel_fpu_begin();
+ *(__u16 *)out = crc_t10dif_pcl(*crcp, data, len);
+ kernel_fpu_end();
+ } else
+ *(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+ return 0;
+}
+
+static int chksum_finup(struct shash_desc *desc, const u8 *data,
+ unsigned int len, u8 *out)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ return __chksum_finup(&ctx->crc, data, len, out);
+}
+
+static int chksum_digest(struct shash_desc *desc, const u8 *data,
+ unsigned int length, u8 *out)
+{
+ struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+ return __chksum_finup(&ctx->crc, data, length, out);
+}
+
+static struct shash_alg alg = {
+ .digestsize = CRC_T10DIF_DIGEST_SIZE,
+ .init = chksum_init,
+ .update = chksum_update,
+ .final = chksum_final,
+ .finup = chksum_finup,
+ .digest = chksum_digest,
+ .descsize = sizeof(struct chksum_desc_ctx),
+ .base = {
+ .cra_name = "crct10dif",
+ .cra_driver_name = "crct10dif-pclmul",
+ .cra_priority = 200,
+ .cra_blocksize = CRC_T10DIF_BLOCK_SIZE,
+ .cra_module = THIS_MODULE,
+ }
+};
+
+static const struct x86_cpu_id crct10dif_cpu_id[] = {
+ X86_FEATURE_MATCH(X86_FEATURE_PCLMULQDQ),
+ {}
+};
+MODULE_DEVICE_TABLE(x86cpu, crct10dif_cpu_id);
+
+static int __init crct10dif_intel_mod_init(void)
+{
+ if (!x86_match_cpu(crct10dif_cpu_id))
+ return -ENODEV;
+
+ return crypto_register_shash(&alg);
+}
+
+static void __exit crct10dif_intel_mod_fini(void)
+{
+ crypto_unregister_shash(&alg);
+}
+
+module_init(crct10dif_intel_mod_init);
+module_exit(crct10dif_intel_mod_fini);
+
+MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
+MODULE_DESCRIPTION("T10 DIF CRC calculation accelerated with PCLMULQDQ.");
+MODULE_LICENSE("GPL");
+
+MODULE_ALIAS("crct10dif");
+MODULE_ALIAS("crct10dif-pclmul");
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index bccfca68430..665a730307f 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -457,7 +457,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
else
put_user_ex(0, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
- err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+ compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
if (ksig->ka.sa.sa_flags & SA_RESTORER)
restorer = ksig->ka.sa.sa_restorer;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 474dc1b59f7..4299eb05023 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -452,7 +452,7 @@ ia32_badsys:
CFI_ENDPROC
- .macro PTREGSCALL label, func, arg
+ .macro PTREGSCALL label, func
ALIGN
GLOBAL(\label)
leaq \func(%rip),%rax
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 2dfac58f3b1..b1977bad543 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -86,6 +86,7 @@ extern int acpi_pci_disabled;
extern int acpi_skip_timer_override;
extern int acpi_use_timer_override;
extern int acpi_fix_pin2_polarity;
+extern int acpi_disable_cmcff;
extern u8 acpi_sci_flags;
extern int acpi_sci_override_gsi;
@@ -168,6 +169,7 @@ static inline void arch_acpi_set_pdc_bits(u32 *buf)
#define acpi_lapic 0
#define acpi_ioapic 0
+#define acpi_disable_cmcff 0
static inline void acpi_noirq_set(void) { }
static inline void acpi_disable_pci(void) { }
static inline void disable_acpi(void) { }
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 58ed6d96a6a..0a3f9c9f98d 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -5,6 +5,7 @@
#include <linux/stddef.h>
#include <linux/stringify.h>
#include <asm/asm.h>
+#include <asm/ptrace.h>
/*
* Alternative inline assembly for SMP.
@@ -220,20 +221,11 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
* no thread can be preempted in the instructions being modified (no iret to an
* invalid instruction possible) or if the instructions are changed from a
* consistent state to another consistent state atomically.
- * More care must be taken when modifying code in the SMP case because of
- * Intel's errata. text_poke_smp() takes care that errata, but still
- * doesn't support NMI/MCE handler code modifying.
* On the local CPU you need to be protected again NMI or MCE handlers seeing an
* inconsistent instruction while you patch.
*/
-struct text_poke_param {
- void *addr;
- const void *opcode;
- size_t len;
-};
-
extern void *text_poke(void *addr, const void *opcode, size_t len);
-extern void *text_poke_smp(void *addr, const void *opcode, size_t len);
-extern void text_poke_smp_batch(struct text_poke_param *params, int n);
+extern int poke_int3_handler(struct pt_regs *regs);
+extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
#endif /* _ASM_X86_ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index f8119b582c3..1d2091a226b 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -715,4 +715,6 @@ static inline void exiting_ack_irq(void)
ack_APIC_irq();
}
+extern void ioapic_zap_locks(void);
+
#endif /* _ASM_X86_APIC_H */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 1c2d247f65c..4582e8e1cd1 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -3,21 +3,25 @@
#ifdef __ASSEMBLY__
# define __ASM_FORM(x) x
+# define __ASM_FORM_RAW(x) x
# define __ASM_FORM_COMMA(x) x,
#else
# define __ASM_FORM(x) " " #x " "
+# define __ASM_FORM_RAW(x) #x
# define __ASM_FORM_COMMA(x) " " #x ","
#endif
#ifdef CONFIG_X86_32
# define __ASM_SEL(a,b) __ASM_FORM(a)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a)
#else
# define __ASM_SEL(a,b) __ASM_FORM(b)
+# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b)
#endif
#define __ASM_SIZE(inst, ...) __ASM_SEL(inst##l##__VA_ARGS__, \
inst##q##__VA_ARGS__)
-#define __ASM_REG(reg) __ASM_SEL(e##reg, r##reg)
+#define __ASM_REG(reg) __ASM_SEL_RAW(e##reg, r##reg)
#define _ASM_PTR __ASM_SEL(.long, .quad)
#define _ASM_ALIGN __ASM_SEL(.balign 4, .balign 8)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 722aa3b0462..da31c8b8a92 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -6,6 +6,7 @@
#include <asm/processor.h>
#include <asm/alternative.h>
#include <asm/cmpxchg.h>
+#include <asm/rmwcc.h>
/*
* Atomic operations that C can't guarantee us. Useful for
@@ -76,12 +77,7 @@ static inline void atomic_sub(int i, atomic_t *v)
*/
static inline int atomic_sub_and_test(int i, atomic_t *v)
{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
- : "+m" (v->counter), "=qm" (c)
- : "ir" (i) : "memory");
- return c;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, i, "%0", "e");
}
/**
@@ -118,12 +114,7 @@ static inline void atomic_dec(atomic_t *v)
*/
static inline int atomic_dec_and_test(atomic_t *v)
{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "decl %0; sete %1"
- : "+m" (v->counter), "=qm" (c)
- : : "memory");
- return c != 0;
+ GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
}
/**
@@ -136,12 +127,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
*/
static inline int atomic_inc_and_test(atomic_t *v)
{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "incl %0; sete %1"
- : "+m" (v->counter), "=qm" (c)
- : : "memory");
- return c != 0;
+ GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
}
/**
@@ -155,12 +141,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
*/
static inline int atomic_add_negative(int i, atomic_t *v)
{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
- : "+m" (v->counter), "=qm" (c)
- : "ir" (i) : "memory");
- return c;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, i, "%0", "s");
}
/**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 0e1cbfc8ee0..3f065c985ae 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -72,12 +72,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
*/
static inline int atomic64_sub_and_test(long i, atomic64_t *v)
{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
- : "=m" (v->counter), "=qm" (c)
- : "er" (i), "m" (v->counter) : "memory");
- return c;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, i, "%0", "e");
}
/**
@@ -116,12 +111,7 @@ static inline void atomic64_dec(atomic64_t *v)
*/
static inline int atomic64_dec_and_test(atomic64_t *v)
{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "decq %0; sete %1"
- : "=m" (v->counter), "=qm" (c)
- : "m" (v->counter) : "memory");
- return c != 0;
+ GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
}
/**
@@ -134,12 +124,7 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
*/
static inline int atomic64_inc_and_test(atomic64_t *v)
{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "incq %0; sete %1"
- : "=m" (v->counter), "=qm" (c)
- : "m" (v->counter) : "memory");
- return c != 0;
+ GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e");
}
/**
@@ -153,12 +138,7 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
*/
static inline int atomic64_add_negative(long i, atomic64_t *v)
{
- unsigned char c;
-
- asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
- : "=m" (v->counter), "=qm" (c)
- : "er" (i), "m" (v->counter) : "memory");
- return c;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, i, "%0", "s");
}
/**
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 6dfd0195bb5..6d76d093598 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -14,6 +14,15 @@
#include <linux/compiler.h>
#include <asm/alternative.h>
+#include <asm/rmwcc.h>
+
+#if BITS_PER_LONG == 32
+# define _BITOPS_LONG_SHIFT 5
+#elif BITS_PER_LONG == 64
+# define _BITOPS_LONG_SHIFT 6
+#else
+# error "Unexpected BITS_PER_LONG"
+#endif
#define BIT_64(n) (U64_C(1) << (n))
@@ -59,7 +68,7 @@
* restricted to acting on a single-word quantity.
*/
static __always_inline void
-set_bit(unsigned int nr, volatile unsigned long *addr)
+set_bit(long nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "orb %1,%0"
@@ -81,7 +90,7 @@ set_bit(unsigned int nr, volatile unsigned long *addr)
* If it's called on the same region of memory simultaneously, the effect
* may be that only one operation succeeds.
*/
-static inline void __set_bit(int nr, volatile unsigned long *addr)
+static inline void __set_bit(long nr, volatile unsigned long *addr)
{
asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
}
@@ -97,7 +106,7 @@ static inline void __set_bit(int nr, volatile unsigned long *addr)
* in order to ensure changes are visible on other processors.
*/
static __always_inline void
-clear_bit(int nr, volatile unsigned long *addr)
+clear_bit(long nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "andb %1,%0"
@@ -118,13 +127,13 @@ clear_bit(int nr, volatile unsigned long *addr)
* clear_bit() is atomic and implies release semantics before the memory
* operation. It can be used for an unlock.
*/
-static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
{
barrier();
clear_bit(nr, addr);
}
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
+static inline void __clear_bit(long nr, volatile unsigned long *addr)
{
asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
}
@@ -141,7 +150,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr)
* No memory barrier is required here, because x86 cannot reorder stores past
* older loads. Same principle as spin_unlock.
*/
-static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
{
barrier();
__clear_bit(nr, addr);
@@ -159,7 +168,7 @@ static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
* If it's called on the same region of memory simultaneously, the effect
* may be that only one operation succeeds.
*/
-static inline void __change_bit(int nr, volatile unsigned long *addr)
+static inline void __change_bit(long nr, volatile unsigned long *addr)
{
asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
}
@@ -173,7 +182,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static inline void change_bit(long nr, volatile unsigned long *addr)
{
if (IS_IMMEDIATE(nr)) {
asm volatile(LOCK_PREFIX "xorb %1,%0"
@@ -194,14 +203,9 @@ static inline void change_bit(int nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
{
- int oldbit;
-
- asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
- "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
- return oldbit;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, nr, "%0", "c");
}
/**
@@ -212,7 +216,7 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
* This is the same as test_and_set_bit on x86.
*/
static __always_inline int
-test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+test_and_set_bit_lock(long nr, volatile unsigned long *addr)
{
return test_and_set_bit(nr, addr);
}
@@ -226,7 +230,7 @@ test_and_set_bit_lock(int nr, volatile unsigned long *addr)
* If two examples of this operation race, one can appear to succeed
* but actually fail. You must protect multiple accesses with a lock.
*/
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
@@ -245,15 +249,9 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
{
- int oldbit;
-
- asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
- "sbb %0,%0"
- : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
- return oldbit;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, nr, "%0", "c");
}
/**
@@ -272,7 +270,7 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
* accessed from a hypervisor on the same CPU if running in a VM: don't change
* this without also updating arch/x86/kernel/kvm.c
*/
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
@@ -284,7 +282,7 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
}
/* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
@@ -304,24 +302,18 @@ static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
{
- int oldbit;
-
- asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
- "sbb %0,%0"
- : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
- return oldbit;
+ GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, nr, "%0", "c");
}
-static __always_inline int constant_test_bit(unsigned int nr, const volatile unsigned long *addr)
+static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
{
- return ((1UL << (nr % BITS_PER_LONG)) &
- (addr[nr / BITS_PER_LONG])) != 0;
+ return ((1UL << (nr & (BITS_PER_LONG-1))) &
+ (addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
}
-static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
+static inline int variable_test_bit(long nr, volatile const unsigned long *addr)
{
int oldbit;
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 0fa67503391..cb4c73bfeb4 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -48,6 +48,8 @@ For 32-bit we have the following conventions - kernel is built with
#include <asm/dwarf2.h>
+#ifdef CONFIG_X86_64
+
/*
* 64-bit system call stack frame layout defines and helpers,
* for assembly code:
@@ -192,3 +194,51 @@ For 32-bit we have the following conventions - kernel is built with
.macro icebp
.byte 0xf1
.endm
+
+#else /* CONFIG_X86_64 */
+
+/*
+ * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
+ * are different from the entry_32.S versions in not changing the segment
+ * registers. So only suitable for in kernel use, not when transitioning
+ * from or to user space. The resulting stack frame is not a standard
+ * pt_regs frame. The main use case is calling C code from assembler
+ * when all the registers need to be preserved.
+ */
+
+ .macro SAVE_ALL
+ pushl_cfi %eax
+ CFI_REL_OFFSET eax, 0
+ pushl_cfi %ebp
+ CFI_REL_OFFSET ebp, 0
+ pushl_cfi %edi
+ CFI_REL_OFFSET edi, 0
+ pushl_cfi %esi
+ CFI_REL_OFFSET esi, 0
+ pushl_cfi %edx
+ CFI_REL_OFFSET edx, 0
+ pushl_cfi %ecx
+ CFI_REL_OFFSET ecx, 0
+ pushl_cfi %ebx
+ CFI_REL_OFFSET ebx, 0
+ .endm
+
+ .macro RESTORE_ALL
+ popl_cfi %ebx
+ CFI_RESTORE ebx
+ popl_cfi %ecx
+ CFI_RESTORE ecx
+ popl_cfi %edx
+ CFI_RESTORE edx
+ popl_cfi %esi
+ CFI_RESTORE esi
+ popl_cfi %edi
+ CFI_RESTORE edi
+ popl_cfi %ebp
+ CFI_RESTORE ebp
+ popl_cfi %eax
+ CFI_RESTORE eax
+ .endm
+
+#endif /* CONFIG_X86_64 */
+
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 46fc474fd81..f50de695173 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -49,9 +49,15 @@ static inline __wsum csum_partial_copy_from_user(const void __user *src,
int len, __wsum sum,
int *err_ptr)
{
+ __wsum ret;
+
might_sleep();
- return csum_partial_copy_generic((__force void *)src, dst,
- len, sum, err_ptr, NULL);
+ stac();
+ ret = csum_partial_copy_generic((__force void *)src, dst,
+ len, sum, err_ptr, NULL);
+ clac();
+
+ return ret;
}
/*
@@ -176,10 +182,16 @@ static inline __wsum csum_and_copy_to_user(const void *src,
int len, __wsum sum,
int *err_ptr)
{
+ __wsum ret;
+
might_sleep();
- if (access_ok(VERIFY_WRITE, dst, len))
- return csum_partial_copy_generic(src, (__force void *)dst,
- len, sum, NULL, err_ptr);
+ if (access_ok(VERIFY_WRITE, dst, len)) {
+ stac();
+ ret = csum_partial_copy_generic(src, (__force void *)dst,
+ len, sum, NULL, err_ptr);
+ clac();
+ return ret;
+ }
if (len)
*err_ptr = -EFAULT;
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index 9bfdc41629e..e6fd8a026c7 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -133,7 +133,7 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum);
/* Do not call this directly. Use the wrappers below */
-extern __wsum csum_partial_copy_generic(const void *src, const void *dst,
+extern __visible __wsum csum_partial_copy_generic(const void *src, const void *dst,
int len, __wsum sum,
int *src_err_ptr, int *dst_err_ptr);
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 47538a61c91..89270b4318d 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -366,14 +366,15 @@ extern bool __static_cpu_has_safe(u16 bit);
*/
static __always_inline __pure bool __static_cpu_has(u16 bit)
{
-#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
+#ifdef CC_HAVE_ASM_GOTO
#ifdef CONFIG_X86_DEBUG_STATIC_CPU_HAS
+
/*
* Catch too early usage of this before alternatives
* have run.
*/
- asm goto("1: jmp %l[t_warn]\n"
+ asm_volatile_goto("1: jmp %l[t_warn]\n"
"2:\n"
".section .altinstructions,\"a\"\n"
" .long 1b - .\n"
@@ -384,9 +385,10 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
".previous\n"
/* skipping size check since replacement size = 0 */
: : "i" (X86_FEATURE_ALWAYS) : : t_warn);
+
#endif
- asm goto("1: jmp %l[t_no]\n"
+ asm_volatile_goto("1: jmp %l[t_no]\n"
"2:\n"
".section .altinstructions,\"a\"\n"
" .long 1b - .\n"
@@ -406,7 +408,9 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
warn_pre_alternatives();
return false;
#endif
-#else /* GCC_VERSION >= 40500 */
+
+#else /* CC_HAVE_ASM_GOTO */
+
u8 flag;
/* Open-coded due to __stringify() in ALTERNATIVE() */
asm volatile("1: movb $0,%0\n"
@@ -427,7 +431,8 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
".previous\n"
: "=qm" (flag) : "i" (bit));
return flag;
-#endif
+
+#endif /* CC_HAVE_ASM_GOTO */
}
#define static_cpu_has(bit) \
@@ -441,14 +446,14 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
{
-#if __GNUC__ > 4 || __GNUC_MINOR__ >= 5
+#ifdef CC_HAVE_ASM_GOTO
/*
* We need to spell the jumps to the compiler because, depending on the offset,
* the replacement jump can be bigger than the original jump, and this we cannot
* have. Thus, we force the jump to the widest, 4-byte, signed relative
* offset even though the last would often fit in less bytes.
*/
- asm goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+ asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
"2:\n"
".section .altinstructions,\"a\"\n"
" .long 1b - .\n" /* src offset */
@@ -475,7 +480,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
return false;
t_dynamic:
return __static_cpu_has_safe(bit);
-#else /* GCC_VERSION >= 40500 */
+#else
u8 flag;
/* Open-coded due to __stringify() in ALTERNATIVE() */
asm volatile("1: movb $2,%0\n"
@@ -511,7 +516,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
: "=qm" (flag)
: "i" (bit), "i" (X86_FEATURE_ALWAYS));
return (flag == 2 ? __static_cpu_has_safe(bit) : flag);
-#endif
+#endif /* CC_HAVE_ASM_GOTO */
}
#define static_cpu_has_safe(bit) \
diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h
index c0924165997..b4b38bacb40 100644
--- a/arch/x86/include/asm/dma-contiguous.h
+++ b/arch/x86/include/asm/dma-contiguous.h
@@ -4,7 +4,6 @@
#ifdef __KERNEL__
#include <linux/types.h>
-#include <asm-generic/dma-contiguous.h>
static inline void
dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index cccd07fa5e3..779c2efe2e9 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -29,7 +29,7 @@ extern void e820_setup_gap(void);
extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
unsigned long start_addr, unsigned long long end_addr);
struct setup_data;
-extern void parse_e820_ext(struct setup_data *data);
+extern void parse_e820_ext(u64 phys_addr, u32 data_len);
#if defined(CONFIG_X86_64) || \
(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 0062a012504..65c6e6e3a55 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -109,6 +109,8 @@ static inline bool efi_is_native(void)
return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
}
+extern struct console early_efi_console;
+
#else
/*
* IF EFI is not configured, have the EFI calls return -ENOSYS.
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index e4ac559c4a2..92b3bae08b7 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -26,56 +26,56 @@
#include <asm/sections.h>
/* Interrupt handlers registered during init_IRQ */
-extern void apic_timer_interrupt(void);
-extern void x86_platform_ipi(void);
-extern void kvm_posted_intr_ipi(void);
-extern void error_interrupt(void);
-extern void irq_work_interrupt(void);
-
-extern void spurious_interrupt(void);
-extern void thermal_interrupt(void);
-extern void reschedule_interrupt(void);
-
-extern void invalidate_interrupt(void);
-extern void invalidate_interrupt0(void);
-extern void invalidate_interrupt1(void);
-extern void invalidate_interrupt2(void);
-extern void invalidate_interrupt3(void);
-extern void invalidate_interrupt4(void);
-extern void invalidate_interrupt5(void);
-extern void invalidate_interrupt6(void);
-extern void invalidate_interrupt7(void);
-extern void invalidate_interrupt8(void);
-extern void invalidate_interrupt9(void);
-extern void invalidate_interrupt10(void);
-extern void invalidate_interrupt11(void);
-extern void invalidate_interrupt12(void);
-extern void invalidate_interrupt13(void);
-extern void invalidate_interrupt14(void);
-extern void invalidate_interrupt15(void);
-extern void invalidate_interrupt16(void);
-extern void invalidate_interrupt17(void);
-extern void invalidate_interrupt18(void);
-extern void invalidate_interrupt19(void);
-extern void invalidate_interrupt20(void);
-extern void invalidate_interrupt21(void);
-extern void invalidate_interrupt22(void);
-extern void invalidate_interrupt23(void);
-extern void invalidate_interrupt24(void);
-extern void invalidate_interrupt25(void);
-extern void invalidate_interrupt26(void);
-extern void invalidate_interrupt27(void);
-extern void invalidate_interrupt28(void);
-extern void invalidate_interrupt29(void);
-extern void invalidate_interrupt30(void);
-extern void invalidate_interrupt31(void);
-
-extern void irq_move_cleanup_interrupt(void);
-extern void reboot_interrupt(void);
-extern void threshold_interrupt(void);
-
-extern void call_function_interrupt(void);
-extern void call_function_single_interrupt(void);
+extern asmlinkage void apic_timer_interrupt(void);
+extern asmlinkage void x86_platform_ipi(void);
+extern asmlinkage void kvm_posted_intr_ipi(void);
+extern asmlinkage void error_interrupt(void);
+extern asmlinkage void irq_work_interrupt(void);
+
+extern asmlinkage void spurious_interrupt(void);
+extern asmlinkage void thermal_interrupt(void);
+extern asmlinkage void reschedule_interrupt(void);
+
+extern asmlinkage void invalidate_interrupt(void);
+extern asmlinkage void invalidate_interrupt0(void);
+extern asmlinkage void invalidate_interrupt1(void);
+extern asmlinkage void invalidate_interrupt2(void);
+extern asmlinkage void invalidate_interrupt3(void);
+extern asmlinkage void invalidate_interrupt4(void);
+extern asmlinkage void invalidate_interrupt5(void);
+extern asmlinkage void invalidate_interrupt6(void);
+extern asmlinkage void invalidate_interrupt7(void);
+extern asmlinkage void invalidate_interrupt8(void);
+extern asmlinkage void invalidate_interrupt9(void);
+extern asmlinkage void invalidate_interrupt10(void);
+extern asmlinkage void invalidate_interrupt11(void);
+extern asmlinkage void invalidate_interrupt12(void);
+extern asmlinkage void invalidate_interrupt13(void);
+extern asmlinkage void invalidate_interrupt14(void);
+extern asmlinkage void invalidate_interrupt15(void);
+extern asmlinkage void invalidate_interrupt16(void);
+extern asmlinkage void invalidate_interrupt17(void);
+extern asmlinkage void invalidate_interrupt18(void);
+extern asmlinkage void invalidate_interrupt19(void);
+extern asmlinkage void invalidate_interrupt20(void);
+extern asmlinkage void invalidate_interrupt21(void);
+extern asmlinkage void invalidate_interrupt22(void);
+extern asmlinkage void invalidate_interrupt23(void);
+extern asmlinkage void invalidate_interrupt24(void);
+extern asmlinkage void invalidate_interrupt25(void);
+extern asmlinkage void invalidate_interrupt26(void);
+extern asmlinkage void invalidate_interrupt27(void);
+extern asmlinkage void invalidate_interrupt28(void);
+extern asmlinkage void invalidate_interrupt29(void);
+extern asmlinkage void invalidate_interrupt30(void);
+extern asmlinkage void invalidate_interrupt31(void);
+
+extern asmlinkage void irq_move_cleanup_interrupt(void);
+extern asmlinkage void reboot_interrupt(void);
+extern asmlinkage void threshold_interrupt(void);
+
+extern asmlinkage void call_function_interrupt(void);
+extern asmlinkage void call_function_single_interrupt(void);
#ifdef CONFIG_TRACING
/* Interrupt handlers registered during init_IRQ */
@@ -172,22 +172,18 @@ extern atomic_t irq_mis_count;
extern void eisa_set_level_irq(unsigned int irq);
/* SMP */
-extern void smp_apic_timer_interrupt(struct pt_regs *);
-extern void smp_spurious_interrupt(struct pt_regs *);
-extern void smp_x86_platform_ipi(struct pt_regs *);
-extern void smp_error_interrupt(struct pt_regs *);
+extern __visible void smp_apic_timer_interrupt(struct pt_regs *);
+extern __visible void smp_spurious_interrupt(struct pt_regs *);
+extern __visible void smp_x86_platform_ipi(struct pt_regs *);
+extern __visible void smp_error_interrupt(struct pt_regs *);
#ifdef CONFIG_X86_IO_APIC
extern asmlinkage void smp_irq_move_cleanup_interrupt(void);
#endif
#ifdef CONFIG_SMP
-extern void smp_reschedule_interrupt(struct pt_regs *);
-extern void smp_call_function_interrupt(struct pt_regs *);
-extern void smp_call_function_single_interrupt(struct pt_regs *);
-#ifdef CONFIG_X86_32
-extern void smp_invalidate_interrupt(struct pt_regs *);
-#else
-extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
-#endif
+extern __visible void smp_reschedule_interrupt(struct pt_regs *);
+extern __visible void smp_call_function_interrupt(struct pt_regs *);
+extern __visible void smp_call_function_single_interrupt(struct pt_regs *);
+extern __visible void smp_invalidate_interrupt(struct pt_regs *);
#endif
extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 2d4b5e6107c..e42f758a0fb 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -33,7 +33,7 @@ struct hypervisor_x86 {
const char *name;
/* Detection routine */
- bool (*detect)(void);
+ uint32_t (*detect)(void);
/* Adjust CPU feature bits (run once per CPU) */
void (*set_cpu_features)(struct cpuinfo_x86 *);
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
new file mode 100644
index 00000000000..459769d3926
--- /dev/null
+++ b/arch/x86/include/asm/intel-mid.h
@@ -0,0 +1,113 @@
+/*
+ * intel-mid.h: Intel MID specific setup code
+ *
+ * (C) Copyright 2009 Intel Corporation
+ *
+ * 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_INTEL_MID_H
+#define _ASM_X86_INTEL_MID_H
+
+#include <linux/sfi.h>
+#include <linux/platform_device.h>
+
+extern int intel_mid_pci_init(void);
+extern int get_gpio_by_name(const char *name);
+extern void intel_scu_device_register(struct platform_device *pdev);
+extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
+extern int __init sfi_parse_mtmr(struct sfi_table_header *table);
+extern int sfi_mrtc_num;
+extern struct sfi_rtc_table_entry sfi_mrtc_array[];
+
+/*
+ * Here defines the array of devices platform data that IAFW would export
+ * through SFI "DEVS" table, we use name and type to match the device and
+ * its platform data.
+ */
+struct devs_id {
+ char name[SFI_NAME_LEN + 1];
+ u8 type;
+ u8 delay;
+ void *(*get_platform_data)(void *info);
+ /* Custom handler for devices */
+ void (*device_handler)(struct sfi_device_table_entry *pentry,
+ struct devs_id *dev);
+};
+
+#define sfi_device(i) \
+ static const struct devs_id *const __intel_mid_sfi_##i##_dev __used \
+ __attribute__((__section__(".x86_intel_mid_dev.init"))) = &i
+
+/*
+ * Medfield is the follow-up of Moorestown, it combines two chip solution into
+ * one. Other than that it also added always-on and constant tsc and lapic
+ * timers. Medfield is the platform name, and the chip name is called Penwell
+ * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be
+ * identified via MSRs.
+ */
+enum intel_mid_cpu_type {
+ /* 1 was Moorestown */
+ INTEL_MID_CPU_CHIP_PENWELL = 2,
+};
+
+extern enum intel_mid_cpu_type __intel_mid_cpu_chip;
+
+#ifdef CONFIG_X86_INTEL_MID
+
+static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void)
+{
+ return __intel_mid_cpu_chip;
+}
+
+static inline bool intel_mid_has_msic(void)
+{
+ return (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_PENWELL);
+}
+
+#else /* !CONFIG_X86_INTEL_MID */
+
+#define intel_mid_identify_cpu() (0)
+#define intel_mid_has_msic() (0)
+
+#endif /* !CONFIG_X86_INTEL_MID */
+
+enum intel_mid_timer_options {
+ INTEL_MID_TIMER_DEFAULT,
+ INTEL_MID_TIMER_APBT_ONLY,
+ INTEL_MID_TIMER_LAPIC_APBT,
+};
+
+extern enum intel_mid_timer_options intel_mid_timer_options;
+
+/*
+ * Penwell uses spread spectrum clock, so the freq number is not exactly
+ * the same as reported by MSR based on SDM.
+ */
+#define PENWELL_FSB_FREQ_83SKU 83200
+#define PENWELL_FSB_FREQ_100SKU 99840
+
+#define SFI_MTMR_MAX_NUM 8
+#define SFI_MRTC_MAX 8
+
+extern struct console early_mrst_console;
+extern void mrst_early_console_init(void);
+
+extern struct console early_hsu_console;
+extern void hsu_early_console_init(const char *);
+
+extern void intel_scu_devices_create(void);
+extern void intel_scu_devices_destroy(void);
+
+/* VRTC timer */
+#define MRST_VRTC_MAP_SZ (1024)
+/*#define MRST_VRTC_PGOFFSET (0xc00) */
+
+extern void intel_mid_rtc_init(void);
+
+/* the offset for the mapping of global gpio pin to irq */
+#define INTEL_MID_IRQ_OFFSET 0x100
+
+#endif /* _ASM_X86_INTEL_MID_H */
diff --git a/arch/x86/include/asm/mrst-vrtc.h b/arch/x86/include/asm/intel_mid_vrtc.h
index 1e69a75412a..86ff4685c40 100644
--- a/arch/x86/include/asm/mrst-vrtc.h
+++ b/arch/x86/include/asm/intel_mid_vrtc.h
@@ -1,5 +1,5 @@
-#ifndef _MRST_VRTC_H
-#define _MRST_VRTC_H
+#ifndef _INTEL_MID_VRTC_H
+#define _INTEL_MID_VRTC_H
extern unsigned char vrtc_cmos_read(unsigned char reg);
extern void vrtc_cmos_write(unsigned char val, unsigned char reg);
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 57873beb329..0ea10f27d61 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -33,7 +33,7 @@ extern void (*x86_platform_ipi_callback)(void);
extern void native_init_IRQ(void);
extern bool handle_irq(unsigned irq, struct pt_regs *regs);
-extern unsigned int do_IRQ(struct pt_regs *regs);
+extern __visible unsigned int do_IRQ(struct pt_regs *regs);
/* Interrupt vector management */
extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 3a16c1483b4..6a2cefb4395 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -3,18 +3,23 @@
#ifdef __KERNEL__
+#include <linux/stringify.h>
#include <linux/types.h>
#include <asm/nops.h>
#include <asm/asm.h>
#define JUMP_LABEL_NOP_SIZE 5
-#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+#ifdef CONFIG_X86_64
+# define STATIC_KEY_INIT_NOP P6_NOP5_ATOMIC
+#else
+# define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC
+#endif
static __always_inline bool arch_static_branch(struct static_key *key)
{
- asm goto("1:"
- STATIC_KEY_INITIAL_NOP
+ asm_volatile_goto("1:"
+ ".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
".pushsection __jump_table, \"aw\" \n\t"
_ASM_ALIGN "\n\t"
_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 5a6d2873f80..9454c167629 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -49,10 +49,10 @@ typedef u8 kprobe_opcode_t;
#define flush_insn_slot(p) do { } while (0)
/* optinsn template addresses */
-extern kprobe_opcode_t optprobe_template_entry;
-extern kprobe_opcode_t optprobe_template_val;
-extern kprobe_opcode_t optprobe_template_call;
-extern kprobe_opcode_t optprobe_template_end;
+extern __visible kprobe_opcode_t optprobe_template_entry;
+extern __visible kprobe_opcode_t optprobe_template_val;
+extern __visible kprobe_opcode_t optprobe_template_call;
+extern __visible kprobe_opcode_t optprobe_template_end;
#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + RELATIVE_ADDR_SIZE)
#define MAX_OPTINSN_SIZE \
(((unsigned long)&optprobe_template_end - \
@@ -62,7 +62,7 @@ extern kprobe_opcode_t optprobe_template_end;
extern const int kretprobe_blacklist_size;
void arch_remove_kprobe(struct kprobe *p);
-void kretprobe_trampoline(void);
+asmlinkage void kretprobe_trampoline(void);
/* Architecture specific copy of original instruction*/
struct arch_specific_insn {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f87f7fcefa0..c76ff74a98f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -286,6 +286,7 @@ struct kvm_mmu {
u64 *pae_root;
u64 *lm_root;
u64 rsvd_bits_mask[2][4];
+ u64 bad_mt_xwr;
/*
* Bitmap: bit set = last pte in walk
@@ -323,6 +324,7 @@ struct kvm_pmu {
u64 global_ovf_ctrl;
u64 counter_bitmask[2];
u64 global_ctrl_mask;
+ u64 reserved_bits;
u8 version;
struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
@@ -511,6 +513,14 @@ struct kvm_vcpu_arch {
* instruction.
*/
bool write_fault_to_shadow_pgtable;
+
+ /* set at EPT violation at this point */
+ unsigned long exit_qualification;
+
+ /* pv related host specific info */
+ struct {
+ bool pv_unhalted;
+ } pv;
};
struct kvm_lpage_info {
@@ -802,8 +812,8 @@ extern u32 kvm_min_guest_tsc_khz;
extern u32 kvm_max_guest_tsc_khz;
enum emulation_result {
- EMULATE_DONE, /* no further processing */
- EMULATE_DO_MMIO, /* kvm_run filled with mmio request */
+ EMULATE_DONE, /* no further processing */
+ EMULATE_USER_EXIT, /* kvm_run ready for userspace exit */
EMULATE_FAIL, /* can't emulate this instruction */
};
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 695399f2d5e..1df11590975 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -85,26 +85,20 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
return ret;
}
-static inline bool kvm_para_available(void)
+static inline uint32_t kvm_cpuid_base(void)
{
- unsigned int eax, ebx, ecx, edx;
- char signature[13];
-
if (boot_cpu_data.cpuid_level < 0)
- return false; /* So we don't blow up on old processors */
+ return 0; /* So we don't blow up on old processors */
- if (cpu_has_hypervisor) {
- cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
- memcpy(signature + 0, &ebx, 4);
- memcpy(signature + 4, &ecx, 4);
- memcpy(signature + 8, &edx, 4);
- signature[12] = 0;
+ if (cpu_has_hypervisor)
+ return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
- if (strcmp(signature, "KVMKVMKVM") == 0)
- return true;
- }
+ return 0;
+}
- return false;
+static inline bool kvm_para_available(void)
+{
+ return kvm_cpuid_base() != 0;
}
static inline unsigned int kvm_arch_para_features(void)
@@ -118,10 +112,20 @@ void kvm_async_pf_task_wait(u32 token);
void kvm_async_pf_task_wake(u32 token);
u32 kvm_read_and_reset_pf_reason(void);
extern void kvm_disable_steal_time(void);
-#else
-#define kvm_guest_init() do { } while (0)
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+void __init kvm_spinlock_init(void);
+#else /* !CONFIG_PARAVIRT_SPINLOCKS */
+static inline void kvm_spinlock_init(void)
+{
+}
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#else /* CONFIG_KVM_GUEST */
+#define kvm_guest_init() do {} while (0)
#define kvm_async_pf_task_wait(T) do {} while(0)
#define kvm_async_pf_task_wake(T) do {} while(0)
+
static inline u32 kvm_read_and_reset_pf_reason(void)
{
return 0;
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 2d89e3980cb..5b23e605e70 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -52,12 +52,7 @@ static inline void local_sub(long i, local_t *l)
*/
static inline int local_sub_and_test(long i, local_t *l)
{
- unsigned char c;
-
- asm volatile(_ASM_SUB "%2,%0; sete %1"
- : "+m" (l->a.counter), "=qm" (c)
- : "ir" (i) : "memory");
- return c;
+ GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, i, "%0", "e");
}
/**
@@ -70,12 +65,7 @@ static inline int local_sub_and_test(long i, local_t *l)
*/
static inline int local_dec_and_test(local_t *l)
{
- unsigned char c;
-
- asm volatile(_ASM_DEC "%0; sete %1"
- : "+m" (l->a.counter), "=qm" (c)
- : : "memory");
- return c != 0;
+ GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
}
/**
@@ -88,12 +78,7 @@ static inline int local_dec_and_test(local_t *l)
*/
static inline int local_inc_and_test(local_t *l)
{
- unsigned char c;
-
- asm volatile(_ASM_INC "%0; sete %1"
- : "+m" (l->a.counter), "=qm" (c)
- : : "memory");
- return c != 0;
+ GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e");
}
/**
@@ -107,12 +92,7 @@ static inline int local_inc_and_test(local_t *l)
*/
static inline int local_add_negative(long i, local_t *l)
{
- unsigned char c;
-
- asm volatile(_ASM_ADD "%2,%0; sets %1"
- : "+m" (l->a.counter), "=qm" (c)
- : "ir" (i) : "memory");
- return c;
+ GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, i, "%0", "s");
}
/**
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 29e3093bbd2..c696a868756 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -16,6 +16,7 @@
#define MCG_EXT_CNT_SHIFT 16
#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
#define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */
+#define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */
/* MCG_STATUS register defines */
#define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */
@@ -32,11 +33,20 @@
#define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */
#define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */
#define MCI_STATUS_AR (1ULL<<55) /* Action required */
-#define MCACOD 0xffff /* MCA Error Code */
+
+/*
+ * Note that the full MCACOD field of IA32_MCi_STATUS MSR is
+ * bits 15:0. But bit 12 is the 'F' bit, defined for corrected
+ * errors to indicate that errors are being filtered by hardware.
+ * We should mask out bit 12 when looking for specific signatures
+ * of uncorrected errors - so the F bit is deliberately skipped
+ * in this #define.
+ */
+#define MCACOD 0xefff /* MCA Error Code */
/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */
-#define MCACOD_SCRUBMSK 0xfff0
+#define MCACOD_SCRUBMSK 0xeff0 /* Skip bit 12 ('F' bit) */
#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */
#define MCACOD_DATA 0x0134 /* Data Load */
#define MCACOD_INSTR 0x0150 /* Instruction Fetch */
@@ -188,6 +198,9 @@ extern void register_mce_write_callback(ssize_t (*)(struct file *filp,
const char __user *ubuf,
size_t usize, loff_t *off));
+/* Disable CMCI/polling for MCA bank claimed by firmware */
+extern void mce_disable_bank(int bank);
+
/*
* Exception handler
*/
diff --git a/arch/x86/include/asm/misc.h b/arch/x86/include/asm/misc.h
new file mode 100644
index 00000000000..475f5bbc7f5
--- /dev/null
+++ b/arch/x86/include/asm/misc.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_X86_MISC_H
+#define _ASM_X86_MISC_H
+
+int num_digits(int val);
+
+#endif /* _ASM_X86_MISC_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index cdbf3677610..be12c534fd5 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -45,22 +45,28 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
/* Re-load page tables */
load_cr3(next->pgd);
- /* stop flush ipis for the previous mm */
+ /* Stop flush ipis for the previous mm */
cpumask_clear_cpu(cpu, mm_cpumask(prev));
- /*
- * load the LDT, if the LDT is different:
- */
+ /* Load the LDT, if the LDT is different: */
if (unlikely(prev->context.ldt != next->context.ldt))
load_LDT_nolock(&next->context);
}
#ifdef CONFIG_SMP
- else {
+ else {
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
- if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
- /* We were in lazy tlb mode and leave_mm disabled
+ if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+ /*
+ * On established mms, the mm_cpumask is only changed
+ * from irq context, from ptep_clear_flush() while in
+ * lazy tlb mode, and here. Irqs are blocked during
+ * schedule, protecting us from simultaneous changes.
+ */
+ cpumask_set_cpu(cpu, mm_cpumask(next));
+ /*
+ * We were in lazy tlb mode and leave_mm disabled
* tlb flush IPI delivery. We must reload CR3
* to make sure to use no freed page tables.
*/
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
deleted file mode 100644
index fc18bf3ce7c..00000000000
--- a/arch/x86/include/asm/mrst.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * mrst.h: Intel Moorestown platform specific setup code
- *
- * (C) Copyright 2009 Intel Corporation
- *
- * 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_MRST_H
-#define _ASM_X86_MRST_H
-
-#include <linux/sfi.h>
-
-extern int pci_mrst_init(void);
-extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
-extern int sfi_mrtc_num;
-extern struct sfi_rtc_table_entry sfi_mrtc_array[];
-
-/*
- * Medfield is the follow-up of Moorestown, it combines two chip solution into
- * one. Other than that it also added always-on and constant tsc and lapic
- * timers. Medfield is the platform name, and the chip name is called Penwell
- * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be
- * identified via MSRs.
- */
-enum mrst_cpu_type {
- /* 1 was Moorestown */
- MRST_CPU_CHIP_PENWELL = 2,
-};
-
-extern enum mrst_cpu_type __mrst_cpu_chip;
-
-#ifdef CONFIG_X86_INTEL_MID
-
-static inline enum mrst_cpu_type mrst_identify_cpu(void)
-{
- return __mrst_cpu_chip;
-}
-
-#else /* !CONFIG_X86_INTEL_MID */
-
-#define mrst_identify_cpu() (0)
-
-#endif /* !CONFIG_X86_INTEL_MID */
-
-enum mrst_timer_options {
- MRST_TIMER_DEFAULT,
- MRST_TIMER_APBT_ONLY,
- MRST_TIMER_LAPIC_APBT,
-};
-
-extern enum mrst_timer_options mrst_timer_options;
-
-/*
- * Penwell uses spread spectrum clock, so the freq number is not exactly
- * the same as reported by MSR based on SDM.
- */
-#define PENWELL_FSB_FREQ_83SKU 83200
-#define PENWELL_FSB_FREQ_100SKU 99840
-
-#define SFI_MTMR_MAX_NUM 8
-#define SFI_MRTC_MAX 8
-
-extern struct console early_mrst_console;
-extern void mrst_early_console_init(void);
-
-extern struct console early_hsu_console;
-extern void hsu_early_console_init(const char *);
-
-extern void intel_scu_devices_create(void);
-extern void intel_scu_devices_destroy(void);
-
-/* VRTC timer */
-#define MRST_VRTC_MAP_SZ (1024)
-/*#define MRST_VRTC_PGOFFSET (0xc00) */
-
-extern void mrst_rtc_init(void);
-
-#endif /* _ASM_X86_MRST_H */
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index 2c543fff241..07537a44216 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -16,6 +16,20 @@
*
* Atomically decrements @v and calls <fail_fn> if the result is negative.
*/
+#ifdef CC_HAVE_ASM_GOTO
+static inline void __mutex_fastpath_lock(atomic_t *v,
+ void (*fail_fn)(atomic_t *))
+{
+ asm_volatile_goto(LOCK_PREFIX " decl %0\n"
+ " jns %l[exit]\n"
+ : : "m" (v->counter)
+ : "memory", "cc"
+ : exit);
+ fail_fn(v);
+exit:
+ return;
+}
+#else
#define __mutex_fastpath_lock(v, fail_fn) \
do { \
unsigned long dummy; \
@@ -32,6 +46,7 @@ do { \
: "rax", "rsi", "rdx", "rcx", \
"r8", "r9", "r10", "r11", "memory"); \
} while (0)
+#endif
/**
* __mutex_fastpath_lock_retval - try to take the lock by moving the count
@@ -56,6 +71,20 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count)
*
* Atomically increments @v and calls <fail_fn> if the result is nonpositive.
*/
+#ifdef CC_HAVE_ASM_GOTO
+static inline void __mutex_fastpath_unlock(atomic_t *v,
+ void (*fail_fn)(atomic_t *))
+{
+ asm_volatile_goto(LOCK_PREFIX " incl %0\n"
+ " jg %l[exit]\n"
+ : : "m" (v->counter)
+ : "memory", "cc"
+ : exit);
+ fail_fn(v);
+exit:
+ return;
+}
+#else
#define __mutex_fastpath_unlock(v, fail_fn) \
do { \
unsigned long dummy; \
@@ -72,6 +101,7 @@ do { \
: "rax", "rsi", "rdx", "rcx", \
"r8", "r9", "r10", "r11", "memory"); \
} while (0)
+#endif
#define __mutex_slowpath_needs_to_unlock() 1
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index ef17af01347..f48b17df422 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -15,6 +15,8 @@
*/
#define __PAGE_OFFSET _AC(CONFIG_PAGE_OFFSET, UL)
+#define __START_KERNEL_map __PAGE_OFFSET
+
#define THREAD_SIZE_ORDER 1
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 6c896fbe21d..43dcd804ebd 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -32,11 +32,6 @@
*/
#define __PAGE_OFFSET _AC(0xffff880000000000, UL)
-#define __PHYSICAL_START ((CONFIG_PHYSICAL_START + \
- (CONFIG_PHYSICAL_ALIGN - 1)) & \
- ~(CONFIG_PHYSICAL_ALIGN - 1))
-
-#define __START_KERNEL (__START_KERNEL_map + __PHYSICAL_START)
#define __START_KERNEL_map _AC(0xffffffff80000000, UL)
/* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 54c97879195..f97fbe3abb6 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -33,6 +33,11 @@
(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define __PHYSICAL_START ALIGN(CONFIG_PHYSICAL_START, \
+ CONFIG_PHYSICAL_ALIGN)
+
+#define __START_KERNEL (__START_KERNEL_map + __PHYSICAL_START)
+
#ifdef CONFIG_X86_64
#include <asm/page_64_types.h>
#else
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index cfdc9ee4c90..401f350ef71 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,36 +712,16 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
#if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS)
-static inline int arch_spin_is_locked(struct arch_spinlock *lock)
+static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock,
+ __ticket_t ticket)
{
- return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
+ PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket);
}
-static inline int arch_spin_is_contended(struct arch_spinlock *lock)
+static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock,
+ __ticket_t ticket)
{
- return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
-}
-#define arch_spin_is_contended arch_spin_is_contended
-
-static __always_inline void arch_spin_lock(struct arch_spinlock *lock)
-{
- PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
-}
-
-static __always_inline void arch_spin_lock_flags(struct arch_spinlock *lock,
- unsigned long flags)
-{
- PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags);
-}
-
-static __always_inline int arch_spin_trylock(struct arch_spinlock *lock)
-{
- return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
-}
-
-static __always_inline void arch_spin_unlock(struct arch_spinlock *lock)
-{
- PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
+ PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket);
}
#endif
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0db1fcac668..aab8f671b52 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -327,13 +327,15 @@ struct pv_mmu_ops {
};
struct arch_spinlock;
+#ifdef CONFIG_SMP
+#include <asm/spinlock_types.h>
+#else
+typedef u16 __ticket_t;
+#endif
+
struct pv_lock_ops {
- int (*spin_is_locked)(struct arch_spinlock *lock);
- int (*spin_is_contended)(struct arch_spinlock *lock);
- void (*spin_lock)(struct arch_spinlock *lock);
- void (*spin_lock_flags)(struct arch_spinlock *lock, unsigned long flags);
- int (*spin_trylock)(struct arch_spinlock *lock);
- void (*spin_unlock)(struct arch_spinlock *lock);
+ struct paravirt_callee_save lock_spinning;
+ void (*unlock_kick)(struct arch_spinlock *lock, __ticket_t ticket);
};
/* This contains all the paravirt structures: we get a convenient
@@ -387,7 +389,8 @@ extern struct pv_lock_ops pv_lock_ops;
/* Simple instruction patching code. */
#define DEF_NATIVE(ops, name, code) \
- extern const char start_##ops##_##name[], end_##ops##_##name[]; \
+ extern const char start_##ops##_##name[] __visible, \
+ end_##ops##_##name[] __visible; \
asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
unsigned paravirt_patch_nop(void);
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index d9e9e6c7ed3..7d7443283a9 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -100,29 +100,6 @@ static inline void early_quirks(void) { }
extern void pci_iommu_alloc(void);
#ifdef CONFIG_PCI_MSI
-/* MSI arch specific hooks */
-static inline int x86_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
- return x86_msi.setup_msi_irqs(dev, nvec, type);
-}
-
-static inline void x86_teardown_msi_irqs(struct pci_dev *dev)
-{
- x86_msi.teardown_msi_irqs(dev);
-}
-
-static inline void x86_teardown_msi_irq(unsigned int irq)
-{
- x86_msi.teardown_msi_irq(irq);
-}
-static inline void x86_restore_msi_irqs(struct pci_dev *dev, int irq)
-{
- x86_msi.restore_msi_irqs(dev, irq);
-}
-#define arch_setup_msi_irqs x86_setup_msi_irqs
-#define arch_teardown_msi_irqs x86_teardown_msi_irqs
-#define arch_teardown_msi_irq x86_teardown_msi_irq
-#define arch_restore_msi_irqs x86_restore_msi_irqs
/* implemented in arch/x86/kernel/apic/io_apic. */
struct msi_desc;
int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
@@ -130,16 +107,9 @@ void native_teardown_msi_irq(unsigned int irq);
void native_restore_msi_irqs(struct pci_dev *dev, int irq);
int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
unsigned int irq_base, unsigned int irq_offset);
-/* default to the implementation in drivers/lib/msi.c */
-#define HAVE_DEFAULT_MSI_TEARDOWN_IRQS
-#define HAVE_DEFAULT_MSI_RESTORE_IRQS
-void default_teardown_msi_irqs(struct pci_dev *dev);
-void default_restore_msi_irqs(struct pci_dev *dev, int irq);
#else
#define native_setup_msi_irqs NULL
#define native_teardown_msi_irq NULL
-#define default_teardown_msi_irqs NULL
-#define default_restore_msi_irqs NULL
#endif
#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0da5200ee79..b3e18f80030 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -128,7 +128,8 @@ do { \
do { \
typedef typeof(var) pao_T__; \
const int pao_ID__ = (__builtin_constant_p(val) && \
- ((val) == 1 || (val) == -1)) ? (val) : 0; \
+ ((val) == 1 || (val) == -1)) ? \
+ (int)(val) : 0; \
if (0) { \
pao_T__ pao_tmp__; \
pao_tmp__ = (val); \
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1c00631164c..3d199945870 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -22,7 +22,8 @@
* ZERO_PAGE is a global shared page that is always zero: used
* for zero-mapped memory areas etc..
*/
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
+ __visible;
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
extern spinlock_t pgd_lock;
@@ -314,21 +315,6 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
}
-static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
-{
- return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
-}
-
-static inline int pte_swp_soft_dirty(pte_t pte)
-{
- return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
-}
-
-static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
-{
- return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
-}
-
static inline pte_t pte_file_clear_soft_dirty(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
@@ -445,6 +431,7 @@ pte_t *populate_extra_pte(unsigned long vaddr);
#ifndef __ASSEMBLY__
#include <linux/mm_types.h>
+#include <linux/mmdebug.h>
#include <linux/log2.h>
static inline int pte_none(pte_t pte)
@@ -863,6 +850,24 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
{
}
+static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
+{
+ VM_BUG_ON(pte_present(pte));
+ return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
+static inline int pte_swp_soft_dirty(pte_t pte)
+{
+ VM_BUG_ON(pte_present(pte));
+ return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
+}
+
+static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
+{
+ VM_BUG_ON(pte_present(pte));
+ return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
+}
+
#include <asm-generic/pgtable.h>
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index f4843e03113..0ecac257fb2 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -75,6 +75,9 @@
* with swap entry format. On x86 bits 6 and 7 are *not* involved
* into swap entry computation, but bit 6 is used for nonlinear
* file mapping, so we borrow bit 7 for soft dirty tracking.
+ *
+ * Please note that this bit must be treated as swap dirty page
+ * mark if and only if the PTE has present bit clear!
*/
#ifdef CONFIG_MEM_SOFT_DIRTY
#define _PAGE_SWP_SOFT_DIRTY _PAGE_PSE
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
new file mode 100644
index 00000000000..8729723636f
--- /dev/null
+++ b/arch/x86/include/asm/preempt.h
@@ -0,0 +1,100 @@
+#ifndef __ASM_PREEMPT_H
+#define __ASM_PREEMPT_H
+
+#include <asm/rmwcc.h>
+#include <asm/percpu.h>
+#include <linux/thread_info.h>
+
+DECLARE_PER_CPU(int, __preempt_count);
+
+/*
+ * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
+ * that think a non-zero value indicates we cannot preempt.
+ */
+static __always_inline int preempt_count(void)
+{
+ return __this_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
+}
+
+static __always_inline void preempt_count_set(int pc)
+{
+ __this_cpu_write_4(__preempt_count, pc);
+}
+
+/*
+ * must be macros to avoid header recursion hell
+ */
+#define task_preempt_count(p) \
+ (task_thread_info(p)->saved_preempt_count & ~PREEMPT_NEED_RESCHED)
+
+#define init_task_preempt_count(p) do { \
+ task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
+} while (0)
+
+#define init_idle_preempt_count(p, cpu) do { \
+ task_thread_info(p)->saved_preempt_count = PREEMPT_ENABLED; \
+ per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \
+} while (0)
+
+/*
+ * We fold the NEED_RESCHED bit into the preempt count such that
+ * preempt_enable() can decrement and test for needing to reschedule with a
+ * single instruction.
+ *
+ * We invert the actual bit, so that when the decrement hits 0 we know we both
+ * need to resched (the bit is cleared) and can resched (no preempt count).
+ */
+
+static __always_inline void set_preempt_need_resched(void)
+{
+ __this_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
+}
+
+static __always_inline void clear_preempt_need_resched(void)
+{
+ __this_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
+}
+
+static __always_inline bool test_preempt_need_resched(void)
+{
+ return !(__this_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
+}
+
+/*
+ * The various preempt_count add/sub methods
+ */
+
+static __always_inline void __preempt_count_add(int val)
+{
+ __this_cpu_add_4(__preempt_count, val);
+}
+
+static __always_inline void __preempt_count_sub(int val)
+{
+ __this_cpu_add_4(__preempt_count, -val);
+}
+
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+ GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
+}
+
+/*
+ * Returns true when we need to resched and can (barring IRQ state).
+ */
+static __always_inline bool should_resched(void)
+{
+ return unlikely(!__this_cpu_read_4(__preempt_count));
+}
+
+#ifdef CONFIG_PREEMPT
+ extern asmlinkage void ___preempt_schedule(void);
+# define __preempt_schedule() asm ("call ___preempt_schedule")
+ extern asmlinkage void preempt_schedule(void);
+# ifdef CONFIG_CONTEXT_TRACKING
+ extern asmlinkage void ___preempt_schedule_context(void);
+# define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
+# endif
+#endif
+
+#endif /* __ASM_PREEMPT_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 24cf5aefb70..987c75ecc33 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -412,7 +412,7 @@ union irq_stack_union {
};
};
-DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union);
+DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
DECLARE_INIT_PER_CPU(irq_stack_union);
DECLARE_PER_CPU(char *, irq_stack_ptr);
@@ -942,33 +942,19 @@ extern int set_tsc_mode(unsigned int val);
extern u16 amd_get_nb_id(int cpu);
-struct aperfmperf {
- u64 aperf, mperf;
-};
-
-static inline void get_aperfmperf(struct aperfmperf *am)
+static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
{
- WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_APERFMPERF));
-
- rdmsrl(MSR_IA32_APERF, am->aperf);
- rdmsrl(MSR_IA32_MPERF, am->mperf);
-}
+ uint32_t base, eax, signature[3];
-#define APERFMPERF_SHIFT 10
+ for (base = 0x40000000; base < 0x40010000; base += 0x100) {
+ cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
-static inline
-unsigned long calc_aperfmperf_ratio(struct aperfmperf *old,
- struct aperfmperf *new)
-{
- u64 aperf = new->aperf - old->aperf;
- u64 mperf = new->mperf - old->mperf;
- unsigned long ratio = aperf;
-
- mperf >>= APERFMPERF_SHIFT;
- if (mperf)
- ratio = div64_u64(aperf, mperf);
+ if (!memcmp(sig, signature, 12) &&
+ (leaves == 0 || ((eax - base) >= leaves)))
+ return base;
+ }
- return ratio;
+ return 0;
}
extern unsigned long arch_align_stack(unsigned long sp);
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 109a9dd5d45..be8269b00e2 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -93,7 +93,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
struct pvclock_vsyscall_time_info {
struct pvclock_vcpu_time_info pvti;
- u32 migrate_count;
} __attribute__((__aligned__(SMP_CACHE_BYTES)));
#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
new file mode 100644
index 00000000000..1ff990f1de8
--- /dev/null
+++ b/arch/x86/include/asm/rmwcc.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_X86_RMWcc
+#define _ASM_X86_RMWcc
+
+#ifdef CC_HAVE_ASM_GOTO
+
+#define __GEN_RMWcc(fullop, var, cc, ...) \
+do { \
+ asm_volatile_goto (fullop "; j" cc " %l[cc_label]" \
+ : : "m" (var), ## __VA_ARGS__ \
+ : "memory" : cc_label); \
+ return 0; \
+cc_label: \
+ return 1; \
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) \
+ __GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, val, arg0, cc) \
+ __GEN_RMWcc(op " %1, " arg0, var, cc, "er" (val))
+
+#else /* !CC_HAVE_ASM_GOTO */
+
+#define __GEN_RMWcc(fullop, var, cc, ...) \
+do { \
+ char c; \
+ asm volatile (fullop "; set" cc " %1" \
+ : "+m" (var), "=qm" (c) \
+ : __VA_ARGS__ : "memory"); \
+ return c != 0; \
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) \
+ __GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, val, arg0, cc) \
+ __GEN_RMWcc(op " %2, " arg0, var, cc, "er" (val))
+
+#endif /* CC_HAVE_ASM_GOTO */
+
+#endif /* _ASM_X86_RMWcc */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index b7bf3505e1e..59bcf4e2241 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -6,6 +6,8 @@
#define COMMAND_LINE_SIZE 2048
+#include <linux/linkage.h>
+
#ifdef __i386__
#include <linux/pfn.h>
@@ -49,9 +51,9 @@ extern void i386_reserve_resources(void);
extern void setup_default_timer_irq(void);
#ifdef CONFIG_X86_INTEL_MID
-extern void x86_mrst_early_setup(void);
+extern void x86_intel_mid_early_setup(void);
#else
-static inline void x86_mrst_early_setup(void) { }
+static inline void x86_intel_mid_early_setup(void) { }
#endif
#ifdef CONFIG_X86_INTEL_CE
@@ -108,11 +110,11 @@ void *extend_brk(size_t size, size_t align);
extern void probe_roms(void);
#ifdef __i386__
-void __init i386_start_kernel(void);
+asmlinkage void __init i386_start_kernel(void);
#else
-void __init x86_64_start_kernel(char *real_mode);
-void __init x86_64_start_reservations(char *real_mode_data);
+asmlinkage void __init x86_64_start_kernel(char *real_mode);
+asmlinkage void __init x86_64_start_reservations(char *real_mode_data);
#endif /* __i386__ */
#endif /* _SETUP */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 2f4d924fe6c..645cad2c95f 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -101,7 +101,7 @@ static inline void native_wbinvd(void)
asm volatile("wbinvd": : :"memory");
}
-extern void native_load_gs_index(unsigned);
+extern asmlinkage void native_load_gs_index(unsigned);
#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index e3ddd7db723..bf156ded74b 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -1,11 +1,14 @@
#ifndef _ASM_X86_SPINLOCK_H
#define _ASM_X86_SPINLOCK_H
+#include <linux/jump_label.h>
#include <linux/atomic.h>
#include <asm/page.h>
#include <asm/processor.h>
#include <linux/compiler.h>
#include <asm/paravirt.h>
+#include <asm/bitops.h>
+
/*
* Your basic SMP spinlocks, allowing only a single CPU anywhere
*
@@ -34,6 +37,36 @@
# define UNLOCK_LOCK_PREFIX
#endif
+/* How long a lock should spin before we consider blocking */
+#define SPIN_THRESHOLD (1 << 15)
+
+extern struct static_key paravirt_ticketlocks_enabled;
+static __always_inline bool static_key_false(struct static_key *key);
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+
+static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
+{
+ set_bit(0, (volatile unsigned long *)&lock->tickets.tail);
+}
+
+#else /* !CONFIG_PARAVIRT_SPINLOCKS */
+static __always_inline void __ticket_lock_spinning(arch_spinlock_t *lock,
+ __ticket_t ticket)
+{
+}
+static inline void __ticket_unlock_kick(arch_spinlock_t *lock,
+ __ticket_t ticket)
+{
+}
+
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+ return lock.tickets.head == lock.tickets.tail;
+}
+
/*
* Ticket locks are conceptually two parts, one indicating the current head of
* the queue, and the other indicating the current tail. The lock is acquired
@@ -47,81 +80,101 @@
* in the high part, because a wide xadd increment of the low part would carry
* up and contaminate the high part.
