diff options
Diffstat (limited to 'arch')
427 files changed, 8913 insertions, 4555 deletions
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 9a20821b111c..c5fb9e6bc3a5 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -92,4 +92,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 34e1569a11ee..426115f7cb63 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -20,6 +20,7 @@ config ARM select GENERIC_ALLOCATOR select GENERIC_ATOMIC64 if (CPU_V7M || CPU_V6 || !CPU_32v6K || !AEABI) select GENERIC_CLOCKEVENTS_BROADCAST if SMP + select GENERIC_EARLY_IOREMAP select GENERIC_IDLE_POLL_SETUP select GENERIC_IRQ_PROBE select GENERIC_IRQ_SHOW @@ -33,10 +34,11 @@ config ARM select HARDIRQS_SW_RESEND select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 - select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 - select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 + select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU + select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) select HAVE_ARCH_TRACEHOOK + select HAVE_ARM_SMCCC if CPU_V7 select HAVE_BPF_JIT select HAVE_CC_STACKPROTECTOR select HAVE_CONTEXT_TRACKING @@ -45,7 +47,7 @@ config ARM select HAVE_DMA_API_DEBUG select HAVE_DMA_ATTRS select HAVE_DMA_CONTIGUOUS if MMU - select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 + select HAVE_DYNAMIC_FTRACE if (!XIP_KERNEL) && !CPU_ENDIAN_BE32 && MMU select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU select HAVE_FTRACE_MCOUNT_RECORD if (!XIP_KERNEL) select HAVE_FUNCTION_GRAPH_TRACER if (!THUMB2_KERNEL) @@ -611,6 +613,7 @@ config ARCH_PXA select AUTO_ZRELADDR select COMMON_CLK select CLKDEV_LOOKUP + select CLKSRC_PXA select CLKSRC_MMIO select CLKSRC_OF select GENERIC_CLOCKEVENTS @@ -650,6 +653,8 @@ config ARCH_SA1100 select ARCH_SPARSEMEM_ENABLE select CLKDEV_LOOKUP select CLKSRC_MMIO + select CLKSRC_PXA + select CLKSRC_OF if OF select CPU_FREQ select CPU_SA1100 select GENERIC_CLOCKEVENTS @@ -799,6 +804,7 @@ config ARCH_VIRT bool "Dummy Virtual Machine" if ARCH_MULTI_V7 select ARM_AMBA select ARM_GIC + select ARM_GIC_V2M if PCI_MSI select ARM_GIC_V3 select ARM_PSCI select HAVE_ARM_ARCH_TIMER @@ -1422,7 +1428,7 @@ config BIG_LITTLE config BL_SWITCHER bool "big.LITTLE switcher support" - depends on BIG_LITTLE && MCPM && HOTPLUG_CPU + depends on BIG_LITTLE && MCPM && HOTPLUG_CPU && ARM_GIC select ARM_CPU_SUSPEND select CPU_PM help @@ -1481,7 +1487,7 @@ config HOTPLUG_CPU config ARM_PSCI bool "Support for the ARM Power State Coordination Interface (PSCI)" - depends on CPU_V7 + depends on HAVE_ARM_SMCCC select ARM_PSCI_FW help Say Y here if you want Linux to communicate with system firmware @@ -1604,6 +1610,24 @@ config THUMB2_AVOID_R_ARM_THM_JUMP11 config ARM_ASM_UNIFIED bool +config ARM_PATCH_IDIV + bool "Runtime patch udiv/sdiv instructions into __aeabi_{u}idiv()" + depends on CPU_32v7 && !XIP_KERNEL + default y + help + The ARM compiler inserts calls to __aeabi_idiv() and + __aeabi_uidiv() when it needs to perform division on signed + and unsigned integers. Some v7 CPUs have support for the sdiv + and udiv instructions that can be used to implement those + functions. + + Enabling this option allows the kernel to modify itself to + replace the first two instructions of these library functions + with the sdiv or udiv plus "bx lr" instructions when the CPU + it is running on supports them. Typically this will be faster + and less power intensive than running the original library + code to do integer division. + config AEABI bool "Use the ARM EABI to compile the kernel" help @@ -1800,6 +1824,25 @@ config SWIOTLB config IOMMU_HELPER def_bool SWIOTLB +config PARAVIRT + bool "Enable paravirtualization code" + help + This changes the kernel so it can modify itself when it is run + under a hypervisor, potentially improving performance significantly + over full virtualization. + +config PARAVIRT_TIME_ACCOUNTING + bool "Paravirtual steal time accounting" + select PARAVIRT + default n + help + Select this option to enable fine granularity task steal time + accounting. Time spent executing other tasks in parallel with + the current vCPU is discounted from the vCPU power. To account for + that, there can be a small performance impact. + + If in doubt, say N here. + config XEN_DOM0 def_bool y depends on XEN @@ -1813,6 +1856,7 @@ config XEN select ARCH_DMA_ADDR_T_64BIT select ARM_PSCI select SWIOTLB_XEN + select PARAVIRT help Say Y if you want to run Linux in a Virtual Machine on Xen on ARM. @@ -2040,6 +2084,25 @@ config AUTO_ZRELADDR 0xf8000000. This assumes the zImage being placed in the first 128MB from start of memory. +config EFI_STUB + bool + +config EFI + bool "UEFI runtime support" + depends on OF && !CPU_BIG_ENDIAN && MMU && AUTO_ZRELADDR && !XIP_KERNEL + select UCS2_STRING + select EFI_PARAMS_FROM_FDT + select EFI_STUB + select EFI_ARMSTUB + select EFI_RUNTIME_WRAPPERS + ---help--- + This option provides support for runtime services provided + by UEFI firmware (such as non-volatile variables, realtime + clock, and platform reset). A UEFI stub is also provided to + allow the kernel to be booted as an EFI application. This + is only useful for kernels that may run on systems that have + UEFI firmware. + endmenu menu "CPU Power Management" diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile index 3f9a9ebc77c3..4c23a68a0917 100644 --- a/arch/arm/boot/compressed/Makefile +++ b/arch/arm/boot/compressed/Makefile @@ -167,9 +167,11 @@ if [ $(words $(ZRELADDR)) -gt 1 -a "$(CONFIG_AUTO_ZRELADDR)" = "" ]; then \ false; \ fi +efi-obj-$(CONFIG_EFI_STUB) := $(objtree)/drivers/firmware/efi/libstub/lib.a + $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.$(suffix_y).o \ $(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) \ - $(bswapsdi2) FORCE + $(bswapsdi2) $(efi-obj-y) FORCE @$(check_for_multiple_zreladdr) $(call if_changed,ld) @$(check_for_bad_syms) diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S new file mode 100644 index 000000000000..9d5dc4fda3c1 --- /dev/null +++ b/arch/arm/boot/compressed/efi-header.S @@ -0,0 +1,130 @@ +/* + * Copyright (C) 2013-2015 Linaro Ltd + * Authors: Roy Franz <roy.franz@linaro.org> + * Ard Biesheuvel <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + + .macro __nop +#ifdef CONFIG_EFI_STUB + @ This is almost but not quite a NOP, since it does clobber the + @ condition flags. But it is the best we can do for EFI, since + @ PE/COFF expects the magic string "MZ" at offset 0, while the + @ ARM/Linux boot protocol expects an executable instruction + @ there. + .inst 'M' | ('Z' << 8) | (0x1310 << 16) @ tstne r0, #0x4d000 +#else + mov r0, r0 +#endif + .endm + + .macro __EFI_HEADER +#ifdef CONFIG_EFI_STUB + b __efi_start + + .set start_offset, __efi_start - start + .org start + 0x3c + @ + @ The PE header can be anywhere in the file, but for + @ simplicity we keep it together with the MSDOS header + @ The offset to the PE/COFF header needs to be at offset + @ 0x3C in the MSDOS header. + @ The only 2 fields of the MSDOS header that are used are this + @ PE/COFF offset, and the "MZ" bytes at offset 0x0. + @ + .long pe_header - start @ Offset to the PE header. + +pe_header: + .ascii "PE\0\0" + +coff_header: + .short 0x01c2 @ ARM or Thumb + .short 2 @ nr_sections + .long 0 @ TimeDateStamp + .long 0 @ PointerToSymbolTable + .long 1 @ NumberOfSymbols + .short section_table - optional_header + @ SizeOfOptionalHeader + .short 0x306 @ Characteristics. + @ IMAGE_FILE_32BIT_MACHINE | + @ IMAGE_FILE_DEBUG_STRIPPED | + @ IMAGE_FILE_EXECUTABLE_IMAGE | + @ IMAGE_FILE_LINE_NUMS_STRIPPED + +optional_header: + .short 0x10b @ PE32 format + .byte 0x02 @ MajorLinkerVersion + .byte 0x14 @ MinorLinkerVersion + .long _end - __efi_start @ SizeOfCode + .long 0 @ SizeOfInitializedData + .long 0 @ SizeOfUninitializedData + .long efi_stub_entry - start @ AddressOfEntryPoint + .long start_offset @ BaseOfCode + .long 0 @ data + +extra_header_fields: + .long 0 @ ImageBase + .long 0x200 @ SectionAlignment + .long 0x200 @ FileAlignment + .short 0 @ MajorOperatingSystemVersion + .short 0 @ MinorOperatingSystemVersion + .short 0 @ MajorImageVersion + .short 0 @ MinorImageVersion + .short 0 @ MajorSubsystemVersion + .short 0 @ MinorSubsystemVersion + .long 0 @ Win32VersionValue + + .long _end - start @ SizeOfImage + .long start_offset @ SizeOfHeaders + .long 0 @ CheckSum + .short 0xa @ Subsystem (EFI application) + .short 0 @ DllCharacteristics + .long 0 @ SizeOfStackReserve + .long 0 @ SizeOfStackCommit + .long 0 @ SizeOfHeapReserve + .long 0 @ SizeOfHeapCommit + .long 0 @ LoaderFlags + .long 0x6 @ NumberOfRvaAndSizes + + .quad 0 @ ExportTable + .quad 0 @ ImportTable + .quad 0 @ ResourceTable + .quad 0 @ ExceptionTable + .quad 0 @ CertificationTable + .quad 0 @ BaseRelocationTable + +section_table: + @ + @ The EFI application loader requires a relocation section + @ because EFI applications must be relocatable. This is a + @ dummy section as far as we are concerned. + @ + .ascii ".reloc\0\0" + .long 0 @ VirtualSize + .long 0 @ VirtualAddress + .long 0 @ SizeOfRawData + .long 0 @ PointerToRawData + .long 0 @ PointerToRelocations + .long 0 @ PointerToLineNumbers + .short 0 @ NumberOfRelocations + .short 0 @ NumberOfLineNumbers + .long 0x42100040 @ Characteristics + + .ascii ".text\0\0\0" + .long _end - __efi_start @ VirtualSize + .long __efi_start @ VirtualAddress + .long _edata - __efi_start @ SizeOfRawData + .long __efi_start @ PointerToRawData + .long 0 @ PointerToRelocations + .long 0 @ PointerToLineNumbers + .short 0 @ NumberOfRelocations + .short 0 @ NumberOfLineNumbers + .long 0xe0500020 @ Characteristics + + .align 9 +__efi_start: +#endif + .endm diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S index 06e983f59980..af11c2f8f3b7 100644 --- a/arch/arm/boot/compressed/head.S +++ b/arch/arm/boot/compressed/head.S @@ -12,6 +12,8 @@ #include <asm/assembler.h> #include <asm/v7m.h> +#include "efi-header.S" + AR_CLASS( .arch armv7-a ) M_CLASS( .arch armv7-m ) @@ -126,7 +128,7 @@ start: .type start,#function .rept 7 - mov r0, r0 + __nop .endr ARM( mov r0, r0 ) ARM( b 1f ) @@ -139,7 +141,8 @@ start: .word 0x04030201 @ endianness flag THUMB( .thumb ) -1: +1: __EFI_HEADER + ARM_BE8( setend be ) @ go BE8 if compiled for BE8 AR_CLASS( mrs r9, cpsr ) #ifdef CONFIG_ARM_VIRT_EXT @@ -1353,6 +1356,53 @@ __enter_kernel: reloc_code_end: +#ifdef CONFIG_EFI_STUB + .align 2 +_start: .long start - . + +ENTRY(efi_stub_entry) + @ allocate space on stack for passing current zImage address + @ and for the EFI stub to return of new entry point of + @ zImage, as EFI stub may copy the kernel. Pointer address + @ is passed in r2. r0 and r1 are passed through from the + @ EFI firmware to efi_entry + adr ip, _start + ldr r3, [ip] + add r3, r3, ip + stmfd sp!, {r3, lr} + mov r2, sp @ pass zImage address in r2 + bl efi_entry + + @ Check for error return from EFI stub. r0 has FDT address + @ or error code. + cmn r0, #1 + beq efi_load_fail + + @ Preserve return value of efi_entry() in r4 + mov r4, r0 + bl cache_clean_flush + bl cache_off + + @ Set parameters for booting zImage according to boot protocol + @ put FDT address in r2, it was returned by efi_entry() + @ r1 is the machine type, and r0 needs to be 0 + mov r0, #0 + mov r1, #0xFFFFFFFF + mov r2, r4 + + @ Branch to (possibly) relocated zImage that is in [sp] + ldr lr, [sp] + ldr ip, =start_offset + add lr, lr, ip + mov pc, lr @ no mode switch + +efi_load_fail: + @ Return EFI_LOAD_ERROR to EFI firmware on error. + ldr r0, =0x80000001 + ldmfd sp!, {ip, pc} +ENDPROC(efi_stub_entry) +#endif + .align .section ".stack", "aw", %nobits .L_user_stack: .space 4096 diff --git a/arch/arm/boot/compressed/vmlinux.lds.S b/arch/arm/boot/compressed/vmlinux.lds.S index 2b60b843ac5e..81c493156ce8 100644 --- a/arch/arm/boot/compressed/vmlinux.lds.S +++ b/arch/arm/boot/compressed/vmlinux.lds.S @@ -48,6 +48,13 @@ SECTIONS *(.rodata) *(.rodata.*) } + .data : { + /* + * The EFI stub always executes from RAM, and runs strictly before the + * decompressor, so we can make an exception for its r/w data, and keep it + */ + *(.data.efistub) + } .piggydata : { *(.piggydata) } diff --git a/arch/arm/boot/dts/stihxxx-b2120.dtsi b/arch/arm/boot/dts/stihxxx-b2120.dtsi index ad21a4293a33..133375bc8aa5 100644 --- a/arch/arm/boot/dts/stihxxx-b2120.dtsi +++ b/arch/arm/boot/dts/stihxxx-b2120.dtsi @@ -6,6 +6,9 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <dt-bindings/clock/stih407-clks.h> +#include <dt-bindings/gpio/gpio.h> +#include <dt-bindings/media/c8sectpfe.h> / { soc { sbc_serial0: serial@9530000 { @@ -35,12 +38,18 @@ status = "okay"; }; - i2c@9842000 { + ssc2: i2c@9842000 { status = "okay"; + clock-frequency = <100000>; + st,i2c-min-scl-pulse-width-us = <0>; + st,i2c-min-sda-pulse-width-us = <5>; }; - i2c@9843000 { + ssc3: i2c@9843000 { status = "okay"; + clock-frequency = <100000>; + st,i2c-min-scl-pulse-width-us = <0>; + st,i2c-min-sda-pulse-width-us = <5>; }; i2c@9844000 { @@ -93,5 +102,38 @@ phy-mode = "rgmii"; fixed-link = <0 1 1000 0 0>; }; + + demux@08a20000 { + compatible = "st,stih407-c8sectpfe"; + status = "okay"; + reg = <0x08a20000 0x10000>, + <0x08a00000 0x4000>; + reg-names = "c8sectpfe", "c8sectpfe-ram"; + interrupts = <GIC_SPI 34 IRQ_TYPE_NONE>, + <GIC_SPI 35 IRQ_TYPE_NONE>; + interrupt-names = "c8sectpfe-error-irq", + "c8sectpfe-idle-irq"; + pinctrl-0 = <&pinctrl_tsin0_serial>; + pinctrl-1 = <&pinctrl_tsin0_parallel>; + pinctrl-2 = <&pinctrl_tsin3_serial>; + pinctrl-3 = <&pinctrl_tsin4_serial_alt3>; + pinctrl-4 = <&pinctrl_tsin5_serial_alt1>; + pinctrl-names = "tsin0-serial", + "tsin0-parallel", + "tsin3-serial", + "tsin4-serial", + "tsin5-serial"; + clocks = <&clk_s_c0_flexgen CLK_PROC_STFE>; + clock-names = "c8sectpfe"; + + /* tsin0 is TSA on NIMA */ + tsin0: port@0 { + tsin-num = <0>; + serial-not-parallel; + i2c-bus = <&ssc2>; + reset-gpios = <&pio15 4 GPIO_ACTIVE_HIGH>; + dvb-card = <STV0367_TDA18212_NIMA_1>; + }; + }; }; }; diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index bd425302c97a..16da6380eb85 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -3,6 +3,7 @@ generic-y += bitsperlong.h generic-y += cputime.h generic-y += current.h +generic-y += early_ioremap.h generic-y += emergency-restart.h generic-y += errno.h generic-y += exec.h diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h index e7335a92144e..4e6e88a6b2f4 100644 --- a/arch/arm/include/asm/bug.h +++ b/arch/arm/include/asm/bug.h @@ -5,8 +5,6 @@ #include <linux/types.h> #include <asm/opcodes.h> -#ifdef CONFIG_BUG - /* * Use a suitable undefined instruction to use for ARM/Thumb2 bug handling. * We need to be careful not to conflict with those used by other modules and @@ -47,7 +45,7 @@ do { \ unreachable(); \ } while (0) -#else /* not CONFIG_DEBUG_BUGVERBOSE */ +#else #define __BUG(__file, __line, __value) \ do { \ @@ -57,7 +55,6 @@ do { \ #endif /* CONFIG_DEBUG_BUGVERBOSE */ #define HAVE_ARCH_BUG -#endif /* CONFIG_BUG */ #include <asm-generic/bug.h> diff --git a/arch/arm/include/asm/cpuidle.h b/arch/arm/include/asm/cpuidle.h index 0f8424924902..3848259bebf8 100644 --- a/arch/arm/include/asm/cpuidle.h +++ b/arch/arm/include/asm/cpuidle.h @@ -30,7 +30,7 @@ static inline int arm_cpuidle_simple_enter(struct cpuidle_device *dev, struct device_node; struct cpuidle_ops { - int (*suspend)(int cpu, unsigned long arg); + int (*suspend)(unsigned long arg); int (*init)(struct device_node *, int cpu); }; diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h new file mode 100644 index 000000000000..e0eea72deb87 --- /dev/null +++ b/arch/arm/include/asm/efi.h @@ -0,0 +1,83 @@ +/* + * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __ASM_ARM_EFI_H +#define __ASM_ARM_EFI_H + +#include <asm/cacheflush.h> +#include <asm/cachetype.h> +#include <asm/early_ioremap.h> +#include <asm/fixmap.h> +#include <asm/highmem.h> +#include <asm/mach/map.h> +#include <asm/mmu_context.h> +#include <asm/pgtable.h> + +#ifdef CONFIG_EFI +void efi_init(void); + +int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); + +#define efi_call_virt(f, ...) \ +({ \ + efi_##f##_t *__f; \ + efi_status_t __s; \ + \ + efi_virtmap_load(); \ + __f = efi.systab->runtime->f; \ + __s = __f(__VA_ARGS__); \ + efi_virtmap_unload(); \ + __s; \ +}) + +#define __efi_call_virt(f, ...) \ +({ \ + efi_##f##_t *__f; \ + \ + efi_virtmap_load(); \ + __f = efi.systab->runtime->f; \ + __f(__VA_ARGS__); \ + efi_virtmap_unload(); \ +}) + +static inline void efi_set_pgd(struct mm_struct *mm) +{ + check_and_switch_context(mm, NULL); +} + +void efi_virtmap_load(void); +void efi_virtmap_unload(void); + +#else +#define efi_init() +#endif /* CONFIG_EFI */ + +/* arch specific definitions used by the stub code */ + +#define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__) + +/* + * A reasonable upper bound for the uncompressed kernel size is 32 MBytes, + * so we will reserve that amount of memory. We have no easy way to tell what + * the actuall size of code + data the uncompressed kernel will use. + * If this is insufficient, the decompressor will relocate itself out of the + * way before performing the decompression. + */ +#define MAX_UNCOMP_KERNEL_SIZE SZ_32M + +/* + * The kernel zImage should preferably be located between 32 MB and 128 MB + * from the base of DRAM. The min address leaves space for a maximal size + * uncompressed image, and the max address is due to how the zImage decompressor + * picks a destination address. + */ +#define ZIMAGE_OFFSET_LIMIT SZ_128M +#define MIN_ZIMAGE_OFFSET MAX_UNCOMP_KERNEL_SIZE +#define MAX_FDT_OFFSET ZIMAGE_OFFSET_LIMIT + +#endif /* _ASM_ARM_EFI_H */ diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h index 58cfe9f1a687..5c17d2dec777 100644 --- a/arch/arm/include/asm/fixmap.h +++ b/arch/arm/include/asm/fixmap.h @@ -19,20 +19,47 @@ enum fixed_addresses { FIX_TEXT_POKE0, FIX_TEXT_POKE1, - __end_of_fixed_addresses + __end_of_fixmap_region, + + /* + * Share the kmap() region with early_ioremap(): this is guaranteed + * not to clash since early_ioremap() is only available before + * paging_init(), and kmap() only after. + */ +#define NR_FIX_BTMAPS 32 +#define FIX_BTMAPS_SLOTS 7 +#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) + + FIX_BTMAP_END = __end_of_permanent_fixed_addresses, + FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1, + __end_of_early_ioremap_region }; +static const enum fixed_addresses __end_of_fixed_addresses = + __end_of_fixmap_region > __end_of_early_ioremap_region ? + __end_of_fixmap_region : __end_of_early_ioremap_region; + #define FIXMAP_PAGE_COMMON (L_PTE_YOUNG | L_PTE_PRESENT | L_PTE_XN | L_PTE_DIRTY) #define FIXMAP_PAGE_NORMAL (FIXMAP_PAGE_COMMON | L_PTE_MT_WRITEBACK) +#define FIXMAP_PAGE_RO (FIXMAP_PAGE_NORMAL | L_PTE_RDONLY) /* Used by set_fixmap_(io|nocache), both meant for mapping a device */ #define FIXMAP_PAGE_IO (FIXMAP_PAGE_COMMON | L_PTE_MT_DEV_SHARED | L_PTE_SHARED) #define FIXMAP_PAGE_NOCACHE FIXMAP_PAGE_IO +#define __early_set_fixmap __set_fixmap + +#ifdef CONFIG_MMU + void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot); void __init early_fixmap_init(void); #include <asm-generic/fixmap.h> +#else + +static inline void early_fixmap_init(void) { } + +#endif #endif diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h index fe3ea776dc34..3d7351c844aa 100644 --- a/arch/arm/include/asm/hardirq.h +++ b/arch/arm/include/asm/hardirq.h @@ -5,7 +5,7 @@ #include <linux/threads.h> #include <asm/irq.h> -#define NR_IPI 8 +#define NR_IPI 7 typedef struct { unsigned int __softirq_pending; diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h index dc641ddf0784..e22089fb44dc 100644 --- a/arch/arm/include/asm/kvm_arm.h +++ b/arch/arm/include/asm/kvm_arm.h @@ -19,6 +19,7 @@ #ifndef __ARM_KVM_ARM_H__ #define __ARM_KVM_ARM_H__ +#include <linux/const.h> #include <linux/types.h> /* Hyp Configuration Register (HCR) bits */ @@ -132,10 +133,9 @@ * space. */ #define KVM_PHYS_SHIFT (40) -#define KVM_PHYS_SIZE (1ULL << KVM_PHYS_SHIFT) -#define KVM_PHYS_MASK (KVM_PHYS_SIZE - 1ULL) -#define PTRS_PER_S2_PGD (1ULL << (KVM_PHYS_SHIFT - 30)) -#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) +#define KVM_PHYS_SIZE (_AC(1, ULL) << KVM_PHYS_SHIFT) +#define KVM_PHYS_MASK (KVM_PHYS_SIZE - _AC(1, ULL)) +#define PTRS_PER_S2_PGD (_AC(1, ULL) << (KVM_PHYS_SHIFT - 30)) /* Virtualization Translation Control Register (VTCR) bits */ #define VTCR_SH0 (3 << 12) @@ -162,17 +162,17 @@ #define VTTBR_X (5 - KVM_T0SZ) #endif #define VTTBR_BADDR_SHIFT (VTTBR_X - 1) -#define VTTBR_BADDR_MASK (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) -#define VTTBR_VMID_SHIFT (48LLU) -#define VTTBR_VMID_MASK (0xffLLU << VTTBR_VMID_SHIFT) +#define VTTBR_BADDR_MASK (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) +#define VTTBR_VMID_SHIFT _AC(48, ULL) +#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT) /* Hyp Syndrome Register (HSR) bits */ #define HSR_EC_SHIFT (26) -#define HSR_EC (0x3fU << HSR_EC_SHIFT) -#define HSR_IL (1U << 25) +#define HSR_EC (_AC(0x3f, UL) << HSR_EC_SHIFT) +#define HSR_IL (_AC(1, UL) << 25) #define HSR_ISS (HSR_IL - 1) #define HSR_ISV_SHIFT (24) -#define HSR_ISV (1U << HSR_ISV_SHIFT) +#define HSR_ISV (_AC(1, UL) << HSR_ISV_SHIFT) #define HSR_SRT_SHIFT (16) #define HSR_SRT_MASK (0xf << HSR_SRT_SHIFT) #define HSR_FSC (0x3f) @@ -180,9 +180,9 @@ #define HSR_SSE (1 << 21) #define HSR_WNR (1 << 6) #define HSR_CV_SHIFT (24) -#define HSR_CV (1U << HSR_CV_SHIFT) +#define HSR_CV (_AC(1, UL) << HSR_CV_SHIFT) #define HSR_COND_SHIFT (20) -#define HSR_COND (0xfU << HSR_COND_SHIFT) +#define HSR_COND (_AC(0xf, UL) << HSR_COND_SHIFT) #define FSC_FAULT (0x04) #define FSC_ACCESS (0x08) @@ -210,13 +210,13 @@ #define HSR_EC_DABT (0x24) #define HSR_EC_DABT_HYP (0x25) -#define HSR_WFI_IS_WFE (1U << 0) +#define HSR_WFI_IS_WFE (_AC(1, UL) << 0) -#define HSR_HVC_IMM_MASK ((1UL << 16) - 1) +#define HSR_HVC_IMM_MASK ((_AC(1, UL) << 16) - 1) -#define HSR_DABT_S1PTW (1U << 7) -#define HSR_DABT_CM (1U << 8) -#define HSR_DABT_EA (1U << 9) +#define HSR_DABT_S1PTW (_AC(1, UL) << 7) +#define HSR_DABT_CM (_AC(1, UL) << 8) +#define HSR_DABT_EA (_AC(1, UL) << 9) #define kvm_arm_exception_type \ {0, "RESET" }, \ diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 6692982c9b57..f9f27792d8ed 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -150,6 +150,12 @@ struct kvm_vcpu_stat { u32 halt_successful_poll; u32 halt_attempted_poll; u32 halt_wakeup; + u32 hvc_exit_stat; + u64 wfe_exit_stat; + u64 wfi_exit_stat; + u64 mmio_exit_user; + u64 mmio_exit_kernel; + u64 exits; }; int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h index 405aa1883307..9203c21b4673 100644 --- a/arch/arm/include/asm/kvm_mmu.h +++ b/arch/arm/include/asm/kvm_mmu.h @@ -279,6 +279,11 @@ static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd, pgd_t *merged_hyp_pgd, unsigned long hyp_idmap_start) { } +static inline unsigned int kvm_get_vmid_bits(void) +{ + return 8; +} + #endif /* !__ASSEMBLY__ */ #endif /* __ARM_KVM_MMU_H__ */ diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h index f98c7f32c9c8..9b7c328fb207 100644 --- a/arch/arm/include/asm/mach/map.h +++ b/arch/arm/include/asm/mach/map.h @@ -42,6 +42,8 @@ enum { extern void iotable_init(struct map_desc *, int); extern void vm_reserve_area_early(unsigned long addr, unsigned long size, void *caller); +extern void create_mapping_late(struct mm_struct *mm, struct map_desc *md, + bool ng); #ifdef CONFIG_DEBUG_LL extern void debug_ll_addr(unsigned long *paddr, unsigned long *vaddr); diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h index 9b32f76bb0dd..432ce8176498 100644 --- a/arch/arm/include/asm/mmu_context.h +++ b/arch/arm/include/asm/mmu_context.h @@ -26,7 +26,7 @@ void __check_vmalloc_seq(struct mm_struct *mm); #ifdef CONFIG_CPU_HAS_ASID void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk); -#define init_new_context(tsk,mm) ({ atomic64_set(&mm->context.id, 0); 0; }) +#define init_new_context(tsk,mm) ({ atomic64_set(&(mm)->context.id, 0); 0; }) #ifdef CONFIG_ARM_ERRATA_798181 void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm, diff --git a/arch/arm/include/asm/paravirt.h b/arch/arm/include/asm/paravirt.h new file mode 100644 index 000000000000..8435ff591386 --- /dev/null +++ b/arch/arm/include/asm/paravirt.h @@ -0,0 +1,20 @@ +#ifndef _ASM_ARM_PARAVIRT_H +#define _ASM_ARM_PARAVIRT_H + +#ifdef CONFIG_PARAVIRT +struct static_key; +extern struct static_key paravirt_steal_enabled; +extern struct static_key paravirt_steal_rq_enabled; + +struct pv_time_ops { + unsigned long long (*steal_clock)(int cpu); +}; +extern struct pv_time_ops pv_time_ops; + +static inline u64 paravirt_steal_clock(int cpu) +{ + return pv_time_ops.steal_clock(cpu); +} +#endif + +#endif diff --git a/arch/arm/include/asm/psci.h b/arch/arm/include/asm/psci.h index 68ee3ce17b82..b4c6d99364f1 100644 --- a/arch/arm/include/asm/psci.h +++ b/arch/arm/include/asm/psci.h @@ -16,7 +16,7 @@ extern struct smp_operations psci_smp_ops; -#ifdef CONFIG_ARM_PSCI +#if defined(CONFIG_SMP) && defined(CONFIG_ARM_PSCI) bool psci_smp_available(void); #else static inline bool psci_smp_available(void) { return false; } diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h index e0adb9f1bf94..3613d7e9fc40 100644 --- a/arch/arm/include/asm/setup.h +++ b/arch/arm/include/asm/setup.h @@ -25,4 +25,10 @@ extern int arm_add_memory(u64 start, u64 size); extern void early_print(const char *str, ...); extern void dump_machine_table(void); +#ifdef CONFIG_ATAGS_PROC +extern void save_atags(const struct tag *tags); +#else +static inline void save_atags(const struct tag *tags) { } +#endif + #endif diff --git a/arch/arm/include/asm/xen/hypercall.h b/arch/arm/include/asm/xen/hypercall.h index 712b50e0a6dc..d769972db8cb 100644 --- a/arch/arm/include/asm/xen/hypercall.h +++ b/arch/arm/include/asm/xen/hypercall.h @@ -35,6 +35,7 @@ #include <xen/interface/xen.h> #include <xen/interface/sched.h> +#include <xen/interface/platform.h> long privcmd_call(unsigned call, unsigned long a1, unsigned long a2, unsigned long a3, @@ -49,6 +50,12 @@ int HYPERVISOR_memory_op(unsigned int cmd, void *arg); int HYPERVISOR_physdev_op(int cmd, void *arg); int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args); int HYPERVISOR_tmem_op(void *arg); +int HYPERVISOR_platform_op_raw(void *arg); +static inline int HYPERVISOR_platform_op(struct xen_platform_op *op) +{ + op->interface_version = XENPF_INTERFACE_VERSION; + return HYPERVISOR_platform_op_raw(op); +} int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr); static inline int diff --git a/arch/arm/include/asm/xen/interface.h b/arch/arm/include/asm/xen/interface.h index 50066006e6bd..75d596862892 100644 --- a/arch/arm/include/asm/xen/interface.h +++ b/arch/arm/include/asm/xen/interface.h @@ -27,6 +27,8 @@ (hnd).p = val; \ } while (0) +#define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op + #ifndef __ASSEMBLY__ /* Explicitly size integers that represent pfns in the interface with * Xen so that we can have one ABI that works for 32 and 64 bit guests. @@ -76,6 +78,7 @@ struct pvclock_wall_clock { u32 version; u32 sec; u32 nsec; + u32 sec_hi; } __attribute__((__packed__)); #endif diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile index af9e59bf3831..2c5f160be65e 100644 --- a/arch/arm/kernel/Makefile +++ b/arch/arm/kernel/Makefile @@ -73,14 +73,15 @@ obj-$(CONFIG_IWMMXT) += iwmmxt.o obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o obj-$(CONFIG_HW_PERF_EVENTS) += perf_event_xscale.o perf_event_v6.o \ perf_event_v7.o -CFLAGS_pj4-cp0.o := -marm AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o obj-$(CONFIG_VDSO) += vdso.o +obj-$(CONFIG_EFI) += efi.o ifneq ($(CONFIG_ARCH_EBSA110),y) obj-y += io.o endif +obj-$(CONFIG_PARAVIRT) += paravirt.o head-y := head$(MMUEXT).o obj-$(CONFIG_DEBUG_LL) += debug.o @@ -88,8 +89,9 @@ obj-$(CONFIG_EARLY_PRINTK) += early_printk.o obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o ifeq ($(CONFIG_ARM_PSCI),y) -obj-y += psci-call.o obj-$(CONFIG_SMP) += psci_smp.o endif +obj-$(CONFIG_HAVE_ARM_SMCCC) += smccc-call.o + extra-y := $(head-y) vmlinux.lds diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c index f89811fb9a55..7e45f69a0ddc 100644 --- a/arch/arm/kernel/armksyms.c +++ b/arch/arm/kernel/armksyms.c @@ -16,6 +16,7 @@ #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/io.h> +#include <linux/arm-smccc.h> #include <asm/checksum.h> #include <asm/ftrace.h> @@ -175,3 +176,8 @@ EXPORT_SYMBOL(__gnu_mcount_nc); EXPORT_SYMBOL(__pv_phys_pfn_offset); EXPORT_SYMBOL(__pv_offset); #endif + +#ifdef CONFIG_HAVE_ARM_SMCCC +EXPORT_SYMBOL(arm_smccc_smc); +EXPORT_SYMBOL(arm_smccc_hvc); +#endif diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h index ec4164da6e30..edfa2268c127 100644 --- a/arch/arm/kernel/atags.h +++ b/arch/arm/kernel/atags.h @@ -1,9 +1,3 @@ -#ifdef CONFIG_ATAGS_PROC -extern void save_atags(struct tag *tags); -#else -static inline void save_atags(struct tag *tags) { } -#endif - void convert_to_tag_list(struct tag *tags); #ifdef CONFIG_ATAGS diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c index 318da33465f4..703926e7007b 100644 --- a/arch/arm/kernel/cpuidle.c +++ b/arch/arm/kernel/cpuidle.c @@ -56,7 +56,7 @@ int arm_cpuidle_suspend(int index) int cpu = smp_processor_id(); if (cpuidle_ops[cpu].suspend) - ret = cpuidle_ops[cpu].suspend(cpu, index); + ret = cpuidle_ops[cpu].suspend(index); return ret; } diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c new file mode 100644 index 000000000000..ff8a9d8acfac --- /dev/null +++ b/arch/arm/kernel/efi.c @@ -0,0 +1,38 @@ +/* + * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/efi.h> +#include <asm/efi.h> +#include <asm/mach/map.h> +#include <asm/mmu_context.h> + +int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) +{ + struct map_desc desc = { + .virtual = md->virt_addr, + .pfn = __phys_to_pfn(md->phys_addr), + .length = md->num_pages * EFI_PAGE_SIZE, + }; + + /* + * Order is important here: memory regions may have all of the + * bits below set (and usually do), so we check them in order of + * preference. + */ + if (md->attribute & EFI_MEMORY_WB) + desc.type = MT_MEMORY_RWX; + else if (md->attribute & EFI_MEMORY_WT) + desc.type = MT_MEMORY_RWX_NONCACHED; + else if (md->attribute & EFI_MEMORY_WC) + desc.type = MT_DEVICE_WC; + else + desc.type = MT_DEVICE; + + create_mapping_late(mm, &desc, true); + return 0; +} diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S index b6c8bb9315e7..907534f97053 100644 --- a/arch/arm/kernel/entry-v7m.S +++ b/arch/arm/kernel/entry-v7m.S @@ -88,7 +88,7 @@ __pendsv_entry: @ execute the pending work, including reschedule get_thread_info tsk mov why, #0 - b ret_to_user + b ret_to_user_from_irq ENDPROC(__pendsv_entry) /* diff --git a/arch/arm64/kernel/psci-call.S b/arch/arm/kernel/paravirt.c index cf83e61cd3b5..53f371ed4568 100644 --- a/arch/arm64/kernel/psci-call.S +++ b/arch/arm/kernel/paravirt.c @@ -8,21 +8,18 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * Copyright (C) 2015 ARM Limited + * Copyright (C) 2013 Citrix Systems * - * Author: Will Deacon <will.deacon@arm.com> + * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com> */ -#include <linux/linkage.h> +#include <linux/export.h> +#include <linux/jump_label.h> +#include <linux/types.h> +#include <asm/paravirt.h> -/* int __invoke_psci_fn_hvc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */ -ENTRY(__invoke_psci_fn_hvc) - hvc #0 - ret -ENDPROC(__invoke_psci_fn_hvc) +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; -/* int __invoke_psci_fn_smc(u64 function_id, u64 arg0, u64 arg1, u64 arg2) */ -ENTRY(__invoke_psci_fn_smc) - smc #0 - ret -ENDPROC(__invoke_psci_fn_smc) +struct pv_time_ops pv_time_ops; +EXPORT_SYMBOL_GPL(pv_time_ops); diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c index 126dc679b230..4152158f6e6a 100644 --- a/arch/arm/kernel/perf_event_v7.c +++ b/arch/arm/kernel/perf_event_v7.c @@ -35,133 +35,117 @@ * but the encodings are considered to be `reserved' in the case that * they are not available. */ -enum armv7_perf_types { - ARMV7_PERFCTR_PMNC_SW_INCR = 0x00, - ARMV7_PERFCTR_L1_ICACHE_REFILL = 0x01, - ARMV7_PERFCTR_ITLB_REFILL = 0x02, - ARMV7_PERFCTR_L1_DCACHE_REFILL = 0x03, - ARMV7_PERFCTR_L1_DCACHE_ACCESS = 0x04, - ARMV7_PERFCTR_DTLB_REFILL = 0x05, - ARMV7_PERFCTR_MEM_READ = 0x06, - ARMV7_PERFCTR_MEM_WRITE = 0x07, - ARMV7_PERFCTR_INSTR_EXECUTED = 0x08, - ARMV7_PERFCTR_EXC_TAKEN = 0x09, - ARMV7_PERFCTR_EXC_EXECUTED = 0x0A, - ARMV7_PERFCTR_CID_WRITE = 0x0B, +#define ARMV7_PERFCTR_PMNC_SW_INCR 0x00 +#define ARMV7_PERFCTR_L1_ICACHE_REFILL 0x01 +#define ARMV7_PERFCTR_ITLB_REFILL 0x02 +#define ARMV7_PERFCTR_L1_DCACHE_REFILL 0x03 +#define ARMV7_PERFCTR_L1_DCACHE_ACCESS 0x04 +#define ARMV7_PERFCTR_DTLB_REFILL 0x05 +#define ARMV7_PERFCTR_MEM_READ 0x06 +#define ARMV7_PERFCTR_MEM_WRITE 0x07 +#define ARMV7_PERFCTR_INSTR_EXECUTED 0x08 +#define ARMV7_PERFCTR_EXC_TAKEN 0x09 +#define ARMV7_PERFCTR_EXC_EXECUTED 0x0A +#define ARMV7_PERFCTR_CID_WRITE 0x0B - /* - * ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS. - * It counts: - * - all (taken) branch instructions, - * - instructions that explicitly write the PC, - * - exception generating instructions. - */ - ARMV7_PERFCTR_PC_WRITE = 0x0C, - ARMV7_PERFCTR_PC_IMM_BRANCH = 0x0D, - ARMV7_PERFCTR_PC_PROC_RETURN = 0x0E, - ARMV7_PERFCTR_MEM_UNALIGNED_ACCESS = 0x0F, - ARMV7_PERFCTR_PC_BRANCH_MIS_PRED = 0x10, - ARMV7_PERFCTR_CLOCK_CYCLES = 0x11, - ARMV7_PERFCTR_PC_BRANCH_PRED = 0x12, - - /* These events are defined by the PMUv2 supplement (ARM DDI 0457A). */ - ARMV7_PERFCTR_MEM_ACCESS = 0x13, - ARMV7_PERFCTR_L1_ICACHE_ACCESS = 0x14, - ARMV7_PERFCTR_L1_DCACHE_WB = 0x15, - ARMV7_PERFCTR_L2_CACHE_ACCESS = 0x16, - ARMV7_PERFCTR_L2_CACHE_REFILL = 0x17, - ARMV7_PERFCTR_L2_CACHE_WB = 0x18, - ARMV7_PERFCTR_BUS_ACCESS = 0x19, - ARMV7_PERFCTR_MEM_ERROR = 0x1A, - ARMV7_PERFCTR_INSTR_SPEC = 0x1B, - ARMV7_PERFCTR_TTBR_WRITE = 0x1C, - ARMV7_PERFCTR_BUS_CYCLES = 0x1D, - - ARMV7_PERFCTR_CPU_CYCLES = 0xFF -}; +/* + * ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS. + * It counts: + * - all (taken) branch instructions, + * - instructions that explicitly write the PC, + * - exception generating instructions. + */ +#define ARMV7_PERFCTR_PC_WRITE 0x0C +#define ARMV7_PERFCTR_PC_IMM_BRANCH 0x0D +#define ARMV7_PERFCTR_PC_PROC_RETURN 0x0E +#define ARMV7_PERFCTR_MEM_UNALIGNED_ACCESS 0x0F +#define ARMV7_PERFCTR_PC_BRANCH_MIS_PRED 0x10 +#define ARMV7_PERFCTR_CLOCK_CYCLES 0x11 +#define ARMV7_PERFCTR_PC_BRANCH_PRED 0x12 + +/* These events are defined by the PMUv2 supplement (ARM DDI 0457A). */ +#define ARMV7_PERFCTR_MEM_ACCESS 0x13 +#define ARMV7_PERFCTR_L1_ICACHE_ACCESS 0x14 +#define ARMV7_PERFCTR_L1_DCACHE_WB 0x15 +#define ARMV7_PERFCTR_L2_CACHE_ACCESS 0x16 +#define ARMV7_PERFCTR_L2_CACHE_REFILL 0x17 +#define ARMV7_PERFCTR_L2_CACHE_WB 0x18 +#define ARMV7_PERFCTR_BUS_ACCESS 0x19 +#define ARMV7_PERFCTR_MEM_ERROR 0x1A +#define ARMV7_PERFCTR_INSTR_SPEC 0x1B +#define ARMV7_PERFCTR_TTBR_WRITE 0x1C +#define ARMV7_PERFCTR_BUS_CYCLES 0x1D + +#define ARMV7_PERFCTR_CPU_CYCLES 0xFF /* ARMv7 Cortex-A8 specific event types */ -enum armv7_a8_perf_types { - ARMV7_A8_PERFCTR_L2_CACHE_ACCESS = 0x43, - ARMV7_A8_PERFCTR_L2_CACHE_REFILL = 0x44, - ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS = 0x50, - ARMV7_A8_PERFCTR_STALL_ISIDE = 0x56, -}; +#define ARMV7_A8_PERFCTR_L2_CACHE_ACCESS 0x43 +#define ARMV7_A8_PERFCTR_L2_CACHE_REFILL 0x44 +#define ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS 0x50 +#define ARMV7_A8_PERFCTR_STALL_ISIDE 0x56 /* ARMv7 Cortex-A9 specific event types */ -enum armv7_a9_perf_types { - ARMV7_A9_PERFCTR_INSTR_CORE_RENAME = 0x68, - ARMV7_A9_PERFCTR_STALL_ICACHE = 0x60, - ARMV7_A9_PERFCTR_STALL_DISPATCH = 0x66, -}; +#define ARMV7_A9_PERFCTR_INSTR_CORE_RENAME 0x68 +#define ARMV7_A9_PERFCTR_STALL_ICACHE 0x60 +#define ARMV7_A9_PERFCTR_STALL_DISPATCH 0x66 /* ARMv7 Cortex-A5 specific event types */ -enum armv7_a5_perf_types { - ARMV7_A5_PERFCTR_PREFETCH_LINEFILL = 0xc2, - ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP = 0xc3, -}; +#define ARMV7_A5_PERFCTR_PREFETCH_LINEFILL 0xc2 +#define ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP 0xc3 /* ARMv7 Cortex-A15 specific event types */ -enum armv7_a15_perf_types { - ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ = 0x40, - ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE = 0x41, - ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ = 0x42, - ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE = 0x43, +#define ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ 0x40 +#define ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE 0x41 +#define ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ 0x42 +#define ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE 0x43 - ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ = 0x4C, - ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE = 0x4D, +#define ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ 0x4C +#define ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE 0x4D - ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ = 0x50, - ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE = 0x51, - ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ = 0x52, - ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE = 0x53, +#define ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ 0x50 +#define ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE 0x51 +#define ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ 0x52 +#define ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE 0x53 - ARMV7_A15_PERFCTR_PC_WRITE_SPEC = 0x76, -}; +#define ARMV7_A15_PERFCTR_PC_WRITE_SPEC 0x76 /* ARMv7 Cortex-A12 specific event types */ -enum armv7_a12_perf_types { - ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ = 0x40, - ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE = 0x41, +#define ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ 0x40 +#define ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE 0x41 - ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ = 0x50, - ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE = 0x51, +#define ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ 0x50 +#define ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE 0x51 - ARMV7_A12_PERFCTR_PC_WRITE_SPEC = 0x76, +#define ARMV7_A12_PERFCTR_PC_WRITE_SPEC 0x76 - ARMV7_A12_PERFCTR_PF_TLB_REFILL = 0xe7, -}; +#define ARMV7_A12_PERFCTR_PF_TLB_REFILL 0xe7 /* ARMv7 Krait specific event types */ -enum krait_perf_types { - KRAIT_PMRESR0_GROUP0 = 0xcc, - KRAIT_PMRESR1_GROUP0 = 0xd0, - KRAIT_PMRESR2_GROUP0 = 0xd4, - KRAIT_VPMRESR0_GROUP0 = 0xd8, +#define KRAIT_PMRESR0_GROUP0 0xcc +#define KRAIT_PMRESR1_GROUP0 0xd0 +#define KRAIT_PMRESR2_GROUP0 0xd4 +#define KRAIT_VPMRESR0_GROUP0 0xd8 - KRAIT_PERFCTR_L1_ICACHE_ACCESS = 0x10011, - KRAIT_PERFCTR_L1_ICACHE_MISS = 0x10010, +#define KRAIT_PERFCTR_L1_ICACHE_ACCESS 0x10011 +#define KRAIT_PERFCTR_L1_ICACHE_MISS 0x10010 - KRAIT_PERFCTR_L1_ITLB_ACCESS = 0x12222, - KRAIT_PERFCTR_L1_DTLB_ACCESS = 0x12210, -}; +#define KRAIT_PERFCTR_L1_ITLB_ACCESS 0x12222 +#define KRAIT_PERFCTR_L1_DTLB_ACCESS 0x12210 /* ARMv7 Scorpion specific event types */ -enum scorpion_perf_types { - SCORPION_LPM0_GROUP0 = 0x4c, - SCORPION_LPM1_GROUP0 = 0x50, - SCORPION_LPM2_GROUP0 = 0x54, - SCORPION_L2LPM_GROUP0 = 0x58, - SCORPION_VLPM_GROUP0 = 0x5c, +#define SCORPION_LPM0_GROUP0 0x4c +#define SCORPION_LPM1_GROUP0 0x50 +#define SCORPION_LPM2_GROUP0 0x54 +#define SCORPION_L2LPM_GROUP0 0x58 +#define SCORPION_VLPM_GROUP0 0x5c - SCORPION_ICACHE_ACCESS = 0x10053, - SCORPION_ICACHE_MISS = 0x10052, +#define SCORPION_ICACHE_ACCESS 0x10053 +#define SCORPION_ICACHE_MISS 0x10052 - SCORPION_DTLB_ACCESS = 0x12013, - SCORPION_DTLB_MISS = 0x12012, +#define SCORPION_DTLB_ACCESS 0x12013 +#define SCORPION_DTLB_MISS 0x12012 - SCORPION_ITLB_MISS = 0x12021, -}; +#define SCORPION_ITLB_MISS 0x12021 /* * Cortex-A8 HW events mapping @@ -547,6 +531,134 @@ static const unsigned scorpion_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, }; +PMU_FORMAT_ATTR(event, "config:0-7"); + +static struct attribute *armv7_pmu_format_attrs[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group armv7_pmu_format_attr_group = { + .name = "format", + .attrs = armv7_pmu_format_attrs, +}; + +#define ARMV7_EVENT_ATTR_RESOLVE(m) #m +#define ARMV7_EVENT_ATTR(name, config) \ + PMU_EVENT_ATTR_STRING(name, armv7_event_attr_##name, \ + "event=" ARMV7_EVENT_ATTR_RESOLVE(config)) + +ARMV7_EVENT_ATTR(sw_incr, ARMV7_PERFCTR_PMNC_SW_INCR); +ARMV7_EVENT_ATTR(l1i_cache_refill, ARMV7_PERFCTR_L1_ICACHE_REFILL); +ARMV7_EVENT_ATTR(l1i_tlb_refill, ARMV7_PERFCTR_ITLB_REFILL); +ARMV7_EVENT_ATTR(l1d_cache_refill, ARMV7_PERFCTR_L1_DCACHE_REFILL); +ARMV7_EVENT_ATTR(l1d_cache, ARMV7_PERFCTR_L1_DCACHE_ACCESS); +ARMV7_EVENT_ATTR(l1d_tlb_refill, ARMV7_PERFCTR_DTLB_REFILL); +ARMV7_EVENT_ATTR(ld_retired, ARMV7_PERFCTR_MEM_READ); +ARMV7_EVENT_ATTR(st_retired, ARMV7_PERFCTR_MEM_WRITE); +ARMV7_EVENT_ATTR(inst_retired, ARMV7_PERFCTR_INSTR_EXECUTED); +ARMV7_EVENT_ATTR(exc_taken, ARMV7_PERFCTR_EXC_TAKEN); +ARMV7_EVENT_ATTR(exc_return, ARMV7_PERFCTR_EXC_EXECUTED); +ARMV7_EVENT_ATTR(cid_write_retired, ARMV7_PERFCTR_CID_WRITE); +ARMV7_EVENT_ATTR(pc_write_retired, ARMV7_PERFCTR_PC_WRITE); +ARMV7_EVENT_ATTR(br_immed_retired, ARMV7_PERFCTR_PC_IMM_BRANCH); +ARMV7_EVENT_ATTR(br_return_retired, ARMV7_PERFCTR_PC_PROC_RETURN); +ARMV7_EVENT_ATTR(unaligned_ldst_retired, ARMV7_PERFCTR_MEM_UNALIGNED_ACCESS); +ARMV7_EVENT_ATTR(br_mis_pred, ARMV7_PERFCTR_PC_BRANCH_MIS_PRED); +ARMV7_EVENT_ATTR(cpu_cycles, ARMV7_PERFCTR_CLOCK_CYCLES); +ARMV7_EVENT_ATTR(br_pred, ARMV7_PERFCTR_PC_BRANCH_PRED); + +static struct attribute *armv7_pmuv1_event_attrs[] = { + &armv7_event_attr_sw_incr.attr.attr, + &armv7_event_attr_l1i_cache_refill.attr.attr, + &armv7_event_attr_l1i_tlb_refill.attr.attr, + &armv7_event_attr_l1d_cache_refill.attr.attr, + &armv7_event_attr_l1d_cache.attr.attr, + &armv7_event_attr_l1d_tlb_refill.attr.attr, + &armv7_event_attr_ld_retired.attr.attr, + &armv7_event_attr_st_retired.attr.attr, + &armv7_event_attr_inst_retired.attr.attr, + &armv7_event_attr_exc_taken.attr.attr, + &armv7_event_attr_exc_return.attr.attr, + &armv7_event_attr_cid_write_retired.attr.attr, + &armv7_event_attr_pc_write_retired.attr.attr, + &armv7_event_attr_br_immed_retired.attr.attr, + &armv7_event_attr_br_return_retired.attr.attr, + &armv7_event_attr_unaligned_ldst_retired.attr.attr, + &armv7_event_attr_br_mis_pred.attr.attr, + &armv7_event_attr_cpu_cycles.attr.attr, + &armv7_event_attr_br_pred.attr.attr, + NULL, +}; + +static struct attribute_group armv7_pmuv1_events_attr_group = { + .name = "events", + .attrs = armv7_pmuv1_event_attrs, +}; + +static const struct attribute_group *armv7_pmuv1_attr_groups[] = { + &armv7_pmuv1_events_attr_group, + &armv7_pmu_format_attr_group, + NULL, +}; + +ARMV7_EVENT_ATTR(mem_access, ARMV7_PERFCTR_MEM_ACCESS); +ARMV7_EVENT_ATTR(l1i_cache, ARMV7_PERFCTR_L1_ICACHE_ACCESS); +ARMV7_EVENT_ATTR(l1d_cache_wb, ARMV7_PERFCTR_L1_DCACHE_WB); +ARMV7_EVENT_ATTR(l2d_cache, ARMV7_PERFCTR_L2_CACHE_ACCESS); +ARMV7_EVENT_ATTR(l2d_cache_refill, ARMV7_PERFCTR_L2_CACHE_REFILL); +ARMV7_EVENT_ATTR(l2d_cache_wb, ARMV7_PERFCTR_L2_CACHE_WB); +ARMV7_EVENT_ATTR(bus_access, ARMV7_PERFCTR_BUS_ACCESS); +ARMV7_EVENT_ATTR(memory_error, ARMV7_PERFCTR_MEM_ERROR); +ARMV7_EVENT_ATTR(inst_spec, ARMV7_PERFCTR_INSTR_SPEC); +ARMV7_EVENT_ATTR(ttbr_write_retired, ARMV7_PERFCTR_TTBR_WRITE); +ARMV7_EVENT_ATTR(bus_cycles, ARMV7_PERFCTR_BUS_CYCLES); + +static struct attribute *armv7_pmuv2_event_attrs[] = { + &armv7_event_attr_sw_incr.attr.attr, + &armv7_event_attr_l1i_cache_refill.attr.attr, + &armv7_event_attr_l1i_tlb_refill.attr.attr, + &armv7_event_attr_l1d_cache_refill.attr.attr, + &armv7_event_attr_l1d_cache.attr.attr, + &armv7_event_attr_l1d_tlb_refill.attr.attr, + &armv7_event_attr_ld_retired.attr.attr, + &armv7_event_attr_st_retired.attr.attr, + &armv7_event_attr_inst_retired.attr.attr, + &armv7_event_attr_exc_taken.attr.attr, + &armv7_event_attr_exc_return.attr.attr, + &armv7_event_attr_cid_write_retired.attr.attr, + &armv7_event_attr_pc_write_retired.attr.attr, + &armv7_event_attr_br_immed_retired.attr.attr, + &armv7_event_attr_br_return_retired.attr.attr, + &armv7_event_attr_unaligned_ldst_retired.attr.attr, + &armv7_event_attr_br_mis_pred.attr.attr, + &armv7_event_attr_cpu_cycles.attr.attr, + &armv7_event_attr_br_pred.attr.attr, + &armv7_event_attr_mem_access.attr.attr, + &armv7_event_attr_l1i_cache.attr.attr, + &armv7_event_attr_l1d_cache_wb.attr.attr, + &armv7_event_attr_l2d_cache.attr.attr, + &armv7_event_attr_l2d_cache_refill.attr.attr, + &armv7_event_attr_l2d_cache_wb.attr.attr, + &armv7_event_attr_bus_access.attr.attr, + &armv7_event_attr_memory_error.attr.attr, + &armv7_event_attr_inst_spec.attr.attr, + &armv7_event_attr_ttbr_write_retired.attr.attr, + &armv7_event_attr_bus_cycles.attr.attr, + NULL, +}; + +static struct attribute_group armv7_pmuv2_events_attr_group = { + .name = "events", + .attrs = armv7_pmuv2_event_attrs, +}; + +static const struct attribute_group *armv7_pmuv2_attr_groups[] = { + &armv7_pmuv2_events_attr_group, + &armv7_pmu_format_attr_group, + NULL, +}; + /* * Perf Events' indices */ @@ -1085,6 +1197,7 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) armv7pmu_init(cpu_pmu); cpu_pmu->name = "armv7_cortex_a8"; cpu_pmu->map_event = armv7_a8_map_event; + cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups; return armv7_probe_num_events(cpu_pmu); } @@ -1093,6 +1206,7 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu) armv7pmu_init(cpu_pmu); cpu_pmu->name = "armv7_cortex_a9"; cpu_pmu->map_event = armv7_a9_map_event; + cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups; return armv7_probe_num_events(cpu_pmu); } @@ -1101,6 +1215,7 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu) armv7pmu_init(cpu_pmu); cpu_pmu->name = "armv7_cortex_a5"; cpu_pmu->map_event = armv7_a5_map_event; + cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups; return armv7_probe_num_events(cpu_pmu); } @@ -1110,6 +1225,7 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->name = "armv7_cortex_a15"; cpu_pmu->map_event = armv7_a15_map_event; cpu_pmu->set_event_filter = armv7pmu_set_event_filter; + cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups; return armv7_probe_num_events(cpu_pmu); } @@ -1119,6 +1235,7 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->name = "armv7_cortex_a7"; cpu_pmu->map_event = armv7_a7_map_event; cpu_pmu->set_event_filter = armv7pmu_set_event_filter; + cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups; return armv7_probe_num_events(cpu_pmu); } @@ -1128,6 +1245,7 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu) cpu_pmu->name = "armv7_cortex_a12"; cpu_pmu->map_event = armv7_a12_map_event; cpu_pmu->set_event_filter = armv7pmu_set_event_filter; + cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups; return armv7_probe_num_events(cpu_pmu); } @@ -1135,6 +1253,7 @@ static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu) { int ret = armv7_a12_pmu_init(cpu_pmu); cpu_pmu->name = "armv7_cortex_a17"; + cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups; return ret; } diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c index 8153e36b2491..7c9248b74d3f 100644 --- a/arch/arm/kernel/pj4-cp0.c +++ b/arch/arm/kernel/pj4-cp0.c @@ -66,9 +66,13 @@ static void __init pj4_cp_access_write(u32 value) __asm__ __volatile__ ( "mcr p15, 0, %1, c1, c0, 2\n\t" +#ifdef CONFIG_THUMB2_KERNEL + "isb\n\t" +#else "mrc p15, 0, %0, c1, c0, 2\n\t" "mov %0, %0\n\t" "sub pc, pc, #4\n\t" +#endif : "=r" (temp) : "r" (value)); } diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 20edd349d379..7d0cba6f1cc5 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -7,6 +7,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/efi.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/stddef.h> @@ -37,7 +38,9 @@ #include <asm/cp15.h> #include <asm/cpu.h> #include <asm/cputype.h> +#include <asm/efi.h> #include <asm/elf.h> +#include <asm/early_ioremap.h> #include <asm/fixmap.h> #include <asm/procinfo.h> #include <asm/psci.h> @@ -375,6 +378,72 @@ void __init early_print(const char *str, ...) printk("%s", buf); } +#ifdef CONFIG_ARM_PATCH_IDIV + +static inline u32 __attribute_const__ sdiv_instruction(void) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + /* "sdiv r0, r0, r1" */ + u32 insn = __opcode_thumb32_compose(0xfb90, 0xf0f1); + return __opcode_to_mem_thumb32(insn); + } + + /* "sdiv r0, r0, r1" */ + return __opcode_to_mem_arm(0xe710f110); +} + +static inline u32 __attribute_const__ udiv_instruction(void) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + /* "udiv r0, r0, r1" */ + u32 insn = __opcode_thumb32_compose(0xfbb0, 0xf0f1); + return __opcode_to_mem_thumb32(insn); + } + + /* "udiv r0, r0, r1" */ + return __opcode_to_mem_arm(0xe730f110); +} + +static inline u32 __attribute_const__ bx_lr_instruction(void) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + /* "bx lr; nop" */ + u32 insn = __opcode_thumb32_compose(0x4770, 0x46c0); + return __opcode_to_mem_thumb32(insn); + } + + /* "bx lr" */ + return __opcode_to_mem_arm(0xe12fff1e); +} + +static void __init patch_aeabi_idiv(void) +{ + extern void __aeabi_uidiv(void); + extern void __aeabi_idiv(void); + uintptr_t fn_addr; + unsigned int mask; + + mask = IS_ENABLED(CONFIG_THUMB2_KERNEL) ? HWCAP_IDIVT : HWCAP_IDIVA; + if (!(elf_hwcap & mask)) + return; + + pr_info("CPU: div instructions available: patching division code\n"); + + fn_addr = ((uintptr_t)&__aeabi_uidiv) & ~1; + ((u32 *)fn_addr)[0] = udiv_instruction(); + ((u32 *)fn_addr)[1] = bx_lr_instruction(); + flush_icache_range(fn_addr, fn_addr + 8); + + fn_addr = ((uintptr_t)&__aeabi_idiv) & ~1; + ((u32 *)fn_addr)[0] = sdiv_instruction(); + ((u32 *)fn_addr)[1] = bx_lr_instruction(); + flush_icache_range(fn_addr, fn_addr + 8); +} + +#else +static inline void patch_aeabi_idiv(void) { } +#endif + static void __init cpuid_init_hwcaps(void) { int block; @@ -642,6 +711,7 @@ static void __init setup_processor(void) elf_hwcap = list->elf_hwcap; cpuid_init_hwcaps(); + patch_aeabi_idiv(); #ifndef CONFIG_ARM_THUMB elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT); @@ -956,8 +1026,8 @@ void __init setup_arch(char **cmdline_p) strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE); *cmdline_p = cmd_line; - if (IS_ENABLED(CONFIG_FIX_EARLYCON_MEM)) - early_fixmap_init(); + early_fixmap_init(); + early_ioremap_init(); parse_early_param(); @@ -965,9 +1035,12 @@ void __init setup_arch(char **cmdline_p) early_paging_init(mdesc); #endif setup_dma_zone(mdesc); + efi_init(); sanity_check_meminfo(); arm_memblock_init(mdesc); + early_ioremap_reset(); + paging_init(mdesc); request_standard_resources(mdesc); diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S new file mode 100644 index 000000000000..2e48b674aab1 --- /dev/null +++ b/arch/arm/kernel/smccc-call.S @@ -0,0 +1,62 @@ +/* + * Copyright (c) 2015, Linaro Limited + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ +#include <linux/linkage.h> + +#include <asm/opcodes-sec.h> +#include <asm/opcodes-virt.h> +#include <asm/unwind.h> + + /* + * Wrap c macros in asm macros to delay expansion until after the + * SMCCC asm macro is expanded. + */ + .macro SMCCC_SMC + __SMC(0) + .endm + + .macro SMCCC_HVC + __HVC(0) + .endm + + .macro SMCCC instr +UNWIND( .fnstart) + mov r12, sp + push {r4-r7} +UNWIND( .save {r4-r7}) + ldm r12, {r4-r7} + \instr + pop {r4-r7} + ldr r12, [sp, #(4 * 4)] + stm r12, {r0-r3} + bx lr +UNWIND( .fnend) + .endm + +/* + * void smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2, + * unsigned long a3, unsigned long a4, unsigned long a5, + * unsigned long a6, unsigned long a7, struct arm_smccc_res *res) + */ +ENTRY(arm_smccc_smc) + SMCCC SMCCC_SMC +ENDPROC(arm_smccc_smc) + +/* + * void smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2, + * unsigned long a3, unsigned long a4, unsigned long a5, + * unsigned long a6, unsigned long a7, struct arm_smccc_res *res) + */ +ENTRY(arm_smccc_hvc) + SMCCC SMCCC_HVC +ENDPROC(arm_smccc_hvc) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c index b26361355dae..37312f6749f3 100644 --- a/arch/arm/kernel/smp.c +++ b/arch/arm/kernel/smp.c @@ -69,11 +69,15 @@ enum ipi_msg_type { IPI_TIMER, IPI_RESCHEDULE, IPI_CALL_FUNC, - IPI_CALL_FUNC_SINGLE, IPI_CPU_STOP, IPI_IRQ_WORK, IPI_COMPLETION, - IPI_CPU_BACKTRACE = 15, + IPI_CPU_BACKTRACE, + /* + * SGI8-15 can be reserved by secure firmware, and thus may + * not be usable by the kernel. Please keep the above limited + * to at most 8 entries. + */ }; static DECLARE_COMPLETION(cpu_running); @@ -475,7 +479,6 @@ static const char *ipi_types[NR_IPI] __tracepoint_string = { S(IPI_TIMER, "Timer broadcast interrupts"), S(IPI_RESCHEDULE, "Rescheduling interrupts"), S(IPI_CALL_FUNC, "Function call interrupts"), - S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"), S(IPI_CPU_STOP, "CPU stop interrupts"), S(IPI_IRQ_WORK, "IRQ work interrupts"), S(IPI_COMPLETION, "completion interrupts"), @@ -525,7 +528,7 @@ void arch_send_wakeup_ipi_mask(const struct cpumask *mask) void arch_send_call_function_single_ipi(int cpu) { - smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE); + smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC); } #ifdef CONFIG_IRQ_WORK @@ -620,12 +623,6 @@ void handle_IPI(int ipinr, struct pt_regs *regs) irq_exit(); break; - case IPI_CALL_FUNC_SINGLE: - irq_enter(); - generic_smp_call_function_single_interrupt(); - irq_exit(); - break; - case IPI_CPU_STOP: irq_enter(); ipi_cpu_stop(cpu); diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c index 54a5aeab988d..994e971a8538 100644 --- a/arch/arm/kernel/vdso.c +++ b/arch/arm/kernel/vdso.c @@ -224,7 +224,7 @@ static int install_vvar(struct mm_struct *mm, unsigned long addr) VM_READ | VM_MAYREAD, &vdso_data_mapping); - return IS_ERR(vma) ? PTR_ERR(vma) : 0; + return PTR_ERR_OR_ZERO(vma); } /* assumes mmap_sem is write-locked */ diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index e06fd299de08..dda1959f0dde 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -44,6 +44,7 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> #include <asm/kvm_psci.h> +#include <asm/sections.h> #ifdef REQUIRES_VIRT __asm__(".arch_extension virt"); @@ -58,9 +59,12 @@ static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu); /* The VMID used in the VTTBR */ static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1); -static u8 kvm_next_vmid; +static u32 kvm_next_vmid; +static unsigned int kvm_vmid_bits __read_mostly; static DEFINE_SPINLOCK(kvm_vmid_lock); +static bool vgic_present; + static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu) { BUG_ON(preemptible()); @@ -132,7 +136,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.vmid_gen = 0; /* The maximum number of VCPUs is limited by the host's GIC model */ - kvm->arch.max_vcpus = kvm_vgic_get_max_vcpus(); + kvm->arch.max_vcpus = vgic_present ? + kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS; return ret; out_free_stage2_pgd: @@ -172,6 +177,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) int r; switch (ext) { case KVM_CAP_IRQCHIP: + r = vgic_present; + break; case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_USER_MEMORY: @@ -433,11 +440,12 @@ static void update_vttbr(struct kvm *kvm) kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen); kvm->arch.vmid = kvm_next_vmid; kvm_next_vmid++; + kvm_next_vmid &= (1 << kvm_vmid_bits) - 1; /* update vttbr to be used with the new vmid */ pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm)); BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK); - vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK; + vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits); kvm->arch.vttbr = pgd_phys | vmid; spin_unlock(&kvm_vmid_lock); @@ -603,6 +611,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_call_hyp(__kvm_vcpu_run, vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; + vcpu->stat.exits++; /* * Back from guest *************************************************************/ @@ -913,6 +922,8 @@ static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm, switch (dev_id) { case KVM_ARM_DEVICE_VGIC_V2: + if (!vgic_present) + return -ENXIO; return kvm_vgic_addr(kvm, type, &dev_addr->addr, true); default: return -ENODEV; @@ -927,6 +938,8 @@ long kvm_arch_vm_ioctl(struct file *filp, switch (ioctl) { case KVM_CREATE_IRQCHIP: { + if (!vgic_present) + return -ENXIO; return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); } case KVM_ARM_SET_DEVICE_ADDR: { @@ -1067,6 +1080,12 @@ static int init_hyp_mode(void) goto out_free_mappings; } + err = create_hyp_mappings(__start_rodata, __end_rodata); + if (err) { + kvm_err("Cannot map rodata section\n"); + goto out_free_mappings; + } + /* * Map the Hyp stack pages */ @@ -1111,8 +1130,17 @@ static int init_hyp_mode(void) * Init HYP view of VGIC */ err = kvm_vgic_hyp_init(); - if (err) + switch (err) { + case 0: + vgic_present = true; + break; + case -ENODEV: + case -ENXIO: + vgic_present = false; + break; + default: goto out_free_context; + } /* * Init HYP architected timer support @@ -1127,6 +1155,10 @@ static int init_hyp_mode(void) kvm_perf_init(); + /* set size of VMID supported by CPU */ + kvm_vmid_bits = kvm_get_vmid_bits(); + kvm_info("%d-bit VMID\n", kvm_vmid_bits); + kvm_info("Hyp mode initialized successfully\n"); return 0; diff --git a/arch/arm/kvm/emulate.c b/arch/arm/kvm/emulate.c index d6c005283678..dc99159857b4 100644 --- a/arch/arm/kvm/emulate.c +++ b/arch/arm/kvm/emulate.c @@ -275,6 +275,40 @@ static u32 exc_vector_base(struct kvm_vcpu *vcpu) return vbar; } +/* + * Switch to an exception mode, updating both CPSR and SPSR. Follow + * the logic described in AArch32.EnterMode() from the ARMv8 ARM. + */ +static void kvm_update_psr(struct kvm_vcpu *vcpu, unsigned long mode) +{ + unsigned long cpsr = *vcpu_cpsr(vcpu); + u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; + + *vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | mode; + + switch (mode) { + case FIQ_MODE: + *vcpu_cpsr(vcpu) |= PSR_F_BIT; + /* Fall through */ + case ABT_MODE: + case IRQ_MODE: + *vcpu_cpsr(vcpu) |= PSR_A_BIT; + /* Fall through */ + default: + *vcpu_cpsr(vcpu) |= PSR_I_BIT; + } + + *vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT); + + if (sctlr & SCTLR_TE) + *vcpu_cpsr(vcpu) |= PSR_T_BIT; + if (sctlr & SCTLR_EE) + *vcpu_cpsr(vcpu) |= PSR_E_BIT; + + /* Note: These now point to the mode banked copies */ + *vcpu_spsr(vcpu) = cpsr; +} + /** * kvm_inject_undefined - inject an undefined exception into the guest * @vcpu: The VCPU to receive the undefined exception @@ -286,29 +320,13 @@ static u32 exc_vector_base(struct kvm_vcpu *vcpu) */ void kvm_inject_undefined(struct kvm_vcpu *vcpu) { - unsigned long new_lr_value; - unsigned long new_spsr_value; unsigned long cpsr = *vcpu_cpsr(vcpu); - u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; bool is_thumb = (cpsr & PSR_T_BIT); u32 vect_offset = 4; u32 return_offset = (is_thumb) ? 