*/
-static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
+static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
{
- register struct __raw_tickets inc = { .tail = 1 };
+ register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC };
inc = xadd(&lock->tickets, inc);
+ if (likely(inc.head == inc.tail))
+ goto out;
+ inc.tail &= ~TICKET_SLOWPATH_FLAG;
for (;;) {
- if (inc.head == inc.tail)
- break;
- cpu_relax();
- inc.head = ACCESS_ONCE(lock->tickets.head);
+ unsigned count = SPIN_THRESHOLD;
+
+ do {
+ if (ACCESS_ONCE(lock->tickets.head) == inc.tail)
+ goto out;
+ cpu_relax();
+ } while (--count);
+ __ticket_lock_spinning(lock, inc.tail);
}
- barrier(); /* make sure nothing creeps before the lock is taken */
+out: barrier(); /* make sure nothing creeps before the lock is taken */
}
-static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
+static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
{
arch_spinlock_t old, new;
old.tickets = ACCESS_ONCE(lock->tickets);
- if (old.tickets.head != old.tickets.tail)
+ if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG))
return 0;
- new.head_tail = old.head_tail + (1 << TICKET_SHIFT);
+ new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT);
/* cmpxchg is a full barrier, so nothing can move before it */
return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail;
}
-static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
+static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock,
+ arch_spinlock_t old)
{
- __add(&lock->tickets.head, 1, UNLOCK_LOCK_PREFIX);
+ arch_spinlock_t new;
+
+ BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
+
+ /* Perform the unlock on the "before" copy */
+ old.tickets.head += TICKET_LOCK_INC;
+
+ /* Clear the slowpath flag */
+ new.head_tail = old.head_tail & ~(TICKET_SLOWPATH_FLAG << TICKET_SHIFT);
+
+ /*
+ * If the lock is uncontended, clear the flag - use cmpxchg in
+ * case it changes behind our back though.
+ */
+ if (new.tickets.head != new.tickets.tail ||
+ cmpxchg(&lock->head_tail, old.head_tail,
+ new.head_tail) != old.head_tail) {
+ /*
+ * Lock still has someone queued for it, so wake up an
+ * appropriate waiter.
+ */
+ __ticket_unlock_kick(lock, old.tickets.head);
+ }
}
-static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
+static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
{
- struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+ if (TICKET_SLOWPATH_FLAG &&
+ static_key_false(&paravirt_ticketlocks_enabled)) {
+ arch_spinlock_t prev;
- return tmp.tail != tmp.head;
-}
+ prev = *lock;
+ add_smp(&lock->tickets.head, TICKET_LOCK_INC);
-static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
-{
- struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
+ /* add_smp() is a full mb() */
- return (__ticket_t)(tmp.tail - tmp.head) > 1;
+ if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
+ __ticket_unlock_slowpath(lock, prev);
+ } else
+ __add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX);
}
-#ifndef CONFIG_PARAVIRT_SPINLOCKS
-
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
- return __ticket_spin_is_locked(lock);
-}
-
-static inline int arch_spin_is_contended(arch_spinlock_t *lock)
-{
- return __ticket_spin_is_contended(lock);
-}
-#define arch_spin_is_contended arch_spin_is_contended
+ struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
-static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
-{
- __ticket_spin_lock(lock);
+ return tmp.tail != tmp.head;
}
-static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
{
- return __ticket_spin_trylock(lock);
-}
+ struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
-static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
- __ticket_spin_unlock(lock);
+ return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
}
+#define arch_spin_is_contended arch_spin_is_contended
static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
unsigned long flags)
@@ -129,8 +182,6 @@ static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
arch_spin_lock(lock);
}
-#endif /* CONFIG_PARAVIRT_SPINLOCKS */
-
static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
while (arch_spin_is_locked(lock))
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index ad0ad07fc00..4f1bea19945 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -1,13 +1,17 @@
#ifndef _ASM_X86_SPINLOCK_TYPES_H
#define _ASM_X86_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
#include <linux/types.h>
-#if (CONFIG_NR_CPUS < 256)
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#define __TICKET_LOCK_INC 2
+#define TICKET_SLOWPATH_FLAG ((__ticket_t)1)
+#else
+#define __TICKET_LOCK_INC 1
+#define TICKET_SLOWPATH_FLAG ((__ticket_t)0)
+#endif
+
+#if (CONFIG_NR_CPUS < (256 / __TICKET_LOCK_INC))
typedef u8 __ticket_t;
typedef u16 __ticketpair_t;
#else
@@ -15,6 +19,8 @@ typedef u16 __ticket_t;
typedef u32 __ticketpair_t;
#endif
+#define TICKET_LOCK_INC ((__ticket_t)__TICKET_LOCK_INC)
+
#define TICKET_SHIFT (sizeof(__ticket_t) * 8)
typedef struct arch_spinlock {
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 4ec45b3abba..d7f3b3b78ac 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -2,8 +2,8 @@
#define _ASM_X86_SWITCH_TO_H
struct task_struct; /* one of the stranger aspects of C forward declarations */
-struct task_struct *__switch_to(struct task_struct *prev,
- struct task_struct *next);
+__visible struct task_struct *__switch_to(struct task_struct *prev,
+ struct task_struct *next);
struct tss_struct;
void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
struct tss_struct *tss);
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index 9d09b4073b6..05af3b31d52 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -26,9 +26,9 @@
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
-static inline void sync_set_bit(int nr, volatile unsigned long *addr)
+static inline void sync_set_bit(long nr, volatile unsigned long *addr)
{
- asm volatile("lock; btsl %1,%0"
+ asm volatile("lock; bts %1,%0"
: "+m" (ADDR)
: "Ir" (nr)
: "memory");
@@ -44,9 +44,9 @@ static inline void sync_set_bit(int nr, volatile unsigned long *addr)
* you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
* in order to ensure changes are visible on other processors.
*/
-static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
+static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
{
- asm volatile("lock; btrl %1,%0"
+ asm volatile("lock; btr %1,%0"
: "+m" (ADDR)
: "Ir" (nr)
: "memory");
@@ -61,9 +61,9 @@ static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
* Note that @nr may be almost arbitrarily large; this function is not
* restricted to acting on a single-word quantity.
*/
-static inline void sync_change_bit(int nr, volatile unsigned long *addr)
+static inline void sync_change_bit(long nr, volatile unsigned long *addr)
{
- asm volatile("lock; btcl %1,%0"
+ asm volatile("lock; btc %1,%0"
: "+m" (ADDR)
: "Ir" (nr)
: "memory");
@@ -77,11 +77,11 @@ static inline void sync_change_bit(int nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
- asm volatile("lock; btsl %2,%1\n\tsbbl %0,%0"
+ asm volatile("lock; bts %2,%1\n\tsbbl %0,%0"
: "=r" (oldbit), "+m" (ADDR)
: "Ir" (nr) : "memory");
return oldbit;
@@ -95,11 +95,11 @@ static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
- asm volatile("lock; btrl %2,%1\n\tsbbl %0,%0"
+ asm volatile("lock; btr %2,%1\n\tsbbl %0,%0"
: "=r" (oldbit), "+m" (ADDR)
: "Ir" (nr) : "memory");
return oldbit;
@@ -113,11 +113,11 @@ static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
* This operation is atomic and cannot be reordered.
* It also implies a memory barrier.
*/
-static inline int sync_test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
{
int oldbit;
- asm volatile("lock; btcl %2,%1\n\tsbbl %0,%0"
+ asm volatile("lock; btc %2,%1\n\tsbbl %0,%0"
: "=r" (oldbit), "+m" (ADDR)
: "Ir" (nr) : "memory");
return oldbit;
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 2e188d68397..aea284b4131 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -20,7 +20,8 @@
#include <asm/thread_info.h> /* for TS_COMPAT */
#include <asm/unistd.h>
-extern const unsigned long sys_call_table[];
+typedef void (*sys_call_ptr_t)(void);
+extern const sys_call_ptr_t sys_call_table[];
/*
* Only the low 32 bits of orig_ax are meaningful, so we return int.
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 2917a6452c4..592a6a672e0 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -24,7 +24,7 @@ asmlinkage long sys_iopl(unsigned int);
asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
/* kernel/signal.c */
-long sys_rt_sigreturn(void);
+asmlinkage long sys_rt_sigreturn(void);
/* kernel/tls.c */
asmlinkage long sys_set_thread_area(struct user_desc __user *);
@@ -34,7 +34,7 @@ asmlinkage long sys_get_thread_area(struct user_desc __user *);
#ifdef CONFIG_X86_32
/* kernel/signal.c */
-unsigned long sys_sigreturn(void);
+asmlinkage unsigned long sys_sigreturn(void);
/* kernel/vm86_32.c */
asmlinkage long sys_vm86old(struct vm86_struct __user *);
@@ -44,7 +44,7 @@ asmlinkage long sys_vm86(unsigned long, unsigned long);
/* X86_64 only */
/* kernel/process_64.c */
-long sys_arch_prctl(int, unsigned long);
+asmlinkage long sys_arch_prctl(int, unsigned long);
/* kernel/sys_x86_64.c */
asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
diff --git a/arch/x86/include/asm/sysfb.h b/arch/x86/include/asm/sysfb.h
new file mode 100644
index 00000000000..2aeb3e25579
--- /dev/null
+++ b/arch/x86/include/asm/sysfb.h
@@ -0,0 +1,98 @@
+#ifndef _ARCH_X86_KERNEL_SYSFB_H
+#define _ARCH_X86_KERNEL_SYSFB_H
+
+/*
+ * Generic System Framebuffers on x86
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/screen_info.h>
+
+enum {
+ M_I17, /* 17-Inch iMac */
+ M_I20, /* 20-Inch iMac */
+ M_I20_SR, /* 20-Inch iMac (Santa Rosa) */
+ M_I24, /* 24-Inch iMac */
+ M_I24_8_1, /* 24-Inch iMac, 8,1th gen */
+ M_I24_10_1, /* 24-Inch iMac, 10,1th gen */
+ M_I27_11_1, /* 27-Inch iMac, 11,1th gen */
+ M_MINI, /* Mac Mini */
+ M_MINI_3_1, /* Mac Mini, 3,1th gen */
+ M_MINI_4_1, /* Mac Mini, 4,1th gen */
+ M_MB, /* MacBook */
+ M_MB_2, /* MacBook, 2nd rev. */
+ M_MB_3, /* MacBook, 3rd rev. */
+ M_MB_5_1, /* MacBook, 5th rev. */
+ M_MB_6_1, /* MacBook, 6th rev. */
+ M_MB_7_1, /* MacBook, 7th rev. */
+ M_MB_SR, /* MacBook, 2nd gen, (Santa Rosa) */
+ M_MBA, /* MacBook Air */
+ M_MBA_3, /* Macbook Air, 3rd rev */
+ M_MBP, /* MacBook Pro */
+ M_MBP_2, /* MacBook Pro 2nd gen */
+ M_MBP_2_2, /* MacBook Pro 2,2nd gen */
+ M_MBP_SR, /* MacBook Pro (Santa Rosa) */
+ M_MBP_4, /* MacBook Pro, 4th gen */
+ M_MBP_5_1, /* MacBook Pro, 5,1th gen */
+ M_MBP_5_2, /* MacBook Pro, 5,2th gen */
+ M_MBP_5_3, /* MacBook Pro, 5,3rd gen */
+ M_MBP_6_1, /* MacBook Pro, 6,1th gen */
+ M_MBP_6_2, /* MacBook Pro, 6,2th gen */
+ M_MBP_7_1, /* MacBook Pro, 7,1th gen */
+ M_MBP_8_2, /* MacBook Pro, 8,2nd gen */
+ M_UNKNOWN /* placeholder */
+};
+
+struct efifb_dmi_info {
+ char *optname;
+ unsigned long base;
+ int stride;
+ int width;
+ int height;
+ int flags;
+};
+
+#ifdef CONFIG_EFI
+
+extern struct efifb_dmi_info efifb_dmi_list[];
+void sysfb_apply_efi_quirks(void);
+
+#else /* CONFIG_EFI */
+
+static inline void sysfb_apply_efi_quirks(void)
+{
+}
+
+#endif /* CONFIG_EFI */
+
+#ifdef CONFIG_X86_SYSFB
+
+bool parse_mode(const struct screen_info *si,
+ struct simplefb_platform_data *mode);
+int create_simplefb(const struct screen_info *si,
+ const struct simplefb_platform_data *mode);
+
+#else /* CONFIG_X86_SYSFB */
+
+static inline bool parse_mode(const struct screen_info *si,
+ struct simplefb_platform_data *mode)
+{
+ return false;
+}
+
+static inline int create_simplefb(const struct screen_info *si,
+ const struct simplefb_platform_data *mode)
+{
+ return -EINVAL;
+}
+
+#endif /* CONFIG_X86_SYSFB */
+
+#endif /* _ARCH_X86_KERNEL_SYSFB_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 27811190cbd..c46a46be1ec 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -28,8 +28,7 @@ struct thread_info {
__u32 flags; /* low level flags */
__u32 status; /* thread synchronous flags */
__u32 cpu; /* current CPU */
- int preempt_count; /* 0 => preemptable,
- <0 => BUG */
+ int saved_preempt_count;
mm_segment_t addr_limit;
struct restart_block restart_block;
void __user *sysenter_return;
@@ -49,7 +48,7 @@ struct thread_info {
.exec_domain = &default_exec_domain, \
.flags = 0, \
.cpu = 0, \
- .preempt_count = INIT_PREEMPT_COUNT, \
+ .saved_preempt_count = INIT_PREEMPT_COUNT, \
.addr_limit = KERNEL_DS, \
.restart_block = { \
.fn = do_no_restart_syscall, \
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cf512003e66..e6d90babc24 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -62,6 +62,7 @@ static inline void __flush_tlb_all(void)
static inline void __flush_tlb_one(unsigned long addr)
{
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
}
@@ -84,14 +85,38 @@ static inline void __flush_tlb_one(unsigned long addr)
#ifndef CONFIG_SMP
-#define flush_tlb() __flush_tlb()
-#define flush_tlb_all() __flush_tlb_all()
-#define local_flush_tlb() __flush_tlb()
+/* "_up" is for UniProcessor.
+ *
+ * This is a helper for other header functions. *Not* intended to be called
+ * directly. All global TLB flushes need to either call this, or to bump the
+ * vm statistics themselves.
+ */
+static inline void __flush_tlb_up(void)
+{
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+ __flush_tlb();
+}
+
+static inline void flush_tlb_all(void)
+{
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
+ __flush_tlb_all();
+}
+
+static inline void flush_tlb(void)
+{
+ __flush_tlb_up();
+}
+
+static inline void local_flush_tlb(void)
+{
+ __flush_tlb_up();
+}
static inline void flush_tlb_mm(struct mm_struct *mm)
{
if (mm == current->active_mm)
- __flush_tlb();
+ __flush_tlb_up();
}
static inline void flush_tlb_page(struct vm_area_struct *vma,
@@ -105,14 +130,14 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
if (vma->vm_mm == current->active_mm)
- __flush_tlb();
+ __flush_tlb_up();
}
static inline void flush_tlb_mm_range(struct mm_struct *mm,
unsigned long start, unsigned long end, unsigned long vmflag)
{
if (mm == current->active_mm)
- __flush_tlb();
+ __flush_tlb_up();
}
static inline void native_flush_tlb_others(const struct cpumask *cpumask,
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 095b21507b6..d35f24e231c 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -124,9 +124,6 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
-
-/* indicates that pointers to the topology cpumask_t maps are valid */
-#define arch_provides_topology_pointers yes
#endif
static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 88eae2aec61..7036cb60cd8 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -6,11 +6,7 @@
#include <asm/debugreg.h>
#include <asm/siginfo.h> /* TRAP_TRACE, ... */
-#ifdef CONFIG_X86_32
-#define dotraplinkage
-#else
-#define dotraplinkage asmlinkage
-#endif
+#define dotraplinkage __visible
asmlinkage void divide_error(void);
asmlinkage void debug(void);
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index c91e8b9d588..235be70d5bb 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -49,6 +49,7 @@ extern void tsc_init(void);
extern void mark_tsc_unstable(char *reason);
extern int unsynchronized_tsc(void);
extern int check_tsc_unstable(void);
+extern int check_tsc_disabled(void);
extern unsigned long native_calibrate_tsc(void);
extern int tsc_clocksource_reliable;
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5ee26875bae..8ec57c07b12 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -153,16 +153,19 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
* Careful: we have to cast the result to the type of the pointer
* for sign reasons.
*
- * The use of %edx as the register specifier is a bit of a
+ * The use of _ASM_DX as the register specifier is a bit of a
* simplification, as gcc only cares about it as the starting point
* and not size: for a 64-bit value it will use %ecx:%edx on 32 bits
* (%ecx being the next register in gcc's x86 register sequence), and
* %rdx on 64 bits.
+ *
+ * Clang/LLVM cares about the size of the register, but still wants
+ * the base register for something that ends up being a pair.
*/
#define get_user(x, ptr) \
({ \
int __ret_gu; \
- register __inttype(*(ptr)) __val_gu asm("%edx"); \
+ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \
__chk_user_ptr(ptr); \
might_fault(); \
asm volatile("call __get_user_%P3" \
@@ -539,5 +542,103 @@ extern struct movsl_mask {
# include <asm/uaccess_64.h>
#endif
+unsigned long __must_check _copy_from_user(void *to, const void __user *from,
+ unsigned n);
+unsigned long __must_check _copy_to_user(void __user *to, const void *from,
+ unsigned n);
+
+#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
+# define copy_user_diag __compiletime_error
+#else
+# define copy_user_diag __compiletime_warning
+#endif
+
+extern void copy_user_diag("copy_from_user() buffer size is too small")
+copy_from_user_overflow(void);
+extern void copy_user_diag("copy_to_user() buffer size is too small")
+copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
+
+#undef copy_user_diag
+
+#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
+
+extern void
+__compiletime_warning("copy_from_user() buffer size is not provably correct")
+__copy_from_user_overflow(void) __asm__("copy_from_user_overflow");
+#define __copy_from_user_overflow(size, count) __copy_from_user_overflow()
+
+extern void
+__compiletime_warning("copy_to_user() buffer size is not provably correct")
+__copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
+#define __copy_to_user_overflow(size, count) __copy_to_user_overflow()
+
+#else
+
+static inline void
+__copy_from_user_overflow(int size, unsigned long count)
+{
+ WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
+
+#define __copy_to_user_overflow __copy_from_user_overflow
+
+#endif
+
+static inline unsigned long __must_check
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+ int sz = __compiletime_object_size(to);
+
+ might_fault();
+
+ /*
+ * While we would like to have the compiler do the checking for us
+ * even in the non-constant size case, any false positives there are
+ * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even
+ * without - the [hopefully] dangerous looking nature of the warning
+ * would make people go look at the respecitive call sites over and
+ * over again just to find that there's no problem).
+ *
+ * And there are cases where it's just not realistic for the compiler
+ * to prove the count to be in range. For example when multiple call
+ * sites of a helper function - perhaps in different source files -
+ * all doing proper range checking, yet the helper function not doing
+ * so again.
+ *
+ * Therefore limit the compile time checking to the constant size
+ * case, and do only runtime checking for non-constant sizes.
+ */
+
+ if (likely(sz < 0 || sz >= n))
+ n = _copy_from_user(to, from, n);
+ else if(__builtin_constant_p(n))
+ copy_from_user_overflow();
+ else
+ __copy_from_user_overflow(sz, n);
+
+ return n;
+}
+
+static inline unsigned long __must_check
+copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+ int sz = __compiletime_object_size(from);
+
+ might_fault();
+
+ /* See the comment in copy_from_user() above. */
+ if (likely(sz < 0 || sz >= n))
+ n = _copy_to_user(to, from, n);
+ else if(__builtin_constant_p(n))
+ copy_to_user_overflow();
+ else
+ __copy_to_user_overflow(sz, n);
+
+ return n;
+}
+
+#undef __copy_from_user_overflow
+#undef __copy_to_user_overflow
+
#endif /* _ASM_X86_UACCESS_H */
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 7f760a9f1f6..3c03a5de64d 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -184,33 +184,4 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from,
return __copy_from_user_ll_nocache_nozero(to, from, n);
}
-unsigned long __must_check copy_to_user(void __user *to,
- const void *from, unsigned long n);
-unsigned long __must_check _copy_from_user(void *to,
- const void __user *from,
- unsigned long n);
-
-
-extern void copy_from_user_overflow(void)
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
- __compiletime_error("copy_from_user() buffer size is not provably correct")
-#else
- __compiletime_warning("copy_from_user() buffer size is not provably correct")
-#endif
-;
-
-static inline unsigned long __must_check copy_from_user(void *to,
- const void __user *from,
- unsigned long n)
-{
- int sz = __compiletime_object_size(to);
-
- if (likely(sz == -1 || sz >= n))
- n = _copy_from_user(to, from, n);
- else
- copy_from_user_overflow();
-
- return n;
-}
-
#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 64476bb2a14..190413d0de5 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -46,36 +46,8 @@ copy_user_generic(void *to, const void *from, unsigned len)
}
__must_check unsigned long
-_copy_to_user(void __user *to, const void *from, unsigned len);
-__must_check unsigned long
-_copy_from_user(void *to, const void __user *from, unsigned len);
-__must_check unsigned long
copy_in_user(void __user *to, const void __user *from, unsigned len);
-static inline unsigned long __must_check copy_from_user(void *to,
- const void __user *from,
- unsigned long n)
-{
- int sz = __compiletime_object_size(to);
-
- might_fault();
- if (likely(sz == -1 || sz >= n))
- n = _copy_from_user(to, from, n);
-#ifdef CONFIG_DEBUG_VM
- else
- WARN(1, "Buffer overflow detected!\n");
-#endif
- return n;
-}
-
-static __always_inline __must_check
-int copy_to_user(void __user *dst, const void *src, unsigned size)
-{
- might_fault();
-
- return _copy_to_user(dst, src, size);
-}
-
static __always_inline __must_check
int __copy_from_user_nocheck(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 6e5197910fd..3087ea9c5f2 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -35,7 +35,10 @@ typedef u8 uprobe_opcode_t;
struct arch_uprobe {
u16 fixups;
- u8 insn[MAX_UINSN_BYTES];
+ union {
+ u8 insn[MAX_UINSN_BYTES];
+ u8 ixol[MAX_UINSN_BYTES];
+ };
#ifdef CONFIG_X86_64
unsigned long rip_rela_target_address;
#endif
@@ -49,11 +52,4 @@ struct arch_uprobe_task {
unsigned int saved_tf;
};
-extern int arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr);
-extern int arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern int arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
-extern int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
-extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
#endif /* _ASM_UPROBES_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index f3e01a2cbaa..966502d4682 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -387,6 +387,7 @@ enum vmcs_field {
#define VMX_EPT_EXTENT_INDIVIDUAL_ADDR 0
#define VMX_EPT_EXTENT_CONTEXT 1
#define VMX_EPT_EXTENT_GLOBAL 2
+#define VMX_EPT_EXTENT_SHIFT 24
#define VMX_EPT_EXECUTE_ONLY_BIT (1ull)
#define VMX_EPT_PAGE_WALK_4_BIT (1ull << 6)
@@ -394,6 +395,7 @@ enum vmcs_field {
#define VMX_EPTP_WB_BIT (1ull << 14)
#define VMX_EPT_2MB_PAGE_BIT (1ull << 16)
#define VMX_EPT_1GB_PAGE_BIT (1ull << 17)
+#define VMX_EPT_INVEPT_BIT (1ull << 20)
#define VMX_EPT_AD_BIT (1ull << 21)
#define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25)
#define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26)
diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h
index de656ac2af4..d76ac40da20 100644
--- a/arch/x86/include/asm/vvar.h
+++ b/arch/x86/include/asm/vvar.h
@@ -35,7 +35,7 @@
#define DEFINE_VVAR(type, name) \
type name \
- __attribute__((section(".vvar_" #name), aligned(16)))
+ __attribute__((section(".vvar_" #name), aligned(16))) __visible
#define VVAR(name) (*vvaraddr_ ## name)
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
index ca842f2769e..608a79d5a46 100644
--- a/arch/x86/include/asm/xen/events.h
+++ b/arch/x86/include/asm/xen/events.h
@@ -7,6 +7,7 @@ enum ipi_vector {
XEN_CALL_FUNCTION_SINGLE_VECTOR,
XEN_SPIN_UNLOCK_VECTOR,
XEN_IRQ_WORK_VECTOR,
+ XEN_NMI_VECTOR,
XEN_NR_IPIS,
};
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 125f344f06a..d866959e568 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -40,21 +40,7 @@ extern struct start_info *xen_start_info;
static inline uint32_t xen_cpuid_base(void)
{
- uint32_t base, eax, ebx, ecx, edx;
- char signature[13];
-
- for (base = 0x40000000; base < 0x40010000; base += 0x100) {
- cpuid(base, &eax, &ebx, &ecx, &edx);
- *(uint32_t *)(signature + 0) = ebx;
- *(uint32_t *)(signature + 4) = ecx;
- *(uint32_t *)(signature + 8) = edx;
- signature[12] = 0;
-
- if (!strcmp("XenVMMXenVMM", signature) && ((eax - base) >= 2))
- return base;
- }
-
- return 0;
+ return hypervisor_cpuid_base("XenVMMXenVMM", 2);
}
#ifdef CONFIG_XEN
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 6aef9fbc09b..b913915e8e6 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
}
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
{
unsigned long pfn;
- int ret = 0;
+ int ret;
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
- if (unlikely(mfn >= machine_to_phys_nr)) {
- pfn = ~0;
- goto try_override;
- }
- pfn = 0;
+ if (unlikely(mfn >= machine_to_phys_nr))
+ return ~0;
+
/*
* The array access can fail (e.g., device space beyond end of RAM).
* In such cases it doesn't matter what we return (we return garbage),
* but we must handle the fault without crashing!
*/
ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-try_override:
- /* ret might be < 0 if there are no entries in the m2p for mfn */
if (ret < 0)
- pfn = ~0;
- else if (get_phys_to_machine(pfn) != mfn)
+ return ~0;
+
+ return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+ unsigned long pfn;
+
+ if (xen_feature(XENFEAT_auto_translated_physmap))
+ return mfn;
+
+ pfn = mfn_to_pfn_no_overrides(mfn);
+ if (get_phys_to_machine(pfn) != mfn) {
/*
* If this appears to be a foreign mfn (because the pfn
* doesn't map back to the mfn), then check the local override
@@ -111,6 +119,7 @@ try_override:
* m2p_find_override_pfn returns ~0 if it doesn't find anything.
*/
pfn = m2p_find_override_pfn(mfn, ~0);
+ }
/*
* pfn is ~0 if there are no entries in the m2p for mfn or if the
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 7ea79c5fa1f..492b29802f5 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = {
#define AVX_XOR_SPEED \
do { \
- if (cpu_has_avx) \
+ if (cpu_has_avx && cpu_has_osxsave) \
xor_speed(&xor_block_avx); \
} while (0)
#define AVX_SELECT(FASTEST) \
- (cpu_has_avx ? &xor_block_avx : FASTEST)
+ (cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST)
#else
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index c15ddaf9071..9c3733c5f8f 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -158,7 +158,7 @@ enum {
X86_SUBARCH_PC = 0,
X86_SUBARCH_LGUEST,
X86_SUBARCH_XEN,
- X86_SUBARCH_MRST,
+ X86_SUBARCH_INTEL_MID,
X86_SUBARCH_CE4100,
X86_NR_SUBARCHS,
};
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index b80420bcd09..b8f1c0176cb 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -27,6 +27,19 @@
#define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0)
/* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1)
+
+/*
+ * There is a single feature flag that signifies the presence of the MSR
+ * that can be used to retrieve both the local APIC Timer frequency as
+ * well as the TSC frequency.
+ */
+
+/* Local APIC timer frequency MSR (HV_X64_MSR_APIC_FREQUENCY) is available */
+#define HV_X64_MSR_APIC_FREQUENCY_AVAILABLE (1 << 11)
+
+/* TSC frequency MSR (HV_X64_MSR_TSC_FREQUENCY) is available */
+#define HV_X64_MSR_TSC_FREQUENCY_AVAILABLE (1 << 11)
+
/*
* Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
* and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
@@ -136,6 +149,12 @@
/* MSR used to read the per-partition time reference counter */
#define HV_X64_MSR_TIME_REF_COUNT 0x40000020
+/* MSR used to retrieve the TSC frequency */
+#define HV_X64_MSR_TSC_FREQUENCY 0x40000022
+
+/* MSR used to retrieve the local APIC timer frequency */
+#define HV_X64_MSR_APIC_FREQUENCY 0x40000023
+
/* Define the virtual APIC registers */
#define HV_X64_MSR_EOI 0x40000070
#define HV_X64_MSR_ICR 0x40000071
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 06fdbd987e9..94dc8ca434e 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -23,6 +23,7 @@
#define KVM_FEATURE_ASYNC_PF 4
#define KVM_FEATURE_STEAL_TIME 5
#define KVM_FEATURE_PV_EOI 6
+#define KVM_FEATURE_PV_UNHALT 7
/* The last 8 bits are used to indicate how to interpret the flags field
* in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index d651082c7cf..0e79420376e 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,7 @@
#define EXIT_REASON_EOI_INDUCED 45
#define EXIT_REASON_EPT_VIOLATION 48
#define EXIT_REASON_EPT_MISCONFIG 49
+#define EXIT_REASON_INVEPT 50
#define EXIT_REASON_PREEMPTION_TIMER 52
#define EXIT_REASON_WBINVD 54
#define EXIT_REASON_XSETBV 55
@@ -106,12 +107,13 @@
{ EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
{ EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
{ EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
+ { EXIT_REASON_INVEPT, "INVEPT" }, \
+ { EXIT_REASON_PREEMPTION_TIMER, "PREEMPTION_TIMER" }, \
{ EXIT_REASON_WBINVD, "WBINVD" }, \
{ EXIT_REASON_APIC_WRITE, "APIC_WRITE" }, \
{ EXIT_REASON_EOI_INDUCED, "EOI_INDUCED" }, \
{ EXIT_REASON_INVALID_STATE, "INVALID_STATE" }, \
{ EXIT_REASON_INVD, "INVD" }, \
- { EXIT_REASON_INVPCID, "INVPCID" }, \
- { EXIT_REASON_PREEMPTION_TIMER, "PREEMPTION_TIMER" }
+ { EXIT_REASON_INVPCID, "INVPCID" }
#endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 88d99ea7772..9b0a34e2cd7 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -36,6 +36,8 @@ obj-y += tsc.o io_delay.o rtc.o
obj-y += pci-iommu_table.o
obj-y += resource.o
+obj-$(CONFIG_PREEMPT) += preempt.o
+
obj-y += process.o
obj-y += i387.o xsave.o
obj-y += ptrace.o
@@ -103,6 +105,9 @@ obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
obj-$(CONFIG_SWIOTLB) += pci-swiotlb.o
obj-$(CONFIG_OF) += devicetree.o
obj-$(CONFIG_UPROBES) += uprobes.o
+obj-y += sysfb.o
+obj-$(CONFIG_X86_SYSFB) += sysfb_simplefb.o
+obj-$(CONFIG_EFI) += sysfb_efi.o
obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
obj-$(CONFIG_TRACING) += tracepoint.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 2627a81253e..40c76604199 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -67,6 +67,7 @@ EXPORT_SYMBOL(acpi_pci_disabled);
int acpi_lapic;
int acpi_ioapic;
int acpi_strict;
+int acpi_disable_cmcff;
u8 acpi_sci_flags __initdata;
int acpi_sci_override_gsi __initdata;
@@ -141,16 +142,8 @@ static u32 irq_to_gsi(int irq)
}
/*
- * Temporarily use the virtual area starting from FIX_IO_APIC_BASE_END,
- * to map the target physical address. The problem is that set_fixmap()
- * provides a single page, and it is possible that the page is not
- * sufficient.
- * By using this area, we can map up to MAX_IO_APICS pages temporarily,
- * i.e. until the next __va_range() call.
- *
- * Important Safety Note: The fixed I/O APIC page numbers are *subtracted*
- * from the fixed base. That's why we start at FIX_IO_APIC_BASE_END and
- * count idx down while incrementing the phys address.
+ * This is just a simple wrapper around early_ioremap(),
+ * with sanity checks for phys == 0 and size == 0.
*/
char *__init __acpi_map_table(unsigned long phys, unsigned long size)
{
@@ -160,6 +153,7 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
return early_ioremap(phys, size);
}
+
void __init __acpi_unmap_table(char *map, unsigned long size)
{
if (!map || !size)
@@ -199,7 +193,7 @@ static void acpi_register_lapic(int id, u8 enabled)
{
unsigned int ver = 0;
- if (id >= (MAX_LOCAL_APIC-1)) {
+ if (id >= MAX_LOCAL_APIC) {
printk(KERN_INFO PREFIX "skipped apicid that is too big\n");
return;
}
@@ -1120,6 +1114,7 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
int ioapic;
int ioapic_pin;
struct io_apic_irq_attr irq_attr;
+ int ret;
if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
return gsi;
@@ -1149,7 +1144,9 @@ int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
- io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr);
+ ret = io_apic_set_pci_routing(dev, gsi_to_irq(gsi), &irq_attr);
+ if (ret < 0)
+ gsi = INT_MIN;
return gsi;
}
@@ -1626,6 +1623,10 @@ static int __init parse_acpi(char *arg)
/* "acpi=copy_dsdt" copys DSDT */
else if (strcmp(arg, "copy_dsdt") == 0) {
acpi_gbl_copy_dsdt_locally = 1;
+ }
+ /* "acpi=nocmcff" disables FF mode for corrected errors */
+ else if (strcmp(arg, "nocmcff") == 0) {
+ acpi_disable_cmcff = 1;
} else {
/* Core will printk when we return error. */
return -EINVAL;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c15cf9a25e2..15e8563e5c2 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -11,6 +11,7 @@
#include <linux/memory.h>
#include <linux/stop_machine.h>
#include <linux/slab.h>
+#include <linux/kdebug.h>
#include <asm/alternative.h>
#include <asm/sections.h>
#include <asm/pgtable.h>
@@ -596,97 +597,93 @@ void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
return addr;
}
-/*
- * Cross-modifying kernel text with stop_machine().
- * This code originally comes from immediate value.
- */
-static atomic_t stop_machine_first;
-static int wrote_text;
+static void do_sync_core(void *info)
+{
+ sync_core();
+}
-struct text_poke_params {
- struct text_poke_param *params;
- int nparams;
-};
+static bool bp_patching_in_progress;
+static void *bp_int3_handler, *bp_int3_addr;
-static int __kprobes stop_machine_text_poke(void *data)
+int poke_int3_handler(struct pt_regs *regs)
{
- struct text_poke_params *tpp = data;
- struct text_poke_param *p;
- int i;
+ /* bp_patching_in_progress */
+ smp_rmb();
- if (atomic_xchg(&stop_machine_first, 0)) {
- for (i = 0; i < tpp->nparams; i++) {
- p = &tpp->params[i];
- text_poke(p->addr, p->opcode, p->len);
- }
- smp_wmb(); /* Make sure other cpus see that this has run */
- wrote_text = 1;
- } else {
- while (!wrote_text)
- cpu_relax();
- smp_mb(); /* Load wrote_text before following execution */
- }
+ if (likely(!bp_patching_in_progress))
+ return 0;
- for (i = 0; i < tpp->nparams; i++) {
- p = &tpp->params[i];
- flush_icache_range((unsigned long)p->addr,
- (unsigned long)p->addr + p->len);
- }
- /*
- * Intel Archiecture Software Developer's Manual section 7.1.3 specifies
- * that a core serializing instruction such as "cpuid" should be
- * executed on _each_ core before the new instruction is made visible.
- */
- sync_core();
- return 0;
-}
+ if (user_mode_vm(regs) || regs->ip != (unsigned long)bp_int3_addr)
+ return 0;
+
+ /* set up the specified breakpoint handler */
+ regs->ip = (unsigned long) bp_int3_handler;
+
+ return 1;
-/**
- * text_poke_smp - Update instructions on a live kernel on SMP
- * @addr: address to modify
- * @opcode: source of the copy
- * @len: length to copy
- *
- * Modify multi-byte instruction by using stop_machine() on SMP. This allows
- * user to poke/set multi-byte text on SMP. Only non-NMI/MCE code modifying
- * should be allowed, since stop_machine() does _not_ protect code against
- * NMI and MCE.
- *
- * Note: Must be called under get_online_cpus() and text_mutex.
- */
-void *__kprobes text_poke_smp(void *addr, const void *opcode, size_t len)
-{
- struct text_poke_params tpp;
- struct text_poke_param p;
-
- p.addr = addr;
- p.opcode = opcode;
- p.len = len;
- tpp.params = &p;
- tpp.nparams = 1;
- atomic_set(&stop_machine_first, 1);
- wrote_text = 0;
- /* Use __stop_machine() because the caller already got online_cpus. */
- __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
- return addr;
}
/**
- * text_poke_smp_batch - Update instructions on a live kernel on SMP
- * @params: an array of text_poke parameters
- * @n: the number of elements in params.
+ * text_poke_bp() -- update instructions on live kernel on SMP
+ * @addr: address to patch
+ * @opcode: opcode of new instruction
+ * @len: length to copy
+ * @handler: address to jump to when the temporary breakpoint is hit
*
- * Modify multi-byte instruction by using stop_machine() on SMP. Since the
- * stop_machine() is heavy task, it is better to aggregate text_poke requests
- * and do it once if possible.
+ * Modify multi-byte instruction by using int3 breakpoint on SMP.
+ * We completely avoid stop_machine() here, and achieve the
+ * synchronization using int3 breakpoint.
*
- * Note: Must be called under get_online_cpus() and text_mutex.
+ * The way it is done:
+ * - add a int3 trap to the address that will be patched
+ * - sync cores
+ * - update all but the first byte of the patched range
+ * - sync cores
+ * - replace the first byte (int3) by the first byte of
+ * replacing opcode
+ * - sync cores
+ *
+ * Note: must be called under text_mutex.
*/
-void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
+void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
{
- struct text_poke_params tpp = {.params = params, .nparams = n};
+ unsigned char int3 = 0xcc;
+
+ bp_int3_handler = handler;
+ bp_int3_addr = (u8 *)addr + sizeof(int3);
+ bp_patching_in_progress = true;
+ /*
+ * Corresponding read barrier in int3 notifier for
+ * making sure the in_progress flags is correctly ordered wrt.
+ * patching
+ */
+ smp_wmb();
+
+ text_poke(addr, &int3, sizeof(int3));
- atomic_set(&stop_machine_first, 1);
- wrote_text = 0;
- __stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
+ on_each_cpu(do_sync_core, NULL, 1);
+
+ if (len - sizeof(int3) > 0) {
+ /* patch all but the first byte */
+ text_poke((char *)addr + sizeof(int3),
+ (const char *) opcode + sizeof(int3),
+ len - sizeof(int3));
+ /*
+ * According to Intel, this core syncing is very likely
+ * not necessary and we'd be safe even without it. But
+ * better safe than sorry (plus there's not only Intel).
+ */
+ on_each_cpu(do_sync_core, NULL, 1);
+ }
+
+ /* patch the first byte */
+ text_poke(addr, opcode, sizeof(int3));
+
+ on_each_cpu(do_sync_core, NULL, 1);
+
+ bp_patching_in_progress = false;
+ smp_wmb();
+
+ return addr;
}
+
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 3048ded1b59..59554dca96e 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -20,6 +20,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
{}
};
@@ -27,6 +28,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids);
static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
{}
};
@@ -81,13 +83,20 @@ int amd_cache_northbridges(void)
next_northbridge(misc, amd_nb_misc_ids);
node_to_amd_nb(i)->link = link =
next_northbridge(link, amd_nb_link_ids);
- }
+ }
+ /* GART present only on Fam15h upto model 0fh */
if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
- boot_cpu_data.x86 == 0x15)
+ (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
amd_northbridges.flags |= AMD_NB_GART;
/*
+ * Check for L3 cache presence.
+ */
+ if (!cpuid_edx(0x80000006))
+ return 0;
+
+ /*
* Some CPU families support L3 Cache Index Disable. There are some
* limitations because of E382 and E388 on family 0x10.
*/
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index c9876efecaf..af5b08ab3b7 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -40,7 +40,7 @@
#include <asm/fixmap.h>
#include <asm/apb_timer.h>
-#include <asm/mrst.h>
+#include <asm/intel-mid.h>
#include <asm/time.h>
#define APBT_CLOCKEVENT_RATING 110
@@ -157,13 +157,13 @@ static int __init apbt_clockevent_register(void)
adev->num = smp_processor_id();
adev->timer = dw_apb_clockevent_init(smp_processor_id(), "apbt0",
- mrst_timer_options == MRST_TIMER_LAPIC_APBT ?
+ intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ?
APBT_CLOCKEVENT_RATING - 100 : APBT_CLOCKEVENT_RATING,
adev_virt_addr(adev), 0, apbt_freq);
/* Firmware does EOI handling for us. */
adev->timer->eoi = NULL;
- if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) {
+ if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT) {
global_clock_event = &adev->timer->ced;
printk(KERN_DEBUG "%s clockevent registered as global\n",
global_clock_event->name);
@@ -253,7 +253,7 @@ static int apbt_cpuhp_notify(struct notifier_block *n,
static __init int apbt_late_init(void)
{
- if (mrst_timer_options == MRST_TIMER_LAPIC_APBT ||
+ if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ||
!apb_timer_block_enabled)
return 0;
/* This notifier should be called after workqueue is ready */
@@ -340,7 +340,7 @@ void __init apbt_time_init(void)
}
#ifdef CONFIG_SMP
/* kernel cmdline disable apb timer, so we will use lapic timers */
- if (mrst_timer_options == MRST_TIMER_LAPIC_APBT) {
+ if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT) {
printk(KERN_INFO "apbt: disabled per cpu timer\n");
return;
}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index eca89c53a7f..a7eb82d9b01 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -913,7 +913,7 @@ static void local_apic_timer_interrupt(void)
* [ if a single-CPU system runs an SMP kernel then we call the local
* interrupt as well. Thus we cannot inline the local irq ... ]
*/
-void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
@@ -932,7 +932,7 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs)
set_irq_regs(old_regs);
}
-void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs)
+__visible void __irq_entry smp_trace_apic_timer_interrupt(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
@@ -1946,14 +1946,14 @@ static inline void __smp_spurious_interrupt(void)
"should never happen.\n", smp_processor_id());
}
-void smp_spurious_interrupt(struct pt_regs *regs)
+__visible void smp_spurious_interrupt(struct pt_regs *regs)
{
entering_irq();
__smp_spurious_interrupt();
exiting_irq();
}
-void smp_trace_spurious_interrupt(struct pt_regs *regs)
+__visible void smp_trace_spurious_interrupt(struct pt_regs *regs)
{
entering_irq();
trace_spurious_apic_entry(SPURIOUS_APIC_VECTOR);
@@ -2002,14 +2002,14 @@ static inline void __smp_error_interrupt(struct pt_regs *regs)
}
-void smp_error_interrupt(struct pt_regs *regs)
+__visible void smp_error_interrupt(struct pt_regs *regs)
{
entering_irq();
__smp_error_interrupt(regs);
exiting_irq();
}
-void smp_trace_error_interrupt(struct pt_regs *regs)
+__visible void smp_trace_error_interrupt(struct pt_regs *regs)
{
entering_irq();
trace_error_apic_entry(ERROR_APIC_VECTOR);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 9ed796ccc32..e63a5bd2a78 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1534,6 +1534,11 @@ void intel_ir_io_apic_print_entries(unsigned int apic,
}
}
+void ioapic_zap_locks(void)
+{
+ raw_spin_lock_init(&ioapic_lock);
+}
+
__apicdebuginit(void) print_IO_APIC(int ioapic_idx)
{
union IO_APIC_reg_00 reg_00;
@@ -3375,12 +3380,15 @@ int io_apic_setup_irq_pin_once(unsigned int irq, int node,
{
unsigned int ioapic_idx = attr->ioapic, pin = attr->ioapic_pin;
int ret;
+ struct IO_APIC_route_entry orig_entry;
/* Avoid redundant programming */
if (test_bit(pin, ioapics[ioapic_idx].pin_programmed)) {
- pr_debug("Pin %d-%d already programmed\n",
- mpc_ioapic_id(ioapic_idx), pin);
- return 0;
+ pr_debug("Pin %d-%d already programmed\n", mpc_ioapic_id(ioapic_idx), pin);
+ orig_entry = ioapic_read_entry(attr->ioapic, pin);
+ if (attr->trigger == orig_entry.trigger && attr->polarity == orig_entry.polarity)
+ return 0;
+ return -EBUSY;
}
ret = io_apic_setup_irq_pin(irq, node, attr);
if (!ret)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1191ac1c9d2..a419814cea5 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -113,7 +113,7 @@ static int __init early_get_pnodeid(void)
break;
case UV3_HUB_PART_NUMBER:
case UV3_HUB_PART_NUMBER_X:
- uv_min_hub_revision_id += UV3_HUB_REVISION_BASE - 1;
+ uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
break;
}
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 53a4e274484..3ab03430211 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -392,7 +392,7 @@ static struct cpuidle_device apm_cpuidle_device;
/*
* Local variables
*/
-static struct {
+__visible struct {
unsigned long offset;
unsigned short segment;
} apm_bios_entry;
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 28610822fb3..9f6b9341950 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -32,7 +32,6 @@ void common(void) {
OFFSET(TI_flags, thread_info, flags);
OFFSET(TI_status, thread_info, status);
OFFSET(TI_addr_limit, thread_info, addr_limit);
- OFFSET(TI_preempt_count, thread_info, preempt_count);
BLANK();
OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 08a089043cc..3daece79a14 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -66,8 +66,8 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
* performance at the same time..
*/
-extern void vide(void);
-__asm__(".align 4\nvide: ret");
+extern __visible void vide(void);
+__asm__(".globl vide\n\t.align 4\nvide: ret");
static void init_amd_k5(struct cpuinfo_x86 *c)
{
@@ -823,8 +823,8 @@ static const struct cpu_dev amd_cpu_dev = {
.c_vendor = "AMD",
.c_ident = { "AuthenticAMD" },
#ifdef CONFIG_X86_32
- .c_models = {
- { .vendor = X86_VENDOR_AMD, .family = 4, .model_names =
+ .legacy_models = {
+ { .family = 4, .model_names =
{
[3] = "486 DX/2",
[7] = "486 DX/2-WB",
@@ -835,7 +835,7 @@ static const struct cpu_dev amd_cpu_dev = {
}
},
},
- .c_size_cache = amd_size_cache,
+ .legacy_cache_size = amd_size_cache,
#endif
.c_early_init = early_init_amd,
.c_detect_tlb = cpu_detect_tlb_amd,
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index fbf6c3bc240..8d5652dc99d 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -468,10 +468,10 @@ static void init_centaur(struct cpuinfo_x86 *c)
#endif
}
+#ifdef CONFIG_X86_32
static unsigned int
centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size)
{
-#ifdef CONFIG_X86_32
/* VIA C3 CPUs (670-68F) need further shifting. */
if ((c->x86 == 6) && ((c->x86_model == 7) || (c->x86_model == 8)))
size >>= 8;
@@ -484,16 +484,18 @@ centaur_size_cache(struct cpuinfo_x86 *c, unsigned int size)
if ((c->x86 == 6) && (c->x86_model == 9) &&
(c->x86_mask == 1) && (size == 65))
size -= 1;
-#endif
return size;
}
+#endif
static const struct cpu_dev centaur_cpu_dev = {
.c_vendor = "Centaur",
.c_ident = { "CentaurHauls" },
.c_early_init = early_init_centaur,
.c_init = init_centaur,
- .c_size_cache = centaur_size_cache,
+#ifdef CONFIG_X86_32
+ .legacy_cache_size = centaur_size_cache,
+#endif
.c_x86_vendor = X86_VENDOR_CENTAUR,
};
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 25eb2747b06..6abc172b825 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -346,7 +346,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
/* Look up CPU names by table lookup. */
static const char *table_lookup_model(struct cpuinfo_x86 *c)
{
- const struct cpu_model_info *info;
+#ifdef CONFIG_X86_32
+ const struct legacy_cpu_model_info *info;
if (c->x86_model >= 16)
return NULL; /* Range check */
@@ -354,13 +355,14 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
if (!this_cpu)
return NULL;
- info = this_cpu->c_models;
+ info = this_cpu->legacy_models;
- while (info && info->family) {
+ while (info->family) {
if (info->family == c->x86)
return info->model_names[c->x86_model];
info++;
}
+#endif
return NULL; /* Not found */
}
@@ -450,8 +452,8 @@ void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
c->x86_tlbsize += ((ebx >> 16) & 0xfff) + (ebx & 0xfff);
#else
/* do processor-specific cache resizing */
- if (this_cpu->c_size_cache)
- l2size = this_cpu->c_size_cache(c, l2size);
+ if (this_cpu->legacy_cache_size)
+ l2size = this_cpu->legacy_cache_size(c, l2size);
/* Allow user to override all this if necessary. */
if (cachesize_override != -1)
@@ -1076,7 +1078,7 @@ struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
(unsigned long) debug_idt_table };
DEFINE_PER_CPU_FIRST(union irq_stack_union,
- irq_stack_union) __aligned(PAGE_SIZE);
+ irq_stack_union) __aligned(PAGE_SIZE) __visible;
/*
* The following four percpu variables are hot. Align current_task to
@@ -1093,7 +1095,10 @@ EXPORT_PER_CPU_SYMBOL(kernel_stack);
DEFINE_PER_CPU(char *, irq_stack_ptr) =
init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
-DEFINE_PER_CPU(unsigned int, irq_count) = -1;
+DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
+
+DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
@@ -1169,6 +1174,8 @@ void debug_stack_reset(void)
DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
EXPORT_PER_CPU_SYMBOL(current_task);
+DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
+EXPORT_PER_CPU_SYMBOL(__preempt_count);
DEFINE_PER_CPU(struct task_struct *, fpu_owner_task);
#ifdef CONFIG_CC_STACKPROTECTOR
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 4041c24ae7d..c37dc37e831 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -1,12 +1,6 @@
#ifndef ARCH_X86_CPU_H
#define ARCH_X86_CPU_H
-struct cpu_model_info {
- int vendor;
- int family;
- const char *model_names[16];
-};
-
/* attempt to consolidate cpu attributes */
struct cpu_dev {
const char *c_vendor;
@@ -14,15 +8,23 @@ struct cpu_dev {
/* some have two possibilities for cpuid string */
const char *c_ident[2];
- struct cpu_model_info c_models[4];
-
void (*c_early_init)(struct cpuinfo_x86 *);
void (*c_bsp_init)(struct cpuinfo_x86 *);
void (*c_init)(struct cpuinfo_x86 *);
void (*c_identify)(struct cpuinfo_x86 *);
void (*c_detect_tlb)(struct cpuinfo_x86 *);
- unsigned int (*c_size_cache)(struct cpuinfo_x86 *, unsigned int);
int c_x86_vendor;
+#ifdef CONFIG_X86_32
+ /* Optional vendor specific routine to obtain the cache size. */
+ unsigned int (*legacy_cache_size)(struct cpuinfo_x86 *,
+ unsigned int);
+
+ /* Family/stepping-based lookup table for model names. */
+ struct legacy_cpu_model_info {
+ int family;
+ const char *model_names[16];
+ } legacy_models[5];
+#endif
};
struct _tlb_table {
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 87279212d31..36ce402a3fa 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -25,11 +25,6 @@
#include <asm/processor.h>
#include <asm/hypervisor.h>
-/*
- * Hypervisor detect order. This is specified explicitly here because
- * some hypervisors might implement compatibility modes for other
- * hypervisors and therefore need to be detected in specific sequence.
- */
static const __initconst struct hypervisor_x86 * const hypervisors[] =
{
#ifdef CONFIG_XEN_PVHVM
@@ -49,15 +44,19 @@ static inline void __init
detect_hypervisor_vendor(void)
{
const struct hypervisor_x86 *h, * const *p;
+ uint32_t pri, max_pri = 0;
for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) {
h = *p;
- if (h->detect()) {
+ pri = h->detect();
+ if (pri != 0 && pri > max_pri) {
+ max_pri = pri;
x86_hyper = h;
- printk(KERN_INFO "Hypervisor detected: %s\n", h->name);
- break;
}
}
+
+ if (max_pri)
+ printk(KERN_INFO "Hypervisor detected: %s\n", x86_hyper->name);
}
void init_hypervisor(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index ec7299566f7..dc1ec0dff93 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -665,8 +665,8 @@ static const struct cpu_dev intel_cpu_dev = {
.c_vendor = "Intel",
.c_ident = { "GenuineIntel" },
#ifdef CONFIG_X86_32
- .c_models = {
- { .vendor = X86_VENDOR_INTEL, .family = 4, .model_names =
+ .legacy_models = {
+ { .family = 4, .model_names =
{
[0] = "486 DX-25/33",
[1] = "486 DX-50",
@@ -679,7 +679,7 @@ static const struct cpu_dev intel_cpu_dev = {
[9] = "486 DX/4-WB"
}
},
- { .vendor = X86_VENDOR_INTEL, .family = 5, .model_names =
+ { .family = 5, .model_names =
{
[0] = "Pentium 60/66 A-step",
[1] = "Pentium 60/66",
@@ -690,7 +690,7 @@ static const struct cpu_dev intel_cpu_dev = {
[8] = "Mobile Pentium MMX"
}
},
- { .vendor = X86_VENDOR_INTEL, .family = 6, .model_names =
+ { .family = 6, .model_names =
{
[0] = "Pentium Pro A-step",
[1] = "Pentium Pro",
@@ -704,7 +704,7 @@ static const struct cpu_dev intel_cpu_dev = {
[11] = "Pentium III (Tualatin)",
}
},
- { .vendor = X86_VENDOR_INTEL, .family = 15, .model_names =
+ { .family = 15, .model_names =
{
[0] = "Pentium 4 (Unknown)",
[1] = "Pentium 4 (Willamette)",
@@ -714,7 +714,7 @@ static const struct cpu_dev intel_cpu_dev = {
}
},
},
- .c_size_cache = intel_size_cache,
+ .legacy_cache_size = intel_size_cache,
#endif
.c_detect_tlb = intel_detect_tlb,
.c_early_init = early_init_intel,
diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c
index cd8b166a173..de8b60a53f6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-apei.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c
@@ -42,8 +42,7 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err)
struct mce m;
/* Only corrected MC is reported */
- if (!corrected || !(mem_err->validation_bits &
- CPER_MEM_VALID_PHYSICAL_ADDRESS))
+ if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA))
return;
mce_setup(&m);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
index 5b7d4fa5d3b..09edd0b65fe 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-internal.h
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -25,15 +25,18 @@ int mce_severity(struct mce *a, int tolerant, char **msg);
struct dentry *mce_get_debugfs_dir(void);
extern struct mce_bank *mce_banks;
+extern mce_banks_t mce_banks_ce_disabled;
#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);
+void cmci_disable_bank(int bank);
#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) { }
+static inline void cmci_disable_bank(int bank) { }
#endif
void mce_timer_kick(unsigned long interval);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 87a65c939bc..b3218cdee95 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -97,6 +97,15 @@ DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
};
+/*
+ * MCA banks controlled through firmware first for corrected errors.
+ * This is a global list of banks for which we won't enable CMCI and we
+ * won't poll. Firmware controls these banks and is responsible for
+ * reporting corrected errors through GHES. Uncorrected/recoverable
+ * errors are still notified through a machine check.
+ */
+mce_banks_t mce_banks_ce_disabled;
+
static DEFINE_PER_CPU(struct work_struct, mce_work);
static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs);
@@ -1935,6 +1944,25 @@ static struct miscdevice mce_chrdev_device = {
&mce_chrdev_ops,
};
+static void __mce_disable_bank(void *arg)
+{
+ int bank = *((int *)arg);
+ __clear_bit(bank, __get_cpu_var(mce_poll_banks));
+ cmci_disable_bank(bank);
+}
+
+void mce_disable_bank(int bank)
+{
+ if (bank >= mca_cfg.banks) {
+ pr_warn(FW_BUG
+ "Ignoring request to disable invalid MCA bank %d.\n",
+ bank);
+ return;
+ }
+ set_bit(bank, mce_banks_ce_disabled);
+ on_each_cpu(__mce_disable_bank, &bank, 1);
+}
+
/*
* mce=off Disables machine check
* mce=no_cmci Disables CMCI
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index d56405309dc..4cfe0458ca6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -203,6 +203,10 @@ static void cmci_discover(int banks)
if (test_bit(i, owned))
continue;
+ /* Skip banks in firmware first mode */
+ if (test_bit(i, mce_banks_ce_disabled))
+ continue;
+
rdmsrl(MSR_IA32_MCx_CTL2(i), val);
/* Already owned by someone else? */
@@ -271,6 +275,19 @@ void cmci_recheck(void)
local_irq_restore(flags);
}
+/* Caller must hold the lock on cmci_discover_lock */
+static void __cmci_disable_bank(int bank)
+{
+ u64 val;
+
+ if (!test_bit(bank, __get_cpu_var(mce_banks_owned)))
+ return;
+ rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ val &= ~MCI_CTL2_CMCI_EN;
+ wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ __clear_bit(bank, __get_cpu_var(mce_banks_owned));
+}
+
/*
* Disable CMCI on this CPU for all banks it owns when it goes down.
* This allows other CPUs to claim the banks on rediscovery.
@@ -280,20 +297,12 @@ void cmci_clear(void)
unsigned long flags;
int i;
int banks;
- u64 val;
if (!cmci_supported(&banks))
return;
raw_spin_lock_irqsave(&cmci_discover_lock, flags);
- for (i = 0; i < banks; i++) {
- if (!test_bit(i, __get_cpu_var(mce_banks_owned)))
- continue;
- /* Disable CMCI */
- rdmsrl(MSR_IA32_MCx_CTL2(i), val);
- val &= ~MCI_CTL2_CMCI_EN;
- wrmsrl(MSR_IA32_MCx_CTL2(i), val);
- __clear_bit(i, __get_cpu_var(mce_banks_owned));
- }
+ for (i = 0; i < banks; i++)
+ __cmci_disable_bank(i);
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
@@ -327,6 +336,19 @@ void cmci_reenable(void)
cmci_discover(banks);
}
+void cmci_disable_bank(int bank)
+{
+ int banks;
+ unsigned long flags;
+
+ if (!cmci_supported(&banks))
+ return;
+
+ raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+ __cmci_disable_bank(bank);
+ raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
static void intel_init_cmci(void)
{
int banks;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 8f4be53ea04..9f7ca266864 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -15,6 +15,7 @@
#include <linux/clocksource.h>
#include <linux/module.h>
#include <linux/hardirq.h>
+#include <linux/efi.h>
#include <linux/interrupt.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
@@ -23,24 +24,29 @@
#include <asm/desc.h>
#include <asm/idle.h>
#include <asm/irq_regs.h>
+#include <asm/i8259.h>
+#include <asm/apic.h>
struct ms_hyperv_info ms_hyperv;
EXPORT_SYMBOL_GPL(ms_hyperv);
-static bool __init ms_hyperv_platform(void)
+static uint32_t __init ms_hyperv_platform(void)
{
u32 eax;
u32 hyp_signature[3];
if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
- return false;
+ return 0;
cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
&eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
- return eax >= HYPERV_CPUID_MIN &&
- eax <= HYPERV_CPUID_MAX &&
- !memcmp("Microsoft Hv", hyp_signature, 12);
+ if (eax >= HYPERV_CPUID_MIN &&
+ eax <= HYPERV_CPUID_MAX &&
+ !memcmp("Microsoft Hv", hyp_signature, 12))
+ return HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS;
+
+ return 0;
}
static cycle_t read_hv_clock(struct clocksource *arg)
@@ -73,6 +79,30 @@ static void __init ms_hyperv_init_platform(void)
printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n",
ms_hyperv.features, ms_hyperv.hints);
+#ifdef CONFIG_X86_LOCAL_APIC
+ if (ms_hyperv.features & HV_X64_MSR_APIC_FREQUENCY_AVAILABLE) {
+ /*
+ * Get the APIC frequency.
+ */
+ u64 hv_lapic_frequency;
+
+ rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
+ hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
+ lapic_timer_frequency = hv_lapic_frequency;
+ printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n",
+ lapic_timer_frequency);
+
+ /*
+ * On Hyper-V, when we are booting off an EFI firmware stack,
+ * we do not have many legacy devices including PIC, PIT etc.