2 : 4; - new_spsr_value = cpsr; - new_lr_value = *vcpu_pc(vcpu) - return_offset; - - *vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | UND_MODE; - *vcpu_cpsr(vcpu) |= PSR_I_BIT; - *vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT); - - if (sctlr & SCTLR_TE) - *vcpu_cpsr(vcpu) |= PSR_T_BIT; - if (sctlr & SCTLR_EE) - *vcpu_cpsr(vcpu) |= PSR_E_BIT; - - /* Note: These now point to UND banked copies */ - *vcpu_spsr(vcpu) = cpsr; - *vcpu_reg(vcpu, 14) = new_lr_value; + kvm_update_psr(vcpu, UND_MODE); + *vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) - return_offset; /* Branch to exception vector */ *vcpu_pc(vcpu) = exc_vector_base(vcpu) + vect_offset; @@ -320,30 +338,14 @@ void kvm_inject_undefined(struct kvm_vcpu *vcpu) */ static void inject_abt(struct kvm_vcpu *vcpu, bool is_pabt, unsigned long addr) { - unsigned long new_lr_value; - unsigned long new_spsr_value; unsigned long cpsr = *vcpu_cpsr(vcpu); - u32 sctlr = vcpu->arch.cp15[c1_SCTLR]; bool is_thumb = (cpsr & PSR_T_BIT); u32 vect_offset; u32 return_offset = (is_thumb) ? 4 : 0; bool is_lpae; - new_spsr_value = cpsr; - new_lr_value = *vcpu_pc(vcpu) + return_offset; - - *vcpu_cpsr(vcpu) = (cpsr & ~MODE_MASK) | ABT_MODE; - *vcpu_cpsr(vcpu) |= PSR_I_BIT | PSR_A_BIT; - *vcpu_cpsr(vcpu) &= ~(PSR_IT_MASK | PSR_J_BIT | PSR_E_BIT | PSR_T_BIT); - - if (sctlr & SCTLR_TE) - *vcpu_cpsr(vcpu) |= PSR_T_BIT; - if (sctlr & SCTLR_EE) - *vcpu_cpsr(vcpu) |= PSR_E_BIT; - - /* Note: These now point to ABT banked copies */ - *vcpu_spsr(vcpu) = cpsr; - *vcpu_reg(vcpu, 14) = new_lr_value; + kvm_update_psr(vcpu, ABT_MODE); + *vcpu_reg(vcpu, 14) = *vcpu_pc(vcpu) + return_offset; if (is_pabt) vect_offset = 12; diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c index 96e935bbc38c..5fa69d7bae58 100644 --- a/arch/arm/kvm/guest.c +++ b/arch/arm/kvm/guest.c @@ -33,6 +33,12 @@ #define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU } struct kvm_stats_debugfs_item debugfs_entries[] = { + VCPU_STAT(hvc_exit_stat), + VCPU_STAT(wfe_exit_stat), + VCPU_STAT(wfi_exit_stat), + VCPU_STAT(mmio_exit_user), + VCPU_STAT(mmio_exit_kernel), + VCPU_STAT(exits), { NULL } }; diff --git a/arch/arm/kvm/handle_exit.c b/arch/arm/kvm/handle_exit.c index 95f12b2ccdcb..3ede90d8b20b 100644 --- a/arch/arm/kvm/handle_exit.c +++ b/arch/arm/kvm/handle_exit.c @@ -42,6 +42,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) trace_kvm_hvc(*vcpu_pc(vcpu), *vcpu_reg(vcpu, 0), kvm_vcpu_hvc_get_imm(vcpu)); + vcpu->stat.hvc_exit_stat++; ret = kvm_psci_call(vcpu); if (ret < 0) { @@ -89,9 +90,11 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) { if (kvm_vcpu_get_hsr(vcpu) & HSR_WFI_IS_WFE) { trace_kvm_wfx(*vcpu_pc(vcpu), true); + vcpu->stat.wfe_exit_stat++; kvm_vcpu_on_spin(vcpu); } else { trace_kvm_wfx(*vcpu_pc(vcpu), false); + vcpu->stat.wfi_exit_stat++; kvm_vcpu_block(vcpu); } diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 3a10c9f1d0a4..7f33b2056ae6 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -210,8 +210,11 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, if (!ret) { /* We handled the access successfully in the kernel. */ + vcpu->stat.mmio_exit_kernel++; kvm_handle_mmio_return(vcpu, run); return 1; + } else { + vcpu->stat.mmio_exit_user++; } run->exit_reason = KVM_EXIT_MMIO; diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 61d96a645ff3..22f7fa0124ec 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -656,9 +656,9 @@ static void *kvm_alloc_hwpgd(void) * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation. * @kvm: The KVM struct pointer for the VM. * - * Allocates the 1st level table only of size defined by S2_PGD_ORDER (can - * support either full 40-bit input addresses or limited to 32-bit input - * addresses). Clears the allocated pages. + * Allocates only the stage-2 HW PGD level table(s) (can support either full + * 40-bit input addresses or limited to 32-bit input addresses). Clears the + * allocated pages. * * Note we don't need locking here as this is only called when the VM is * created, which can only be done once. diff --git a/arch/arm/lib/lib1funcs.S b/arch/arm/lib/lib1funcs.S index af2267f6a529..9397b2e532af 100644 --- a/arch/arm/lib/lib1funcs.S +++ b/arch/arm/lib/lib1funcs.S @@ -205,6 +205,10 @@ Boston, MA 02111-1307, USA. */ .endm +#ifdef CONFIG_ARM_PATCH_IDIV + .align 3 +#endif + ENTRY(__udivsi3) ENTRY(__aeabi_uidiv) UNWIND(.fnstart) @@ -253,6 +257,10 @@ UNWIND(.fnstart) UNWIND(.fnend) ENDPROC(__umodsi3) +#ifdef CONFIG_ARM_PATCH_IDIV + .align 3 +#endif + ENTRY(__divsi3) ENTRY(__aeabi_idiv) UNWIND(.fnstart) diff --git a/arch/arm/mach-davinci/board-da850-evm.c b/arch/arm/mach-davinci/board-da850-evm.c index 1ed545cc2b83..9cc7b818fbf6 100644 --- a/arch/arm/mach-davinci/board-da850-evm.c +++ b/arch/arm/mach-davinci/board-da850-evm.c @@ -49,8 +49,8 @@ #include <asm/mach/arch.h> #include <asm/system_info.h> -#include <media/tvp514x.h> -#include <media/adv7343.h> +#include <media/i2c/tvp514x.h> +#include <media/i2c/adv7343.h> #define DA850_EVM_PHY_ID "davinci_mdio-0:00" #define DA850_LCD_PWR_PIN GPIO_TO_PIN(2, 8) diff --git a/arch/arm/mach-davinci/board-dm355-evm.c b/arch/arm/mach-davinci/board-dm355-evm.c index b46b4d25f93e..c71dd9982f03 100644 --- a/arch/arm/mach-davinci/board-dm355-evm.c +++ b/arch/arm/mach-davinci/board-dm355-evm.c @@ -19,7 +19,7 @@ #include <linux/gpio.h> #include <linux/clk.h> #include <linux/videodev2.h> -#include <media/tvp514x.h> +#include <media/i2c/tvp514x.h> #include <linux/spi/spi.h> #include <linux/spi/eeprom.h> #include <linux/platform_data/gpio-davinci.h> diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c index a756003595e9..f073518f621a 100644 --- a/arch/arm/mach-davinci/board-dm365-evm.c +++ b/arch/arm/mach-davinci/board-dm365-evm.c @@ -40,8 +40,8 @@ #include <linux/platform_data/mtd-davinci.h> #include <linux/platform_data/keyscan-davinci.h> -#include <media/ths7303.h> -#include <media/tvp514x.h> +#include <media/i2c/ths7303.h> +#include <media/i2c/tvp514x.h> #include "davinci.h" diff --git a/arch/arm/mach-davinci/board-dm644x-evm.c b/arch/arm/mach-davinci/board-dm644x-evm.c index bbdd2d614b49..7a20507a3eef 100644 --- a/arch/arm/mach-davinci/board-dm644x-evm.c +++ b/arch/arm/mach-davinci/board-dm644x-evm.c @@ -26,7 +26,7 @@ #include <linux/v4l2-dv-timings.h> #include <linux/export.h> -#include <media/tvp514x.h> +#include <media/i2c/tvp514x.h> #include <asm/mach-types.h> #include <asm/mach/arch.h> diff --git a/arch/arm/mach-davinci/board-dm646x-evm.c b/arch/arm/mach-davinci/board-dm646x-evm.c index 846a84ddc28e..ee6ab7e8d3b0 100644 --- a/arch/arm/mach-davinci/board-dm646x-evm.c +++ b/arch/arm/mach-davinci/board-dm646x-evm.c @@ -25,8 +25,8 @@ #include <linux/platform_data/at24.h> #include <linux/i2c/pcf857x.h> -#include <media/tvp514x.h> -#include <media/adv7343.h> +#include <media/i2c/tvp514x.h> +#include <media/i2c/adv7343.h> #include <linux/mtd/mtd.h> #include <linux/mtd/nand.h> diff --git a/arch/arm/mach-exynos/Kconfig b/arch/arm/mach-exynos/Kconfig index 3a10f1a8317a..ff105399aae4 100644 --- a/arch/arm/mach-exynos/Kconfig +++ b/arch/arm/mach-exynos/Kconfig @@ -27,6 +27,7 @@ menuconfig ARCH_EXYNOS select SRAM select THERMAL select MFD_SYSCON + select CLKSRC_EXYNOS_MCT help Support for SAMSUNG EXYNOS SoCs (EXYNOS4/5) diff --git a/arch/arm/mach-imx/devices/devices-common.h b/arch/arm/mach-imx/devices/devices-common.h index 67f7fb13050d..09cebd8cef2b 100644 --- a/arch/arm/mach-imx/devices/devices-common.h +++ b/arch/arm/mach-imx/devices/devices-common.h @@ -177,7 +177,7 @@ struct platform_device *__init imx_add_imx_uart_1irq( const struct imxuart_platform_data *pdata); #include <linux/platform_data/video-mx3fb.h> -#include <linux/platform_data/camera-mx3.h> +#include <linux/platform_data/media/camera-mx3.h> struct imx_ipu_core_data { resource_size_t iobase; resource_size_t synirq; @@ -192,7 +192,7 @@ struct platform_device *__init imx_add_mx3_sdc_fb( const struct imx_ipu_core_data *data, struct mx3fb_platform_data *pdata); -#include <linux/platform_data/camera-mx2.h> +#include <linux/platform_data/media/camera-mx2.h> struct imx_mx2_camera_data { const char *devid; resource_size_t iobasecsi; diff --git a/arch/arm/mach-omap1/include/mach/camera.h b/arch/arm/mach-omap1/include/mach/camera.h index 847d00f0bb0a..caa6c0d6f0ac 100644 --- a/arch/arm/mach-omap1/include/mach/camera.h +++ b/arch/arm/mach-omap1/include/mach/camera.h @@ -1,7 +1,7 @@ #ifndef __ASM_ARCH_CAMERA_H_ #define __ASM_ARCH_CAMERA_H_ -#include <media/omap1_camera.h> +#include <linux/platform_data/media/omap1_camera.h> void omap1_camera_init(void *); diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c index 04a56cc04dfa..809827265fb3 100644 --- a/arch/arm/mach-omap2/board-generic.c +++ b/arch/arm/mach-omap2/board-generic.c @@ -16,6 +16,7 @@ #include <linux/of_platform.h> #include <linux/irqdomain.h> +#include <asm/setup.h> #include <asm/mach/arch.h> #include "common.h" @@ -76,8 +77,17 @@ static const char *const n900_boards_compat[] __initconst = { NULL, }; +/* Legacy userspace on Nokia N900 needs ATAGS exported in /proc/atags, + * save them while the data is still not overwritten + */ +static void __init rx51_reserve(void) +{ + save_atags((const struct tag *)(PAGE_OFFSET + 0x100)); + omap_reserve(); +} + DT_MACHINE_START(OMAP3_N900_DT, "Nokia RX-51 board") - .reserve = omap_reserve, + .reserve = rx51_reserve, .map_io = omap3_map_io, .init_early = omap3430_init_early, .init_machine = omap_generic_init, diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c index 14edcd7a2a1d..0a0567f8e8a0 100644 --- a/arch/arm/mach-omap2/board-rx51-peripherals.c +++ b/arch/arm/mach-omap2/board-rx51-peripherals.c @@ -39,7 +39,7 @@ #include <sound/tlv320aic3x.h> #include <sound/tpa6130a2-plat.h> -#include <media/si4713.h> +#include <linux/platform_data/media/si4713.h> #include <linux/platform_data/leds-lp55xx.h> #include <linux/platform_data/tsl2563.h> @@ -48,7 +48,7 @@ #include <video/omap-panel-data.h> #if defined(CONFIG_IR_RX51) || defined(CONFIG_IR_RX51_MODULE) -#include <media/ir-rx51.h> +#include <linux/platform_data/media/ir-rx51.h> #endif #include "mux.h" diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c index 2a6e0ae2b920..d1211a40f400 100644 --- a/arch/arm/mach-pxa/devices.c +++ b/arch/arm/mach-pxa/devices.c @@ -14,7 +14,7 @@ #include <mach/irqs.h> #include <linux/platform_data/usb-ohci-pxa27x.h> #include <linux/platform_data/keypad-pxa27x.h> -#include <linux/platform_data/camera-pxa.h> +#include <linux/platform_data/media/camera-pxa.h> #include <mach/audio.h> #include <mach/hardware.h> #include <linux/platform_data/mmp_dma.h> diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c index 9d7072b04045..8b1f89e096c6 100644 --- a/arch/arm/mach-pxa/em-x270.c +++ b/arch/arm/mach-pxa/em-x270.c @@ -46,7 +46,7 @@ #include <linux/platform_data/usb-ohci-pxa27x.h> #include <linux/platform_data/mmc-pxamci.h> #include <linux/platform_data/keypad-pxa27x.h> -#include <linux/platform_data/camera-pxa.h> +#include <linux/platform_data/media/camera-pxa.h> #include "generic.h" #include "devices.h" diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c index 7c0d5618be5e..cd6224032109 100644 --- a/arch/arm/mach-pxa/ezx.c +++ b/arch/arm/mach-pxa/ezx.c @@ -34,7 +34,7 @@ #include <linux/platform_data/usb-ohci-pxa27x.h> #include <mach/hardware.h> #include <linux/platform_data/keypad-pxa27x.h> -#include <linux/platform_data/camera-pxa.h> +#include <linux/platform_data/media/camera-pxa.h> #include "devices.h" #include "generic.h" diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c index 3b52b1aa0659..ccfd2b63c6a4 100644 --- a/arch/arm/mach-pxa/mioa701.c +++ b/arch/arm/mach-pxa/mioa701.c @@ -54,7 +54,7 @@ #include <linux/platform_data/mmc-pxamci.h> #include <mach/udc.h> #include <mach/pxa27x-udc.h> -#include <linux/platform_data/camera-pxa.h> +#include <linux/platform_data/media/camera-pxa.h> #include <mach/audio.h> #include <mach/smemc.h> #include <media/soc_camera.h> diff --git a/arch/arm/mach-pxa/palmtreo.c b/arch/arm/mach-pxa/palmtreo.c index d8b937c870de..2dc56062fb7e 100644 --- a/arch/arm/mach-pxa/palmtreo.c +++ b/arch/arm/mach-pxa/palmtreo.c @@ -43,7 +43,7 @@ #include <linux/platform_data/usb-ohci-pxa27x.h> #include <mach/pxa2xx-regs.h> #include <linux/platform_data/asoc-palm27x.h> -#include <linux/platform_data/camera-pxa.h> +#include <linux/platform_data/media/camera-pxa.h> #include <mach/palm27x.h> #include <sound/pxa2xx-lib.h> diff --git a/arch/arm/mach-pxa/palmz72.c b/arch/arm/mach-pxa/palmz72.c index 1a35ddf218da..e3df17a7e8d4 100644 --- a/arch/arm/mach-pxa/palmz72.c +++ b/arch/arm/mach-pxa/palmz72.c @@ -49,7 +49,7 @@ #include <mach/palm27x.h> #include <mach/pm.h> -#include <linux/platform_data/camera-pxa.h> +#include <linux/platform_data/media/camera-pxa.h> #include <media/soc_camera.h> diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c index b71c96f614f9..8459239a093c 100644 --- a/arch/arm/mach-pxa/pcm990-baseboard.c +++ b/arch/arm/mach-pxa/pcm990-baseboard.c @@ -27,10 +27,10 @@ #include <linux/pwm.h> #include <linux/pwm_backlight.h> -#include <media/mt9v022.h> +#include <media/i2c/mt9v022.h> #include <media/soc_camera.h> -#include <linux/platform_data/camera-pxa.h> +#include <linux/platform_data/media/camera-pxa.h> #include <asm/mach/map.h> #include <mach/pxa27x.h> #include <mach/audio.h> diff --git a/arch/arm/mach-sti/Kconfig b/arch/arm/mach-sti/Kconfig index 125865daaf17..12dd1dc0a041 100644 --- a/arch/arm/mach-sti/Kconfig +++ b/arch/arm/mach-sti/Kconfig @@ -3,6 +3,7 @@ menuconfig ARCH_STI select ARM_GIC select ST_IRQCHIP select ARM_GLOBAL_TIMER + select CLKSRC_ST_LPC select PINCTRL select PINCTRL_ST select MFD_SYSCON diff --git a/arch/arm/mach-ux500/Kconfig b/arch/arm/mach-ux500/Kconfig index c9ac19b24e5a..5eacdd61e61c 100644 --- a/arch/arm/mach-ux500/Kconfig +++ b/arch/arm/mach-ux500/Kconfig @@ -32,6 +32,7 @@ config UX500_SOC_DB8500 select PINCTRL_AB8540 select REGULATOR select REGULATOR_DB8500_PRCMU + select CLKSRC_DBX500_PRCMU select PM_GENERIC_DOMAINS if PM config MACH_MOP500 diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index 493692d838c6..9f9d54271aad 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -790,7 +790,7 @@ static const struct l2c_init_data l2c310_init_fns __initconst = { }; static int __init __l2c_init(const struct l2c_init_data *data, - u32 aux_val, u32 aux_mask, u32 cache_id) + u32 aux_val, u32 aux_mask, u32 cache_id, bool nosync) { struct outer_cache_fns fns; unsigned way_size_bits, ways; @@ -866,6 +866,10 @@ static int __init __l2c_init(const struct l2c_init_data *data, fns.configure = outer_cache.configure; if (data->fixup) data->fixup(l2x0_base, cache_id, &fns); + if (nosync) { + pr_info("L2C: disabling outer sync\n"); + fns.sync = NULL; + } /* * Check if l2x0 controller is already enabled. If we are booting @@ -925,7 +929,7 @@ void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) if (data->save) data->save(l2x0_base); - __l2c_init(data, aux_val, aux_mask, cache_id); + __l2c_init(data, aux_val, aux_mask, cache_id, false); } #ifdef CONFIG_OF @@ -1060,6 +1064,18 @@ static void __init l2x0_of_parse(const struct device_node *np, val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT; } + if (of_property_read_bool(np, "arm,parity-enable")) { + mask &= ~L2C_AUX_CTRL_PARITY_ENABLE; + val |= L2C_AUX_CTRL_PARITY_ENABLE; + } else if (of_property_read_bool(np, "arm,parity-disable")) { + mask &= ~L2C_AUX_CTRL_PARITY_ENABLE; + } + + if (of_property_read_bool(np, "arm,shared-override")) { + mask &= ~L2C_AUX_CTRL_SHARED_OVERRIDE; + val |= L2C_AUX_CTRL_SHARED_OVERRIDE; + } + ret = l2x0_cache_size_of_parse(np, aux_val, aux_mask, &assoc, SZ_256K); if (ret) return; @@ -1176,6 +1192,14 @@ static void __init l2c310_of_parse(const struct device_node *np, *aux_mask &= ~L2C_AUX_CTRL_SHARED_OVERRIDE; } + if (of_property_read_bool(np, "arm,parity-enable")) { + *aux_val |= L2C_AUX_CTRL_PARITY_ENABLE; + *aux_mask &= ~L2C_AUX_CTRL_PARITY_ENABLE; + } else if (of_property_read_bool(np, "arm,parity-disable")) { + *aux_val &= ~L2C_AUX_CTRL_PARITY_ENABLE; + *aux_mask &= ~L2C_AUX_CTRL_PARITY_ENABLE; + } + prefetch = l2x0_saved_regs.prefetch_ctrl; ret = of_property_read_u32(np, "arm,double-linefill", &val); @@ -1704,6 +1728,7 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask) struct resource res; u32 cache_id, old_aux; u32 cache_level = 2; + bool nosync = false; np = of_find_matching_node(NULL, l2x0_ids); if (!np) @@ -1742,6 +1767,8 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask) if (cache_level != 2) pr_err("L2C: device tree specifies invalid cache level\n"); + nosync = of_property_read_bool(np, "arm,outer-sync-disable"); + /* Read back current (default) hardware configuration */ if (data->save) data->save(l2x0_base); @@ -1756,6 +1783,6 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask) else cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID); - return __l2c_init(data, aux_val, aux_mask, cache_id); + return __l2c_init(data, aux_val, aux_mask, cache_id, nosync); } #endif diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c index 0502ba17a3ab..a6fa7b73fbe0 100644 --- a/arch/arm/mm/cache-uniphier.c +++ b/arch/arm/mm/cache-uniphier.c @@ -377,17 +377,6 @@ static const struct of_device_id uniphier_cache_match[] __initconst = { { /* sentinel */ } }; -static struct device_node * __init uniphier_cache_get_next_level_node( - struct device_node *np) -{ - u32 phandle; - - if (of_property_read_u32(np, "next-level-cache", &phandle)) - return NULL; - - return of_find_node_by_phandle(phandle); -} - static int __init __uniphier_cache_init(struct device_node *np, unsigned int *cache_level) { @@ -491,7 +480,7 @@ static int __init __uniphier_cache_init(struct device_node *np, * next level cache fails because we want to continue with available * cache levels. */ - next_np = uniphier_cache_get_next_level_node(np); + next_np = of_find_next_cache_node(np); if (next_np) { (*cache_level)++; ret = __uniphier_cache_init(next_np, cache_level); diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 7f8cd1b3557f..49bd08178008 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -192,7 +192,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max_low, #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { - return memblock_is_memory(__pfn_to_phys(pfn)); + return memblock_is_map_memory(__pfn_to_phys(pfn)); } EXPORT_SYMBOL(pfn_valid); #endif @@ -433,6 +433,9 @@ static void __init free_highpages(void) if (end <= max_low) continue; + if (memblock_is_nomap(mem)) + continue; + /* Truncate partial highmem entries */ if (start < max_low) start = max_low; diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c index 0c81056c1dd7..66a978d05958 100644 --- a/arch/arm/mm/ioremap.c +++ b/arch/arm/mm/ioremap.c @@ -30,6 +30,7 @@ #include <asm/cp15.h> #include <asm/cputype.h> #include <asm/cacheflush.h> +#include <asm/early_ioremap.h> #include <asm/mmu_context.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> @@ -469,3 +470,11 @@ int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr) } EXPORT_SYMBOL_GPL(pci_ioremap_io); #endif + +/* + * Must be called after early_fixmap_init + */ +void __init early_ioremap_init(void) +{ + early_ioremap_setup(); +} diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 4867f5daf82c..a87f6cc3fa2b 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -390,7 +390,7 @@ void __init early_fixmap_init(void) * The early fixmap range spans multiple pmds, for which * we are not prepared: */ - BUILD_BUG_ON((__fix_to_virt(__end_of_permanent_fixed_addresses) >> PMD_SHIFT) + BUILD_BUG_ON((__fix_to_virt(__end_of_early_ioremap_region) >> PMD_SHIFT) != FIXADDR_TOP >> PMD_SHIFT); pmd = fixmap_pmd(FIXADDR_TOP); @@ -572,7 +572,7 @@ static void __init build_mem_type_table(void) * in the Short-descriptor translation table format descriptors. */ if (cpu_arch == CPU_ARCH_ARMv7 && - (read_cpuid_ext(CPUID_EXT_MMFR0) & 0xF) == 4) { + (read_cpuid_ext(CPUID_EXT_MMFR0) & 0xF) >= 4) { user_pmd_table |= PMD_PXNTABLE; } #endif @@ -724,30 +724,49 @@ static void __init *early_alloc(unsigned long sz) return early_alloc_aligned(sz, sz); } -static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, unsigned long prot) +static void *__init late_alloc(unsigned long sz) +{ + void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz)); + + BUG_ON(!ptr); + return ptr; +} + +static pte_t * __init pte_alloc(pmd_t *pmd, unsigned long addr, + unsigned long prot, + void *(*alloc)(unsigned long sz)) { if (pmd_none(*pmd)) { - pte_t *pte = early_alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE); + pte_t *pte = alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE); __pmd_populate(pmd, __pa(pte), prot); } BUG_ON(pmd_bad(*pmd)); return pte_offset_kernel(pmd, addr); } +static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, + unsigned long prot) +{ + return pte_alloc(pmd, addr, prot, early_alloc); +} + static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr, unsigned long end, unsigned long pfn, - const struct mem_type *type) + const struct mem_type *type, + void *(*alloc)(unsigned long sz), + bool ng) { - pte_t *pte = early_pte_alloc(pmd, addr, type->prot_l1); + pte_t *pte = pte_alloc(pmd, addr, type->prot_l1, alloc); do { - set_pte_ext(pte, pfn_pte(pfn, __pgprot(type->prot_pte)), 0); + set_pte_ext(pte, pfn_pte(pfn, __pgprot(type->prot_pte)), + ng ? PTE_EXT_NG : 0); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); } static void __init __map_init_section(pmd_t *pmd, unsigned long addr, unsigned long end, phys_addr_t phys, - const struct mem_type *type) + const struct mem_type *type, bool ng) { pmd_t *p = pmd; @@ -765,7 +784,7 @@ static void __init __map_init_section(pmd_t *pmd, unsigned long addr, pmd++; #endif do { - *pmd = __pmd(phys | type->prot_sect); + *pmd = __pmd(phys | type->prot_sect | (ng ? PMD_SECT_nG : 0)); phys += SECTION_SIZE; } while (pmd++, addr += SECTION_SIZE, addr != end); @@ -774,7 +793,8 @@ static void __init __map_init_section(pmd_t *pmd, unsigned long addr, static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end, phys_addr_t phys, - const struct mem_type *type) + const struct mem_type *type, + void *(*alloc)(unsigned long sz), bool ng) { pmd_t *pmd = pmd_offset(pud, addr); unsigned long next; @@ -792,10 +812,10 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, */ if (type->prot_sect && ((addr | next | phys) & ~SECTION_MASK) == 0) { - __map_init_section(pmd, addr, next, phys, type); + __map_init_section(pmd, addr, next, phys, type, ng); } else { alloc_init_pte(pmd, addr, next, - __phys_to_pfn(phys), type); + __phys_to_pfn(phys), type, alloc, ng); } phys += next - addr; @@ -805,21 +825,24 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr, static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end, phys_addr_t phys, - const struct mem_type *type) + const struct mem_type *type, + void *(*alloc)(unsigned long sz), bool ng) { pud_t *pud = pud_offset(pgd, addr); unsigned long next; do { next = pud_addr_end(addr, end); - alloc_init_pmd(pud, addr, next, phys, type); + alloc_init_pmd(pud, addr, next, phys, type, alloc, ng); phys += next - addr; } while (pud++, addr = next, addr != end); } #ifndef CONFIG_ARM_LPAE -static void __init create_36bit_mapping(struct map_desc *md, - const struct mem_type *type) +static void __init create_36bit_mapping(struct mm_struct *mm, + struct map_desc *md, + const struct mem_type *type, + bool ng) { unsigned long addr, length, end; phys_addr_t phys; @@ -859,7 +882,7 @@ static void __init create_36bit_mapping(struct map_desc *md, */ phys |= (((md->pfn >> (32 - PAGE_SHIFT)) & 0xF) << 20); - pgd = pgd_offset_k(addr); + pgd = pgd_offset(mm, addr); end = addr + length; do { pud_t *pud = pud_offset(pgd, addr); @@ -867,7 +890,8 @@ static void __init create_36bit_mapping(struct map_desc *md, int i; for (i = 0; i < 16; i++) - *pmd++ = __pmd(phys | type->prot_sect | PMD_SECT_SUPER); + *pmd++ = __pmd(phys | type->prot_sect | PMD_SECT_SUPER | + (ng ? PMD_SECT_nG : 0)); addr += SUPERSECTION_SIZE; phys += SUPERSECTION_SIZE; @@ -876,33 +900,15 @@ static void __init create_36bit_mapping(struct map_desc *md, } #endif /* !CONFIG_ARM_LPAE */ -/* - * Create the page directory entries and any necessary - * page tables for the mapping specified by `md'. We - * are able to cope here with varying sizes and address - * offsets, and we take full advantage of sections and - * supersections. - */ -static void __init create_mapping(struct map_desc *md) +static void __init __create_mapping(struct mm_struct *mm, struct map_desc *md, + void *(*alloc)(unsigned long sz), + bool ng) { unsigned long addr, length, end; phys_addr_t phys; const struct mem_type *type; pgd_t *pgd; - if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) { - pr_warn("BUG: not creating mapping for 0x%08llx at 0x%08lx in user region\n", - (long long)__pfn_to_phys((u64)md->pfn), md->virtual); - return; - } - - if ((md->type == MT_DEVICE || md->type == MT_ROM) && - md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START && - (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) { - pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n", - (long long)__pfn_to_phys((u64)md->pfn), md->virtual); - } - type = &mem_types[md->type]; #ifndef CONFIG_ARM_LPAE @@ -910,7 +916,7 @@ static void __init create_mapping(struct map_desc *md) * Catch 36-bit addresses */ if (md->pfn >= 0x100000) { - create_36bit_mapping(md, type); + create_36bit_mapping(mm, md, type, ng); return; } #endif @@ -925,12 +931,12 @@ static void __init create_mapping(struct map_desc *md) return; } - pgd = pgd_offset_k(addr); + pgd = pgd_offset(mm, addr); end = addr + length; do { unsigned long next = pgd_addr_end(addr, end); - alloc_init_pud(pgd, addr, next, phys, type); + alloc_init_pud(pgd, addr, next, phys, type, alloc, ng); phys += next - addr; addr = next; @@ -938,6 +944,43 @@ static void __init create_mapping(struct map_desc *md) } /* + * Create the page directory entries and any necessary + * page tables for the mapping specified by `md'. We + * are able to cope here with varying sizes and address + * offsets, and we take full advantage of sections and + * supersections. + */ +static void __init create_mapping(struct map_desc *md) +{ + if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) { + pr_warn("BUG: not creating mapping for 0x%08llx at 0x%08lx in user region\n", + (long long)__pfn_to_phys((u64)md->pfn), md->virtual); + return; + } + + if ((md->type == MT_DEVICE || md->type == MT_ROM) && + md->virtual >= PAGE_OFFSET && md->virtual < FIXADDR_START && + (md->virtual < VMALLOC_START || md->virtual >= VMALLOC_END)) { + pr_warn("BUG: mapping for 0x%08llx at 0x%08lx out of vmalloc space\n", + (long long)__pfn_to_phys((u64)md->pfn), md->virtual); + } + + __create_mapping(&init_mm, md, early_alloc, false); +} + +void __init create_mapping_late(struct mm_struct *mm, struct map_desc *md, + bool ng) +{ +#ifdef CONFIG_ARM_LPAE + pud_t *pud = pud_alloc(mm, pgd_offset(mm, md->virtual), md->virtual); + if (WARN_ON(!pud)) + return; + pmd_alloc(mm, pud, 0); +#endif + __create_mapping(mm, md, late_alloc, ng); +} + +/* * Create the architecture specific mappings */ void __init iotable_init(struct map_desc *io_desc, int nr) @@ -1392,6 +1435,9 @@ static void __init map_lowmem(void) phys_addr_t end = start + reg->size; struct map_desc map; + if (memblock_is_nomap(reg)) + continue; + if (end > arm_lowmem_limit) end = arm_lowmem_limit; if (start >= end) diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 8e1ea433c3f1..0f92d575a304 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -274,10 +274,12 @@ __v7_ca15mp_setup: __v7_b15mp_setup: __v7_ca17mp_setup: mov r10, #0 -1: adr r12, __v7_setup_stack @ the local stack - stmia r12, {r0-r5, lr} @ v7_invalidate_l1 touches r0-r6 +1: adr r0, __v7_setup_stack_ptr + ldr r12, [r0] + add r12, r12, r0 @ the local stack + stmia r12, {r1-r6, lr} @ v7_invalidate_l1 touches r0-r6 bl v7_invalidate_l1 - ldmia r12, {r0-r5, lr} + ldmia r12, {r1-r6, lr} #ifdef CONFIG_SMP ALT_SMP(mrc p15, 0, r0, c1, c0, 1) ALT_UP(mov r0, #(1 << 6)) @ fake it for UP @@ -415,10 +417,12 @@ __v7_pj4b_setup: #endif /* CONFIG_CPU_PJ4B */ __v7_setup: - adr r12, __v7_setup_stack @ the local stack - stmia r12, {r0-r5, lr} @ v7_invalidate_l1 touches r0-r6 + adr r0, __v7_setup_stack_ptr + ldr r12, [r0] + add r12, r12, r0 @ the local stack + stmia r12, {r1-r6, lr} @ v7_invalidate_l1 touches r0-r6 bl v7_invalidate_l1 - ldmia r12, {r0-r5, lr} + ldmia r12, {r1-r6, lr} __v7_setup_cont: and r0, r9, #0xff000000 @ ARM? @@ -480,11 +484,16 @@ __errata_finish: orr r0, r0, r6 @ set them THUMB( orr r0, r0, #1 << 30 ) @ Thumb exceptions ret lr @ return to head.S:__ret + + .align 2 +__v7_setup_stack_ptr: + .word __v7_setup_stack - . ENDPROC(__v7_setup) + .bss .align 2 __v7_setup_stack: - .space 4 * 7 @ 12 registers + .space 4 * 7 @ 7 registers __INITDATA diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S index 67d9209077c6..7229d8d0be1a 100644 --- a/arch/arm/mm/proc-v7m.S +++ b/arch/arm/mm/proc-v7m.S @@ -12,6 +12,7 @@ */ #include <linux/linkage.h> #include <asm/assembler.h> +#include <asm/memory.h> #include <asm/v7m.h> #include "proc-macros.S" @@ -97,19 +98,19 @@ __v7m_setup: mov r5, #0x00800000 str r5, [r0, V7M_SCB_SHPR3] @ set PendSV priority - @ SVC to run the kernel in this mode + @ SVC to switch to handler mode. Notice that this requires sp to + @ point to writeable memory because the processor saves + @ some registers to the stack. badr r1, 1f ldr r5, [r12, #11 * 4] @ read the SVC vector entry str r1, [r12, #11 * 4] @ write the temporary SVC vector entry mov r6, lr @ save LR - mov r7, sp @ save SP - ldr sp, =__v7m_setup_stack_top + ldr sp, =init_thread_union + THREAD_START_SP cpsie i svc #0 1: cpsid i str r5, [r12, #11 * 4] @ restore the original SVC vector entry mov lr, r6 @ restore LR - mov sp, r7 @ restore SP @ Special-purpose control register mov r1, #1 @@ -123,11 +124,6 @@ __v7m_setup: ret lr ENDPROC(__v7m_setup) - .align 2 -__v7m_setup_stack: - .space 4 * 8 @ 8 registers -__v7m_setup_stack_top: - define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" diff --git a/arch/arm/plat-samsung/devs.c b/arch/arm/plat-samsung/devs.c index 82074625de5c..74ef8891254e 100644 --- a/arch/arm/plat-samsung/devs.c +++ b/arch/arm/plat-samsung/devs.c @@ -36,7 +36,7 @@ #include <linux/platform_data/s3c-hsotg.h> #include <linux/platform_data/dma-s3c24xx.h> -#include <media/s5p_hdmi.h> +#include <linux/platform_data/media/s5p_hdmi.h> #include <asm/irq.h> #include <asm/mach/arch.h> diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index fc7ea529f462..75cd7345c654 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -12,6 +12,7 @@ #include <xen/page.h> #include <xen/interface/sched.h> #include <xen/xen-ops.h> +#include <asm/paravirt.h> #include <asm/xen/hypervisor.h> #include <asm/xen/hypercall.h> #include <asm/system_misc.h> @@ -25,6 +26,10 @@ #include <linux/cpufreq.h> #include <linux/cpu.h> #include <linux/console.h> +#include <linux/pvclock_gtod.h> +#include <linux/time64.h> +#include <linux/timekeeping.h> +#include <linux/timekeeper_internal.h> #include <linux/mm.h> @@ -79,6 +84,83 @@ int xen_unmap_domain_gfn_range(struct vm_area_struct *vma, } EXPORT_SYMBOL_GPL(xen_unmap_domain_gfn_range); +static unsigned long long xen_stolen_accounting(int cpu) +{ + struct vcpu_runstate_info state; + + BUG_ON(cpu != smp_processor_id()); + + xen_get_runstate_snapshot(&state); + + WARN_ON(state.state != RUNSTATE_running); + + return state.time[RUNSTATE_runnable] + state.time[RUNSTATE_offline]; +} + +static void xen_read_wallclock(struct timespec64 *ts) +{ + u32 version; + struct timespec64 now, ts_monotonic; + struct shared_info *s = HYPERVISOR_shared_info; + struct pvclock_wall_clock *wall_clock = &(s->wc); + + /* get wallclock at system boot */ + do { + version = wall_clock->version; + rmb(); /* fetch version before time */ + now.tv_sec = ((uint64_t)wall_clock->sec_hi << 32) | wall_clock->sec; + now.tv_nsec = wall_clock->nsec; + rmb(); /* fetch time before checking version */ + } while ((wall_clock->version & 1) || (version != wall_clock->version)); + + /* time since system boot */ + ktime_get_ts64(&ts_monotonic); + *ts = timespec64_add(now, ts_monotonic); +} + +static int xen_pvclock_gtod_notify(struct notifier_block *nb, + unsigned long was_set, void *priv) +{ + /* Protected by the calling core code serialization */ + static struct timespec64 next_sync; + + struct xen_platform_op op; + struct timespec64 now, system_time; + struct timekeeper *tk = priv; + + now.tv_sec = tk->xtime_sec; + now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); + system_time = timespec64_add(now, tk->wall_to_monotonic); + + /* + * We only take the expensive HV call when the clock was set + * or when the 11 minutes RTC synchronization time elapsed. + */ + if (!was_set && timespec64_compare(&now, &next_sync) < 0) + return NOTIFY_OK; + + op.cmd = XENPF_settime64; + op.u.settime64.mbz = 0; + op.u.settime64.secs = now.tv_sec; + op.u.settime64.nsecs = now.tv_nsec; + op.u.settime64.system_time = timespec64_to_ns(&system_time); + (void)HYPERVISOR_platform_op(&op); + + /* + * Move the next drift compensation time 11 minutes + * ahead. That's emulating the sync_cmos_clock() update for + * the hardware RTC. + */ + next_sync = now; + next_sync.tv_sec += 11 * 60; + + return NOTIFY_OK; +} + +static struct notifier_block xen_pvclock_gtod_notifier = { + .notifier_call = xen_pvclock_gtod_notify, +}; + static void xen_percpu_init(void) { struct vcpu_register_vcpu_info info; @@ -104,6 +186,8 @@ static void xen_percpu_init(void) BUG_ON(err); per_cpu(xen_vcpu, cpu) = vcpup; + xen_setup_runstate_info(cpu); + after_register_vcpu_info: enable_percpu_irq(xen_events_irq, 0); put_cpu(); @@ -271,6 +355,11 @@ static int __init xen_guest_init(void) register_cpu_notifier(&xen_cpu_notifier); + pv_time_ops.steal_clock = xen_stolen_accounting; + static_key_slow_inc(¶virt_steal_enabled); + if (xen_initial_domain()) + pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier); + return 0; } early_initcall(xen_guest_init); @@ -282,6 +371,11 @@ static int __init xen_pm_init(void) pm_power_off = xen_power_off; arm_pm_restart = xen_restart; + if (!xen_initial_domain()) { + struct timespec64 ts; + xen_read_wallclock(&ts); + do_settimeofday64(&ts); + } return 0; } @@ -307,5 +401,6 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op); EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op); EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op); EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op); +EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op); EXPORT_SYMBOL_GPL(HYPERVISOR_multicall); EXPORT_SYMBOL_GPL(privcmd_call); diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S index 10fd99c568c6..9a36f4f49c10 100644 --- a/arch/arm/xen/hypercall.S +++ b/arch/arm/xen/hypercall.S @@ -89,6 +89,7 @@ HYPERCALL2(memory_op); HYPERCALL2(physdev_op); HYPERCALL3(vcpu_op); HYPERCALL1(tmem_op); +HYPERCALL1(platform_op_raw); HYPERCALL2(multicall); ENTRY(privcmd_call) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 871f21783866..d6ebffdc6bb1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -70,6 +70,7 @@ config ARM64 select HAVE_FUNCTION_GRAPH_TRACER select HAVE_GENERIC_DMA_COHERENT select HAVE_HW_BREAKPOINT if PERF_EVENTS + select HAVE_IRQ_TIME_ACCOUNTING select HAVE_MEMBLOCK select HAVE_PATA_PLATFORM select HAVE_PERF_EVENTS @@ -92,6 +93,7 @@ config ARM64 select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE select HAVE_CONTEXT_TRACKING + select HAVE_ARM_SMCCC help ARM 64-bit (AArch64) Linux support. @@ -529,9 +531,6 @@ config HW_PERF_EVENTS config SYS_SUPPORTS_HUGETLBFS def_bool y -config ARCH_WANT_GENERAL_HUGETLB - def_bool y - config ARCH_WANT_HUGE_PMD_SHARE def_bool y if ARM64_4K_PAGES || (ARM64_16K_PAGES && !ARM64_VA_BITS_36) @@ -556,6 +555,25 @@ config SECCOMP and the task is only allowed to execute a few safe syscalls defined by each seccomp mode. +config PARAVIRT + bool "Enable paravirtualization code" + help + This changes the kernel so it can modify itself when it is run + under a hypervisor, potentially improving performance significantly + over full virtualization. + +config PARAVIRT_TIME_ACCOUNTING + bool "Paravirtual steal time accounting" + select PARAVIRT + default n + help + Select this option to enable fine granularity task steal time + accounting. Time spent executing other tasks in parallel with + the current vCPU is discounted from the vCPU power. To account for + that, there can be a small performance impact. + + If in doubt, say N here. + config XEN_DOM0 def_bool y depends on XEN @@ -564,6 +582,7 @@ config XEN bool "Xen guest support on ARM64" depends on ARM64 && OF select SWIOTLB_XEN + select PARAVIRT help Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64. diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index d56ec0715157..e4962f04201e 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -19,7 +19,6 @@ struct alt_instr { void __init apply_alternatives_all(void); void apply_alternatives(void *start, size_t length); -void free_alternatives_memory(void); #define ALTINSTR_ENTRY(feature) \ " .word 661b - .\n" /* label */ \ diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 12eff928ef8b..bb7b72734c24 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -193,6 +193,17 @@ lr .req x30 // link register str \src, [\tmp, :lo12:\sym] .endm + /* + * @sym: The name of the per-cpu variable + * @reg: Result of per_cpu(sym, smp_processor_id()) + * @tmp: scratch register + */ + .macro this_cpu_ptr, sym, reg, tmp + adr_l \reg, \sym + mrs \tmp, tpidr_el1 + add \reg, \reg, \tmp + .endm + /* * Annotate a function as position independent, i.e., safe to be called before * the kernel virtual mapping is activated. diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index 54efedaf331f..7fc294c3bc5b 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -68,6 +68,7 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end); extern void flush_icache_range(unsigned long start, unsigned long end); extern void __flush_dcache_area(void *addr, size_t len); +extern void __clean_dcache_area_pou(void *addr, size_t len); extern long __flush_cache_user_range(unsigned long start, unsigned long end); static inline void flush_cache_mm(struct mm_struct *mm) diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index 9ea611ea69df..510c7b404454 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -19,7 +19,6 @@ #define __ASM_CMPXCHG_H #include <linux/bug.h> -#include <linux/mmdebug.h> #include <asm/atomic.h> #include <asm/barrier.h> diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index ef572206f1c3..8e88a696c9cb 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -2,7 +2,9 @@ #define _ASM_EFI_H #include <asm/io.h> +#include <asm/mmu_context.h> #include <asm/neon.h> +#include <asm/tlbflush.h> #ifdef CONFIG_EFI extern void efi_init(void); @@ -10,6 +12,8 @@ extern void efi_init(void); #define efi_init() #endif +int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); + #define efi_call_virt(f, ...) \ ({ \ efi_##f##_t *__f; \ @@ -63,6 +67,11 @@ extern void efi_init(void); * Services are enabled and the EFI_RUNTIME_SERVICES bit set. */ +static inline void efi_set_pgd(struct mm_struct *mm) +{ + switch_mm(NULL, mm, NULL); +} + void efi_virtmap_load(void); void efi_virtmap_unload(void); diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h index c5534facf941..3c60f37e48ab 100644 --- a/arch/arm64/include/asm/ftrace.h +++ b/arch/arm64/include/asm/ftrace.h @@ -28,6 +28,8 @@ struct dyn_arch_ftrace { extern unsigned long ftrace_graph_call; +extern void return_to_handler(void); + static inline unsigned long ftrace_call_adjust(unsigned long addr) { /* diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h index bb4052e85dba..bbc1e35aa601 100644 --- a/arch/arm64/include/asm/hugetlb.h +++ b/arch/arm64/include/asm/hugetlb.h @@ -26,36 +26,7 @@ static inline pte_t huge_ptep_get(pte_t *ptep) return *ptep; } -static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) -{ - set_pte_at(mm, addr, ptep, pte); -} - -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - ptep_clear_flush(vma, addr, ptep); -} - -static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - ptep_set_wrprotect(mm, addr, ptep); -} -static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) -{ - return ptep_get_and_clear(mm, addr, ptep); -} - -static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep, - pte_t pte, int dirty) -{ - return ptep_set_access_flags(vma, addr, ptep, pte, dirty); -} static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, @@ -97,4 +68,19 @@ static inline void arch_clear_hugepage_flags(struct page *page) clear_bit(PG_dcache_clean, &page->flags); } +extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writable); +#define arch_make_huge_pte arch_make_huge_pte +extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte); +extern int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty); +extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); +extern void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); +extern void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + #endif /* __ASM_HUGETLB_H */ diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h index 8e8d30684392..b77197d941fc 100644 --- a/arch/arm64/include/asm/irq.h +++ b/arch/arm64/include/asm/irq.h @@ -1,10 +1,45 @@ #ifndef __ASM_IRQ_H #define __ASM_IRQ_H +#define IRQ_STACK_SIZE THREAD_SIZE +#define IRQ_STACK_START_SP THREAD_START_SP + +#ifndef __ASSEMBLER__ + +#include <linux/percpu.h> + #include <asm-generic/irq.h> +#include <asm/thread_info.h> struct pt_regs; +DECLARE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack); + +/* + * The highest address on the stack, and the first to be used. Used to + * find the dummy-stack frame put down by el?_irq() in entry.S, which + * is structured as follows: + * + * ------------ + * | | <- irq_stack_ptr + * top ------------ + * | x19 | <- irq_stack_ptr - 0x08 + * ------------ + * | x29 | <- irq_stack_ptr - 0x10 + * ------------ + * + * where x19 holds a copy of the task stack pointer where the struct pt_regs + * from kernel_entry can be found. + * + */ +#define IRQ_STACK_PTR(cpu) ((unsigned long)per_cpu(irq_stack, cpu) + IRQ_STACK_START_SP) + +/* + * The offset from irq_stack_ptr where entry.S will store the original + * stack pointer. Used by unwind_frame() and dump_backtrace(). + */ +#define IRQ_STACK_TO_TASK_STACK(ptr) (*((unsigned long *)((ptr) - 0x08))) + extern void set_handle_irq(void (*handle_irq)(struct pt_regs *)); static inline int nr_legacy_irqs(void) @@ -12,4 +47,14 @@ static inline int nr_legacy_irqs(void) return 0; } +static inline bool on_irq_stack(unsigned long sp, int cpu) +{ + /* variable names the same as kernel/stacktrace.c */ + unsigned long low = (unsigned long)per_cpu(irq_stack, cpu); + unsigned long high = low + IRQ_STACK_START_SP; + + return (low <= sp && sp <= high); +} + +#endif /* !__ASSEMBLER__ */ #endif diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 5e6857b6bdc4..738a95f93e49 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -125,6 +125,7 @@ #define VTCR_EL2_SL0_LVL1 (1 << 6) #define VTCR_EL2_T0SZ_MASK 0x3f #define VTCR_EL2_T0SZ_40B 24 +#define VTCR_EL2_VS 19 /* * We configure the Stage-2 page tables to always restrict the IPA space to be @@ -169,7 +170,7 @@ #define VTTBR_BADDR_SHIFT (VTTBR_X - 1) #define VTTBR_BADDR_MASK (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT) #define VTTBR_VMID_SHIFT (UL(48)) -#define VTTBR_VMID_MASK (UL(0xFF) << VTTBR_VMID_SHIFT) +#define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT) /* Hyp System Trap Register */ #define HSTR_EL2_T(x) (1 << x) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 5e377101f919..52b777b7d407 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -20,82 +20,6 @@ #include <asm/virt.h> -/* - * 0 is reserved as an invalid value. - * Order *must* be kept in sync with the hyp switch code. - */ -#define MPIDR_EL1 1 /* MultiProcessor Affinity Register */ -#define CSSELR_EL1 2 /* Cache Size Selection Register */ -#define SCTLR_EL1 3 /* System Control Register */ -#define ACTLR_EL1 4 /* Auxiliary Control Register */ -#define CPACR_EL1 5 /* Coprocessor Access Control */ -#define TTBR0_EL1 6 /* Translation Table Base Register 0 */ -#define TTBR1_EL1 7 /* Translation Table Base Register 1 */ -#define TCR_EL1 8 /* Translation Control Register */ -#define ESR_EL1 9 /* Exception Syndrome Register */ -#define AFSR0_EL1 10 /* Auxilary Fault Status Register 0 */ -#define AFSR1_EL1 11 /* Auxilary Fault Status Register 1 */ -#define FAR_EL1 12 /* Fault Address Register */ -#define MAIR_EL1 13 /* Memory Attribute Indirection Register */ -#define VBAR_EL1 14 /* Vector Base Address Register */ -#define CONTEXTIDR_EL1 15 /* Context ID Register */ -#define TPIDR_EL0 16 /* Thread ID, User R/W */ -#define TPIDRRO_EL0 17 /* Thread ID, User R/O */ -#define TPIDR_EL1 18 /* Thread ID, Privileged */ -#define AMAIR_EL1 19 /* Aux Memory Attribute Indirection Register */ -#define CNTKCTL_EL1 20 /* Timer Control Register (EL1) */ -#define PAR_EL1 21 /* Physical Address Register */ -#define MDSCR_EL1 22 /* Monitor Debug System Control Register */ -#define MDCCINT_EL1 23 /* Monitor Debug Comms Channel Interrupt Enable Reg */ - -/* 32bit specific registers. Keep them at the end of the range */ -#define DACR32_EL2 24 /* Domain Access Control Register */ -#define IFSR32_EL2 25 /* Instruction Fault Status Register */ -#define FPEXC32_EL2 26 /* Floating-Point Exception Control Register */ -#define DBGVCR32_EL2 27 /* Debug Vector Catch Register */ -#define NR_SYS_REGS 28 - -/* 32bit mapping */ -#define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */ -#define c0_CSSELR (CSSELR_EL1 * 2)/* Cache Size Selection Register */ -#define c1_SCTLR (SCTLR_EL1 * 2) /* System Control Register */ -#define c1_ACTLR (ACTLR_EL1 * 2) /* Auxiliary Control Register */ -#define c1_CPACR (CPACR_EL1 * 2) /* Coprocessor Access Control */ -#define c2_TTBR0 (TTBR0_EL1 * 2) /* Translation Table Base Register 0 */ -#define c2_TTBR0_high (c2_TTBR0 + 1) /* TTBR0 top 32 bits */ -#define c2_TTBR1 (TTBR1_EL1 * 2) /* Translation Table Base Register 1 */ -#define c2_TTBR1_high (c2_TTBR1 + 1) /* TTBR1 top 32 bits */ -#define c2_TTBCR (TCR_EL1 * 2) /* Translation Table Base Control R. */ -#define c3_DACR (DACR32_EL2 * 2)/* Domain Access Control Register */ -#define c5_DFSR (ESR_EL1 * 2) /* Data Fault Status Register */ -#define c5_IFSR (IFSR32_EL2 * 2)/* Instruction Fault Status Register */ -#define c5_ADFSR (AFSR0_EL1 * 2) /* Auxiliary Data Fault Status R */ -#define c5_AIFSR (AFSR1_EL1 * 2) /* Auxiliary Instr Fault Status R */ -#define c6_DFAR (FAR_EL1 * 2) /* Data Fault Address Register */ -#define c6_IFAR (c6_DFAR + 1) /* Instruction Fault Address Register */ -#define c7_PAR (PAR_EL1 * 2) /* Physical Address Register */ -#define c7_PAR_high (c7_PAR + 1) /* PAR top 32 bits */ -#define c10_PRRR (MAIR_EL1 * 2) /* Primary Region Remap Register */ -#define c10_NMRR (c10_PRRR + 1) /* Normal Memory Remap Register */ -#define c12_VBAR (VBAR_EL1 * 2) /* Vector Base Address Register */ -#define c13_CID (CONTEXTIDR_EL1 * 2) /* Context ID Register */ -#define c13_TID_URW (TPIDR_EL0 * 2) /* Thread ID, User R/W */ -#define c13_TID_URO (TPIDRRO_EL0 * 2)/* Thread ID, User R/O */ -#define c13_TID_PRIV (TPIDR_EL1 * 2) /* Thread ID, Privileged */ -#define c10_AMAIR0 (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */ -#define c10_AMAIR1 (c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */ -#define c14_CNTKCTL (CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */ - -#define cp14_DBGDSCRext (MDSCR_EL1 * 2) -#define cp14_DBGBCR0 (DBGBCR0_EL1 * 2) -#define cp14_DBGBVR0 (DBGBVR0_EL1 * 2) -#define cp14_DBGBXVR0 (cp14_DBGBVR0 + 1) -#define cp14_DBGWCR0 (DBGWCR0_EL1 * 2) -#define cp14_DBGWVR0 (DBGWVR0_EL1 * 2) -#define cp14_DBGDCCINT (MDCCINT_EL1 * 2) - -#define NR_COPRO_REGS (NR_SYS_REGS * 2) - #define ARM_EXCEPTION_IRQ 0 #define ARM_EXCEPTION_TRAP 1 diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 25a40213bd9b..3066328cd86b 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -26,7 +26,6 @@ #include <asm/esr.h> #include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> #include <asm/ptrace.h> #include <asm/cputype.h> diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index a35ce7266aac..689d4c95e12f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -25,7 +25,6 @@ #include <linux/types.h> #include <linux/kvm_types.h> #include <asm/kvm.h> -#include <asm/kvm_asm.h> #include <asm/kvm_mmio.