+ */
+ if (efi_enabled(EFI_BOOT)) {
+ printk(KERN_INFO "HyperV: Using null_legacy_pic\n");
+ legacy_pic = &null_legacy_pic;
+ }
+ }
+#endif
+
if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
}
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index d4cdfa67509..ce2d0a2c3e4 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -683,6 +683,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
}
/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb();
/* Save MTRR state */
@@ -696,6 +697,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
static void post_set(void) __releases(set_atomicity_lock)
{
/* Flush TLBs (no need to flush caches - they are disabled) */
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
__flush_tlb();
/* Intel (P6) standard MTRRs */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index a7c7305030c..8e132931614 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1276,16 +1276,16 @@ void perf_events_lapic_init(void)
static int __kprobes
perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
{
- int ret;
u64 start_clock;
u64 finish_clock;
+ int ret;
if (!atomic_read(&active_events))
return NMI_DONE;
- start_clock = local_clock();
+ start_clock = sched_clock();
ret = x86_pmu.handle_irq(regs);
- finish_clock = local_clock();
+ finish_clock = sched_clock();
perf_sample_event_took(finish_clock - start_clock);
@@ -1506,7 +1506,7 @@ static int __init init_hw_perf_events(void)
err = amd_pmu_init();
break;
default:
- return 0;
+ err = -ENOTSUPP;
}
if (err != 0) {
pr_cont("no PMU driver, software events only.\n");
@@ -1883,20 +1883,21 @@ static struct pmu pmu = {
void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
- userpg->cap_usr_time = 0;
- userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
+ userpg->cap_user_time = 0;
+ userpg->cap_user_time_zero = 0;
+ userpg->cap_user_rdpmc = x86_pmu.attr_rdpmc;
userpg->pmc_width = x86_pmu.cntval_bits;
- if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+ if (!sched_clock_stable)
return;
- if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
- return;
-
- userpg->cap_usr_time = 1;
+ userpg->cap_user_time = 1;
userpg->time_mult = this_cpu_read(cyc2ns);
userpg->time_shift = CYC2NS_SCALE_FACTOR;
userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
+
+ userpg->cap_user_time_zero = 1;
+ userpg->time_zero = this_cpu_read(cyc2ns_offset);
}
/*
@@ -1988,7 +1989,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry)
frame.return_address = 0;
bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
- if (bytes != sizeof(frame))
+ if (bytes != 0)
break;
if (!valid_user_frame(fp, sizeof(frame)))
@@ -2040,7 +2041,7 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
frame.return_address = 0;
bytes = copy_from_user_nmi(&frame, fp, sizeof(frame));
- if (bytes != sizeof(frame))
+ if (bytes != 0)
break;
if (!valid_user_frame(fp, sizeof(frame)))
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 97e557bc4c9..fd00bb29425 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -164,6 +164,11 @@ struct cpu_hw_events {
struct perf_guest_switch_msr guest_switch_msrs[X86_PMC_IDX_MAX];
/*
+ * Intel checkpoint mask
+ */
+ u64 intel_cp_status;
+
+ /*
* manage shared (per-core, per-cpu) registers
* used on Intel NHM/WSM/SNB
*/
@@ -440,6 +445,7 @@ struct x86_pmu {
int lbr_nr; /* hardware stack size */
u64 lbr_sel_mask; /* LBR_SELECT valid bits */
const int *lbr_sel_map; /* lbr_select mappings */
+ bool lbr_double_abort; /* duplicated lbr aborts */
/*
* Extra registers for events
@@ -641,6 +647,8 @@ extern struct event_constraint intel_core2_pebs_event_constraints[];
extern struct event_constraint intel_atom_pebs_event_constraints[];
+extern struct event_constraint intel_slm_pebs_event_constraints[];
+
extern struct event_constraint intel_nehalem_pebs_event_constraints[];
extern struct event_constraint intel_westmere_pebs_event_constraints[];
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 4cbe03287b0..beeb7cc0704 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -347,8 +347,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
struct amd_nb *nb;
int i;
- nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO,
- cpu_to_node(cpu));
+ nb = kzalloc_node(sizeof(struct amd_nb), GFP_KERNEL, cpu_to_node(cpu));
if (!nb)
return NULL;
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index a45d8d4ace1..0fa4f242f05 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -81,7 +81,8 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly =
static struct extra_reg intel_nehalem_extra_regs[] __read_mostly =
{
- INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+ /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
EVENT_EXTRA_END
};
@@ -123,6 +124,7 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
INTEL_UEVENT_CONSTRAINT(0x0148, 0x4), /* L1D_PEND_MISS.PENDING */
INTEL_UEVENT_CONSTRAINT(0x0279, 0xf), /* IDQ.EMTPY */
INTEL_UEVENT_CONSTRAINT(0x019c, 0xf), /* IDQ_UOPS_NOT_DELIVERED.CORE */
+ INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_LDM_PENDING */
INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */
INTEL_UEVENT_CONSTRAINT(0x06a3, 0xf), /* CYCLE_ACTIVITY.STALLS_LDM_PENDING */
@@ -143,8 +145,9 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
static struct extra_reg intel_westmere_extra_regs[] __read_mostly =
{
- INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
- INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
+ /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b),
EVENT_EXTRA_END
};
@@ -162,23 +165,34 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
EVENT_CONSTRAINT_END
};
+static struct event_constraint intel_slm_event_constraints[] __read_mostly =
+{
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
+ EVENT_CONSTRAINT_END
+};
+
static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
- INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
- INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+ /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
EVENT_EXTRA_END
};
static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
- INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
- INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
+ /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
EVENT_EXTRA_END
};
-EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
-EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
-EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
+EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3");
+EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3");
+EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2");
struct attribute *nhm_events_attrs[] = {
EVENT_PTR(mem_ld_nhm),
@@ -882,6 +896,140 @@ static __initconst const u64 atom_hw_cache_event_ids
},
};
+static struct extra_reg intel_slm_extra_regs[] __read_mostly =
+{
+ /* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x768005ffffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0x768005ffffull, RSP_1),
+ EVENT_EXTRA_END
+};
+
+#define SLM_DMND_READ SNB_DMND_DATA_RD
+#define SLM_DMND_WRITE SNB_DMND_RFO
+#define SLM_DMND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_RFO)
+
+#define SLM_SNP_ANY (SNB_SNP_NONE|SNB_SNP_MISS|SNB_NO_FWD|SNB_HITM)
+#define SLM_LLC_ACCESS SNB_RESP_ANY
+#define SLM_LLC_MISS (SLM_SNP_ANY|SNB_NON_DRAM)
+
+static __initconst const u64 slm_hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = SLM_DMND_READ|SLM_LLC_ACCESS,
+ [ C(RESULT_MISS) ] = SLM_DMND_READ|SLM_LLC_MISS,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = SLM_DMND_WRITE|SLM_LLC_ACCESS,
+ [ C(RESULT_MISS) ] = SLM_DMND_WRITE|SLM_LLC_MISS,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = SLM_DMND_PREFETCH|SLM_LLC_ACCESS,
+ [ C(RESULT_MISS) ] = SLM_DMND_PREFETCH|SLM_LLC_MISS,
+ },
+ },
+};
+
+static __initconst const u64 slm_hw_cache_event_ids
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0x0104, /* LD_DCU_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(L1I ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x0380, /* ICACHE.ACCESSES */
+ [ C(RESULT_MISS) ] = 0x0280, /* ICACGE.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_WRITE) ] = {
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_PREFETCH) ] = {
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ },
+ [ C(DTLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0x0804, /* LD_DTLB_MISS */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0,
+ [ C(RESULT_MISS) ] = 0,
+ },
+ },
+ [ C(ITLB) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c0, /* INST_RETIRED.ANY_P */
+ [ C(RESULT_MISS) ] = 0x0282, /* ITLB.MISSES */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+ [ C(BPU ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x00c4, /* BR_INST_RETIRED.ANY */
+ [ C(RESULT_MISS) ] = 0x00c5, /* BP_INST_RETIRED.MISPRED */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
+};
+
static inline bool intel_pmu_needs_lbr_smpl(struct perf_event *event)
{
/* user explicitly requested branch sampling */
@@ -1036,6 +1184,11 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
wrmsrl(hwc->config_base, ctrl_val);
}
+static inline bool event_is_checkpointed(struct perf_event *event)
+{
+ return (event->hw.config & HSW_IN_TX_CHECKPOINTED) != 0;
+}
+
static void intel_pmu_disable_event(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
@@ -1049,6 +1202,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
+ cpuc->intel_cp_status &= ~(1ull << hwc->idx);
/*
* must disable before any actual event
@@ -1123,6 +1277,9 @@ static void intel_pmu_enable_event(struct perf_event *event)
if (event->attr.exclude_guest)
cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
+ if (unlikely(event_is_checkpointed(event)))
+ cpuc->intel_cp_status |= (1ull << hwc->idx);
+
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
intel_pmu_enable_fixed(hwc);
return;
@@ -1141,6 +1298,17 @@ static void intel_pmu_enable_event(struct perf_event *event)
int intel_pmu_save_and_restart(struct perf_event *event)
{
x86_perf_event_update(event);
+ /*
+ * For a checkpointed counter always reset back to 0. This
+ * avoids a situation where the counter overflows, aborts the
+ * transaction and is then set back to shortly before the
+ * overflow, and overflows and aborts again.
+ */
+ if (unlikely(event_is_checkpointed(event))) {
+ /* No race with NMIs because the counter should not be armed */
+ wrmsrl(event->hw.event_base, 0);
+ local64_set(&event->hw.prev_count, 0);
+ }
return x86_perf_event_set_period(event);
}
@@ -1224,6 +1392,13 @@ again:
x86_pmu.drain_pebs(regs);
}
+ /*
+ * Checkpointed counters can lead to 'spurious' PMIs because the
+ * rollback caused by the PMI will have cleared the overflow status
+ * bit. Therefore always force probe these counters.
+ */
+ status |= cpuc->intel_cp_status;
+
for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[bit];
@@ -1301,11 +1476,11 @@ static void intel_fixup_er(struct perf_event *event, int idx)
if (idx == EXTRA_REG_RSP_0) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
- event->hw.config |= 0x01b7;
+ event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_0].event;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_0;
} else if (idx == EXTRA_REG_RSP_1) {
event->hw.config &= ~INTEL_ARCH_EVENT_MASK;
- event->hw.config |= 0x01bb;
+ event->hw.config |= x86_pmu.extra_regs[EXTRA_REG_RSP_1].event;
event->hw.extra_reg.reg = MSR_OFFCORE_RSP_1;
}
}
@@ -1689,6 +1864,20 @@ static int hsw_hw_config(struct perf_event *event)
event->attr.precise_ip > 0))
return -EOPNOTSUPP;
+ if (event_is_checkpointed(event)) {
+ /*
+ * Sampling of checkpointed events can cause situations where
+ * the CPU constantly aborts because of a overflow, which is
+ * then checkpointed back and ignored. Forbid checkpointing
+ * for sampling.
+ *
+ * But still allow a long sampling period, so that perf stat
+ * from KVM works.
+ */
+ if (event->attr.sample_period > 0 &&
+ event->attr.sample_period < 0x7fffffff)
+ return -EOPNOTSUPP;
+ }
return 0;
}
@@ -2034,10 +2223,36 @@ static __init void intel_nehalem_quirk(void)
}
}
-EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3");
-EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82")
+EVENT_ATTR_STR(mem-loads, mem_ld_hsw, "event=0xcd,umask=0x1,ldlat=3");
+EVENT_ATTR_STR(mem-stores, mem_st_hsw, "event=0xd0,umask=0x82")
+
+/* Haswell special events */
+EVENT_ATTR_STR(tx-start, tx_start, "event=0xc9,umask=0x1");
+EVENT_ATTR_STR(tx-commit, tx_commit, "event=0xc9,umask=0x2");
+EVENT_ATTR_STR(tx-abort, tx_abort, "event=0xc9,umask=0x4");
+EVENT_ATTR_STR(tx-capacity, tx_capacity, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(tx-conflict, tx_conflict, "event=0x54,umask=0x1");
+EVENT_ATTR_STR(el-start, el_start, "event=0xc8,umask=0x1");
+EVENT_ATTR_STR(el-commit, el_commit, "event=0xc8,umask=0x2");
+EVENT_ATTR_STR(el-abort, el_abort, "event=0xc8,umask=0x4");
+EVENT_ATTR_STR(el-capacity, el_capacity, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-conflict, el_conflict, "event=0x54,umask=0x1");
+EVENT_ATTR_STR(cycles-t, cycles_t, "event=0x3c,in_tx=1");
+EVENT_ATTR_STR(cycles-ct, cycles_ct, "event=0x3c,in_tx=1,in_tx_cp=1");
static struct attribute *hsw_events_attrs[] = {
+ EVENT_PTR(tx_start),
+ EVENT_PTR(tx_commit),
+ EVENT_PTR(tx_abort),
+ EVENT_PTR(tx_capacity),
+ EVENT_PTR(tx_conflict),
+ EVENT_PTR(el_start),
+ EVENT_PTR(el_commit),
+ EVENT_PTR(el_abort),
+ EVENT_PTR(el_capacity),
+ EVENT_PTR(el_conflict),
+ EVENT_PTR(cycles_t),
+ EVENT_PTR(cycles_ct),
EVENT_PTR(mem_ld_hsw),
EVENT_PTR(mem_st_hsw),
NULL
@@ -2176,6 +2391,22 @@ __init int intel_pmu_init(void)
pr_cont("Atom events, ");
break;
+ case 55: /* Atom 22nm "Silvermont" */
+ case 77: /* Avoton "Silvermont" */
+ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));
+
+ intel_pmu_lbr_init_atom();
+
+ x86_pmu.event_constraints = intel_slm_event_constraints;
+ x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_slm_extra_regs;
+ x86_pmu.er_flags |= ERF_HAS_RSP_1;
+ pr_cont("Silvermont events, ");
+ break;
+
case 37: /* 32 nm nehalem, "Clarkdale" */
case 44: /* 32 nm nehalem, "Gulftown" */
case 47: /* 32 nm Xeon E7 */
@@ -2288,6 +2519,7 @@ __init int intel_pmu_init(void)
x86_pmu.hw_config = hsw_hw_config;
x86_pmu.get_event_constraints = hsw_get_event_constraints;
x86_pmu.cpu_events = hsw_events_attrs;
+ x86_pmu.lbr_double_abort = true;
pr_cont("Haswell events, ");
break;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 3065c57a63c..ae96cfa5edd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -12,6 +12,7 @@
#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
#define PEBS_BUFFER_SIZE PAGE_SIZE
+#define PEBS_FIXUP_SIZE PAGE_SIZE
/*
* pebs_record_32 for p4 and core not supported
@@ -182,18 +183,32 @@ struct pebs_record_nhm {
* Same as pebs_record_nhm, with two additional fields.
*/
struct pebs_record_hsw {
- struct pebs_record_nhm nhm;
- /*
- * Real IP of the event. In the Intel documentation this
- * is called eventingrip.
- */
- u64 real_ip;
- /*
- * TSX tuning information field: abort cycles and abort flags.
- */
- u64 tsx_tuning;
+ u64 flags, ip;
+ u64 ax, bx, cx, dx;
+ u64 si, di, bp, sp;
+ u64 r8, r9, r10, r11;
+ u64 r12, r13, r14, r15;
+ u64 status, dla, dse, lat;
+ u64 real_ip, tsx_tuning;
+};
+
+union hsw_tsx_tuning {
+ struct {
+ u32 cycles_last_block : 32,
+ hle_abort : 1,
+ rtm_abort : 1,
+ instruction_abort : 1,
+ non_instruction_abort : 1,
+ retry : 1,
+ data_conflict : 1,
+ capacity_writes : 1,
+ capacity_reads : 1;
+ };
+ u64 value;
};
+#define PEBS_HSW_TSX_FLAGS 0xff00000000ULL
+
void init_debug_store_on_cpu(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
@@ -214,20 +229,35 @@ void fini_debug_store_on_cpu(int cpu)
wrmsr_on_cpu(cpu, MSR_IA32_DS_AREA, 0, 0);
}
+static DEFINE_PER_CPU(void *, insn_buffer);
+
static int alloc_pebs_buffer(int cpu)
{
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
int node = cpu_to_node(cpu);
int max, thresh = 1; /* always use a single PEBS record */
- void *buffer;
+ void *buffer, *ibuffer;
if (!x86_pmu.pebs)
return 0;
- buffer = kmalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+ buffer = kzalloc_node(PEBS_BUFFER_SIZE, GFP_KERNEL, node);
if (unlikely(!buffer))
return -ENOMEM;
+ /*
+ * HSW+ already provides us the eventing ip; no need to allocate this
+ * buffer then.
+ */
+ if (x86_pmu.intel_cap.pebs_format < 2) {
+ ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
+ if (!ibuffer) {
+ kfree(buffer);
+ return -ENOMEM;
+ }
+ per_cpu(insn_buffer, cpu) = ibuffer;
+ }
+
max = PEBS_BUFFER_SIZE / x86_pmu.pebs_record_size;
ds->pebs_buffer_base = (u64)(unsigned long)buffer;
@@ -248,6 +278,9 @@ static void release_pebs_buffer(int cpu)
if (!ds || !x86_pmu.pebs)
return;
+ kfree(per_cpu(insn_buffer, cpu));
+ per_cpu(insn_buffer, cpu) = NULL;
+
kfree((void *)(unsigned long)ds->pebs_buffer_base);
ds->pebs_buffer_base = 0;
}
@@ -262,7 +295,7 @@ static int alloc_bts_buffer(int cpu)
if (!x86_pmu.bts)
return 0;
- buffer = kmalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_ZERO, node);
+ buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node);
if (unlikely(!buffer))
return -ENOMEM;
@@ -295,7 +328,7 @@ static int alloc_ds_buffer(int cpu)
int node = cpu_to_node(cpu);
struct debug_store *ds;
- ds = kmalloc_node(sizeof(*ds), GFP_KERNEL | __GFP_ZERO, node);
+ ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
if (unlikely(!ds))
return -ENOMEM;
@@ -517,6 +550,32 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+struct event_constraint intel_slm_pebs_event_constraints[] = {
+ INTEL_UEVENT_CONSTRAINT(0x0103, 0x1), /* REHABQ.LD_BLOCK_ST_FORWARD_PS */
+ INTEL_UEVENT_CONSTRAINT(0x0803, 0x1), /* REHABQ.LD_SPLITS_PS */
+ INTEL_UEVENT_CONSTRAINT(0x0204, 0x1), /* MEM_UOPS_RETIRED.L2_HIT_LOADS_PS */
+ INTEL_UEVENT_CONSTRAINT(0x0404, 0x1), /* MEM_UOPS_RETIRED.L2_MISS_LOADS_PS */
+ INTEL_UEVENT_CONSTRAINT(0x0804, 0x1), /* MEM_UOPS_RETIRED.DTLB_MISS_LOADS_PS */
+ INTEL_UEVENT_CONSTRAINT(0x2004, 0x1), /* MEM_UOPS_RETIRED.HITM_PS */
+ INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY_PS */
+ INTEL_UEVENT_CONSTRAINT(0x00c4, 0x1), /* BR_INST_RETIRED.ALL_BRANCHES_PS */
+ INTEL_UEVENT_CONSTRAINT(0x7ec4, 0x1), /* BR_INST_RETIRED.JCC_PS */
+ INTEL_UEVENT_CONSTRAINT(0xbfc4, 0x1), /* BR_INST_RETIRED.FAR_BRANCH_PS */
+ INTEL_UEVENT_CONSTRAINT(0xebc4, 0x1), /* BR_INST_RETIRED.NON_RETURN_IND_PS */
+ INTEL_UEVENT_CONSTRAINT(0xf7c4, 0x1), /* BR_INST_RETIRED.RETURN_PS */
+ INTEL_UEVENT_CONSTRAINT(0xf9c4, 0x1), /* BR_INST_RETIRED.CALL_PS */
+ INTEL_UEVENT_CONSTRAINT(0xfbc4, 0x1), /* BR_INST_RETIRED.IND_CALL_PS */
+ INTEL_UEVENT_CONSTRAINT(0xfdc4, 0x1), /* BR_INST_RETIRED.REL_CALL_PS */
+ INTEL_UEVENT_CONSTRAINT(0xfec4, 0x1), /* BR_INST_RETIRED.TAKEN_JCC_PS */
+ INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_MISP_RETIRED.ALL_BRANCHES_PS */
+ INTEL_UEVENT_CONSTRAINT(0x7ec5, 0x1), /* BR_INST_MISP_RETIRED.JCC_PS */
+ INTEL_UEVENT_CONSTRAINT(0xebc5, 0x1), /* BR_INST_MISP_RETIRED.NON_RETURN_IND_PS */
+ INTEL_UEVENT_CONSTRAINT(0xf7c5, 0x1), /* BR_INST_MISP_RETIRED.RETURN_PS */
+ INTEL_UEVENT_CONSTRAINT(0xfbc5, 0x1), /* BR_INST_MISP_RETIRED.IND_CALL_PS */
+ INTEL_UEVENT_CONSTRAINT(0xfec5, 0x1), /* BR_INST_MISP_RETIRED.TAKEN_JCC_PS */
+ EVENT_CONSTRAINT_END
+};
+
struct event_constraint intel_nehalem_pebs_event_constraints[] = {
INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */
INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */
@@ -558,6 +617,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
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.* */
INTEL_UEVENT_CONSTRAINT(0x02d4, 0xf), /* MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS */
EVENT_CONSTRAINT_END
};
@@ -688,6 +748,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
unsigned long old_to, to = cpuc->lbr_entries[0].to;
unsigned long ip = regs->ip;
int is_64bit = 0;
+ void *kaddr;
/*
* We don't need to fixup if the PEBS assist is fault like
@@ -711,7 +772,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
* unsigned math, either ip is before the start (impossible) or
* the basic block is larger than 1 page (sanity)
*/
- if ((ip - to) > PAGE_SIZE)
+ if ((ip - to) > PEBS_FIXUP_SIZE)
return 0;
/*
@@ -722,29 +783,33 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 1;
}
+ if (!kernel_ip(ip)) {
+ int size, bytes;
+ u8 *buf = this_cpu_read(insn_buffer);
+
+ size = ip - to; /* Must fit our buffer, see above */
+ bytes = copy_from_user_nmi(buf, (void __user *)to, size);
+ if (bytes != 0)
+ return 0;
+
+ kaddr = buf;
+ } else {
+ kaddr = (void *)to;
+ }
+
do {
struct insn insn;
- u8 buf[MAX_INSN_SIZE];
- void *kaddr;
old_to = to;
- if (!kernel_ip(ip)) {
- int bytes, size = MAX_INSN_SIZE;
-
- bytes = copy_from_user_nmi(buf, (void __user *)to, size);
- if (bytes != size)
- return 0;
-
- kaddr = buf;
- } else
- kaddr = (void *)to;
#ifdef CONFIG_X86_64
is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
#endif
insn_init(&insn, kaddr, is_64bit);
insn_get_length(&insn);
+
to += insn.length;
+ kaddr += insn.length;
} while (to < ip);
if (to == ip) {
@@ -759,16 +824,34 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
return 0;
}
+static inline u64 intel_hsw_weight(struct pebs_record_hsw *pebs)
+{
+ if (pebs->tsx_tuning) {
+ union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+ return tsx.cycles_last_block;
+ }
+ return 0;
+}
+
+static inline u64 intel_hsw_transaction(struct pebs_record_hsw *pebs)
+{
+ u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+
+ /* For RTM XABORTs also log the abort code from AX */
+ if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
+ txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+ return txn;
+}
+
static void __intel_pmu_pebs_event(struct perf_event *event,
struct pt_regs *iregs, void *__pebs)
{
/*
- * We cast to pebs_record_nhm to get the load latency data
- * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used
+ * We cast to the biggest pebs_record but are careful not to
+ * unconditionally access the 'extra' entries.
*/
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct pebs_record_nhm *pebs = __pebs;
- struct pebs_record_hsw *pebs_hsw = __pebs;
+ struct pebs_record_hsw *pebs = __pebs;
struct perf_sample_data data;
struct pt_regs regs;
u64 sample_type;
@@ -827,7 +910,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
regs.sp = pebs->sp;
if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
- regs.ip = pebs_hsw->real_ip;
+ regs.ip = pebs->real_ip;
regs.flags |= PERF_EFLAGS_EXACT;
} else if (event->attr.precise_ip > 1 && intel_pmu_pebs_fixup_ip(&regs))
regs.flags |= PERF_EFLAGS_EXACT;
@@ -835,9 +918,18 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
regs.flags &= ~PERF_EFLAGS_EXACT;
if ((event->attr.sample_type & PERF_SAMPLE_ADDR) &&
- x86_pmu.intel_cap.pebs_format >= 1)
+ x86_pmu.intel_cap.pebs_format >= 1)
data.addr = pebs->dla;
+ if (x86_pmu.intel_cap.pebs_format >= 2) {
+ /* Only set the TSX weight when no memory weight. */
+ if ((event->attr.sample_type & PERF_SAMPLE_WEIGHT) && !fll)
+ data.weight = intel_hsw_weight(pebs);
+
+ if (event->attr.sample_type & PERF_SAMPLE_TRANSACTION)
+ data.txn = intel_hsw_transaction(pebs);
+ }
+
if (has_branch_stack(event))
data.br_stack = &cpuc->lbr_stack;
@@ -886,17 +978,34 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
__intel_pmu_pebs_event(event, iregs, at);
}
-static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at,
- void *top)
+static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
{
struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
struct debug_store *ds = cpuc->ds;
struct perf_event *event = NULL;
+ void *at, *top;
u64 status = 0;
int bit;
+ if (!x86_pmu.pebs_active)
+ return;
+
+ at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
+ top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
+
ds->pebs_index = ds->pebs_buffer_base;
+ if (unlikely(at > top))
+ return;
+
+ /*
+ * Should not happen, we program the threshold at 1 and do not
+ * set a reset value.
+ */
+ WARN_ONCE(top - at > x86_pmu.max_pebs_events * x86_pmu.pebs_record_size,
+ "Unexpected number of pebs records %ld\n",
+ (long)(top - at) / x86_pmu.pebs_record_size);
+
for (; at < top; at += x86_pmu.pebs_record_size) {
struct pebs_record_nhm *p = at;
@@ -924,61 +1033,6 @@ static void __intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, void *at,
}
}
-static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct debug_store *ds = cpuc->ds;
- struct pebs_record_nhm *at, *top;
- int n;
-
- if (!x86_pmu.pebs_active)
- return;
-
- at = (struct pebs_record_nhm *)(unsigned long)ds->pebs_buffer_base;
- top = (struct pebs_record_nhm *)(unsigned long)ds->pebs_index;
-
- ds->pebs_index = ds->pebs_buffer_base;
-
- n = top - at;
- if (n <= 0)
- return;
-
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(n > x86_pmu.max_pebs_events,
- "Unexpected number of pebs records %d\n", n);
-
- return __intel_pmu_drain_pebs_nhm(iregs, at, top);
-}
-
-static void intel_pmu_drain_pebs_hsw(struct pt_regs *iregs)
-{
- struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
- struct debug_store *ds = cpuc->ds;
- struct pebs_record_hsw *at, *top;
- int n;
-
- if (!x86_pmu.pebs_active)
- return;
-
- at = (struct pebs_record_hsw *)(unsigned long)ds->pebs_buffer_base;
- top = (struct pebs_record_hsw *)(unsigned long)ds->pebs_index;
-
- n = top - at;
- if (n <= 0)
- return;
- /*
- * Should not happen, we program the threshold at 1 and do not
- * set a reset value.
- */
- WARN_ONCE(n > x86_pmu.max_pebs_events,
- "Unexpected number of pebs records %d\n", n);
-
- return __intel_pmu_drain_pebs_nhm(iregs, at, top);
-}
-
/*
* BTS, PEBS probe and setup
*/
@@ -1013,7 +1067,7 @@ void intel_ds_init(void)
case 2:
pr_cont("PEBS fmt2%c, ", pebs_type);
x86_pmu.pebs_record_size = sizeof(struct pebs_record_hsw);
- x86_pmu.drain_pebs = intel_pmu_drain_pebs_hsw;
+ x86_pmu.drain_pebs = intel_pmu_drain_pebs_nhm;
break;
default:
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index d5be06a5005..d82d155aca8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -284,6 +284,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
int lbr_format = x86_pmu.intel_cap.lbr_format;
u64 tos = intel_pmu_lbr_tos();
int i;
+ int out = 0;
for (i = 0; i < x86_pmu.lbr_nr; i++) {
unsigned long lbr_idx = (tos - i) & mask;
@@ -306,15 +307,27 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
}
from = (u64)((((s64)from) << skip) >> skip);
- cpuc->lbr_entries[i].from = from;
- cpuc->lbr_entries[i].to = to;
- cpuc->lbr_entries[i].mispred = mis;
- cpuc->lbr_entries[i].predicted = pred;
- cpuc->lbr_entries[i].in_tx = in_tx;
- cpuc->lbr_entries[i].abort = abort;
- cpuc->lbr_entries[i].reserved = 0;
+ /*
+ * Some CPUs report duplicated abort records,
+ * with the second entry not having an abort bit set.
+ * Skip them here. This loop runs backwards,
+ * so we need to undo the previous record.
+ * If the abort just happened outside the window
+ * the extra entry cannot be removed.
+ */
+ if (abort && x86_pmu.lbr_double_abort && out > 0)
+ out--;
+
+ cpuc->lbr_entries[out].from = from;
+ cpuc->lbr_entries[out].to = to;
+ cpuc->lbr_entries[out].mispred = mis;
+ cpuc->lbr_entries[out].predicted = pred;
+ cpuc->lbr_entries[out].in_tx = in_tx;
+ cpuc->lbr_entries[out].abort = abort;
+ cpuc->lbr_entries[out].reserved = 0;
+ out++;
}
- cpuc->lbr_stack.nr = i;
+ cpuc->lbr_stack.nr = out;
}
void intel_pmu_lbr_read(void)
@@ -478,7 +491,7 @@ static int branch_type(unsigned long from, unsigned long to, int abort)
/* may fail if text not present */
bytes = copy_from_user_nmi(buf, (void __user *)from, size);
- if (bytes != size)
+ if (bytes != 0)
return X86_BR_NONE;
addr = buf;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 1fb6c72717b..29c248799ce 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -6,6 +6,8 @@ static struct intel_uncore_type **pci_uncores = empty_uncore;
/* pci bus to socket mapping */
static int pcibus_to_physid[256] = { [0 ... 255] = -1, };
+static struct pci_dev *extra_pci_dev[UNCORE_SOCKET_MAX][UNCORE_EXTRA_PCI_DEV_MAX];
+
static DEFINE_RAW_SPINLOCK(uncore_box_lock);
/* mask of cpus that collect uncore events */
@@ -45,6 +47,24 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(match_rds, match_rds, "config1:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid30, match_rnid30, "config1:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(match_rnid4, match_rnid4, "config1:31");
+DEFINE_UNCORE_FORMAT_ATTR(match_dnid, match_dnid, "config1:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(match_mc, match_mc, "config1:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(match_opc, match_opc, "config1:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(match_vnw, match_vnw, "config1:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(match0, match0, "config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(match1, match1, "config1:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rds, mask_rds, "config2:48-51");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid30, mask_rnid30, "config2:32-35");
+DEFINE_UNCORE_FORMAT_ATTR(mask_rnid4, mask_rnid4, "config2:31");
+DEFINE_UNCORE_FORMAT_ATTR(mask_dnid, mask_dnid, "config2:13-17");
+DEFINE_UNCORE_FORMAT_ATTR(mask_mc, mask_mc, "config2:9-12");
+DEFINE_UNCORE_FORMAT_ATTR(mask_opc, mask_opc, "config2:5-8");
+DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
+DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
{
@@ -281,7 +301,7 @@ static struct attribute *snbep_uncore_cbox_formats_attr[] = {
};
static struct attribute *snbep_uncore_pcu_formats_attr[] = {
- &format_attr_event.attr,
+ &format_attr_event_ext.attr,
&format_attr_occ_sel.attr,
&format_attr_edge.attr,
&format_attr_inv.attr,
@@ -301,6 +321,24 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = {
&format_attr_edge.attr,
&format_attr_inv.attr,
&format_attr_thresh8.attr,
+ &format_attr_match_rds.attr,
+ &format_attr_match_rnid30.attr,
+ &format_attr_match_rnid4.attr,
+ &format_attr_match_dnid.attr,
+ &format_attr_match_mc.attr,
+ &format_attr_match_opc.attr,
+ &format_attr_match_vnw.attr,
+ &format_attr_match0.attr,
+ &format_attr_match1.attr,
+ &format_attr_mask_rds.attr,
+ &format_attr_mask_rnid30.attr,
+ &format_attr_mask_rnid4.attr,
+ &format_attr_mask_dnid.attr,
+ &format_attr_mask_mc.attr,
+ &format_attr_mask_opc.attr,
+ &format_attr_mask_vnw.attr,
+ &format_attr_mask0.attr,
+ &format_attr_mask1.attr,
NULL,
};
@@ -356,13 +394,16 @@ static struct intel_uncore_ops snbep_uncore_msr_ops = {
SNBEP_UNCORE_MSR_OPS_COMMON_INIT(),
};
+#define SNBEP_UNCORE_PCI_OPS_COMMON_INIT() \
+ .init_box = snbep_uncore_pci_init_box, \
+ .disable_box = snbep_uncore_pci_disable_box, \
+ .enable_box = snbep_uncore_pci_enable_box, \
+ .disable_event = snbep_uncore_pci_disable_event, \
+ .read_counter = snbep_uncore_pci_read_counter
+
static struct intel_uncore_ops snbep_uncore_pci_ops = {
- .init_box = snbep_uncore_pci_init_box,
- .disable_box = snbep_uncore_pci_disable_box,
- .enable_box = snbep_uncore_pci_enable_box,
- .disable_event = snbep_uncore_pci_disable_event,
- .enable_event = snbep_uncore_pci_enable_event,
- .read_counter = snbep_uncore_pci_read_counter,
+ SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+ .enable_event = snbep_uncore_pci_enable_event, \
};
static struct event_constraint snbep_uncore_cbox_constraints[] = {
@@ -726,6 +767,61 @@ static struct intel_uncore_type *snbep_msr_uncores[] = {
NULL,
};
+enum {
+ SNBEP_PCI_QPI_PORT0_FILTER,
+ SNBEP_PCI_QPI_PORT1_FILTER,
+};
+
+static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if ((hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK) == 0x38) {
+ reg1->idx = 0;
+ reg1->reg = SNBEP_Q_Py_PCI_PMON_PKT_MATCH0;
+ reg1->config = event->attr.config1;
+ reg2->reg = SNBEP_Q_Py_PCI_PMON_PKT_MASK0;
+ reg2->config = event->attr.config2;
+ }
+ return 0;
+}
+
+static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+ struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+ struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+ if (reg1->idx != EXTRA_REG_NONE) {
+ int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
+ struct pci_dev *filter_pdev = extra_pci_dev[box->phys_id][idx];
+ WARN_ON_ONCE(!filter_pdev);
+ if (filter_pdev) {
+ pci_write_config_dword(filter_pdev, reg1->reg,
+ (u32)reg1->config);
+ pci_write_config_dword(filter_pdev, reg1->reg + 4,
+ (u32)(reg1->config >> 32));
+ pci_write_config_dword(filter_pdev, reg2->reg,
+ (u32)reg2->config);
+ pci_write_config_dword(filter_pdev, reg2->reg + 4,
+ (u32)(reg2->config >> 32));
+ }
+ }
+
+ pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static struct intel_uncore_ops snbep_uncore_qpi_ops = {
+ SNBEP_UNCORE_PCI_OPS_COMMON_INIT(),
+ .enable_event = snbep_qpi_enable_event,
+ .hw_config = snbep_qpi_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
#define SNBEP_UNCORE_PCI_COMMON_INIT() \
.perf_ctr = SNBEP_PCI_PMON_CTR0, \
.event_ctl = SNBEP_PCI_PMON_CTL0, \
@@ -755,17 +851,18 @@ static struct intel_uncore_type snbep_uncore_imc = {
};
static struct intel_uncore_type snbep_uncore_qpi = {
- .name = "qpi",
- .num_counters = 4,
- .num_boxes = 2,
- .perf_ctr_bits = 48,
- .perf_ctr = SNBEP_PCI_PMON_CTR0,
- .event_ctl = SNBEP_PCI_PMON_CTL0,
- .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
- .ops = &snbep_uncore_pci_ops,
- .event_descs = snbep_uncore_qpi_events,
- .format_group = &snbep_uncore_qpi_format_group,
+ .name = "qpi",
+ .num_counters = 4,
+ .num_boxes = 2,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &snbep_uncore_qpi_ops,
+ .event_descs = snbep_uncore_qpi_events,
+ .format_group = &snbep_uncore_qpi_format_group,
};
@@ -807,43 +904,53 @@ static struct intel_uncore_type *snbep_pci_uncores[] = {
static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = {
{ /* Home Agent */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA),
- .driver_data = SNBEP_PCI_UNCORE_HA,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_HA, 0),
},
{ /* MC Channel 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0),
- .driver_data = SNBEP_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 0),
},
{ /* MC Channel 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1),
- .driver_data = SNBEP_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 1),
},
{ /* MC Channel 2 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2),
- .driver_data = SNBEP_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 2),
},
{ /* MC Channel 3 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3),
- .driver_data = SNBEP_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_IMC, 3),
},
{ /* QPI Port 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0),
- .driver_data = SNBEP_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 0),
},
{ /* QPI Port 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1),
- .driver_data = SNBEP_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_QPI, 1),
},
{ /* R2PCIe */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE),
- .driver_data = SNBEP_PCI_UNCORE_R2PCIE,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R2PCIE, 0),
},
{ /* R3QPI Link 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0),
- .driver_data = SNBEP_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 0),
},
{ /* R3QPI Link 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1),
- .driver_data = SNBEP_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(SNBEP_PCI_UNCORE_R3QPI, 1),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c86),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT0_FILTER),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x3c96),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT1_FILTER),
},
{ /* end: all zeroes */ }
};
@@ -890,6 +997,20 @@ static int snbep_pci2phy_map_init(int devid)
}
}
+ if (!err) {
+ /*
+ * For PCI bus with no UBOX device, find the next bus
+ * that has UBOX device and use its mapping.
+ */
+ i = -1;
+ for (bus = 255; bus >= 0; bus--) {
+ if (pcibus_to_physid[bus] >= 0)
+ i = pcibus_to_physid[bus];
+ else
+ pcibus_to_physid[bus] = i;
+ }
+ }
+
if (ubox_dev)
pci_dev_put(ubox_dev);
@@ -992,6 +1113,24 @@ static struct attribute *ivt_uncore_qpi_formats_attr[] = {
&format_attr_umask.attr,
&format_attr_edge.attr,
&format_attr_thresh8.attr,
+ &format_attr_match_rds.attr,
+ &format_attr_match_rnid30.attr,
+ &format_attr_match_rnid4.attr,
+ &format_attr_match_dnid.attr,
+ &format_attr_match_mc.attr,
+ &format_attr_match_opc.attr,
+ &format_attr_match_vnw.attr,
+ &format_attr_match0.attr,
+ &format_attr_match1.attr,
+ &format_attr_mask_rds.attr,
+ &format_attr_mask_rnid30.attr,
+ &format_attr_mask_rnid4.attr,
+ &format_attr_mask_dnid.attr,
+ &format_attr_mask_mc.attr,
+ &format_attr_mask_opc.attr,
+ &format_attr_mask_vnw.attr,
+ &format_attr_mask0.attr,
+ &format_attr_mask1.attr,
NULL,
};
@@ -1205,17 +1344,83 @@ static struct intel_uncore_type ivt_uncore_imc = {
IVT_UNCORE_PCI_COMMON_INIT(),
};
+/* registers in IRP boxes are not properly aligned */
+static unsigned ivt_uncore_irp_ctls[] = {0xd8, 0xdc, 0xe0, 0xe4};
+static unsigned ivt_uncore_irp_ctrs[] = {0xa0, 0xb0, 0xb8, 0xc0};
+
+static void ivt_uncore_irp_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx],
+ hwc->config | SNBEP_PMON_CTL_EN);
+}
+
+static void ivt_uncore_irp_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+
+ pci_write_config_dword(pdev, ivt_uncore_irp_ctls[hwc->idx], hwc->config);
+}
+
+static u64 ivt_uncore_irp_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+ struct pci_dev *pdev = box->pci_dev;
+ struct hw_perf_event *hwc = &event->hw;
+ u64 count = 0;
+
+ pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx], (u32 *)&count);
+ pci_read_config_dword(pdev, ivt_uncore_irp_ctrs[hwc->idx] + 4, (u32 *)&count + 1);
+
+ return count;
+}
+
+static struct intel_uncore_ops ivt_uncore_irp_ops = {
+ .init_box = ivt_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = ivt_uncore_irp_disable_event,
+ .enable_event = ivt_uncore_irp_enable_event,
+ .read_counter = ivt_uncore_irp_read_counter,
+};
+
+static struct intel_uncore_type ivt_uncore_irp = {
+ .name = "irp",
+ .num_counters = 4,
+ .num_boxes = 1,
+ .perf_ctr_bits = 48,
+ .event_mask = IVT_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .ops = &ivt_uncore_irp_ops,
+ .format_group = &ivt_uncore_format_group,
+};
+
+static struct intel_uncore_ops ivt_uncore_qpi_ops = {
+ .init_box = ivt_uncore_pci_init_box,
+ .disable_box = snbep_uncore_pci_disable_box,
+ .enable_box = snbep_uncore_pci_enable_box,
+ .disable_event = snbep_uncore_pci_disable_event,
+ .enable_event = snbep_qpi_enable_event,
+ .read_counter = snbep_uncore_pci_read_counter,
+ .hw_config = snbep_qpi_hw_config,
+ .get_constraint = uncore_get_constraint,
+ .put_constraint = uncore_put_constraint,
+};
+
static struct intel_uncore_type ivt_uncore_qpi = {
- .name = "qpi",
- .num_counters = 4,
- .num_boxes = 3,
- .perf_ctr_bits = 48,
- .perf_ctr = SNBEP_PCI_PMON_CTR0,
- .event_ctl = SNBEP_PCI_PMON_CTL0,
- .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK,
- .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
- .ops = &ivt_uncore_pci_ops,
- .format_group = &ivt_uncore_qpi_format_group,
+ .name = "qpi",
+ .num_counters = 4,
+ .num_boxes = 3,
+ .perf_ctr_bits = 48,
+ .perf_ctr = SNBEP_PCI_PMON_CTR0,
+ .event_ctl = SNBEP_PCI_PMON_CTL0,
+ .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK,
+ .box_ctl = SNBEP_PCI_PMON_BOX_CTL,
+ .num_shared_regs = 1,
+ .ops = &ivt_uncore_qpi_ops,
+ .format_group = &ivt_uncore_qpi_format_group,
};
static struct intel_uncore_type ivt_uncore_r2pcie = {
@@ -1239,6 +1444,7 @@ static struct intel_uncore_type ivt_uncore_r3qpi = {
enum {
IVT_PCI_UNCORE_HA,
IVT_PCI_UNCORE_IMC,
+ IVT_PCI_UNCORE_IRP,
IVT_PCI_UNCORE_QPI,
IVT_PCI_UNCORE_R2PCIE,
IVT_PCI_UNCORE_R3QPI,
@@ -1247,6 +1453,7 @@ enum {
static struct intel_uncore_type *ivt_pci_uncores[] = {
[IVT_PCI_UNCORE_HA] = &ivt_uncore_ha,
[IVT_PCI_UNCORE_IMC] = &ivt_uncore_imc,
+ [IVT_PCI_UNCORE_IRP] = &ivt_uncore_irp,
[IVT_PCI_UNCORE_QPI] = &ivt_uncore_qpi,
[IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie,
[IVT_PCI_UNCORE_R3QPI] = &ivt_uncore_r3qpi,
@@ -1256,71 +1463,85 @@ static struct intel_uncore_type *ivt_pci_uncores[] = {
static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = {
{ /* Home Agent 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30),
- .driver_data = IVT_PCI_UNCORE_HA,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 0),
},
{ /* Home Agent 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38),
- .driver_data = IVT_PCI_UNCORE_HA,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_HA, 1),
},
{ /* MC0 Channel 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 0),
},
{ /* MC0 Channel 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 1),
},
{ /* MC0 Channel 3 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 2),
},
{ /* MC0 Channel 4 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 3),
},
{ /* MC1 Channel 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 4),
},
{ /* MC1 Channel 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 5),
},
{ /* MC1 Channel 3 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 6),
},
{ /* MC1 Channel 4 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1),
- .driver_data = IVT_PCI_UNCORE_IMC,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IMC, 7),
+ },
+ { /* IRP */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe39),
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_IRP, 0),
},
{ /* QPI0 Port 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32),
- .driver_data = IVT_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 0),
},
{ /* QPI0 Port 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33),
- .driver_data = IVT_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 1),
},
{ /* QPI1 Port 2 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a),
- .driver_data = IVT_PCI_UNCORE_QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_QPI, 2),
},
{ /* R2PCIe */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34),
- .driver_data = IVT_PCI_UNCORE_R2PCIE,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R2PCIE, 0),
},
{ /* R3QPI0 Link 0 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36),
- .driver_data = IVT_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 0),
},
{ /* R3QPI0 Link 1 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37),
- .driver_data = IVT_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 1),
},
{ /* R3QPI1 Link 2 */
PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e),
- .driver_data = IVT_PCI_UNCORE_R3QPI,
+ .driver_data = UNCORE_PCI_DEV_DATA(IVT_PCI_UNCORE_R3QPI, 2),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe86),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT0_FILTER),
+ },
+ { /* QPI Port 0 filter */
+ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe96),
+ .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+ SNBEP_PCI_QPI_PORT1_FILTER),
},
{ /* end: all zeroes */ }
};
@@ -2599,14 +2820,14 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
box->hrtimer.function = uncore_pmu_hrtimer;
}
-struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
+static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int node)
{
struct intel_uncore_box *box;
int i, size;
size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
- box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu));
+ box = kzalloc_node(size, GFP_KERNEL, node);
if (!box)
return NULL;
@@ -2701,7 +2922,7 @@ uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *eve
return c;
}
- if (event->hw.config == ~0ULL)
+ if (event->attr.config == UNCORE_FIXED_EVENT)
return &constraint_fixed;
if (type->constraints) {
@@ -2924,7 +3145,7 @@ static int uncore_validate_group(struct intel_uncore_pmu *pmu,
struct intel_uncore_box *fake_box;
int ret = -EINVAL, n;
- fake_box = uncore_alloc_box(pmu->type, smp_processor_id());
+ fake_box = uncore_alloc_box(pmu->type, NUMA_NO_NODE);
if (!fake_box)
return -ENOMEM;
@@ -3005,7 +3226,9 @@ static int uncore_pmu_event_init(struct perf_event *event)
*/
if (pmu->type->single_fixed && pmu->pmu_idx > 0)
return -EINVAL;
- hwc->config = ~0ULL;
+
+ /* fixed counters have event field hardcoded to zero */
+ hwc->config = 0ULL;
} else {
hwc->config = event->attr.config & pmu->type->event_mask;
if (pmu->type->ops->hw_config) {
@@ -3167,17 +3390,25 @@ static bool pcidrv_registered;
/*
* add a pci uncore device
*/
-static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
+static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
{
struct intel_uncore_pmu *pmu;
struct intel_uncore_box *box;
- int i, phys_id;
+ struct intel_uncore_type *type;
+ int phys_id;
phys_id = pcibus_to_physid[pdev->bus->number];
if (phys_id < 0)
return -ENODEV;
- box = uncore_alloc_box(type, 0);
+ if (UNCORE_PCI_DEV_TYPE(id->driver_data) == UNCORE_EXTRA_PCI_DEV) {
+ extra_pci_dev[phys_id][UNCORE_PCI_DEV_IDX(id->driver_data)] = pdev;
+ pci_set_drvdata(pdev, NULL);
+ return 0;
+ }
+
+ type = pci_uncores[UNCORE_PCI_DEV_TYPE(id->driver_data)];
+ box = uncore_alloc_box(type, NUMA_NO_NODE);
if (!box)
return -ENOMEM;
@@ -3185,21 +3416,11 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
* for performance monitoring unit with multiple boxes,
* each box has a different function id.
*/
- for (i = 0; i < type->num_boxes; i++) {
- pmu = &type->pmus[i];
- if (pmu->func_id == pdev->devfn)
- break;
- if (pmu->func_id < 0) {
- pmu->func_id = pdev->devfn;
- break;
- }
- pmu = NULL;
- }
-
- if (!pmu) {
- kfree(box);
- return -EINVAL;
- }
+ pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)];
+ if (pmu->func_id < 0)
+ pmu->func_id = pdev->devfn;
+ else
+ WARN_ON_ONCE(pmu->func_id != pdev->devfn);
box->phys_id = phys_id;
box->pci_dev = pdev;
@@ -3217,9 +3438,22 @@ static int uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
static void uncore_pci_remove(struct pci_dev *pdev)
{
struct intel_uncore_box *box = pci_get_drvdata(pdev);
- struct intel_uncore_pmu *pmu = box->pmu;
- int cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+ struct intel_uncore_pmu *pmu;
+ int i, cpu, phys_id = pcibus_to_physid[pdev->bus->number];
+
+ box = pci_get_drvdata(pdev);
+ if (!box) {
+ for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
+ if (extra_pci_dev[phys_id][i] == pdev) {
+ extra_pci_dev[phys_id][i] = NULL;
+ break;
+ }
+ }
+ WARN_ON_ONCE(i >= UNCORE_EXTRA_PCI_DEV_MAX);
+ return;
+ }
+ pmu = box->pmu;
if (WARN_ON_ONCE(phys_id != box->phys_id))
return;
@@ -3240,12 +3474,6 @@ static void uncore_pci_remove(struct pci_dev *pdev)
kfree(box);
}
-static int uncore_pci_probe(struct pci_dev *pdev,
- const struct pci_device_id *id)
-{
- return uncore_pci_add(pci_uncores[id->driver_data], pdev);
-}
-
static int __init uncore_pci_init(void)
{
int ret;
@@ -3385,7 +3613,7 @@ static int uncore_cpu_prepare(int cpu, int phys_id)
if (pmu->func_id < 0)
pmu->func_id = j;
- box = uncore_alloc_box(type, cpu);
+ box = uncore_alloc_box(type, cpu_to_node(cpu));
if (!box)
return -ENOMEM;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 47b3d00c9d8..a80ab71a883 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -12,6 +12,15 @@
#define UNCORE_PMC_IDX_FIXED UNCORE_PMC_IDX_MAX_GENERIC
#define UNCORE_PMC_IDX_MAX (UNCORE_PMC_IDX_FIXED + 1)
+#define UNCORE_PCI_DEV_DATA(type, idx) ((type << 8) | idx)
+#define UNCORE_PCI_DEV_TYPE(data) ((data >> 8) & 0xff)
+#define UNCORE_PCI_DEV_IDX(data) (data & 0xff)
+#define UNCORE_EXTRA_PCI_DEV 0xff
+#define UNCORE_EXTRA_PCI_DEV_MAX 2
+
+/* support up to 8 sockets */
+#define UNCORE_SOCKET_MAX 8
+
#define UNCORE_EVENT_CONSTRAINT(c, n) EVENT_CONSTRAINT(c, n, 0xff)
/* SNB event control */
@@ -108,6 +117,7 @@
(SNBEP_PMON_CTL_EV_SEL_MASK | \
SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \
SNBEP_PMON_CTL_EDGE_DET | \
+ SNBEP_PMON_CTL_EV_SEL_EXT | \
SNBEP_PMON_CTL_INVERT | \
SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \
SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index aee6317b902..06fe3ed8b85 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -11,15 +11,12 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
unsigned int cpu)
{
#ifdef CONFIG_SMP
- if (c->x86_max_cores * smp_num_siblings > 1) {
- seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
- seq_printf(m, "siblings\t: %d\n",
- cpumask_weight(cpu_core_mask(cpu)));
- seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
- seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
- seq_printf(m, "apicid\t\t: %d\n", c->apicid);
- seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid);
- }
+ seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
+ seq_printf(m, "siblings\t: %d\n", cpumask_weight(cpu_core_mask(cpu)));
+ seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
+ seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
+ seq_printf(m, "apicid\t\t: %d\n", c->apicid);
+ seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid);
#endif
}
diff --git a/arch/x86/kernel/cpu/umc.c b/arch/x86/kernel/cpu/umc.c
index 202759a1412..75c5ad5d35c 100644
--- a/arch/x86/kernel/cpu/umc.c
+++ b/arch/x86/kernel/cpu/umc.c
@@ -11,8 +11,8 @@
static const struct cpu_dev umc_cpu_dev = {
.c_vendor = "UMC",
.c_ident = { "UMC UMC UMC" },
- .c_models = {
- { .vendor = X86_VENDOR_UMC, .family = 4, .model_names =
+ .legacy_models = {
+ { .family = 4, .model_names =
{
[1] = "U5D",
[2] = "U5S",
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 7076878404e..628a059a9a0 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -93,7 +93,7 @@ static void __init vmware_platform_setup(void)
* serial key should be enough, as this will always have a VMware
* specific string when running under VMware hypervisor.
*/
-static bool __init vmware_platform(void)
+static uint32_t __init vmware_platform(void)
{
if (cpu_has_hypervisor) {
unsigned int eax;
@@ -102,12 +102,12 @@ static bool __init vmware_platform(void)
cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &hyper_vendor_id[0],
&hyper_vendor_id[1], &hyper_vendor_id[2]);
if (!memcmp(hyper_vendor_id, "VMwareVMware", 12))
- return true;
+ return CPUID_VMWARE_INFO_LEAF;
} else if (dmi_available && dmi_name_in_serial("VMware") &&
__vmware_platform())
- return true;
+ return 1;
- return false;
+ return 0;
}
/*
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 74467feb4dc..18677a90d6a 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -127,10 +127,12 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
cpu_emergency_vmxoff();
cpu_emergency_svm_disable();
- lapic_shutdown();
-#if defined(CONFIG_X86_IO_APIC)
+#ifdef CONFIG_X86_IO_APIC
+ /* Prevent crash_kexec() from deadlocking on ioapic_lock. */
+ ioapic_zap_locks();
disable_IO_APIC();
#endif
+ lapic_shutdown();
#ifdef CONFIG_HPET_TIMER
hpet_disable();
#endif
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 69eb2fa2549..376dc787344 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -52,8 +52,7 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
}
#ifdef CONFIG_BLK_DEV_INITRD
-void __init early_init_dt_setup_initrd_arch(unsigned long start,
- unsigned long end)
+void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
{
initrd_start = (unsigned long)__va(start);
initrd_end = (unsigned long)__va(end);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index d32abeabbda..174da5fc5a7 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -658,15 +658,18 @@ __init void e820_setup_gap(void)
* boot_params.e820_map, others are passed via SETUP_E820_EXT node of
* linked list of struct setup_data, which is parsed here.
*/
-void __init parse_e820_ext(struct setup_data *sdata)
+void __init parse_e820_ext(u64 phys_addr, u32 data_len)
{
int entries;
struct e820entry *extmap;
+ struct setup_data *sdata;
+ sdata = early_memremap(phys_addr, data_len);
entries = sdata->len / sizeof(struct e820entry);
extmap = (struct e820entry *)(sdata->data);
__append_e820_map(extmap, entries);
sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map);
+ early_iounmap(sdata, data_len);
printk(KERN_INFO "e820: extended physical RAM map:\n");
e820_print_map("extended");
}
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 63bdb29b254..b3cd3ebae07 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -12,6 +12,7 @@
#include <linux/pci.h>
#include <linux/acpi.h>
#include <linux/pci_ids.h>
+#include <drm/i915_drm.h>
#include <asm/pci-direct.h>
#include <asm/dma.h>
#include <asm/io_apic.h>
@@ -216,6 +217,157 @@ static void __init intel_remapping_check(int num, int slot, int func)
}
+/*
+ * Systems with Intel graphics controllers set aside memory exclusively
+ * for gfx driver use. This memory is not marked in the E820 as reserved
+ * or as RAM, and so is subject to overlap from E820 manipulation later
+ * in the boot process. On some systems, MMIO space is allocated on top,
+ * despite the efforts of the "RAM buffer" approach, which simply rounds
+ * memory boundaries up to 64M to try to catch space that may decode
+ * as RAM and so is not suitable for MMIO.
+ *
+ * And yes, so far on current devices the base addr is always under 4G.
+ */
+static u32 __init intel_stolen_base(int num, int slot, int func)
+{
+ u32 base;
+
+ /*
+ * For the PCI IDs in this quirk, the stolen base is always
+ * in 0x5c, aka the BDSM register (yes that's really what
+ * it's called).
+ */
+ base = read_pci_config(num, slot, func, 0x5c);
+ base &= ~((1<<20) - 1);
+
+ return base;
+}
+
+#define KB(x) ((x) * 1024)
+#define MB(x) (KB (KB (x)))
+#define GB(x) (MB (KB (x)))
+
+static size_t __init gen3_stolen_size(int num, int slot, int func)
+{
+ size_t stolen_size;
+ u16 gmch_ctrl;
+
+ gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL);
+
+ switch (gmch_ctrl & I855_GMCH_GMS_MASK) {
+ case I855_GMCH_GMS_STOLEN_1M:
+ stolen_size = MB(1);
+ break;
+ case I855_GMCH_GMS_STOLEN_4M:
+ stolen_size = MB(4);
+ break;
+ case I855_GMCH_GMS_STOLEN_8M:
+ stolen_size = MB(8);
+ break;
+ case I855_GMCH_GMS_STOLEN_16M:
+ stolen_size = MB(16);
+ break;
+ case I855_GMCH_GMS_STOLEN_32M:
+ stolen_size = MB(32);
+ break;
+ case I915_GMCH_GMS_STOLEN_48M:
+ stolen_size = MB(48);
+ break;
+ case I915_GMCH_GMS_STOLEN_64M:
+ stolen_size = MB(64);
+ break;
+ case G33_GMCH_GMS_STOLEN_128M:
+ stolen_size = MB(128);
+ break;
+ case G33_GMCH_GMS_STOLEN_256M:
+ stolen_size = MB(256);
+ break;
+ case INTEL_GMCH_GMS_STOLEN_96M:
+ stolen_size = MB(96);
+ break;
+ case INTEL_GMCH_GMS_STOLEN_160M:
+ stolen_size = MB(160);
+ break;
+ case INTEL_GMCH_GMS_STOLEN_224M:
+ stolen_size = MB(224);
+ break;
+ case INTEL_GMCH_GMS_STOLEN_352M:
+ stolen_size = MB(352);
+ break;
+ default:
+ stolen_size = 0;
+ break;
+ }
+
+ return stolen_size;
+}
+
+static size_t __init gen6_stolen_size(int num, int slot, int func)
+{
+ u16 gmch_ctrl;
+
+ gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL);
+ gmch_ctrl >>= SNB_GMCH_GMS_SHIFT;
+ gmch_ctrl &= SNB_GMCH_GMS_MASK;
+
+ return gmch_ctrl << 25; /* 32 MB units */
+}
+
+typedef size_t (*stolen_size_fn)(int num, int slot, int func);
+
+static struct pci_device_id intel_stolen_ids[] __initdata = {
+ INTEL_I915G_IDS(gen3_stolen_size),
+ INTEL_I915GM_IDS(gen3_stolen_size),
+ INTEL_I945G_IDS(gen3_stolen_size),
+ INTEL_I945GM_IDS(gen3_stolen_size),
+ INTEL_VLV_M_IDS(gen3_stolen_size),
+ INTEL_VLV_D_IDS(gen3_stolen_size),
+ INTEL_PINEVIEW_IDS(gen3_stolen_size),
+ INTEL_I965G_IDS(gen3_stolen_size),
+ INTEL_G33_IDS(gen3_stolen_size),
+ INTEL_I965GM_IDS(gen3_stolen_size),
+ INTEL_GM45_IDS(gen3_stolen_size),
+ INTEL_G45_IDS(gen3_stolen_size),
+ INTEL_IRONLAKE_D_IDS(gen3_stolen_size),
+ INTEL_IRONLAKE_M_IDS(gen3_stolen_size),
+ INTEL_SNB_D_IDS(gen6_stolen_size),
+ INTEL_SNB_M_IDS(gen6_stolen_size),
+ INTEL_IVB_M_IDS(gen6_stolen_size),
+ INTEL_IVB_D_IDS(gen6_stolen_size),
+ INTEL_HSW_D_IDS(gen6_stolen_size),
+ INTEL_HSW_M_IDS(gen6_stolen_size),
+};
+
+static void __init intel_graphics_stolen(int num, int slot, int func)
+{
+ size_t size;
+ int i;
+ u32 start;
+ u16 device, subvendor, subdevice;
+
+ device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID);
+ subvendor = read_pci_config_16(num, slot, func,
+ PCI_SUBSYSTEM_VENDOR_ID);
+ subdevice = read_pci_config_16(num, slot, func, PCI_SUBSYSTEM_ID);
+
+ for (i = 0; i < ARRAY_SIZE(intel_stolen_ids); i++) {
+ if (intel_stolen_ids[i].device == device) {
+ stolen_size_fn stolen_size =
+ (stolen_size_fn)intel_stolen_ids[i].driver_data;
+ size = stolen_size(num, slot, func);
+ start = intel_stolen_base(num, slot, func);
+ if (size && start) {
+ /* Mark this space as reserved */
+ e820_add_region(start, size, E820_RESERVED);
+ sanitize_e820_map(e820.map,
+ ARRAY_SIZE(e820.map),
+ &e820.nr_map);
+ }
+ return;
+ }
+ }
+}
+
#define QFLAG_APPLY_ONCE 0x1
#define QFLAG_APPLIED 0x2
#define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -251,6 +403,8 @@ static struct chipset early_qrk[] __initdata = {
PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
{ PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
+ { PCI_VENDOR_ID_INTEL, PCI_ANY_ID, PCI_CLASS_DISPLAY_VGA, PCI_ANY_ID,
+ QFLAG_APPLY_ONCE, intel_graphics_stolen },
{}
};
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index d15f575a861..01d1c187c9f 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -14,9 +14,11 @@
#include <xen/hvc-console.h>
#include <asm/pci-direct.h>
#include <asm/fixmap.h>
-#include <asm/mrst.h>
+#include <asm/intel-mid.h>
#include <asm/pgtable.h>
#include <linux/usb/ehci_def.h>
+#include <linux/efi.h>
+#include <asm/efi.h>
/* Simple VGA output */
#define VGABASE (__ISA_IO_base + 0xb8000)
@@ -234,6 +236,11 @@ static int __init setup_early_printk(char *buf)
early_console_register(&early_hsu_console, keep);
}
#endif
+#ifdef CONFIG_EARLY_PRINTK_EFI
+ if (!strncmp(buf, "efi", 3))
+ early_console_register(&early_efi_console, keep);
+#endif
+
buf++;
}
return 0;
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 2cfbc3a3a2d..fd1bc1b15e6 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -362,12 +362,9 @@ END(ret_from_exception)
#ifdef CONFIG_PREEMPT
ENTRY(resume_kernel)
DISABLE_INTERRUPTS(CLBR_ANY)
- cmpl $0,TI_preempt_count(%ebp) # non-zero preempt_count ?
- jnz restore_all
need_resched:
- movl TI_flags(%ebp), %ecx # need_resched set ?
- testb $_TIF_NEED_RESCHED, %cl
- jz restore_all
+ cmpl $0,PER_CPU_VAR(__preempt_count)
+ jnz restore_all
testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ?
jz restore_all
call preempt_schedule_irq
@@ -1176,6 +1173,9 @@ ftrace_restore_flags:
#else /* ! CONFIG_DYNAMIC_FTRACE */
ENTRY(mcount)
+ cmpl $__PAGE_OFFSET, %esp
+ jb ftrace_stub /* Paging not enabled yet? */
+
cmpl $0, function_trace_stop
jne ftrace_stub
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1b69951a81e..603be7c7067 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -487,21 +487,6 @@ ENDPROC(native_usergs_sysret64)
TRACE_IRQS_OFF
.endm
-ENTRY(save_rest)
- 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
- movq_cfi r12, R12+16
- movq_cfi r13, R13+16
- movq_cfi r14, R14+16
- movq_cfi r15, R15+16
- movq %r11, 8(%rsp) /* return address */
- FIXUP_TOP_OF_STACK %r11, 16
- ret
- CFI_ENDPROC
-END(save_rest)
-
/* save complete stack frame */
.pushsection .kprobes.text, "ax"
ENTRY(save_paranoid)
@@ -1118,10 +1103,8 @@ retint_signal:
/* Returning to kernel space. Check if we need preemption */
/* rcx: threadinfo. interrupts off. */
ENTRY(retint_kernel)
- cmpl $0,TI_preempt_count(%rcx)
+ cmpl $0,PER_CPU_VAR(__preempt_count)
jnz retint_restore_args
- bt $TIF_NEED_RESCHED,TI_flags(%rcx)
- jnc retint_restore_args
bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */
jnc retint_restore_args
call preempt_schedule_irq
@@ -1357,7 +1340,7 @@ bad_gs:
.previous
/* Call softirq on interrupt stack. Interrupts are off. */
-ENTRY(call_softirq)
+ENTRY(do_softirq_own_stack)
CFI_STARTPROC
pushq_cfi %rbp
CFI_REL_OFFSET rbp,0
@@ -1374,7 +1357,7 @@ ENTRY(call_softirq)
decl PER_CPU_VAR(irq_count)
ret
CFI_ENDPROC
-END(call_softirq)
+END(do_softirq_own_stack)
#ifdef CONFIG_XEN
zeroentry xen_hypervisor_callback xen_do_hypervisor_callback
diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c
index 138463a2487..c61a14a4a31 100644
--- a/arch/x86/kernel/head32.c
+++ b/arch/x86/kernel/head32.c
@@ -29,14 +29,14 @@ static void __init i386_default_early_setup(void)
reserve_ebda_region();
}
-void __init i386_start_kernel(void)
+asmlinkage void __init i386_start_kernel(void)
{
sanitize_boot_params(&boot_params);
/* Call the subarch specific early setup function */
switch (boot_params.hdr.hardware_subarch) {
- case X86_SUBARCH_MRST:
- x86_mrst_early_setup();
+ case X86_SUBARCH_INTEL_MID:
+ x86_intel_mid_early_setup();
break;
case X86_SUBARCH_CE4100:
x86_ce4100_early_setup();
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 55b67614ed9..1be8e43b669 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -137,7 +137,7 @@ static void __init copy_bootdata(char *real_mode_data)
}
}
-void __init x86_64_start_kernel(char * real_mode_data)
+asmlinkage void __init x86_64_start_kernel(char * real_mode_data)
{
int i;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 5dd87a89f01..81ba27679f1 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -409,6 +409,7 @@ enable_paging:
/*
* Check if it is 486
*/
+ movb $4,X86 # at least 486
cmpl $-1,X86_CPUID
je is486
@@ -436,7 +437,6 @@ enable_paging:
movl %edx,X86_CAPABILITY
is486:
- movb $4,X86
movl $0x50022,%ecx # set AM, WP, NE and MP
movl %cr0,%eax
andl $0x80000011,%eax # Save PG,PE,ET
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 0fa69127209..05fd74f537d 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -37,3 +37,10 @@ EXPORT_SYMBOL(strstr);
EXPORT_SYMBOL(csum_partial);
EXPORT_SYMBOL(empty_zero_page);
+
+#ifdef CONFIG_PREEMPT
+EXPORT_SYMBOL(___preempt_schedule);
+#ifdef CONFIG_CONTEXT_TRACKING
+EXPORT_SYMBOL(___preempt_schedule_context);
+#endif
+#endif
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 9a5c460404d..2e977b5d61d 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -312,8 +312,7 @@ static void init_8259A(int auto_eoi)
*/
outb_pic(0x11, PIC_MASTER_CMD); /* ICW1: select 8259A-1 init */
- /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 on x86-64,
- to 0x20-0x27 on i386 */
+ /* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
/* 8259A-1 (the master) has a slave on IR2 */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 3a8185c042a..22d0687e7fd 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -177,7 +177,7 @@ u64 arch_irq_stat(void)
* SMP cross-CPU interrupts have their own specific
* handlers).
*/
-unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
+__visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
@@ -215,7 +215,7 @@ void __smp_x86_platform_ipi(void)
x86_platform_ipi_callback();
}
-void smp_x86_platform_ipi(struct pt_regs *regs)
+__visible void smp_x86_platform_ipi(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
@@ -229,7 +229,7 @@ void smp_x86_platform_ipi(struct pt_regs *regs)
/*
* Handler for POSTED_INTERRUPT_VECTOR.
*/
-void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
+__visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
@@ -247,7 +247,7 @@ void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
}
#endif
-void smp_trace_x86_platform_ipi(struct pt_regs *regs)
+__visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 4186755f1d7..d7fcbedc9c4 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -100,9 +100,6 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
irqctx->tinfo.task = curctx->tinfo.task;
irqctx->tinfo.previous_esp = current_stack_pointer;
- /* Copy the preempt_count so that the [soft]irq checks work. */
- irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count;
-
if (unlikely(overflow))
call_on_stack(print_stack_overflow, isp);
@@ -131,7 +128,6 @@ void irq_ctx_init(int cpu)
THREAD_SIZE_ORDER));
memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
irqctx->tinfo.cpu = cpu;
- irqctx->tinfo.preempt_count = HARDIRQ_OFFSET;
irqctx->tinfo.addr_limit = MAKE_MM_SEG(0);
per_cpu(hardirq_ctx, cpu) = irqctx;
@@ -149,35 +145,21 @@ void irq_ctx_init(int cpu)
cpu, per_cpu(hardirq_ctx, cpu), per_cpu(softirq_ctx, cpu));
}
-asmlinkage void do_softirq(void)
+void do_softirq_own_stack(void)
{
- unsigned long flags;
struct thread_info *curctx;
union irq_ctx *irqctx;
u32 *isp;
- if (in_interrupt())
- return;
-
- local_irq_save(flags);
-
- if (local_softirq_pending()) {
- curctx = current_thread_info();
- irqctx = __this_cpu_read(softirq_ctx);
- irqctx->tinfo.task = curctx->task;
- irqctx->tinfo.previous_esp = current_stack_pointer;
-
- /* build the stack frame on the softirq stack */
- isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
+ curctx = current_thread_info();
+ irqctx = __this_cpu_read(softirq_ctx);
+ irqctx->tinfo.task = curctx->task;
+ irqctx->tinfo.previous_esp = current_stack_pointer;
- call_on_stack(__do_softirq, isp);
- /*
- * Shouldn't happen, we returned above if in_interrupt():
- */
- WARN_ON_ONCE(softirq_count());
- }
+ /* build the stack frame on the softirq stack */
+ isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
- local_irq_restore(flags);
+ call_on_stack(__do_softirq, isp);
}
bool handle_irq(unsigned irq, struct pt_regs *regs)
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index d04d3ecded6..4d1c746892e 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -87,24 +87,3 @@ bool handle_irq(unsigned irq, struct pt_regs *regs)
generic_handle_irq_desc(irq, desc);
return true;
}
-
-
-extern void call_softirq(void);
-
-asmlinkage void do_softirq(void)
-{
- __u32 pending;
- unsigned long flags;
-
- if (in_interrupt())
- return;
-
- local_irq_save(flags);
- pending = local_softirq_pending();
- /* Switch to interrupt stack */
- if (pending) {
- call_softirq();
- WARN_ON_ONCE(softirq_count());
- }
- local_irq_restore(flags);
-}
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index 636a55e4a13..1de84e3ab4e 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -22,14 +22,14 @@ static inline void __smp_irq_work_interrupt(void)
irq_work_run();
}
-void smp_irq_work_interrupt(struct pt_regs *regs)
+__visible void smp_irq_work_interrupt(struct pt_regs *regs)
{
irq_work_entering_irq();
__smp_irq_work_interrupt();
exiting_irq();
}
-void smp_trace_irq_work_interrupt(struct pt_regs *regs)
+__visible void smp_trace_irq_work_interrupt(struct pt_regs *regs)
{
irq_work_entering_irq();
trace_irq_work_entry(IRQ_WORK_VECTOR);
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 2889b3d4388..ee11b7dfbfb 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -24,20 +24,71 @@ union jump_code_union {
} __attribute__((packed));
};
+static void bug_at(unsigned char *ip, int line)
+{
+ /*
+ * The location is not an op that we were expecting.
+ * Something went wrong. Crash the box, as something could be
+ * corrupting the kernel.
+ */
+ pr_warning("Unexpected op at %pS [%p] (%02x %02x %02x %02x %02x) %s:%d\n",
+ ip, ip, ip[0], ip[1], ip[2], ip[3], ip[4], __FILE__, line);
+ BUG();
+}
+
static void __jump_label_transform(struct jump_entry *entry,
enum jump_label_type type,
- void *(*poker)(void *, const void *, size_t))
+ void *(*poker)(void *, const void *, size_t),
+ int init)
{
union jump_code_union code;
+ const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
if (type == JUMP_LABEL_ENABLE) {
+ /*
+ * We are enabling this jump label. If it is not a nop
+ * then something must have gone wrong.
+ */
+ if (unlikely(memcmp((void *)entry->code, ideal_nop, 5) != 0))
+ bug_at((void *)entry->code, __LINE__);
+
code.jump = 0xe9;
code.offset = entry->target -
(entry->code + JUMP_LABEL_NOP_SIZE);
- } else
+ } else {
+ /*
+ * We are disabling this jump label. If it is not what
+ * we think it is, then something must have gone wrong.
+ * If this is the first initialization call, then we
+ * are converting the default nop to the ideal nop.
+ */
+ if (init) {
+ const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
+ if (unlikely(memcmp((void *)entry->code, default_nop, 5) != 0))
+ bug_at((void *)entry->code, __LINE__);
+ } else {
+ code.jump = 0xe9;
+ code.offset = entry->target -
+ (entry->code + JUMP_LABEL_NOP_SIZE);
+ if (unlikely(memcmp((void *)entry->code, &code, 5) != 0))
+ bug_at((void *)entry->code, __LINE__);
+ }
memcpy(&code, ideal_nops[NOP_ATOMIC5], JUMP_LABEL_NOP_SIZE);
+ }
- (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
+ /*
+ * Make text_poke_bp() a default fallback poker.
+ *
+ * At the time the change is being done, just ignore whether we
+ * are doing nop -> jump or jump -> nop transition, and assume
+ * always nop being the 'currently valid' instruction
+ *
+ */
+ if (poker)
+ (*poker)((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE);
+ else
+ text_poke_bp((void *)entry->code, &code, JUMP_LABEL_NOP_SIZE,
+ (void *)entry->code + JUMP_LABEL_NOP_SIZE);
}
void arch_jump_label_transform(struct jump_entry *entry,
@@ -45,15 +96,38 @@ void arch_jump_label_transform(struct jump_entry *entry,
{
get_online_cpus();
mutex_lock(&text_mutex);
- __jump_label_transform(entry, type, text_poke_smp);
+ __jump_label_transform(entry, type, NULL, 0);
mutex_unlock(&text_mutex);
put_online_cpus();
}
+static enum {
+ JL_STATE_START,
+ JL_STATE_NO_UPDATE,
+ JL_STATE_UPDATE,
+} jlstate __initdata_or_module = JL_STATE_START;
+
__init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
enum jump_label_type type)
{
- __jump_label_transform(entry, type, text_poke_early);
+ /*
+ * This function is called at boot up and when modules are
+ * first loaded. Check if the default nop, the one that is
+ * inserted at compile time, is the ideal nop. If it is, then
+ * we do not need to update the nop, and we can leave it as is.
+ * If it is not, then we need to update the nop to the ideal nop.
+ */
+ if (jlstate == JL_STATE_START) {
+ const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
+ const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
+
+ if (memcmp(ideal_nop, default_nop, 5) != 0)
+ jlstate = JL_STATE_UPDATE;
+ else
+ jlstate = JL_STATE_NO_UPDATE;
+ }
+ if (jlstate == JL_STATE_UPDATE)
+ __jump_label_transform(entry, type, text_poke_early, 1);
}
#endif
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index 2e9d4b5af03..c6ee63f927a 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -82,14 +82,9 @@ extern void synthesize_reljump(void *from, void *to);
extern void synthesize_relcall(void *from, void *to);
#ifdef CONFIG_OPTPROBES
-extern int arch_init_optprobes(void);
extern int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter);
extern unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsigned long addr);
#else /* !CONFIG_OPTPROBES */
-static inline int arch_init_optprobes(void)
-{
- return 0;
-}
static inline int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
{
return 0;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 211bce44552..79a3f968287 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -661,7 +661,7 @@ static void __used __kprobes kretprobe_trampoline_holder(void)
/*
* Called from kretprobe_trampoline
*/
-static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
+__visible __used __kprobes void *trampoline_handler(struct pt_regs *regs)
{
struct kretprobe_instance *ri = NULL;
struct hlist_head *head, empty_rp;
@@ -1068,7 +1068,7 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
int __init arch_init_kprobes(void)
{
- return arch_init_optprobes();
+ return 0;
}
int __kprobes arch_trampoline_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 76dc6f09572..898160b42e4 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -88,9 +88,7 @@ static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long v
*(unsigned long *)addr = val;
}
-static void __used __kprobes kprobes_optinsn_template_holder(void)
-{
- asm volatile (
+asm (
".global optprobe_template_entry\n"
"optprobe_template_entry:\n"
#ifdef CONFIG_X86_64
@@ -129,7 +127,6 @@ static void __used __kprobes kprobes_optinsn_template_holder(void)
#endif
".global optprobe_template_end\n"
"optprobe_template_end:\n");
-}
#define TMPL_MOVE_IDX \
((long)&optprobe_template_val - (long)&optprobe_template_entry)
@@ -371,31 +368,6 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op)
return 0;
}
-#define MAX_OPTIMIZE_PROBES 256
-static struct text_poke_param *jump_poke_params;
-static struct jump_poke_buffer {
- u8 buf[RELATIVEJUMP_SIZE];
-} *jump_poke_bufs;
-
-static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
- u8 *insn_buf,
- struct optimized_kprobe *op)
-{
- s32 rel = (s32)((long)op->optinsn.insn -
- ((long)op->kp.addr + RELATIVEJUMP_SIZE));
-
- /* Backup instructions which will be replaced by jump address */
- memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
- RELATIVE_ADDR_SIZE);
-
- insn_buf[0] = RELATIVEJUMP_OPCODE;
- *(s32 *)(&insn_buf[1]) = rel;
-
- tprm->addr = op->kp.addr;
- tprm->opcode = insn_buf;
- tprm->len = RELATIVEJUMP_SIZE;
-}
-
/*
* Replace breakpoints (int3) with relative jumps.
* Caller must call with locking kprobe_mutex and text_mutex.
@@ -403,37 +375,38 @@ static void __kprobes setup_optimize_kprobe(struct text_poke_param *tprm,
void __kprobes arch_optimize_kprobes(struct list_head *oplist)
{
struct optimized_kprobe *op, *tmp;
- int c = 0;
+ u8 insn_buf[RELATIVEJUMP_SIZE];
list_for_each_entry_safe(op, tmp, oplist, list) {
+ s32 rel = (s32)((long)op->optinsn.insn -
+ ((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
WARN_ON(kprobe_disabled(&op->kp));
- /* Setup param */
- setup_optimize_kprobe(&jump_poke_params[c],
- jump_poke_bufs[c].buf, op);
+
+ /* Backup instructions which will be replaced by jump address */
+ memcpy(op->optinsn.copied_insn, op->kp.addr + INT3_SIZE,
+ RELATIVE_ADDR_SIZE);
+
+ insn_buf[0] = RELATIVEJUMP_OPCODE;
+ *(s32 *)(&insn_buf[1]) = rel;
+
+ text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+ op->optinsn.insn);
+
list_del_init(&op->list);
- if (++c >= MAX_OPTIMIZE_PROBES)
- break;
}
-
- /*
- * text_poke_smp doesn't support NMI/MCE code modifying.
- * However, since kprobes itself also doesn't support NMI/MCE
- * code probing, it's not a problem.
- */
- text_poke_smp_batch(jump_poke_params, c);
}
-static void __kprobes setup_unoptimize_kprobe(struct text_poke_param *tprm,
- u8 *insn_buf,
- struct optimized_kprobe *op)
+/* Replace a relative jump with a breakpoint (int3). */
+void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
{
+ u8 insn_buf[RELATIVEJUMP_SIZE];
+
/* Set int3 to first byte for kprobes */
insn_buf[0] = BREAKPOINT_INSTRUCTION;
memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
-
- tprm->addr = op->kp.addr;
- tprm->opcode = insn_buf;
- tprm->len = RELATIVEJUMP_SIZE;
+ text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+ op->optinsn.insn);
}
/*
@@ -444,34 +417,11 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist,
struct list_head *done_list)
{
struct optimized_kprobe *op, *tmp;
- int c = 0;
list_for_each_entry_safe(op, tmp, oplist, list) {
- /* Setup param */
- setup_unoptimize_kprobe(&jump_poke_params[c],
- jump_poke_bufs[c].buf, op);
+ arch_unoptimize_kprobe(op);
list_move(&op->list, done_list);
- if (++c >= MAX_OPTIMIZE_PROBES)
- break;
}
-
- /*
- * text_poke_smp doesn't support NMI/MCE code modifying.
- * However, since kprobes itself also doesn't support NMI/MCE
- * code probing, it's not a problem.
- */
- text_poke_smp_batch(jump_poke_params, c);
-}
-
-/* Replace a relative jump with a breakpoint (int3). */
-void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op)
-{
- u8 buf[RELATIVEJUMP_SIZE];
-
- /* Set int3 to first byte for kprobes */
- buf[0] = BREAKPOINT_INSTRUCTION;
- memcpy(buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
- text_poke_smp(op->kp.addr, buf, RELATIVEJUMP_SIZE);
}
int __kprobes
@@ -491,22 +441,3 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
}
return 0;
}
-
-int __kprobes arch_init_optprobes(void)
-{
- /* Allocate code buffer and parameter array */
- jump_poke_bufs = kmalloc(sizeof(struct jump_poke_buffer) *
- MAX_OPTIMIZE_PROBES, GFP_KERNEL);
- if (!jump_poke_bufs)
- return -ENOMEM;
-
- jump_poke_params = kmalloc(sizeof(struct text_poke_param) *
- MAX_OPTIMIZE_PROBES, GFP_KERNEL);
- if (!jump_poke_params) {
- kfree(jump_poke_bufs);
- jump_poke_bufs = NULL;
- return -ENOMEM;
- }
-
- return 0;
-}
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index a96d32cc55b..b2046e4d0b5 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -34,6 +34,7 @@
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/kprobes.h>
+#include <linux/debugfs.h>
#include <asm/timer.h>
#include <asm/cpu.h>
#include <asm/traps.h>
@@ -419,6 +420,7 @@ static void __init kvm_smp_prepare_boot_cpu(void)
WARN_ON(kvm_register_clock("primary cpu clock"));
kvm_guest_cpu_init();
native_smp_prepare_boot_cpu();
+ kvm_spinlock_init();
}
static void kvm_guest_cpu_online(void *dummy)
@@ -498,11 +500,9 @@ void __init kvm_guest_init(void)
#endif
}
-static bool __init kvm_detect(void)
+static uint32_t __init kvm_detect(void)
{
- if (!kvm_para_available())
- return false;
- return true;
+ return kvm_cpuid_base();
}
const struct hypervisor_x86 x86_hyper_kvm __refconst = {
@@ -523,3 +523,274 @@ static __init int activate_jump_labels(void)
return 0;
}
arch_initcall(activate_jump_labels);
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+
+/* Kick a cpu by its apicid. Used to wake up a halted vcpu */
+static void kvm_kick_cpu(int cpu)
+{
+ int apicid;
+ unsigned long flags = 0;
+
+ apicid = per_cpu(x86_cpu_to_apicid, cpu);
+ kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
+}
+
+enum kvm_contention_stat {
+ TAKEN_SLOW,
+ TAKEN_SLOW_PICKUP,
+ RELEASED_SLOW,
+ RELEASED_SLOW_KICKED,
+ NR_CONTENTION_STATS
+};
+
+#ifdef CONFIG_KVM_DEBUG_FS
+#define HISTO_BUCKETS 30
+
+static struct kvm_spinlock_stats
+{
+ u32 contention_stats[NR_CONTENTION_STATS];
+ u32 histo_spin_blocked[HISTO_BUCKETS+1];
+ u64 time_blocked;
+} spinlock_stats;
+
+static u8 zero_stats;
+
+static inline void check_zero(void)
+{
+ u8 ret;
+ u8 old;
+
+ old = ACCESS_ONCE(zero_stats);
+ if (unlikely(old)) {
+ ret = cmpxchg(&zero_stats, old, 0);
+ /* This ensures only one fellow resets the stat */
+ if (ret == old)
+ memset(&spinlock_stats, 0, sizeof(spinlock_stats));
+ }
+}
+
+static inline void add_stats(enum kvm_contention_stat var, u32 val)
+{
+ check_zero();
+ spinlock_stats.contention_stats[var] += val;
+}
+
+
+static inline u64 spin_time_start(void)
+{
+ return sched_clock();
+}
+
+static void __spin_time_accum(u64 delta, u32 *array)
+{
+ unsigned index;
+
+ index = ilog2(delta);
+ check_zero();
+
+ if (index < HISTO_BUCKETS)
+ array[index]++;
+ else
+ array[HISTO_BUCKETS]++;
+}
+
+static inline void spin_time_accum_blocked(u64 start)
+{
+ u32 delta;
+
+ delta = sched_clock() - start;
+ __spin_time_accum(delta, spinlock_stats.histo_spin_blocked);
+ spinlock_stats.time_blocked += delta;
+}
+
+static struct dentry *d_spin_debug;
+static struct dentry *d_kvm_debug;
+
+struct dentry *kvm_init_debugfs(void)
+{
+ d_kvm_debug = debugfs_create_dir("kvm-guest", NULL);
+ if (!d_kvm_debug)
+ printk(KERN_WARNING "Could not create 'kvm' debugfs directory\n");
+
+ return d_kvm_debug;
+}
+
+static int __init kvm_spinlock_debugfs(void)
+{
+ struct dentry *d_kvm;
+
+ d_kvm = kvm_init_debugfs();
+ if (d_kvm == NULL)
+ return -ENOMEM;
+
+ d_spin_debug = debugfs_create_dir("spinlocks", d_kvm);
+
+ debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);
+
+ debugfs_create_u32("taken_slow", 0444, d_spin_debug,
+ &spinlock_stats.contention_stats[TAKEN_SLOW]);
+ debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
+ &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
+
+ debugfs_create_u32("released_slow", 0444, d_spin_debug,
+ &spinlock_stats.contention_stats[RELEASED_SLOW]);
+ debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
+ &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);
+
+ debugfs_create_u64("time_blocked", 0444, d_spin_debug,
+ &spinlock_stats.time_blocked);
+
+ debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
+ spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
+
+ return 0;
+}
+fs_initcall(kvm_spinlock_debugfs);
+#else /* !CONFIG_KVM_DEBUG_FS */
+static inline void add_stats(enum kvm_contention_stat var, u32 val)
+{
+}
+
+static inline u64 spin_time_start(void)
+{
+ return 0;
+}
+
+static inline void spin_time_accum_blocked(u64 start)
+{
+}
+#endif /* CONFIG_KVM_DEBUG_FS */
+
+struct kvm_lock_waiting {
+ struct arch_spinlock *lock;
+ __ticket_t want;
+};
+
+/* cpus 'waiting' on a spinlock to become available */
+static cpumask_t waiting_cpus;
+
+/* Track spinlock on which a cpu is waiting */
+static DEFINE_PER_CPU(struct kvm_lock_waiting, klock_waiting);
+
+static void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
+{
+ struct kvm_lock_waiting *w;
+ int cpu;
+ u64 start;
+ unsigned long flags;
+
+ if (in_nmi())
+ return;
+
+ w = &__get_cpu_var(klock_waiting);
+ cpu = smp_processor_id();
+ start = spin_time_start();
+
+ /*
+ * Make sure an interrupt handler can't upset things in a
+ * partially setup state.
+ */
+ local_irq_save(flags);
+
+ /*
+ * The ordering protocol on this is that the "lock" pointer
+ * may only be set non-NULL if the "want" ticket is correct.
+ * If we're updating "want", we must first clear "lock".
+ */
+ w->lock = NULL;
+ smp_wmb();
+ w->want = want;
+ smp_wmb();
+ w->lock = lock;
+
+ add_stats(TAKEN_SLOW, 1);
+
+ /*
+ * This uses set_bit, which is atomic but we should not rely on its
+ * reordering gurantees. So barrier is needed after this call.
+ */
+ cpumask_set_cpu(cpu, &waiting_cpus);
+
+ barrier();
+
+ /*
+ * Mark entry to slowpath before doing the pickup test to make
+ * sure we don't deadlock with an unlocker.
+ */
+ __ticket_enter_slowpath(lock);
+
+ /*
+ * check again make sure it didn't become free while
+ * we weren't looking.
+ */
+ if (ACCESS_ONCE(lock->tickets.head) == want) {
+ add_stats(TAKEN_SLOW_PICKUP, 1);
+ goto out;
+ }
+
+ /*
+ * halt until it's our turn and kicked. Note that we do safe halt
+ * for irq enabled case to avoid hang when lock info is overwritten
+ * in irq spinlock slowpath and no spurious interrupt occur to save us.
+ */
+ if (arch_irqs_disabled_flags(flags))
+ halt();
+ else
+ safe_halt();
+
+out:
+ cpumask_clear_cpu(cpu, &waiting_cpus);
+ w->lock = NULL;
+ local_irq_restore(flags);
+ spin_time_accum_blocked(start);
+}
+PV_CALLEE_SAVE_REGS_THUNK(kvm_lock_spinning);
+
+/* Kick vcpu waiting on @lock->head to reach value @ticket */
+static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
+{
+ int cpu;
+
+ add_stats(RELEASED_SLOW, 1);
+ for_each_cpu(cpu, &waiting_cpus) {
+ const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu);
+ if (ACCESS_ONCE(w->lock) == lock &&
+ ACCESS_ONCE(w->want) == ticket) {
+ add_stats(RELEASED_SLOW_KICKED, 1);
+ kvm_kick_cpu(cpu);
+ break;
+ }
+ }
+}
+
+/*
+ * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
+ */
+void __init kvm_spinlock_init(void)
+{
+ if (!kvm_para_available())
+ return;
+ /* Does host kernel support KVM_FEATURE_PV_UNHALT? */
+ if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
+ return;
+
+ pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(kvm_lock_spinning);
+ pv_lock_ops.unlock_kick = kvm_unlock_kick;
+}
+
+static __init int kvm_spinlock_init_jump(void)
+{
+ if (!kvm_para_available())
+ return 0;
+ if (!kvm_para_has_feature(KVM_FEATURE_PV_UNHALT))
+ return 0;
+
+ static_key_slow_inc(&paravirt_ticketlocks_enabled);
+ printk(KERN_INFO "KVM setup paravirtual spinlock\n");
+
+ return 0;
+}
+early_initcall(kvm_spinlock_init_jump);
+
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 7123b5df479..af99f71aeb7 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -216,6 +216,7 @@ int apply_microcode_amd(int cpu)
/* need to apply patch? */
if (rev >= mc_amd->hdr.patch_id) {
c->microcode = rev;
+ uci->cpu_sig.rev = rev;
return 0;
}
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 88458faea2f..05266b5aae2 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -46,7 +46,7 @@ static struct class *msr_class;
static loff_t msr_seek(struct file *file, loff_t offset, int orig)
{
loff_t ret;
- struct inode *inode = file->f_mapping->host;
+ struct inode *inode = file_inode(file);
mutex_lock(&inode->i_mutex);
switch (orig) {
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index ba77ebc2c35..6fcb49ce50a 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -113,10 +113,10 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
u64 before, delta, whole_msecs;
int remainder_ns, decimal_msecs, thishandled;
- before = local_clock();
+ before = sched_clock();
thishandled = a->handler(type, regs);
handled += thishandled;
- delta = local_clock() - before;
+ delta = sched_clock() - before;
trace_nmi_handler(a->handler, (int)delta, thishandled);
if (delta < nmi_longest_ns)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 676b8c77a97..bbb6c731634 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -4,25 +4,17 @@
*/
#include <linux/spinlock.h>
#include <linux/module.h>
+#include <linux/jump_label.h>
#include <asm/paravirt.h>
-static inline void
-default_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
-{
- arch_spin_lock(lock);
-}
-
struct pv_lock_ops pv_lock_ops = {
#ifdef CONFIG_SMP
- .spin_is_locked = __ticket_spin_is_locked,
- .spin_is_contended = __ticket_spin_is_contended,
-
- .spin_lock = __ticket_spin_lock,
- .spin_lock_flags = default_spin_lock_flags,
- .spin_trylock = __ticket_spin_trylock,
- .spin_unlock = __ticket_spin_unlock,
+ .lock_spinning = __PV_IS_CALLEE_SAVE(paravirt_nop),
+ .unlock_kick = paravirt_nop,
#endif
};
EXPORT_SYMBOL(pv_lock_ops);
+struct static_key paravirt_ticketlocks_enabled = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL(paravirt_ticketlocks_enabled);
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index cd6de64cc48..1b10af835c3 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -62,11 +62,6 @@ void __init default_banner(void)
pv_info.name);
}
-/* Simple instruction patching code. */
-#define DEF_NATIVE(ops, name, code) \
- extern const char start_##ops##_##name[], end_##ops##_##name[]; \
- asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
-
/* Undefined instruction for dealing with missing ops pointers. */
static const unsigned char ud2a[] = { 0x0f, 0x0b };
@@ -324,7 +319,7 @@ struct pv_time_ops pv_time_ops = {
.steal_clock = native_steal_clock,
};
-struct pv_irq_ops pv_irq_ops = {
+__visible struct pv_irq_ops pv_irq_ops = {
.save_fl = __PV_IS_CALLEE_SAVE(native_save_fl),
.restore_fl = __PV_IS_CALLEE_SAVE(native_restore_fl),
.irq_disable = __PV_IS_CALLEE_SAVE(native_irq_disable),
@@ -336,7 +331,7 @@ struct pv_irq_ops pv_irq_ops = {
#endif
};
-struct pv_cpu_ops pv_cpu_ops = {
+__visible struct pv_cpu_ops pv_cpu_ops = {
.cpuid = native_cpuid,
.get_debugreg = native_get_debugreg,
.set_debugreg = native_set_debugreg,
diff --git a/arch/x86/kernel/preempt.S b/arch/x86/kernel/preempt.S
new file mode 100644
index 00000000000..ca7f0d58a87
--- /dev/null
+++ b/arch/x86/kernel/preempt.S
@@ -0,0 +1,25 @@
+
+#include <linux/linkage.h>
+#include <asm/dwarf2.h>
+#include <asm/asm.h>
+#include <asm/calling.h>
+
+ENTRY(___preempt_schedule)
+ CFI_STARTPROC
+ SAVE_ALL
+ call preempt_schedule
+ RESTORE_ALL
+ ret
+ CFI_ENDPROC
+
+#ifdef CONFIG_CONTEXT_TRACKING
+
+ENTRY(___preempt_schedule_context)
+ CFI_STARTPROC
+ SAVE_ALL
+ call preempt_schedule_context
+ RESTORE_ALL
+ ret
+ CFI_ENDPROC
+
+#endif
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 83369e5a1d2..3fb8d95ab8b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -36,7 +36,7 @@
* section. Since TSS's are completely CPU-local, we want them
* on exact cacheline boundaries, to eliminate cacheline ping-pong.
*/
-DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
+__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
#ifdef CONFIG_X86_64
static DEFINE_PER_CPU(unsigned char, is_idle);
@@ -391,9 +391,9 @@ static void amd_e400_idle(void)
* The switch back from broadcast mode needs to be
* called with interrupts disabled.
*/
- local_irq_disable();
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
- local_irq_enable();
+ local_irq_disable();
+ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
+ local_irq_enable();
} else
default_idle();
}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index f8adefca71d..c2ec1aa6d45 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -247,7 +247,7 @@ EXPORT_SYMBOL_GPL(start_thread);
* the task-switch, and shows up in ret_from_fork in entry.S,
* for example.
*/
-__notrace_funcgraph struct task_struct *
+__visible __notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread,
@@ -292,6 +292,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
set_iopl_mask(next->iopl);
/*
+ * If it were not for PREEMPT_ACTIVE we could guarantee that the
+ * preempt_count of all tasks was equal here and this would not be
+ * needed.
+ */
+ task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
+ this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
+
+ /*
* Now maybe handle debug registers and/or IO bitmaps
*/
if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV ||
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 05646bab4ca..45ab4d6fc8a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -52,7 +52,7 @@
asmlinkage extern void ret_from_fork(void);
-DEFINE_PER_CPU(unsigned long, old_rsp);
+asmlinkage DEFINE_PER_CPU(unsigned long, old_rsp);
/* Prints also some state that isn't saved in the pt_regs */
void __show_regs(struct pt_regs *regs, int all)
@@ -274,7 +274,7 @@ void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp)
* Kprobes not supported here. Set the probe on schedule instead.
* Function graph tracer not supported too.
*/
-__notrace_funcgraph struct task_struct *
+__visible __notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
struct thread_struct *prev = &prev_p->thread;
@@ -363,6 +363,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
this_cpu_write(old_rsp, next->usersp);
this_cpu_write(current_task, next_p);
+ /*
+ * If it were not for PREEMPT_ACTIVE we could guarantee that the
+ * preempt_count of all tasks was equal here and this would not be
+ * needed.
+ */
+ task_thread_info(prev_p)->saved_preempt_count = this_cpu_read(__preempt_count);
+ this_cpu_write(__preempt_count, task_thread_info(next_p)->saved_preempt_count);
+
this_cpu_write(kernel_stack,
(unsigned long)task_stack_page(next_p) +
THREAD_SIZE - KERNEL_STACK_OFFSET);
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2cb9470ea85..a16bae3f83b 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -128,46 +128,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
}
-static struct pvclock_vsyscall_time_info *pvclock_vdso_info;
-
-static struct pvclock_vsyscall_time_info *
-pvclock_get_vsyscall_user_time_info(int cpu)
-{
- if (!pvclock_vdso_info) {
- BUG();
- return NULL;
- }
-
- return &pvclock_vdso_info[cpu];
-}
-
-struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu)
-{
- return &pvclock_get_vsyscall_user_time_info(cpu)->pvti;
-}
-
#ifdef CONFIG_X86_64
-static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l,
- void *v)
-{
- struct task_migration_notifier *mn = v;
- struct pvclock_vsyscall_time_info *pvti;
-
- pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu);
-
- /* this is NULL when pvclock vsyscall is not initialized */
- if (unlikely(pvti == NULL))
- return NOTIFY_DONE;
-
- pvti->migrate_count++;
-
- return NOTIFY_DONE;
-}
-
-static struct notifier_block pvclock_migrate = {
- .notifier_call = pvclock_task_migrate,
-};
-
/*
* Initialize the generic pvclock vsyscall state. This will allocate
* a/some page(s) for the per-vcpu pvclock information, set up a
@@ -181,17 +142,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
- pvclock_vdso_info = i;
-
for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
__pa(i) + (idx*PAGE_SIZE),
PAGE_KERNEL_VVAR);
}
-
- register_task_migration_notifier(&pvclock_migrate);
-
return 0;
}
#endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 563ed91e6fa..da3c599584a 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -61,7 +61,7 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
if (reboot_type != BOOT_BIOS) {
reboot_type = BOOT_BIOS;
pr_info("%s series board detected. Selecting %s-method for reboots.\n",
- "BIOS", d->ident);
+ d->ident, "BIOS");
}
return 0;
}
@@ -117,7 +117,7 @@ static int __init set_pci_reboot(const struct dmi_system_id *d)
if (reboot_type != BOOT_CF9) {
reboot_type = BOOT_CF9;
pr_info("%s series board detected. Selecting %s-method for reboots.\n",
- "PCI", d->ident);
+ d->ident, "PCI");
}
return 0;
}
@@ -127,7 +127,7 @@ static int __init set_kbd_reboot(const struct dmi_system_id *d)
if (reboot_type != BOOT_KBD) {
reboot_type = BOOT_KBD;
pr_info("%s series board detected. Selecting %s-method for reboot.\n",
- "KBD", d->ident);
+ d->ident, "KBD");
}
return 0;
}
@@ -136,228 +136,256 @@ static int __init set_kbd_reboot(const struct dmi_system_id *d)
* This is a single dmi_table handling all reboot quirks.
*/
static struct dmi_system_id __initdata reboot_dmi_table[] = {
- { /* Handle problems with rebooting on Dell E520's */
- .callback = set_bios_reboot,
- .ident = "Dell E520",
+
+ /* Acer */
+ { /* Handle reboot issue on Acer Aspire one */
+ .callback = set_kbd_reboot,
+ .ident = "Acer Aspire One A110",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Dell DM061"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
},
},
- { /* Handle problems with rebooting on Dell 1300's */
- .callback = set_bios_reboot,
- .ident = "Dell PowerEdge 1300",
+
+ /* Apple */
+ { /* Handle problems with rebooting on Apple MacBook5 */
+ .callback = set_pci_reboot,
+ .ident = "Apple MacBook5",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1300/"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"),
},
},
- { /* Handle problems with rebooting on Dell 300's */
- .callback = set_bios_reboot,
- .ident = "Dell PowerEdge 300",
+ { /* Handle problems with rebooting on Apple MacBookPro5 */
+ .callback = set_pci_reboot,
+ .ident = "Apple MacBookPro5",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 300/"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro5"),
},
},
- { /* Handle problems with rebooting on Dell Optiplex 745's SFF */
- .callback = set_bios_reboot,
- .ident = "Dell OptiPlex 745",
+ { /* Handle problems with rebooting on Apple Macmini3,1 */
+ .callback = set_pci_reboot,
+ .ident = "Apple Macmini3,1",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Macmini3,1"),
},
},
- { /* Handle problems with rebooting on Dell Optiplex 745's DFF */
+ { /* Handle problems with rebooting on the iMac9,1. */
+ .callback = set_pci_reboot,
+ .ident = "Apple iMac9,1",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"),
+ },
+ },
+
+ /* ASUS */
+ { /* Handle problems with rebooting on ASUS P4S800 */
.callback = set_bios_reboot,
- .ident = "Dell OptiPlex 745",
+ .ident = "ASUS P4S800",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
- DMI_MATCH(DMI_BOARD_NAME, "0MM599"),
+ DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
},
},
- { /* Handle problems with rebooting on Dell Optiplex 745 with 0KW626 */
+
+ /* Dell */
+ { /* Handle problems with rebooting on Dell DXP061 */
.callback = set_bios_reboot,
- .ident = "Dell OptiPlex 745",
+ .ident = "Dell DXP061",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
- DMI_MATCH(DMI_BOARD_NAME, "0KW626"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"),
},
},
- { /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */
+ { /* Handle problems with rebooting on Dell E520's */
.callback = set_bios_reboot,
- .ident = "Dell OptiPlex 330",
+ .ident = "Dell E520",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"),
- DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Dell DM061"),
},
},
- { /* Handle problems with rebooting on Dell Optiplex 360 with 0T656F */
- .callback = set_bios_reboot,
- .ident = "Dell OptiPlex 360",
+ { /* Handle problems with rebooting on the Latitude E5410. */
+ .callback = set_pci_reboot,
+ .ident = "Dell Latitude E5410",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 360"),
- DMI_MATCH(DMI_BOARD_NAME, "0T656F"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5410"),
},
},
- { /* Handle problems with rebooting on Dell OptiPlex 760 with 0G919G */
- .callback = set_bios_reboot,
- .ident = "Dell OptiPlex 760",
+ { /* Handle problems with rebooting on the Latitude E5420. */
+ .callback = set_pci_reboot,
+ .ident = "Dell Latitude E5420",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 760"),
- DMI_MATCH(DMI_BOARD_NAME, "0G919G"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"),
},
},
- { /* Handle problems with rebooting on Dell 2400's */
- .callback = set_bios_reboot,
- .ident = "Dell PowerEdge 2400",
+ { /* Handle problems with rebooting on the Latitude E6320. */
+ .callback = set_pci_reboot,
+ .ident = "Dell Latitude E6320",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2400"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"),
},
},
- { /* Handle problems with rebooting on Dell T5400's */
- .callback = set_bios_reboot,
- .ident = "Dell Precision T5400",
+ { /* Handle problems with rebooting on the Latitude E6420. */
+ .callback = set_pci_reboot,
+ .ident = "Dell Latitude E6420",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T5400"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"),
},
},
- { /* Handle problems with rebooting on Dell T7400's */
+ { /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */
.callback = set_bios_reboot,
- .ident = "Dell Precision T7400",
+ .ident = "Dell OptiPlex 330",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T7400"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"),
+ DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
},
},
- { /* Handle problems with rebooting on HP laptops */
+ { /* Handle problems with rebooting on Dell Optiplex 360 with 0T656F */
.callback = set_bios_reboot,
- .ident = "HP Compaq Laptop",
+ .ident = "Dell OptiPlex 360",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
- DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 360"),
+ DMI_MATCH(DMI_BOARD_NAME, "0T656F"),
},
},
- { /* Handle problems with rebooting on Dell XPS710 */
+ { /* Handle problems with rebooting on Dell Optiplex 745's SFF */
.callback = set_bios_reboot,
- .ident = "Dell XPS710",
+ .ident = "Dell OptiPlex 745",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
},
},
- { /* Handle problems with rebooting on Dell DXP061 */
+ { /* Handle problems with rebooting on Dell Optiplex 745's DFF */
.callback = set_bios_reboot,
- .ident = "Dell DXP061",
+ .ident = "Dell OptiPlex 745",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
+ DMI_MATCH(DMI_BOARD_NAME, "0MM599"),
},
},
- { /* Handle problems with rebooting on Sony VGN-Z540N */
+ { /* Handle problems with rebooting on Dell Optiplex 745 with 0KW626 */
.callback = set_bios_reboot,
- .ident = "Sony VGN-Z540N",
+ .ident = "Dell OptiPlex 745",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
- DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 745"),
+ DMI_MATCH(DMI_BOARD_NAME, "0KW626"),
},
},
- { /* Handle problems with rebooting on ASUS P4S800 */
+ { /* Handle problems with rebooting on Dell OptiPlex 760 with 0G919G */
.callback = set_bios_reboot,
- .ident = "ASUS P4S800",
+ .ident = "Dell OptiPlex 760",
.matches = {
- DMI_MATCH(DMI_BOARD_VENDOR, "ASUSTeK Computer INC."),
- DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 760"),
+ DMI_MATCH(DMI_BOARD_NAME, "0G919G"),
},
},
-
- { /* Handle reboot issue on Acer Aspire one */
- .callback = set_kbd_reboot,
- .ident = "Acer Aspire One A110",
+ { /* Handle problems with rebooting on the OptiPlex 990. */
+ .callback = set_pci_reboot,
+ .ident = "Dell OptiPlex 990",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
- DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"),
},
},
- { /* Handle problems with rebooting on Apple MacBook5 */
- .callback = set_pci_reboot,
- .ident = "Apple MacBook5",
+ { /* Handle problems with rebooting on Dell 300's */
+ .callback = set_bios_reboot,
+ .ident = "Dell PowerEdge 300",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "MacBook5"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 300/"),
},
},
- { /* Handle problems with rebooting on Apple MacBookPro5 */
- .callback = set_pci_reboot,
- .ident = "Apple MacBookPro5",
+ { /* Handle problems with rebooting on Dell 1300's */
+ .callback = set_bios_reboot,
+ .ident = "Dell PowerEdge 1300",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro5"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 1300/"),
},
},
- { /* Handle problems with rebooting on Apple Macmini3,1 */
- .callback = set_pci_reboot,
- .ident = "Apple Macmini3,1",
+ { /* Handle problems with rebooting on Dell 2400's */
+ .callback = set_bios_reboot,
+ .ident = "Dell PowerEdge 2400",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Macmini3,1"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Computer Corporation"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2400"),
},
},
- { /* Handle problems with rebooting on the iMac9,1. */
+ { /* Handle problems with rebooting on the Dell PowerEdge C6100. */
.callback = set_pci_reboot,
- .ident = "Apple iMac9,1",
+ .ident = "Dell PowerEdge C6100",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "C6100"),
},
},
- { /* Handle problems with rebooting on the Latitude E6320. */
+ { /* Handle problems with rebooting on the Precision M6600. */
.callback = set_pci_reboot,
- .ident = "Dell Latitude E6320",
+ .ident = "Dell Precision M6600",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
},
},
- { /* Handle problems with rebooting on the Latitude E5420. */
- .callback = set_pci_reboot,
- .ident = "Dell Latitude E5420",
+ { /* Handle problems with rebooting on Dell T5400's */
+ .callback = set_bios_reboot,
+ .ident = "Dell Precision T5400",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T5400"),
},
},
- { /* Handle problems with rebooting on the Latitude E6420. */
- .callback = set_pci_reboot,
- .ident = "Dell Latitude E6420",
+ { /* Handle problems with rebooting on Dell T7400's */
+ .callback = set_bios_reboot,
+ .ident = "Dell Precision T7400",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T7400"),
},
},
- { /* Handle problems with rebooting on the OptiPlex 990. */
- .callback = set_pci_reboot,
- .ident = "Dell OptiPlex 990",
+ { /* Handle problems with rebooting on Dell XPS710 */
+ .callback = set_bios_reboot,
+ .ident = "Dell XPS710",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"),
},
},
- { /* Handle problems with rebooting on the Precision M6600. */
- .callback = set_pci_reboot,
- .ident = "Dell OptiPlex 990",
+
+ /* Hewlett-Packard */
+ { /* Handle problems with rebooting on HP laptops */
+ .callback = set_bios_reboot,
+ .ident = "HP Compaq Laptop",
.matches = {
- DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "Precision M6600"),
+ DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"),
+ },
+ },
+
+ /* Sony */
+ { /* Handle problems with rebooting on Sony VGN-Z540N */
+ .callback = set_bios_reboot,
+ .ident = "Sony VGN-Z540N",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"),
},
},
+
{ }
};
@@ -511,10 +539,13 @@ static void native_machine_emergency_restart(void)
case BOOT_CF9_COND:
if (port_cf9_safe) {
- u8 cf9 = inb(0xcf9) & ~6;
+ u8 reboot_code = reboot_mode == REBOOT_WARM ?
+ 0x06 : 0x0E;
+ u8 cf9 = inb(0xcf9) & ~reboot_code;
outb(cf9|2, 0xcf9); /* Request hard reset */
udelay(50);
- outb(cf9|6, 0xcf9); /* Actually do the reset */
+ /* Actually do the reset */
+ outb(cf9|reboot_code, 0xcf9);
udelay(50);
}
reboot_type = BOOT_KBD;
@@ -526,6 +557,10 @@ static void native_machine_emergency_restart(void)
void native_machine_shutdown(void)
{
/* Stop the cpus and apics */
+#ifdef CONFIG_X86_IO_APIC
+ disable_IO_APIC();
+#endif
+
#ifdef CONFIG_SMP
/*
* Stop all of the others. Also disable the local irq to
@@ -538,10 +573,6 @@ void native_machine_shutdown(void)
lapic_shutdown();
-#ifdef CONFIG_X86_IO_APIC
- disable_IO_APIC();
-#endif
-
#ifdef CONFIG_HPET_TIMER
hpet_disable();
#endif
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 0aa29394ed6..ca9622a25e9 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -12,7 +12,7 @@
#include <asm/vsyscall.h>
#include <asm/x86_init.h>
#include <asm/time.h>
-#include <asm/mrst.h>
+#include <asm/intel-mid.h>
#include <asm/rtc.h>
#ifdef CONFIG_X86_32
@@ -189,9 +189,17 @@ static __init int add_rtc_cmos(void)
return 0;
/* Intel MID platforms don't have ioport rtc */
- if (mrst_identify_cpu())
+ if (intel_mid_identify_cpu())
return -ENODEV;
+#ifdef CONFIG_ACPI
+ if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_CMOS_RTC) {
+ /* This warning can likely go away again in a year or two. */
+ pr_info("ACPI: not registering RTC platform device\n");
+ return -ENODEV;
+ }
+#endif
+
platform_device_register(&rtc_device);
dev_info(&rtc_device.dev,
"registered platform RTC device (no PNP device found)\n");
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f8ec57815c0..918d489fa53 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -206,9 +206,9 @@ EXPORT_SYMBOL(boot_cpu_data);
#if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-unsigned long mmu_cr4_features;
+__visible unsigned long mmu_cr4_features;
#else
-unsigned long mmu_cr4_features = X86_CR4_PAE;
+__visible unsigned long mmu_cr4_features = X86_CR4_PAE;
#endif
/* Boot loader ID and version as integers, for the benefit of proc_dointvec */
@@ -426,25 +426,23 @@ static void __init reserve_initrd(void)
static void __init parse_setup_data(void)
{
struct setup_data *data;
- u64 pa_data;
+ u64 pa_data, pa_next;
pa_data = boot_params.hdr.setup_data;
while (pa_data) {
- u32 data_len, map_len;
+ u32 data_len, map_len, data_type;
map_len = max(PAGE_SIZE - (pa_data & ~PAGE_MASK),
(u64)sizeof(struct setup_data));
data = early_memremap(pa_data, map_len);
data_len = data->len + sizeof(struct setup_data);
- if (data_len > map_len) {
- early_iounmap(data, map_len);
- data = early_memremap(pa_data, data_len);
- map_len = data_len;
- }
+ data_type = data->type;
+ pa_next = data->next;
+ early_iounmap(data, map_len);
- switch (data->type) {
+ switch (data_type) {
case SETUP_E820_EXT:
- parse_e820_ext(data);
+ parse_e820_ext(pa_data, data_len);
break;
case SETUP_DTB:
add_dtb(pa_data);
@@ -452,8 +450,7 @@ static void __init parse_setup_data(void)
default:
break;
}
- pa_data = data->next;
- early_iounmap(data, map_len);
+ pa_data = pa_next;
}
}
@@ -996,6 +993,7 @@ void __init setup_arch(char **cmdline_p)
efi_init();
dmi_scan_machine();
+ dmi_memdev_walk();
dmi_set_dump_stack_arch_desc();
/*
@@ -1070,7 +1068,7 @@ void __init setup_arch(char **cmdline_p)
cleanup_highmap();
- memblock.current_limit = ISA_END_ADDRESS;
+ memblock_set_current_limit(ISA_END_ADDRESS);
memblock_x86_fill();
/*
@@ -1103,7 +1101,7 @@ void __init setup_arch(char **cmdline_p)
setup_real_mode();
- memblock.current_limit = get_max_mapped();
+ memblock_set_current_limit(get_max_mapped());
dma_contiguous_reserve(0);
/*
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index cf913587d4d..9e5de6813e1 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -358,7 +358,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
else
put_user_ex(0, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
- err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+ save_altstack_ex(&frame->uc.uc_stack, regs->sp);
/* Set up to return from userspace. */
restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
@@ -423,7 +423,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
else
put_user_ex(0, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
- err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+ save_altstack_ex(&frame->uc.uc_stack, regs->sp);
/* Set up to return from userspace. If provided, use a stub
already in userspace. */
@@ -490,7 +490,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
else
put_user_ex(0, &frame->uc.uc_flags);
put_user_ex(0, &frame->uc.uc_link);
- err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+ compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
put_user_ex(0, &frame->uc.uc__pad0);
if (ksig->ka.sa.sa_flags & SA_RESTORER) {
@@ -533,7 +533,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
* Do a signal return; undo the signal stack.
*/
#ifdef CONFIG_X86_32
-unsigned long sys_sigreturn(void)
+asmlinkage unsigned long sys_sigreturn(void)
{
struct pt_regs *regs = current_pt_regs();
struct sigframe __user *frame;
@@ -562,7 +562,7 @@ badframe:
}
#endif /* CONFIG_X86_32 */
-long sys_rt_sigreturn(void)
+asmlinkage long sys_rt_sigreturn(void)
{
struct pt_regs *regs = current_pt_regs();
struct rt_sigframe __user *frame;
@@ -728,7 +728,7 @@ static void do_signal(struct pt_regs *regs)
* notification of userspace execution resumption
* - triggered by the TIF_WORK_MASK flags
*/
-void
+__visible void
do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
{
user_exit();
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index cdaa347dfca..7c3a5a61f2e 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -256,7 +256,7 @@ static inline void __smp_reschedule_interrupt(void)
scheduler_ipi();
}
-void smp_reschedule_interrupt(struct pt_regs *regs)
+__visible void smp_reschedule_interrupt(struct pt_regs *regs)
{
ack_APIC_irq();
__smp_reschedule_interrupt();
@@ -271,7 +271,7 @@ static inline void smp_entering_irq(void)
irq_enter();
}
-void smp_trace_reschedule_interrupt(struct pt_regs *regs)
+__visible void smp_trace_reschedule_interrupt(struct pt_regs *regs)
{
/*
* Need to call irq_enter() before calling the trace point.
@@ -295,14 +295,14 @@ static inline void __smp_call_function_interrupt(void)
inc_irq_stat(irq_call_count);
}
-void smp_call_function_interrupt(struct pt_regs *regs)
+__visible void smp_call_function_interrupt(struct pt_regs *regs)
{
smp_entering_irq();
__smp_call_function_interrupt();
exiting_irq();
}
-void smp_trace_call_function_interrupt(struct pt_regs *regs)
+__visible void smp_trace_call_function_interrupt(struct pt_regs *regs)
{
smp_entering_irq();
trace_call_function_entry(CALL_FUNCTION_VECTOR);
@@ -317,14 +317,14 @@ static inline void __smp_call_function_single_interrupt(void)
inc_irq_stat(irq_call_count);
}
-void smp_call_function_single_interrupt(struct pt_regs *regs)
+__visible void smp_call_function_single_interrupt(struct pt_regs *regs)
{
smp_entering_irq();
__smp_call_function_single_interrupt();
exiting_irq();
}
-void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
+__visible void smp_trace_call_function_single_interrupt(struct pt_regs *regs)
{
smp_entering_irq();
trace_call_function_single_entry(CALL_FUNCTION_SINGLE_VECTOR);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index aecc98a93d1..2a165580fa1 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -73,11 +73,10 @@
#include <asm/setup.h>
#include <asm/uv/uv.h>
#include <linux/mc146818rtc.h>
-
#include <asm/smpboot_hooks.h>
#include <asm/i8259.h>
-
#include <asm/realmode.h>
+#include <asm/misc.h>
/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
@@ -648,21 +647,46 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
return (send_status | accept_status);
}
+void smp_announce(void)
+{
+ int num_nodes = num_online_nodes();
+
+ printk(KERN_INFO "x86: Booted up %d node%s, %d CPUs\n",
+ num_nodes, (num_nodes > 1 ? "s" : ""), num_online_cpus());
+}
+
/* reduce the number of lines printed when booting a large cpu count system */
static void announce_cpu(int cpu, int apicid)
{
static int current_node = -1;
int node = early_cpu_to_node(cpu);
+ static int width, node_width;
+
+ if (!width)
+ width = num_digits(num_possible_cpus()) + 1; /* + '#' sign */
+
+ if (!node_width)
+ node_width = num_digits(num_possible_nodes()) + 1; /* + '#' */
+
+ if (cpu == 1)
+ printk(KERN_INFO "x86: Booting SMP configuration:\n");
if (system_state == SYSTEM_BOOTING) {
if (node != current_node) {
if (current_node > (-1))
- pr_cont(" OK\n");
+ pr_cont("\n");
current_node = node;
- pr_info("Booting Node %3d, Processors ", node);
+
+ printk(KERN_INFO ".... node %*s#%d, CPUs: ",
+ node_width - num_digits(node), " ", node);
}
- pr_cont(" #%d%s", cpu, cpu == (nr_cpu_ids - 1) ? " OK\n" : "");
- return;
+
+ /* Add padding for the BSP */
+ if (cpu == 1)
+ pr_cont("%*s", width + 1, " ");
+
+ pr_cont("%*s#%d", width - num_digits(cpu), " ", cpu);
+
} else
pr_info("Booting Node %d Processor %d APIC 0x%x\n",
node, cpu, apicid);
diff --git a/arch/x86/kernel/syscall_32.c b/arch/x86/kernel/syscall_32.c
index 147fcd4941c..e9bcd57d8a9 100644
--- a/arch/x86/kernel/syscall_32.c
+++ b/arch/x86/kernel/syscall_32.c
@@ -15,7 +15,7 @@ typedef asmlinkage void (*sys_call_ptr_t)(void);
extern asmlinkage void sys_ni_syscall(void);
-const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
+__visible const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
/*
* Smells like a compiler bug -- it doesn't work
* when the & below is removed.
diff --git a/arch/x86/kernel/syscall_64.c b/arch/x86/kernel/syscall_64.c
index 5c7f8c20da7..4ac730b37f0 100644
--- a/arch/x86/kernel/syscall_64.c
+++ b/arch/x86/kernel/syscall_64.c
@@ -4,6 +4,7 @@
#include <linux/sys.h>
#include <linux/cache.h>
#include <asm/asm-offsets.h>
+#include <asm/syscall.h>
#define __SYSCALL_COMMON(nr, sym, compat) __SYSCALL_64(nr, sym, compat)
@@ -19,11 +20,9 @@
#define __SYSCALL_64(nr, sym, compat) [nr] = sym,
-typedef void (*sys_call_ptr_t)(void);
-
extern void sys_ni_syscall(void);
-const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
+asmlinkage const sys_call_ptr_t sys_call_table[__NR_syscall_max+1] = {
/*
* Smells like a compiler bug -- it doesn't work
* when the & below is removed.
diff --git a/arch/x86/kernel/sysfb.c b/arch/x86/kernel/sysfb.c
new file mode 100644
index 00000000000..193ec2ce46c
--- /dev/null
+++ b/arch/x86/kernel/sysfb.c
@@ -0,0 +1,74 @@
+/*
+ * Generic System Framebuffers on x86
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+/*
+ * Simple-Framebuffer support for x86 systems
+ * Create a platform-device for any available boot framebuffer. The
+ * simple-framebuffer platform device is already available on DT systems, so
+ * this module parses the global "screen_info" object and creates a suitable
+ * platform device compatible with the "simple-framebuffer" DT object. If
+ * the framebuffer is incompatible, we instead create a legacy
+ * "vesa-framebuffer", "efi-framebuffer" or "platform-framebuffer" device and
+ * pass the screen_info as platform_data. This allows legacy drivers
+ * to pick these devices up without messing with simple-framebuffer drivers.
+ * The global "screen_info" is still valid at all times.
+ *
+ * If CONFIG_X86_SYSFB is not selected, we never register "simple-framebuffer"
+ * platform devices, but only use legacy framebuffer devices for
+ * backwards compatibility.
+ *
+ * TODO: We set the dev_id field of all platform-devices to 0. This allows
+ * other x86 OF/DT parsers to create such devices, too. However, they must
+ * start at offset 1 for this to work.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/platform_device.h>
+#include <linux/screen_info.h>
+#include <asm/sysfb.h>
+
+static __init int sysfb_init(void)
+{
+ struct screen_info *si = &screen_info;
+ struct simplefb_platform_data mode;
+ struct platform_device *pd;
+ const char *name;
+ bool compatible;
+ int ret;
+
+ sysfb_apply_efi_quirks();
+
+ /* try to create a simple-framebuffer device */
+ compatible = parse_mode(si, &mode);
+ if (compatible) {
+ ret = create_simplefb(si, &mode);
+ if (!ret)
+ return 0;
+ }
+
+ /* if the FB is incompatible, create a legacy framebuffer device */
+ if (si->orig_video_isVGA == VIDEO_TYPE_EFI)
+ name = "efi-framebuffer";
+ else if (si->orig_video_isVGA == VIDEO_TYPE_VLFB)
+ name = "vesa-framebuffer";
+ else
+ name = "platform-framebuffer";
+
+ pd = platform_device_register_resndata(NULL, name, 0,
+ NULL, 0, si, sizeof(*si));
+ return IS_ERR(pd) ? PTR_ERR(pd) : 0;
+}
+
+/* must execute after PCI subsystem for EFI quirks */
+device_initcall(sysfb_init);
diff --git a/arch/x86/kernel/sysfb_efi.c b/arch/x86/kernel/sysfb_efi.c
new file mode 100644
index 00000000000..b285d4e8c68
--- /dev/null
+++ b/arch/x86/kernel/sysfb_efi.c
@@ -0,0 +1,214 @@
+/*
+ * Generic System Framebuffers on x86
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * EFI Quirks Copyright (c) 2006 Edgar Hucek <gimli@dark-green.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+/*
+ * EFI Quirks
+ * Several EFI systems do not correctly advertise their boot framebuffers.
+ * Hence, we use this static table of known broken machines and fix up the
+ * information so framebuffer drivers can load corectly.