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED @@ -85,6 +84,86 @@ struct kvm_vcpu_fault_info { u64 hpfar_el2; /* Hyp IPA Fault Address Register */ }; +/* + * 0 is reserved as an invalid value. + * Order should be kept in sync with the save/restore code. + */ +enum vcpu_sysreg { + __INVALID_SYSREG__, + MPIDR_EL1, /* MultiProcessor Affinity Register */ + CSSELR_EL1, /* Cache Size Selection Register */ + SCTLR_EL1, /* System Control Register */ + ACTLR_EL1, /* Auxiliary Control Register */ + CPACR_EL1, /* Coprocessor Access Control */ + TTBR0_EL1, /* Translation Table Base Register 0 */ + TTBR1_EL1, /* Translation Table Base Register 1 */ + TCR_EL1, /* Translation Control Register */ + ESR_EL1, /* Exception Syndrome Register */ + AFSR0_EL1, /* Auxilary Fault Status Register 0 */ + AFSR1_EL1, /* Auxilary Fault Status Register 1 */ + FAR_EL1, /* Fault Address Register */ + MAIR_EL1, /* Memory Attribute Indirection Register */ + VBAR_EL1, /* Vector Base Address Register */ + CONTEXTIDR_EL1, /* Context ID Register */ + TPIDR_EL0, /* Thread ID, User R/W */ + TPIDRRO_EL0, /* Thread ID, User R/O */ + TPIDR_EL1, /* Thread ID, Privileged */ + AMAIR_EL1, /* Aux Memory Attribute Indirection Register */ + CNTKCTL_EL1, /* Timer Control Register (EL1) */ + PAR_EL1, /* Physical Address Register */ + MDSCR_EL1, /* Monitor Debug System Control Register */ + MDCCINT_EL1, /* Monitor Debug Comms Channel Interrupt Enable Reg */ + + /* 32bit specific registers. Keep them at the end of the range */ + DACR32_EL2, /* Domain Access Control Register */ + IFSR32_EL2, /* Instruction Fault Status Register */ + FPEXC32_EL2, /* Floating-Point Exception Control Register */ + DBGVCR32_EL2, /* Debug Vector Catch Register */ + + NR_SYS_REGS /* Nothing after this line! */ +}; + +/* 32bit mapping */ +#define c0_MPIDR (MPIDR_EL1 * 2) /* MultiProcessor ID Register */ +#define c0_CSSELR (CSSELR_EL1 * 2)/* Cache Size Selection Register */ +#define c1_SCTLR (SCTLR_EL1 * 2) /* System Control Register */ +#define c1_ACTLR (ACTLR_EL1 * 2) /* Auxiliary Control Register */ +#define c1_CPACR (CPACR_EL1 * 2) /* Coprocessor Access Control */ +#define c2_TTBR0 (TTBR0_EL1 * 2) /* Translation Table Base Register 0 */ +#define c2_TTBR0_high (c2_TTBR0 + 1) /* TTBR0 top 32 bits */ +#define c2_TTBR1 (TTBR1_EL1 * 2) /* Translation Table Base Register 1 */ +#define c2_TTBR1_high (c2_TTBR1 + 1) /* TTBR1 top 32 bits */ +#define c2_TTBCR (TCR_EL1 * 2) /* Translation Table Base Control R. */ +#define c3_DACR (DACR32_EL2 * 2)/* Domain Access Control Register */ +#define c5_DFSR (ESR_EL1 * 2) /* Data Fault Status Register */ +#define c5_IFSR (IFSR32_EL2 * 2)/* Instruction Fault Status Register */ +#define c5_ADFSR (AFSR0_EL1 * 2) /* Auxiliary Data Fault Status R */ +#define c5_AIFSR (AFSR1_EL1 * 2) /* Auxiliary Instr Fault Status R */ +#define c6_DFAR (FAR_EL1 * 2) /* Data Fault Address Register */ +#define c6_IFAR (c6_DFAR + 1) /* Instruction Fault Address Register */ +#define c7_PAR (PAR_EL1 * 2) /* Physical Address Register */ +#define c7_PAR_high (c7_PAR + 1) /* PAR top 32 bits */ +#define c10_PRRR (MAIR_EL1 * 2) /* Primary Region Remap Register */ +#define c10_NMRR (c10_PRRR + 1) /* Normal Memory Remap Register */ +#define c12_VBAR (VBAR_EL1 * 2) /* Vector Base Address Register */ +#define c13_CID (CONTEXTIDR_EL1 * 2) /* Context ID Register */ +#define c13_TID_URW (TPIDR_EL0 * 2) /* Thread ID, User R/W */ +#define c13_TID_URO (TPIDRRO_EL0 * 2)/* Thread ID, User R/O */ +#define c13_TID_PRIV (TPIDR_EL1 * 2) /* Thread ID, Privileged */ +#define c10_AMAIR0 (AMAIR_EL1 * 2) /* Aux Memory Attr Indirection Reg */ +#define c10_AMAIR1 (c10_AMAIR0 + 1)/* Aux Memory Attr Indirection Reg */ +#define c14_CNTKCTL (CNTKCTL_EL1 * 2) /* Timer Control Register (PL1) */ + +#define cp14_DBGDSCRext (MDSCR_EL1 * 2) +#define cp14_DBGBCR0 (DBGBCR0_EL1 * 2) +#define cp14_DBGBVR0 (DBGBVR0_EL1 * 2) +#define cp14_DBGBXVR0 (cp14_DBGBVR0 + 1) +#define cp14_DBGWCR0 (DBGWCR0_EL1 * 2) +#define cp14_DBGWVR0 (DBGWVR0_EL1 * 2) +#define cp14_DBGDCCINT (MDCCINT_EL1 * 2) + +#define NR_COPRO_REGS (NR_SYS_REGS * 2) + struct kvm_cpu_context { struct kvm_regs gp_regs; union { @@ -197,6 +276,12 @@ struct kvm_vcpu_stat { u32 halt_successful_poll; u32 halt_attempted_poll; u32 halt_wakeup; + u32 hvc_exit_stat; + u64 wfe_exit_stat; + u64 wfi_exit_stat; + u64 mmio_exit_user; + u64 mmio_exit_kernel; + u64 exits; }; int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init); diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h index 889c908ee631..fe612a962576 100644 --- a/arch/arm64/include/asm/kvm_mmio.h +++ b/arch/arm64/include/asm/kvm_mmio.h @@ -19,7 +19,6 @@ #define __ARM64_KVM_MMIO_H__ #include <linux/kvm_host.h> -#include <asm/kvm_asm.h> #include <asm/kvm_arm.h> /* diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 61505676d085..0bf8b4320a91 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -20,6 +20,7 @@ #include <asm/page.h> #include <asm/memory.h> +#include <asm/cpufeature.h> /* * As we only have the TTBR0_EL2 register, we cannot express @@ -158,7 +159,6 @@ static inline bool kvm_s2pmd_readonly(pmd_t *pmd) #define PTRS_PER_S2_PGD_SHIFT (KVM_PHYS_SHIFT - PGDIR_SHIFT) #endif #define PTRS_PER_S2_PGD (1 << PTRS_PER_S2_PGD_SHIFT) -#define S2_PGD_ORDER get_order(PTRS_PER_S2_PGD * sizeof(pgd_t)) #define kvm_pgd_index(addr) (((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1)) @@ -302,5 +302,12 @@ static inline void __kvm_extend_hypmap(pgd_t *boot_hyp_pgd, merged_hyp_pgd[idmap_idx] = __pgd(__pa(boot_hyp_pgd) | PMD_TYPE_TABLE); } +static inline unsigned int kvm_get_vmid_bits(void) +{ + int reg = read_system_reg(SYS_ID_AA64MMFR1_EL1); + + return (cpuid_feature_extract_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8; +} + #endif /* __ASSEMBLY__ */ #endif /* __ARM64_KVM_MMU_H__ */ diff --git a/arch/arm64/include/asm/paravirt.h b/arch/arm64/include/asm/paravirt.h new file mode 100644 index 000000000000..fd5f42886251 --- /dev/null +++ b/arch/arm64/include/asm/paravirt.h @@ -0,0 +1,20 @@ +#ifndef _ASM_ARM64_PARAVIRT_H +#define _ASM_ARM64_PARAVIRT_H + +#ifdef CONFIG_PARAVIRT +struct static_key; +extern struct static_key paravirt_steal_enabled; +extern struct static_key paravirt_steal_rq_enabled; + +struct pv_time_ops { + unsigned long long (*steal_clock)(int cpu); +}; +extern struct pv_time_ops pv_time_ops; + +static inline u64 paravirt_steal_clock(int cpu) +{ + return pv_time_ops.steal_clock(cpu); +} +#endif + +#endif diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index d6739e836f7b..5c25b831273d 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -90,7 +90,23 @@ /* * Contiguous page definitions. */ -#define CONT_PTES (_AC(1, UL) << CONT_SHIFT) +#ifdef CONFIG_ARM64_64K_PAGES +#define CONT_PTE_SHIFT 5 +#define CONT_PMD_SHIFT 5 +#elif defined(CONFIG_ARM64_16K_PAGES) +#define CONT_PTE_SHIFT 7 +#define CONT_PMD_SHIFT 5 +#else +#define CONT_PTE_SHIFT 4 +#define CONT_PMD_SHIFT 4 +#endif + +#define CONT_PTES (1 << CONT_PTE_SHIFT) +#define CONT_PTE_SIZE (CONT_PTES * PAGE_SIZE) +#define CONT_PTE_MASK (~(CONT_PTE_SIZE - 1)) +#define CONT_PMDS (1 << CONT_PMD_SHIFT) +#define CONT_PMD_SIZE (CONT_PMDS * PMD_SIZE) +#define CONT_PMD_MASK (~(CONT_PMD_SIZE - 1)) /* the the numerical offset of the PTE within a range of CONT_PTES */ #define CONT_RANGE_OFFSET(addr) (((addr)>>PAGE_SHIFT)&(CONT_PTES-1)) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 63f52b55defe..69d2e2f86bce 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -167,6 +167,16 @@ extern struct page *empty_zero_page; ((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID) +#define pte_valid_young(pte) \ + ((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF)) + +/* + * Could the pte be present in the TLB? We must check mm_tlb_flush_pending + * so that we don't erroneously return false for pages that have been + * remapped as PROT_NONE but are yet to be flushed from the TLB. + */ +#define pte_accessible(mm, pte) \ + (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid_young(pte)) static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { @@ -217,7 +227,8 @@ static inline pte_t pte_mkspecial(pte_t pte) static inline pte_t pte_mkcont(pte_t pte) { - return set_pte_bit(pte, __pgprot(PTE_CONT)); + pte = set_pte_bit(pte, __pgprot(PTE_CONT)); + return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE)); } static inline pte_t pte_mknoncont(pte_t pte) @@ -225,6 +236,11 @@ static inline pte_t pte_mknoncont(pte_t pte) return clear_pte_bit(pte, __pgprot(PTE_CONT)); } +static inline pmd_t pmd_mkcont(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) | PMD_SECT_CONT); +} + static inline void set_pte(pte_t *ptep, pte_t pte) { *ptep = pte; @@ -298,7 +314,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, /* * Hugetlb definitions. */ -#define HUGE_MAX_HSTATE 2 +#define HUGE_MAX_HSTATE 4 #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) @@ -664,7 +680,8 @@ extern int kern_addr_valid(unsigned long addr); #include <asm-generic/pgtable.h> -#define pgtable_cache_init() do { } while (0) +void pgd_cache_init(void); +#define pgtable_cache_init pgd_cache_init /* * On AArch64, the cache coherency is handled via the set_pte_at() function. diff --git a/arch/arm64/include/asm/shmparam.h b/arch/arm64/include/asm/shmparam.h index 4df608a8459e..e368a55ebd22 100644 --- a/arch/arm64/include/asm/shmparam.h +++ b/arch/arm64/include/asm/shmparam.h @@ -21,7 +21,7 @@ * alignment value. Since we don't have aliasing D-caches, the rest of * the time we can safely use PAGE_SIZE. */ -#define COMPAT_SHMLBA 0x4000 +#define COMPAT_SHMLBA (4 * PAGE_SIZE) #include <asm-generic/shmparam.h> diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h index c85e96d174a5..fc9682bfe002 100644 --- a/arch/arm64/include/asm/spinlock.h +++ b/arch/arm64/include/asm/spinlock.h @@ -26,9 +26,28 @@ * The memory barriers are implicit with the load-acquire and store-release * instructions. */ +static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) +{ + unsigned int tmp; + arch_spinlock_t lockval; -#define arch_spin_unlock_wait(lock) \ - do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0) + asm volatile( +" sevl\n" +"1: wfe\n" +"2: ldaxr %w0, %2\n" +" eor %w1, %w0, %w0, ror #16\n" +" cbnz %w1, 1b\n" + ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ +" stxr %w1, %w0, %2\n" +" cbnz %w1, 2b\n", /* Serialise against any concurrent lockers */ + /* LSE atomics */ +" nop\n" +" nop\n") + : "=&r" (lockval), "=&r" (tmp), "+Q" (*lock) + : + : "memory"); +} #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock) diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h index 7318f6d54aa9..801a16dbbdf6 100644 --- a/arch/arm64/include/asm/stacktrace.h +++ b/arch/arm64/include/asm/stacktrace.h @@ -16,14 +16,19 @@ #ifndef __ASM_STACKTRACE_H #define __ASM_STACKTRACE_H +struct task_struct; + struct stackframe { unsigned long fp; unsigned long sp; unsigned long pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + unsigned int graph; +#endif }; -extern int unwind_frame(struct stackframe *frame); -extern void walk_stackframe(struct stackframe *frame, +extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame); +extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data); #endif /* __ASM_STACKTRACE_H */ diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index d48ab5b41f52..4aeebec3d882 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -20,6 +20,8 @@ #ifndef __ASM_SYSREG_H #define __ASM_SYSREG_H +#include <linux/stringify.h> + #include <asm/opcodes.h> /* @@ -208,6 +210,8 @@ #else +#include <linux/types.h> + asm( " .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" " .equ __reg_num_x\\num, \\num\n" @@ -232,6 +236,23 @@ static inline void config_sctlr_el1(u32 clear, u32 set) val |= set; asm volatile("msr sctlr_el1, %0" : : "r" (val)); } + +/* + * Unlike read_cpuid, calls to read_sysreg are never expected to be + * optimized away or replaced with synthetic values. + */ +#define read_sysreg(r) ({ \ + u64 __val; \ + asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \ + __val; \ +}) + +#define write_sysreg(v, r) do { \ + u64 __val = (u64)v; \ + asm volatile("msr " __stringify(r) ", %0" \ + : : "r" (__val)); \ +} while (0) + #endif #endif /* __ASM_SYSREG_H */ diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 90c7ff233735..abd64bd1f6d9 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -73,10 +73,16 @@ register unsigned long current_stack_pointer asm ("sp"); */ static inline struct thread_info *current_thread_info(void) __attribute_const__; +/* + * struct thread_info can be accessed directly via sp_el0. + */ static inline struct thread_info *current_thread_info(void) { - return (struct thread_info *) - (current_stack_pointer & ~(THREAD_SIZE - 1)); + unsigned long sp_el0; + + asm ("mrs %0, sp_el0" : "=r" (sp_el0)); + + return (struct thread_info *)sp_el0; } #define thread_saved_pc(tsk) \ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 474691f8b13a..83cd7e68e83b 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -14,10 +14,10 @@ CFLAGS_REMOVE_return_address.o = -pg arm64-obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ entry-fpsimd.o process.o ptrace.o setup.o signal.o \ sys.o stacktrace.o time.o traps.o io.o vdso.o \ - hyp-stub.o psci.o psci-call.o cpu_ops.o insn.o \ + hyp-stub.o psci.o cpu_ops.o insn.o \ return_address.o cpuinfo.o cpu_errata.o \ cpufeature.o alternative.o cacheinfo.o \ - smp.o smp_spin_table.o topology.o + smp.o smp_spin_table.o topology.o smccc-call.o extra-$(CONFIG_EFI) := efi-entry.o @@ -41,6 +41,7 @@ arm64-obj-$(CONFIG_EFI) += efi.o efi-entry.stub.o arm64-obj-$(CONFIG_PCI) += pci.o arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o arm64-obj-$(CONFIG_ACPI) += acpi.o +arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o obj-y += $(arm64-obj-y) vdso/ obj-m += $(arm64-obj-m) diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index ab9db0e9818c..d2ee1b21a10d 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -158,9 +158,3 @@ void apply_alternatives(void *start, size_t length) __apply_alternatives(®ion); } - -void free_alternatives_memory(void) -{ - free_reserved_area(__alt_instructions, __alt_instructions_end, - 0, "alternatives"); -} diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index 3b6d8cc9dfe0..678f30b05a45 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -26,6 +26,7 @@ #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/io.h> +#include <linux/arm-smccc.h> #include <asm/checksum.h> @@ -68,3 +69,7 @@ EXPORT_SYMBOL(test_and_change_bit); #ifdef CONFIG_FUNCTION_TRACER EXPORT_SYMBOL(_mcount); #endif + + /* arm-smccc */ +EXPORT_SYMBOL(arm_smccc_smc); +EXPORT_SYMBOL(arm_smccc_hvc); diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index 937f5e58a4d3..3e01207917b1 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -62,7 +62,7 @@ struct insn_emulation { }; static LIST_HEAD(insn_emulation); -static int nr_insn_emulated; +static int nr_insn_emulated __initdata; static DEFINE_RAW_SPINLOCK(insn_emulation_lock); static void register_emulation_hooks(struct insn_emulation_ops *ops) @@ -173,7 +173,7 @@ static int update_insn_emulation_mode(struct insn_emulation *insn, return ret; } -static void register_insn_emulation(struct insn_emulation_ops *ops) +static void __init register_insn_emulation(struct insn_emulation_ops *ops) { unsigned long flags; struct insn_emulation *insn; @@ -237,7 +237,7 @@ static struct ctl_table ctl_abi[] = { { } }; -static void register_insn_emulation_sysctl(struct ctl_table *table) +static void __init register_insn_emulation_sysctl(struct ctl_table *table) { unsigned long flags; int i = 0; diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 25de8b244961..fffa4ac6c25a 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -28,6 +28,7 @@ #include <asm/suspend.h> #include <asm/vdso_datapage.h> #include <linux/kbuild.h> +#include <linux/arm-smccc.h> int main(void) { @@ -108,49 +109,11 @@ int main(void) DEFINE(CPU_GP_REGS, offsetof(struct kvm_cpu_context, gp_regs)); DEFINE(CPU_USER_PT_REGS, offsetof(struct kvm_regs, regs)); DEFINE(CPU_FP_REGS, offsetof(struct kvm_regs, fp_regs)); - DEFINE(CPU_SP_EL1, offsetof(struct kvm_regs, sp_el1)); - DEFINE(CPU_ELR_EL1, offsetof(struct kvm_regs, elr_el1)); - DEFINE(CPU_SPSR, offsetof(struct kvm_regs, spsr)); - DEFINE(CPU_SYSREGS, offsetof(struct kvm_cpu_context, sys_regs)); + DEFINE(VCPU_FPEXC32_EL2, offsetof(struct kvm_vcpu, arch.ctxt.sys_regs[FPEXC32_EL2])); DEFINE(VCPU_ESR_EL2, offsetof(struct kvm_vcpu, arch.fault.esr_el2)); DEFINE(VCPU_FAR_EL2, offsetof(struct kvm_vcpu, arch.fault.far_el2)); DEFINE(VCPU_HPFAR_EL2, offsetof(struct kvm_vcpu, arch.fault.hpfar_el2)); - DEFINE(VCPU_DEBUG_FLAGS, offsetof(struct kvm_vcpu, arch.debug_flags)); - DEFINE(VCPU_DEBUG_PTR, offsetof(struct kvm_vcpu, arch.debug_ptr)); - DEFINE(DEBUG_BCR, offsetof(struct kvm_guest_debug_arch, dbg_bcr)); - DEFINE(DEBUG_BVR, offsetof(struct kvm_guest_debug_arch, dbg_bvr)); - DEFINE(DEBUG_WCR, offsetof(struct kvm_guest_debug_arch, dbg_wcr)); - DEFINE(DEBUG_WVR, offsetof(struct kvm_guest_debug_arch, dbg_wvr)); - DEFINE(VCPU_HCR_EL2, offsetof(struct kvm_vcpu, arch.hcr_el2)); - DEFINE(VCPU_MDCR_EL2, offsetof(struct kvm_vcpu, arch.mdcr_el2)); - DEFINE(VCPU_IRQ_LINES, offsetof(struct kvm_vcpu, arch.irq_lines)); DEFINE(VCPU_HOST_CONTEXT, offsetof(struct kvm_vcpu, arch.host_cpu_context)); - DEFINE(VCPU_HOST_DEBUG_STATE, offsetof(struct kvm_vcpu, arch.host_debug_state)); - DEFINE(VCPU_TIMER_CNTV_CTL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl)); - DEFINE(VCPU_TIMER_CNTV_CVAL, offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_cval)); - DEFINE(KVM_TIMER_CNTVOFF, offsetof(struct kvm, arch.timer.cntvoff)); - DEFINE(KVM_TIMER_ENABLED, offsetof(struct kvm, arch.timer.enabled)); - DEFINE(VCPU_KVM, offsetof(struct kvm_vcpu, kvm)); - DEFINE(VCPU_VGIC_CPU, offsetof(struct kvm_vcpu, arch.vgic_cpu)); - DEFINE(VGIC_V2_CPU_HCR, offsetof(struct vgic_cpu, vgic_v2.vgic_hcr)); - DEFINE(VGIC_V2_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr)); - DEFINE(VGIC_V2_CPU_MISR, offsetof(struct vgic_cpu, vgic_v2.vgic_misr)); - DEFINE(VGIC_V2_CPU_EISR, offsetof(struct vgic_cpu, vgic_v2.vgic_eisr)); - DEFINE(VGIC_V2_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr)); - DEFINE(VGIC_V2_CPU_APR, offsetof(struct vgic_cpu, vgic_v2.vgic_apr)); - DEFINE(VGIC_V2_CPU_LR, offsetof(struct vgic_cpu, vgic_v2.vgic_lr)); - DEFINE(VGIC_V3_CPU_SRE, offsetof(struct vgic_cpu, vgic_v3.vgic_sre)); - DEFINE(VGIC_V3_CPU_HCR, offsetof(struct vgic_cpu, vgic_v3.vgic_hcr)); - DEFINE(VGIC_V3_CPU_VMCR, offsetof(struct vgic_cpu, vgic_v3.vgic_vmcr)); - DEFINE(VGIC_V3_CPU_MISR, offsetof(struct vgic_cpu, vgic_v3.vgic_misr)); - DEFINE(VGIC_V3_CPU_EISR, offsetof(struct vgic_cpu, vgic_v3.vgic_eisr)); - DEFINE(VGIC_V3_CPU_ELRSR, offsetof(struct vgic_cpu, vgic_v3.vgic_elrsr)); - DEFINE(VGIC_V3_CPU_AP0R, offsetof(struct vgic_cpu, vgic_v3.vgic_ap0r)); - DEFINE(VGIC_V3_CPU_AP1R, offsetof(struct vgic_cpu, vgic_v3.vgic_ap1r)); - DEFINE(VGIC_V3_CPU_LR, offsetof(struct vgic_cpu, vgic_v3.vgic_lr)); - DEFINE(VGIC_CPU_NR_LR, offsetof(struct vgic_cpu, nr_lr)); - DEFINE(KVM_VTTBR, offsetof(struct kvm, arch.vttbr)); - DEFINE(KVM_VGIC_VCTRL, offsetof(struct kvm, arch.vgic.vctrl_base)); #endif #ifdef CONFIG_CPU_PM DEFINE(CPU_SUSPEND_SZ, sizeof(struct cpu_suspend_ctx)); @@ -161,5 +124,7 @@ int main(void) DEFINE(SLEEP_SAVE_SP_PHYS, offsetof(struct sleep_save_sp, save_ptr_stash_phys)); DEFINE(SLEEP_SAVE_SP_VIRT, offsetof(struct sleep_save_sp, save_ptr_stash)); #endif + DEFINE(ARM_SMCCC_RES_X0_OFFS, offsetof(struct arm_smccc_res, a0)); + DEFINE(ARM_SMCCC_RES_X2_OFFS, offsetof(struct arm_smccc_res, a2)); return 0; } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0669c63281ea..5c90aa490a2b 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -684,7 +684,7 @@ static const struct arm64_cpu_capabilities arm64_hwcaps[] = { {}, }; -static void cap_set_hwcap(const struct arm64_cpu_capabilities *cap) +static void __init cap_set_hwcap(const struct arm64_cpu_capabilities *cap) { switch (cap->hwcap_type) { case CAP_HWCAP: @@ -729,7 +729,7 @@ static bool __maybe_unused cpus_have_hwcap(const struct arm64_cpu_capabilities * return rc; } -static void setup_cpu_hwcaps(void) +static void __init setup_cpu_hwcaps(void) { int i; const struct arm64_cpu_capabilities *hwcaps = arm64_hwcaps; @@ -758,7 +758,8 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, * Run through the enabled capabilities and enable() it on all active * CPUs */ -static void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) +static void __init +enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) { int i; @@ -897,7 +898,7 @@ static inline void set_sys_caps_initialised(void) #endif /* CONFIG_HOTPLUG_CPU */ -static void setup_feature_capabilities(void) +static void __init setup_feature_capabilities(void) { update_cpu_capabilities(arm64_features, "detected feature:"); enable_cpu_capabilities(arm64_features); diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 4eeb17198cfa..b6abc852f2a1 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -11,317 +11,34 @@ * */ -#include <linux/atomic.h> #include <linux/dmi.h> #include <linux/efi.h> -#include <linux/export.h> -#include <linux/memblock.h> -#include <linux/mm_types.h> -#include <linux/bootmem.h> -#include <linux/of.h> -#include <linux/of_fdt.h> -#include <linux/preempt.h> -#include <linux/rbtree.h> -#include <linux/rwsem.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/spinlock.h> +#include <linux/init.h> -#include <asm/cacheflush.h> #include <asm/efi.h> -#include <asm/tlbflush.h> -#include <asm/mmu_context.h> -#include <asm/mmu.h> -#include <asm/pgtable.h> -struct efi_memory_map memmap; - -static u64 efi_system_table; - -static pgd_t efi_pgd[PTRS_PER_PGD] __page_aligned_bss; - -static struct mm_struct efi_mm = { - .mm_rb = RB_ROOT, - .pgd = efi_pgd, - .mm_users = ATOMIC_INIT(2), - .mm_count = ATOMIC_INIT(1), - .mmap_sem = __RWSEM_INITIALIZER(efi_mm.mmap_sem), - .page_table_lock = __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock), - .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), -}; - -static int __init is_normal_ram(efi_memory_desc_t *md) -{ - if (md->attribute & EFI_MEMORY_WB) - return 1; - return 0; -} - -/* - * Translate a EFI virtual address into a physical address: this is necessary, - * as some data members of the EFI system table are virtually remapped after - * SetVirtualAddressMap() has been called. - */ -static phys_addr_t efi_to_phys(unsigned long addr) +int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) { - efi_memory_desc_t *md; - - for_each_efi_memory_desc(&memmap, md) { - if (!(md->attribute & EFI_MEMORY_RUNTIME)) - continue; - if (md->virt_addr == 0) - /* no virtual mapping has been installed by the stub */ - break; - if (md->virt_addr <= addr && - (addr - md->virt_addr) < (md->num_pages << EFI_PAGE_SHIFT)) - return md->phys_addr + addr - md->virt_addr; - } - return addr; -} - -static int __init uefi_init(void) -{ - efi_char16_t *c16; - void *config_tables; - u64 table_size; - char vendor[100] = "unknown"; - int i, retval; - - efi.systab = early_memremap(efi_system_table, - sizeof(efi_system_table_t)); - if (efi.systab == NULL) { - pr_warn("Unable to map EFI system table.\n"); - return -ENOMEM; - } - - set_bit(EFI_BOOT, &efi.flags); - set_bit(EFI_64BIT, &efi.flags); + pteval_t prot_val; /* - * Verify the EFI Table + * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be + * executable, everything else can be mapped with the XN bits + * set. */ - if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) { - pr_err("System table signature incorrect\n"); - retval = -EINVAL; - goto out; - } - if ((efi.systab->hdr.revision >> 16) < 2) - pr_warn("Warning: EFI system table version %d.%02d, expected 2.00 or greater\n", - efi.systab->hdr.revision >> 16, - efi.systab->hdr.revision & 0xffff); - - /* Show what we know for posterity */ - c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor), - sizeof(vendor) * sizeof(efi_char16_t)); - if (c16) { - for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i) - vendor[i] = c16[i]; - vendor[i] = '\0'; - early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t)); - } - - pr_info("EFI v%u.%.02u by %s\n", - efi.systab->hdr.revision >> 16, - efi.systab->hdr.revision & 0xffff, vendor); - - table_size = sizeof(efi_config_table_64_t) * efi.systab->nr_tables; - config_tables = early_memremap(efi_to_phys(efi.systab->tables), - table_size); - if (config_tables == NULL) { - pr_warn("Unable to map EFI config table array.\n"); - retval = -ENOMEM; - goto out; - } - retval = efi_config_parse_tables(config_tables, efi.systab->nr_tables, - sizeof(efi_config_table_64_t), NULL); - - early_memunmap(config_tables, table_size); -out: - early_memunmap(efi.systab, sizeof(efi_system_table_t)); - return retval; -} - -/* - * Return true for RAM regions we want to permanently reserve. - */ -static __init int is_reserve_region(efi_memory_desc_t *md) -{ - switch (md->type) { - case EFI_LOADER_CODE: - case EFI_LOADER_DATA: - case EFI_BOOT_SERVICES_CODE: - case EFI_BOOT_SERVICES_DATA: - case EFI_CONVENTIONAL_MEMORY: - case EFI_PERSISTENT_MEMORY: - return 0; - default: - break; - } - return is_normal_ram(md); -} - -static __init void reserve_regions(void) -{ - efi_memory_desc_t *md; - u64 paddr, npages, size; - - if (efi_enabled(EFI_DBG)) - pr_info("Processing EFI memory map:\n"); - - for_each_efi_memory_desc(&memmap, md) { - paddr = md->phys_addr; - npages = md->num_pages; - - if (efi_enabled(EFI_DBG)) { - char buf[64]; - - pr_info(" 0x%012llx-0x%012llx %s", - paddr, paddr + (npages << EFI_PAGE_SHIFT) - 1, - efi_md_typeattr_format(buf, sizeof(buf), md)); - } - - memrange_efi_to_native(&paddr, &npages); - size = npages << PAGE_SHIFT; - - if (is_normal_ram(md)) - early_init_dt_add_memory_arch(paddr, size); - - if (is_reserve_region(md)) { - memblock_reserve(paddr, size); - if (efi_enabled(EFI_DBG)) - pr_cont("*"); - } - - if (efi_enabled(EFI_DBG)) - pr_cont("\n"); - } - - set_bit(EFI_MEMMAP, &efi.flags); -} - -void __init efi_init(void) -{ - struct efi_fdt_params params; - - /* Grab UEFI information placed in FDT by stub */ - if (!efi_get_fdt_params(¶ms)) - return; - - efi_system_table = params.system_table; - - memblock_reserve(params.mmap & PAGE_MASK, - PAGE_ALIGN(params.mmap_size + (params.mmap & ~PAGE_MASK))); - memmap.phys_map = params.mmap; - memmap.map = early_memremap(params.mmap, params.mmap_size); - if (memmap.map == NULL) { - /* - * If we are booting via UEFI, the UEFI memory map is the only - * description of memory we have, so there is little point in - * proceeding if we cannot access it. - */ - panic("Unable to map EFI memory map.\n"); - } - memmap.map_end = memmap.map + params.mmap_size; - memmap.desc_size = params.desc_size; - memmap.desc_version = params.desc_ver; - - if (uefi_init() < 0) - return; - - reserve_regions(); - early_memunmap(memmap.map, params.mmap_size); -} - -static bool __init efi_virtmap_init(void) -{ - efi_memory_desc_t *md; - - init_new_context(NULL, &efi_mm); - - for_each_efi_memory_desc(&memmap, md) { - pgprot_t prot; - - if (!(md->attribute & EFI_MEMORY_RUNTIME)) - continue; - if (md->virt_addr == 0) - return false; - - pr_info(" EFI remap 0x%016llx => %p\n", - md->phys_addr, (void *)md->virt_addr); - - /* - * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be - * executable, everything else can be mapped with the XN bits - * set. - */ - if (!is_normal_ram(md)) - prot = __pgprot(PROT_DEVICE_nGnRE); - else if (md->type == EFI_RUNTIME_SERVICES_CODE || - !PAGE_ALIGNED(md->phys_addr)) - prot = PAGE_KERNEL_EXEC; - else - prot = PAGE_KERNEL; - - create_pgd_mapping(&efi_mm, md->phys_addr, md->virt_addr, - md->num_pages << EFI_PAGE_SHIFT, - __pgprot(pgprot_val(prot) | PTE_NG)); - } - return true; -} - -/* - * Enable the UEFI Runtime Services if all prerequisites are in place, i.e., - * non-early mapping of the UEFI system table and virtual mappings for all - * EFI_MEMORY_RUNTIME regions. - */ -static int __init arm64_enable_runtime_services(void) -{ - u64 mapsize; - - if (!efi_enabled(EFI_BOOT)) { - pr_info("EFI services will not be available.\n"); - return 0; - } - - if (efi_runtime_disabled()) { - pr_info("EFI runtime services will be disabled.\n"); - return 0; - } - - pr_info("Remapping and enabling EFI services.