+ */
+
+#include <linux/dmi.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/pci.h>
+#include <linux/screen_info.h>
+#include <video/vga.h>
+#include <asm/sysfb.h>
+
+enum {
+ OVERRIDE_NONE = 0x0,
+ OVERRIDE_BASE = 0x1,
+ OVERRIDE_STRIDE = 0x2,
+ OVERRIDE_HEIGHT = 0x4,
+ OVERRIDE_WIDTH = 0x8,
+};
+
+struct efifb_dmi_info efifb_dmi_list[] = {
+ [M_I17] = { "i17", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+ [M_I20] = { "i20", 0x80010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE }, /* guess */
+ [M_I20_SR] = { "imac7", 0x40010000, 1728 * 4, 1680, 1050, OVERRIDE_NONE },
+ [M_I24] = { "i24", 0x80010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE }, /* guess */
+ [M_I24_8_1] = { "imac8", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+ [M_I24_10_1] = { "imac10", 0xc0010000, 2048 * 4, 1920, 1080, OVERRIDE_NONE },
+ [M_I27_11_1] = { "imac11", 0xc0010000, 2560 * 4, 2560, 1440, OVERRIDE_NONE },
+ [M_MINI]= { "mini", 0x80000000, 2048 * 4, 1024, 768, OVERRIDE_NONE },
+ [M_MINI_3_1] = { "mini31", 0x40010000, 1024 * 4, 1024, 768, OVERRIDE_NONE },
+ [M_MINI_4_1] = { "mini41", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+ [M_MB] = { "macbook", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+ [M_MB_5_1] = { "macbook51", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+ [M_MB_6_1] = { "macbook61", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+ [M_MB_7_1] = { "macbook71", 0x80010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+ [M_MBA] = { "mba", 0x80000000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+ /* 11" Macbook Air 3,1 passes the wrong stride */
+ [M_MBA_3] = { "mba3", 0, 2048 * 4, 0, 0, OVERRIDE_STRIDE },
+ [M_MBP] = { "mbp", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+ [M_MBP_2] = { "mbp2", 0, 0, 0, 0, OVERRIDE_NONE }, /* placeholder */
+ [M_MBP_2_2] = { "mbp22", 0x80010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+ [M_MBP_SR] = { "mbp3", 0x80030000, 2048 * 4, 1440, 900, OVERRIDE_NONE },
+ [M_MBP_4] = { "mbp4", 0xc0060000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+ [M_MBP_5_1] = { "mbp51", 0xc0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE },
+ [M_MBP_5_2] = { "mbp52", 0xc0010000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+ [M_MBP_5_3] = { "mbp53", 0xd0010000, 2048 * 4, 1440, 900, OVERRIDE_NONE },
+ [M_MBP_6_1] = { "mbp61", 0x90030000, 2048 * 4, 1920, 1200, OVERRIDE_NONE },
+ [M_MBP_6_2] = { "mbp62", 0x90030000, 2048 * 4, 1680, 1050, OVERRIDE_NONE },
+ [M_MBP_7_1] = { "mbp71", 0xc0010000, 2048 * 4, 1280, 800, OVERRIDE_NONE },
+ [M_MBP_8_2] = { "mbp82", 0x90010000, 1472 * 4, 1440, 900, OVERRIDE_NONE },
+ [M_UNKNOWN] = { NULL, 0, 0, 0, 0, OVERRIDE_NONE }
+};
+
+#define choose_value(dmivalue, fwvalue, field, flags) ({ \
+ typeof(fwvalue) _ret_ = fwvalue; \
+ if ((flags) & (field)) \
+ _ret_ = dmivalue; \
+ else if ((fwvalue) == 0) \
+ _ret_ = dmivalue; \
+ _ret_; \
+ })
+
+static int __init efifb_set_system(const struct dmi_system_id *id)
+{
+ struct efifb_dmi_info *info = id->driver_data;
+
+ if (info->base == 0 && info->height == 0 && info->width == 0 &&
+ info->stride == 0)
+ return 0;
+
+ /* Trust the bootloader over the DMI tables */
+ if (screen_info.lfb_base == 0) {
+#if defined(CONFIG_PCI)
+ struct pci_dev *dev = NULL;
+ int found_bar = 0;
+#endif
+ if (info->base) {
+ screen_info.lfb_base = choose_value(info->base,
+ screen_info.lfb_base, OVERRIDE_BASE,
+ info->flags);
+
+#if defined(CONFIG_PCI)
+ /* make sure that the address in the table is actually
+ * on a VGA device's PCI BAR */
+
+ for_each_pci_dev(dev) {
+ int i;
+ if ((dev->class >> 8) != PCI_CLASS_DISPLAY_VGA)
+ continue;
+ for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+ resource_size_t start, end;
+
+ start = pci_resource_start(dev, i);
+ if (start == 0)
+ break;
+ end = pci_resource_end(dev, i);
+ if (screen_info.lfb_base >= start &&
+ screen_info.lfb_base < end) {
+ found_bar = 1;
+ }
+ }
+ }
+ if (!found_bar)
+ screen_info.lfb_base = 0;
+#endif
+ }
+ }
+ if (screen_info.lfb_base) {
+ screen_info.lfb_linelength = choose_value(info->stride,
+ screen_info.lfb_linelength, OVERRIDE_STRIDE,
+ info->flags);
+ screen_info.lfb_width = choose_value(info->width,
+ screen_info.lfb_width, OVERRIDE_WIDTH,
+ info->flags);
+ screen_info.lfb_height = choose_value(info->height,
+ screen_info.lfb_height, OVERRIDE_HEIGHT,
+ info->flags);
+ if (screen_info.orig_video_isVGA == 0)
+ screen_info.orig_video_isVGA = VIDEO_TYPE_EFI;
+ } else {
+ screen_info.lfb_linelength = 0;
+ screen_info.lfb_width = 0;
+ screen_info.lfb_height = 0;
+ screen_info.orig_video_isVGA = 0;
+ return 0;
+ }
+
+ printk(KERN_INFO "efifb: dmi detected %s - framebuffer at 0x%08x "
+ "(%dx%d, stride %d)\n", id->ident,
+ screen_info.lfb_base, screen_info.lfb_width,
+ screen_info.lfb_height, screen_info.lfb_linelength);
+
+ return 1;
+}
+
+#define EFIFB_DMI_SYSTEM_ID(vendor, name, enumid) \
+ { \
+ efifb_set_system, \
+ name, \
+ { \
+ DMI_MATCH(DMI_BIOS_VENDOR, vendor), \
+ DMI_MATCH(DMI_PRODUCT_NAME, name) \
+ }, \
+ &efifb_dmi_list[enumid] \
+ }
+
+static const struct dmi_system_id efifb_dmi_system_table[] __initconst = {
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac4,1", M_I17),
+ /* At least one of these two will be right; maybe both? */
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac5,1", M_I20),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac5,1", M_I20),
+ /* At least one of these two will be right; maybe both? */
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "iMac6,1", M_I24),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac6,1", M_I24),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac7,1", M_I20_SR),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac8,1", M_I24_8_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac10,1", M_I24_10_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "iMac11,1", M_I27_11_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "Macmini1,1", M_MINI),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini3,1", M_MINI_3_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "Macmini4,1", M_MINI_4_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook1,1", M_MB),
+ /* At least one of these two will be right; maybe both? */
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook2,1", M_MB),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook2,1", M_MB),
+ /* At least one of these two will be right; maybe both? */
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBook3,1", M_MB),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook3,1", M_MB),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook4,1", M_MB),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook5,1", M_MB_5_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook6,1", M_MB_6_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBook7,1", M_MB_7_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir1,1", M_MBA),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookAir3,1", M_MBA_3),
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro1,1", M_MBP),
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,1", M_MBP_2),
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro2,2", M_MBP_2_2),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro2,1", M_MBP_2),
+ EFIFB_DMI_SYSTEM_ID("Apple Computer, Inc.", "MacBookPro3,1", M_MBP_SR),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro3,1", M_MBP_SR),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro4,1", M_MBP_4),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,1", M_MBP_5_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,2", M_MBP_5_2),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro5,3", M_MBP_5_3),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,1", M_MBP_6_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro6,2", M_MBP_6_2),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro7,1", M_MBP_7_1),
+ EFIFB_DMI_SYSTEM_ID("Apple Inc.", "MacBookPro8,2", M_MBP_8_2),
+ {},
+};
+
+__init void sysfb_apply_efi_quirks(void)
+{
+ if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI ||
+ !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS))
+ dmi_check_system(efifb_dmi_system_table);
+}
diff --git a/arch/x86/kernel/sysfb_simplefb.c b/arch/x86/kernel/sysfb_simplefb.c
new file mode 100644
index 00000000000..86179d40989
--- /dev/null
+++ b/arch/x86/kernel/sysfb_simplefb.c
@@ -0,0 +1,95 @@
+/*
+ * Generic System Framebuffers on x86
+ * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+/*
+ * simple-framebuffer probing
+ * Try to convert "screen_info" into a "simple-framebuffer" compatible mode.
+ * If the mode is incompatible, we return "false" and let the caller create
+ * legacy nodes instead.
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/platform_data/simplefb.h>
+#include <linux/platform_device.h>
+#include <linux/screen_info.h>
+#include <asm/sysfb.h>
+
+static const char simplefb_resname[] = "BOOTFB";
+static const struct simplefb_format formats[] = SIMPLEFB_FORMATS;
+
+/* try parsing x86 screen_info into a simple-framebuffer mode struct */
+__init bool parse_mode(const struct screen_info *si,
+ struct simplefb_platform_data *mode)
+{
+ const struct simplefb_format *f;
+ __u8 type;
+ unsigned int i;
+
+ type = si->orig_video_isVGA;
+ if (type != VIDEO_TYPE_VLFB && type != VIDEO_TYPE_EFI)
+ return false;
+
+ for (i = 0; i < ARRAY_SIZE(formats); ++i) {
+ f = &formats[i];
+ if (si->lfb_depth == f->bits_per_pixel &&
+ si->red_size == f->red.length &&
+ si->red_pos == f->red.offset &&
+ si->green_size == f->green.length &&
+ si->green_pos == f->green.offset &&
+ si->blue_size == f->blue.length &&
+ si->blue_pos == f->blue.offset &&
+ si->rsvd_size == f->transp.length &&
+ si->rsvd_pos == f->transp.offset) {
+ mode->format = f->name;
+ mode->width = si->lfb_width;
+ mode->height = si->lfb_height;
+ mode->stride = si->lfb_linelength;
+ return true;
+ }
+ }
+
+ return false;
+}
+
+__init int create_simplefb(const struct screen_info *si,
+ const struct simplefb_platform_data *mode)
+{
+ struct platform_device *pd;
+ struct resource res;
+ unsigned long len;
+
+ /* don't use lfb_size as it may contain the whole VMEM instead of only
+ * the part that is occupied by the framebuffer */
+ len = mode->height * mode->stride;
+ len = PAGE_ALIGN(len);
+ if (len > (u64)si->lfb_size << 16) {
+ printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
+ return -EINVAL;
+ }
+
+ /* setup IORESOURCE_MEM as framebuffer memory */
+ memset(&res, 0, sizeof(res));
+ res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+ res.name = simplefb_resname;
+ res.start = si->lfb_base;
+ res.end = si->lfb_base + len - 1;
+ if (res.end <= res.start)
+ return -EINVAL;
+
+ pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0,
+ &res, 1, mode, sizeof(*mode));
+ if (IS_ERR(pd))
+ return PTR_ERR(pd);
+
+ return 0;
+}
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index addf7b58f4e..91a4496db43 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -301,6 +301,15 @@ static int tboot_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control)
return 0;
}
+static int tboot_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b)
+{
+ if (!tboot_enabled())
+ return 0;
+
+ pr_warning("tboot is not able to suspend on platforms with reduced hardware sleep (ACPIv5)");
+ return -ENODEV;
+}
+
static atomic_t ap_wfs_count;
static int tboot_wait_for_aps(int num_aps)
@@ -422,6 +431,7 @@ static __init int tboot_late_init(void)
#endif
acpi_os_set_prepare_sleep(&tboot_sleep);
+ acpi_os_set_prepare_extended_sleep(&tboot_extended_sleep);
return 0;
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 1b23a1c9274..729aa779ff7 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -58,6 +58,7 @@
#include <asm/mce.h>
#include <asm/fixmap.h>
#include <asm/mach_traps.h>
+#include <asm/alternative.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -87,7 +88,7 @@ static inline void conditional_sti(struct pt_regs *regs)
static inline void preempt_conditional_sti(struct pt_regs *regs)
{
- inc_preempt_count();
+ preempt_count_inc();
if (regs->flags & X86_EFLAGS_IF)
local_irq_enable();
}
@@ -102,7 +103,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs)
{
if (regs->flags & X86_EFLAGS_IF)
local_irq_disable();
- dec_preempt_count();
+ preempt_count_dec();
}
static int __kprobes
@@ -327,6 +328,9 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co
ftrace_int3_handler(regs))
return;
#endif
+ if (poke_int3_handler(regs))
+ return;
+
prev_state = exception_enter();
#ifdef CONFIG_KGDB_LOW_LEVEL_TRAP
if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP,
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6ff49247edf..930e5d48f56 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -89,6 +89,12 @@ int check_tsc_unstable(void)
}
EXPORT_SYMBOL_GPL(check_tsc_unstable);
+int check_tsc_disabled(void)
+{
+ return tsc_disabled;
+}
+EXPORT_SYMBOL_GPL(check_tsc_disabled);
+
#ifdef CONFIG_X86_TSC
int __init notsc_setup(char *str)
{
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 10c4f3006af..da6b35a9826 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -199,6 +199,15 @@ SECTIONS
__x86_cpu_dev_end = .;
}
+#ifdef CONFIG_X86_INTEL_MID
+ .x86_intel_mid_dev.init : AT(ADDR(.x86_intel_mid_dev.init) - \
+ LOAD_OFFSET) {
+ __x86_intel_mid_dev_start = .;
+ *(.x86_intel_mid_dev.init)
+ __x86_intel_mid_dev_end = .;
+ }
+#endif
+
/*
* start address and size of operations which during runtime
* can be patched with virtualization friendly instructions or
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index b014d9414d0..040681928e9 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -66,3 +66,10 @@ EXPORT_SYMBOL(empty_zero_page);
#ifndef CONFIG_PARAVIRT
EXPORT_SYMBOL(native_load_gs_index);
#endif
+
+#ifdef CONFIG_PREEMPT
+EXPORT_SYMBOL(___preempt_schedule);
+#ifdef CONFIG_CONTEXT_TRACKING
+EXPORT_SYMBOL(___preempt_schedule_context);
+#endif
+#endif
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 5f24c71acca..8ce0072cd70 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -107,6 +107,8 @@ struct x86_platform_ops x86_platform = {
};
EXPORT_SYMBOL_GPL(x86_platform);
+
+#if defined(CONFIG_PCI_MSI)
struct x86_msi_ops x86_msi = {
.setup_msi_irqs = native_setup_msi_irqs,
.compose_msi_msg = native_compose_msi_msg,
@@ -116,6 +118,28 @@ struct x86_msi_ops x86_msi = {
.setup_hpet_msi = default_setup_hpet_msi,
};
+/* MSI arch specific hooks */
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+ return x86_msi.setup_msi_irqs(dev, nvec, type);
+}
+
+void arch_teardown_msi_irqs(struct pci_dev *dev)
+{
+ x86_msi.teardown_msi_irqs(dev);
+}
+
+void arch_teardown_msi_irq(unsigned int irq)
+{
+ x86_msi.teardown_msi_irq(irq);
+}
+
+void arch_restore_msi_irqs(struct pci_dev *dev, int irq)
+{
+ x86_msi.restore_msi_irqs(dev, irq);
+}
+#endif
+
struct x86_io_apic_ops x86_io_apic_ops = {
.init = native_io_apic_init_mappings,
.read = native_io_apic_read,
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a20ecb5b6cb..b110fe6c03d 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -413,7 +413,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
(1 << KVM_FEATURE_CLOCKSOURCE2) |
(1 << KVM_FEATURE_ASYNC_PF) |
(1 << KVM_FEATURE_PV_EOI) |
- (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
+ (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT) |
+ (1 << KVM_FEATURE_PV_UNHALT);
if (sched_info_on())
entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 2bc1e81045b..ddc3f3d2afd 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2025,6 +2025,17 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
return rc;
}
+static int em_ret_far_imm(struct x86_emulate_ctxt *ctxt)
+{
+ int rc;
+
+ rc = em_ret_far(ctxt);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ rsp_increment(ctxt, ctxt->src.val);
+ return X86EMUL_CONTINUE;
+}
+
static int em_cmpxchg(struct x86_emulate_ctxt *ctxt)
{
/* Save real source value, then compare EAX against destination. */
@@ -3763,7 +3774,8 @@ static const struct opcode opcode_table[256] = {
G(ByteOp, group11), G(0, group11),
/* 0xC8 - 0xCF */
I(Stack | SrcImmU16 | Src2ImmByte, em_enter), I(Stack, em_leave),
- N, I(ImplicitOps | Stack, em_ret_far),
+ I(ImplicitOps | Stack | SrcImmU16, em_ret_far_imm),
+ I(ImplicitOps | Stack, em_ret_far),
D(ImplicitOps), DI(SrcImmByte, intn),
D(ImplicitOps | No64), II(ImplicitOps, em_iret, iret),
/* 0xD0 - 0xD7 */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index afc11245827..5439117d5c4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -79,16 +79,6 @@ static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
*((u32 *) (apic->regs + reg_off)) = val;
}
-static inline int apic_test_and_set_vector(int vec, void *bitmap)
-{
- return test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
-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_test_vector(int vec, void *bitmap)
{
return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
@@ -331,10 +321,10 @@ void kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir)
}
EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
-static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic)
+static inline void apic_set_irr(int vec, struct kvm_lapic *apic)
{
apic->irr_pending = true;
- return apic_test_and_set_vector(vec, apic->regs + APIC_IRR);
+ apic_set_vector(vec, apic->regs + APIC_IRR);
}
static inline int apic_search_irr(struct kvm_lapic *apic)
@@ -681,32 +671,28 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
if (unlikely(!apic_enabled(apic)))
break;
+ result = 1;
+
if (dest_map)
__set_bit(vcpu->vcpu_id, dest_map);
- if (kvm_x86_ops->deliver_posted_interrupt) {
- result = 1;
+ if (kvm_x86_ops->deliver_posted_interrupt)
kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
- } else {
- result = !apic_test_and_set_irr(vector, apic);
-
- if (!result) {
- if (trig_mode)
- apic_debug("level trig mode repeatedly "
- "for vector %d", vector);
- goto out;
- }
+ else {
+ apic_set_irr(vector, apic);
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_vcpu_kick(vcpu);
}
-out:
trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
- trig_mode, vector, !result);
+ trig_mode, vector, false);
break;
case APIC_DM_REMRD:
- apic_debug("Ignoring delivery mode 3\n");
+ result = 1;
+ vcpu->arch.pv.pv_unhalted = 1;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ kvm_vcpu_kick(vcpu);
break;
case APIC_DM_SMI:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9e9285ae9b9..dce0df8150d 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -132,8 +132,8 @@ module_param(dbg, bool, 0644);
(PAGE_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
* PT32_LEVEL_BITS))) - 1))
-#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | PT_USER_MASK \
- | PT64_NX_MASK)
+#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
+ | shadow_x_mask | shadow_nx_mask)
#define ACC_EXEC_MASK 1
#define ACC_WRITE_MASK PT_WRITABLE_MASK
@@ -331,11 +331,6 @@ static int is_large_pte(u64 pte)
return pte & PT_PAGE_SIZE_MASK;
}
-static int is_dirty_gpte(unsigned long pte)
-{
- return pte & PT_DIRTY_MASK;
-}
-
static int is_rmap_spte(u64 pte)
{
return is_shadow_present_pte(pte);
@@ -2052,12 +2047,18 @@ static void shadow_walk_next(struct kvm_shadow_walk_iterator *iterator)
return __shadow_walk_next(iterator, *iterator->sptep);
}
-static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp)
+static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed)
{
u64 spte;
+ BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK ||
+ VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
+
spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
- shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
+ shadow_user_mask | shadow_x_mask;
+
+ if (accessed)
+ spte |= shadow_accessed_mask;
mmu_spte_set(sptep, spte);
}
@@ -2574,14 +2575,6 @@ static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
mmu_free_roots(vcpu);
}
-static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
-{
- int bit7;
-
- bit7 = (gpte >> 7) & 1;
- return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
-}
-
static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
bool no_dirty_log)
{
@@ -2594,26 +2587,6 @@ static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
return gfn_to_pfn_memslot_atomic(slot, gfn);
}
-static bool prefetch_invalid_gpte(struct kvm_vcpu *vcpu,
- struct kvm_mmu_page *sp, u64 *spte,
- u64 gpte)
-{
- if (is_rsvd_bits_set(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
- goto no_present;
-
- if (!is_present_gpte(gpte))
- goto no_present;
-
- if (!(gpte & PT_ACCESSED_MASK))
- goto no_present;
-
- return false;
-
-no_present:
- drop_spte(vcpu->kvm, spte);
- return true;
-}
-
static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
struct kvm_mmu_page *sp,
u64 *start, u64 *end)
@@ -2710,7 +2683,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
iterator.level - 1,
1, ACC_ALL, iterator.sptep);
- link_shadow_page(iterator.sptep, sp);
+ link_shadow_page(iterator.sptep, sp, true);
}
}
return emulate;
@@ -2808,7 +2781,7 @@ exit:
return ret;
}
-static bool page_fault_can_be_fast(struct kvm_vcpu *vcpu, u32 error_code)
+static bool page_fault_can_be_fast(u32 error_code)
{
/*
* Do not fix the mmio spte with invalid generation number which
@@ -2861,7 +2834,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
bool ret = false;
u64 spte = 0ull;
- if (!page_fault_can_be_fast(vcpu, error_code))
+ if (!page_fault_can_be_fast(error_code))
return false;
walk_shadow_page_lockless_begin(vcpu);
@@ -3209,6 +3182,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
mmu_sync_roots(vcpu);
spin_unlock(&vcpu->kvm->mmu_lock);
}
+EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots);
static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gva_t vaddr,
u32 access, struct x86_exception *exception)
@@ -3478,6 +3452,7 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
++vcpu->stat.tlb_flush;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
+EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb);
static void paging_new_cr3(struct kvm_vcpu *vcpu)
{
@@ -3501,18 +3476,6 @@ static void paging_free(struct kvm_vcpu *vcpu)
nonpaging_free(vcpu);
}
-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(struct kvm *kvm, u64 *sptep, gfn_t gfn,
unsigned access, int *nr_present)
{
@@ -3530,16 +3493,6 @@ static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
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;
@@ -3549,6 +3502,11 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gp
return mmu->last_pte_bitmap & (1 << index);
}
+#define PTTYPE_EPT 18 /* arbitrary */
+#define PTTYPE PTTYPE_EPT
+#include "paging_tmpl.h"
+#undef PTTYPE
+
#define PTTYPE 64
#include "paging_tmpl.h"
#undef PTTYPE
@@ -3563,6 +3521,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
int maxphyaddr = cpuid_maxphyaddr(vcpu);
u64 exb_bit_rsvd = 0;
+ context->bad_mt_xwr = 0;
+
if (!context->nx)
exb_bit_rsvd = rsvd_bits(63, 63);
switch (context->root_level) {
@@ -3618,7 +3578,40 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
}
}
-static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *context, bool execonly)
+{
+ int maxphyaddr = cpuid_maxphyaddr(vcpu);
+ int pte;
+
+ context->rsvd_bits_mask[0][3] =
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7);
+ context->rsvd_bits_mask[0][2] =
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
+ context->rsvd_bits_mask[0][1] =
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6);
+ context->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51);
+
+ /* large page */
+ context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3];
+ context->rsvd_bits_mask[1][2] =
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29);
+ context->rsvd_bits_mask[1][1] =
+ rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20);
+ context->rsvd_bits_mask[1][0] = context->rsvd_bits_mask[0][0];
+
+ for (pte = 0; pte < 64; pte++) {
+ int rwx_bits = pte & 7;
+ int mt = pte >> 3;
+ if (mt == 0x2 || mt == 0x3 || mt == 0x7 ||
+ rwx_bits == 0x2 || rwx_bits == 0x6 ||
+ (rwx_bits == 0x4 && !execonly))
+ context->bad_mt_xwr |= (1ull << pte);
+ }
+}
+
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+ struct kvm_mmu *mmu, bool ept)
{
unsigned bit, byte, pfec;
u8 map;
@@ -3636,12 +3629,16 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu
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);
+ if (!ept) {
+ /* 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);
+ } else
+ /* Not really needed: no U/S accesses on ept */
+ u = 1;
fault = (ff && !x) || (uf && !u) || (wf && !w);
map |= fault << bit;
@@ -3676,7 +3673,7 @@ 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_permission_bitmask(vcpu, context, false);
update_last_pte_bitmap(vcpu, context);
ASSERT(is_pae(vcpu));
@@ -3706,7 +3703,7 @@ 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_permission_bitmask(vcpu, context, false);
update_last_pte_bitmap(vcpu, context);
context->new_cr3 = paging_new_cr3;
@@ -3768,7 +3765,7 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
context->gva_to_gpa = paging32_gva_to_gpa;
}
- update_permission_bitmask(vcpu, context);
+ update_permission_bitmask(vcpu, context, false);
update_last_pte_bitmap(vcpu, context);
return 0;
@@ -3800,6 +3797,33 @@ int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
}
EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
+int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+ bool execonly)
+{
+ ASSERT(vcpu);
+ ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
+
+ context->shadow_root_level = kvm_x86_ops->get_tdp_level();
+
+ context->nx = true;
+ context->new_cr3 = paging_new_cr3;
+ context->page_fault = ept_page_fault;
+ context->gva_to_gpa = ept_gva_to_gpa;
+ context->sync_page = ept_sync_page;
+ context->invlpg = ept_invlpg;
+ context->update_pte = ept_update_pte;
+ context->free = paging_free;
+ context->root_level = context->shadow_root_level;
+ context->root_hpa = INVALID_PAGE;
+ context->direct_map = false;
+
+ update_permission_bitmask(vcpu, context, true);
+ reset_rsvds_bits_mask_ept(vcpu, context, execonly);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
+
static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
{
int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu);
@@ -3847,7 +3871,7 @@ 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_permission_bitmask(vcpu, g_context, false);
update_last_pte_bitmap(vcpu, g_context);
return 0;
@@ -3923,8 +3947,8 @@ static bool need_remote_flush(u64 old, u64 new)
return true;
if ((old ^ new) & PT64_BASE_ADDR_MASK)
return true;
- old ^= PT64_NX_MASK;
- new ^= PT64_NX_MASK;
+ old ^= shadow_nx_mask;
+ new ^= shadow_nx_mask;
return (old & ~new & PT64_PERM_MASK) != 0;
}
@@ -4182,7 +4206,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
switch (er) {
case EMULATE_DONE:
return 1;
- case EMULATE_DO_MMIO:
+ case EMULATE_USER_EXIT:
++vcpu->stat.mmio_exits;
/* fall through */
case EMULATE_FAIL:
@@ -4390,23 +4414,19 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm)
/*
* The very rare case: if the generation-number is round,
* zap all shadow pages.
- *
- * The max value is MMIO_MAX_GEN - 1 since it is not called
- * when mark memslot invalid.
*/
- if (unlikely(kvm_current_mmio_generation(kvm) >= (MMIO_MAX_GEN - 1))) {
+ if (unlikely(kvm_current_mmio_generation(kvm) >= MMIO_MAX_GEN)) {
printk_ratelimited(KERN_INFO "kvm: zapping shadow pages for mmio generation wraparound\n");
kvm_mmu_invalidate_zap_all_pages(kvm);
}
}
-static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
+static unsigned long
+mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
{
struct kvm *kvm;
int nr_to_scan = sc->nr_to_scan;
-
- if (nr_to_scan == 0)
- goto out;
+ unsigned long freed = 0;
raw_spin_lock(&kvm_lock);
@@ -4441,25 +4461,37 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
goto unlock;
}
- prepare_zap_oldest_mmu_page(kvm, &invalid_list);
+ if (prepare_zap_oldest_mmu_page(kvm, &invalid_list))
+ freed++;
kvm_mmu_commit_zap_page(kvm, &invalid_list);
unlock:
spin_unlock(&kvm->mmu_lock);
srcu_read_unlock(&kvm->srcu, idx);
+ /*
+ * unfair on small ones
+ * per-vm shrinkers cry out
+ * sadness comes quickly
+ */
list_move_tail(&kvm->vm_list, &vm_list);
break;
}
raw_spin_unlock(&kvm_lock);
+ return freed;
-out:
+}
+
+static unsigned long
+mmu_shrink_count(struct shrinker *shrink, struct shrink_control *sc)
+{
return percpu_counter_read_positive(&kvm_total_used_mmu_pages);
}
static struct shrinker mmu_shrinker = {
- .shrink = mmu_shrink,
+ .count_objects = mmu_shrink_count,
+ .scan_objects = mmu_shrink_scan,
.seeks = DEFAULT_SEEKS * 10,
};
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 5b59c573aba..77e044a0f5f 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -71,6 +71,8 @@ enum {
int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
+int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+ bool execonly);
static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
{
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 7769699d48a..ad75d77999d 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -23,6 +23,13 @@
* so the code in this file is compiled twice, once per pte size.
*/
+/*
+ * This is used to catch non optimized PT_GUEST_(DIRTY|ACCESS)_SHIFT macro
+ * uses for EPT without A/D paging type.
+ */
+extern u64 __pure __using_nonexistent_pte_bit(void)
+ __compiletime_error("wrong use of PT_GUEST_(DIRTY|ACCESS)_SHIFT");
+
#if PTTYPE == 64
#define pt_element_t u64
#define guest_walker guest_walker64
@@ -32,6 +39,10 @@
#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define PT_LEVEL_BITS PT64_LEVEL_BITS
+ #define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK
+ #define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
+ #define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
#ifdef CONFIG_X86_64
#define PT_MAX_FULL_LEVELS 4
#define CMPXCHG cmpxchg
@@ -49,7 +60,26 @@
#define PT_INDEX(addr, level) PT32_INDEX(addr, level)
#define PT_LEVEL_BITS PT32_LEVEL_BITS
#define PT_MAX_FULL_LEVELS 2
+ #define PT_GUEST_ACCESSED_MASK PT_ACCESSED_MASK
+ #define PT_GUEST_DIRTY_MASK PT_DIRTY_MASK
+ #define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT
+ #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT
#define CMPXCHG cmpxchg
+#elif PTTYPE == PTTYPE_EPT
+ #define pt_element_t u64
+ #define guest_walker guest_walkerEPT
+ #define FNAME(name) ept_##name
+ #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+ #define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
+ #define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
+ #define PT_INDEX(addr, level) PT64_INDEX(addr, level)
+ #define PT_LEVEL_BITS PT64_LEVEL_BITS
+ #define PT_GUEST_ACCESSED_MASK 0
+ #define PT_GUEST_DIRTY_MASK 0
+ #define PT_GUEST_DIRTY_SHIFT __using_nonexistent_pte_bit()
+ #define PT_GUEST_ACCESSED_SHIFT __using_nonexistent_pte_bit()
+ #define CMPXCHG cmpxchg64
+ #define PT_MAX_FULL_LEVELS 4
#else
#error Invalid PTTYPE value
#endif
@@ -69,6 +99,7 @@ struct guest_walker {
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];
+ bool pte_writable[PT_MAX_FULL_LEVELS];
unsigned pt_access;
unsigned pte_access;
gfn_t gfn;
@@ -80,6 +111,40 @@ static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
}
+static inline void FNAME(protect_clean_gpte)(unsigned *access, unsigned gpte)
+{
+ unsigned mask;
+
+ /* dirty bit is not supported, so no need to track it */
+ if (!PT_GUEST_DIRTY_MASK)
+ return;
+
+ BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
+
+ mask = (unsigned)~ACC_WRITE_MASK;
+ /* Allow write access to dirty gptes */
+ mask |= (gpte >> (PT_GUEST_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) &
+ PT_WRITABLE_MASK;
+ *access &= mask;
+}
+
+static bool FNAME(is_rsvd_bits_set)(struct kvm_mmu *mmu, u64 gpte, int level)
+{
+ int bit7 = (gpte >> 7) & 1, low6 = gpte & 0x3f;
+
+ return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) |
+ ((mmu->bad_mt_xwr & (1ull << low6)) != 0);
+}
+
+static inline int FNAME(is_present_gpte)(unsigned long pte)
+{
+#if PTTYPE != PTTYPE_EPT
+ return is_present_gpte(pte);
+#else
+ return pte & 7;
+#endif
+}
+
static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
pt_element_t __user *ptep_user, unsigned index,
pt_element_t orig_pte, pt_element_t new_pte)
@@ -103,6 +168,42 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
return (ret != orig_pte);
}
+static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
+ struct kvm_mmu_page *sp, u64 *spte,
+ u64 gpte)
+{
+ if (FNAME(is_rsvd_bits_set)(&vcpu->arch.mmu, gpte, PT_PAGE_TABLE_LEVEL))
+ goto no_present;
+
+ if (!FNAME(is_present_gpte)(gpte))
+ goto no_present;
+
+ /* if accessed bit is not supported prefetch non accessed gpte */
+ if (PT_GUEST_ACCESSED_MASK && !(gpte & PT_GUEST_ACCESSED_MASK))
+ goto no_present;
+
+ return false;
+
+no_present:
+ drop_spte(vcpu->kvm, spte);
+ return true;
+}
+
+static inline unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, u64 gpte)
+{
+ unsigned access;
+#if PTTYPE == PTTYPE_EPT
+ access = ((gpte & VMX_EPT_WRITABLE_MASK) ? ACC_WRITE_MASK : 0) |
+ ((gpte & VMX_EPT_EXECUTABLE_MASK) ? ACC_EXEC_MASK : 0) |
+ ACC_USER_MASK;
+#else
+ access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
+ access &= ~(gpte >> PT64_NX_SHIFT);
+#endif
+
+ return access;
+}
+
static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
struct kvm_mmu *mmu,
struct guest_walker *walker,
@@ -114,22 +215,43 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
gfn_t table_gfn;
int ret;
+ /* dirty/accessed bits are not supported, so no need to update them */
+ if (!PT_GUEST_DIRTY_MASK)
+ return 0;
+
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)) {
+ if (!(pte & PT_GUEST_ACCESSED_MASK)) {
trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte));
- pte |= PT_ACCESSED_MASK;
+ pte |= PT_GUEST_ACCESSED_MASK;
}
- if (level == walker->level && write_fault && !is_dirty_gpte(pte)) {
+ if (level == walker->level && write_fault &&
+ !(pte & PT_GUEST_DIRTY_MASK)) {
trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
- pte |= PT_DIRTY_MASK;
+ pte |= PT_GUEST_DIRTY_MASK;
}
if (pte == orig_pte)
continue;
+ /*
+ * If the slot is read-only, simply do not process the accessed
+ * and dirty bits. This is the correct thing to do if the slot
+ * is ROM, and page tables in read-as-ROM/write-as-MMIO slots
+ * are only supported if the accessed and dirty bits are already
+ * set in the ROM (so that MMIO writes are never needed).
+ *
+ * Note that NPT does not allow this at all and faults, since
+ * it always wants nested page table entries for the guest
+ * page tables to be writable. And EPT works but will simply
+ * overwrite the read-only memory to set the accessed and dirty
+ * bits.
+ */
+ if (unlikely(!walker->pte_writable[level - 1]))
+ continue;
+
ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
if (ret)
return ret;
@@ -170,7 +292,7 @@ retry_walk:
if (walker->level == PT32E_ROOT_LEVEL) {
pte = mmu->get_pdptr(vcpu, (addr >> 30) & 3);
trace_kvm_mmu_paging_element(pte, walker->level);
- if (!is_present_gpte(pte))
+ if (!FNAME(is_present_gpte)(pte))
goto error;
--walker->level;
}
@@ -179,7 +301,7 @@ retry_walk:
ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
(mmu->get_cr3(vcpu) & CR3_NONPAE_RESERVED_BITS) == 0);
- accessed_dirty = PT_ACCESSED_MASK;
+ accessed_dirty = PT_GUEST_ACCESSED_MASK;
pt_access = pte_access = ACC_ALL;
++walker->level;
@@ -204,7 +326,8 @@ retry_walk:
goto error;
real_gfn = gpa_to_gfn(real_gfn);
- host_addr = gfn_to_hva(vcpu->kvm, real_gfn);
+ host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn,
+ &walker->pte_writable[walker->level - 1]);
if (unlikely(kvm_is_error_hva(host_addr)))
goto error;
@@ -215,17 +338,17 @@ retry_walk:
trace_kvm_mmu_paging_element(pte, walker->level);
- if (unlikely(!is_present_gpte(pte)))
+ if (unlikely(!FNAME(is_present_gpte)(pte)))
goto error;
- if (unlikely(is_rsvd_bits_set(&vcpu->arch.mmu, pte,
- walker->level))) {
+ if (unlikely(FNAME(is_rsvd_bits_set)(mmu, pte,
+ walker->level))) {
errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
goto error;
}
accessed_dirty &= pte;
- pte_access = pt_access & gpte_access(vcpu, pte);
+ pte_access = pt_access & FNAME(gpte_access)(vcpu, pte);
walker->ptes[walker->level - 1] = pte;
} while (!is_last_gpte(mmu, walker->level, pte));
@@ -248,13 +371,15 @@ retry_walk:
walker->gfn = real_gpa >> PAGE_SHIFT;
if (!write_fault)
- protect_clean_gpte(&pte_access, pte);
+ FNAME(protect_clean_gpte)(&pte_access, pte);
else
/*
- * On a write fault, fold the dirty bit into accessed_dirty by
- * shifting it one place right.
+ * On a write fault, fold the dirty bit into accessed_dirty.
+ * For modes without A/D bits support accessed_dirty will be
+ * always clear.
*/
- accessed_dirty &= pte >> (PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT);
+ accessed_dirty &= pte >>
+ (PT_GUEST_DIRTY_SHIFT - PT_GUEST_ACCESSED_SHIFT);
if (unlikely(!accessed_dirty)) {
ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
@@ -279,6 +404,25 @@ error:
walker->fault.vector = PF_VECTOR;
walker->fault.error_code_valid = true;
walker->fault.error_code = errcode;
+
+#if PTTYPE == PTTYPE_EPT
+ /*
+ * Use PFERR_RSVD_MASK in error_code to to tell if EPT
+ * misconfiguration requires to be injected. The detection is
+ * done by is_rsvd_bits_set() above.
+ *
+ * We set up the value of exit_qualification to inject:
+ * [2:0] - Derive from [2:0] of real exit_qualification at EPT violation
+ * [5:3] - Calculated by the page walk of the guest EPT page tables
+ * [7:8] - Derived from [7:8] of real exit_qualification
+ *
+ * The other bits are set to 0.
+ */
+ if (!(errcode & PFERR_RSVD_MASK)) {
+ vcpu->arch.exit_qualification &= 0x187;
+ vcpu->arch.exit_qualification |= ((pt_access & pte) & 0x7) << 3;
+ }
+#endif
walker->fault.address = addr;
walker->fault.nested_page_fault = mmu != vcpu->arch.walk_mmu;
@@ -293,6 +437,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker,
access);
}
+#if PTTYPE != PTTYPE_EPT
static int FNAME(walk_addr_nested)(struct guest_walker *walker,
struct kvm_vcpu *vcpu, gva_t addr,
u32 access)
@@ -300,6 +445,7 @@ static int FNAME(walk_addr_nested)(struct guest_walker *walker,
return FNAME(walk_addr_generic)(walker, vcpu, &vcpu->arch.nested_mmu,
addr, access);
}
+#endif
static bool
FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
@@ -309,14 +455,14 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
gfn_t gfn;
pfn_t pfn;
- if (prefetch_invalid_gpte(vcpu, sp, spte, gpte))
+ if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
return false;
pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
gfn = gpte_to_gfn(gpte);
- pte_access = sp->role.access & gpte_access(vcpu, gpte);
- protect_clean_gpte(&pte_access, gpte);
+ pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte);
+ FNAME(protect_clean_gpte)(&pte_access, gpte);
pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
no_dirty_log && (pte_access & ACC_WRITE_MASK));
if (is_error_pfn(pfn))
@@ -446,7 +592,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
goto out_gpte_changed;
if (sp)
- link_shadow_page(it.sptep, sp);
+ link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
}
for (;
@@ -466,7 +612,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1,
true, direct_access, it.sptep);
- link_shadow_page(it.sptep, sp);
+ link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK);
}
clear_sp_write_flooding_count(it.sptep);
@@ -727,6 +873,7 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access,
return gpa;
}
+#if PTTYPE != PTTYPE_EPT
static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
u32 access,
struct x86_exception *exception)
@@ -745,6 +892,7 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr,
return gpa;
}
+#endif
/*
* Using the cached information from sp->gfns is safe because:
@@ -785,15 +933,15 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
sizeof(pt_element_t)))
return -EINVAL;
- if (prefetch_invalid_gpte(vcpu, sp, &sp->spt[i], gpte)) {
+ if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) {
vcpu->kvm->tlbs_dirty++;
continue;
}
gfn = gpte_to_gfn(gpte);
pte_access = sp->role.access;
- pte_access &= gpte_access(vcpu, gpte);
- protect_clean_gpte(&pte_access, gpte);
+ pte_access &= FNAME(gpte_access)(vcpu, gpte);
+ FNAME(protect_clean_gpte)(&pte_access, gpte);
if (sync_mmio_spte(vcpu->kvm, &sp->spt[i], gfn, pte_access,
&nr_present))
@@ -830,3 +978,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
#undef gpte_to_gfn
#undef gpte_to_gfn_lvl
#undef CMPXCHG
+#undef PT_GUEST_ACCESSED_MASK
+#undef PT_GUEST_DIRTY_MASK
+#undef PT_GUEST_DIRTY_SHIFT
+#undef PT_GUEST_ACCESSED_SHIFT
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index c53e797e736..5c4f63151b4 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -160,7 +160,7 @@ static void stop_counter(struct kvm_pmc *pmc)
static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
unsigned config, bool exclude_user, bool exclude_kernel,
- bool intr)
+ bool intr, bool in_tx, bool in_tx_cp)
{
struct perf_event *event;
struct perf_event_attr attr = {
@@ -173,6 +173,10 @@ static void reprogram_counter(struct kvm_pmc *pmc, u32 type,
.exclude_kernel = exclude_kernel,
.config = config,
};
+ if (in_tx)
+ attr.config |= HSW_IN_TX;
+ if (in_tx_cp)
+ attr.config |= HSW_IN_TX_CHECKPOINTED;
attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc);
@@ -226,7 +230,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
if (!(eventsel & (ARCH_PERFMON_EVENTSEL_EDGE |
ARCH_PERFMON_EVENTSEL_INV |
- ARCH_PERFMON_EVENTSEL_CMASK))) {
+ ARCH_PERFMON_EVENTSEL_CMASK |
+ HSW_IN_TX |
+ HSW_IN_TX_CHECKPOINTED))) {
config = find_arch_event(&pmc->vcpu->arch.pmu, event_select,
unit_mask);
if (config != PERF_COUNT_HW_MAX)
@@ -239,7 +245,9 @@ static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
reprogram_counter(pmc, type, config,
!(eventsel & ARCH_PERFMON_EVENTSEL_USR),
!(eventsel & ARCH_PERFMON_EVENTSEL_OS),
- eventsel & ARCH_PERFMON_EVENTSEL_INT);
+ eventsel & ARCH_PERFMON_EVENTSEL_INT,
+ (eventsel & HSW_IN_TX),
+ (eventsel & HSW_IN_TX_CHECKPOINTED));
}
static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
@@ -256,7 +264,7 @@ static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx)
arch_events[fixed_pmc_events[idx]].event_type,
!(en & 0x2), /* exclude user */
!(en & 0x1), /* exclude kernel */
- pmi);
+ pmi, false, false);
}
static inline u8 fixed_en_pmi(u64 ctrl, int idx)
@@ -408,7 +416,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
} else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) {
if (data == pmc->eventsel)
return 0;
- if (!(data & 0xffffffff00200000ull)) {
+ if (!(data & pmu->reserved_bits)) {
reprogram_gp_counter(pmc, data);
return 0;
}
@@ -450,6 +458,7 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
pmu->counter_bitmask[KVM_PMC_GP] = 0;
pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
pmu->version = 0;
+ pmu->reserved_bits = 0xffffffff00200000ull;
entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
if (!entry)
@@ -478,6 +487,12 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
(((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED);
pmu->global_ctrl_mask = ~pmu->global_ctrl;
+
+ entry = kvm_find_cpuid_entry(vcpu, 7, 0);
+ if (entry &&
+ (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) &&
+ (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM)))
+ pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED;
}
void kvm_pmu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 064d0be67ec..2b2fce1b200 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -373,6 +373,7 @@ struct nested_vmx {
* we must keep them pinned while L2 runs.
*/
struct page *apic_access_page;
+ u64 msr_ia32_feature_control;
};
#define POSTED_INTR_ON 0
@@ -711,10 +712,10 @@ static void nested_release_page_clean(struct page *page)
kvm_release_page_clean(page);
}
+static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
static u64 construct_eptp(unsigned long root_hpa);
static void kvm_cpu_vmxon(u64 addr);
static void kvm_cpu_vmxoff(void);
-static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
static void vmx_set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg);
@@ -1039,12 +1040,16 @@ static inline bool nested_cpu_has2(struct vmcs12 *vmcs12, u32 bit)
(vmcs12->secondary_vm_exec_control & bit);
}
-static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12,
- struct kvm_vcpu *vcpu)
+static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12)
{
return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS;
}
+static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12)
+{
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT);
+}
+
static inline bool is_exception(u32 intr_info)
{
return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
@@ -2155,6 +2160,7 @@ static u32 nested_vmx_pinbased_ctls_low, nested_vmx_pinbased_ctls_high;
static u32 nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high;
static u32 nested_vmx_entry_ctls_low, nested_vmx_entry_ctls_high;
static u32 nested_vmx_misc_low, nested_vmx_misc_high;
+static u32 nested_vmx_ept_caps;
static __init void nested_vmx_setup_ctls_msrs(void)
{
/*
@@ -2190,14 +2196,17 @@ static __init void nested_vmx_setup_ctls_msrs(void)
* If bit 55 of VMX_BASIC is off, bits 0-8 and 10, 11, 13, 14, 16 and
* 17 must be 1.
*/
+ rdmsr(MSR_IA32_VMX_EXIT_CTLS,
+ nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high);
nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
/* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */
+ nested_vmx_exit_ctls_high &=
#ifdef CONFIG_X86_64
- nested_vmx_exit_ctls_high = VM_EXIT_HOST_ADDR_SPACE_SIZE;
-#else
- nested_vmx_exit_ctls_high = 0;
+ VM_EXIT_HOST_ADDR_SPACE_SIZE |
#endif
- nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
+ VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+ nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
+ VM_EXIT_LOAD_IA32_EFER);
/* entry controls */
rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
@@ -2205,8 +2214,12 @@ static __init void nested_vmx_setup_ctls_msrs(void)
/* If bit 55 of VMX_BASIC is off, bits 0-8 and 12 must be 1. */
nested_vmx_entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
nested_vmx_entry_ctls_high &=
- VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_IA32E_MODE;
- nested_vmx_entry_ctls_high |= VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR;
+#ifdef CONFIG_X86_64
+ VM_ENTRY_IA32E_MODE |
+#endif
+ VM_ENTRY_LOAD_IA32_PAT;
+ nested_vmx_entry_ctls_high |= (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR |
+ VM_ENTRY_LOAD_IA32_EFER);
/* cpu-based controls */
rdmsr(MSR_IA32_VMX_PROCBASED_CTLS,
@@ -2241,6 +2254,22 @@ static __init void nested_vmx_setup_ctls_msrs(void)
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_WBINVD_EXITING;
+ if (enable_ept) {
+ /* nested EPT: emulate EPT also to L1 */
+ nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT;
+ nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
+ VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
+ nested_vmx_ept_caps &= vmx_capability.ept;
+ /*
+ * Since invept is completely emulated we support both global
+ * and context invalidation independent of what host cpu
+ * supports
+ */
+ nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
+ VMX_EPT_EXTENT_CONTEXT_BIT;
+ } else
+ nested_vmx_ept_caps = 0;
+
/* miscellaneous data */
rdmsr(MSR_IA32_VMX_MISC, nested_vmx_misc_low, nested_vmx_misc_high);
nested_vmx_misc_low &= VMX_MISC_PREEMPTION_TIMER_RATE_MASK |
@@ -2282,8 +2311,11 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
switch (msr_index) {
case MSR_IA32_FEATURE_CONTROL:
- *pdata = 0;
- break;
+ if (nested_vmx_allowed(vcpu)) {
+ *pdata = to_vmx(vcpu)->nested.msr_ia32_feature_control;
+ break;
+ }
+ return 0;
case MSR_IA32_VMX_BASIC:
/*
* This MSR reports some information about VMX support. We
@@ -2346,8 +2378,8 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
nested_vmx_secondary_ctls_high);
break;
case MSR_IA32_VMX_EPT_VPID_CAP:
- /* Currently, no nested ept or nested vpid */
- *pdata = 0;
+ /* Currently, no nested vpid support */
+ *pdata = nested_vmx_ept_caps;
break;
default:
return 0;
@@ -2356,14 +2388,24 @@ static int vmx_get_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
return 1;
}
-static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
+static int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
+ u32 msr_index = msr_info->index;
+ u64 data = msr_info->data;
+ bool host_initialized = msr_info->host_initiated;
+
if (!nested_vmx_allowed(vcpu))
return 0;
- if (msr_index == MSR_IA32_FEATURE_CONTROL)
- /* TODO: the right thing. */
+ if (msr_index == MSR_IA32_FEATURE_CONTROL) {
+ if (!host_initialized &&
+ to_vmx(vcpu)->nested.msr_ia32_feature_control
+ & FEATURE_CONTROL_LOCKED)
+ return 0;
+ to_vmx(vcpu)->nested.msr_ia32_feature_control = data;
return 1;
+ }
+
/*
* No need to treat VMX capability MSRs specially: If we don't handle
* them, handle_wrmsr will #GP(0), which is correct (they are readonly)
@@ -2494,7 +2536,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
/* Otherwise falls through */
default:
- if (vmx_set_vmx_msr(vcpu, msr_index, data))
+ if (vmx_set_vmx_msr(vcpu, msr_info))
break;
msr = find_msr_entry(vmx, msr_index);
if (msr) {
@@ -3213,25 +3255,29 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
{
+ struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
if (!test_bit(VCPU_EXREG_PDPTR,
(unsigned long *)&vcpu->arch.regs_dirty))
return;
if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
- vmcs_write64(GUEST_PDPTR0, vcpu->arch.mmu.pdptrs[0]);
- vmcs_write64(GUEST_PDPTR1, vcpu->arch.mmu.pdptrs[1]);
- vmcs_write64(GUEST_PDPTR2, vcpu->arch.mmu.pdptrs[2]);
- vmcs_write64(GUEST_PDPTR3, vcpu->arch.mmu.pdptrs[3]);
+ vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
+ vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
+ vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
+ vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
}
}
static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
{
+ struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
- vcpu->arch.mmu.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
- vcpu->arch.mmu.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
- vcpu->arch.mmu.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
- vcpu->arch.mmu.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+ mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+ mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+ mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+ mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
}
__set_bit(VCPU_EXREG_PDPTR,
@@ -5297,14 +5343,29 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
return 0;
}
+ /*
+ * EPT violation happened while executing iret from NMI,
+ * "blocked by NMI" bit has to be set before next VM entry.
+ * There are errata that may cause this bit to not be set:
+ * AAK134, BY25.
+ */
+ if (!(to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) &&
+ cpu_has_virtual_nmis() &&
+ (exit_qualification & INTR_INFO_UNBLOCK_NMI))
+ vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO, GUEST_INTR_STATE_NMI);
+
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
trace_kvm_page_fault(gpa, exit_qualification);
/* It is a write fault? */
error_code = exit_qualification & (1U << 1);
+ /* It is a fetch fault? */
+ error_code |= (exit_qualification & (1U << 2)) << 2;
/* ept page table is present? */
error_code |= (exit_qualification >> 3) & 0x1;
+ vcpu->arch.exit_qualification = exit_qualification;
+
return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
}
@@ -5438,7 +5499,8 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
- if (err == EMULATE_DO_MMIO) {
+ if (err == EMULATE_USER_EXIT) {
+ ++vcpu->stat.mmio_exits;
ret = 0;
goto out;
}
@@ -5567,8 +5629,47 @@ static void nested_free_all_saved_vmcss(struct vcpu_vmx *vmx)
free_loaded_vmcs(&vmx->vmcs01);
}
+/*
+ * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
+ * set the success or error code of an emulated VMX instruction, as specified
+ * by Vol 2B, VMX Instruction Reference, "Conventions".
+ */
+static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
+{
+ vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
+ & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+ X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
+}
+
+static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
+{
+ vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+ & ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
+ X86_EFLAGS_SF | X86_EFLAGS_OF))
+ | X86_EFLAGS_CF);
+}
+
static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
- u32 vm_instruction_error);
+ u32 vm_instruction_error)
+{
+ if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
+ /*
+ * failValid writes the error number to the current VMCS, which
+ * can't be done there isn't a current VMCS.
+ */
+ nested_vmx_failInvalid(vcpu);
+ return;
+ }
+ vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
+ & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
+ X86_EFLAGS_SF | X86_EFLAGS_OF))
+ | X86_EFLAGS_ZF);
+ get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
+ /*
+ * We don't need to force a shadow sync because
+ * VM_INSTRUCTION_ERROR is not shadowed
+ */
+}
/*
* Emulate the VMXON instruction.
@@ -5583,6 +5684,8 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
struct kvm_segment cs;
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs *shadow_vmcs;
+ const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
+ | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
/* The Intel VMX Instruction Reference lists a bunch of bits that
* are prerequisite to running VMXON, most notably cr4.VMXE must be
@@ -5611,6 +5714,13 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
skip_emulated_instruction(vcpu);
return 1;
}
+
+ if ((vmx->nested.msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
+ != VMXON_NEEDED_FEATURES) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+
if (enable_shadow_vmcs) {
shadow_vmcs = alloc_vmcs();
if (!shadow_vmcs)
@@ -5628,6 +5738,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
vmx->nested.vmxon = true;
skip_emulated_instruction(vcpu);
+ nested_vmx_succeed(vcpu);
return 1;
}
@@ -5712,6 +5823,7 @@ static int handle_vmoff(struct kvm_vcpu *vcpu)
return 1;
free_nested(to_vmx(vcpu));
skip_emulated_instruction(vcpu);
+ nested_vmx_succeed(vcpu);
return 1;
}
@@ -5768,48 +5880,6 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
return 0;
}
-/*
- * The following 3 functions, nested_vmx_succeed()/failValid()/failInvalid(),
- * set the success or error code of an emulated VMX instruction, as specified
- * by Vol 2B, VMX Instruction Reference, "Conventions".
- */
-static void nested_vmx_succeed(struct kvm_vcpu *vcpu)
-{
- vmx_set_rflags(vcpu, vmx_get_rflags(vcpu)
- & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
- X86_EFLAGS_ZF | X86_EFLAGS_SF | X86_EFLAGS_OF));
-}
-
-static void nested_vmx_failInvalid(struct kvm_vcpu *vcpu)
-{
- vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
- & ~(X86_EFLAGS_PF | X86_EFLAGS_AF | X86_EFLAGS_ZF |
- X86_EFLAGS_SF | X86_EFLAGS_OF))
- | X86_EFLAGS_CF);
-}
-
-static void nested_vmx_failValid(struct kvm_vcpu *vcpu,
- u32 vm_instruction_error)
-{
- if (to_vmx(vcpu)->nested.current_vmptr == -1ull) {
- /*
- * failValid writes the error number to the current VMCS, which
- * can't be done there isn't a current VMCS.
- */
- nested_vmx_failInvalid(vcpu);
- return;
- }
- vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
- & ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
- X86_EFLAGS_SF | X86_EFLAGS_OF))
- | X86_EFLAGS_ZF);
- get_vmcs12(vcpu)->vm_instruction_error = vm_instruction_error;
- /*
- * We don't need to force a shadow sync because
- * VM_INSTRUCTION_ERROR is not shadowed
- */
-}
-
/* Emulate the VMCLEAR instruction */
static int handle_vmclear(struct kvm_vcpu *vcpu)
{
@@ -5972,8 +6042,8 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
unsigned long field;
u64 field_value;
struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs;
- unsigned long *fields = (unsigned long *)shadow_read_write_fields;
- int num_fields = max_shadow_read_write_fields;
+ const unsigned long *fields = shadow_read_write_fields;
+ const int num_fields = max_shadow_read_write_fields;
vmcs_load(shadow_vmcs);
@@ -6002,12 +6072,11 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx)
static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
{
- unsigned long *fields[] = {
- (unsigned long *)shadow_read_write_fields,
- (unsigned long *)shadow_read_only_fields
+ const unsigned long *fields[] = {
+ shadow_read_write_fields,
+ shadow_read_only_fields
};
- int num_lists = ARRAY_SIZE(fields);
- int max_fields[] = {
+ const int max_fields[] = {
max_shadow_read_write_fields,
max_shadow_read_only_fields
};
@@ -6018,7 +6087,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx)
vmcs_load(shadow_vmcs);
- for (q = 0; q < num_lists; q++) {
+ for (q = 0; q < ARRAY_SIZE(fields); q++) {
for (i = 0; i < max_fields[q]; i++) {
field = fields[q][i];
vmcs12_read_any(&vmx->vcpu, field, &field_value);
@@ -6248,6 +6317,74 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
return 1;
}
+/* Emulate the INVEPT instruction */
+static int handle_invept(struct kvm_vcpu *vcpu)
+{
+ u32 vmx_instruction_info, types;
+ unsigned long type;
+ gva_t gva;
+ struct x86_exception e;
+ struct {
+ u64 eptp, gpa;
+ } operand;
+ u64 eptp_mask = ((1ull << 51) - 1) & PAGE_MASK;
+
+ if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) ||
+ !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+
+ if (!nested_vmx_check_permission(vcpu))
+ return 1;
+
+ if (!kvm_read_cr0_bits(vcpu, X86_CR0_PE)) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
+ return 1;
+ }
+
+ vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+ type = kvm_register_read(vcpu, (vmx_instruction_info >> 28) & 0xf);
+
+ types = (nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
+
+ if (!(types & (1UL << type))) {
+ nested_vmx_failValid(vcpu,
+ VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+ return 1;
+ }
+
+ /* According to the Intel VMX instruction reference, the memory
+ * operand is read even if it isn't needed (e.g., for type==global)
+ */
+ if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+ vmx_instruction_info, &gva))
+ return 1;
+ if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &operand,
+ sizeof(operand), &e)) {
+ kvm_inject_page_fault(vcpu, &e);
+ return 1;
+ }
+
+ switch (type) {
+ case VMX_EPT_EXTENT_CONTEXT:
+ if ((operand.eptp & eptp_mask) !=
+ (nested_ept_get_cr3(vcpu) & eptp_mask))
+ break;
+ case VMX_EPT_EXTENT_GLOBAL:
+ kvm_mmu_sync_roots(vcpu);
+ kvm_mmu_flush_tlb(vcpu);
+ nested_vmx_succeed(vcpu);
+ break;
+ default:
+ BUG_ON(1);
+ break;
+ }
+
+ skip_emulated_instruction(vcpu);
+ return 1;
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
@@ -6292,6 +6429,7 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause,
[EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op,
[EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op,
+ [EXIT_REASON_INVEPT] = handle_invept,
};
static const int kvm_vmx_max_exit_handlers =
@@ -6518,6 +6656,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_VMPTRST: case EXIT_REASON_VMREAD:
case EXIT_REASON_VMRESUME: case EXIT_REASON_VMWRITE:
case EXIT_REASON_VMOFF: case EXIT_REASON_VMON:
+ case EXIT_REASON_INVEPT:
/*
* VMX instructions trap unconditionally. This allows L1 to
* emulate them for its L2 guest, i.e., allows 3-level nesting!
@@ -6550,7 +6689,20 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
return nested_cpu_has2(vmcs12,
SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
case EXIT_REASON_EPT_VIOLATION:
+ /*
+ * L0 always deals with the EPT violation. If nested EPT is
+ * used, and the nested mmu code discovers that the address is
+ * missing in the guest EPT table (EPT12), the EPT violation
+ * will be injected with nested_ept_inject_page_fault()
+ */
+ return 0;
case EXIT_REASON_EPT_MISCONFIG:
+ /*
+ * L2 never uses directly L1's EPT, but rather L0's own EPT
+ * table (shadow on EPT) or a merged EPT table that L0 built
+ * (EPT on EPT). So any problems with the structure of the
+ * table is L0's fault.
+ */
return 0;
case EXIT_REASON_PREEMPTION_TIMER:
return vmcs12->pin_based_vm_exec_control &
@@ -6638,7 +6790,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked &&
!(is_guest_mode(vcpu) && nested_cpu_has_virtual_nmis(
- get_vmcs12(vcpu), vcpu)))) {
+ get_vmcs12(vcpu))))) {
if (vmx_interrupt_allowed(vcpu)) {
vmx->soft_vnmi_blocked = 0;
} else if (vmx->vnmi_blocked_time > 1000000000LL &&
@@ -7326,6 +7478,48 @@ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
entry->ecx |= bit(X86_FEATURE_VMX);
}
+static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
+ struct x86_exception *fault)
+{
+ struct vmcs12 *vmcs12;
+ nested_vmx_vmexit(vcpu);
+ vmcs12 = get_vmcs12(vcpu);
+
+ if (fault->error_code & PFERR_RSVD_MASK)
+ vmcs12->vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
+ else
+ vmcs12->vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
+ vmcs12->exit_qualification = vcpu->arch.exit_qualification;
+ vmcs12->guest_physical_address = fault->address;
+}
+
+/* Callbacks for nested_ept_init_mmu_context: */
+
+static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
+{
+ /* return the page table to be shadowed - in our case, EPT12 */
+ return get_vmcs12(vcpu)->ept_pointer;
+}
+
+static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+{
+ int r = kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu,
+ nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT);
+
+ vcpu->arch.mmu.set_cr3 = vmx_set_cr3;
+ vcpu->arch.mmu.get_cr3 = nested_ept_get_cr3;
+ vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
+
+ vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu;
+
+ return r;
+}
+
+static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.walk_mmu = &vcpu->arch.mmu;
+}
+
/*
* prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
* L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
@@ -7388,7 +7582,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmcs12->guest_interruptibility_info);
vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_writel(GUEST_RFLAGS, vmcs12->guest_rflags);
+ vmx_set_rflags(vcpu, vmcs12->guest_rflags);
vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
vmcs12->guest_pending_dbg_exceptions);
vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
@@ -7508,15 +7702,24 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vcpu->arch.cr0_guest_owned_bits &= ~vmcs12->cr0_guest_host_mask;
vmcs_writel(CR0_GUEST_HOST_MASK, ~vcpu->arch.cr0_guest_owned_bits);
- /* Note: IA32_MODE, LOAD_IA32_EFER are modified by vmx_set_efer below */
- vmcs_write32(VM_EXIT_CONTROLS,
- vmcs12->vm_exit_controls | vmcs_config.vmexit_ctrl);
- vmcs_write32(VM_ENTRY_CONTROLS, vmcs12->vm_entry_controls |
+ /* L2->L1 exit controls are emulated - the hardware exit is to L0 so
+ * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
+ * bits are further modified by vmx_set_efer() below.
+ */
+ vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
+
+ /* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
+ * emulated by vmx_set_efer(), below.
+ */
+ vmcs_write32(VM_ENTRY_CONTROLS,
+ (vmcs12->vm_entry_controls & ~VM_ENTRY_LOAD_IA32_EFER &
+ ~VM_ENTRY_IA32E_MODE) |
(vmcs_config.vmentry_ctrl & ~VM_ENTRY_IA32E_MODE));
- if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT)
+ if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) {
vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
- else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
+ vcpu->arch.pat = vmcs12->guest_ia32_pat;
+ } else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
@@ -7538,6 +7741,11 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmx_flush_tlb(vcpu);
}
+ if (nested_cpu_has_ept(vmcs12)) {
+ kvm_mmu_unload(vcpu);
+ nested_ept_init_mmu_context(vcpu);
+ }
+
if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)
vcpu->arch.efer = vmcs12->guest_ia32_efer;
else if (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE)
@@ -7565,6 +7773,16 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
kvm_set_cr3(vcpu, vmcs12->guest_cr3);
kvm_mmu_reset_context(vcpu);
+ /*
+ * L1 may access the L2's PDPTR, so save them to construct vmcs12
+ */
+ if (enable_ept) {
+ vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+ vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+ vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+ vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+ }
+
kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
}
@@ -7887,6 +8105,22 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmcs12->guest_pending_dbg_exceptions =
vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
+ /*
+ * In some cases (usually, nested EPT), L2 is allowed to change its
+ * own CR3 without exiting. If it has changed it, we must keep it.