\n"); - - mapsize = memmap.map_end - memmap.map; - memmap.map = (__force void *)ioremap_cache(memmap.phys_map, - mapsize); - if (!memmap.map) { - pr_err("Failed to remap EFI memory map\n"); - return -ENOMEM; - } - memmap.map_end = memmap.map + mapsize; - efi.memmap = &memmap; - - efi.systab = (__force void *)ioremap_cache(efi_system_table, - sizeof(efi_system_table_t)); - if (!efi.systab) { - pr_err("Failed to remap EFI System Table\n"); - return -ENOMEM; - } - set_bit(EFI_SYSTEM_TABLES, &efi.flags); - - if (!efi_virtmap_init()) { - pr_err("No UEFI virtual mapping was installed -- runtime services will not be available\n"); - return -ENOMEM; - } - - /* Set up runtime services function pointers */ - efi_native_runtime_setup(); - set_bit(EFI_RUNTIME_SERVICES, &efi.flags); - - efi.runtime_version = efi.systab->hdr.revision; - + if ((md->attribute & EFI_MEMORY_WB) == 0) + prot_val = PROT_DEVICE_nGnRE; + else if (md->type == EFI_RUNTIME_SERVICES_CODE || + !PAGE_ALIGNED(md->phys_addr)) + prot_val = pgprot_val(PAGE_KERNEL_EXEC); + else + prot_val = pgprot_val(PAGE_KERNEL); + + create_pgd_mapping(mm, md->phys_addr, md->virt_addr, + md->num_pages << EFI_PAGE_SHIFT, + __pgprot(prot_val | PTE_NG)); return 0; } -early_initcall(arm64_enable_runtime_services); static int __init arm64_dmi_init(void) { @@ -337,23 +54,6 @@ static int __init arm64_dmi_init(void) } core_initcall(arm64_dmi_init); -static void efi_set_pgd(struct mm_struct *mm) -{ - switch_mm(NULL, mm, NULL); -} - -void efi_virtmap_load(void) -{ - preempt_disable(); - efi_set_pgd(&efi_mm); -} - -void efi_virtmap_unload(void) -{ - efi_set_pgd(current->active_mm); - preempt_enable(); -} - /* * UpdateCapsule() depends on the system being shutdown via * ResetSystem(). diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 7ed3d75f6304..1f7f5a2b61bf 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -27,6 +27,7 @@ #include <asm/cpufeature.h> #include <asm/errno.h> #include <asm/esr.h> +#include <asm/irq.h> #include <asm/thread_info.h> #include <asm/unistd.h> @@ -88,9 +89,12 @@ .if \el == 0 mrs x21, sp_el0 - get_thread_info tsk // Ensure MDSCR_EL1.SS is clear, + mov tsk, sp + and tsk, tsk, #~(THREAD_SIZE - 1) // Ensure MDSCR_EL1.SS is clear, ldr x19, [tsk, #TI_FLAGS] // since we can unmask debug disable_step_tsk x19, x20 // exceptions when scheduling. + + mov x29, xzr // fp pointed to user-space .else add x21, sp, #S_FRAME_SIZE .endif @@ -108,6 +112,13 @@ .endif /* + * Set sp_el0 to current thread_info. + */ + .if \el == 0 + msr sp_el0, tsk + .endif + + /* * Registers that may be useful after this macro is invoked: * * x21 - aborted SP @@ -164,8 +175,44 @@ alternative_endif .endm .macro get_thread_info, rd - mov \rd, sp - and \rd, \rd, #~(THREAD_SIZE - 1) // top of stack + mrs \rd, sp_el0 + .endm + + .macro irq_stack_entry + mov x19, sp // preserve the original sp + + /* + * Compare sp with the current thread_info, if the top + * ~(THREAD_SIZE - 1) bits match, we are on a task stack, and + * should switch to the irq stack. + */ + and x25, x19, #~(THREAD_SIZE - 1) + cmp x25, tsk + b.ne 9998f + + this_cpu_ptr irq_stack, x25, x26 + mov x26, #IRQ_STACK_START_SP + add x26, x25, x26 + + /* switch to the irq stack */ + mov sp, x26 + + /* + * Add a dummy stack frame, this non-standard format is fixed up + * by unwind_frame() + */ + stp x29, x19, [sp, #-16]! + mov x29, sp + +9998: + .endm + + /* + * x19 should be preserved between irq_stack_entry and + * irq_stack_exit. + */ + .macro irq_stack_exit + mov sp, x19 .endm /* @@ -183,10 +230,11 @@ tsk .req x28 // current thread_info * Interrupt handling. */ .macro irq_handler - adrp x1, handle_arch_irq - ldr x1, [x1, #:lo12:handle_arch_irq] + ldr_l x1, handle_arch_irq mov x0, sp + irq_stack_entry blr x1 + irq_stack_exit .endm .text @@ -358,10 +406,10 @@ el1_irq: bl trace_hardirqs_off #endif + get_thread_info tsk irq_handler #ifdef CONFIG_PREEMPT - get_thread_info tsk ldr w24, [tsk, #TI_PREEMPT] // get preempt count cbnz w24, 1f // preempt count != 0 ldr x0, [tsk, #TI_FLAGS] // get flags @@ -599,6 +647,8 @@ ENTRY(cpu_switch_to) ldp x29, x9, [x8], #16 ldr lr, [x8] mov sp, x9 + and x9, x9, #~(THREAD_SIZE - 1) + msr sp_el0, x9 ret ENDPROC(cpu_switch_to) @@ -626,14 +676,14 @@ ret_fast_syscall_trace: work_pending: tbnz x1, #TIF_NEED_RESCHED, work_resched /* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */ - ldr x2, [sp, #S_PSTATE] mov x0, sp // 'regs' - tst x2, #PSR_MODE_MASK // user mode regs? - b.ne no_work_pending // returning to kernel enable_irq // enable interrupts for do_notify_resume() bl do_notify_resume b ret_to_user work_resched: +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off // the IRQs are off here, inform the tracing code +#endif bl schedule /* @@ -645,7 +695,6 @@ ret_to_user: and x2, x1, #_TIF_WORK_MASK cbnz x2, work_pending enable_step_tsk x1, x2 -no_work_pending: kernel_exit 0 ENDPROC(ret_to_user) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 4c46c54a3ad7..acc1afd5c749 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -289,7 +289,7 @@ static struct notifier_block fpsimd_cpu_pm_notifier_block = { .notifier_call = fpsimd_cpu_pm_notifier, }; -static void fpsimd_pm_init(void) +static void __init fpsimd_pm_init(void) { cpu_pm_register_notifier(&fpsimd_cpu_pm_notifier_block); } diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c index c851be795080..ebecf9aa33d1 100644 --- a/arch/arm64/kernel/ftrace.c +++ b/arch/arm64/kernel/ftrace.c @@ -29,12 +29,11 @@ static int ftrace_modify_code(unsigned long pc, u32 old, u32 new, /* * Note: - * Due to modules and __init, code can disappear and change, - * we need to protect against faulting as well as code changing. - * We do this by aarch64_insn_*() which use the probe_kernel_*(). - * - * No lock is held here because all the modifications are run - * through stop_machine(). + * We are paranoid about modifying text, as if a bug were to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with aarch64_insn_*() which uses + * probe_kernel_*(), and make sure what we read is what we expected it + * to be before modifying it. */ if (validate) { if (aarch64_insn_read((void *)pc, &replaced)) @@ -93,6 +92,11 @@ int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, return ftrace_modify_code(pc, old, new, true); } +void arch_ftrace_update_code(int command) +{ + ftrace_modify_all_code(command); +} + int __init ftrace_dyn_arch_init(void) { return 0; @@ -125,23 +129,20 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, * on other archs. It's unlikely on AArch64. */ old = *parent; - *parent = return_hooker; trace.func = self_addr; trace.depth = current->curr_ret_stack + 1; /* Only trace if the calling function expects to */ - if (!ftrace_graph_entry(&trace)) { - *parent = old; + if (!ftrace_graph_entry(&trace)) return; - } err = ftrace_push_return_trace(old, self_addr, &trace.depth, frame_pointer); - if (err == -EBUSY) { - *parent = old; + if (err == -EBUSY) return; - } + else + *parent = return_hooker; } #ifdef CONFIG_DYNAMIC_FTRACE diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 23cfc08fc8ba..ffe9c2b6431b 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -415,15 +415,17 @@ ENDPROC(__create_page_tables) */ .set initial_sp, init_thread_union + THREAD_START_SP __mmap_switched: - adr_l x6, __bss_start - adr_l x7, __bss_stop - -1: cmp x6, x7 - b.hs 2f - str xzr, [x6], #8 // Clear BSS - b 1b -2: + // Clear BSS + adr_l x0, __bss_start + mov x1, xzr + adr_l x2, __bss_stop + sub x2, x2, x0 + bl __pi_memset + adr_l sp, initial_sp, x4 + mov x4, sp + and x4, x4, #~(THREAD_SIZE - 1) + msr sp_el0, x4 // Save thread_info str_l x21, __fdt_pointer, x5 // Save FDT pointer str_l x24, memstart_addr, x6 // Save PHYS_OFFSET mov x29, #0 @@ -606,6 +608,8 @@ ENDPROC(secondary_startup) ENTRY(__secondary_switched) ldr x0, [x21] // get secondary_data.stack mov sp, x0 + and x0, x0, #~(THREAD_SIZE - 1) + msr sp_el0, x0 // save thread_info mov x29, #0 b secondary_start_kernel ENDPROC(__secondary_switched) diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c index 9f17ec071ee0..2386b26c0712 100644 --- a/arch/arm64/kernel/irq.c +++ b/arch/arm64/kernel/irq.c @@ -30,6 +30,9 @@ unsigned long irq_err_count; +/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ +DEFINE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack) __aligned(16); + int arch_show_interrupts(struct seq_file *p, int prec) { show_ipi_list(p, prec); diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index f4bc779e62e8..93e970231ca9 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -30,9 +30,6 @@ #include <asm/insn.h> #include <asm/sections.h> -#define AARCH64_INSN_IMM_MOVNZ AARCH64_INSN_IMM_MAX -#define AARCH64_INSN_IMM_MOVK AARCH64_INSN_IMM_16 - void *module_alloc(unsigned long size) { void *p; @@ -75,15 +72,18 @@ static u64 do_reloc(enum aarch64_reloc_op reloc_op, void *place, u64 val) static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len) { - u64 imm_mask = (1 << len) - 1; s64 sval = do_reloc(op, place, val); switch (len) { case 16: *(s16 *)place = sval; + if (sval < S16_MIN || sval > U16_MAX) + return -ERANGE; break; case 32: *(s32 *)place = sval; + if (sval < S32_MIN || sval > U32_MAX) + return -ERANGE; break; case 64: *(s64 *)place = sval; @@ -92,34 +92,23 @@ static int reloc_data(enum aarch64_reloc_op op, void *place, u64 val, int len) pr_err("Invalid length (%d) for data relocation\n", len); return 0; } - - /* - * Extract the upper value bits (including the sign bit) and - * shift them to bit 0. - */ - sval = (s64)(sval & ~(imm_mask >> 1)) >> (len - 1); - - /* - * Overflow has occurred if the value is not representable in - * len bits (i.e the bottom len bits are not sign-extended and - * the top bits are not all zero). - */ - if ((u64)(sval + 1) > 2) - return -ERANGE; - return 0; } +enum aarch64_insn_movw_imm_type { + AARCH64_INSN_IMM_MOVNZ, + AARCH64_INSN_IMM_MOVKZ, +}; + static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, - int lsb, enum aarch64_insn_imm_type imm_type) + int lsb, enum aarch64_insn_movw_imm_type imm_type) { - u64 imm, limit = 0; + u64 imm; s64 sval; u32 insn = le32_to_cpu(*(u32 *)place); sval = do_reloc(op, place, val); - sval >>= lsb; - imm = sval & 0xffff; + imm = sval >> lsb; if (imm_type == AARCH64_INSN_IMM_MOVNZ) { /* @@ -128,7 +117,7 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, * immediate is less than zero. */ insn &= ~(3 << 29); - if ((s64)imm >= 0) { + if (sval >= 0) { /* >=0: Set the instruction to MOVZ (opcode 10b). */ insn |= 2 << 29; } else { @@ -140,29 +129,13 @@ static int reloc_insn_movw(enum aarch64_reloc_op op, void *place, u64 val, */ imm = ~imm; } - imm_type = AARCH64_INSN_IMM_MOVK; } /* Update the instruction with the new encoding. */ - insn = aarch64_insn_encode_immediate(imm_type, insn, imm); + insn = aarch64_insn_encode_immediate(AARCH64_INSN_IMM_16, insn, imm); *(u32 *)place = cpu_to_le32(insn); - /* Shift out the immediate field. */ - sval >>= 16; - - /* - * For unsigned immediates, the overflow check is straightforward. - * For signed immediates, the sign bit is actually the bit past the - * most significant bit of the field. - * The AARCH64_INSN_IMM_16 immediate type is unsigned. - */ - if (imm_type != AARCH64_INSN_IMM_16) { - sval++; - limit++; - } - - /* Check the upper bits depending on the sign of the immediate. */ - if ((u64)sval > limit) + if (imm > U16_MAX) return -ERANGE; return 0; @@ -267,25 +240,25 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, overflow_check = false; case R_AARCH64_MOVW_UABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G1_NC: overflow_check = false; case R_AARCH64_MOVW_UABS_G1: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 16, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G2_NC: overflow_check = false; case R_AARCH64_MOVW_UABS_G2: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 32, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_UABS_G3: /* We're using the top bits so we can't overflow. */ overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 48, - AARCH64_INSN_IMM_16); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_SABS_G0: ovf = reloc_insn_movw(RELOC_OP_ABS, loc, val, 0, @@ -302,7 +275,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_MOVW_PREL_G0_NC: overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0, - AARCH64_INSN_IMM_MOVK); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_PREL_G0: ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 0, @@ -311,7 +284,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_MOVW_PREL_G1_NC: overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16, - AARCH64_INSN_IMM_MOVK); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_PREL_G1: ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 16, @@ -320,7 +293,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs, case R_AARCH64_MOVW_PREL_G2_NC: overflow_check = false; ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32, - AARCH64_INSN_IMM_MOVK); + AARCH64_INSN_IMM_MOVKZ); break; case R_AARCH64_MOVW_PREL_G2: ovf = reloc_insn_movw(RELOC_OP_PREL, loc, val, 32, diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c new file mode 100644 index 000000000000..53f371ed4568 --- /dev/null +++ b/arch/arm64/kernel/paravirt.c @@ -0,0 +1,25 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * Copyright (C) 2013 Citrix Systems + * + * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com> + */ + +#include <linux/export.h> +#include <linux/jump_label.h> +#include <linux/types.h> +#include <asm/paravirt.h> + +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; + +struct pv_time_ops pv_time_ops; +EXPORT_SYMBOL_GPL(pv_time_ops); diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c index 3aa74830cc69..ff4665462a02 100644 --- a/arch/arm64/kernel/perf_callchain.c +++ b/arch/arm64/kernel/perf_callchain.c @@ -164,8 +164,11 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry, frame.fp = regs->regs[29]; frame.sp = regs->sp; frame.pc = regs->pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = current->curr_ret_stack; +#endif - walk_stackframe(&frame, callchain_trace, entry); + walk_stackframe(current, &frame, callchain_trace, entry); } unsigned long perf_instruction_pointer(struct pt_regs *regs) diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index 5b1897e8ca24..f7ab14c4d5df 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -29,60 +29,74 @@ * ARMv8 PMUv3 Performance Events handling code. * Common event types. */ -enum armv8_pmuv3_perf_types { - /* Required events. */ - ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR = 0x00, - ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL = 0x03, - ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS = 0x04, - ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED = 0x10, - ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES = 0x11, - ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED = 0x12, - - /* At least one of the following is required. */ - ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED = 0x08, - ARMV8_PMUV3_PERFCTR_OP_SPEC = 0x1B, - - /* Common architectural events. */ - ARMV8_PMUV3_PERFCTR_MEM_READ = 0x06, - ARMV8_PMUV3_PERFCTR_MEM_WRITE = 0x07, - ARMV8_PMUV3_PERFCTR_EXC_TAKEN = 0x09, - ARMV8_PMUV3_PERFCTR_EXC_EXECUTED = 0x0A, - ARMV8_PMUV3_PERFCTR_CID_WRITE = 0x0B, - ARMV8_PMUV3_PERFCTR_PC_WRITE = 0x0C, - ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH = 0x0D, - ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN = 0x0E, - ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS = 0x0F, - ARMV8_PMUV3_PERFCTR_TTBR_WRITE = 0x1C, - - /* Common microarchitectural events. */ - ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL = 0x01, - ARMV8_PMUV3_PERFCTR_ITLB_REFILL = 0x02, - ARMV8_PMUV3_PERFCTR_DTLB_REFILL = 0x05, - ARMV8_PMUV3_PERFCTR_MEM_ACCESS = 0x13, - ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS = 0x14, - ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB = 0x15, - ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS = 0x16, - ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL = 0x17, - ARMV8_PMUV3_PERFCTR_L2_CACHE_WB = 0x18, - ARMV8_PMUV3_PERFCTR_BUS_ACCESS = 0x19, - ARMV8_PMUV3_PERFCTR_MEM_ERROR = 0x1A, - ARMV8_PMUV3_PERFCTR_BUS_CYCLES = 0x1D, -}; + +/* Required events. */ +#define ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR 0x00 +#define ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL 0x03 +#define ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS 0x04 +#define ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED 0x10 +#define ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES 0x11 +#define ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED 0x12 + +/* At least one of the following is required. */ +#define ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED 0x08 +#define ARMV8_PMUV3_PERFCTR_OP_SPEC 0x1B + +/* Common architectural events. */ +#define ARMV8_PMUV3_PERFCTR_MEM_READ 0x06 +#define ARMV8_PMUV3_PERFCTR_MEM_WRITE 0x07 +#define ARMV8_PMUV3_PERFCTR_EXC_TAKEN 0x09 +#define ARMV8_PMUV3_PERFCTR_EXC_EXECUTED 0x0A +#define ARMV8_PMUV3_PERFCTR_CID_WRITE 0x0B +#define ARMV8_PMUV3_PERFCTR_PC_WRITE 0x0C +#define ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH 0x0D +#define ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN 0x0E +#define ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS 0x0F +#define ARMV8_PMUV3_PERFCTR_TTBR_WRITE 0x1C +#define ARMV8_PMUV3_PERFCTR_CHAIN 0x1E +#define ARMV8_PMUV3_PERFCTR_BR_RETIRED 0x21 + +/* Common microarchitectural events. */ +#define ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL 0x01 +#define ARMV8_PMUV3_PERFCTR_ITLB_REFILL 0x02 +#define ARMV8_PMUV3_PERFCTR_DTLB_REFILL 0x05 +#define ARMV8_PMUV3_PERFCTR_MEM_ACCESS 0x13 +#define ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS 0x14 +#define ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB 0x15 +#define ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS 0x16 +#define ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL 0x17 +#define ARMV8_PMUV3_PERFCTR_L2_CACHE_WB 0x18 +#define ARMV8_PMUV3_PERFCTR_BUS_ACCESS 0x19 +#define ARMV8_PMUV3_PERFCTR_MEM_ERROR 0x1A +#define ARMV8_PMUV3_PERFCTR_BUS_CYCLES 0x1D +#define ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE 0x1F +#define ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE 0x20 +#define ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED 0x22 +#define ARMV8_PMUV3_PERFCTR_STALL_FRONTEND 0x23 +#define ARMV8_PMUV3_PERFCTR_STALL_BACKEND 0x24 +#define ARMV8_PMUV3_PERFCTR_L1D_TLB 0x25 +#define ARMV8_PMUV3_PERFCTR_L1I_TLB 0x26 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE 0x27 +#define ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL 0x28 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE 0x29 +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL 0x2A +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE 0x2B +#define ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB 0x2C +#define ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL 0x2D +#define ARMV8_PMUV3_PERFCTR_L21_TLB_REFILL 0x2E +#define ARMV8_PMUV3_PERFCTR_L2D_TLB 0x2F +#define ARMV8_PMUV3_PERFCTR_L21_TLB 0x30 /* ARMv8 Cortex-A53 specific event types. */ -enum armv8_a53_pmu_perf_types { - ARMV8_A53_PERFCTR_PREFETCH_LINEFILL = 0xC2, -}; +#define ARMV8_A53_PERFCTR_PREFETCH_LINEFILL 0xC2 -/* ARMv8 Cortex-A57 specific event types. */ -enum armv8_a57_perf_types { - ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD = 0x40, - ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST = 0x41, - ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD = 0x42, - ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST = 0x43, - ARMV8_A57_PERFCTR_DTLB_REFILL_LD = 0x4c, - ARMV8_A57_PERFCTR_DTLB_REFILL_ST = 0x4d, -}; +/* ARMv8 Cortex-A57 and Cortex-A72 specific event types. */ +#define ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_LD 0x40 +#define ARMV8_A57_PERFCTR_L1_DCACHE_ACCESS_ST 0x41 +#define ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_LD 0x42 +#define ARMV8_A57_PERFCTR_L1_DCACHE_REFILL_ST 0x43 +#define ARMV8_A57_PERFCTR_DTLB_REFILL_LD 0x4c +#define ARMV8_A57_PERFCTR_DTLB_REFILL_ST 0x4d /* PMUv3 HW events mapping. */ static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = { @@ -106,6 +120,7 @@ static const unsigned armv8_a53_perf_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_BUS_CYCLES] = ARMV8_PMUV3_PERFCTR_BUS_CYCLES, }; +/* ARM Cortex-A57 and Cortex-A72 events mapping. */ static const unsigned armv8_a57_perf_map[PERF_COUNT_HW_MAX] = { PERF_MAP_ALL_UNSUPPORTED, [PERF_COUNT_HW_CPU_CYCLES] = ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES, @@ -178,6 +193,137 @@ static const unsigned armv8_a57_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED, }; +#define ARMV8_EVENT_ATTR_RESOLVE(m) #m +#define ARMV8_EVENT_ATTR(name, config) \ + PMU_EVENT_ATTR_STRING(name, armv8_event_attr_##name, \ + "event=" ARMV8_EVENT_ATTR_RESOLVE(config)) + +ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_PMNC_SW_INCR); +ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1_ICACHE_REFILL); +ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_ITLB_REFILL); +ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1_DCACHE_REFILL); +ARMV8_EVENT_ATTR(l1d_cache, ARMV8_PMUV3_PERFCTR_L1_DCACHE_ACCESS); +ARMV8_EVENT_ATTR(l1d_tlb_refill, ARMV8_PMUV3_PERFCTR_DTLB_REFILL); +ARMV8_EVENT_ATTR(ld_retired, ARMV8_PMUV3_PERFCTR_MEM_READ); +ARMV8_EVENT_ATTR(st_retired, ARMV8_PMUV3_PERFCTR_MEM_WRITE); +ARMV8_EVENT_ATTR(inst_retired, ARMV8_PMUV3_PERFCTR_INSTR_EXECUTED); +ARMV8_EVENT_ATTR(exc_taken, ARMV8_PMUV3_PERFCTR_EXC_TAKEN); +ARMV8_EVENT_ATTR(exc_return, ARMV8_PMUV3_PERFCTR_EXC_EXECUTED); +ARMV8_EVENT_ATTR(cid_write_retired, ARMV8_PMUV3_PERFCTR_CID_WRITE); +ARMV8_EVENT_ATTR(pc_write_retired, ARMV8_PMUV3_PERFCTR_PC_WRITE); +ARMV8_EVENT_ATTR(br_immed_retired, ARMV8_PMUV3_PERFCTR_PC_IMM_BRANCH); +ARMV8_EVENT_ATTR(br_return_retired, ARMV8_PMUV3_PERFCTR_PC_PROC_RETURN); +ARMV8_EVENT_ATTR(unaligned_ldst_retired, ARMV8_PMUV3_PERFCTR_MEM_UNALIGNED_ACCESS); +ARMV8_EVENT_ATTR(br_mis_pred, ARMV8_PMUV3_PERFCTR_PC_BRANCH_MIS_PRED); +ARMV8_EVENT_ATTR(cpu_cycles, ARMV8_PMUV3_PERFCTR_CLOCK_CYCLES); +ARMV8_EVENT_ATTR(br_pred, ARMV8_PMUV3_PERFCTR_PC_BRANCH_PRED); +ARMV8_EVENT_ATTR(mem_access, ARMV8_PMUV3_PERFCTR_MEM_ACCESS); +ARMV8_EVENT_ATTR(l1i_cache, ARMV8_PMUV3_PERFCTR_L1_ICACHE_ACCESS); +ARMV8_EVENT_ATTR(l1d_cache_wb, ARMV8_PMUV3_PERFCTR_L1_DCACHE_WB); +ARMV8_EVENT_ATTR(l2d_cache, ARMV8_PMUV3_PERFCTR_L2_CACHE_ACCESS); +ARMV8_EVENT_ATTR(l2d_cache_refill, ARMV8_PMUV3_PERFCTR_L2_CACHE_REFILL); +ARMV8_EVENT_ATTR(l2d_cache_wb, ARMV8_PMUV3_PERFCTR_L2_CACHE_WB); +ARMV8_EVENT_ATTR(bus_access, ARMV8_PMUV3_PERFCTR_BUS_ACCESS); +ARMV8_EVENT_ATTR(memory_error, ARMV8_PMUV3_PERFCTR_MEM_ERROR); +ARMV8_EVENT_ATTR(inst_spec, ARMV8_PMUV3_PERFCTR_OP_SPEC); +ARMV8_EVENT_ATTR(ttbr_write_retired, ARMV8_PMUV3_PERFCTR_TTBR_WRITE); +ARMV8_EVENT_ATTR(bus_cycles, ARMV8_PMUV3_PERFCTR_BUS_CYCLES); +ARMV8_EVENT_ATTR(chain, ARMV8_PMUV3_PERFCTR_CHAIN); +ARMV8_EVENT_ATTR(l1d_cache_allocate, ARMV8_PMUV3_PERFCTR_L1D_CACHE_ALLOCATE); +ARMV8_EVENT_ATTR(l2d_cache_allocate, ARMV8_PMUV3_PERFCTR_L2D_CACHE_ALLOCATE); +ARMV8_EVENT_ATTR(br_retired, ARMV8_PMUV3_PERFCTR_BR_RETIRED); +ARMV8_EVENT_ATTR(br_mis_pred_retired, ARMV8_PMUV3_PERFCTR_BR_MIS_PRED_RETIRED); +ARMV8_EVENT_ATTR(stall_frontend, ARMV8_PMUV3_PERFCTR_STALL_FRONTEND); +ARMV8_EVENT_ATTR(stall_backend, ARMV8_PMUV3_PERFCTR_STALL_BACKEND); +ARMV8_EVENT_ATTR(l1d_tlb, ARMV8_PMUV3_PERFCTR_L1D_TLB); +ARMV8_EVENT_ATTR(l1i_tlb, ARMV8_PMUV3_PERFCTR_L1I_TLB); +ARMV8_EVENT_ATTR(l2i_cache, ARMV8_PMUV3_PERFCTR_L2I_CACHE); +ARMV8_EVENT_ATTR(l2i_cache_refill, ARMV8_PMUV3_PERFCTR_L2I_CACHE_REFILL); +ARMV8_EVENT_ATTR(l3d_cache_allocate, ARMV8_PMUV3_PERFCTR_L3D_CACHE_ALLOCATE); +ARMV8_EVENT_ATTR(l3d_cache_refill, ARMV8_PMUV3_PERFCTR_L3D_CACHE_REFILL); +ARMV8_EVENT_ATTR(l3d_cache, ARMV8_PMUV3_PERFCTR_L3D_CACHE); +ARMV8_EVENT_ATTR(l3d_cache_wb, ARMV8_PMUV3_PERFCTR_L3D_CACHE_WB); +ARMV8_EVENT_ATTR(l2d_tlb_refill, ARMV8_PMUV3_PERFCTR_L2D_TLB_REFILL); +ARMV8_EVENT_ATTR(l21_tlb_refill, ARMV8_PMUV3_PERFCTR_L21_TLB_REFILL); +ARMV8_EVENT_ATTR(l2d_tlb, ARMV8_PMUV3_PERFCTR_L2D_TLB); +ARMV8_EVENT_ATTR(l21_tlb, ARMV8_PMUV3_PERFCTR_L21_TLB); + +static struct attribute *armv8_pmuv3_event_attrs[] = { + &armv8_event_attr_sw_incr.attr.attr, + &armv8_event_attr_l1i_cache_refill.attr.attr, + &armv8_event_attr_l1i_tlb_refill.attr.attr, + &armv8_event_attr_l1d_cache_refill.attr.attr, + &armv8_event_attr_l1d_cache.attr.attr, + &armv8_event_attr_l1d_tlb_refill.attr.attr, + &armv8_event_attr_ld_retired.attr.attr, + &armv8_event_attr_st_retired.attr.attr, + &armv8_event_attr_inst_retired.attr.attr, + &armv8_event_attr_exc_taken.attr.attr, + &armv8_event_attr_exc_return.attr.attr, + &armv8_event_attr_cid_write_retired.attr.attr, + &armv8_event_attr_pc_write_retired.attr.attr, + &armv8_event_attr_br_immed_retired.attr.attr, + &armv8_event_attr_br_return_retired.attr.attr, + &armv8_event_attr_unaligned_ldst_retired.attr.attr, + &armv8_event_attr_br_mis_pred.attr.attr, + &armv8_event_attr_cpu_cycles.attr.attr, + &armv8_event_attr_br_pred.attr.attr, + &armv8_event_attr_mem_access.attr.attr, + &armv8_event_attr_l1i_cache.attr.attr, + &armv8_event_attr_l1d_cache_wb.attr.attr, + &armv8_event_attr_l2d_cache.attr.attr, + &armv8_event_attr_l2d_cache_refill.attr.attr, + &armv8_event_attr_l2d_cache_wb.attr.attr, + &armv8_event_attr_bus_access.attr.attr, + &armv8_event_attr_memory_error.attr.attr, + &armv8_event_attr_inst_spec.attr.attr, + &armv8_event_attr_ttbr_write_retired.attr.attr, + &armv8_event_attr_bus_cycles.attr.attr, + &armv8_event_attr_chain.attr.attr, + &armv8_event_attr_l1d_cache_allocate.attr.attr, + &armv8_event_attr_l2d_cache_allocate.attr.attr, + &armv8_event_attr_br_retired.attr.attr, + &armv8_event_attr_br_mis_pred_retired.attr.attr, + &armv8_event_attr_stall_frontend.attr.attr, + &armv8_event_attr_stall_backend.attr.attr, + &armv8_event_attr_l1d_tlb.attr.attr, + &armv8_event_attr_l1i_tlb.attr.attr, + &armv8_event_attr_l2i_cache.attr.attr, + &armv8_event_attr_l2i_cache_refill.attr.attr, + &armv8_event_attr_l3d_cache_allocate.attr.attr, + &armv8_event_attr_l3d_cache_refill.attr.attr, + &armv8_event_attr_l3d_cache.attr.attr, + &armv8_event_attr_l3d_cache_wb.attr.attr, + &armv8_event_attr_l2d_tlb_refill.attr.attr, + &armv8_event_attr_l21_tlb_refill.attr.attr, + &armv8_event_attr_l2d_tlb.attr.attr, + &armv8_event_attr_l21_tlb.attr.attr, + NULL, +}; + +static struct attribute_group armv8_pmuv3_events_attr_group = { + .name = "events", + .attrs = armv8_pmuv3_event_attrs, +}; + +PMU_FORMAT_ATTR(event, "config:0-9"); + +static struct attribute *armv8_pmuv3_format_attrs[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group armv8_pmuv3_format_attr_group = { + .name = "format", + .attrs = armv8_pmuv3_format_attrs, +}; + +static const struct attribute_group *armv8_pmuv3_attr_groups[] = { + &armv8_pmuv3_events_attr_group, + &armv8_pmuv3_format_attr_group, + NULL, +}; + /* * Perf Events' indices @@ -574,9 +720,6 @@ static void armv8pmu_reset(void *info) /* Initialize & Reset PMNC: C and P bits. */ armv8pmu_pmcr_write(ARMV8_PMCR_P | ARMV8_PMCR_C); - - /* Disable access from userspace. */ - asm volatile("msr pmuserenr_el0, %0" :: "r" (0)); } static int armv8_pmuv3_map_event(struct perf_event *event) @@ -646,6 +789,7 @@ static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu) armv8_pmu_init(cpu_pmu); cpu_pmu->name = "armv8_cortex_a53"; cpu_pmu->map_event = armv8_a53_map_event; + cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups; return armv8pmu_probe_num_events(cpu_pmu); } @@ -654,6 +798,16 @@ static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu) armv8_pmu_init(cpu_pmu); cpu_pmu->name = "armv8_cortex_a57"; cpu_pmu->map_event = armv8_a57_map_event; + cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups; + return armv8pmu_probe_num_events(cpu_pmu); +} + +static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv8_pmu_init(cpu_pmu); + cpu_pmu->name = "armv8_cortex_a72"; + cpu_pmu->map_event = armv8_a57_map_event; + cpu_pmu->pmu.attr_groups = armv8_pmuv3_attr_groups; return armv8pmu_probe_num_events(cpu_pmu); } @@ -661,6 +815,7 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = { {.compatible = "arm,armv8-pmuv3", .data = armv8_pmuv3_init}, {.compatible = "arm,cortex-a53-pmu", .data = armv8_a53_pmu_init}, {.compatible = "arm,cortex-a57-pmu", .data = armv8_a57_pmu_init}, + {.compatible = "arm,cortex-a72-pmu", .data = armv8_a72_pmu_init}, {}, }; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index f75b540bc3b4..88d742ba19d5 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -344,11 +344,14 @@ unsigned long get_wchan(struct task_struct *p) frame.fp = thread_saved_fp(p); frame.sp = thread_saved_sp(p); frame.pc = thread_saved_pc(p); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = p->curr_ret_stack; +#endif stack_page = (unsigned long)task_stack_page(p); do { if (frame.sp < stack_page || frame.sp >= stack_page + THREAD_SIZE || - unwind_frame(&frame)) + unwind_frame(p, &frame)) return 0; if (!in_sched_functions(frame.pc)) return frame.pc; diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 1971f491bb90..ff7f13239515 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -58,6 +58,12 @@ */ void ptrace_disable(struct task_struct *child) { + /* + * This would be better off in core code, but PTRACE_DETACH has + * grown its fair share of arch-specific worts and changing it + * is likely to cause regressions on obscure architectures. + */ + user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT diff --git a/arch/arm64/kernel/return_address.c b/arch/arm64/kernel/return_address.c index 6c4fd2810ecb..1718706fde83 100644 --- a/arch/arm64/kernel/return_address.c +++ b/arch/arm64/kernel/return_address.c @@ -43,8 +43,11 @@ void *return_address(unsigned int level) frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; frame.pc = (unsigned long)return_address; /* dummy */ +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = current->curr_ret_stack; +#endif - walk_stackframe(&frame, save_return_addr, &data); + walk_stackframe(current, &frame, save_return_addr, &data); if (!data.level) return data.addr; diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index f586f7c875e2..e33fe33876ab 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -173,6 +173,9 @@ ENTRY(cpu_resume) /* load physical address of identity map page table in x1 */ adrp x1, idmap_pg_dir mov sp, x2 + /* save thread_info */ + and x2, x2, #~(THREAD_SIZE - 1) + msr sp_el0, x2 /* * cpu_do_resume expects x0 to contain context physical address * pointer and x1 to contain physical address of 1:1 page tables diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S new file mode 100644 index 000000000000..ae0496fa4235 --- /dev/null +++ b/arch/arm64/kernel/smccc-call.S @@ -0,0 +1,43 @@ +/* + * Copyright (c) 2015, Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License Version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ +#include <linux/linkage.h> +#include <asm/asm-offsets.h> + + .macro SMCCC instr + .cfi_startproc + \instr #0 + ldr x4, [sp] + stp x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS] + stp x2, x3, [x4, #ARM_SMCCC_RES_X2_OFFS] + ret + .cfi_endproc + .endm + +/* + * void arm_smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2, + * unsigned long a3, unsigned long a4, unsigned long a5, + * unsigned long a6, unsigned long a7, struct arm_smccc_res *res) + */ +ENTRY(arm_smccc_smc) + SMCCC smc +ENDPROC(arm_smccc_smc) + +/* + * void arm_smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2, + * unsigned long a3, unsigned