+ * Of course, if L0 is using shadow page tables, GUEST_CR3 was defined
+ * by L0, not L1 or L2, so we mustn't unconditionally copy it to vmcs12.
+ *
+ * Additionally, restore L2's PDPTR to vmcs12.
+ */
+ if (enable_ept) {
+ vmcs12->guest_cr3 = vmcs_read64(GUEST_CR3);
+ vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0);
+ vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1);
+ vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2);
+ vmcs12->guest_pdptr3 = vmcs_read64(GUEST_PDPTR3);
+ }
+
vmcs12->vm_entry_controls =
(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
(vmcs_read32(VM_ENTRY_CONTROLS) & VM_ENTRY_IA32E_MODE);
@@ -7948,6 +8182,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
+ struct kvm_segment seg;
+
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
vcpu->arch.efer = vmcs12->host_ia32_efer;
else if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
@@ -7982,7 +8218,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
kvm_set_cr4(vcpu, vmcs12->host_cr4);
- /* shadow page tables on either EPT or shadow page tables */
+ if (nested_cpu_has_ept(vmcs12))
+ nested_ept_uninit_mmu_context(vcpu);
+
kvm_set_cr3(vcpu, vmcs12->host_cr3);
kvm_mmu_reset_context(vcpu);
@@ -8001,23 +8239,61 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->host_ia32_sysenter_eip);
vmcs_writel(GUEST_IDTR_BASE, vmcs12->host_idtr_base);
vmcs_writel(GUEST_GDTR_BASE, vmcs12->host_gdtr_base);
- vmcs_writel(GUEST_TR_BASE, vmcs12->host_tr_base);
- vmcs_writel(GUEST_GS_BASE, vmcs12->host_gs_base);
- vmcs_writel(GUEST_FS_BASE, vmcs12->host_fs_base);
- vmcs_write16(GUEST_ES_SELECTOR, vmcs12->host_es_selector);
- vmcs_write16(GUEST_CS_SELECTOR, vmcs12->host_cs_selector);
- vmcs_write16(GUEST_SS_SELECTOR, vmcs12->host_ss_selector);
- vmcs_write16(GUEST_DS_SELECTOR, vmcs12->host_ds_selector);
- vmcs_write16(GUEST_FS_SELECTOR, vmcs12->host_fs_selector);
- vmcs_write16(GUEST_GS_SELECTOR, vmcs12->host_gs_selector);
- vmcs_write16(GUEST_TR_SELECTOR, vmcs12->host_tr_selector);
-
- if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT)
+
+ if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PAT) {
vmcs_write64(GUEST_IA32_PAT, vmcs12->host_ia32_pat);
+ vcpu->arch.pat = vmcs12->host_ia32_pat;
+ }
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
vmcs12->host_ia32_perf_global_ctrl);
+ /* Set L1 segment info according to Intel SDM
+ 27.5.2 Loading Host Segment and Descriptor-Table Registers */
+ seg = (struct kvm_segment) {
+ .base = 0,
+ .limit = 0xFFFFFFFF,
+ .selector = vmcs12->host_cs_selector,
+ .type = 11,
+ .present = 1,
+ .s = 1,
+ .g = 1
+ };
+ if (vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)
+ seg.l = 1;
+ else
+ seg.db = 1;
+ vmx_set_segment(vcpu, &seg, VCPU_SREG_CS);
+ seg = (struct kvm_segment) {
+ .base = 0,
+ .limit = 0xFFFFFFFF,
+ .type = 3,
+ .present = 1,
+ .s = 1,
+ .db = 1,
+ .g = 1
+ };
+ seg.selector = vmcs12->host_ds_selector;
+ vmx_set_segment(vcpu, &seg, VCPU_SREG_DS);
+ seg.selector = vmcs12->host_es_selector;
+ vmx_set_segment(vcpu, &seg, VCPU_SREG_ES);
+ seg.selector = vmcs12->host_ss_selector;
+ vmx_set_segment(vcpu, &seg, VCPU_SREG_SS);
+ seg.selector = vmcs12->host_fs_selector;
+ seg.base = vmcs12->host_fs_base;
+ vmx_set_segment(vcpu, &seg, VCPU_SREG_FS);
+ seg.selector = vmcs12->host_gs_selector;
+ seg.base = vmcs12->host_gs_base;
+ vmx_set_segment(vcpu, &seg, VCPU_SREG_GS);
+ seg = (struct kvm_segment) {
+ .base = vmcs12->host_tr_base,
+ .limit = 0x67,
+ .selector = vmcs12->host_tr_selector,
+ .type = 11,
+ .present = 1
+ };
+ vmx_set_segment(vcpu, &seg, VCPU_SREG_TR);
+
kvm_set_dr(vcpu, 7, 0x400);
vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d21bce50531..e5ca72a5cdb 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -682,17 +682,6 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
*/
}
- /*
- * Does the new cr3 value map to physical memory? (Note, we
- * catch an invalid cr3 even in real-mode, because it would
- * cause trouble later on when we turn on paging anyway.)
- *
- * A real CPU would silently accept an invalid cr3 and would
- * attempt to use it - with largely undefined (and often hard
- * to debug) behavior on the guest side.
- */
- if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
- return 1;
vcpu->arch.cr3 = cr3;
__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
vcpu->arch.mmu.new_cr3(vcpu);
@@ -850,7 +839,8 @@ static u32 msrs_to_save[] = {
#ifdef CONFIG_X86_64
MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
- MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
+ MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
+ MSR_IA32_FEATURE_CONTROL
};
static unsigned num_msrs_to_save;
@@ -1457,6 +1447,29 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm)
#endif
}
+static void kvm_gen_update_masterclock(struct kvm *kvm)
+{
+#ifdef CONFIG_X86_64
+ int i;
+ struct kvm_vcpu *vcpu;
+ struct kvm_arch *ka = &kvm->arch;
+
+ spin_lock(&ka->pvclock_gtod_sync_lock);
+ kvm_make_mclock_inprogress_request(kvm);
+ /* no guest entries from this point */
+ pvclock_update_vm_gtod_copy(kvm);
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+
+ /* guest entries allowed */
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
+
+ spin_unlock(&ka->pvclock_gtod_sync_lock);
+#endif
+}
+
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
unsigned long flags, this_tsc_khz;
@@ -3806,6 +3819,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
delta = user_ns.clock - now_ns;
local_irq_enable();
kvm->arch.kvmclock_offset = delta;
+ kvm_gen_update_masterclock(kvm);
break;
}
case KVM_GET_CLOCK: {
@@ -4955,6 +4969,97 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
static int complete_emulated_pio(struct kvm_vcpu *vcpu);
+static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
+ unsigned long *db)
+{
+ u32 dr6 = 0;
+ int i;
+ u32 enable, rwlen;
+
+ enable = dr7;
+ rwlen = dr7 >> 16;
+ for (i = 0; i < 4; i++, enable >>= 2, rwlen >>= 4)
+ if ((enable & 3) && (rwlen & 15) == type && db[i] == addr)
+ dr6 |= (1 << i);
+ return dr6;
+}
+
+static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r)
+{
+ struct kvm_run *kvm_run = vcpu->run;
+
+ /*
+ * Use the "raw" value to see if TF was passed to the processor.
+ * Note that the new value of the flags has not been saved yet.
+ *
+ * This is correct even for TF set by the guest, because "the
+ * processor will not generate this exception after the instruction
+ * that sets the TF flag".
+ */
+ unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
+
+ if (unlikely(rflags & X86_EFLAGS_TF)) {
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+ kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1;
+ kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
+ kvm_run->debug.arch.exception = DB_VECTOR;
+ kvm_run->exit_reason = KVM_EXIT_DEBUG;
+ *r = EMULATE_USER_EXIT;
+ } else {
+ vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
+ /*
+ * "Certain debug exceptions may clear bit 0-3. The
+ * remaining contents of the DR6 register are never
+ * cleared by the processor".
+ */
+ vcpu->arch.dr6 &= ~15;
+ vcpu->arch.dr6 |= DR6_BS;
+ kvm_queue_exception(vcpu, DB_VECTOR);
+ }
+ }
+}
+
+static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
+{
+ struct kvm_run *kvm_run = vcpu->run;
+ unsigned long eip = vcpu->arch.emulate_ctxt.eip;
+ u32 dr6 = 0;
+
+ if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) &&
+ (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) {
+ dr6 = kvm_vcpu_check_hw_bp(eip, 0,
+ vcpu->arch.guest_debug_dr7,
+ vcpu->arch.eff_db);
+
+ if (dr6 != 0) {
+ kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
+ kvm_run->debug.arch.pc = kvm_rip_read(vcpu) +
+ get_segment_base(vcpu, VCPU_SREG_CS);
+
+ kvm_run->debug.arch.exception = DB_VECTOR;
+ kvm_run->exit_reason = KVM_EXIT_DEBUG;
+ *r = EMULATE_USER_EXIT;
+ return true;
+ }
+ }
+
+ if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK)) {
+ dr6 = kvm_vcpu_check_hw_bp(eip, 0,
+ vcpu->arch.dr7,
+ vcpu->arch.db);
+
+ if (dr6 != 0) {
+ vcpu->arch.dr6 &= ~15;
+ vcpu->arch.dr6 |= dr6;
+ kvm_queue_exception(vcpu, DB_VECTOR);
+ *r = EMULATE_DONE;
+ return true;
+ }
+ }
+
+ return false;
+}
+
int x86_emulate_instruction(struct kvm_vcpu *vcpu,
unsigned long cr2,
int emulation_type,
@@ -4975,6 +5080,16 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
if (!(emulation_type & EMULTYPE_NO_DECODE)) {
init_emulate_ctxt(vcpu);
+
+ /*
+ * We will reenter on the same instruction since
+ * we do not set complete_userspace_io. This does not
+ * handle watchpoints yet, those would be handled in
+ * the emulate_ops.
+ */
+ if (kvm_vcpu_check_breakpoint(vcpu, &r))
+ return r;
+
ctxt->interruptibility = 0;
ctxt->have_exception = false;
ctxt->perm_ok = false;
@@ -5031,17 +5146,18 @@ restart:
inject_emulated_exception(vcpu);
r = EMULATE_DONE;
} else if (vcpu->arch.pio.count) {
- if (!vcpu->arch.pio.in)
+ if (!vcpu->arch.pio.in) {
+ /* FIXME: return into emulator if single-stepping. */
vcpu->arch.pio.count = 0;
- else {
+ } else {
writeback = false;
vcpu->arch.complete_userspace_io = complete_emulated_pio;
}
- r = EMULATE_DO_MMIO;
+ r = EMULATE_USER_EXIT;
} else if (vcpu->mmio_needed) {
if (!vcpu->mmio_is_write)
writeback = false;
- r = EMULATE_DO_MMIO;
+ r = EMULATE_USER_EXIT;
vcpu->arch.complete_userspace_io = complete_emulated_mmio;
} else if (r == EMULATION_RESTART)
goto restart;
@@ -5050,10 +5166,12 @@ restart:
if (writeback) {
toggle_interruptibility(vcpu, ctxt->interruptibility);
- kvm_set_rflags(vcpu, ctxt->eflags);
kvm_make_request(KVM_REQ_EVENT, vcpu);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
kvm_rip_write(vcpu, ctxt->eip);
+ if (r == EMULATE_DONE)
+ kvm_vcpu_check_singlestep(vcpu, &r);
+ kvm_set_rflags(vcpu, ctxt->eflags);
} else
vcpu->arch.emulate_regs_need_sync_to_vcpu = true;
@@ -5347,7 +5465,7 @@ static struct notifier_block pvclock_gtod_notifier = {
int kvm_arch_init(void *opaque)
{
int r;
- struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque;
+ struct kvm_x86_ops *ops = opaque;
if (kvm_x86_ops) {
printk(KERN_ERR "kvm: already loaded the other module\n");
@@ -5495,6 +5613,23 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
return 1;
}
+/*
+ * kvm_pv_kick_cpu_op: Kick a vcpu.
+ *
+ * @apicid - apicid of vcpu to be kicked.
+ */
+static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid)
+{
+ struct kvm_lapic_irq lapic_irq;
+
+ lapic_irq.shorthand = 0;
+ lapic_irq.dest_mode = 0;
+ lapic_irq.dest_id = apicid;
+
+ lapic_irq.delivery_mode = APIC_DM_REMRD;
+ kvm_irq_delivery_to_apic(kvm, 0, &lapic_irq, NULL);
+}
+
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
{
unsigned long nr, a0, a1, a2, a3, ret;
@@ -5528,6 +5663,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
case KVM_HC_VAPIC_POLL_IRQ:
ret = 0;
break;
+ case KVM_HC_KICK_CPU:
+ kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
+ ret = 0;
+ break;
default:
ret = -KVM_ENOSYS;
break;
@@ -5689,29 +5828,6 @@ static void process_nmi(struct kvm_vcpu *vcpu)
kvm_make_request(KVM_REQ_EVENT, vcpu);
}
-static void kvm_gen_update_masterclock(struct kvm *kvm)
-{
-#ifdef CONFIG_X86_64
- int i;
- struct kvm_vcpu *vcpu;
- struct kvm_arch *ka = &kvm->arch;
-
- spin_lock(&ka->pvclock_gtod_sync_lock);
- kvm_make_mclock_inprogress_request(kvm);
- /* no guest entries from this point */
- pvclock_update_vm_gtod_copy(kvm);
-
- kvm_for_each_vcpu(i, vcpu, kvm)
- set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
-
- /* guest entries allowed */
- kvm_for_each_vcpu(i, vcpu, kvm)
- clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
-
- spin_unlock(&ka->pvclock_gtod_sync_lock);
-#endif
-}
-
static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
{
u64 eoi_exit_bitmap[4];
@@ -5950,6 +6066,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
kvm_apic_accept_events(vcpu);
switch(vcpu->arch.mp_state) {
case KVM_MP_STATE_HALTED:
+ vcpu->arch.pv.pv_unhalted = false;
vcpu->arch.mp_state =
KVM_MP_STATE_RUNNABLE;
case KVM_MP_STATE_RUNNABLE:
@@ -6061,6 +6178,8 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
vcpu->mmio_needed = 0;
+
+ /* FIXME: return into emulator if single-stepping. */
if (vcpu->mmio_is_write)
return 1;
vcpu->mmio_read_completed = 1;
@@ -6249,7 +6368,12 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
kvm_apic_accept_events(vcpu);
- mp_state->mp_state = vcpu->arch.mp_state;
+ if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED &&
+ vcpu->arch.pv.pv_unhalted)
+ mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
+ else
+ mp_state->mp_state = vcpu->arch.mp_state;
+
return 0;
}
@@ -6770,6 +6894,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
BUG_ON(vcpu->kvm == NULL);
kvm = vcpu->kvm;
+ vcpu->arch.pv.pv_unhalted = false;
vcpu->arch.emulate_ctxt.ops = &emulate_ops;
if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
@@ -7019,6 +7144,15 @@ out_free:
return -ENOMEM;
}
+void kvm_arch_memslots_updated(struct kvm *kvm)
+{
+ /*
+ * memslots->generation has been incremented.
+ * mmio generation may have reached its maximum value.
+ */
+ kvm_mmu_invalidate_mmio_sptes(kvm);
+}
+
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_userspace_memory_region *mem,
@@ -7079,11 +7213,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
*/
if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES))
kvm_mmu_slot_remove_write_access(kvm, mem->slot);
- /*
- * If memory slot is created, or moved, we need to clear all
- * mmio sptes.
- */
- kvm_mmu_invalidate_mmio_sptes(kvm);
}
void kvm_arch_flush_shadow_all(struct kvm *kvm)
@@ -7103,6 +7232,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
!vcpu->arch.apf.halted)
|| !list_empty_careful(&vcpu->async_pf.done)
|| kvm_apic_has_events(vcpu)
+ || vcpu->arch.pv.pv_unhalted
|| atomic_read(&vcpu->arch.nmi_queued) ||
(kvm_arch_interrupt_allowed(vcpu) &&
kvm_cpu_has_interrupt(vcpu));
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 6a22c19da66..bdf8532494f 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -7,8 +7,7 @@
* kernel and insert a module (lg.ko) which allows us to run other Linux
* kernels the same way we'd run processes. We call the first kernel the Host,
* and the others the Guests. The program which sets up and configures Guests
- * (such as the example in Documentation/virtual/lguest/lguest.c) is called the
- * Launcher.
+ * (such as the example in tools/lguest/lguest.c) is called the Launcher.
*
* Secondly, we only run specially modified Guests, not normal kernels: setting
* CONFIG_LGUEST_GUEST to "y" compiles this file into the kernel so it knows
@@ -1057,6 +1056,12 @@ static void lguest_load_sp0(struct tss_struct *tss,
}
/* Let's just say, I wouldn't do debugging under a Guest. */
+static unsigned long lguest_get_debugreg(int regno)
+{
+ /* FIXME: Implement */
+ return 0;
+}
+
static void lguest_set_debugreg(int regno, unsigned long value)
{
/* FIXME: Implement */
@@ -1304,6 +1309,7 @@ __init void lguest_init(void)
pv_cpu_ops.load_tr_desc = lguest_load_tr_desc;
pv_cpu_ops.set_ldt = lguest_set_ldt;
pv_cpu_ops.load_tls = lguest_load_tls;
+ pv_cpu_ops.get_debugreg = lguest_get_debugreg;
pv_cpu_ops.set_debugreg = lguest_set_debugreg;
pv_cpu_ops.clts = lguest_clts;
pv_cpu_ops.read_cr0 = lguest_read_cr0;
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 96b2c6697c9..992d63bb154 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -16,7 +16,7 @@ clean-files := inat-tables.c
obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
-lib-y := delay.o
+lib-y := delay.o misc.o
lib-y += thunk_$(BITS).o
lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
lib-y += memcpy_$(BITS).o
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 25b7ae8d058..7609e0e421e 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -6,6 +6,7 @@
*/
#include <asm/checksum.h>
#include <linux/module.h>
+#include <asm/smap.h>
/**
* csum_partial_copy_from_user - Copy and checksum from user space.
@@ -52,8 +53,10 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
len -= 2;
}
}
+ stac();
isum = csum_partial_copy_generic((__force const void *)src,
dst, len, isum, errp, NULL);
+ clac();
if (unlikely(*errp))
goto out_err;
@@ -82,6 +85,8 @@ __wsum
csum_partial_copy_to_user(const void *src, void __user *dst,
int len, __wsum isum, int *errp)
{
+ __wsum ret;
+
might_sleep();
if (unlikely(!access_ok(VERIFY_WRITE, dst, len))) {
@@ -105,8 +110,11 @@ csum_partial_copy_to_user(const void *src, void __user *dst,
}
*errp = 0;
- return csum_partial_copy_generic(src, (void __force *)dst,
- len, isum, NULL, errp);
+ stac();
+ ret = csum_partial_copy_generic(src, (void __force *)dst,
+ len, isum, NULL, errp);
+ clac();
+ return ret;
}
EXPORT_SYMBOL(csum_partial_copy_to_user);
diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c
new file mode 100644
index 00000000000..76b373af03f
--- /dev/null
+++ b/arch/x86/lib/misc.c
@@ -0,0 +1,21 @@
+/*
+ * Count the digits of @val including a possible sign.
+ *
+ * (Typed on and submitted from hpa's mobile phone.)
+ */
+int num_digits(int val)
+{
+ int m = 10;
+ int d = 1;
+
+ if (val < 0) {
+ d++;
+ val = -val;
+ }
+
+ while (val >= m) {
+ m *= 10;
+ d++;
+ }
+ return d;
+}
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 4f74d94c8d9..ddf9ecb53cc 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -11,39 +11,26 @@
#include <linux/sched.h>
/*
- * best effort, GUP based copy_from_user() that is NMI-safe
+ * We rely on the nested NMI work to allow atomic faults from the NMI path; the
+ * nested NMI paths are careful to preserve CR2.
*/
unsigned long
copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
{
- unsigned long offset, addr = (unsigned long)from;
- unsigned long size, len = 0;
- struct page *page;
- void *map;
- int ret;
+ unsigned long ret;
if (__range_not_ok(from, n, TASK_SIZE))
- return len;
-
- do {
- ret = __get_user_pages_fast(addr, 1, 0, &page);
- if (!ret)
- break;
-
- offset = addr & (PAGE_SIZE - 1);
- size = min(PAGE_SIZE - offset, n - len);
-
- map = kmap_atomic(page);
- memcpy(to, map+offset, size);
- kunmap_atomic(map);
- put_page(page);
-
- len += size;
- to += size;
- addr += size;
-
- } while (len < n);
-
- return len;
+ return 0;
+
+ /*
+ * Even though this function is typically called from NMI/IRQ context
+ * disable pagefaults so that its behaviour is consistent even when
+ * called form other contexts.
+ */
+ pagefault_disable();
+ ret = __copy_from_user_inatomic(to, from, n);
+ pagefault_enable();
+
+ return ret;
}
EXPORT_SYMBOL_GPL(copy_from_user_nmi);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 3eb18acd0e4..e2f5e21c03b 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -654,14 +654,13 @@ EXPORT_SYMBOL(__copy_from_user_ll_nocache_nozero);
* Returns number of bytes that could not be copied.
* On success, this will be zero.
*/
-unsigned long
-copy_to_user(void __user *to, const void *from, unsigned long n)
+unsigned long _copy_to_user(void __user *to, const void *from, unsigned n)
{
if (access_ok(VERIFY_WRITE, to, n))
n = __copy_to_user(to, from, n);
return n;
}
-EXPORT_SYMBOL(copy_to_user);
+EXPORT_SYMBOL(_copy_to_user);
/**
* copy_from_user: - Copy a block of data from user space.
@@ -679,8 +678,7 @@ EXPORT_SYMBOL(copy_to_user);
* If some data could not be copied, this function will pad the copied
* data to the requested size using zero bytes.
*/
-unsigned long
-_copy_from_user(void *to, const void __user *from, unsigned long n)
+unsigned long _copy_from_user(void *to, const void __user *from, unsigned n)
{
if (access_ok(VERIFY_READ, from, n))
n = __copy_from_user(to, from, n);
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index 906fea31579..c905e89e19f 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -68,7 +68,7 @@ EXPORT_SYMBOL(copy_in_user);
* Since protection fault in copy_from/to_user is not a normal situation,
* it is not necessary to optimize tail handling.
*/
-unsigned long
+__visible unsigned long
copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest)
{
char c;
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index 5d7e51f3fd2..533a85e3a07 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -1,10 +1,8 @@
# x86 Opcode Maps
#
# This is (mostly) based on following documentations.
-# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2
-# (#325383-040US, October 2011)
-# - Intel(R) Advanced Vector Extensions Programming Reference
-# (#319433-011,JUNE 2011).
+# - Intel(R) 64 and IA-32 Architectures Software Developer's Manual Vol.2C
+# (#326018-047US, June 2013)
#
#<Opcode maps>
# Table: table-name
@@ -29,6 +27,7 @@
# - (F3): the last prefix is 0xF3
# - (F2): the last prefix is 0xF2
# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
+# - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
Table: one byte opcode
Referrer:
@@ -246,8 +245,8 @@ c2: RETN Iw (f64)
c3: RETN
c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
-c6: Grp11 Eb,Ib (1A)
-c7: Grp11 Ev,Iz (1A)
+c6: Grp11A Eb,Ib (1A)
+c7: Grp11B Ev,Iz (1A)
c8: ENTER Iw,Ib
c9: LEAVE (d64)
ca: RETF Iw
@@ -293,8 +292,8 @@ ef: OUT DX,eAX
# 0xf0 - 0xff
f0: LOCK (Prefix)
f1:
-f2: REPNE (Prefix)
-f3: REP/REPE (Prefix)
+f2: REPNE (Prefix) | XACQUIRE (Prefix)
+f3: REP/REPE (Prefix) | XRELEASE (Prefix)
f4: HLT
f5: CMC
f6: Grp3_1 Eb (1A)
@@ -326,7 +325,8 @@ AVXcode: 1
0a:
0b: UD2 (1B)
0c:
-0d: NOP Ev | GrpP
+# AMD's prefetch group. Intel supports prefetchw(/1) only.
+0d: GrpP
0e: FEMMS
# 3DNow! uses the last imm byte as opcode extension.
0f: 3DNow! Pq,Qq,Ib
@@ -729,12 +729,12 @@ dc: VAESENC Vdq,Hdq,Wdq (66),(v1)
dd: VAESENCLAST Vdq,Hdq,Wdq (66),(v1)
de: VAESDEC Vdq,Hdq,Wdq (66),(v1)
df: VAESDECLAST Vdq,Hdq,Wdq (66),(v1)
-f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2)
-f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2)
+f0: MOVBE Gy,My | MOVBE Gw,Mw (66) | CRC32 Gd,Eb (F2) | CRC32 Gd,Eb (66&F2)
+f1: MOVBE My,Gy | MOVBE Mw,Gw (66) | CRC32 Gd,Ey (F2) | CRC32 Gd,Ew (66&F2)
f2: ANDN Gy,By,Ey (v)
f3: Grp17 (1A)
f5: BZHI Gy,Ey,By (v) | PEXT Gy,By,Ey (F3),(v) | PDEP Gy,By,Ey (F2),(v)
-f6: MULX By,Gy,rDX,Ey (F2),(v)
+f6: ADCX Gy,Ey (66) | ADOX Gy,Ey (F3) | MULX By,Gy,rDX,Ey (F2),(v)
f7: BEXTR Gy,Ey,By (v) | SHLX Gy,Ey,By (66),(v) | SARX Gy,Ey,By (F3),(v) | SHRX Gy,Ey,By (F2),(v)
EndTable
@@ -861,8 +861,8 @@ EndTable
GrpTable: Grp7
0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B)
-1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001)
-2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B)
+1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B)
+2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B)
3: LIDT Ms
4: SMSW Mw/Rv
5:
@@ -880,15 +880,21 @@ EndTable
GrpTable: Grp9
1: CMPXCHG8B/16B Mq/Mdq
6: VMPTRLD Mq | VMCLEAR Mq (66) | VMXON Mq (F3) | RDRAND Rv (11B)
-7: VMPTRST Mq | VMPTRST Mq (F3)
+7: VMPTRST Mq | VMPTRST Mq (F3) | RDSEED Rv (11B)
EndTable
GrpTable: Grp10
EndTable
-GrpTable: Grp11
-# Note: the operands are given by group opcode
-0: MOV
+# Grp11A and Grp11B are expressed as Grp11 in Intel SDM
+GrpTable: Grp11A
+0: MOV Eb,Ib
+7: XABORT Ib (000),(11B)
+EndTable
+
+GrpTable: Grp11B
+0: MOV Eb,Iz
+7: XBEGIN Jz (000),(11B)
EndTable
GrpTable: Grp12
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 654be4ae304..7a517bb4106 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -51,7 +51,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr)
return 0;
}
-static inline int __kprobes notify_page_fault(struct pt_regs *regs)
+static inline int __kprobes kprobes_fault(struct pt_regs *regs)
{
int ret = 0;
@@ -842,23 +842,15 @@ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
force_sig_info_fault(SIGBUS, code, address, tsk, fault);
}
-static noinline int
+static noinline void
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
unsigned long address, unsigned int fault)
{
- /*
- * Pagefault was interrupted by SIGKILL. We have no reason to
- * continue pagefault.
- */
- if (fatal_signal_pending(current)) {
- if (!(fault & VM_FAULT_RETRY))
- up_read(&current->mm->mmap_sem);
- if (!(error_code & PF_USER))
- no_context(regs, error_code, address, 0, 0);
- return 1;
+ if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
+ up_read(&current->mm->mmap_sem);
+ no_context(regs, error_code, address, 0, 0);
+ return;
}
- if (!(fault & VM_FAULT_ERROR))
- return 0;
if (fault & VM_FAULT_OOM) {
/* Kernel mode? Handle exceptions or die: */
@@ -866,7 +858,7 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
up_read(&current->mm->mmap_sem);
no_context(regs, error_code, address,
SIGSEGV, SEGV_MAPERR);
- return 1;
+ return;
}
up_read(&current->mm->mmap_sem);
@@ -884,7 +876,6 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
else
BUG();
}
- return 1;
}
static int spurious_fault_check(unsigned long error_code, pte_t *pte)
@@ -1011,9 +1002,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
unsigned long address;
struct mm_struct *mm;
int fault;
- int write = error_code & PF_WRITE;
- unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE |
- (write ? FAULT_FLAG_WRITE : 0);
+ unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
mm = tsk->mm;
@@ -1059,7 +1048,7 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
return;
/* kprobes don't want to hook the spurious faults: */
- if (notify_page_fault(regs))
+ if (kprobes_fault(regs))
return;
/*
* Don't take the mm semaphore here. If we fixup a prefetch
@@ -1071,22 +1060,8 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
}
/* kprobes don't want to hook the spurious faults: */
- if (unlikely(notify_page_fault(regs)))
+ if (unlikely(kprobes_fault(regs)))
return;
- /*
- * It's safe to allow irq's after cr2 has been saved and the
- * vmalloc fault has been handled.
- *
- * User-mode registers count as a user access even for any
- * potential system fault or CPU buglet:
- */
- if (user_mode_vm(regs)) {
- local_irq_enable();
- error_code |= PF_USER;
- } else {
- if (regs->flags & X86_EFLAGS_IF)
- local_irq_enable();
- }
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
@@ -1098,8 +1073,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
}
}
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
-
/*
* If we're in an interrupt, have no user context or are running
* in an atomic region then we must not take the fault:
@@ -1110,6 +1083,27 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
}
/*
+ * It's safe to allow irq's after cr2 has been saved and the
+ * vmalloc fault has been handled.
+ *
+ * User-mode registers count as a user access even for any
+ * potential system fault or CPU buglet:
+ */
+ if (user_mode_vm(regs)) {
+ local_irq_enable();
+ error_code |= PF_USER;
+ flags |= FAULT_FLAG_USER;
+ } else {
+ if (regs->flags & X86_EFLAGS_IF)
+ local_irq_enable();
+ }
+
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
+
+ if (error_code & PF_WRITE)
+ flags |= FAULT_FLAG_WRITE;
+
+ /*
* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in
* the kernel and should generate an OOPS. Unfortunately, in the
@@ -1187,9 +1181,17 @@ good_area:
*/
fault = handle_mm_fault(mm, vma, address, flags);
- if (unlikely(fault & (VM_FAULT_RETRY|VM_FAULT_ERROR))) {
- if (mm_fault_error(regs, error_code, address, fault))
- return;
+ /*
+ * If we need to retry but a fatal signal is pending, handle the
+ * signal first. We do not need to release the mmap_sem because it
+ * would already be released in __lock_page_or_retry in mm/filemap.c.
+ */
+ if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
+ return;
+
+ if (unlikely(fault & VM_FAULT_ERROR)) {
+ mm_fault_error(regs, error_code, address, fault);
+ return;
}
/*
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 7e73e8c6909..9d980d88b74 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -59,6 +59,10 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
return NULL;
}
+int pmd_huge_support(void)
+{
+ return 0;
+}
#else
struct page *
@@ -77,6 +81,10 @@ int pud_huge(pud_t pud)
return !!(pud_val(pud) & _PAGE_PSE);
}
+int pmd_huge_support(void)
+{
+ return 1;
+}
#endif
/* x86_64 also uses this file */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 04664cdb7fd..ce32017c5e3 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -399,8 +399,25 @@ static unsigned long __init init_range_memory_mapping(
return mapped_ram_size;
}
-/* (PUD_SHIFT-PMD_SHIFT)/2 */
-#define STEP_SIZE_SHIFT 5
+static unsigned long __init get_new_step_size(unsigned long step_size)
+{
+ /*
+ * Explain why we shift by 5 and why we don't have to worry about
+ * 'step_size << 5' overflowing:
+ *
+ * initial mapped size is PMD_SIZE (2M).
+ * We can not set step_size to be PUD_SIZE (1G) yet.
+ * In worse case, when we cross the 1G boundary, and
+ * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k)
+ * to map 1G range with PTE. Use 5 as shift for now.
+ *
+ * Don't need to worry about overflow, on 32bit, when step_size
+ * is 0, round_down() returns 0 for start, and that turns it
+ * into 0x100000000ULL.
+ */
+ return step_size << 5;
+}
+
void __init init_mem_mapping(void)
{
unsigned long end, real_end, start, last_start;
@@ -449,7 +466,7 @@ void __init init_mem_mapping(void)
min_pfn_mapped = last_start >> PAGE_SHIFT;
/* only increase step_size after big range get mapped */
if (new_mapped_ram_size > mapped_ram_size)
- step_size <<= STEP_SIZE_SHIFT;
+ step_size = get_new_step_size(step_size);
mapped_ram_size += new_mapped_ram_size;
}
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0215e2c563e..799580cabc7 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -487,7 +487,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
unsigned long offset;
resource_size_t last_addr;
unsigned int nrpages;
- enum fixed_addresses idx0, idx;
+ enum fixed_addresses idx;
int i, slot;
WARN_ON(system_state != SYSTEM_BOOTING);
@@ -540,8 +540,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
/*
* Ok, go for it..
*/
- idx0 = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
- idx = idx0;
+ idx = FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*slot;
while (nrpages > 0) {
early_set_fixmap(idx, phys_addr, prot);
phys_addr += PAGE_SIZE;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index cdd0da9dd53..266ca912f62 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -146,6 +146,7 @@ int __init
acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
{
u64 start, end;
+ u32 hotpluggable;
int node, pxm;
if (srat_disabled())
@@ -154,7 +155,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
goto out_err_bad_srat;
if ((ma->flags & ACPI_SRAT_MEM_ENABLED) == 0)
goto out_err;
- if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && !save_add_info())
+ hotpluggable = ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE;
+ if (hotpluggable && !save_add_info())
goto out_err;
start = ma->base_address;
@@ -174,9 +176,10 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
node_set(node, numa_nodes_parsed);
- printk(KERN_INFO "SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]\n",
- node, pxm,
- (unsigned long long) start, (unsigned long long) end - 1);
+ pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n",
+ node, pxm,
+ (unsigned long long) start, (unsigned long long) end - 1,
+ hotpluggable ? " hotplug" : "");
return 0;
out_err_bad_srat:
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 282375f13c7..ae699b3bbac 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -103,6 +103,7 @@ static void flush_tlb_func(void *info)
if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
return;
+ count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
if (f->flush_end == TLB_FLUSH_ALL)
local_flush_tlb();
@@ -130,6 +131,7 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
info.flush_start = start;
info.flush_end = end;
+ count_vm_event(NR_TLB_REMOTE_FLUSH);
if (is_uv_system()) {
unsigned int cpu;
@@ -149,6 +151,7 @@ void flush_tlb_current_task(void)
preempt_disable();
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
local_flush_tlb();
if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
@@ -211,16 +214,19 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
/* tlb_flushall_shift is on balance point, details in commit log */
- if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+ if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift) {
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ALL);
local_flush_tlb();
- else {
+ } else {
if (has_large_page(mm, start, end)) {
local_flush_tlb();
goto flush_all;
}
/* flush range by one by one 'invlpg' */
- for (addr = start; addr < end; addr += PAGE_SIZE)
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
+ count_vm_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
+ }
if (cpumask_any_but(mm_cpumask(mm),
smp_processor_id()) < nr_cpu_ids)
@@ -256,6 +262,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
static void do_flush_tlb_all(void *info)
{
+ count_vm_event(NR_TLB_REMOTE_FLUSH_RECEIVED);
__flush_tlb_all();
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
leave_mm(smp_processor_id());
@@ -263,6 +270,7 @@ static void do_flush_tlb_all(void *info)
void flush_tlb_all(void)
{
+ count_vm_event(NR_TLB_REMOTE_FLUSH);
on_each_cpu(do_flush_tlb_all, NULL, 1);
}
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 79c216aa0e2..516593e1ce3 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -772,13 +772,21 @@ out:
return;
}
+static void bpf_jit_free_deferred(struct work_struct *work)
+{
+ struct sk_filter *fp = container_of(work, struct sk_filter, work);
+ unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
+ struct bpf_binary_header *header = (void *)addr;
+
+ set_memory_rw(addr, header->pages);
+ module_free(NULL, header);
+ kfree(fp);
+}
+
void bpf_jit_free(struct sk_filter *fp)
{
if (fp->bpf_func != sk_run_filter) {
- unsigned long addr = (unsigned long)fp->bpf_func & PAGE_MASK;
- struct bpf_binary_header *header = (void *)addr;
-
- set_memory_rw(addr, header->pages);
- module_free(NULL, header);
+ INIT_WORK(&fp->work, bpf_jit_free_deferred);
+ schedule_work(&fp->work);
}
}
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index d6aa6e8315d..5d04be5efb6 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -47,7 +47,7 @@ dump_user_backtrace_32(struct stack_frame_ia32 *head)
unsigned long bytes;
bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
- if (bytes != sizeof(bufhead))
+ if (bytes != 0)
return NULL;
fp = (struct stack_frame_ia32 *) compat_ptr(bufhead[0].next_frame);
@@ -93,7 +93,7 @@ static struct stack_frame *dump_user_backtrace(struct stack_frame *head)
unsigned long bytes;
bytes = copy_from_user_nmi(bufhead, head, sizeof(bufhead));
- if (bytes != sizeof(bufhead))
+ if (bytes != 0)
return NULL;
oprofile_add_trace(bufhead[0].return_address);
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 48768df2471..6890d8498e0 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -403,7 +403,7 @@ static void nmi_cpu_down(void *dummy)
nmi_cpu_shutdown(dummy);
}
-static int nmi_create_files(struct super_block *sb, struct dentry *root)
+static int nmi_create_files(struct dentry *root)
{
unsigned int i;
@@ -420,14 +420,14 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root)
continue;
snprintf(buf, sizeof(buf), "%d", i);
- dir = oprofilefs_mkdir(sb, root, buf);
- oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
- oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
- oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
- oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
- oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
- oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
- oprofilefs_create_ulong(sb, dir, "extra", &counter_config[i].extra);
+ dir = oprofilefs_mkdir(root, buf);
+ oprofilefs_create_ulong(dir, "enabled", &counter_config[i].enabled);
+ oprofilefs_create_ulong(dir, "event", &counter_config[i].event);
+ oprofilefs_create_ulong(dir, "count", &counter_config[i].count);
+ oprofilefs_create_ulong(dir, "unit_mask", &counter_config[i].unit_mask);
+ oprofilefs_create_ulong(dir, "kernel", &counter_config[i].kernel);
+ oprofilefs_create_ulong(dir, "user", &counter_config[i].user);
+ oprofilefs_create_ulong(dir, "extra", &counter_config[i].extra);
}
return 0;
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index b2b94438ff0..50d86c0e9ba 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -454,16 +454,16 @@ static void init_ibs(void)
printk(KERN_INFO "oprofile: AMD IBS detected (0x%08x)\n", ibs_caps);
}
-static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
+static int (*create_arch_files)(struct dentry *root);
-static int setup_ibs_files(struct super_block *sb, struct dentry *root)
+static int setup_ibs_files(struct dentry *root)
{
struct dentry *dir;
int ret = 0;
/* architecture specific files */
if (create_arch_files)
- ret = create_arch_files(sb, root);
+ ret = create_arch_files(root);
if (ret)
return ret;
@@ -479,26 +479,26 @@ static int setup_ibs_files(struct super_block *sb, struct dentry *root)
ibs_config.max_cnt_op = 250000;
if (ibs_caps & IBS_CAPS_FETCHSAM) {
- dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
- oprofilefs_create_ulong(sb, dir, "enable",
+ dir = oprofilefs_mkdir(root, "ibs_fetch");
+ oprofilefs_create_ulong(dir, "enable",
&ibs_config.fetch_enabled);
- oprofilefs_create_ulong(sb, dir, "max_count",
+ oprofilefs_create_ulong(dir, "max_count",
&ibs_config.max_cnt_fetch);
- oprofilefs_create_ulong(sb, dir, "rand_enable",
+ oprofilefs_create_ulong(dir, "rand_enable",
&ibs_config.rand_en);
}
if (ibs_caps & IBS_CAPS_OPSAM) {
- dir = oprofilefs_mkdir(sb, root, "ibs_op");
- oprofilefs_create_ulong(sb, dir, "enable",
+ dir = oprofilefs_mkdir(root, "ibs_op");
+ oprofilefs_create_ulong(dir, "enable",
&ibs_config.op_enabled);
- oprofilefs_create_ulong(sb, dir, "max_count",
+ oprofilefs_create_ulong(dir, "max_count",
&ibs_config.max_cnt_op);
if (ibs_caps & IBS_CAPS_OPCNT)
- oprofilefs_create_ulong(sb, dir, "dispatched_ops",
+ oprofilefs_create_ulong(dir, "dispatched_ops",
&ibs_config.dispatched_ops);
if (ibs_caps & IBS_CAPS_BRNTRGT)
- oprofilefs_create_ulong(sb, dir, "branch_target",
+ oprofilefs_create_ulong(dir, "branch_target",
&ibs_config.branch_target);
}
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index ee0af58ca5b..e063eed0f91 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -18,7 +18,7 @@ obj-$(CONFIG_X86_VISWS) += visws.o
obj-$(CONFIG_X86_NUMAQ) += numaq_32.o
obj-$(CONFIG_X86_NUMACHIP) += numachip.o
-obj-$(CONFIG_X86_INTEL_MID) += mrst.o
+obj-$(CONFIG_X86_INTEL_MID) += intel_mid_pci.o
obj-y += common.o early.o
obj-y += bus_numa.o
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index d641897a1f4..b30e937689d 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -568,13 +568,8 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
*/
if (bus) {
struct pci_bus *child;
- list_for_each_entry(child, &bus->children, node) {
- struct pci_dev *self = child->self;
- if (!self)
- continue;
-
- pcie_bus_configure_settings(child, self->pcie_mpss);
- }
+ list_for_each_entry(child, &bus->children, node)
+ pcie_bus_configure_settings(child);
}
if (bus && node != -1) {
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index 94919e307f8..db6b1ab4325 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -210,6 +210,8 @@ static void pcibios_allocate_bridge_resources(struct pci_dev *dev)
r = &dev->resource[idx];
if (!r->flags)
continue;
+ if (r->parent) /* Already allocated */
+ continue;
if (!r->start || pci_claim_resource(dev, idx) < 0) {
/*
* Something is wrong with the region.
@@ -318,6 +320,8 @@ static void pcibios_allocate_dev_rom_resource(struct pci_dev *dev)
r = &dev->resource[PCI_ROM_RESOURCE];
if (!r->flags || !r->start)
return;
+ if (r->parent) /* Already allocated */
+ return;
if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) {
r->end -= r->start;
diff --git a/arch/x86/pci/mrst.c b/arch/x86/pci/intel_mid_pci.c
index 6eb18c42a28..51384ca727a 100644
--- a/arch/x86/pci/mrst.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -1,5 +1,5 @@
/*
- * Moorestown PCI support
+ * Intel MID PCI support
* Copyright (c) 2008 Intel Corporation
* Jesse Barnes <jesse.barnes@intel.com>
*
@@ -23,11 +23,11 @@
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/dmi.h>
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/smp.h>
-#include <asm/acpi.h>
#include <asm/segment.h>
-#include <asm/io.h>
-#include <asm/smp.h>
#include <asm/pci_x86.h>
#include <asm/hw_irq.h>
#include <asm/io_apic.h>
@@ -43,7 +43,7 @@
#define PCI_FIXED_BAR_4_SIZE 0x14
#define PCI_FIXED_BAR_5_SIZE 0x1c
-static int pci_soc_mode = 0;
+static int pci_soc_mode;
/**
* fixed_bar_cap - return the offset of the fixed BAR cap if found
@@ -141,7 +141,8 @@ static int pci_device_update_fixed(struct pci_bus *bus, unsigned int devfn,
*/
static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
{
- /* This is a workaround for A0 LNC bug where PCI status register does
+ /*
+ * This is a workaround for A0 LNC bug where PCI status register does
* not have new CAP bit set. can not be written by SW either.
*
* PCI header type in real LNC indicates a single function device, this
@@ -149,12 +150,12 @@ static bool type1_access_ok(unsigned int bus, unsigned int devfn, int reg)
* shim. Therefore, use the header type in shim instead.
*/
if (reg >= 0x100 || reg == PCI_STATUS || reg == PCI_HEADER_TYPE)
- return 0;
+ return false;
if (bus == 0 && (devfn == PCI_DEVFN(2, 0)
|| devfn == PCI_DEVFN(0, 0)
|| devfn == PCI_DEVFN(3, 0)))
- return 1;
- return 0; /* langwell on others */
+ return true;
+ return false; /* Langwell on others */
}
static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
@@ -172,7 +173,8 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
{
int offset;
- /* On MRST, there is no PCI ROM BAR, this will cause a subsequent read
+ /*
+ * On MRST, there is no PCI ROM BAR, this will cause a subsequent read
* to ROM BAR return 0 then being ignored.
*/
if (where == PCI_ROM_ADDRESS)
@@ -203,14 +205,15 @@ static int pci_write(struct pci_bus *bus, unsigned int devfn, int where,
where, size, value);
}
-static int mrst_pci_irq_enable(struct pci_dev *dev)
+static int intel_mid_pci_irq_enable(struct pci_dev *dev)
{
u8 pin;
struct io_apic_irq_attr irq_attr;
pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
- /* MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
+ /*
+ * MRST only have IOAPIC, the PCI irq lines are 1:1 mapped to
* IOAPIC RTE entries, so we just enable RTE for the device.
*/
irq_attr.ioapic = mp_find_ioapic(dev->irq);
@@ -222,39 +225,43 @@ static int mrst_pci_irq_enable(struct pci_dev *dev)
return 0;
}
-struct pci_ops pci_mrst_ops = {
+struct pci_ops intel_mid_pci_ops = {
.read = pci_read,
.write = pci_write,
};
/**
- * pci_mrst_init - installs pci_mrst_ops
+ * intel_mid_pci_init - installs intel_mid_pci_ops
*
* Moorestown has an interesting PCI implementation (see above).
* Called when the early platform detection installs it.
*/
-int __init pci_mrst_init(void)
+int __init intel_mid_pci_init(void)
{
- printk(KERN_INFO "Intel MID platform detected, using MID PCI ops\n");
+ pr_info("Intel MID platform detected, using MID PCI ops\n");
pci_mmcfg_late_init();
- pcibios_enable_irq = mrst_pci_irq_enable;
- pci_root_ops = pci_mrst_ops;
+ pcibios_enable_irq = intel_mid_pci_irq_enable;
+ pci_root_ops = intel_mid_pci_ops;
pci_soc_mode = 1;
/* Continue with standard init */
return 1;
}
-/* Langwell devices are not true pci devices, they are not subject to 10 ms
- * d3 to d0 delay required by pci spec.
+/*
+ * Langwell devices are not true PCI devices; they are not subject to 10 ms
+ * d3 to d0 delay required by PCI spec.
*/
static void pci_d3delay_fixup(struct pci_dev *dev)
{
- /* PCI fixups are effectively decided compile time. If we have a dual
- SoC/non-SoC kernel we don't want to mangle d3 on non SoC devices */
- if (!pci_soc_mode)
- return;
- /* true pci devices in lincroft should allow type 1 access, the rest
- * are langwell fake pci devices.
+ /*
+ * PCI fixups are effectively decided compile time. If we have a dual
+ * SoC/non-SoC kernel we don't want to mangle d3 on non-SoC devices.
+ */
+ if (!pci_soc_mode)
+ return;
+ /*
+ * True PCI devices in Lincroft should allow type 1 access, the rest
+ * are Langwell fake PCI devices.
*/
if (type1_access_ok(dev->bus->number, dev->devfn, PCI_DEVICE_ID))
return;
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile
index 01e0231a113..20342d4c82c 100644
--- a/arch/x86/platform/Makefile
+++ b/arch/x86/platform/Makefile
@@ -4,7 +4,7 @@ obj-y += efi/
obj-y += geode/
obj-y += goldfish/
obj-y += iris/
-obj-y += mrst/
+obj-y += intel-mid/
obj-y += olpc/
obj-y += scx200/
obj-y += sfi/
diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile
index 6db1cc4c753..b7b0b35c198 100644
--- a/arch/x86/platform/efi/Makefile
+++ b/arch/x86/platform/efi/Makefile
@@ -1,2 +1,3 @@
obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o
obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
+obj-$(CONFIG_EARLY_PRINTK_EFI) += early_printk.o
diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c
new file mode 100644
index 00000000000..6599a0027b7
--- /dev/null
+++ b/arch/x86/platform/efi/early_printk.c
@@ -0,0 +1,191 @@
+/*
+ * Copyright (C) 2013 Intel Corporation; author Matt Fleming
+ *
+ * This file is part of the Linux kernel, and is made available under
+ * the terms of the GNU General Public License version 2.
+ */
+
+#include <linux/console.h>
+#include <linux/efi.h>
+#include <linux/font.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <asm/setup.h>
+
+static const struct font_desc *font;
+static u32 efi_x, efi_y;
+
+static __init void early_efi_clear_scanline(unsigned int y)
+{
+ unsigned long base, *dst;
+ u16 len;
+
+ base = boot_params.screen_info.lfb_base;
+ len = boot_params.screen_info.lfb_linelength;
+
+ dst = early_ioremap(base + y*len, len);
+ if (!dst)
+ return;
+
+ memset(dst, 0, len);
+ early_iounmap(dst, len);
+}
+
+static __init void early_efi_scroll_up(void)
+{
+ unsigned long base, *dst, *src;
+ u16 len;
+ u32 i, height;
+
+ base = boot_params.screen_info.lfb_base;
+ len = boot_params.screen_info.lfb_linelength;
+ height = boot_params.screen_info.lfb_height;
+
+ for (i = 0; i < height - font->height; i++) {
+ dst = early_ioremap(base + i*len, len);
+ if (!dst)
+ return;
+
+ src = early_ioremap(base + (i + font->height) * len, len);
+ if (!src) {
+ early_iounmap(dst, len);
+ return;
+ }
+
+ memmove(dst, src, len);
+
+ early_iounmap(src, len);
+ early_iounmap(dst, len);
+ }
+}
+
+static void early_efi_write_char(u32 *dst, unsigned char c, unsigned int h)
+{
+ const u32 color_black = 0x00000000;
+ const u32 color_white = 0x00ffffff;
+ const u8 *src;
+ u8 s8;
+ int m;
+
+ src = font->data + c * font->height;
+ s8 = *(src + h);
+
+ for (m = 0; m < 8; m++) {
+ if ((s8 >> (7 - m)) & 1)
+ *dst = color_white;
+ else
+ *dst = color_black;
+ dst++;
+ }
+}
+
+static __init void
+early_efi_write(struct console *con, const char *str, unsigned int num)
+{
+ struct screen_info *si;
+ unsigned long base;
+ unsigned int len;
+ const char *s;
+ void *dst;
+
+ base = boot_params.screen_info.lfb_base;
+ si = &boot_params.screen_info;
+ len = si->lfb_linelength;
+
+ while (num) {
+ unsigned int linemax;
+ unsigned int h, count = 0;
+
+ for (s = str; *s && *s != '\n'; s++) {
+ if (count == num)
+ break;
+ count++;
+ }
+
+ linemax = (si->lfb_width - efi_x) / font->width;
+ if (count > linemax)
+ count = linemax;
+
+ for (h = 0; h < font->height; h++) {
+ unsigned int n, x;
+
+ dst = early_ioremap(base + (efi_y + h) * len, len);
+ if (!dst)
+ return;
+
+ s = str;
+ n = count;
+ x = efi_x;
+
+ while (n-- > 0) {
+ early_efi_write_char(dst + x*4, *s, h);
+ x += font->width;
+ s++;
+ }
+
+ early_iounmap(dst, len);
+ }
+
+ num -= count;
+ efi_x += count * font->width;
+ str += count;
+
+ if (num > 0 && *s == '\n') {
+ efi_x = 0;
+ efi_y += font->height;
+ str++;
+ num--;
+ }
+
+ if (efi_x >= si->lfb_width) {
+ efi_x = 0;
+ efi_y += font->height;
+ }
+
+ if (efi_y + font->height >= si->lfb_height) {
+ u32 i;
+
+ efi_y -= font->height;
+ early_efi_scroll_up();
+
+ for (i = 0; i < font->height; i++)
+ early_efi_clear_scanline(efi_y + i);
+ }
+ }
+}
+
+static __init int early_efi_setup(struct console *con, char *options)
+{
+ struct screen_info *si;
+ u16 xres, yres;
+ u32 i;
+
+ si = &boot_params.screen_info;
+ xres = si->lfb_width;
+ yres = si->lfb_height;
+
+ /*
+ * early_efi_write_char() implicitly assumes a framebuffer with
+ * 32-bits per pixel.
+ */
+ if (si->lfb_depth != 32)
+ return -ENODEV;
+
+ font = get_default_font(xres, yres, -1, -1);
+ if (!font)
+ return -ENODEV;
+
+ efi_y = rounddown(yres, font->height) - font->height;
+ for (i = 0; i < (yres - efi_y) / font->height; i++)
+ early_efi_scroll_up();
+
+ return 0;
+}
+
+struct console early_efi_console = {
+ .name = "earlyefi",
+ .write = early_efi_write,
+ .setup = early_efi_setup,
+ .flags = CON_PRINTBUFFER,
+ .index = -1,
+};
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 90f6ed12709..92c02344a06 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -60,19 +60,6 @@
static efi_char16_t efi_dummy_name[6] = { 'D', 'U', 'M', 'M', 'Y', 0 };
-struct efi __read_mostly efi = {
- .mps = EFI_INVALID_TABLE_ADDR,
- .acpi = EFI_INVALID_TABLE_ADDR,
- .acpi20 = EFI_INVALID_TABLE_ADDR,
- .smbios = EFI_INVALID_TABLE_ADDR,
- .sal_systab = EFI_INVALID_TABLE_ADDR,
- .boot_info = EFI_INVALID_TABLE_ADDR,
- .hcdp = EFI_INVALID_TABLE_ADDR,
- .uga = EFI_INVALID_TABLE_ADDR,
- .uv_systab = EFI_INVALID_TABLE_ADDR,
-};
-EXPORT_SYMBOL(efi);
-
struct efi_memory_map memmap;
static struct efi efi_phys __initdata;
@@ -80,6 +67,13 @@ static efi_system_table_t efi_systab __initdata;
unsigned long x86_efi_facility;
+static __initdata efi_config_table_type_t arch_tables[] = {
+#ifdef CONFIG_X86_UV
+ {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab},
+#endif
+ {NULL_GUID, NULL, NULL},
+};
+
/*
* Returns 1 if 'facility' is enabled, 0 otherwise.
*/
@@ -399,6 +393,8 @@ int __init efi_memblock_x86_reserve_range(void)
memblock_reserve(pmap, memmap.nr_map * memmap.desc_size);
+ efi.memmap = &memmap;
+
return 0;
}
@@ -578,80 +574,6 @@ static int __init efi_systab_init(void *phys)
return 0;
}
-static int __init efi_config_init(u64 tables, int nr_tables)
-{
- void *config_tables, *tablep;
- int i, sz;
-
- if (efi_enabled(EFI_64BIT))
- sz = sizeof(efi_config_table_64_t);
- else
- sz = sizeof(efi_config_table_32_t);
-
- /*
- * Let's see what config tables the firmware passed to us.
- */
- config_tables = early_ioremap(tables, nr_tables * sz);
- if (config_tables == NULL) {
- pr_err("Could not map Configuration table!\n");
- return -ENOMEM;
- }
-
- tablep = config_tables;
- pr_info("");
- for (i = 0; i < efi.systab->nr_tables; i++) {
- efi_guid_t guid;
- unsigned long table;
-
- if (efi_enabled(EFI_64BIT)) {
- u64 table64;
- guid = ((efi_config_table_64_t *)tablep)->guid;
- table64 = ((efi_config_table_64_t *)tablep)->table;
- table = table64;
-#ifdef CONFIG_X86_32
- if (table64 >> 32) {
- pr_cont("\n");
- pr_err("Table located above 4GB, disabling EFI.\n");
- early_iounmap(config_tables,
- efi.systab->nr_tables * sz);
- return -EINVAL;
- }
-#endif
- } else {
- guid = ((efi_config_table_32_t *)tablep)->guid;
- table = ((efi_config_table_32_t *)tablep)->table;
- }
- if (!efi_guidcmp(guid, MPS_TABLE_GUID)) {
- efi.mps = table;
- pr_cont(" MPS=0x%lx ", table);
- } else if (!efi_guidcmp(guid, ACPI_20_TABLE_GUID)) {
- efi.acpi20 = table;
- pr_cont(" ACPI 2.0=0x%lx ", table);
- } else if (!efi_guidcmp(guid, ACPI_TABLE_GUID)) {
- efi.acpi = table;
- pr_cont(" ACPI=0x%lx ", table);
- } else if (!efi_guidcmp(guid, SMBIOS_TABLE_GUID)) {
- efi.smbios = table;
- pr_cont(" SMBIOS=0x%lx ", table);
-#ifdef CONFIG_X86_UV
- } else if (!efi_guidcmp(guid, UV_SYSTEM_TABLE_GUID)) {
- efi.uv_systab = table;
- pr_cont(" UVsystab=0x%lx ", table);
-#endif
- } else if (!efi_guidcmp(guid, HCDP_TABLE_GUID)) {
- efi.hcdp = table;
- pr_cont(" HCDP=0x%lx ", table);
- } else if (!efi_guidcmp(guid, UGA_IO_PROTOCOL_GUID)) {
- efi.uga = table;
- pr_cont(" UGA=0x%lx ", table);
- }
- tablep += sz;
- }
- pr_cont("\n");
- early_iounmap(config_tables, efi.systab->nr_tables * sz);
- return 0;
-}
-
static int __init efi_runtime_init(void)
{
efi_runtime_services_t *runtime;
@@ -745,7 +667,7 @@ void __init efi_init(void)
efi.systab->hdr.revision >> 16,
efi.systab->hdr.revision & 0xffff, vendor);
- if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
+ if (efi_config_init(arch_tables))
return;
set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
@@ -816,34 +738,6 @@ 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;
-}
-
void efi_memory_uc(u64 addr, unsigned long size)
{
unsigned long page_shift = 1UL << EFI_PAGE_SHIFT;
@@ -912,10 +806,13 @@ void __init efi_enter_virtual_mode(void)
for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
md = p;
- if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
- md->type != EFI_BOOT_SERVICES_CODE &&
- md->type != EFI_BOOT_SERVICES_DATA)
- continue;
+ if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
+#ifdef CONFIG_X86_64
+ if (md->type != EFI_BOOT_SERVICES_CODE &&
+ md->type != EFI_BOOT_SERVICES_DATA)
+#endif
+ continue;
+ }
size = md->num_pages << EFI_PAGE_SHIFT;
end = md->phys_addr + size;
diff --git a/arch/x86/platform/geode/alix.c b/arch/x86/platform/geode/alix.c
index 90e23e7679a..76b6632d314 100644
--- a/arch/x86/platform/geode/alix.c
+++ b/arch/x86/platform/geode/alix.c
@@ -98,7 +98,7 @@ static struct platform_device alix_leds_dev = {
.dev.platform_data = &alix_leds_data,
};
-static struct __initdata platform_device *alix_devs[] = {
+static struct platform_device *alix_devs[] __initdata = {
&alix_buttons_dev,
&alix_leds_dev,
};
diff --git a/arch/x86/platform/geode/geos.c b/arch/x86/platform/geode/geos.c
index c2e6d53558b..aa733fba247 100644
--- a/arch/x86/platform/geode/geos.c
+++ b/arch/x86/platform/geode/geos.c
@@ -87,7 +87,7 @@ static struct platform_device geos_leds_dev = {
.dev.platform_data = &geos_leds_data,
};
-static struct __initdata platform_device *geos_devs[] = {
+static struct platform_device *geos_devs[] __initdata = {
&geos_buttons_dev,
&geos_leds_dev,
};
diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c
index 646e3b5b4bb..927e38c0089 100644
--- a/arch/x86/platform/geode/net5501.c
+++ b/arch/x86/platform/geode/net5501.c
@@ -78,7 +78,7 @@ static struct platform_device net5501_leds_dev = {
.dev.platform_data = &net5501_leds_data,
};
-static struct __initdata platform_device *net5501_devs[] = {
+static struct platform_device *net5501_devs[] __initdata = {
&net5501_buttons_dev,
&net5501_leds_dev,
};
diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile
new file mode 100644
index 00000000000..01cc29ea5ff
--- /dev/null
+++ b/arch/x86/platform/intel-mid/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o
+obj-$(CONFIG_X86_INTEL_MID) += intel_mid_vrtc.o
+obj-$(CONFIG_EARLY_PRINTK_INTEL_MID) += early_printk_intel_mid.o
+# SFI specific code
+ifdef CONFIG_X86_INTEL_MID
+obj-$(CONFIG_SFI) += sfi.o device_libs/
+endif
diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile
new file mode 100644
index 00000000000..097e7a7940d
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/Makefile
@@ -0,0 +1,22 @@
+# IPC Devices
+obj-y += platform_ipc.o
+obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic.o
+obj-$(subst m,y,$(CONFIG_SND_MFLD_MACHINE)) += platform_msic_audio.o
+obj-$(subst m,y,$(CONFIG_GPIO_MSIC)) += platform_msic_gpio.o
+obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_ocd.o
+obj-$(subst m,y,$(CONFIG_MFD_INTEL_MSIC)) += platform_msic_battery.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_POWER_BUTTON)) += platform_msic_power_btn.o
+obj-$(subst m,y,$(CONFIG_GPIO_INTEL_PMIC)) += platform_pmic_gpio.o
+obj-$(subst m,y,$(CONFIG_INTEL_MFLD_THERMAL)) += platform_msic_thermal.o
+# I2C Devices
+obj-$(subst m,y,$(CONFIG_SENSORS_EMC1403)) += platform_emc1403.o
+obj-$(subst m,y,$(CONFIG_SENSORS_LIS3LV02D)) += platform_lis331.o
+obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_max7315.o
+obj-$(subst m,y,$(CONFIG_INPUT_MPU3050)) += platform_mpu3050.o
+obj-$(subst m,y,$(CONFIG_INPUT_BMA150)) += platform_bma023.o
+obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
+obj-$(subst m,y,$(CONFIG_DRM_MEDFIELD)) += platform_tc35876x.o
+# SPI Devices
+obj-$(subst m,y,$(CONFIG_SERIAL_MRST_MAX3110)) += platform_max3111.o
+# MISC Devices
+obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_bma023.c b/arch/x86/platform/intel-mid/device_libs/platform_bma023.c
new file mode 100644
index 00000000000..0ae7f2ae229
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_bma023.c
@@ -0,0 +1,20 @@
+/*
+ * platform_bma023.c: bma023 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ *
+ * 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.