long a4, unsigned long a5, + * unsigned long a6, unsigned long a7, struct arm_smccc_res *res) + */ +ENTRY(arm_smccc_hvc) + SMCCC hvc +ENDPROC(arm_smccc_hvc) diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index ccb6078ed9f2..4fad9787ab46 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -17,9 +17,11 @@ */ #include <linux/kernel.h> #include <linux/export.h> +#include <linux/ftrace.h> #include <linux/sched.h> #include <linux/stacktrace.h> +#include <asm/irq.h> #include <asm/stacktrace.h> /* @@ -35,25 +37,83 @@ * ldp x29, x30, [sp] * add sp, sp, #0x10 */ -int notrace unwind_frame(struct stackframe *frame) +int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) { unsigned long high, low; unsigned long fp = frame->fp; + unsigned long irq_stack_ptr; + + /* + * Use raw_smp_processor_id() to avoid false-positives from + * CONFIG_DEBUG_PREEMPT. get_wchan() calls unwind_frame() on sleeping + * task stacks, we can be pre-empted in this case, so + * {raw_,}smp_processor_id() may give us the wrong value. Sleeping + * tasks can't ever be on an interrupt stack, so regardless of cpu, + * the checks will always fail. + */ + irq_stack_ptr = IRQ_STACK_PTR(raw_smp_processor_id()); low = frame->sp; - high = ALIGN(low, THREAD_SIZE); + /* irq stacks are not THREAD_SIZE aligned */ + if (on_irq_stack(frame->sp, raw_smp_processor_id())) + high = irq_stack_ptr; + else + high = ALIGN(low, THREAD_SIZE) - 0x20; - if (fp < low || fp > high - 0x18 || fp & 0xf) + if (fp < low || fp > high || fp & 0xf) return -EINVAL; frame->sp = fp + 0x10; frame->fp = *(unsigned long *)(fp); frame->pc = *(unsigned long *)(fp + 8); +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (tsk && tsk->ret_stack && + (frame->pc == (unsigned long)return_to_handler)) { + /* + * This is a case where function graph tracer has + * modified a return address (LR) in a stack frame + * to hook a function return. + * So replace it to an original value. + */ + frame->pc = tsk->ret_stack[frame->graph--].ret; + } +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + /* + * Check whether we are going to walk through from interrupt stack + * to task stack. + * If we reach the end of the stack - and its an interrupt stack, + * unpack the dummy frame to find the original elr. + * + * Check the frame->fp we read from the bottom of the irq_stack, + * and the original task stack pointer are both in current->stack. + */ + if (frame->sp == irq_stack_ptr) { + struct pt_regs *irq_args; + unsigned long orig_sp = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr); + + if (object_is_on_stack((void *)orig_sp) && + object_is_on_stack((void *)frame->fp)) { + frame->sp = orig_sp; + + /* orig_sp is the saved pt_regs, find the elr */ + irq_args = (struct pt_regs *)orig_sp; + frame->pc = irq_args->pc; + } else { + /* + * This frame has a non-standard format, and we + * didn't fix it, because the data looked wrong. + * Refuse to output this frame. + */ + return -EINVAL; + } + } + return 0; } -void notrace walk_stackframe(struct stackframe *frame, +void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame, int (*fn)(struct stackframe *, void *), void *data) { while (1) { @@ -61,7 +121,7 @@ void notrace walk_stackframe(struct stackframe *frame, if (fn(frame, data)) break; - ret = unwind_frame(frame); + ret = unwind_frame(tsk, frame); if (ret < 0) break; } @@ -112,8 +172,11 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) frame.sp = current_stack_pointer; frame.pc = (unsigned long)save_stack_trace_tsk; } +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = tsk->curr_ret_stack; +#endif - walk_stackframe(&frame, save_trace, &data); + walk_stackframe(tsk, &frame, save_trace, &data); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } diff --git a/arch/arm64/kernel/time.c b/arch/arm64/kernel/time.c index 13339b6ffc1a..59779699a1a4 100644 --- a/arch/arm64/kernel/time.c +++ b/arch/arm64/kernel/time.c @@ -52,8 +52,11 @@ unsigned long profile_pc(struct pt_regs *regs) frame.fp = regs->regs[29]; frame.sp = regs->sp; frame.pc = regs->pc; +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = -1; /* no task info */ +#endif do { - int ret = unwind_frame(&frame); + int ret = unwind_frame(NULL, &frame); if (ret < 0) return 0; } while (in_lock_functions(frame.pc)); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index e9b9b5364393..cbedd724f48e 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -146,17 +146,15 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) { struct stackframe frame; + unsigned long irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id()); + int skip; pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); if (!tsk) tsk = current; - if (regs) { - frame.fp = regs->regs[29]; - frame.sp = regs->sp; - frame.pc = regs->pc; - } else if (tsk == current) { + if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; frame.pc = (unsigned long)dump_backtrace; @@ -168,21 +166,49 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) frame.sp = thread_saved_sp(tsk); frame.pc = thread_saved_pc(tsk); } +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + frame.graph = tsk->curr_ret_stack; +#endif - pr_emerg("Call trace:\n"); + skip = !!regs; + printk("Call trace:\n"); while (1) { unsigned long where = frame.pc; unsigned long stack; int ret; - dump_backtrace_entry(where); - ret = unwind_frame(&frame); + /* skip until specified stack frame */ + if (!skip) { + dump_backtrace_entry(where); + } else if (frame.fp == regs->regs[29]) { + skip = 0; + /* + * Mostly, this is the case where this function is + * called in panic/abort. As exception handler's + * stack frame does not contain the corresponding pc + * at which an exception has taken place, use regs->pc + * instead. + */ + dump_backtrace_entry(regs->pc); + } + ret = unwind_frame(tsk, &frame); if (ret < 0) break; stack = frame.sp; - if (in_exception_text(where)) + if (in_exception_text(where)) { + /* + * If we switched to the irq_stack before calling this + * exception handler, then the pt_regs will be on the + * task stack. The easiest way to tell is if the large + * pt_regs would overlap with the end of the irq_stack. + */ + if (stack < irq_stack_ptr && + (stack + sizeof(struct pt_regs)) > irq_stack_ptr) + stack = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr); + dump_mem("", "Exception stack", stack, stack + sizeof(struct pt_regs), false); + } } } @@ -456,22 +482,22 @@ asmlinkage void bad_mode(struct pt_regs *regs, int reason, unsigned int esr) void __pte_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pte %016lx.\n", file, line, val); + pr_err("%s:%d: bad pte %016lx.\n", file, line, val); } void __pmd_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pmd %016lx.\n", file, line, val); + pr_err("%s:%d: bad pmd %016lx.\n", file, line, val); } void __pud_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pud %016lx.\n", file, line, val); + pr_err("%s:%d: bad pud %016lx.\n", file, line, val); } void __pgd_error(const char *file, int line, unsigned long val) { - pr_crit("%s:%d: bad pgd %016lx.\n", file, line, val); + pr_err("%s:%d: bad pgd %016lx.\n", file, line, val); } /* GENERIC_BUG traps */ diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 71426a78db12..e3928f578891 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -113,7 +113,6 @@ SECTIONS *(.got) /* Global offset table */ } - ALIGN_DEBUG_RO RO_DATA(PAGE_SIZE) EXCEPTION_TABLE(8) NOTES @@ -128,7 +127,6 @@ SECTIONS ARM_EXIT_KEEP(EXIT_TEXT) } - ALIGN_DEBUG_RO_MIN(16) .init.data : { INIT_DATA INIT_SETUP(16) @@ -143,9 +141,6 @@ SECTIONS PERCPU_SECTION(L1_CACHE_BYTES) - . = ALIGN(PAGE_SIZE); - __init_end = .; - . = ALIGN(4); .altinstructions : { __alt_instructions = .; @@ -157,6 +152,8 @@ SECTIONS } . = ALIGN(PAGE_SIZE); + __init_end = .; + _data = .; _sdata = .; RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index 1949fe5f5424..caee9ee8e12a 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -10,6 +10,7 @@ KVM=../../../virt/kvm ARM=../../../arch/arm/kvm obj-$(CONFIG_KVM_ARM_HOST) += kvm.o +obj-$(CONFIG_KVM_ARM_HOST) += hyp/ kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o @@ -22,8 +23,6 @@ kvm-$(CONFIG_KVM_ARM_HOST) += guest.o debug.o reset.o sys_regs.o sys_regs_generi kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v2-emul.o -kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v2-switch.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/vgic-v3-emul.o -kvm-$(CONFIG_KVM_ARM_HOST) += vgic-v3-switch.o kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arch_timer.o diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index d250160d32bc..fcb778899a38 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -28,13 +28,21 @@ #include <asm/cputype.h> #include <asm/uaccess.h> #include <asm/kvm.h> -#include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_coproc.h> #include "trace.h" +#define VM_STAT(x) { #x, offsetof(struct kvm, stat.x), KVM_STAT_VM } +#define VCPU_STAT(x) { #x, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU } + struct kvm_stats_debugfs_item debugfs_entries[] = { + VCPU_STAT(hvc_exit_stat), + VCPU_STAT(wfe_exit_stat), + VCPU_STAT(wfi_exit_stat), + VCPU_STAT(mmio_exit_user), + VCPU_STAT(mmio_exit_kernel), + VCPU_STAT(exits), { NULL } }; diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 15f0477b0d2a..eba89e42f0ed 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -23,6 +23,7 @@ #include <linux/kvm_host.h> #include <asm/esr.h> +#include <asm/kvm_asm.h> #include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> @@ -39,6 +40,7 @@ static int handle_hvc(struct kvm_vcpu *vcpu, struct kvm_run *run) trace_kvm_hvc_arm64(*vcpu_pc(vcpu), vcpu_get_reg(vcpu, 0), kvm_vcpu_hvc_get_imm(vcpu)); + vcpu->stat.hvc_exit_stat++; ret = kvm_psci_call(vcpu); if (ret < 0) { @@ -71,9 +73,11 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) { if (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_WFx_ISS_WFE) { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), true); + vcpu->stat.wfe_exit_stat++; kvm_vcpu_on_spin(vcpu); } else { trace_kvm_wfx_arm64(*vcpu_pc(vcpu), false); + vcpu->stat.wfi_exit_stat++; kvm_vcpu_block(vcpu); } diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S index 178ba2248a98..3e568dcd907b 100644 --- a/arch/arm64/kvm/hyp-init.S +++ b/arch/arm64/kvm/hyp-init.S @@ -94,6 +94,15 @@ __do_hyp_init: */ mrs x5, ID_AA64MMFR0_EL1 bfi x4, x5, #16, #3 + /* + * Read the VMIDBits bits from ID_AA64MMFR1_EL1 and set the VS bit in + * VTCR_EL2. + */ + mrs x5, ID_AA64MMFR1_EL1 + ubfx x5, x5, #5, #1 + lsl x5, x5, #VTCR_EL2_VS + orr x4, x4, x5 + msr vtcr_el2, x4 mrs x4, mair_el1 diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S index 86c289832272..0ccdcbbef3c2 100644 --- a/arch/arm64/kvm/hyp.S +++ b/arch/arm64/kvm/hyp.S @@ -17,910 +17,7 @@ #include <linux/linkage.h> -#include <asm/alternative.h> -#include <asm/asm-offsets.h> #include <asm/assembler.h> -#include <asm/cpufeature.h> -#include <asm/debug-monitors.h> -#include <asm/esr.h> -#include <asm/fpsimdmacros.h> -#include <asm/kvm.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_mmu.h> -#include <asm/memory.h> - -#define CPU_GP_REG_OFFSET(x) (CPU_GP_REGS + x) -#define CPU_XREG_OFFSET(x) CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x) -#define CPU_SPSR_OFFSET(x) CPU_GP_REG_OFFSET(CPU_SPSR + 8*x) -#define CPU_SYSREG_OFFSET(x) (CPU_SYSREGS + 8*x) - - .text - .pushsection .hyp.text, "ax" - .align PAGE_SHIFT - -.macro save_common_regs - // x2: base address for cpu context - // x3: tmp register - - add x3, x2, #CPU_XREG_OFFSET(19) - stp x19, x20, [x3] - stp x21, x22, [x3, #16] - stp x23, x24, [x3, #32] - stp x25, x26, [x3, #48] - stp x27, x28, [x3, #64] - stp x29, lr, [x3, #80] - - mrs x19, sp_el0 - mrs x20, elr_el2 // pc before entering el2 - mrs x21, spsr_el2 // pstate before entering el2 - - stp x19, x20, [x3, #96] - str x21, [x3, #112] - - mrs x22, sp_el1 - mrs x23, elr_el1 - mrs x24, spsr_el1 - - str x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)] - str x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)] - str x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)] -.endm - -.macro restore_common_regs - // x2: base address for cpu context - // x3: tmp register - - ldr x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)] - ldr x23, [x2, #CPU_GP_REG_OFFSET(CPU_ELR_EL1)] - ldr x24, [x2, #CPU_SPSR_OFFSET(KVM_SPSR_EL1)] - - msr sp_el1, x22 - msr elr_el1, x23 - msr spsr_el1, x24 - - add x3, x2, #CPU_XREG_OFFSET(31) // SP_EL0 - ldp x19, x20, [x3] - ldr x21, [x3, #16] - - msr sp_el0, x19 - msr elr_el2, x20 // pc on return from el2 - msr spsr_el2, x21 // pstate on return from el2 - - add x3, x2, #CPU_XREG_OFFSET(19) - ldp x19, x20, [x3] - ldp x21, x22, [x3, #16] - ldp x23, x24, [x3, #32] - ldp x25, x26, [x3, #48] - ldp x27, x28, [x3, #64] - ldp x29, lr, [x3, #80] -.endm - -.macro save_host_regs - save_common_regs -.endm - -.macro restore_host_regs - restore_common_regs -.endm - -.macro save_fpsimd - // x2: cpu context address - // x3, x4: tmp regs - add x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS) - fpsimd_save x3, 4 -.endm - -.macro restore_fpsimd - // x2: cpu context address - // x3, x4: tmp regs - add x3, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS) - fpsimd_restore x3, 4 -.endm - -.macro save_guest_regs - // x0 is the vcpu address - // x1 is the return code, do not corrupt! - // x2 is the cpu context - // x3 is a tmp register - // Guest's x0-x3 are on the stack - - // Compute base to save registers - add x3, x2, #CPU_XREG_OFFSET(4) - stp x4, x5, [x3] - stp x6, x7, [x3, #16] - stp x8, x9, [x3, #32] - stp x10, x11, [x3, #48] - stp x12, x13, [x3, #64] - stp x14, x15, [x3, #80] - stp x16, x17, [x3, #96] - str x18, [x3, #112] - - pop x6, x7 // x2, x3 - pop x4, x5 // x0, x1 - - add x3, x2, #CPU_XREG_OFFSET(0) - stp x4, x5, [x3] - stp x6, x7, [x3, #16] - - save_common_regs -.endm - -.macro restore_guest_regs - // x0 is the vcpu address. - // x2 is the cpu context - // x3 is a tmp register - - // Prepare x0-x3 for later restore - add x3, x2, #CPU_XREG_OFFSET(0) - ldp x4, x5, [x3] - ldp x6, x7, [x3, #16] - push x4, x5 // Push x0-x3 on the stack - push x6, x7 - - // x4-x18 - ldp x4, x5, [x3, #32] - ldp x6, x7, [x3, #48] - ldp x8, x9, [x3, #64] - ldp x10, x11, [x3, #80] - ldp x12, x13, [x3, #96] - ldp x14, x15, [x3, #112] - ldp x16, x17, [x3, #128] - ldr x18, [x3, #144] - - // x19-x29, lr, sp*, elr*, spsr* - restore_common_regs - - // Last bits of the 64bit state - pop x2, x3 - pop x0, x1 - - // Do not touch any register after this! -.endm - -/* - * Macros to perform system register save/restore. - * - * Ordering here is absolutely critical, and must be kept consistent - * in {save,restore}_sysregs, {save,restore}_guest_32bit_state, - * and in kvm_asm.h. - * - * In other words, don't touch any of these unless you know what - * you are doing. - */ -.macro save_sysregs - // x2: base address for cpu context - // x3: tmp register - - add x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1) - - mrs x4, vmpidr_el2 - mrs x5, csselr_el1 - mrs x6, sctlr_el1 - mrs x7, actlr_el1 - mrs x8, cpacr_el1 - mrs x9, ttbr0_el1 - mrs x10, ttbr1_el1 - mrs x11, tcr_el1 - mrs x12, esr_el1 - mrs x13, afsr0_el1 - mrs x14, afsr1_el1 - mrs x15, far_el1 - mrs x16, mair_el1 - mrs x17, vbar_el1 - mrs x18, contextidr_el1 - mrs x19, tpidr_el0 - mrs x20, tpidrro_el0 - mrs x21, tpidr_el1 - mrs x22, amair_el1 - mrs x23, cntkctl_el1 - mrs x24, par_el1 - mrs x25, mdscr_el1 - - stp x4, x5, [x3] - stp x6, x7, [x3, #16] - stp x8, x9, [x3, #32] - stp x10, x11, [x3, #48] - stp x12, x13, [x3, #64] - stp x14, x15, [x3, #80] - stp x16, x17, [x3, #96] - stp x18, x19, [x3, #112] - stp x20, x21, [x3, #128] - stp x22, x23, [x3, #144] - stp x24, x25, [x3, #160] -.endm - -.macro save_debug type - // x4: pointer to register set - // x5: number of registers to skip - // x6..x22 trashed - - adr x22, 1f - add x22, x22, x5, lsl #2 - br x22 -1: - mrs x21, \type\()15_el1 - mrs x20, \type\()14_el1 - mrs x19, \type\()13_el1 - mrs x18, \type\()12_el1 - mrs x17, \type\()11_el1 - mrs x16, \type\()10_el1 - mrs x15, \type\()9_el1 - mrs x14, \type\()8_el1 - mrs x13, \type\()7_el1 - mrs x12, \type\()6_el1 - mrs x11, \type\()5_el1 - mrs x10, \type\()4_el1 - mrs x9, \type\()3_el1 - mrs x8, \type\()2_el1 - mrs x7, \type\()1_el1 - mrs x6, \type\()0_el1 - - adr x22, 1f - add x22, x22, x5, lsl #2 - br x22 -1: - str x21, [x4, #(15 * 8)] - str x20, [x4, #(14 * 8)] - str x19, [x4, #(13 * 8)] - str x18, [x4, #(12 * 8)] - str x17, [x4, #(11 * 8)] - str x16, [x4, #(10 * 8)] - str x15, [x4, #(9 * 8)] - str x14, [x4, #(8 * 8)] - str x13, [x4, #(7 * 8)] - str x12, [x4, #(6 * 8)] - str x11, [x4, #(5 * 8)] - str x10, [x4, #(4 * 8)] - str x9, [x4, #(3 * 8)] - str x8, [x4, #(2 * 8)] - str x7, [x4, #(1 * 8)] - str x6, [x4, #(0 * 8)] -.endm - -.macro restore_sysregs - // x2: base address for cpu context - // x3: tmp register - - add x3, x2, #CPU_SYSREG_OFFSET(MPIDR_EL1) - - ldp x4, x5, [x3] - ldp x6, x7, [x3, #16] - ldp x8, x9, [x3, #32] - ldp x10, x11, [x3, #48] - ldp x12, x13, [x3, #64] - ldp x14, x15, [x3, #80] - ldp x16, x17, [x3, #96] - ldp x18, x19, [x3, #112] - ldp x20, x21, [x3, #128] - ldp x22, x23, [x3, #144] - ldp x24, x25, [x3, #160] - - msr vmpidr_el2, x4 - msr csselr_el1, x5 - msr sctlr_el1, x6 - msr actlr_el1, x7 - msr cpacr_el1, x8 - msr ttbr0_el1, x9 - msr ttbr1_el1, x10 - msr tcr_el1, x11 - msr esr_el1, x12 - msr afsr0_el1, x13 - msr afsr1_el1, x14 - msr far_el1, x15 - msr mair_el1, x16 - msr vbar_el1, x17 - msr contextidr_el1, x18 - msr tpidr_el0, x19 - msr tpidrro_el0, x20 - msr tpidr_el1, x21 - msr amair_el1, x22 - msr cntkctl_el1, x23 - msr par_el1, x24 - msr mdscr_el1, x25 -.endm - -.macro restore_debug type - // x4: pointer to register set - // x5: number of registers to skip - // x6..x22 trashed - - adr x22, 1f - add x22, x22, x5, lsl #2 - br x22 -1: - ldr x21, [x4, #(15 * 8)] - ldr x20, [x4, #(14 * 8)] - ldr x19, [x4, #(13 * 8)] - ldr x18, [x4, #(12 * 8)] - ldr x17, [x4, #(11 * 8)] - ldr x16, [x4, #(10 * 8)] - ldr x15, [x4, #(9 * 8)] - ldr x14, [x4, #(8 * 8)] - ldr x13, [x4, #(7 * 8)] - ldr x12, [x4, #(6 * 8)] - ldr x11, [x4, #(5 * 8)] - ldr x10, [x4, #(4 * 8)] - ldr x9, [x4, #(3 * 8)] - ldr x8, [x4, #(2 * 8)] - ldr x7, [x4, #(1 * 8)] - ldr x6, [x4, #(0 * 8)] - - adr x22, 1f - add x22, x22, x5, lsl #2 - br x22 -1: - msr \type\()15_el1, x21 - msr \type\()14_el1, x20 - msr \type\()13_el1, x19 - msr \type\()12_el1, x18 - msr \type\()11_el1, x17 - msr \type\()10_el1, x16 - msr \type\()9_el1, x15 - msr \type\()8_el1, x14 - msr \type\()7_el1, x13 - msr \type\()6_el1, x12 - msr \type\()5_el1, x11 - msr \type\()4_el1, x10 - msr \type\()3_el1, x9 - msr \type\()2_el1, x8 - msr \type\()1_el1, x7 - msr \type\()0_el1, x6 -.endm - -.macro skip_32bit_state tmp, target - // Skip 32bit state if not needed - mrs \tmp, hcr_el2 - tbnz \tmp, #HCR_RW_SHIFT, \target -.endm - -.macro skip_tee_state tmp, target - // Skip ThumbEE state if not needed - mrs \tmp, id_pfr0_el1 - tbz \tmp, #12, \target -.endm - -.macro skip_debug_state tmp, target - ldr \tmp, [x0, #VCPU_DEBUG_FLAGS] - tbz \tmp, #KVM_ARM64_DEBUG_DIRTY_SHIFT, \target -.endm - -/* - * Branch to target if CPTR_EL2.TFP bit is set (VFP/SIMD trapping enabled) - */ -.macro skip_fpsimd_state tmp, target - mrs \tmp, cptr_el2 - tbnz \tmp, #CPTR_EL2_TFP_SHIFT, \target -.endm - -.macro compute_debug_state target - // Compute debug state: If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY - // is set, we do a full save/restore cycle and disable trapping. - add x25, x0, #VCPU_CONTEXT - - // Check the state of MDSCR_EL1 - ldr x25, [x25, #CPU_SYSREG_OFFSET(MDSCR_EL1)] - and x26, x25, #DBG_MDSCR_KDE - and x25, x25, #DBG_MDSCR_MDE - adds xzr, x25, x26 - b.eq 9998f // Nothing to see there - - // If any interesting bits was set, we must set the flag - mov x26, #KVM_ARM64_DEBUG_DIRTY - str x26, [x0, #VCPU_DEBUG_FLAGS] - b 9999f // Don't skip restore - -9998: - // Otherwise load the flags from memory in case we recently - // trapped - skip_debug_state x25, \target -9999: -.endm - -.macro save_guest_32bit_state - skip_32bit_state x3, 1f - - add x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT) - mrs x4, spsr_abt - mrs x5, spsr_und - mrs x6, spsr_irq - mrs x7, spsr_fiq - stp x4, x5, [x3] - stp x6, x7, [x3, #16] - - add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2) - mrs x4, dacr32_el2 - mrs x5, ifsr32_el2 - stp x4, x5, [x3] - - skip_fpsimd_state x8, 2f - mrs x6, fpexc32_el2 - str x6, [x3, #16] -2: - skip_debug_state x8, 1f - mrs x7, dbgvcr32_el2 - str x7, [x3, #24] -1: -.endm - -.macro restore_guest_32bit_state - skip_32bit_state x3, 1f - - add x3, x2, #CPU_SPSR_OFFSET(KVM_SPSR_ABT) - ldp x4, x5, [x3] - ldp x6, x7, [x3, #16] - msr spsr_abt, x4 - msr spsr_und, x5 - msr spsr_irq, x6 - msr spsr_fiq, x7 - - add x3, x2, #CPU_SYSREG_OFFSET(DACR32_EL2) - ldp x4, x5, [x3] - msr dacr32_el2, x4 - msr ifsr32_el2, x5 - - skip_debug_state x8, 1f - ldr x7, [x3, #24] - msr dbgvcr32_el2, x7 -1: -.endm - -.macro activate_traps - ldr x2, [x0, #VCPU_HCR_EL2] - - /* - * We are about to set CPTR_EL2.TFP to trap all floating point - * register accesses to EL2, however, the ARM ARM clearly states that - * traps are only taken to EL2 if the operation would not otherwise - * trap to EL1. Therefore, always make sure that for 32-bit guests, - * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit. - */ - tbnz x2, #HCR_RW_SHIFT, 99f // open code skip_32bit_state - mov x3, #(1 << 30) - msr fpexc32_el2, x3 - isb -99: - msr hcr_el2, x2 - mov x2, #CPTR_EL2_TTA - orr x2, x2, #CPTR_EL2_TFP - msr cptr_el2, x2 - - mov x2, #(1 << 15) // Trap CP15 Cr=15 - msr hstr_el2, x2 - - // Monitor Debug Config - see kvm_arm_setup_debug() - ldr x2, [x0, #VCPU_MDCR_EL2] - msr mdcr_el2, x2 -.endm - -.macro deactivate_traps - mov x2, #HCR_RW - msr hcr_el2, x2 - msr hstr_el2, xzr - - mrs x2, mdcr_el2 - and x2, x2, #MDCR_EL2_HPMN_MASK - msr mdcr_el2, x2 -.endm - -.macro activate_vm - ldr x1, [x0, #VCPU_KVM] - kern_hyp_va x1 - ldr x2, [x1, #KVM_VTTBR] - msr vttbr_el2, x2 -.endm - -.macro deactivate_vm - msr vttbr_el2, xzr -.endm - -/* - * Call into the vgic backend for state saving - */ -.macro save_vgic_state -alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF - bl __save_vgic_v2_state -alternative_else - bl __save_vgic_v3_state -alternative_endif - mrs x24, hcr_el2 - mov x25, #HCR_INT_OVERRIDE - neg x25, x25 - and x24, x24, x25 - msr hcr_el2, x24 -.endm - -/* - * Call into the vgic backend for state restoring - */ -.macro restore_vgic_state - mrs x24, hcr_el2 - ldr x25, [x0, #VCPU_IRQ_LINES] - orr x24, x24, #HCR_INT_OVERRIDE - orr x24, x24, x25 - msr hcr_el2, x24 -alternative_if_not ARM64_HAS_SYSREG_GIC_CPUIF - bl __restore_vgic_v2_state -alternative_else - bl __restore_vgic_v3_state -alternative_endif -.endm - -.macro save_timer_state - // x0: vcpu pointer - ldr x2, [x0, #VCPU_KVM] - kern_hyp_va x2 - ldr w3, [x2, #KVM_TIMER_ENABLED] - cbz w3, 1f - - mrs x3, cntv_ctl_el0 - and x3, x3, #3 - str w3, [x0, #VCPU_TIMER_CNTV_CTL] - - isb - - mrs x3, cntv_cval_el0 - str x3, [x0, #VCPU_TIMER_CNTV_CVAL] - -1: - // Disable the virtual timer - msr cntv_ctl_el0, xzr - - // Allow physical timer/counter access for the host - mrs x2, cnthctl_el2 - orr x2, x2, #3 - msr cnthctl_el2, x2 - - // Clear cntvoff for the host - msr cntvoff_el2, xzr -.endm - -.macro restore_timer_state - // x0: vcpu pointer - // Disallow physical timer access for the guest - // Physical counter access is allowed - mrs x2, cnthctl_el2 - orr x2, x2, #1 - bic x2, x2, #2 - msr cnthctl_el2, x2 - - ldr x2, [x0, #VCPU_KVM] - kern_hyp_va x2 - ldr w3, [x2, #KVM_TIMER_ENABLED] - cbz w3, 1f - - ldr x3, [x2, #KVM_TIMER_CNTVOFF] - msr cntvoff_el2, x3 - ldr x2, [x0, #VCPU_TIMER_CNTV_CVAL] - msr cntv_cval_el0, x2 - isb - - ldr w2, [x0, #VCPU_TIMER_CNTV_CTL] - and x2, x2, #3 - msr cntv_ctl_el0, x2 -1: -.endm - -__save_sysregs: - save_sysregs - ret - -__restore_sysregs: - restore_sysregs - ret - -/* Save debug state */ -__save_debug: - // x2: ptr to CPU context - // x3: ptr to debug reg struct - // x4/x5/x6-22/x24-26: trashed - - mrs x26, id_aa64dfr0_el1 - ubfx x24, x26, #12, #4 // Extract BRPs - ubfx x25, x26, #20, #4 // Extract WRPs - mov w26, #15 - sub w24, w26, w24 // How many BPs to skip - sub w25, w26, w25 // How many WPs to skip - - mov x5, x24 - add x4, x3, #DEBUG_BCR - save_debug dbgbcr - add x4, x3, #DEBUG_BVR - save_debug dbgbvr - - mov x5, x25 - add x4, x3, #DEBUG_WCR - save_debug dbgwcr - add x4, x3, #DEBUG_WVR - save_debug dbgwvr - - mrs x21, mdccint_el1 - str x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] - ret - -/* Restore debug state */ -__restore_debug: - // x2: ptr to CPU context - // x3: ptr to debug reg struct - // x4/x5/x6-22/x24-26: trashed - - mrs x26, id_aa64dfr0_el1 - ubfx x24, x26, #12, #4 // Extract BRPs - ubfx x25, x26, #20, #4 // Extract WRPs - mov w26, #15 - sub w24, w26, w24 // How many BPs to skip - sub w25, w26, w25 // How many WPs to skip - - mov x5, x24 - add x4, x3, #DEBUG_BCR - restore_debug dbgbcr - add x4, x3, #DEBUG_BVR - restore_debug dbgbvr - - mov x5, x25 - add x4, x3, #DEBUG_WCR - restore_debug dbgwcr - add x4, x3, #DEBUG_WVR - restore_debug dbgwvr - - ldr x21, [x2, #CPU_SYSREG_OFFSET(MDCCINT_EL1)] - msr mdccint_el1, x21 - - ret - -__save_fpsimd: - skip_fpsimd_state x3, 1f - save_fpsimd -1: ret - -__restore_fpsimd: - skip_fpsimd_state x3, 1f - restore_fpsimd -1: ret - -switch_to_guest_fpsimd: - push x4, lr - - mrs x2, cptr_el2 - bic x2, x2, #CPTR_EL2_TFP - msr cptr_el2, x2 - isb - - mrs x0, tpidr_el2 - - ldr x2, [x0, #VCPU_HOST_CONTEXT] - kern_hyp_va x2 - bl __save_fpsimd - - add x2, x0, #VCPU_CONTEXT - bl __restore_fpsimd - - skip_32bit_state x3, 1f - ldr x4, [x2, #CPU_SYSREG_OFFSET(FPEXC32_EL2)] - msr fpexc32_el2, x4 -1: - pop x4, lr - pop x2, x3 - pop x0, x1 - - eret - -/* - * u64 __kvm_vcpu_run(struct kvm_vcpu *vcpu); - * - * This is the world switch. The first half of the function - * deals with entering the guest, and anything from __kvm_vcpu_return - * to the end of the function deals with reentering the host. - * On the enter path, only x0 (vcpu pointer) must be preserved until - * the last moment. On the exit path, x0 (vcpu pointer) and x1 (exception - * code) must both be preserved until the epilogue. - * In both cases, x2 points to the CPU context we're saving/restoring from/to. - */ -ENTRY(__kvm_vcpu_run) - kern_hyp_va x0 - msr tpidr_el2, x0 // Save the vcpu register - - // Host context - ldr x2, [x0, #VCPU_HOST_CONTEXT] - kern_hyp_va x2 - - save_host_regs - bl __save_sysregs - - compute_debug_state 1f - add x3, x0, #VCPU_HOST_DEBUG_STATE - bl __save_debug -1: - activate_traps - activate_vm - - restore_vgic_state - restore_timer_state - - // Guest context - add x2, x0, #VCPU_CONTEXT - - // We must restore the 32-bit state before the sysregs, thanks - // to Cortex-A57 erratum #852523. - restore_guest_32bit_state - bl __restore_sysregs - - skip_debug_state x3, 1f - ldr x3, [x0, #VCPU_DEBUG_PTR] - kern_hyp_va x3 - bl __restore_debug -1: - restore_guest_regs - - // That's it, no more messing around. - eret - -__kvm_vcpu_return: - // Assume x0 is the vcpu pointer, x1 the return code - // Guest's x0-x3 are on the stack - - // Guest context - add x2, x0, #VCPU_CONTEXT - - save_guest_regs - bl __save_fpsimd - bl __save_sysregs - - skip_debug_state x3, 1f - ldr x3, [x0, #VCPU_DEBUG_PTR] - kern_hyp_va x3 - bl __save_debug -1: - save_guest_32bit_state - - save_timer_state - save_vgic_state - - deactivate_traps - deactivate_vm - - // Host context - ldr x2, [x0, #VCPU_HOST_CONTEXT] - kern_hyp_va x2 - - bl __restore_sysregs - bl __restore_fpsimd - /* Clear FPSIMD and Trace trapping */ - msr cptr_el2, xzr - - skip_debug_state x3, 1f - // Clear the dirty flag for the next run, as all the state has - // already been saved. Note that we nuke the whole 64bit word. - // If we ever add more flags, we'll have to be more careful... - str xzr, [x0, #VCPU_DEBUG_FLAGS] - add