+ */
+
+#include <asm/intel-mid.h>
+
+static const struct devs_id bma023_dev_id __initconst = {
+ .name = "bma023",
+ .type = SFI_DEV_TYPE_I2C,
+ .delay = 1,
+};
+
+sfi_device(bma023_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c b/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c
new file mode 100644
index 00000000000..0d942c1d26d
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_emc1403.c
@@ -0,0 +1,41 @@
+/*
+ * platform_emc1403.c: emc1403 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <asm/intel-mid.h>
+
+static void __init *emc1403_platform_data(void *info)
+{
+ static short intr2nd_pdata;
+ struct i2c_board_info *i2c_info = info;
+ int intr = get_gpio_by_name("thermal_int");
+ int intr2nd = get_gpio_by_name("thermal_alert");
+
+ if (intr == -1 || intr2nd == -1)
+ return NULL;
+
+ i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+ intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET;
+
+ return &intr2nd_pdata;
+}
+
+static const struct devs_id emc1403_dev_id __initconst = {
+ .name = "emc1403",
+ .type = SFI_DEV_TYPE_I2C,
+ .delay = 1,
+ .get_platform_data = &emc1403_platform_data,
+};
+
+sfi_device(emc1403_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
new file mode 100644
index 00000000000..a013a4834bb
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_gpio_keys.c
@@ -0,0 +1,83 @@
+/*
+ * platform_gpio_keys.c: gpio_keys platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/input.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/gpio_keys.h>
+#include <linux/platform_device.h>
+#include <asm/intel-mid.h>
+
+#define DEVICE_NAME "gpio-keys"
+
+/*
+ * we will search these buttons in SFI GPIO table (by name)
+ * and register them dynamically. Please add all possible
+ * buttons here, we will shrink them if no GPIO found.
+ */
+static struct gpio_keys_button gpio_button[] = {
+ {KEY_POWER, -1, 1, "power_btn", EV_KEY, 0, 3000},
+ {KEY_PROG1, -1, 1, "prog_btn1", EV_KEY, 0, 20},
+ {KEY_PROG2, -1, 1, "prog_btn2", EV_KEY, 0, 20},
+ {SW_LID, -1, 1, "lid_switch", EV_SW, 0, 20},
+ {KEY_VOLUMEUP, -1, 1, "vol_up", EV_KEY, 0, 20},
+ {KEY_VOLUMEDOWN, -1, 1, "vol_down", EV_KEY, 0, 20},
+ {KEY_CAMERA, -1, 1, "camera_full", EV_KEY, 0, 20},
+ {KEY_CAMERA_FOCUS, -1, 1, "camera_half", EV_KEY, 0, 20},
+ {SW_KEYPAD_SLIDE, -1, 1, "MagSw1", EV_SW, 0, 20},
+ {SW_KEYPAD_SLIDE, -1, 1, "MagSw2", EV_SW, 0, 20},
+};
+
+static struct gpio_keys_platform_data gpio_keys = {
+ .buttons = gpio_button,
+ .rep = 1,
+ .nbuttons = -1, /* will fill it after search */
+};
+
+static struct platform_device pb_device = {
+ .name = DEVICE_NAME,
+ .id = -1,
+ .dev = {
+ .platform_data = &gpio_keys,
+ },
+};
+
+/*
+ * Shrink the non-existent buttons, register the gpio button
+ * device if there is some
+ */
+static int __init pb_keys_init(void)
+{
+ struct gpio_keys_button *gb = gpio_button;
+ int i, num, good = 0;
+
+ num = sizeof(gpio_button) / sizeof(struct gpio_keys_button);
+ for (i = 0; i < num; i++) {
+ gb[i].gpio = get_gpio_by_name(gb[i].desc);
+ pr_debug("info[%2d]: name = %s, gpio = %d\n", i, gb[i].desc,
+ gb[i].gpio);
+ if (gb[i].gpio == -1)
+ continue;
+
+ if (i != good)
+ gb[good] = gb[i];
+ good++;
+ }
+
+ if (good) {
+ gpio_keys.nbuttons = good;
+ return platform_device_register(&pb_device);
+ }
+ return 0;
+}
+late_initcall(pb_keys_init);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.c b/arch/x86/platform/intel-mid/device_libs/platform_ipc.c
new file mode 100644
index 00000000000..a84b73d6c4a
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_ipc.c
@@ -0,0 +1,68 @@
+/*
+ * platform_ipc.c: IPC platform library file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/sfi.h>
+#include <linux/gpio.h>
+#include <asm/intel-mid.h>
+#include "platform_ipc.h"
+
+void __init ipc_device_handler(struct sfi_device_table_entry *pentry,
+ struct devs_id *dev)
+{
+ struct platform_device *pdev;
+ void *pdata = NULL;
+ static struct resource res __initdata = {
+ .name = "IRQ",
+ .flags = IORESOURCE_IRQ,
+ };
+
+ pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n",
+ pentry->name, pentry->irq);
+
+ /*
+ * We need to call platform init of IPC devices to fill misc_pdata
+ * structure. It will be used in msic_init for initialization.
+ */
+ if (dev != NULL)
+ pdata = dev->get_platform_data(pentry);
+
+ /*
+ * On Medfield the platform device creation is handled by the MSIC
+ * MFD driver so we don't need to do it here.
+ */
+ if (intel_mid_has_msic())
+ return;
+
+ pdev = platform_device_alloc(pentry->name, 0);
+ if (pdev == NULL) {
+ pr_err("out of memory for SFI platform device '%s'.\n",
+ pentry->name);
+ return;
+ }
+ res.start = pentry->irq;
+ platform_device_add_resources(pdev, &res, 1);
+
+ pdev->dev.platform_data = pdata;
+ intel_scu_device_register(pdev);
+}
+
+static const struct devs_id pmic_audio_dev_id __initconst = {
+ .name = "pmic_audio",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .device_handler = &ipc_device_handler,
+};
+
+sfi_device(pmic_audio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_ipc.h b/arch/x86/platform/intel-mid/device_libs/platform_ipc.h
new file mode 100644
index 00000000000..8f568dd7960
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_ipc.h
@@ -0,0 +1,17 @@
+/*
+ * platform_ipc.h: IPC platform library header file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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 _PLATFORM_IPC_H_
+#define _PLATFORM_IPC_H_
+
+extern void __init ipc_device_handler(struct sfi_device_table_entry *pentry,
+ struct devs_id *dev) __attribute__((weak));
+#endif
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_lis331.c b/arch/x86/platform/intel-mid/device_libs/platform_lis331.c
new file mode 100644
index 00000000000..15278c11f71
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_lis331.c
@@ -0,0 +1,39 @@
+/*
+ * platform_lis331.c: lis331 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <asm/intel-mid.h>
+
+static void __init *lis331dl_platform_data(void *info)
+{
+ static short intr2nd_pdata;
+ struct i2c_board_info *i2c_info = info;
+ int intr = get_gpio_by_name("accel_int");
+ int intr2nd = get_gpio_by_name("accel_2");
+
+ if (intr == -1 || intr2nd == -1)
+ return NULL;
+
+ i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+ intr2nd_pdata = intr2nd + INTEL_MID_IRQ_OFFSET;
+
+ return &intr2nd_pdata;
+}
+
+static const struct devs_id lis331dl_dev_id __initconst = {
+ .name = "i2c_accel",
+ .type = SFI_DEV_TYPE_I2C,
+ .get_platform_data = &lis331dl_platform_data,
+};
+
+sfi_device(lis331dl_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_max3111.c b/arch/x86/platform/intel-mid/device_libs/platform_max3111.c
new file mode 100644
index 00000000000..afd1df94e0e
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_max3111.c
@@ -0,0 +1,35 @@
+/*
+ * platform_max3111.c: max3111 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/gpio.h>
+#include <linux/spi/spi.h>
+#include <asm/intel-mid.h>
+
+static void __init *max3111_platform_data(void *info)
+{
+ struct spi_board_info *spi_info = info;
+ int intr = get_gpio_by_name("max3111_int");
+
+ spi_info->mode = SPI_MODE_0;
+ if (intr == -1)
+ return NULL;
+ spi_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+ return NULL;
+}
+
+static const struct devs_id max3111_dev_id __initconst = {
+ .name = "spi_max3111",
+ .type = SFI_DEV_TYPE_SPI,
+ .get_platform_data = &max3111_platform_data,
+};
+
+sfi_device(max3111_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_max7315.c b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c
new file mode 100644
index 00000000000..94ade10024a
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_max7315.c
@@ -0,0 +1,79 @@
+/*
+ * platform_max7315.c: max7315 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <linux/platform_data/pca953x.h>
+#include <asm/intel-mid.h>
+
+#define MAX7315_NUM 2
+
+static void __init *max7315_platform_data(void *info)
+{
+ static struct pca953x_platform_data max7315_pdata[MAX7315_NUM];
+ static int nr;
+ struct pca953x_platform_data *max7315 = &max7315_pdata[nr];
+ struct i2c_board_info *i2c_info = info;
+ int gpio_base, intr;
+ char base_pin_name[SFI_NAME_LEN + 1];
+ char intr_pin_name[SFI_NAME_LEN + 1];
+
+ if (nr == MAX7315_NUM) {
+ pr_err("too many max7315s, we only support %d\n",
+ MAX7315_NUM);
+ return NULL;
+ }
+ /* we have several max7315 on the board, we only need load several
+ * instances of the same pca953x driver to cover them
+ */
+ strcpy(i2c_info->type, "max7315");
+ if (nr++) {
+ sprintf(base_pin_name, "max7315_%d_base", nr);
+ sprintf(intr_pin_name, "max7315_%d_int", nr);
+ } else {
+ strcpy(base_pin_name, "max7315_base");
+ strcpy(intr_pin_name, "max7315_int");
+ }
+
+ gpio_base = get_gpio_by_name(base_pin_name);
+ intr = get_gpio_by_name(intr_pin_name);
+
+ if (gpio_base == -1)
+ return NULL;
+ max7315->gpio_base = gpio_base;
+ if (intr != -1) {
+ i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+ max7315->irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
+ } else {
+ i2c_info->irq = -1;
+ max7315->irq_base = -1;
+ }
+ return max7315;
+}
+
+static const struct devs_id max7315_dev_id __initconst = {
+ .name = "i2c_max7315",
+ .type = SFI_DEV_TYPE_I2C,
+ .delay = 1,
+ .get_platform_data = &max7315_platform_data,
+};
+
+static const struct devs_id max7315_2_dev_id __initconst = {
+ .name = "i2c_max7315_2",
+ .type = SFI_DEV_TYPE_I2C,
+ .delay = 1,
+ .get_platform_data = &max7315_platform_data,
+};
+
+sfi_device(max7315_dev_id);
+sfi_device(max7315_2_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c b/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c
new file mode 100644
index 00000000000..dd28d63c84f
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mpu3050.c
@@ -0,0 +1,36 @@
+/*
+ * platform_mpu3050.c: mpu3050 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/gpio.h>
+#include <linux/i2c.h>
+#include <asm/intel-mid.h>
+
+static void *mpu3050_platform_data(void *info)
+{
+ struct i2c_board_info *i2c_info = info;
+ int intr = get_gpio_by_name("mpu3050_int");
+
+ if (intr == -1)
+ return NULL;
+
+ i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+ return NULL;
+}
+
+static const struct devs_id mpu3050_dev_id __initconst = {
+ .name = "mpu3050",
+ .type = SFI_DEV_TYPE_I2C,
+ .delay = 1,
+ .get_platform_data = &mpu3050_platform_data,
+};
+
+sfi_device(mpu3050_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic.c b/arch/x86/platform/intel-mid/device_libs/platform_msic.c
new file mode 100644
index 00000000000..9f4a775a69d
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic.c
@@ -0,0 +1,87 @@
+/*
+ * platform_msic.c: MSIC platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel_scu_ipc.h>
+#include <asm/intel-mid.h>
+#include "platform_msic.h"
+
+struct intel_msic_platform_data msic_pdata;
+
+static struct resource msic_resources[] = {
+ {
+ .start = INTEL_MSIC_IRQ_PHYS_BASE,
+ .end = INTEL_MSIC_IRQ_PHYS_BASE + 64 - 1,
+ .flags = IORESOURCE_MEM,
+ },
+};
+
+static struct platform_device msic_device = {
+ .name = "intel_msic",
+ .id = -1,
+ .dev = {
+ .platform_data = &msic_pdata,
+ },
+ .num_resources = ARRAY_SIZE(msic_resources),
+ .resource = msic_resources,
+};
+
+static int msic_scu_status_change(struct notifier_block *nb,
+ unsigned long code, void *data)
+{
+ if (code == SCU_DOWN) {
+ platform_device_unregister(&msic_device);
+ return 0;
+ }
+
+ return platform_device_register(&msic_device);
+}
+
+static int __init msic_init(void)
+{
+ static struct notifier_block msic_scu_notifier = {
+ .notifier_call = msic_scu_status_change,
+ };
+
+ /*
+ * We need to be sure that the SCU IPC is ready before MSIC device
+ * can be registered.
+ */
+ if (intel_mid_has_msic())
+ intel_scu_notifier_add(&msic_scu_notifier);
+
+ return 0;
+}
+arch_initcall(msic_init);
+
+/*
+ * msic_generic_platform_data - sets generic platform data for the block
+ * @info: pointer to the SFI device table entry for this block
+ * @block: MSIC block
+ *
+ * Function sets IRQ number from the SFI table entry for given device to
+ * the MSIC platform data.
+ */
+void *msic_generic_platform_data(void *info, enum intel_msic_block block)
+{
+ struct sfi_device_table_entry *entry = info;
+
+ BUG_ON(block < 0 || block >= INTEL_MSIC_BLOCK_LAST);
+ msic_pdata.irq[block] = entry->irq;
+
+ return NULL;
+}
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic.h b/arch/x86/platform/intel-mid/device_libs/platform_msic.h
new file mode 100644
index 00000000000..917eb56d77d
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic.h
@@ -0,0 +1,19 @@
+/*
+ * platform_msic.h: MSIC platform data header file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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 _PLATFORM_MSIC_H_
+#define _PLATFORM_MSIC_H_
+
+extern struct intel_msic_platform_data msic_pdata;
+
+extern void *msic_generic_platform_data(void *info,
+ enum intel_msic_block block) __attribute__((weak));
+#endif
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
new file mode 100644
index 00000000000..29629397d2b
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_audio.c
@@ -0,0 +1,47 @@
+/*
+ * platform_msic_audio.c: MSIC audio platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void *msic_audio_platform_data(void *info)
+{
+ struct platform_device *pdev;
+
+ pdev = platform_device_register_simple("sst-platform", -1, NULL, 0);
+
+ if (IS_ERR(pdev)) {
+ pr_err("failed to create audio platform device\n");
+ return NULL;
+ }
+
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_AUDIO);
+}
+
+static const struct devs_id msic_audio_dev_id __initconst = {
+ .name = "msic_audio",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .get_platform_data = &msic_audio_platform_data,
+ .device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_audio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
new file mode 100644
index 00000000000..f446c33df1a
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_battery.c
@@ -0,0 +1,37 @@
+/*
+ * platform_msic_battery.c: MSIC battery platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_battery_platform_data(void *info)
+{
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_BATTERY);
+}
+
+static const struct devs_id msic_battery_dev_id __initconst = {
+ .name = "msic_battery",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .get_platform_data = &msic_battery_platform_data,
+ .device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_battery_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
new file mode 100644
index 00000000000..2a4f7b1dd91
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_gpio.c
@@ -0,0 +1,48 @@
+/*
+ * platform_msic_gpio.c: MSIC GPIO platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/sfi.h>
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_gpio_platform_data(void *info)
+{
+ static struct intel_msic_gpio_pdata msic_gpio_pdata;
+
+ int gpio = get_gpio_by_name("msic_gpio_base");
+
+ if (gpio < 0)
+ return NULL;
+
+ msic_gpio_pdata.gpio_base = gpio;
+ msic_pdata.gpio = &msic_gpio_pdata;
+
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_GPIO);
+}
+
+static const struct devs_id msic_gpio_dev_id __initconst = {
+ .name = "msic_gpio",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .get_platform_data = &msic_gpio_platform_data,
+ .device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_gpio_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
new file mode 100644
index 00000000000..6497111ddb5
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_ocd.c
@@ -0,0 +1,49 @@
+/*
+ * platform_msic_ocd.c: MSIC OCD platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/sfi.h>
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_ocd_platform_data(void *info)
+{
+ static struct intel_msic_ocd_pdata msic_ocd_pdata;
+ int gpio;
+
+ gpio = get_gpio_by_name("ocd_gpio");
+
+ if (gpio < 0)
+ return NULL;
+
+ msic_ocd_pdata.gpio = gpio;
+ msic_pdata.ocd = &msic_ocd_pdata;
+
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_OCD);
+}
+
+static const struct devs_id msic_ocd_dev_id __initconst = {
+ .name = "msic_ocd",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .get_platform_data = &msic_ocd_platform_data,
+ .device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_ocd_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
new file mode 100644
index 00000000000..83a3459bc33
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_power_btn.c
@@ -0,0 +1,36 @@
+/*
+ * platform_msic_power_btn.c: MSIC power btn platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/sfi.h>
+#include <linux/init.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_power_btn_platform_data(void *info)
+{
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_POWER_BTN);
+}
+
+static const struct devs_id msic_power_btn_dev_id __initconst = {
+ .name = "msic_power_btn",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .get_platform_data = &msic_power_btn_platform_data,
+ .device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_power_btn_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
new file mode 100644
index 00000000000..a351878b96b
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_msic_thermal.c
@@ -0,0 +1,37 @@
+/*
+ * platform_msic_thermal.c: msic_thermal platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/input.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/mfd/intel_msic.h>
+#include <asm/intel-mid.h>
+
+#include "platform_msic.h"
+#include "platform_ipc.h"
+
+static void __init *msic_thermal_platform_data(void *info)
+{
+ return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_THERMAL);
+}
+
+static const struct devs_id msic_thermal_dev_id __initconst = {
+ .name = "msic_thermal",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .get_platform_data = &msic_thermal_platform_data,
+ .device_handler = &ipc_device_handler,
+};
+
+sfi_device(msic_thermal_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c b/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
new file mode 100644
index 00000000000..d87182a0926
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_pmic_gpio.c
@@ -0,0 +1,54 @@
+/*
+ * platform_pmic_gpio.c: PMIC GPIO platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/gpio.h>
+#include <linux/init.h>
+#include <linux/sfi.h>
+#include <linux/intel_pmic_gpio.h>
+#include <asm/intel-mid.h>
+
+#include "platform_ipc.h"
+
+static void __init *pmic_gpio_platform_data(void *info)
+{
+ static struct intel_pmic_gpio_platform_data pmic_gpio_pdata;
+ int gpio_base = get_gpio_by_name("pmic_gpio_base");
+
+ if (gpio_base == -1)
+ gpio_base = 64;
+ pmic_gpio_pdata.gpio_base = gpio_base;
+ pmic_gpio_pdata.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
+ pmic_gpio_pdata.gpiointr = 0xffffeff8;
+
+ return &pmic_gpio_pdata;
+}
+
+static const struct devs_id pmic_gpio_spi_dev_id __initconst = {
+ .name = "pmic_gpio",
+ .type = SFI_DEV_TYPE_SPI,
+ .delay = 1,
+ .get_platform_data = &pmic_gpio_platform_data,
+};
+
+static const struct devs_id pmic_gpio_ipc_dev_id __initconst = {
+ .name = "pmic_gpio",
+ .type = SFI_DEV_TYPE_IPC,
+ .delay = 1,
+ .get_platform_data = &pmic_gpio_platform_data,
+ .device_handler = &ipc_device_handler
+};
+
+sfi_device(pmic_gpio_spi_dev_id);
+sfi_device(pmic_gpio_ipc_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
new file mode 100644
index 00000000000..740fc757050
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_tc35876x.c
@@ -0,0 +1,36 @@
+/*
+ * platform_tc35876x.c: tc35876x platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/gpio.h>
+#include <linux/i2c/tc35876x.h>
+#include <asm/intel-mid.h>
+
+/*tc35876x DSI_LVDS bridge chip and panel platform data*/
+static void *tc35876x_platform_data(void *data)
+{
+ static struct tc35876x_platform_data pdata;
+
+ /* gpio pins set to -1 will not be used by the driver */
+ pdata.gpio_bridge_reset = get_gpio_by_name("LCMB_RXEN");
+ pdata.gpio_panel_bl_en = get_gpio_by_name("6S6P_BL_EN");
+ pdata.gpio_panel_vadd = get_gpio_by_name("EN_VREG_LCD_V3P3");
+
+ return &pdata;
+}
+
+static const struct devs_id tc35876x_dev_id __initconst = {
+ .name = "i2c_disp_brig",
+ .type = SFI_DEV_TYPE_I2C,
+ .get_platform_data = &tc35876x_platform_data,
+};
+
+sfi_device(tc35876x_dev_id);
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c b/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c
new file mode 100644
index 00000000000..22881c9a673
--- /dev/null
+++ b/arch/x86/platform/intel-mid/device_libs/platform_tca6416.c
@@ -0,0 +1,57 @@
+/*
+ * platform_tca6416.c: tca6416 platform data initilization file
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/platform_data/pca953x.h>
+#include <linux/i2c.h>
+#include <linux/gpio.h>
+#include <asm/intel-mid.h>
+
+#define TCA6416_NAME "tca6416"
+#define TCA6416_BASE "tca6416_base"
+#define TCA6416_INTR "tca6416_int"
+
+static void *tca6416_platform_data(void *info)
+{
+ static struct pca953x_platform_data tca6416;
+ struct i2c_board_info *i2c_info = info;
+ int gpio_base, intr;
+ char base_pin_name[SFI_NAME_LEN + 1];
+ char intr_pin_name[SFI_NAME_LEN + 1];
+
+ strcpy(i2c_info->type, TCA6416_NAME);
+ strcpy(base_pin_name, TCA6416_BASE);
+ strcpy(intr_pin_name, TCA6416_INTR);
+
+ gpio_base = get_gpio_by_name(base_pin_name);
+ intr = get_gpio_by_name(intr_pin_name);
+
+ if (gpio_base == -1)
+ return NULL;
+ tca6416.gpio_base = gpio_base;
+ if (intr != -1) {
+ i2c_info->irq = intr + INTEL_MID_IRQ_OFFSET;
+ tca6416.irq_base = gpio_base + INTEL_MID_IRQ_OFFSET;
+ } else {
+ i2c_info->irq = -1;
+ tca6416.irq_base = -1;
+ }
+ return &tca6416;
+}
+
+static const struct devs_id tca6416_dev_id __initconst = {
+ .name = "tca6416",
+ .type = SFI_DEV_TYPE_I2C,
+ .delay = 1,
+ .get_platform_data = &tca6416_platform_data,
+};
+
+sfi_device(tca6416_dev_id);
diff --git a/arch/x86/platform/mrst/early_printk_mrst.c b/arch/x86/platform/intel-mid/early_printk_intel_mid.c
index 028454f0c3a..4f702f554f6 100644
--- a/arch/x86/platform/mrst/early_printk_mrst.c
+++ b/arch/x86/platform/intel-mid/early_printk_intel_mid.c
@@ -1,5 +1,5 @@
/*
- * early_printk_mrst.c - early consoles for Intel MID platforms
+ * early_printk_intel_mid.c - early consoles for Intel MID platforms
*
* Copyright (c) 2008-2010, Intel Corporation
*
@@ -27,7 +27,7 @@
#include <asm/fixmap.h>
#include <asm/pgtable.h>
-#include <asm/mrst.h>
+#include <asm/intel-mid.h>
#define MRST_SPI_TIMEOUT 0x200000
#define MRST_REGBASE_SPI0 0xff128000
@@ -152,7 +152,7 @@ void mrst_early_console_init(void)
spi0_cdiv = ((*pclk_spi0) & 0xe00) >> 9;
freq = 100000000 / (spi0_cdiv + 1);
- if (mrst_identify_cpu() == MRST_CPU_CHIP_PENWELL)
+ if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_PENWELL)
mrst_spi_paddr = MRST_REGBASE_SPI1;
pspi = (void *)set_fixmap_offset_nocache(FIX_EARLYCON_MEM_BASE,
@@ -213,13 +213,14 @@ static void early_mrst_spi_putc(char c)
}
if (!timeout)
- pr_warning("MRST earlycon: timed out\n");
+ pr_warn("MRST earlycon: timed out\n");
else
max3110_write_data(c);
}
/* Early SPI only uses polling mode */
-static void early_mrst_spi_write(struct console *con, const char *str, unsigned n)
+static void early_mrst_spi_write(struct console *con, const char *str,
+ unsigned n)
{
int i;
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
new file mode 100644
index 00000000000..f90e290f689
--- /dev/null
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -0,0 +1,213 @@
+/*
+ * intel-mid.c: Intel MID platform setup code
+ *
+ * (C) Copyright 2008, 2012 Intel Corporation
+ * Author: Jacob Pan (jacob.jun.pan@intel.com)
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#define pr_fmt(fmt) "intel_mid: " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/sfi.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+
+#include <asm/setup.h>
+#include <asm/mpspec_def.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/io_apic.h>
+#include <asm/intel-mid.h>
+#include <asm/intel_mid_vrtc.h>
+#include <asm/io.h>
+#include <asm/i8259.h>
+#include <asm/intel_scu_ipc.h>
+#include <asm/apb_timer.h>
+#include <asm/reboot.h>
+
+/*
+ * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
+ * cmdline option x86_intel_mid_timer can be used to override the configuration
+ * to prefer one or the other.
+ * at runtime, there are basically three timer configurations:
+ * 1. per cpu apbt clock only
+ * 2. per cpu always-on lapic clocks only, this is Penwell/Medfield only
+ * 3. per cpu lapic clock (C3STOP) and one apbt clock, with broadcast.
+ *
+ * by default (without cmdline option), platform code first detects cpu type
+ * to see if we are on lincroft or penwell, then set up both lapic or apbt
+ * clocks accordingly.
+ * i.e. by default, medfield uses configuration #2, moorestown uses #1.
+ * config #3 is supported but not recommended on medfield.
+ *
+ * rating and feature summary:
+ * lapic (with C3STOP) --------- 100
+ * apbt (always-on) ------------ 110
+ * lapic (always-on,ARAT) ------ 150
+ */
+
+enum intel_mid_timer_options intel_mid_timer_options;
+
+enum intel_mid_cpu_type __intel_mid_cpu_chip;
+EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip);
+
+static void intel_mid_power_off(void)
+{
+}
+
+static void intel_mid_reboot(void)
+{
+ intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
+}
+
+static unsigned long __init intel_mid_calibrate_tsc(void)
+{
+ unsigned long fast_calibrate;
+ u32 lo, hi, ratio, fsb;
+
+ rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+ pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
+ ratio = (hi >> 8) & 0x1f;
+ pr_debug("ratio is %d\n", ratio);
+ if (!ratio) {
+ pr_err("read a zero ratio, should be incorrect!\n");
+ pr_err("force tsc ratio to 16 ...\n");
+ ratio = 16;
+ }
+ rdmsr(MSR_FSB_FREQ, lo, hi);
+ if ((lo & 0x7) == 0x7)
+ fsb = PENWELL_FSB_FREQ_83SKU;
+ else
+ fsb = PENWELL_FSB_FREQ_100SKU;
+ fast_calibrate = ratio * fsb;
+ pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
+ lapic_timer_frequency = fsb * 1000 / HZ;
+ /* mark tsc clocksource as reliable */
+ set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
+
+ if (fast_calibrate)
+ return fast_calibrate;
+
+ return 0;
+}
+
+static void __init intel_mid_time_init(void)
+{
+ sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
+ switch (intel_mid_timer_options) {
+ case INTEL_MID_TIMER_APBT_ONLY:
+ break;
+ case INTEL_MID_TIMER_LAPIC_APBT:
+ x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
+ x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
+ break;
+ default:
+ if (!boot_cpu_has(X86_FEATURE_ARAT))
+ break;
+ x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
+ x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
+ return;
+ }
+ /* we need at least one APB timer */
+ pre_init_apic_IRQ0();
+ apbt_time_init();
+}
+
+static void intel_mid_arch_setup(void)
+{
+ if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27)
+ __intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_PENWELL;
+ else {
+ pr_err("Unknown Intel MID CPU (%d:%d), default to Penwell\n",
+ boot_cpu_data.x86, boot_cpu_data.x86_model);
+ __intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_PENWELL;
+ }
+}
+
+/* MID systems don't have i8042 controller */
+static int intel_mid_i8042_detect(void)
+{
+ return 0;
+}
+
+/*
+ * Moorestown does not have external NMI source nor port 0x61 to report
+ * NMI status. The possible NMI sources are from pmu as a result of NMI
+ * watchdog or lock debug. Reading io port 0x61 results in 0xff which
+ * misled NMI handler.
+ */
+static unsigned char intel_mid_get_nmi_reason(void)
+{
+ return 0;
+}
+
+/*
+ * Moorestown specific x86_init function overrides and early setup
+ * calls.
+ */
+void __init x86_intel_mid_early_setup(void)
+{
+ x86_init.resources.probe_roms = x86_init_noop;
+ x86_init.resources.reserve_resources = x86_init_noop;
+
+ x86_init.timers.timer_init = intel_mid_time_init;
+ x86_init.timers.setup_percpu_clockev = x86_init_noop;
+
+ x86_init.irqs.pre_vector_init = x86_init_noop;
+
+ x86_init.oem.arch_setup = intel_mid_arch_setup;
+
+ x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock;
+
+ x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
+ x86_platform.i8042_detect = intel_mid_i8042_detect;
+ x86_init.timers.wallclock_init = intel_mid_rtc_init;
+ x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
+
+ x86_init.pci.init = intel_mid_pci_init;
+ x86_init.pci.fixup_irqs = x86_init_noop;
+
+ legacy_pic = &null_legacy_pic;
+
+ pm_power_off = intel_mid_power_off;
+ machine_ops.emergency_restart = intel_mid_reboot;
+
+ /* 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;
+ set_bit(MP_BUS_ISA, mp_bus_not_pci);
+}
+
+/*
+ * if user does not want to use per CPU apb timer, just give it a lower rating
+ * than local apic timer and skip the late per cpu timer init.
+ */
+static inline int __init setup_x86_intel_mid_timer(char *arg)
+{
+ if (!arg)
+ return -EINVAL;
+
+ if (strcmp("apbt_only", arg) == 0)
+ intel_mid_timer_options = INTEL_MID_TIMER_APBT_ONLY;
+ else if (strcmp("lapic_and_apbt", arg) == 0)
+ intel_mid_timer_options = INTEL_MID_TIMER_LAPIC_APBT;
+ else {
+ pr_warn("X86 INTEL_MID timer option %s not recognised"
+ " use x86_intel_mid_timer=apbt_only or lapic_and_apbt\n",
+ arg);
+ return -EINVAL;
+ }
+ return 0;
+}
+__setup("x86_intel_mid_timer=", setup_x86_intel_mid_timer);
+
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
index 5e355b134ba..4762cff7fac 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/intel-mid/intel_mid_vrtc.c
@@ -1,5 +1,5 @@
/*
- * vrtc.c: Driver for virtual RTC device on Intel MID platform
+ * intel_mid_vrtc.c: Driver for virtual RTC device on Intel MID platform
*
* (C) Copyright 2009 Intel Corporation
*
@@ -23,8 +23,8 @@
#include <linux/sfi.h>
#include <linux/platform_device.h>
-#include <asm/mrst.h>
-#include <asm/mrst-vrtc.h>
+#include <asm/intel-mid.h>
+#include <asm/intel_mid_vrtc.h>
#include <asm/time.h>
#include <asm/fixmap.h>
@@ -79,7 +79,7 @@ void vrtc_get_time(struct timespec *now)
/* vRTC YEAR reg contains the offset to 1972 */
year += 1972;
- printk(KERN_INFO "vRTC: sec: %d min: %d hour: %d day: %d "
+ pr_info("vRTC: sec: %d min: %d hour: %d day: %d "
"mon: %d year: %d\n", sec, min, hour, mday, mon, year);
now->tv_sec = mktime(year, mon, mday, hour, min, sec);
@@ -109,15 +109,14 @@ int vrtc_set_mmss(const struct timespec *now)
vrtc_cmos_write(tm.tm_sec, RTC_SECONDS);
spin_unlock_irqrestore(&rtc_lock, flags);
} else {
- printk(KERN_ERR
- "%s: Invalid vRTC value: write of %lx to vRTC failed\n",
+ pr_err("%s: Invalid vRTC value: write of %lx to vRTC failed\n",
__FUNCTION__, now->tv_sec);
retval = -EINVAL;
}
return retval;
}
-void __init mrst_rtc_init(void)
+void __init intel_mid_rtc_init(void)
{
unsigned long vrtc_paddr;
@@ -155,10 +154,10 @@ static struct platform_device vrtc_device = {
};
/* Register the RTC device if appropriate */
-static int __init mrst_device_create(void)
+static int __init intel_mid_device_create(void)
{
/* No Moorestown, no device */
- if (!mrst_identify_cpu())
+ if (!intel_mid_identify_cpu())
return -ENODEV;
/* No timer, no device */
if (!sfi_mrtc_num)
@@ -175,4 +174,4 @@ static int __init mrst_device_create(void)
return platform_device_register(&vrtc_device);
}
-module_init(mrst_device_create);
+module_init(intel_mid_device_create);
diff --git a/arch/x86/platform/intel-mid/sfi.c b/arch/x86/platform/intel-mid/sfi.c
new file mode 100644
index 00000000000..c84c1ca396b
--- /dev/null
+++ b/arch/x86/platform/intel-mid/sfi.c
@@ -0,0 +1,488 @@
+/*
+ * intel_mid_sfi.c: Intel MID SFI initialization code
+ *
+ * (C) Copyright 2013 Intel Corporation
+ * Author: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@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.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/interrupt.h>
+#include <linux/scatterlist.h>
+#include <linux/sfi.h>
+#include <linux/intel_pmic_gpio.h>
+#include <linux/spi/spi.h>
+#include <linux/i2c.h>
+#include <linux/skbuff.h>
+#include <linux/gpio.h>
+#include <linux/gpio_keys.h>
+#include <linux/input.h>
+#include <linux/platform_device.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/notifier.h>
+#include <linux/mmc/core.h>
+#include <linux/mmc/card.h>
+#include <linux/blkdev.h>
+
+#include <asm/setup.h>
+#include <asm/mpspec_def.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/io_apic.h>
+#include <asm/intel-mid.h>
+#include <asm/intel_mid_vrtc.h>
+#include <asm/io.h>
+#include <asm/i8259.h>
+#include <asm/intel_scu_ipc.h>
+#include <asm/apb_timer.h>
+#include <asm/reboot.h>
+
+#define SFI_SIG_OEM0 "OEM0"
+#define MAX_IPCDEVS 24
+#define MAX_SCU_SPI 24
+#define MAX_SCU_I2C 24
+
+static struct platform_device *ipc_devs[MAX_IPCDEVS];
+static struct spi_board_info *spi_devs[MAX_SCU_SPI];
+static struct i2c_board_info *i2c_devs[MAX_SCU_I2C];
+static struct sfi_gpio_table_entry *gpio_table;
+static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM];
+static int ipc_next_dev;
+static int spi_next_dev;
+static int i2c_next_dev;
+static int i2c_bus[MAX_SCU_I2C];
+static int gpio_num_entry;
+static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM];
+int sfi_mrtc_num;
+int sfi_mtimer_num;
+
+struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX];
+EXPORT_SYMBOL_GPL(sfi_mrtc_array);
+
+struct blocking_notifier_head intel_scu_notifier =
+ BLOCKING_NOTIFIER_INIT(intel_scu_notifier);
+EXPORT_SYMBOL_GPL(intel_scu_notifier);
+
+#define intel_mid_sfi_get_pdata(dev, priv) \
+ ((dev)->get_platform_data ? (dev)->get_platform_data(priv) : NULL)
+
+/* parse all the mtimer info to a static mtimer array */
+int __init sfi_parse_mtmr(struct sfi_table_header *table)
+{
+ struct sfi_table_simple *sb;
+ struct sfi_timer_table_entry *pentry;
+ struct mpc_intsrc mp_irq;
+ int totallen;
+
+ sb = (struct sfi_table_simple *)table;
+ if (!sfi_mtimer_num) {
+ sfi_mtimer_num = SFI_GET_NUM_ENTRIES(sb,
+ struct sfi_timer_table_entry);
+ pentry = (struct sfi_timer_table_entry *) sb->pentry;
+ totallen = sfi_mtimer_num * sizeof(*pentry);
+ memcpy(sfi_mtimer_array, pentry, totallen);
+ }
+
+ pr_debug("SFI MTIMER info (num = %d):\n", sfi_mtimer_num);
+ pentry = sfi_mtimer_array;
+ for (totallen = 0; totallen < sfi_mtimer_num; totallen++, pentry++) {
+ pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz, irq = %d\n",
+ totallen, (u32)pentry->phys_addr,
+ pentry->freq_hz, pentry->irq);
+ if (!pentry->irq)
+ continue;
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
+ mp_irq.irqflag = 5;
+ mp_irq.srcbus = MP_BUS_ISA;
+ mp_irq.srcbusirq = pentry->irq; /* IRQ */
+ mp_irq.dstapic = MP_APIC_ALL;
+ mp_irq.dstirq = pentry->irq;
+ mp_save_irq(&mp_irq);
+ }
+
+ return 0;
+}
+
+struct sfi_timer_table_entry *sfi_get_mtmr(int hint)
+{
+ int i;
+ if (hint < sfi_mtimer_num) {
+ if (!sfi_mtimer_usage[hint]) {
+ pr_debug("hint taken for timer %d irq %d\n",
+ hint, sfi_mtimer_array[hint].irq);
+ sfi_mtimer_usage[hint] = 1;
+ return &sfi_mtimer_array[hint];
+ }
+ }
+ /* take the first timer available */
+ for (i = 0; i < sfi_mtimer_num;) {
+ if (!sfi_mtimer_usage[i]) {
+ sfi_mtimer_usage[i] = 1;
+ return &sfi_mtimer_array[i];
+ }
+ i++;
+ }
+ return NULL;
+}
+
+void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr)
+{
+ int i;
+ for (i = 0; i < sfi_mtimer_num;) {
+ if (mtmr->irq == sfi_mtimer_array[i].irq) {
+ sfi_mtimer_usage[i] = 0;
+ return;
+ }
+ i++;
+ }
+}
+
+/* parse all the mrtc info to a global mrtc array */
+int __init sfi_parse_mrtc(struct sfi_table_header *table)
+{
+ struct sfi_table_simple *sb;
+ struct sfi_rtc_table_entry *pentry;
+ struct mpc_intsrc mp_irq;
+
+ int totallen;
+
+ sb = (struct sfi_table_simple *)table;
+ if (!sfi_mrtc_num) {
+ sfi_mrtc_num = SFI_GET_NUM_ENTRIES(sb,
+ struct sfi_rtc_table_entry);
+ pentry = (struct sfi_rtc_table_entry *)sb->pentry;
+ totallen = sfi_mrtc_num * sizeof(*pentry);
+ memcpy(sfi_mrtc_array, pentry, totallen);
+ }
+
+ pr_debug("SFI RTC info (num = %d):\n", sfi_mrtc_num);
+ pentry = sfi_mrtc_array;
+ for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) {
+ pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n",
+ totallen, (u32)pentry->phys_addr, pentry->irq);
+ mp_irq.type = MP_INTSRC;
+ mp_irq.irqtype = mp_INT;
+ mp_irq.irqflag = 0xf; /* level trigger and active low */
+ mp_irq.srcbus = MP_BUS_ISA;
+ mp_irq.srcbusirq = pentry->irq; /* IRQ */
+ mp_irq.dstapic = MP_APIC_ALL;
+ mp_irq.dstirq = pentry->irq;
+ mp_save_irq(&mp_irq);
+ }
+ return 0;
+}
+
+
+/*
+ * Parsing GPIO table first, since the DEVS table will need this table
+ * to map the pin name to the actual pin.
+ */
+static int __init sfi_parse_gpio(struct sfi_table_header *table)
+{
+ struct sfi_table_simple *sb;
+ struct sfi_gpio_table_entry *pentry;
+ int num, i;
+
+ if (gpio_table)
+ return 0;
+ sb = (struct sfi_table_simple *)table;
+ num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry);
+ pentry = (struct sfi_gpio_table_entry *)sb->pentry;
+
+ gpio_table = kmalloc(num * sizeof(*pentry), GFP_KERNEL);
+ if (!gpio_table)
+ return -1;
+ memcpy(gpio_table, pentry, num * sizeof(*pentry));
+ gpio_num_entry = num;
+
+ pr_debug("GPIO pin info:\n");
+ for (i = 0; i < num; i++, pentry++)
+ pr_debug("info[%2d]: controller = %16.16s, pin_name = %16.16s,"
+ " pin = %d\n", i,
+ pentry->controller_name,
+ pentry->pin_name,
+ pentry->pin_no);
+ return 0;
+}
+
+int get_gpio_by_name(const char *name)
+{
+ struct sfi_gpio_table_entry *pentry = gpio_table;
+ int i;
+
+ if (!pentry)
+ return -1;
+ for (i = 0; i < gpio_num_entry; i++, pentry++) {
+ if (!strncmp(name, pentry->pin_name, SFI_NAME_LEN))
+ return pentry->pin_no;
+ }
+ return -1;
+}
+
+void __init intel_scu_device_register(struct platform_device *pdev)
+{
+ if (ipc_next_dev == MAX_IPCDEVS)
+ pr_err("too many SCU IPC devices");
+ else
+ ipc_devs[ipc_next_dev++] = pdev;
+}
+
+static void __init intel_scu_spi_device_register(struct spi_board_info *sdev)
+{
+ struct spi_board_info *new_dev;
+
+ if (spi_next_dev == MAX_SCU_SPI) {
+ pr_err("too many SCU SPI devices");
+ return;
+ }
+
+ new_dev = kzalloc(sizeof(*sdev), GFP_KERNEL);
+ if (!new_dev) {
+ pr_err("failed to alloc mem for delayed spi dev %s\n",
+ sdev->modalias);
+ return;
+ }
+ memcpy(new_dev, sdev, sizeof(*sdev));
+
+ spi_devs[spi_next_dev++] = new_dev;
+}
+
+static void __init intel_scu_i2c_device_register(int bus,
+ struct i2c_board_info *idev)
+{
+ struct i2c_board_info *new_dev;
+
+ if (i2c_next_dev == MAX_SCU_I2C) {
+ pr_err("too many SCU I2C devices");
+ return;
+ }
+
+ new_dev = kzalloc(sizeof(*idev), GFP_KERNEL);
+ if (!new_dev) {
+ pr_err("failed to alloc mem for delayed i2c dev %s\n",
+ idev->type);
+ return;
+ }
+ memcpy(new_dev, idev, sizeof(*idev));
+
+ i2c_bus[i2c_next_dev] = bus;
+ i2c_devs[i2c_next_dev++] = new_dev;
+}
+
+/* Called by IPC driver */
+void intel_scu_devices_create(void)
+{
+ int i;
+
+ for (i = 0; i < ipc_next_dev; i++)
+ platform_device_add(ipc_devs[i]);
+
+ for (i = 0; i < spi_next_dev; i++)
+ spi_register_board_info(spi_devs[i], 1);
+
+ for (i = 0; i < i2c_next_dev; i++) {
+ struct i2c_adapter *adapter;
+ struct i2c_client *client;
+
+ adapter = i2c_get_adapter(i2c_bus[i]);
+ if (adapter) {
+ client = i2c_new_device(adapter, i2c_devs[i]);
+ if (!client)
+ pr_err("can't create i2c device %s\n",
+ i2c_devs[i]->type);
+ } else
+ i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1);
+ }
+ intel_scu_notifier_post(SCU_AVAILABLE, NULL);
+}
+EXPORT_SYMBOL_GPL(intel_scu_devices_create);
+
+/* Called by IPC driver */
+void intel_scu_devices_destroy(void)
+{
+ int i;
+
+ intel_scu_notifier_post(SCU_DOWN, NULL);
+
+ for (i = 0; i < ipc_next_dev; i++)
+ platform_device_del(ipc_devs[i]);
+}
+EXPORT_SYMBOL_GPL(intel_scu_devices_destroy);
+
+static void __init install_irq_resource(struct platform_device *pdev, int irq)
+{
+ /* Single threaded */
+ static struct resource res __initdata = {
+ .name = "IRQ",
+ .flags = IORESOURCE_IRQ,
+ };
+ res.start = irq;
+ platform_device_add_resources(pdev, &res, 1);
+}
+
+static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *pentry,
+ struct devs_id *dev)
+{
+ struct platform_device *pdev;
+ void *pdata = NULL;
+
+ pr_debug("IPC bus, name = %16.16s, irq = 0x%2x\n",
+ pentry->name, pentry->irq);
+ pdata = intel_mid_sfi_get_pdata(dev, pentry);
+
+ pdev = platform_device_alloc(pentry->name, 0);
+ if (pdev == NULL) {
+ pr_err("out of memory for SFI platform device '%s'.\n",
+ pentry->name);
+ return;
+ }
+ install_irq_resource(pdev, pentry->irq);
+
+ pdev->dev.platform_data = pdata;
+ platform_device_add(pdev);
+}
+
+static void __init sfi_handle_spi_dev(struct sfi_device_table_entry *pentry,
+ struct devs_id *dev)
+{
+ struct spi_board_info spi_info;
+ void *pdata = NULL;
+
+ memset(&spi_info, 0, sizeof(spi_info));
+ strncpy(spi_info.modalias, pentry->name, SFI_NAME_LEN);
+ spi_info.irq = ((pentry->irq == (u8)0xff) ? 0 : pentry->irq);
+ spi_info.bus_num = pentry->host_num;
+ spi_info.chip_select = pentry->addr;
+ spi_info.max_speed_hz = pentry->max_freq;
+ pr_debug("SPI bus=%d, name=%16.16s, irq=0x%2x, max_freq=%d, cs=%d\n",
+ spi_info.bus_num,
+ spi_info.modalias,
+ spi_info.irq,
+ spi_info.max_speed_hz,
+ spi_info.chip_select);
+
+ pdata = intel_mid_sfi_get_pdata(dev, &spi_info);
+
+ spi_info.platform_data = pdata;
+ if (dev->delay)
+ intel_scu_spi_device_register(&spi_info);
+ else
+ spi_register_board_info(&spi_info, 1);
+}
+
+static void __init sfi_handle_i2c_dev(struct sfi_device_table_entry *pentry,
+ struct devs_id *dev)
+{
+ struct i2c_board_info i2c_info;
+ void *pdata = NULL;
+
+ memset(&i2c_info, 0, sizeof(i2c_info));
+ strncpy(i2c_info.type, pentry->name, SFI_NAME_LEN);
+ i2c_info.irq = ((pentry->irq == (u8)0xff) ? 0 : pentry->irq);
+ i2c_info.addr = pentry->addr;
+ pr_debug("I2C bus = %d, name = %16.16s, irq = 0x%2x, addr = 0x%x\n",
+ pentry->host_num,
+ i2c_info.type,
+ i2c_info.irq,
+ i2c_info.addr);
+ pdata = intel_mid_sfi_get_pdata(dev, &i2c_info);
+ i2c_info.platform_data = pdata;
+
+ if (dev->delay)
+ intel_scu_i2c_device_register(pentry->host_num, &i2c_info);
+ else
+ i2c_register_board_info(pentry->host_num, &i2c_info, 1);
+}
+
+extern struct devs_id *const __x86_intel_mid_dev_start[],
+ *const __x86_intel_mid_dev_end[];
+
+static struct devs_id __init *get_device_id(u8 type, char *name)
+{
+ struct devs_id *const *dev_table;
+
+ for (dev_table = __x86_intel_mid_dev_start;
+ dev_table < __x86_intel_mid_dev_end; dev_table++) {
+ struct devs_id *dev = *dev_table;
+ if (dev->type == type &&
+ !strncmp(dev->name, name, SFI_NAME_LEN)) {
+ return dev;
+ }
+ }
+
+ return NULL;
+}
+
+static int __init sfi_parse_devs(struct sfi_table_header *table)
+{
+ struct sfi_table_simple *sb;
+ struct sfi_device_table_entry *pentry;
+ struct devs_id *dev = NULL;
+ int num, i;
+ int ioapic;
+ struct io_apic_irq_attr irq_attr;
+
+ sb = (struct sfi_table_simple *)table;
+ num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
+ pentry = (struct sfi_device_table_entry *)sb->pentry;
+
+ for (i = 0; i < num; i++, pentry++) {
+ int irq = pentry->irq;
+
+ if (irq != (u8)0xff) { /* native RTE case */
+ /* these SPI2 devices are not exposed to system as PCI
+ * devices, but they have separate RTE entry in IOAPIC
+ * so we have to enable them one by one here
+ */
+ ioapic = mp_find_ioapic(irq);
+ irq_attr.ioapic = ioapic;
+ irq_attr.ioapic_pin = irq;
+ irq_attr.trigger = 1;
+ irq_attr.polarity = 1;
+ io_apic_set_pci_routing(NULL, irq, &irq_attr);
+ } else
+ irq = 0; /* No irq */
+
+ dev = get_device_id(pentry->type, pentry->name);
+
+ if (!dev)
+ continue;
+
+ if (dev->device_handler) {
+ dev->device_handler(pentry, dev);
+ } else {
+ switch (pentry->type) {
+ case SFI_DEV_TYPE_IPC:
+ sfi_handle_ipc_dev(pentry, dev);
+ break;
+ case SFI_DEV_TYPE_SPI:
+ sfi_handle_spi_dev(pentry, dev);
+ break;
+ case SFI_DEV_TYPE_I2C:
+ sfi_handle_i2c_dev(pentry, dev);
+ break;
+ case SFI_DEV_TYPE_UART:
+ case SFI_DEV_TYPE_HSI:
+ default:
+ break;
+ }
+ }
+ }
+ return 0;
+}
+
+static int __init intel_mid_platform_init(void)
+{
+ sfi_table_parse(SFI_SIG_GPIO, NULL, NULL, sfi_parse_gpio);
+ sfi_table_parse(SFI_SIG_DEVS, NULL, NULL, sfi_parse_devs);
+ return 0;
+}
+arch_initcall(intel_mid_platform_init);
diff --git a/arch/x86/platform/mrst/Makefile b/arch/x86/platform/mrst/Makefile
deleted file mode 100644
index af1da7e623f..00000000000
--- a/arch/x86/platform/mrst/Makefile
+++ /dev/null
@@ -1,3 +0,0 @@
-obj-$(CONFIG_X86_INTEL_MID) += mrst.o
-obj-$(CONFIG_X86_INTEL_MID) += vrtc.o
-obj-$(CONFIG_EARLY_PRINTK_INTEL_MID) += early_printk_mrst.o
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
deleted file mode 100644
index 47fe66fe61f..00000000000
--- a/arch/x86/platform/mrst/mrst.c
+++ /dev/null
@@ -1,1052 +0,0 @@
-/*
- * mrst.c: Intel Moorestown platform specific setup code
- *
- * (C) Copyright 2008 Intel Corporation
- * Author: Jacob Pan (jacob.jun.pan@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.
- */
-
-#define pr_fmt(fmt) "mrst: " fmt
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/interrupt.h>
-#include <linux/scatterlist.h>
-#include <linux/sfi.h>
-#include <linux/intel_pmic_gpio.h>
-#include <linux/spi/spi.h>
-#include <linux/i2c.h>
-#include <linux/i2c/pca953x.h>
-#include <linux/gpio_keys.h>
-#include <linux/input.h>
-#include <linux/platform_device.h>
-#include <linux/irq.h>
-#include <linux/module.h>
-#include <linux/notifier.h>
-#include <linux/mfd/intel_msic.h>
-#include <linux/gpio.h>
-#include <linux/i2c/tc35876x.h>
-
-#include <asm/setup.h>
-#include <asm/mpspec_def.h>
-#include <asm/hw_irq.h>
-#include <asm/apic.h>
-#include <asm/io_apic.h>
-#include <asm/mrst.h>
-#include <asm/mrst-vrtc.h>
-#include <asm/io.h>
-#include <asm/i8259.h>
-#include <asm/intel_scu_ipc.h>
-#include <asm/apb_timer.h>
-#include <asm/reboot.h>
-
-/*
- * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
- * cmdline option x86_mrst_timer can be used to override the configuration
- * to prefer one or the other.
- * at runtime, there are basically three timer configurations:
- * 1. per cpu apbt clock only
- * 2. per cpu always-on lapic clocks only, this is Penwell/Medfield only
- * 3. per cpu lapic clock (C3STOP) and one apbt clock, with broadcast.
- *
- * by default (without cmdline option), platform code first detects cpu type
- * to see if we are on lincroft or penwell, then set up both lapic or apbt
- * clocks accordingly.
- * i.e. by default, medfield uses configuration #2, moorestown uses #1.
- * config #3 is supported but not recommended on medfield.
- *
- * rating and feature summary:
- * lapic (with C3STOP) --------- 100
- * apbt (always-on) ------------ 110
- * lapic (always-on,ARAT) ------ 150
- */
-
-enum mrst_timer_options mrst_timer_options;
-
-static u32 sfi_mtimer_usage[SFI_MTMR_MAX_NUM];
-static struct sfi_timer_table_entry sfi_mtimer_array[SFI_MTMR_MAX_NUM];
-enum mrst_cpu_type __mrst_cpu_chip;
-EXPORT_SYMBOL_GPL(__mrst_cpu_chip);
-
-int sfi_mtimer_num;
-
-struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX];
-EXPORT_SYMBOL_GPL(sfi_mrtc_array);
-int sfi_mrtc_num;
-
-static void mrst_power_off(void)
-{
-}
-
-static void mrst_reboot(void)
-{
- intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
-}
-
-/* parse all the mtimer info to a static mtimer array */
-static int __init sfi_parse_mtmr(struct sfi_table_header *table)
-{
- struct sfi_table_simple *sb;
- struct sfi_timer_table_entry *pentry;
- struct mpc_intsrc mp_irq;
- int totallen;
-
- sb = (struct sfi_table_simple *)table;
- if (!sfi_mtimer_num) {
- sfi_mtimer_num = SFI_GET_NUM_ENTRIES(sb,
- struct sfi_timer_table_entry);
- pentry = (struct sfi_timer_table_entry *) sb->pentry;
- totallen = sfi_mtimer_num * sizeof(*pentry);
- memcpy(sfi_mtimer_array, pentry, totallen);
- }
-
- pr_debug("SFI MTIMER info (num = %d):\n", sfi_mtimer_num);
- pentry = sfi_mtimer_array;
- for (totallen = 0; totallen < sfi_mtimer_num; totallen++, pentry++) {
- pr_debug("timer[%d]: paddr = 0x%08x, freq = %dHz,"
- " irq = %d\n", totallen, (u32)pentry->phys_addr,
- pentry->freq_hz, pentry->irq);
- if (!pentry->irq)
- continue;
- mp_irq.type = MP_INTSRC;
- mp_irq.irqtype = mp_INT;
-/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
- mp_irq.irqflag = 5;
- mp_irq.srcbus = MP_BUS_ISA;
- mp_irq.srcbusirq = pentry->irq; /* IRQ */
- mp_irq.dstapic = MP_APIC_ALL;
- mp_irq.dstirq = pentry->irq;
- mp_save_irq(&mp_irq);
- }
-
- return 0;
-}
-
-struct sfi_timer_table_entry *sfi_get_mtmr(int hint)
-{
- int i;
- if (hint < sfi_mtimer_num) {
- if (!sfi_mtimer_usage[hint]) {
- pr_debug("hint taken for timer %d irq %d\n",\
- hint, sfi_mtimer_array[hint].irq);
- sfi_mtimer_usage[hint] = 1;
- return &sfi_mtimer_array[hint];
- }
- }
- /* take the first timer available */
- for (i = 0; i < sfi_mtimer_num;) {
- if (!sfi_mtimer_usage[i]) {
- sfi_mtimer_usage[i] = 1;
- return &sfi_mtimer_array[i];
- }
- i++;
- }
- return NULL;
-}
-
-void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr)
-{
- int i;
- for (i = 0; i < sfi_mtimer_num;) {
- if (mtmr->irq == sfi_mtimer_array[i].irq) {
- sfi_mtimer_usage[i] = 0;
- return;
- }
- i++;
- }
-}
-
-/* parse all the mrtc info to a global mrtc array */
-int __init sfi_parse_mrtc(struct sfi_table_header *table)
-{
- struct sfi_table_simple *sb;
- struct sfi_rtc_table_entry *pentry;
- struct mpc_intsrc mp_irq;
-
- int totallen;
-
- sb = (struct sfi_table_simple *)table;
- if (!sfi_mrtc_num) {
- sfi_mrtc_num = SFI_GET_NUM_ENTRIES(sb,
- struct sfi_rtc_table_entry);
- pentry = (struct sfi_rtc_table_entry *)sb->pentry;
- totallen = sfi_mrtc_num * sizeof(*pentry);
- memcpy(sfi_mrtc_array, pentry, totallen);
- }
-
- pr_debug("SFI RTC info (num = %d):\n", sfi_mrtc_num);
- pentry = sfi_mrtc_array;
- for (totallen = 0; totallen < sfi_mrtc_num; totallen++, pentry++) {
- pr_debug("RTC[%d]: paddr = 0x%08x, irq = %d\n",
- totallen, (u32)pentry->phys_addr, pentry->irq);
- mp_irq.type = MP_INTSRC;
- mp_irq.irqtype = mp_INT;
- mp_irq.irqflag = 0xf; /* level trigger and active low */
- mp_irq.srcbus = MP_BUS_ISA;
- mp_irq.srcbusirq = pentry->irq; /* IRQ */
- mp_irq.dstapic = MP_APIC_ALL;
- mp_irq.dstirq = pentry->irq;
- mp_save_irq(&mp_irq);
- }
- return 0;
-}
-
-static unsigned long __init mrst_calibrate_tsc(void)
-{
- unsigned long fast_calibrate;
- u32 lo, hi, ratio, fsb;
-
- rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
- pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
- ratio = (hi >> 8) & 0x1f;
- pr_debug("ratio is %d\n", ratio);
- if (!ratio) {
- pr_err("read a zero ratio, should be incorrect!\n");
- pr_err("force tsc ratio to 16 ...\n");
- ratio = 16;
- }
- rdmsr(MSR_FSB_FREQ, lo, hi);
- if ((lo & 0x7) == 0x7)
- fsb = PENWELL_FSB_FREQ_83SKU;
- else
- fsb = PENWELL_FSB_FREQ_100SKU;
- fast_calibrate = ratio * fsb;
- pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
- lapic_timer_frequency = fsb * 1000 / HZ;
- /* mark tsc clocksource as reliable */
- set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
-
- if (fast_calibrate)
- return fast_calibrate;
-
- return 0;
-}
-
-static void __init mrst_time_init(void)
-{
- sfi_table_parse(SFI_SIG_MTMR, NULL, NULL, sfi_parse_mtmr);
- switch (mrst_timer_options) {
- case MRST_TIMER_APBT_ONLY:
- break;
- case MRST_TIMER_LAPIC_APBT:
- x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
- x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
- break;
- default:
- if (!boot_cpu_has(X86_FEATURE_ARAT))
- break;
- x86_init.timers.setup_percpu_clockev = setup_boot_APIC_clock;
- x86_cpuinit.setup_percpu_clockev = setup_secondary_APIC_clock;
- return;
- }
- /* we need at least one APB timer */
- pre_init_apic_IRQ0();
- apbt_time_init();
-}
-
-static void mrst_arch_setup(void)
-{
- if (boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model == 0x27)
- __mrst_cpu_chip = MRST_CPU_CHIP_PENWELL;
- else {
- pr_err("Unknown Intel MID CPU (%d:%d), default to Penwell\n",
- boot_cpu_data.x86, boot_cpu_data.x86_model);
- __mrst_cpu_chip = MRST_CPU_CHIP_PENWELL;
- }
-}
-
-/* MID systems don't have i8042 controller */
-static int mrst_i8042_detect(void)
-{
- return 0;
-}
-
-/*
- * Moorestown does not have external NMI source nor port 0x61 to report
- * NMI status. The possible NMI sources are from pmu as a result of NMI
- * watchdog or lock debug. Reading io port 0x61 results in 0xff which
- * misled NMI handler.
- */
-static unsigned char mrst_get_nmi_reason(void)
-{
- return 0;
-}
-
-/*
- * Moorestown specific x86_init function overrides and early setup
- * calls.
- */
-void __init x86_mrst_early_setup(void)
-{
- x86_init.resources.probe_roms = x86_init_noop;
- x86_init.resources.reserve_resources = x86_init_noop;
-
- x86_init.timers.timer_init = mrst_time_init;
- x86_init.timers.setup_percpu_clockev = x86_init_noop;
-
- x86_init.irqs.pre_vector_init = x86_init_noop;
-
- x86_init.oem.arch_setup = mrst_arch_setup;
-
- x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock;
-
- x86_platform.calibrate_tsc = mrst_calibrate_tsc;
- x86_platform.i8042_detect = mrst_i8042_detect;
- x86_init.timers.wallclock_init = mrst_rtc_init;
- x86_platform.get_nmi_reason = mrst_get_nmi_reason;
-
- x86_init.pci.init = pci_mrst_init;
- x86_init.pci.fixup_irqs = x86_init_noop;
-
- legacy_pic = &null_legacy_pic;
-
- /* Moorestown specific power_off/restart method */
- pm_power_off = mrst_power_off;
- machine_ops.emergency_restart = mrst_reboot;
-
- /* 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;
- set_bit(MP_BUS_ISA, mp_bus_not_pci);
-}
-
-/*
- * if user does not want to use per CPU apb timer, just give it a lower rating
- * than local apic timer and skip the late per cpu timer init.
- */
-static inline int __init setup_x86_mrst_timer(char *arg)
-{
- if (!arg)
- return -EINVAL;
-
- if (strcmp("apbt_only", arg) == 0)
- mrst_timer_options = MRST_TIMER_APBT_ONLY;
- else if (strcmp("lapic_and_apbt", arg) == 0)
- mrst_timer_options = MRST_TIMER_LAPIC_APBT;
- else {
- pr_warning("X86 MRST timer option %s not recognised"
- " use x86_mrst_timer=apbt_only or lapic_and_apbt\n",
- arg);
- return -EINVAL;
- }
- return 0;
-}
-__setup("x86_mrst_timer=", setup_x86_mrst_timer);
-
-/*
- * Parsing GPIO table first, since the DEVS table will need this table
- * to map the pin name to the actual pin.
- */
-static struct sfi_gpio_table_entry *gpio_table;
-static int gpio_num_entry;
-
-static int __init sfi_parse_gpio(struct sfi_table_header *table)
-{
- struct sfi_table_simple *sb;
- struct sfi_gpio_table_entry *pentry;
- int num, i;
-
- if (gpio_table)
- return 0;
- sb = (struct sfi_table_simple *)table;
- num = SFI_GET_NUM_ENTRIES(sb, struct sfi_gpio_table_entry);
- pentry = (struct sfi_gpio_table_entry *)sb->pentry;
-
- gpio_table = kmalloc(num * sizeof(*pentry), GFP_KERNEL);
- if (!gpio_table)
- return -1;
- memcpy(gpio_table, pentry, num * sizeof(*pentry));
- gpio_num_entry = num;
-
- pr_debug("GPIO pin info:\n");
- for (i = 0; i < num; i++, pentry++)
- pr_debug("info[%2d]: controller = %16.16s, pin_name = %16.16s,"
- " pin = %d\n", i,
- pentry->controller_name,
- pentry->pin_name,
- pentry->pin_no);
- return 0;
-}
-
-static int get_gpio_by_name(const char *name)
-{
- struct sfi_gpio_table_entry *pentry = gpio_table;
- int i;
-
- if (!pentry)
- return -1;
- for (i = 0; i < gpio_num_entry; i++, pentry++) {
- if (!strncmp(name, pentry->pin_name, SFI_NAME_LEN))
- return pentry->pin_no;
- }
- return -1;
-}
-
-/*
- * Here defines the array of devices platform data that IAFW would export
- * through SFI "DEVS" table, we use name and type to match the device and
- * its platform data.
- */
-struct devs_id {
- char name[SFI_NAME_LEN + 1];
- u8 type;
- u8 delay;
- void *(*get_platform_data)(void *info);
-};
-
-/* the offset for the mapping of global gpio pin to irq */
-#define MRST_IRQ_OFFSET 0x100
-
-static void __init *pmic_gpio_platform_data(void *info)
-{
- static struct intel_pmic_gpio_platform_data pmic_gpio_pdata;
- int gpio_base = get_gpio_by_name("pmic_gpio_base");
-
- if (gpio_base == -1)
- gpio_base = 64;
- pmic_gpio_pdata.gpio_base = gpio_base;
- pmic_gpio_pdata.irq_base = gpio_base + MRST_IRQ_OFFSET;
- pmic_gpio_pdata.gpiointr = 0xffffeff8;
-
- return &pmic_gpio_pdata;
-}
-
-static void __init *max3111_platform_data(void *info)
-{
- struct spi_board_info *spi_info = info;
- int intr = get_gpio_by_name("max3111_int");
-
- spi_info->mode = SPI_MODE_0;
- if (intr == -1)
- return NULL;
- spi_info->irq = intr + MRST_IRQ_OFFSET;
- return NULL;
-}
-
-/* we have multiple max7315 on the board ... */
-#define MAX7315_NUM 2
-static void __init *max7315_platform_data(void *info)
-{
- static struct pca953x_platform_data max7315_pdata[MAX7315_NUM];
- static int nr;
- struct pca953x_platform_data *max7315 = &max7315_pdata[nr];
- struct i2c_board_info *i2c_info = info;
- int gpio_base, intr;
- char base_pin_name[SFI_NAME_LEN + 1];
- char intr_pin_name[SFI_NAME_LEN + 1];
-
- if (nr == MAX7315_NUM) {
- pr_err("too many max7315s, we only support %d\n",
- MAX7315_NUM);
- return NULL;
- }
- /* we have several max7315 on the board, we only need load several
- * instances of the same pca953x driver to cover them
- */
- strcpy(i2c_info->type, "max7315");
- if (nr++) {
- sprintf(base_pin_name, "max7315_%d_base", nr);
- sprintf(intr_pin_name, "max7315_%d_int", nr);
- } else {
- strcpy(base_pin_name, "max7315_base");
- strcpy(intr_pin_name, "max7315_int");
- }
-
- gpio_base = get_gpio_by_name(base_pin_name);
- intr = get_gpio_by_name(intr_pin_name);
-
- if (gpio_base == -1)
- return NULL;
- max7315->gpio_base = gpio_base;
- if (intr != -1) {
- i2c_info->irq = intr + MRST_IRQ_OFFSET;
- max7315->irq_base = gpio_base + MRST_IRQ_OFFSET;
- } else {
- i2c_info->irq = -1;
- max7315->irq_base = -1;
- }
- return max7315;
-}
-
-static void *tca6416_platform_data(void *info)
-{
- static struct pca953x_platform_data tca6416;
- struct i2c_board_info *i2c_info = info;
- int gpio_base, intr;
- char base_pin_name[SFI_NAME_LEN + 1];
- char intr_pin_name[SFI_NAME_LEN + 1];
-
- strcpy(i2c_info->type, "tca6416");
- strcpy(base_pin_name, "tca6416_base");
- strcpy(intr_pin_name, "tca6416_int");
-
- gpio_base = get_gpio_by_name(base_pin_name);
- intr = get_gpio_by_name(intr_pin_name);
-
- if (gpio_base == -1)
- return NULL;
- tca6416.gpio_base = gpio_base;
- if (intr != -1) {
- i2c_info->irq = intr + MRST_IRQ_OFFSET;
- tca6416.irq_base = gpio_base + MRST_IRQ_OFFSET;
- } else {
- i2c_info->irq = -1;
- tca6416.irq_base = -1;
- }
- return &tca6416;
-}
-
-static void *mpu3050_platform_data(void *info)
-{
- struct i2c_board_info *i2c_info = info;
- int intr = get_gpio_by_name("mpu3050_int");
-
- if (intr == -1)
- return NULL;
-
- i2c_info->irq = intr + MRST_IRQ_OFFSET;
- return NULL;
-}
-
-static void __init *emc1403_platform_data(void *info)
-{
- static short intr2nd_pdata;
- struct i2c_board_info *i2c_info = info;
- int intr = get_gpio_by_name("thermal_int");
- int intr2nd = get_gpio_by_name("thermal_alert");
-
- if (intr == -1 || intr2nd == -1)
- return NULL;
-
- i2c_info->irq = intr + MRST_IRQ_OFFSET;
- intr2nd_pdata = intr2nd + MRST_IRQ_OFFSET;
-
- return &intr2nd_pdata;
-}
-
-static void __init *lis331dl_platform_data(void *info)
-{
- static short intr2nd_pdata;
- struct i2c_board_info *i2c_info = info;
- int intr = get_gpio_by_name("accel_int");
- int intr2nd = get_gpio_by_name("accel_2");
-
- if (intr == -1 || intr2nd == -1)
- return NULL;
-
- i2c_info->irq = intr + MRST_IRQ_OFFSET;
- intr2nd_pdata = intr2nd + MRST_IRQ_OFFSET;
-
- return &intr2nd_pdata;
-}
-
-static void __init *no_platform_data(void *info)
-{
- return NULL;
-}
-
-static struct resource msic_resources[] = {
- {
- .start = INTEL_MSIC_IRQ_PHYS_BASE,
- .end = INTEL_MSIC_IRQ_PHYS_BASE + 64 - 1,
- .flags = IORESOURCE_MEM,
- },
-};
-
-static struct intel_msic_platform_data msic_pdata;
-
-static struct platform_device msic_device = {
- .name = "intel_msic",
- .id = -1,
- .dev = {
- .platform_data = &msic_pdata,
- },
- .num_resources = ARRAY_SIZE(msic_resources),
- .resource = msic_resources,
-};
-
-static inline bool mrst_has_msic(void)
-{
- return mrst_identify_cpu() == MRST_CPU_CHIP_PENWELL;
-}
-
-static int msic_scu_status_change(struct notifier_block *nb,
- unsigned long code, void *data)
-{
- if (code == SCU_DOWN) {
- platform_device_unregister(&msic_device);
- return 0;
- }
-
- return platform_device_register(&msic_device);
-}
-
-static int __init msic_init(void)
-{
- static struct notifier_block msic_scu_notifier = {
- .notifier_call = msic_scu_status_change,
- };
-
- /*
- * We need to be sure that the SCU IPC is ready before MSIC device
- * can be registered.
- */
- if (mrst_has_msic())
- intel_scu_notifier_add(&msic_scu_notifier);
-
- return 0;
-}
-arch_initcall(msic_init);
-
-/*
- * msic_generic_platform_data - sets generic platform data for the block
- * @info: pointer to the SFI device table entry for this block
- * @block: MSIC block
- *
- * Function sets IRQ number from the SFI table entry for given device to
- * the MSIC platform data.
- */
-static void *msic_generic_platform_data(void *info, enum intel_msic_block block)
-{
- struct sfi_device_table_entry *entry = info;
-
- BUG_ON(block < 0 || block >= INTEL_MSIC_BLOCK_LAST);
- msic_pdata.irq[block] = entry->irq;
-
- return no_platform_data(info);
-}
-
-static void *msic_battery_platform_data(void *info)
-{
- return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_BATTERY);
-}
-
-static void *msic_gpio_platform_data(void *info)
-{
- static struct intel_msic_gpio_pdata pdata;
- int gpio = get_gpio_by_name("msic_gpio_base");
-
- if (gpio < 0)
- return NULL;
-
- pdata.gpio_base = gpio;
- msic_pdata.gpio = &pdata;
-
- return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_GPIO);
-}
-
-static void *msic_audio_platform_data(void *info)
-{
- struct platform_device *pdev;
-
- pdev = platform_device_register_simple("sst-platform", -1, NULL, 0);
- if (IS_ERR(pdev)) {
- pr_err("failed to create audio platform device\n");
- return NULL;
- }
-
- return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_AUDIO);
-}
-
-static void *msic_power_btn_platform_data(void *info)
-{
- return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_POWER_BTN);
-}
-
-static void *msic_ocd_platform_data(void *info)
-{
- static struct intel_msic_ocd_pdata pdata;
- int gpio = get_gpio_by_name("ocd_gpio");
-
- if (gpio < 0)
- return NULL;
-
- pdata.gpio = gpio;
- msic_pdata.ocd = &pdata;
-
- return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_OCD);
-}
-
-static void *msic_thermal_platform_data(void *info)
-{
- return msic_generic_platform_data(info, INTEL_MSIC_BLOCK_THERMAL);
-}
-
-/* tc35876x DSI-LVDS bridge chip and panel platform data */
-static void *tc35876x_platform_data(void *data)
-{
- static struct tc35876x_platform_data pdata;
-
- /* gpio pins set to -1 will not be used by the driver */
- pdata.gpio_bridge_reset = get_gpio_by_name("LCMB_RXEN");
- pdata.gpio_panel_bl_en = get_gpio_by_name("6S6P_BL_EN");
- pdata.gpio_panel_vadd = get_gpio_by_name("EN_VREG_LCD_V3P3");
-
- return &pdata;
-}
-
-static const struct devs_id __initconst device_ids[] = {
- {"bma023", SFI_DEV_TYPE_I2C, 1, &no_platform_data},
- {"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data},
- {"pmic_gpio", SFI_DEV_TYPE_IPC, 1, &pmic_gpio_platform_data},
- {"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data},
- {"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
- {"i2c_max7315_2", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
- {"tca6416", SFI_DEV_TYPE_I2C, 1, &tca6416_platform_data},
- {"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data},
- {"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data},
- {"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
- {"mpu3050", SFI_DEV_TYPE_I2C, 1, &mpu3050_platform_data},
- {"i2c_disp_brig", SFI_DEV_TYPE_I2C, 0, &tc35876x_platform_data},
-
- /* MSIC subdevices */
- {"msic_battery", SFI_DEV_TYPE_IPC, 1, &msic_battery_platform_data},
- {"msic_gpio", SFI_DEV_TYPE_IPC, 1, &msic_gpio_platform_data},
- {"msic_audio", SFI_DEV_TYPE_IPC, 1, &msic_audio_platform_data},
- {"msic_power_btn", SFI_DEV_TYPE_IPC, 1, &msic_power_btn_platform_data},
- {"msic_ocd", SFI_DEV_TYPE_IPC, 1, &msic_ocd_platform_data},
- {"msic_thermal", SFI_DEV_TYPE_IPC, 1, &msic_thermal_platform_data},
-
- {},
-};
-
-#define MAX_IPCDEVS 24
-static struct platform_device *ipc_devs[MAX_IPCDEVS];
-static int ipc_next_dev;
-
-#define MAX_SCU_SPI 24
-static struct spi_board_info *spi_devs[MAX_SCU_SPI];
-static int spi_next_dev;
-
-#define MAX_SCU_I2C 24
-static struct i2c_board_info *i2c_devs[MAX_SCU_I2C];
-static int i2c_bus[MAX_SCU_I2C];
-static int i2c_next_dev;
-
-static void __init intel_scu_device_register(struct platform_device *pdev)
-{
- if(ipc_next_dev == MAX_IPCDEVS)
- pr_err("too many SCU IPC devices");
- else
- ipc_devs[ipc_next_dev++] = pdev;
-}
-
-static void __init intel_scu_spi_device_register(struct spi_board_info *sdev)
-{
- struct spi_board_info *new_dev;
-
- if (spi_next_dev == MAX_SCU_SPI) {
- pr_err("too many SCU SPI devices");
- return;
- }
-
- new_dev = kzalloc(sizeof(*sdev), GFP_KERNEL);
- if (!new_dev) {
- pr_err("failed to alloc mem for delayed spi dev %s\n",
- sdev->modalias);
- return;
- }
- memcpy(new_dev, sdev, sizeof(*sdev));
-
- spi_devs[spi_next_dev++] = new_dev;
-}
-
-static void __init intel_scu_i2c_device_register(int bus,
- struct i2c_board_info *idev)
-{
- struct i2c_board_info *new_dev;
-
- if (i2c_next_dev == MAX_SCU_I2C) {
- pr_err("too many SCU I2C devices");
- return;
- }
-
- new_dev = kzalloc(sizeof(*idev), GFP_KERNEL);
- if (!new_dev) {
- pr_err("failed to alloc mem for delayed i2c dev %s\n",
- idev->type);
- return;
- }
- memcpy(new_dev, idev, sizeof(*idev));
-
- i2c_bus[i2c_next_dev] = bus;
- i2c_devs[i2c_next_dev++] = new_dev;
-}
-
-BLOCKING_NOTIFIER_HEAD(intel_scu_notifier);
-EXPORT_SYMBOL_GPL(intel_scu_notifier);
-
-/* Called by IPC driver */
-void intel_scu_devices_create(void)
-{
- int i;
-
- for (i = 0; i < ipc_next_dev; i++)
- platform_device_add(ipc_devs[i]);
-
- for (i = 0; i < spi_next_dev; i++)
- spi_register_board_info(spi_devs[i], 1);
-
- for (i = 0; i < i2c_next_dev; i++) {
- struct i2c_adapter *adapter;
- struct i2c_client *client;
-
- adapter = i2c_get_adapter(i2c_bus[i]);
- if (adapter) {
- client = i2c_new_device(adapter, i2c_devs[i]);
- if (!client)
- pr_err("can't create i2c device %s\n",
- i2c_devs[i]->type);
- } else
- i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1);
- }
- intel_scu_notifier_post(SCU_AVAILABLE, NULL);
-}
-EXPORT_SYMBOL_GPL(intel_scu_devices_create);
-
-/* Called by IPC driver */
-void intel_scu_devices_destroy(void)
-{
- int i;
-
- intel_scu_notifier_post(SCU_DOWN, NULL);
-
- for (i = 0; i < ipc_next_dev; i++)
- platform_device_del(ipc_devs[i]);
-}
-EXPORT_SYMBOL_GPL(intel_scu_devices_destroy);
-
-static void __init install_irq_resource(struct platform_device *pdev, int irq)
-{
- /* Single threaded */
- static struct resource __initdata res = {
- .name = "IRQ",
- .flags = IORESOURCE_IRQ,
- };
- res.start = irq;
- platform_device_add_resources(pdev, &res, 1);
-}
-
-static void __init sfi_handle_ipc_dev(struct sfi_device_table_entry *entry)
-{
- const struct devs_id *dev = device_ids;
- struct platform_device *pdev;
- void *pdata = NULL;
-
- while (dev->name[0]) {
- if (dev->type == SFI_DEV_TYPE_IPC &&
- !strncmp(dev->name, entry->name, SFI_NAME_LEN)) {
- pdata = dev->get_platform_data(entry);
- break;
- }
- dev++;
- }
-
- /*
- * On Medfield the platform device creation is handled by the MSIC
- * MFD driver so we don't need to do it here.
- */
- if (mrst_has_msic())
- return;
-
- pdev = platform_device_alloc(entry->name, 0);
- if (pdev == NULL) {
- pr_err("out of memory for SFI platform device '%s'.\n",
- entry->name);
- return;
- }
- install_irq_resource(pdev, entry->irq);
-
- pdev->dev.platform_data = pdata;
- intel_scu_device_register(pdev);
-}
-
-static void __init sfi_handle_spi_dev(struct spi_board_info *spi_info)
-{
- const struct devs_id *dev = device_ids;
- void *pdata = NULL;
-
- while (dev->name[0]) {
- if (dev->type == SFI_DEV_TYPE_SPI &&
- !strncmp(dev->name, spi_info->modalias, SFI_NAME_LEN)) {
- pdata = dev->get_platform_data(spi_info);
- break;
- }
- dev++;
- }
- spi_info->platform_data = pdata;
- if (dev->delay)
- intel_scu_spi_device_register(spi_info);
- else
- spi_register_board_info(spi_info, 1);
-}
-
-static void __init sfi_handle_i2c_dev(int bus, struct i2c_board_info *i2c_info)
-{
- const struct devs_id *dev = device_ids;
- void *pdata = NULL;
-
- while (dev->name[0]) {
- if (dev->type == SFI_DEV_TYPE_I2C &&
- !strncmp(dev->name, i2c_info->type, SFI_NAME_LEN)) {
- pdata = dev->get_platform_data(i2c_info);
- break;
- }
- dev++;
- }
- i2c_info->platform_data = pdata;
-
- if (dev->delay)
- intel_scu_i2c_device_register(bus, i2c_info);
- else
- i2c_register_board_info(bus, i2c_info, 1);
- }
-
-
-static int __init sfi_parse_devs(struct sfi_table_header *table)
-{
- struct sfi_table_simple *sb;
- struct sfi_device_table_entry *pentry;
- struct spi_board_info spi_info;
- struct i2c_board_info i2c_info;
- int num, i, bus;
- int ioapic;
- struct io_apic_irq_attr irq_attr;
-
- sb = (struct sfi_table_simple *)table;
- num = SFI_GET_NUM_ENTRIES(sb, struct sfi_device_table_entry);
- pentry = (struct sfi_device_table_entry *)sb->pentry;
-
- for (i = 0; i < num; i++, pentry++) {
- int irq = pentry->irq;
-
- if (irq != (u8)0xff) { /* native RTE case */
- /* these SPI2 devices are not exposed to system as PCI
- * devices, but they have separate RTE entry in IOAPIC
- * so we have to enable them one by one here
- */
- ioapic = mp_find_ioapic(irq);
- irq_attr.ioapic = ioapic;
- irq_attr.ioapic_pin = irq;
- irq_attr.trigger = 1;
- irq_attr.polarity = 1;
- io_apic_set_pci_routing(NULL, irq, &irq_attr);
- } else
- irq = 0; /* No irq */
-
- switch (pentry->type) {
- case SFI_DEV_TYPE_IPC:
- pr_debug("info[%2d]: IPC bus, name = %16.16s, "
- "irq = 0x%2x\n", i, pentry->name, pentry->irq);
- sfi_handle_ipc_dev(pentry);
- break;
- case SFI_DEV_TYPE_SPI:
- memset(&spi_info, 0, sizeof(spi_info));
- strncpy(spi_info.modalias, pentry->name, SFI_NAME_LEN);
- spi_info.irq = irq;
- spi_info.bus_num = pentry->host_num;
- spi_info.chip_select = pentry->addr;
- spi_info.max_speed_hz = pentry->max_freq;
- pr_debug("info[%2d]: SPI bus = %d, name = %16.16s, "
- "irq = 0x%2x, max_freq = %d, cs = %d\n", i,
- spi_info.bus_num,
- spi_info.modalias,
- spi_info.irq,
- spi_info.max_speed_hz,
- spi_info.chip_select);
- sfi_handle_spi_dev(&spi_info);
- break;
- case SFI_DEV_TYPE_I2C:
- memset(&i2c_info, 0, sizeof(i2c_info));
- bus = pentry->host_num;
- strncpy(i2c_info.type, pentry->name, SFI_NAME_LEN);
- i2c_info.irq = irq;
- i2c_info.addr = pentry->addr;
- pr_debug("info[%2d]: I2C bus = %d, name = %16.16s, "
- "irq = 0x%2x, addr = 0x%x\n", i, bus,
- i2c_info.type,
- i2c_info.irq,
- i2c_info.addr);
- sfi_handle_i2c_dev(bus, &i2c_info);
- break;
- case SFI_DEV_TYPE_UART:
- case SFI_DEV_TYPE_HSI:
- default:
- ;
- }
- }
- return 0;
-}
-
-static int __init mrst_platform_init(void)
-{
- sfi_table_parse(SFI_SIG_GPIO, NULL, NULL, sfi_parse_gpio);
- sfi_table_parse(SFI_SIG_DEVS, NULL, NULL, sfi_parse_devs);
- return 0;
-}
-arch_initcall(mrst_platform_init);
-
-/*
- * we will search these buttons in SFI GPIO table (by name)
- * and register them dynamically. Please add all possible
- * buttons here, we will shrink them if no GPIO found.
- */
-static struct gpio_keys_button gpio_button[] = {
- {KEY_POWER, -1, 1, "power_btn", EV_KEY, 0, 3000},
- {KEY_PROG1, -1, 1, "prog_btn1", EV_KEY, 0, 20},
- {KEY_PROG2, -1, 1, "prog_btn2", EV_KEY, 0, 20},
- {SW_LID, -1, 1, "lid_switch", EV_SW, 0, 20},
- {KEY_VOLUMEUP, -1, 1, "vol_up", EV_KEY, 0, 20},
- {KEY_VOLUMEDOWN, -1, 1, "vol_down", EV_KEY, 0, 20},
- {KEY_CAMERA, -1, 1, "camera_full", EV_KEY, 0, 20},
- {KEY_CAMERA_FOCUS, -1, 1, "camera_half", EV_KEY, 0, 20},
- {SW_KEYPAD_SLIDE, -1, 1, "MagSw1", EV_SW, 0, 20},
- {SW_KEYPAD_SLIDE, -1, 1, "MagSw2", EV_SW, 0, 20},
-};
-
-static struct gpio_keys_platform_data mrst_gpio_keys = {
- .buttons = gpio_button,
- .rep = 1,
- .nbuttons = -1, /* will fill it after search */
-};
-
-static struct platform_device pb_device = {
- .name = "gpio-keys",
- .id = -1,
- .dev = {
- .platform_data = &mrst_gpio_keys,
- },
-};
-
-/*
- * Shrink the non-existent buttons, register the gpio button
- * device if there is some
- */
-static int __init pb_keys_init(void)
-{
- struct gpio_keys_button *gb = gpio_button;
- int i, num, good = 0;
-
- num = sizeof(gpio_button) / sizeof(struct gpio_keys_button);
- for (i = 0; i < num; i++) {
- gb[i].gpio = get_gpio_by_name(gb[i].desc);
- pr_debug("info[%2d]: name = %s, gpio = %d\n", i, gb[i].desc, gb[i].gpio);
- if (gb[i].gpio == -1)
- continue;
-
- if (i != good)
- gb[good] = gb[i];
- good++;
- }
-
- if (good) {
- mrst_gpio_keys.nbuttons = good;
- return platform_device_register(&pb_device);
- }
- return 0;
-}
-late_initcall(pb_keys_init);
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 1cf5b300305..424f4c97a44 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -25,10 +25,10 @@
#include <asm/cpu.h>
#ifdef CONFIG_X86_32
-unsigned long saved_context_ebx;
-unsigned long saved_context_esp, saved_context_ebp;
-unsigned long saved_context_esi, saved_context_edi;
-unsigned long saved_context_eflags;
+__visible unsigned long saved_context_ebx;
+__visible unsigned long saved_context_esp, saved_context_ebp;
+__visible unsigned long saved_context_esi, saved_context_edi;
+__visible unsigned long saved_context_eflags;
#endif
struct saved_context saved_context;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index a0fde91c16c..304fca20d96 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -20,26 +20,26 @@
#include <asm/suspend.h>
/* References to section boundaries */
-extern const void __nosave_begin, __nosave_end;
+extern __visible const void __nosave_begin, __nosave_end;
/* Defined in hibernate_asm_64.S */
-extern int restore_image(void);
+extern asmlinkage int restore_image(void);
/*
* Address to jump to in the last phase of restore in order to get to the image
* kernel's text (this value is passed in the image header).
*/
-unsigned long restore_jump_address;
+unsigned long restore_jump_address __visible;
/*
* Value of the cr3 register from before the hibernation (this value is passed
* in the image header).
*/
-unsigned long restore_cr3;
+unsigned long restore_cr3 __visible;
-pgd_t *temp_level4_pgt;
+pgd_t *temp_level4_pgt __visible;
-void *relocated_restore_code;
+void *relocated_restore_code __visible;
static void *alloc_pgt_page(void *context)
{
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index e6773dc8ac4..093a892026f 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -68,7 +68,7 @@ BEGIN {
lprefix1_expr = "\\((66|!F3)\\)"
lprefix2_expr = "\\(F3\\)"
- lprefix3_expr = "\\((F2|!F3)\\)"
+ lprefix3_expr = "\\((F2|!F3|66\\&F2)\\)"
lprefix_expr = "\\((66|F2|F3)\\)"
max_lprefix = 4
@@ -83,6 +83,8 @@ BEGIN {
prefix_num["Operand-Size"] = "INAT_PFX_OPNDSZ"
prefix_num["REPNE"] = "INAT_PFX_REPNE"
prefix_num["REP/REPE"] = "INAT_PFX_REPE"
+ prefix_num["XACQUIRE"] = "INAT_PFX_REPNE"
+ prefix_num["XRELEASE"] = "INAT_PFX_REPE"
prefix_num["LOCK"] = "INAT_PFX_LOCK"
prefix_num["SEG=CS"] = "INAT_PFX_CS"
prefix_num["SEG=DS"] = "INAT_PFX_DS"
diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c
index 9d34eddb517..96eb2bd2883 100644
--- a/arch/x86/um/os-Linux/prctl.c
+++ b/arch/x86/um/os-Linux/prctl.c
@@ -4,7 +4,7 @@
*/
#include <sys/ptrace.h>
-#include <linux/ptrace.h>
+#include <asm/ptrace.h>
int os_arch_prctl(int pid, int code, unsigned long *addr)
{
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index c74436e687b..72074d52840 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -85,15 +85,18 @@ static notrace cycle_t vread_pvclock(int *mode)
cycle_t ret;
u64 last;
u32 version;
- u32 migrate_count;
u8 flags;
unsigned cpu, cpu1;
/*
- * When looping to get a consistent (time-info, tsc) pair, we
- * also need to deal with the possibility we can switch vcpus,
- * so make sure we always re-fetch time-info for the current vcpu.
+ * Note: hypervisor must guarantee that:
+ * 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
+ * 2. that per-CPU pvclock time info is updated if the
+ * underlying CPU changes.
+ * 3. that version is increased whenever underlying CPU
+ * changes.
+ *
*/
do {
cpu = __getcpu() & VGETCPU_CPU_MASK;
@@ -104,8 +107,6 @@ static notrace cycle_t vread_pvclock(int *mode)
pvti = get_pvti(cpu);
- migrate_count = pvti->migrate_count;
-
version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
/*
@@ -117,8 +118,7 @@ static notrace cycle_t vread_pvclock(int *mode)
cpu1 = __getcpu() & VGETCPU_CPU_MASK;
} while (unlikely(cpu != cpu1 ||
(pvti->pvti.version & 1) ||
- pvti->pvti.version != version ||
- pvti->migrate_count != migrate_count));
+ pvti->pvti.version != version));
if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
*mode = VCLOCK_NONE;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 193097ef3d7..fa6ade76ef3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -427,8 +427,7 @@ static void __init xen_init_cpuid_mask(void)
if (!xen_initial_domain())
cpuid_leaf1_edx_mask &=
- ~((1 << X86_FEATURE_APIC) | /* disable local APIC */
- (1 << X86_FEATURE_ACPI)); /* disable ACPI */
+ ~((1 << X86_FEATURE_ACPI)); /* disable ACPI */
cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_X2APIC % 32));
@@ -735,8 +734,7 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
addr = (unsigned long)xen_int3;
else if (addr == (unsigned long)stack_segment)
addr = (unsigned long)xen_stack_segment;
- else if (addr == (unsigned long)double_fault ||
- addr == (unsigned long)nmi) {
+ else if (addr == (unsigned long)double_fault) {
/* Don't need to handle these */
return 0;
#ifdef CONFIG_X86_MCE
@@ -747,7 +745,12 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
*/
;
#endif
- } else {
+ } else if (addr == (unsigned long)nmi)
+ /*
+ * Use the native version as well.
+ */
+ ;
+ else {
/* Some other trap using IST? */
if (WARN_ON(val->ist != 0))
return 0;
@@ -1689,7 +1692,6 @@ static int xen_hvm_cpu_notify(struct notifier_block *self, unsigned long action,
case CPU_UP_PREPARE:
xen_vcpu_setup(cpu);
if (xen_have_vector_callback) {
- xen_init_lock_cpu(cpu);
if (xen_feature(XENFEAT_hvm_safe_pvclock))
xen_setup_timer(cpu);
}
@@ -1710,6 +1712,8 @@ static void __init xen_hvm_guest_init(void)
xen_hvm_init_shared_info();
+ xen_panic_handler_init();
+
if (xen_feature(XENFEAT_hvm_callback_vector))
xen_have_vector_callback = 1;
xen_hvm_smp_init();
@@ -1720,15 +1724,12 @@ static void __init xen_hvm_guest_init(void)
xen_hvm_init_mmu_ops();
}
-static bool __init xen_hvm_platform(void)
+static uint32_t __init xen_hvm_platform(void)
{
if (xen_pv_domain())
- return false;
-
- if (!xen_cpuid_base())
- return false;
+ return 0;
- return true;
+ return xen_cpuid_base();
}
bool xen_hvm_need_lapic(void)
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 01a4dc015ae..0da7f863056 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -47,23 +47,18 @@ static void xen_restore_fl(unsigned long flags)
/* convert from IF type flag */
flags = !(flags & X86_EFLAGS_IF);
- /* There's a one instruction preempt window here. We need to
- make sure we're don't switch CPUs between getting the vcpu
- pointer and updating the mask. */
+ /* See xen_irq_enable() for why preemption must be disabled. */
preempt_disable();
vcpu = this_cpu_read(xen_vcpu);
vcpu->evtchn_upcall_mask = flags;
- preempt_enable_no_resched();
-
- /* Doesn't matter if we get preempted here, because any
- pending event will get dealt with anyway. */
if (flags == 0) {
- preempt_check_resched();
barrier(); /* unmask then check (avoid races) */
if (unlikely(vcpu->evtchn_upcall_pending))
xen_force_evtchn_callback();
- }
+ preempt_enable();
+ } else
+ preempt_enable_no_resched();
}
PV_CALLEE_SAVE_REGS_THUNK(xen_restore_fl);
@@ -82,10 +77,12 @@ static void xen_irq_enable(void)
{
struct vcpu_info *vcpu;
- /* We don't need to worry about being preempted here, since
- either a) interrupts are disabled, so no preemption, or b)
- the caller is confused and is trying to re-enable interrupts
- on an indeterminate processor. */
+ /*
+ * We may be preempted as soon as vcpu->evtchn_upcall_mask is
+ * cleared, so disable preemption to ensure we check for
+ * events on the VCPU we are still running on.
+ */
+ preempt_disable();
vcpu = this_cpu_read(xen_vcpu);
vcpu->evtchn_upcall_mask = 0;
@@ -96,6 +93,8 @@ static void xen_irq_enable(void)
barrier(); /* unmask then check (avoid races) */
if (unlikely(vcpu->evtchn_upcall_pending))
xen_force_evtchn_callback();
+
+ preempt_enable();
}
PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 95fb2aa5927..a61c7d5811b 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -161,6 +161,7 @@
#include <asm/xen/page.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
+#include <xen/balloon.h>
#include <xen/grant_table.h>
#include "multicalls.h"
@@ -878,7 +879,6 @@ int m2p_add_override(unsigned long mfn, struct page *page,
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
- int ret = 0;
pfn = page_to_pfn(page);
if (!PageHighMem(page)) {
@@ -925,8 +925,8 @@ int m2p_add_override(unsigned long mfn, struct page *page,
* frontend pages while they are being shared with the backend,
* because mfn_to_pfn (that ends up being called by GUPF) will
* return the backend pfn rather than the frontend pfn. */
- ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
- if (ret == 0 && get_phys_to_machine(pfn) == mfn)
+ pfn = mfn_to_pfn_no_overrides(mfn);
+ if (get_phys_to_machine(pfn) == mfn)
set_phys_to_machine(pfn, FOREIGN_FRAME(mfn));
return 0;
@@ -941,7 +941,6 @@ int m2p_remove_override(struct page *page,
unsigned long uninitialized_var(address);
unsigned level;
pte_t *ptep = NULL;
- int ret = 0;
pfn = page_to_pfn(page);
mfn = get_phys_to_machine(pfn);
@@ -967,7 +966,10 @@ int m2p_remove_override(struct page *page,
if (kmap_op != NULL) {
if (!PageHighMem(page)) {
struct multicall_space mcs;
- struct gnttab_unmap_grant_ref *unmap_op;
+ struct gnttab_unmap_and_replace *unmap_op;
+ struct page *scratch_page = get_balloon_scratch_page();
+ unsigned long scratch_page_address = (unsigned long)
+ __va(page_to_pfn(scratch_page) << PAGE_SHIFT);
/*
* It might be that we queued all the m2p grant table
@@ -986,25 +988,31 @@ int m2p_remove_override(struct page *page,
printk(KERN_WARNING "m2p_remove_override: "
"pfn %lx mfn %lx, failed to modify kernel mappings",
pfn, mfn);
+ put_balloon_scratch_page();
return -1;
}
- mcs = xen_mc_entry(
- sizeof(struct gnttab_unmap_grant_ref));
+ xen_mc_batch();
+
+ mcs = __xen_mc_entry(
+ sizeof(struct gnttab_unmap_and_replace));
unmap_op = mcs.args;
unmap_op->host_addr = kmap_op->host_addr;
+ unmap_op->new_addr = scratch_page_address;
unmap_op->handle = kmap_op->handle;
- unmap_op->dev_bus_addr = 0;
MULTI_grant_table_op(mcs.mc,
- GNTTABOP_unmap_grant_ref, unmap_op, 1);
+ GNTTABOP_unmap_and_replace, unmap_op, 1);
+
+ mcs = __xen_mc_entry(0);
+ MULTI_update_va_mapping(mcs.mc, scratch_page_address,
+ pfn_pte(page_to_pfn(scratch_page),
+ PAGE_KERNEL_RO), 0);
xen_mc_issue(PARAVIRT_LAZY_MMU);
- set_pte_at(&init_mm, address, ptep,
- pfn_pte(pfn, PAGE_KERNEL));
- __flush_tlb_single(address);
kmap_op->host_addr = 0;
+ put_balloon_scratch_page();
}
}
@@ -1019,8 +1027,8 @@ int m2p_remove_override(struct page *page,
* the original pfn causes mfn_to_pfn(mfn) to return the frontend
* pfn again. */
mfn &= ~FOREIGN_FRAME_BIT;
- ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
- if (ret == 0 && get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
+ pfn = mfn_to_pfn_no_overrides(mfn);
+ if (get_phys_to_machine(pfn) == FOREIGN_FRAME(mfn) &&
m2p_find_override(mfn) == NULL)
set_phys_to_machine(pfn, mfn);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 8f3eea6b80c..09f3059cb00 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -33,6 +33,9 @@
/* These are code, but not functions. Defined in entry.S */
extern const char xen_hypervisor_callback[];
extern const char xen_failsafe_callback[];
+#ifdef CONFIG_X86_64
+extern const char nmi[];
+#endif
extern void xen_sysenter_target(void);
extern void xen_syscall_target(void);
extern void xen_syscall32_target(void);
@@ -215,13 +218,19 @@ static void __init xen_set_identity_and_release_chunk(
unsigned long pfn;
/*
- * If the PFNs are currently mapped, the VA mapping also needs
- * to be updated to be 1:1.
+ * If the PFNs are currently mapped, clear the mappings
+ * (except for the ISA region which must be 1:1 mapped) to
+ * release the refcounts (in Xen) on the original frames.
*/
- for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++)
+ for (pfn = start_pfn; pfn <= max_pfn_mapped && pfn < end_pfn; pfn++) {
+ pte_t pte = __pte_ma(0);
+
+ if (pfn < PFN_UP(ISA_END_ADDRESS))
+ pte = mfn_pte(pfn, PAGE_KERNEL_IO);
+
(void)HYPERVISOR_update_va_mapping(
- (unsigned long)__va(pfn << PAGE_SHIFT),
- mfn_pte(pfn, PAGE_KERNEL_IO), 0);
+ (unsigned long)__va(pfn << PAGE_SHIFT), pte, 0);
+ }
if (start_pfn < nr_pages)
*released += xen_release_chunk(
@@ -547,7 +556,13 @@ void xen_enable_syscall(void)
}
#endif /* CONFIG_X86_64 */
}
-
+void __cpuinit xen_enable_nmi(void)
+{
+#ifdef CONFIG_X86_64
+ if (register_callback(CALLBACKTYPE_nmi, nmi))
+ BUG();
+#endif
+}
void __init xen_arch_setup(void)
{
xen_panic_handler_init();
@@ -565,7 +580,7 @@ void __init xen_arch_setup(void)
xen_enable_sysenter();
xen_enable_syscall();
-
+ xen_enable_nmi();
#ifdef CONFIG_ACPI
if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
printk(KERN_INFO "ACPI in unprivileged domain disabled\n");
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index b81c88e51da..31d04758b76 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -273,12 +273,30 @@ static void __init xen_smp_prepare_boot_cpu(void)
BUG_ON(smp_processor_id() != 0);
native_smp_prepare_boot_cpu();
- /* We've switched to the "real" per-cpu gdt, so make sure the
- old memory can be recycled */
- make_lowmem_page_readwrite(xen_initial_gdt);
+ if (xen_pv_domain()) {
+ /* We've switched to the "real" per-cpu gdt, so make sure the
+ old memory can be recycled */
+ make_lowmem_page_readwrite(xen_initial_gdt);
- xen_filter_cpu_maps();
- xen_setup_vcpu_info_placement();
+#ifdef CONFIG_X86_32
+ /*
+ * Xen starts us with XEN_FLAT_RING1_DS, but linux code
+ * expects __USER_DS
+ */
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+#endif
+
+ xen_filter_cpu_maps();
+ xen_setup_vcpu_info_placement();
+ }
+ /*
+ * The alternative logic (which patches the unlock/lock) runs before
+ * the smp bootup up code is activated. Hence we need to set this up
+ * the core kernel is being patched. Otherwise we will have only
+ * modules patched but not core code.
+ */
+ xen_init_spinlocks();
}
static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
@@ -572,6 +590,12 @@ static inline int xen_map_vector(int vector)
case IRQ_WORK_VECTOR:
xen_vector = XEN_IRQ_WORK_VECTOR;
break;
+#ifdef CONFIG_X86_64
+ case NMI_VECTOR:
+ case APIC_DM_NMI: /* Some use that instead of NMI_VECTOR */
+ xen_vector = XEN_NMI_VECTOR;
+ break;
+#endif
default:
xen_vector = -1;
printk(KERN_ERR "xen: vector 0x%x is not implemented\n",
@@ -680,7 +704,6 @@ void __init xen_smp_init(void)
{
smp_ops = xen_smp_ops;
xen_fill_possible_map();
- xen_init_spinlocks();
}
static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
@@ -703,6 +726,15 @@ static int xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
WARN_ON(rc);
if (!rc)
rc = native_cpu_up(cpu, tidle);
+
+ /*
+ * We must initialize the slowpath CPU kicker _after_ the native
+ * path has executed. If we initialized it before none of the
+ * unlocker IPI kicks would reach the booting CPU as the booting
+ * CPU had not set itself 'online' in cpu_online_mask. That mask
+ * is checked when IPIs are sent (on HVM at least).
+ */
+ xen_init_lock_cpu(cpu);
return rc;
}
@@ -722,4 +754,5 @@ void __init xen_hvm_smp_init(void)
smp_ops.cpu_die = xen_hvm_cpu_die;
smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
+ smp_ops.smp_prepare_boot_cpu = xen_smp_prepare_boot_cpu;
}
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cf3caee356b..be6b8607895 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -17,45 +17,44 @@
#include "xen-ops.h"
#include "debugfs.h"
-#ifdef CONFIG_XEN_DEBUG_FS
-static struct xen_spinlock_stats
-{
- u64 taken;
- u32 taken_slow;
- u32 taken_slow_nested;
- u32 taken_slow_pickup;
- u32 taken_slow_spurious;
- u32 taken_slow_irqenable;
+enum xen_contention_stat {
+ TAKEN_SLOW,
+ TAKEN_SLOW_PICKUP,
+ TAKEN_SLOW_SPURIOUS,
+ RELEASED_SLOW,
+ RELEASED_SLOW_KICKED,
+ NR_CONTENTION_STATS
+};
- u64 released;
- u32 released_slow;
- u32 released_slow_kicked;
+#ifdef CONFIG_XEN_DEBUG_FS
#define HISTO_BUCKETS 30
- u32 histo_spin_total[HISTO_BUCKETS+1];
- u32 histo_spin_spinning[HISTO_BUCKETS+1];
+static struct xen_spinlock_stats
+{
+ u32 contention_stats[NR_CONTENTION_STATS];
u32 histo_spin_blocked[HISTO_BUCKETS+1];
-
- u64 time_total;
- u64 time_spinning;
u64 time_blocked;
} spinlock_stats;
static u8 zero_stats;
-static unsigned lock_timeout = 1 << 10;
-#define TIMEOUT lock_timeout
-
static inline void check_zero(void)
{
- if (unlikely(zero_stats)) {
- memset(&spinlock_stats, 0, sizeof(spinlock_stats));
- zero_stats = 0;
+ u8 ret;
+ u8 old = ACCESS_ONCE(zero_stats);
+ if (unlikely(old)) {
+ ret = cmpxchg(&zero_stats, old, 0);
+ /* This ensures only one fellow resets the stat */
+ if (ret == old)
+ memset(&spinlock_stats, 0, sizeof(spinlock_stats));
}
}
-#define ADD_STATS(elem, val) \
- do { check_zero(); spinlock_stats.elem += (val); } while(0)
+static inline void add_stats(enum xen_contention_stat var, u32 val)
+{
+ check_zero();
+ spinlock_stats.contention_stats[var] += val;
+}
static inline u64 spin_time_start(void)
{
@@ -74,22 +73,6 @@ static void __spin_time_accum(u64 delta, u32 *array)
array[HISTO_BUCKETS]++;
}
-static inline void spin_time_accum_spinning(u64 start)
-{
- u32 delta = xen_clocksource_read() - start;
-
- __spin_time_accum(delta, spinlock_stats.histo_spin_spinning);
- spinlock_stats.time_spinning += delta;
-}
-
-static inline void spin_time_accum_total(u64 start)
-{
- u32 delta = xen_clocksource_read() - start;
-
- __spin_time_accum(delta, spinlock_stats.histo_spin_total);
- spinlock_stats.time_total += delta;
-}
-
static inline void spin_time_accum_blocked(u64 start)
{
u32 delta = xen_clocksource_read() - start;
@@ -98,263 +81,138 @@ static inline void spin_time_accum_blocked(u64 start)
spinlock_stats.time_blocked += delta;
}
#else /* !CONFIG_XEN_DEBUG_FS */
-#define TIMEOUT (1 << 10)
-#define ADD_STATS(elem, val) do { (void)(val); } while(0)
+static inline void add_stats(enum xen_contention_stat var, u32 val)
+{
+}
static inline u64 spin_time_start(void)
{
return 0;
}
-static inline void spin_time_accum_total(u64 start)
-{
-}
-static inline void spin_time_accum_spinning(u64 start)
-{
-}
static inline void spin_time_accum_blocked(u64 start)
{
}
#endif /* CONFIG_XEN_DEBUG_FS */
-/*
- * Size struct xen_spinlock so it's the same as arch_spinlock_t.
- */
-#if NR_CPUS < 256
-typedef u8 xen_spinners_t;
-# define inc_spinners(xl) \
- asm(LOCK_PREFIX " incb %0" : "+m" ((xl)->spinners) : : "memory");
-# define dec_spinners(xl) \
- asm(LOCK_PREFIX " decb %0" : "+m" ((xl)->spinners) : : "memory");
-#else
-typedef u16 xen_spinners_t;
-# define inc_spinners(xl) \
- asm(LOCK_PREFIX " incw %0" : "+m" ((xl)->spinners) : : "memory");
-# define dec_spinners(xl) \
- asm(LOCK_PREFIX " decw %0" : "+m" ((xl)->spinners) : : "memory");
-#endif
-
-struct xen_spinlock {
- unsigned char lock; /* 0 -> free; 1 -> locked */
- xen_spinners_t spinners; /* count of waiting cpus */
+struct xen_lock_waiting {
+ struct arch_spinlock *lock;
+ __ticket_t want;
};
-static int xen_spin_is_locked(struct arch_spinlock *lock)
-{
- struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-
- return xl->lock != 0;
-}
-
-static int xen_spin_is_contended(struct arch_spinlock *lock)
-{
- struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-
- /* Not strictly true; this is only the count of contended
- lock-takers entering the slow path. */
- return xl->spinners != 0;
-}
-
-static int xen_spin_trylock(struct arch_spinlock *lock)
-{
- struct xen_spinlock *xl = (struct xen_spinlock *)lock;
- u8 old = 1;
-
- asm("xchgb %b0,%1"
- : "+q" (old), "+m" (xl->lock) : : "memory");
-
- return old == 0;
-}
-
-static DEFINE_PER_CPU(char *, irq_name);
static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
-static DEFINE_PER_CPU(struct xen_spinlock *, lock_spinners);
-
-/*
- * Mark a cpu as interested in a lock. Returns the CPU's previous
- * lock of interest, in case we got preempted by an interrupt.
- */
-static inline struct xen_spinlock *spinning_lock(struct xen_spinlock *xl)
-{
- struct xen_spinlock *prev;
-
- prev = __this_cpu_read(lock_spinners);
- __this_cpu_write(lock_spinners, xl);
-
- wmb(); /* set lock of interest before count */
-
- inc_spinners(xl);
-
- return prev;
-}
-
-/*
- * Mark a cpu as no longer interested in a lock. Restores previous
- * lock of interest (NULL for none).
- */
-static inline void unspinning_lock(struct xen_spinlock *xl, struct xen_spinlock *prev)
-{
- dec_spinners(xl);
- wmb(); /* decrement count before restoring lock */
- __this_cpu_write(lock_spinners, prev);
-}
+static DEFINE_PER_CPU(char *, irq_name);
+static DEFINE_PER_CPU(struct xen_lock_waiting, lock_waiting);
+static cpumask_t waiting_cpus;
-static noinline int xen_spin_lock_slow(struct arch_spinlock *lock, bool irq_enable)
+static bool xen_pvspin = true;
+static void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
{
- struct xen_spinlock *xl = (struct xen_spinlock *)lock;
- struct xen_spinlock *prev;
int irq = __this_cpu_read(lock_kicker_irq);
- int ret;
+ struct xen_lock_waiting *w = &__get_cpu_var(lock_waiting);
+ int cpu = smp_processor_id();
u64 start;
+ unsigned long flags;
/* If kicker interrupts not initialized yet, just spin */
if (irq == -1)
- return 0;
+ return;
start = spin_time_start();
- /* announce we're spinning */
- prev = spinning_lock(xl);
+ /*
+ * Make sure an interrupt handler can't upset things in a
+ * partially setup state.
+ */
+ local_irq_save(flags);
+ /*
+ * We don't really care if we're overwriting some other
+ * (lock,want) pair, as that would mean that we're currently
+ * in an interrupt context, and the outer context had
+ * interrupts enabled. That has already kicked the VCPU out
+ * of xen_poll_irq(), so it will just return spuriously and
+ * retry with newly setup (lock,want).
+ *
+ * The ordering protocol on this is that the "lock" pointer
+ * may only be set non-NULL if the "want" ticket is correct.
+ * If we're updating "want", we must first clear "lock".
+ */
+ w->lock = NULL;
+ smp_wmb();
+ w->want = want;
+ smp_wmb();
+ w->lock = lock;
- ADD_STATS(taken_slow, 1);
- ADD_STATS(taken_slow_nested, prev != NULL);
+ /* This uses set_bit, which atomic and therefore a barrier */
+ cpumask_set_cpu(cpu, &waiting_cpus);
+ add_stats(TAKEN_SLOW, 1);
- do {
- unsigned long flags;
+ /* clear pending */
+ xen_clear_irq_pending(irq);
- /* clear pending */
- xen_clear_irq_pending(irq);
+ /* Only check lock once pending cleared */
+ barrier();
- /* check again make sure it didn't become free while
- we weren't looking */
- ret = xen_spin_trylock(lock);
- if (ret) {
- ADD_STATS(taken_slow_pickup, 1);
+ /*
+ * Mark entry to slowpath before doing the pickup test to make
+ * sure we don't deadlock with an unlocker.
+ */
+ __ticket_enter_slowpath(lock);
- /*
- * If we interrupted another spinlock while it
- * was blocking, make sure it doesn't block
- * without rechecking the lock.
- */
- if (prev != NULL)
- xen_set_irq_pending(irq);
- goto out;
- }
+ /*
+ * check again make sure it didn't become free while
+ * we weren't looking
+ */
+ if (ACCESS_ONCE(lock->tickets.head) == want) {
+ add_stats(TAKEN_SLOW_PICKUP, 1);
+ goto out;
+ }
- flags = arch_local_save_flags();
- if (irq_enable) {
- ADD_STATS(taken_slow_irqenable, 1);
- raw_local_irq_enable();
- }
+ /* Allow interrupts while blocked */
+ local_irq_restore(flags);
- /*
- * Block until irq becomes pending. If we're
- * interrupted at this point (after the trylock but
- * before entering the block), then the nested lock
- * handler guarantees that the irq will be left
- * pending if there's any chance the lock became free;
- * xen_poll_irq() returns immediately if the irq is
- * pending.
- */
- xen_poll_irq(irq);
+ /*
+ * If an interrupt happens here, it will leave the wakeup irq
+ * pending, which will cause xen_poll_irq() to return
+ * immediately.
+ */
- raw_local_irq_restore(flags);
+ /* Block until irq becomes pending (or perhaps a spurious wakeup) */
+ xen_poll_irq(irq);
+ add_stats(TAKEN_SLOW_SPURIOUS, !xen_test_irq_pending(irq));
- ADD_STATS(taken_slow_spurious, !xen_test_irq_pending(irq));
- } while (!xen_test_irq_pending(irq)); /* check for spurious wakeups */
+ local_irq_save(flags);
kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
-
out:
- unspinning_lock(xl, prev);
- spin_time_accum_blocked(start);
-
- return ret;
-}
-
-static inline void __xen_spin_lock(struct arch_spinlock *lock, bool irq_enable)
-{
- struct xen_spinlock *xl = (struct xen_spinlock *)lock;
- unsigned timeout;
- u8 oldval;
- u64 start_spin;
-
- ADD_STATS(taken, 1);
-
- start_spin = spin_time_start();
-
- do {
- u64 start_spin_fast = spin_time_start();
+ cpumask_clear_cpu(cpu, &waiting_cpus);
+ w->lock = NULL;
- timeout = TIMEOUT;
+ local_irq_restore(flags);
- asm("1: xchgb %1,%0\n"
- " testb %1,%1\n"
- " jz 3f\n"
- "2: rep;nop\n"
- " cmpb $0,%0\n"
- " je 1b\n"
- " dec %2\n"
- " jnz 2b\n"
- "3:\n"
- : "+m" (xl->lock), "=q" (oldval), "+r" (timeout)
- : "1" (1)
- : "memory");
-
- spin_time_accum_spinning(start_spin_fast);
-
- } while (unlikely(oldval != 0 &&
- (TIMEOUT == ~0 || !xen_spin_lock_slow(lock, irq_enable))));
-
- spin_time_accum_total(start_spin);
-}
-
-static void xen_spin_lock(struct arch_spinlock *lock)
-{
- __xen_spin_lock(lock, false);
-}
-
-static void xen_spin_lock_flags(struct arch_spinlock *lock, unsigned long flags)
-{
- __xen_spin_lock(lock, !raw_irqs_disabled_flags(flags));
+ spin_time_accum_blocked(start);
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_lock_spinning);
-static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl)
+static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
{
int cpu;
- ADD_STATS(released_slow, 1);
+ add_stats(RELEASED_SLOW, 1);
- for_each_online_cpu(cpu) {
- /* XXX should mix up next cpu selection */
- if (per_cpu(lock_spinners, cpu) == xl) {
- ADD_STATS(released_slow_kicked, 1);
+ for_each_cpu(cpu, &waiting_cpus) {
+ const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
+
+ /* Make sure we read lock before want */
+ if (ACCESS_ONCE(w->lock) == lock &&
+ ACCESS_ONCE(w->want) == next) {
+ add_stats(RELEASED_SLOW_KICKED, 1);
xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
+ break;
}
}
}
-static void xen_spin_unlock(struct arch_spinlock *lock)
-{
- struct xen_spinlock *xl = (struct xen_spinlock *)lock;
-
- ADD_STATS(released, 1);
-
- smp_wmb(); /* make sure no writes get moved after unlock */
- xl->lock = 0; /* release lock */
-
- /*
- * Make sure unlock happens before checking for waiting
- * spinners. We need a strong barrier to enforce the
- * write-read ordering to different memory locations, as the
- * CPU makes no implied guarantees about their ordering.
- */
- mb();
-
- if (unlikely(xl->spinners))
- xen_spin_unlock_slow(xl);
-}
-
static irqreturn_t dummy_handler(int irq, void *dev_id)
{
BUG();
@@ -366,16 +224,12 @@ void xen_init_lock_cpu(int cpu)
int irq;
char *name;
+ if (!xen_pvspin)
+ return;
+
WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
cpu, per_cpu(lock_kicker_irq, cpu));
- /*
- * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
- * (xen: disable PV spinlocks on HVM)
- */
- if (xen_hvm_domain())
- return;
-
name = kasprintf(GFP_KERNEL, "spinlock%d", cpu);
irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR,
cpu,
@@ -395,11 +249,7 @@ void xen_init_lock_cpu(int cpu)
void xen_uninit_lock_cpu(int cpu)
{
- /*
- * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
- * (xen: disable PV spinlocks on HVM)
- */
- if (xen_hvm_domain())
+ if (!xen_pvspin)
return;
unbind_from_irqhandler(per_cpu(lock_kicker_irq, cpu), NULL);
@@ -408,24 +258,49 @@ void xen_uninit_lock_cpu(int cpu)
per_cpu(irq_name, cpu) = NULL;
}
+
+/*
+ * Our init of PV spinlocks is split in two init functions due to us
+ * using paravirt patching and jump labels patching and having to do
+ * all of this before SMP code is invoked.
+ *
+ * The paravirt patching needs to be done _before_ the alternative asm code
+ * is started, otherwise we would not patch the core kernel code.
+ */
void __init xen_init_spinlocks(void)
{
- /*
- * See git commit f10cd522c5fbfec9ae3cc01967868c9c2401ed23
- * (xen: disable PV spinlocks on HVM)
- */
- if (xen_hvm_domain())
+
+ if (!xen_pvspin) {
+ printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
return;
+ }
+
+ pv_lock_ops.lock_spinning = PV_CALLEE_SAVE(xen_lock_spinning);
+ pv_lock_ops.unlock_kick = xen_unlock_kick;
+}
+
+/*
+ * While the jump_label init code needs to happend _after_ the jump labels are
+ * enabled and before SMP is started. Hence we use pre-SMP initcall level
+ * init. We cannot do it in xen_init_spinlocks as that is done before
+ * jump labels are activated.
+ */
+static __init int xen_init_spinlocks_jump(void)
+{
+ if (!xen_pvspin)
+ return 0;
- BUILD_BUG_ON(sizeof(struct xen_spinlock) > sizeof(arch_spinlock_t));
+ static_key_slow_inc(&paravirt_ticketlocks_enabled);
+ return 0;
+}
+early_initcall(xen_init_spinlocks_jump);
- pv_lock_ops.spin_is_locked = xen_spin_is_locked;
- pv_lock_ops.spin_is_contended = xen_spin_is_contended;
- pv_lock_ops.spin_lock = xen_spin_lock;
- pv_lock_ops.spin_lock_flags = xen_spin_lock_flags;
- pv_lock_ops.spin_trylock = xen_spin_trylock;
- pv_lock_ops.spin_unlock = xen_spin_unlock;
+static __init int xen_parse_nopvspin(char *arg)
+{
+ xen_pvspin = false;
+ return 0;
}
+early_param("xen_nopvspin", xen_parse_nopvspin);
#ifdef CONFIG_XEN_DEBUG_FS
@@ -438,41 +313,28 @@ static int __init xen_spinlock_debugfs(void)
if (d_xen == NULL)
return -ENOMEM;
+ if (!xen_pvspin)
+ return 0;
+
d_spin_debug = debugfs_create_dir("spinlocks", d_xen);
debugfs_create_u8("zero_stats", 0644, d_spin_debug, &zero_stats);
- debugfs_create_u32("timeout", 0644, d_spin_debug, &lock_timeout);
-
- debugfs_create_u64("taken", 0444, d_spin_debug, &spinlock_stats.taken);
debugfs_create_u32("taken_slow", 0444, d_spin_debug,
- &spinlock_stats.taken_slow);
- debugfs_create_u32("taken_slow_nested", 0444, d_spin_debug,
- &spinlock_stats.taken_slow_nested);
+ &spinlock_stats.contention_stats[TAKEN_SLOW]);
debugfs_create_u32("taken_slow_pickup", 0444, d_spin_debug,
- &spinlock_stats.taken_slow_pickup);
+ &spinlock_stats.contention_stats[TAKEN_SLOW_PICKUP]);
debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug,
- &spinlock_stats.taken_slow_spurious);
- debugfs_create_u32("taken_slow_irqenable", 0444, d_spin_debug,
- &spinlock_stats.taken_slow_irqenable);
+ &spinlock_stats.contention_stats[TAKEN_SLOW_SPURIOUS]);
- debugfs_create_u64("released", 0444, d_spin_debug, &spinlock_stats.released);
debugfs_create_u32("released_slow", 0444, d_spin_debug,
- &spinlock_stats.released_slow);
+ &spinlock_stats.contention_stats[RELEASED_SLOW]);
debugfs_create_u32("released_slow_kicked", 0444, d_spin_debug,
- &spinlock_stats.released_slow_kicked);
+ &spinlock_stats.contention_stats[RELEASED_SLOW_KICKED]);
- debugfs_create_u64("time_spinning", 0444, d_spin_debug,
- &spinlock_stats.time_spinning);
debugfs_create_u64("time_blocked", 0444, d_spin_debug,
&spinlock_stats.time_blocked);
- debugfs_create_u64("time_total", 0444, d_spin_debug,
- &spinlock_stats.time_total);
- debugfs_create_u32_array("histo_total", 0444, d_spin_debug,
- spinlock_stats.histo_spin_total, HISTO_BUCKETS + 1);
- debugfs_create_u32_array("histo_spinning", 0444, d_spin_debug,
- spinlock_stats.histo_spin_spinning, HISTO_BUCKETS + 1);
debugfs_create_u32_array("histo_blocked", 0444, d_spin_debug,
spinlock_stats.histo_spin_blocked, HISTO_BUCKETS + 1);
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 86782c5d7e2..95f8c614232 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -105,9 +105,9 @@ static inline void __init xen_init_apic(void)
/* Declare an asm function, along with symbols needed to make it
inlineable */
#define DECL_ASM(ret, name, ...) \
- ret name(__VA_ARGS__); \
- extern char name##_end[]; \
- extern char name##_reloc[] \
+ __visible ret name(__VA_ARGS__); \
+ extern char name##_end[] __visible; \
+ extern char name##_reloc[] __visible
DECL_ASM(void, xen_irq_enable_direct, void);
DECL_ASM(void, xen_irq_disable_direct, void);
@@ -115,11 +115,11 @@ DECL_ASM(unsigned long, xen_save_fl_direct, void);
DECL_ASM(void, xen_restore_fl_direct, unsigned long);
/* These are not functions, and cannot be called normally */
-void xen_iret(void);
-void xen_sysexit(void);
-void xen_sysret32(void);
-void xen_sysret64(void);
-void xen_adjust_exception_frame(void);
+__visible void xen_iret(void);
+__visible void xen_sysexit(void);
+__visible void xen_sysret32(void);
+__visible void xen_sysret64(void);
+__visible void xen_adjust_exception_frame(void);
extern int xen_panic_handler_init(void);