x3, x0, #VCPU_HOST_DEBUG_STATE - bl __restore_debug -1: - restore_host_regs - - mov x0, x1 - ret -END(__kvm_vcpu_run) - -// void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa); -ENTRY(__kvm_tlb_flush_vmid_ipa) - dsb ishst - - kern_hyp_va x0 - ldr x2, [x0, #KVM_VTTBR] - msr vttbr_el2, x2 - isb - - /* - * We could do so much better if we had the VA as well. - * Instead, we invalidate Stage-2 for this IPA, and the - * whole of Stage-1. Weep... - */ - lsr x1, x1, #12 - tlbi ipas2e1is, x1 - /* - * We have to ensure completion of the invalidation at Stage-2, - * since a table walk on another CPU could refill a TLB with a - * complete (S1 + S2) walk based on the old Stage-2 mapping if - * the Stage-1 invalidation happened first. - */ - dsb ish - tlbi vmalle1is - dsb ish - isb - - msr vttbr_el2, xzr - ret -ENDPROC(__kvm_tlb_flush_vmid_ipa) - -/** - * void __kvm_tlb_flush_vmid(struct kvm *kvm) - Flush per-VMID TLBs - * @struct kvm *kvm - pointer to kvm structure - * - * Invalidates all Stage 1 and 2 TLB entries for current VMID. - */ -ENTRY(__kvm_tlb_flush_vmid) - dsb ishst - - kern_hyp_va x0 - ldr x2, [x0, #KVM_VTTBR] - msr vttbr_el2, x2 - isb - - tlbi vmalls12e1is - dsb ish - isb - - msr vttbr_el2, xzr - ret -ENDPROC(__kvm_tlb_flush_vmid) - -ENTRY(__kvm_flush_vm_context) - dsb ishst - tlbi alle1is - ic ialluis - dsb ish - ret -ENDPROC(__kvm_flush_vm_context) - -__kvm_hyp_panic: - // Stash PAR_EL1 before corrupting it in __restore_sysregs - mrs x0, par_el1 - push x0, xzr - - // Guess the context by looking at VTTBR: - // If zero, then we're already a host. - // Otherwise restore a minimal host context before panicing. - mrs x0, vttbr_el2 - cbz x0, 1f - - mrs x0, tpidr_el2 - - deactivate_traps - deactivate_vm - - ldr x2, [x0, #VCPU_HOST_CONTEXT] - kern_hyp_va x2 - - bl __restore_sysregs - - /* - * Make sure we have a valid host stack, and don't leave junk in the - * frame pointer that will give us a misleading host stack unwinding. - */ - ldr x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)] - msr sp_el1, x22 - mov x29, xzr - -1: adr x0, __hyp_panic_str - adr x1, 2f - ldp x2, x3, [x1] - sub x0, x0, x2 - add x0, x0, x3 - mrs x1, spsr_el2 - mrs x2, elr_el2 - mrs x3, esr_el2 - mrs x4, far_el2 - mrs x5, hpfar_el2 - pop x6, xzr // active context PAR_EL1 - mrs x7, tpidr_el2 - - mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ - PSR_MODE_EL1h) - msr spsr_el2, lr - ldr lr, =panic - msr elr_el2, lr - eret - - .align 3 -2: .quad HYP_PAGE_OFFSET - .quad PAGE_OFFSET -ENDPROC(__kvm_hyp_panic) - -__hyp_panic_str: - .ascii "HYP panic:\nPS:%08x PC:%016x ESR:%08x\nFAR:%016x HPFAR:%016x PAR:%016x\nVCPU:%p\n\0" - - .align 2 /* * u64 kvm_call_hyp(void *hypfn, ...); @@ -934,7 +31,7 @@ __hyp_panic_str: * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the * function pointer can be passed). The function being called must be mapped * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c). Return values are - * passed in r0 and r1. + * passed in x0. * * A function pointer with a value of 0 has a special meaning, and is * used to implement __hyp_get_vectors in the same way as in @@ -944,179 +41,3 @@ ENTRY(kvm_call_hyp) hvc #0 ret ENDPROC(kvm_call_hyp) - -.macro invalid_vector label, target - .align 2 -\label: - b \target -ENDPROC(\label) -.endm - - /* None of these should ever happen */ - invalid_vector el2t_sync_invalid, __kvm_hyp_panic - invalid_vector el2t_irq_invalid, __kvm_hyp_panic - invalid_vector el2t_fiq_invalid, __kvm_hyp_panic - invalid_vector el2t_error_invalid, __kvm_hyp_panic - invalid_vector el2h_sync_invalid, __kvm_hyp_panic - invalid_vector el2h_irq_invalid, __kvm_hyp_panic - invalid_vector el2h_fiq_invalid, __kvm_hyp_panic - invalid_vector el2h_error_invalid, __kvm_hyp_panic - invalid_vector el1_sync_invalid, __kvm_hyp_panic - invalid_vector el1_irq_invalid, __kvm_hyp_panic - invalid_vector el1_fiq_invalid, __kvm_hyp_panic - invalid_vector el1_error_invalid, __kvm_hyp_panic - -el1_sync: // Guest trapped into EL2 - push x0, x1 - push x2, x3 - - mrs x1, esr_el2 - lsr x2, x1, #ESR_ELx_EC_SHIFT - - cmp x2, #ESR_ELx_EC_HVC64 - b.ne el1_trap - - mrs x3, vttbr_el2 // If vttbr is valid, the 64bit guest - cbnz x3, el1_trap // called HVC - - /* Here, we're pretty sure the host called HVC. */ - pop x2, x3 - pop x0, x1 - - /* Check for __hyp_get_vectors */ - cbnz x0, 1f - mrs x0, vbar_el2 - b 2f - -1: push lr, xzr - - /* - * Compute the function address in EL2, and shuffle the parameters. - */ - kern_hyp_va x0 - mov lr, x0 - mov x0, x1 - mov x1, x2 - mov x2, x3 - blr lr - - pop lr, xzr -2: eret - -el1_trap: - /* - * x1: ESR - * x2: ESR_EC - */ - - /* Guest accessed VFP/SIMD registers, save host, restore Guest */ - cmp x2, #ESR_ELx_EC_FP_ASIMD - b.eq switch_to_guest_fpsimd - - cmp x2, #ESR_ELx_EC_DABT_LOW - mov x0, #ESR_ELx_EC_IABT_LOW - ccmp x2, x0, #4, ne - b.ne 1f // Not an abort we care about - - /* This is an abort. Check for permission fault */ -alternative_if_not ARM64_WORKAROUND_834220 - and x2, x1, #ESR_ELx_FSC_TYPE - cmp x2, #FSC_PERM - b.ne 1f // Not a permission fault -alternative_else - nop // Use the permission fault path to - nop // check for a valid S1 translation, - nop // regardless of the ESR value. -alternative_endif - - /* - * Check for Stage-1 page table walk, which is guaranteed - * to give a valid HPFAR_EL2. - */ - tbnz x1, #7, 1f // S1PTW is set - - /* Preserve PAR_EL1 */ - mrs x3, par_el1 - push x3, xzr - - /* - * Permission fault, HPFAR_EL2 is invalid. - * Resolve the IPA the hard way using the guest VA. - * Stage-1 translation already validated the memory access rights. - * As such, we can use the EL1 translation regime, and don't have - * to distinguish between EL0 and EL1 access. - */ - mrs x2, far_el2 - at s1e1r, x2 - isb - - /* Read result */ - mrs x3, par_el1 - pop x0, xzr // Restore PAR_EL1 from the stack - msr par_el1, x0 - tbnz x3, #0, 3f // Bail out if we failed the translation - ubfx x3, x3, #12, #36 // Extract IPA - lsl x3, x3, #4 // and present it like HPFAR - b 2f - -1: mrs x3, hpfar_el2 - mrs x2, far_el2 - -2: mrs x0, tpidr_el2 - str w1, [x0, #VCPU_ESR_EL2] - str x2, [x0, #VCPU_FAR_EL2] - str x3, [x0, #VCPU_HPFAR_EL2] - - mov x1, #ARM_EXCEPTION_TRAP - b __kvm_vcpu_return - - /* - * Translation failed. Just return to the guest and - * let it fault again. Another CPU is probably playing - * behind our back. - */ -3: pop x2, x3 - pop x0, x1 - - eret - -el1_irq: - push x0, x1 - push x2, x3 - mrs x0, tpidr_el2 - mov x1, #ARM_EXCEPTION_IRQ - b __kvm_vcpu_return - - .ltorg - - .align 11 - -ENTRY(__kvm_hyp_vector) - ventry el2t_sync_invalid // Synchronous EL2t - ventry el2t_irq_invalid // IRQ EL2t - ventry el2t_fiq_invalid // FIQ EL2t - ventry el2t_error_invalid // Error EL2t - - ventry el2h_sync_invalid // Synchronous EL2h - ventry el2h_irq_invalid // IRQ EL2h - ventry el2h_fiq_invalid // FIQ EL2h - ventry el2h_error_invalid // Error EL2h - - ventry el1_sync // Synchronous 64-bit EL1 - ventry el1_irq // IRQ 64-bit EL1 - ventry el1_fiq_invalid // FIQ 64-bit EL1 - ventry el1_error_invalid // Error 64-bit EL1 - - ventry el1_sync // Synchronous 32-bit EL1 - ventry el1_irq // IRQ 32-bit EL1 - ventry el1_fiq_invalid // FIQ 32-bit EL1 - ventry el1_error_invalid // Error 32-bit EL1 -ENDPROC(__kvm_hyp_vector) - - -ENTRY(__kvm_get_mdcr_el2) - mrs x0, mdcr_el2 - ret -ENDPROC(__kvm_get_mdcr_el2) - - .popsection diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile new file mode 100644 index 000000000000..826032bc3945 --- /dev/null +++ b/arch/arm64/kvm/hyp/Makefile @@ -0,0 +1,14 @@ +# +# Makefile for Kernel-based Virtual Machine module, HYP part +# + +obj-$(CONFIG_KVM_ARM_HOST) += vgic-v2-sr.o +obj-$(CONFIG_KVM_ARM_HOST) += vgic-v3-sr.o +obj-$(CONFIG_KVM_ARM_HOST) += timer-sr.o +obj-$(CONFIG_KVM_ARM_HOST) += sysreg-sr.o +obj-$(CONFIG_KVM_ARM_HOST) += debug-sr.o +obj-$(CONFIG_KVM_ARM_HOST) += entry.o +obj-$(CONFIG_KVM_ARM_HOST) += switch.o +obj-$(CONFIG_KVM_ARM_HOST) += fpsimd.o +obj-$(CONFIG_KVM_ARM_HOST) += tlb.o +obj-$(CONFIG_KVM_ARM_HOST) += hyp-entry.o diff --git a/arch/arm64/kvm/hyp/debug-sr.c b/arch/arm64/kvm/hyp/debug-sr.c new file mode 100644 index 000000000000..c9c1e97501a9 --- /dev/null +++ b/arch/arm64/kvm/hyp/debug-sr.c @@ -0,0 +1,140 @@ +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> + +#include "hyp.h" + +#define read_debug(r,n) read_sysreg(r##n##_el1) +#define write_debug(v,r,n) write_sysreg(v, r##n##_el1) + +#define save_debug(ptr,reg,nr) \ + switch (nr) { \ + case 15: ptr[15] = read_debug(reg, 15); \ + case 14: ptr[14] = read_debug(reg, 14); \ + case 13: ptr[13] = read_debug(reg, 13); \ + case 12: ptr[12] = read_debug(reg, 12); \ + case 11: ptr[11] = read_debug(reg, 11); \ + case 10: ptr[10] = read_debug(reg, 10); \ + case 9: ptr[9] = read_debug(reg, 9); \ + case 8: ptr[8] = read_debug(reg, 8); \ + case 7: ptr[7] = read_debug(reg, 7); \ + case 6: ptr[6] = read_debug(reg, 6); \ + case 5: ptr[5] = read_debug(reg, 5); \ + case 4: ptr[4] = read_debug(reg, 4); \ + case 3: ptr[3] = read_debug(reg, 3); \ + case 2: ptr[2] = read_debug(reg, 2); \ + case 1: ptr[1] = read_debug(reg, 1); \ + default: ptr[0] = read_debug(reg, 0); \ + } + +#define restore_debug(ptr,reg,nr) \ + switch (nr) { \ + case 15: write_debug(ptr[15], reg, 15); \ + case 14: write_debug(ptr[14], reg, 14); \ + case 13: write_debug(ptr[13], reg, 13); \ + case 12: write_debug(ptr[12], reg, 12); \ + case 11: write_debug(ptr[11], reg, 11); \ + case 10: write_debug(ptr[10], reg, 10); \ + case 9: write_debug(ptr[9], reg, 9); \ + case 8: write_debug(ptr[8], reg, 8); \ + case 7: write_debug(ptr[7], reg, 7); \ + case 6: write_debug(ptr[6], reg, 6); \ + case 5: write_debug(ptr[5], reg, 5); \ + case 4: write_debug(ptr[4], reg, 4); \ + case 3: write_debug(ptr[3], reg, 3); \ + case 2: write_debug(ptr[2], reg, 2); \ + case 1: write_debug(ptr[1], reg, 1); \ + default: write_debug(ptr[0], reg, 0); \ + } + +void __hyp_text __debug_save_state(struct kvm_vcpu *vcpu, + struct kvm_guest_debug_arch *dbg, + struct kvm_cpu_context *ctxt) +{ + u64 aa64dfr0; + int brps, wrps; + + if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)) + return; + + aa64dfr0 = read_sysreg(id_aa64dfr0_el1); + brps = (aa64dfr0 >> 12) & 0xf; + wrps = (aa64dfr0 >> 20) & 0xf; + + save_debug(dbg->dbg_bcr, dbgbcr, brps); + save_debug(dbg->dbg_bvr, dbgbvr, brps); + save_debug(dbg->dbg_wcr, dbgwcr, wrps); + save_debug(dbg->dbg_wvr, dbgwvr, wrps); + + ctxt->sys_regs[MDCCINT_EL1] = read_sysreg(mdccint_el1); +} + +void __hyp_text __debug_restore_state(struct kvm_vcpu *vcpu, + struct kvm_guest_debug_arch *dbg, + struct kvm_cpu_context *ctxt) +{ + u64 aa64dfr0; + int brps, wrps; + + if (!(vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY)) + return; + + aa64dfr0 = read_sysreg(id_aa64dfr0_el1); + + brps = (aa64dfr0 >> 12) & 0xf; + wrps = (aa64dfr0 >> 20) & 0xf; + + restore_debug(dbg->dbg_bcr, dbgbcr, brps); + restore_debug(dbg->dbg_bvr, dbgbvr, brps); + restore_debug(dbg->dbg_wcr, dbgwcr, wrps); + restore_debug(dbg->dbg_wvr, dbgwvr, wrps); + + write_sysreg(ctxt->sys_regs[MDCCINT_EL1], mdccint_el1); +} + +void __hyp_text __debug_cond_save_host_state(struct kvm_vcpu *vcpu) +{ + /* If any of KDE, MDE or KVM_ARM64_DEBUG_DIRTY is set, perform + * a full save/restore cycle. */ + if ((vcpu->arch.ctxt.sys_regs[MDSCR_EL1] & DBG_MDSCR_KDE) || + (vcpu->arch.ctxt.sys_regs[MDSCR_EL1] & DBG_MDSCR_MDE)) + vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; + + __debug_save_state(vcpu, &vcpu->arch.host_debug_state, + kern_hyp_va(vcpu->arch.host_cpu_context)); +} + +void __hyp_text __debug_cond_restore_host_state(struct kvm_vcpu *vcpu) +{ + __debug_restore_state(vcpu, &vcpu->arch.host_debug_state, + kern_hyp_va(vcpu->arch.host_cpu_context)); + + if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY) + vcpu->arch.debug_flags &= ~KVM_ARM64_DEBUG_DIRTY; +} + +static u32 __hyp_text __debug_read_mdcr_el2(void) +{ + return read_sysreg(mdcr_el2); +} + +__alias(__debug_read_mdcr_el2) u32 __kvm_get_mdcr_el2(void); diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S new file mode 100644 index 000000000000..fd0fbe9b7e6a --- /dev/null +++ b/arch/arm64/kvm/hyp/entry.S @@ -0,0 +1,160 @@ +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/linkage.h> + +#include <asm/asm-offsets.h> +#include <asm/assembler.h> +#include <asm/fpsimdmacros.h> +#include <asm/kvm.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> + +#define CPU_GP_REG_OFFSET(x) (CPU_GP_REGS + x) +#define CPU_XREG_OFFSET(x) CPU_GP_REG_OFFSET(CPU_USER_PT_REGS + 8*x) + + .text + .pushsection .hyp.text, "ax" + +.macro save_callee_saved_regs ctxt + stp x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)] + stp x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)] + stp x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)] + stp x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)] + stp x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)] + stp x29, lr, [\ctxt, #CPU_XREG_OFFSET(29)] +.endm + +.macro restore_callee_saved_regs ctxt + ldp x19, x20, [\ctxt, #CPU_XREG_OFFSET(19)] + ldp x21, x22, [\ctxt, #CPU_XREG_OFFSET(21)] + ldp x23, x24, [\ctxt, #CPU_XREG_OFFSET(23)] + ldp x25, x26, [\ctxt, #CPU_XREG_OFFSET(25)] + ldp x27, x28, [\ctxt, #CPU_XREG_OFFSET(27)] + ldp x29, lr, [\ctxt, #CPU_XREG_OFFSET(29)] +.endm + +/* + * u64 __guest_enter(struct kvm_vcpu *vcpu, + * struct kvm_cpu_context *host_ctxt); + */ +ENTRY(__guest_enter) + // x0: vcpu + // x1: host/guest context + // x2-x18: clobbered by macros + + // Store the host regs + save_callee_saved_regs x1 + + // Preserve vcpu & host_ctxt for use at exit time + stp x0, x1, [sp, #-16]! + + add x1, x0, #VCPU_CONTEXT + + // Prepare x0-x1 for later restore by pushing them onto the stack + ldp x2, x3, [x1, #CPU_XREG_OFFSET(0)] + stp x2, x3, [sp, #-16]! + + // x2-x18 + ldp x2, x3, [x1, #CPU_XREG_OFFSET(2)] + ldp x4, x5, [x1, #CPU_XREG_OFFSET(4)] + ldp x6, x7, [x1, #CPU_XREG_OFFSET(6)] + ldp x8, x9, [x1, #CPU_XREG_OFFSET(8)] + ldp x10, x11, [x1, #CPU_XREG_OFFSET(10)] + ldp x12, x13, [x1, #CPU_XREG_OFFSET(12)] + ldp x14, x15, [x1, #CPU_XREG_OFFSET(14)] + ldp x16, x17, [x1, #CPU_XREG_OFFSET(16)] + ldr x18, [x1, #CPU_XREG_OFFSET(18)] + + // x19-x29, lr + restore_callee_saved_regs x1 + + // Last bits of the 64bit state + ldp x0, x1, [sp], #16 + + // Do not touch any register after this! + eret +ENDPROC(__guest_enter) + +ENTRY(__guest_exit) + // x0: vcpu + // x1: return code + // x2-x3: free + // x4-x29,lr: vcpu regs + // vcpu x0-x3 on the stack + + add x2, x0, #VCPU_CONTEXT + + stp x4, x5, [x2, #CPU_XREG_OFFSET(4)] + stp x6, x7, [x2, #CPU_XREG_OFFSET(6)] + stp x8, x9, [x2, #CPU_XREG_OFFSET(8)] + stp x10, x11, [x2, #CPU_XREG_OFFSET(10)] + stp x12, x13, [x2, #CPU_XREG_OFFSET(12)] + stp x14, x15, [x2, #CPU_XREG_OFFSET(14)] + stp x16, x17, [x2, #CPU_XREG_OFFSET(16)] + str x18, [x2, #CPU_XREG_OFFSET(18)] + + ldp x6, x7, [sp], #16 // x2, x3 + ldp x4, x5, [sp], #16 // x0, x1 + + stp x4, x5, [x2, #CPU_XREG_OFFSET(0)] + stp x6, x7, [x2, #CPU_XREG_OFFSET(2)] + + save_callee_saved_regs x2 + + // Restore vcpu & host_ctxt from the stack + // (preserving return code in x1) + ldp x0, x2, [sp], #16 + // Now restore the host regs + restore_callee_saved_regs x2 + + mov x0, x1 + ret +ENDPROC(__guest_exit) + +ENTRY(__fpsimd_guest_restore) + stp x4, lr, [sp, #-16]! + + mrs x2, cptr_el2 + bic x2, x2, #CPTR_EL2_TFP + msr cptr_el2, x2 + isb + + mrs x3, tpidr_el2 + + ldr x0, [x3, #VCPU_HOST_CONTEXT] + kern_hyp_va x0 + add x0, x0, #CPU_GP_REG_OFFSET(CPU_FP_REGS) + bl __fpsimd_save_state + + add x2, x3, #VCPU_CONTEXT + add x0, x2, #CPU_GP_REG_OFFSET(CPU_FP_REGS) + bl __fpsimd_restore_state + + // Skip restoring fpexc32 for AArch64 guests + mrs x1, hcr_el2 + tbnz x1, #HCR_RW_SHIFT, 1f + ldr x4, [x3, #VCPU_FPEXC32_EL2] + msr fpexc32_el2, x4 +1: + ldp x4, lr, [sp], #16 + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 + + eret +ENDPROC(__fpsimd_guest_restore) diff --git a/arch/arm/kernel/psci-call.S b/arch/arm64/kvm/hyp/fpsimd.S index a78e9e1e206d..da3f22c7f14a 100644 --- a/arch/arm/kernel/psci-call.S +++ b/arch/arm64/kvm/hyp/fpsimd.S @@ -1,4 +1,7 @@ /* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. @@ -8,24 +11,23 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * Copyright (C) 2015 ARM Limited - * - * Author: Mark Rutland <mark.rutland@arm.com> + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. */ #include <linux/linkage.h> -#include <asm/opcodes-sec.h> -#include <asm/opcodes-virt.h> +#include <asm/fpsimdmacros.h> + + .text + .pushsection .hyp.text, "ax" -/* int __invoke_psci_fn_hvc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */ -ENTRY(__invoke_psci_fn_hvc) - __HVC(0) - bx lr -ENDPROC(__invoke_psci_fn_hvc) +ENTRY(__fpsimd_save_state) + fpsimd_save x0, 1 + ret +ENDPROC(__fpsimd_save_state) -/* int __invoke_psci_fn_smc(u32 function_id, u32 arg0, u32 arg1, u32 arg2) */ -ENTRY(__invoke_psci_fn_smc) - __SMC(0) - bx lr -ENDPROC(__invoke_psci_fn_smc) +ENTRY(__fpsimd_restore_state) + fpsimd_restore x0, 1 + ret +ENDPROC(__fpsimd_restore_state) diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S new file mode 100644 index 000000000000..93e8d983c0bd --- /dev/null +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -0,0 +1,212 @@ +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/linkage.h> + +#include <asm/alternative.h> +#include <asm/assembler.h> +#include <asm/asm-offsets.h> +#include <asm/cpufeature.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> + + .text + .pushsection .hyp.text, "ax" + +.macro save_x0_to_x3 + stp x0, x1, [sp, #-16]! + stp x2, x3, [sp, #-16]! +.endm + +.macro restore_x0_to_x3 + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +.endm + +el1_sync: // Guest trapped into EL2 + save_x0_to_x3 + + mrs x1, esr_el2 + lsr x2, x1, #ESR_ELx_EC_SHIFT + + cmp x2, #ESR_ELx_EC_HVC64 + b.ne el1_trap + + mrs x3, vttbr_el2 // If vttbr is valid, the 64bit guest + cbnz x3, el1_trap // called HVC + + /* Here, we're pretty sure the host called HVC. */ + restore_x0_to_x3 + + /* Check for __hyp_get_vectors */ + cbnz x0, 1f + mrs x0, vbar_el2 + b 2f + +1: stp lr, xzr, [sp, #-16]! + + /* + * Compute the function address in EL2, and shuffle the parameters. + */ + kern_hyp_va x0 + mov lr, x0 + mov x0, x1 + mov x1, x2 + mov x2, x3 + blr lr + + ldp lr, xzr, [sp], #16 +2: eret + +el1_trap: + /* + * x1: ESR + * x2: ESR_EC + */ + + /* Guest accessed VFP/SIMD registers, save host, restore Guest */ + cmp x2, #ESR_ELx_EC_FP_ASIMD + b.eq __fpsimd_guest_restore + + cmp x2, #ESR_ELx_EC_DABT_LOW + mov x0, #ESR_ELx_EC_IABT_LOW + ccmp x2, x0, #4, ne + b.ne 1f // Not an abort we care about + + /* This is an abort. Check for permission fault */ +alternative_if_not ARM64_WORKAROUND_834220 + and x2, x1, #ESR_ELx_FSC_TYPE + cmp x2, #FSC_PERM + b.ne 1f // Not a permission fault +alternative_else + nop // Use the permission fault path to + nop // check for a valid S1 translation, + nop // regardless of the ESR value. +alternative_endif + + /* + * Check for Stage-1 page table walk, which is guaranteed + * to give a valid HPFAR_EL2. + */ + tbnz x1, #7, 1f // S1PTW is set + + /* Preserve PAR_EL1 */ + mrs x3, par_el1 + stp x3, xzr, [sp, #-16]! + + /* + * Permission fault, HPFAR_EL2 is invalid. + * Resolve the IPA the hard way using the guest VA. + * Stage-1 translation already validated the memory access rights. + * As such, we can use the EL1 translation regime, and don't have + * to distinguish between EL0 and EL1 access. + */ + mrs x2, far_el2 + at s1e1r, x2 + isb + + /* Read result */ + mrs x3, par_el1 + ldp x0, xzr, [sp], #16 // Restore PAR_EL1 from the stack + msr par_el1, x0 + tbnz x3, #0, 3f // Bail out if we failed the translation + ubfx x3, x3, #12, #36 // Extract IPA + lsl x3, x3, #4 // and present it like HPFAR + b 2f + +1: mrs x3, hpfar_el2 + mrs x2, far_el2 + +2: mrs x0, tpidr_el2 + str w1, [x0, #VCPU_ESR_EL2] + str x2, [x0, #VCPU_FAR_EL2] + str x3, [x0, #VCPU_HPFAR_EL2] + + mov x1, #ARM_EXCEPTION_TRAP + b __guest_exit + + /* + * Translation failed. Just return to the guest and + * let it fault again. Another CPU is probably playing + * behind our back. + */ +3: restore_x0_to_x3 + + eret + +el1_irq: + save_x0_to_x3 + mrs x0, tpidr_el2 + mov x1, #ARM_EXCEPTION_IRQ + b __guest_exit + +ENTRY(__hyp_do_panic) + mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ + PSR_MODE_EL1h) + msr spsr_el2, lr + ldr lr, =panic + msr elr_el2, lr + eret +ENDPROC(__hyp_do_panic) + +.macro invalid_vector label, target = __hyp_panic + .align 2 +\label: + b \target +ENDPROC(\label) +.endm + + /* None of these should ever happen */ + invalid_vector el2t_sync_invalid + invalid_vector el2t_irq_invalid + invalid_vector el2t_fiq_invalid + invalid_vector el2t_error_invalid + invalid_vector el2h_sync_invalid + invalid_vector el2h_irq_invalid + invalid_vector el2h_fiq_invalid + invalid_vector el2h_error_invalid + invalid_vector el1_sync_invalid + invalid_vector el1_irq_invalid + invalid_vector el1_fiq_invalid + invalid_vector el1_error_invalid + + .ltorg + + .align 11 + +ENTRY(__kvm_hyp_vector) + ventry el2t_sync_invalid // Synchronous EL2t + ventry el2t_irq_invalid // IRQ EL2t + ventry el2t_fiq_invalid // FIQ EL2t + ventry el2t_error_invalid // Error EL2t + + ventry el2h_sync_invalid // Synchronous EL2h + ventry el2h_irq_invalid // IRQ EL2h + ventry el2h_fiq_invalid // FIQ EL2h + ventry el2h_error_invalid // Error EL2h + + ventry el1_sync // Synchronous 64-bit EL1 + ventry el1_irq // IRQ 64-bit EL1 + ventry el1_fiq_invalid // FIQ 64-bit EL1 + ventry el1_error_invalid // Error 64-bit EL1 + + ventry el1_sync // Synchronous 32-bit EL1 + ventry el1_irq // IRQ 32-bit EL1 + ventry el1_fiq_invalid // FIQ 32-bit EL1 + ventry el1_error_invalid // Error 32-bit EL1 +ENDPROC(__kvm_hyp_vector) diff --git a/arch/arm64/kvm/hyp/hyp.h b/arch/arm64/kvm/hyp/hyp.h new file mode 100644 index 000000000000..fb275178b6af --- /dev/null +++ b/arch/arm64/kvm/hyp/hyp.h @@ -0,0 +1,90 @@ +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef __ARM64_KVM_HYP_H__ +#define __ARM64_KVM_HYP_H__ + +#include <linux/compiler.h> +#include <linux/kvm_host.h> +#include <asm/kvm_mmu.h> +#include <asm/sysreg.h> + +#define __hyp_text __section(.hyp.text) notrace + +#define kern_hyp_va(v) (typeof(v))((unsigned long)(v) & HYP_PAGE_OFFSET_MASK) +#define hyp_kern_va(v) (typeof(v))((unsigned long)(v) - HYP_PAGE_OFFSET \ + + PAGE_OFFSET) + +/** + * hyp_alternate_select - Generates patchable code sequences that are + * used to switch between two implementations of a function, depending + * on the availability of a feature. + * + * @fname: a symbol name that will be defined as a function returning a + * function pointer whose type will match @orig and @alt + * @orig: A pointer to the default function, as returned by @fname when + * @cond doesn't hold + * @alt: A pointer to the alternate function, as returned by @fname + * when @cond holds + * @cond: a CPU feature (as described in asm/cpufeature.h) + */ +#define hyp_alternate_select(fname, orig, alt, cond) \ +typeof(orig) * __hyp_text fname(void) \ +{ \ + typeof(alt) *val = orig; \ + asm volatile(ALTERNATIVE("nop \n", \ + "mov %0, %1 \n", \ + cond) \ + : "+r" (val) : "r" (alt)); \ + return val; \ +} + +void __vgic_v2_save_state(struct kvm_vcpu *vcpu); +void __vgic_v2_restore_state(struct kvm_vcpu *vcpu); + +void __vgic_v3_save_state(struct kvm_vcpu *vcpu); +void __vgic_v3_restore_state(struct kvm_vcpu *vcpu); + +void __timer_save_state(struct kvm_vcpu *vcpu); +void __timer_restore_state(struct kvm_vcpu *vcpu); + +void __sysreg_save_state(struct kvm_cpu_context *ctxt); +void __sysreg_restore_state(struct kvm_cpu_context *ctxt); +void __sysreg32_save_state(struct kvm_vcpu *vcpu); +void __sysreg32_restore_state(struct kvm_vcpu *vcpu); + +void __debug_save_state(struct kvm_vcpu *vcpu, + struct kvm_guest_debug_arch *dbg, + struct kvm_cpu_context *ctxt); +void __debug_restore_state(struct kvm_vcpu *vcpu, + struct kvm_guest_debug_arch *dbg, + struct kvm_cpu_context *ctxt); +void __debug_cond_save_host_state(struct kvm_vcpu *vcpu); +void __debug_cond_restore_host_state(struct kvm_vcpu *vcpu); + +void __fpsimd_save_state(struct user_fpsimd_state *fp_regs); +void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs); +static inline bool __fpsimd_enabled(void) +{ + return !(read_sysreg(cptr_el2) & CPTR_EL2_TFP); +} + +u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt); +void __noreturn __hyp_do_panic(unsigned long, ...); + +#endif /* __ARM64_KVM_HYP_H__ */ + diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c new file mode 100644 index 000000000000..ca8f5a5e2f96 --- /dev/null +++ b/arch/arm64/kvm/hyp/switch.c @@ -0,0 +1,175 @@ +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "hyp.h" + +static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) +{ + u64 val; + + /* + * We are about to set CPTR_EL2.TFP to trap all floating point + * register accesses to EL2, however, the ARM ARM clearly states that + * traps are only taken to EL2 if the operation would not otherwise + * trap to EL1. Therefore, always make sure that for 32-bit guests, + * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit. + */ + val = vcpu->arch.hcr_el2; + if (!(val & HCR_RW)) { + write_sysreg(1 << 30, fpexc32_el2); + isb(); + } + write_sysreg(val, hcr_el2); + /* Trap on AArch32 cp15 c15 accesses (EL1 or EL0) */ + write_sysreg(1 << 15, hstr_el2); + write_sysreg(CPTR_EL2_TTA | CPTR_EL2_TFP, cptr_el2); + write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); +} + +static void __hyp_text __deactivate_traps(struct kvm_vcpu *vcpu) +{ + write_sysreg(HCR_RW, hcr_el2); + write_sysreg(0, hstr_el2); + write_sysreg(read_sysreg(mdcr_el2) & MDCR_EL2_HPMN_MASK, mdcr_el2); + write_sysreg(0, cptr_el2); +} + +static void __hyp_text __activate_vm(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = kern_hyp_va(vcpu->kvm); + write_sysreg(kvm->arch.vttbr, vttbr_el2); +} + +static void __hyp_text __deactivate_vm(struct kvm_vcpu *vcpu) +{ + write_sysreg(0, vttbr_el2); +} + +static hyp_alternate_select(__vgic_call_save_state, + __vgic_v2_save_state, __vgic_v3_save_state, + ARM64_HAS_SYSREG_GIC_CPUIF); + +static hyp_alternate_select(__vgic_call_restore_state, + __vgic_v2_restore_state, __vgic_v3_restore_state, + ARM64_HAS_SYSREG_GIC_CPUIF); + +static void __hyp_text __vgic_save_state(struct kvm_vcpu *vcpu) +{ + __vgic_call_save_state()(vcpu); + write_sysreg(read_sysreg(hcr_el2) & ~HCR_INT_OVERRIDE, hcr_el2); +} + +static void __hyp_text __vgic_restore_state(struct kvm_vcpu *vcpu) +{ + u64 val; + + val = read_sysreg(hcr_el2); + val |= HCR_INT_OVERRIDE; + val |= vcpu->arch.irq_lines; + write_sysreg(val, hcr_el2); + + __vgic_call_restore_state()(vcpu); +} + +static int __hyp_text __guest_run(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *host_ctxt; + struct kvm_cpu_context *guest_ctxt; + bool fp_enabled; + u64 exit_code; + + vcpu = kern_hyp_va(vcpu); + write_sysreg(vcpu, tpidr_el2); + + host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); + guest_ctxt = &vcpu->arch.ctxt; + + __sysreg_save_state(host_ctxt); + __debug_cond_save_host_state(vcpu); + + __activate_traps(vcpu); + __activate_vm(vcpu); + + __vgic_restore_state(vcpu); + __timer_restore_state(vcpu); + + /* + * We must restore the 32-bit state before the sysregs, thanks + * to Cortex-A57 erratum #852523. + */ + __sysreg32_restore_state(vcpu); + __sysreg_restore_state(guest_ctxt); + __debug_restore_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt); + + /* Jump in the fire! */ + exit_code = __guest_enter(vcpu, host_ctxt); + /* And we're baaack! */ + + fp_enabled = __fpsimd_enabled(); + + __sysreg_save_state(guest_ctxt); + __sysreg32_save_state(vcpu); + __timer_save_state(vcpu); + __vgic_save_state(vcpu); + + __deactivate_traps(vcpu); + __deactivate_vm(vcpu); + + __sysreg_restore_state(host_ctxt); + + if (fp_enabled) { + __fpsimd_save_state(&guest_ctxt->gp_regs.fp_regs); + __fpsimd_restore_state(&host_ctxt->gp_regs.fp_regs); + } + + __debug_save_state(vcpu, kern_hyp_va(vcpu->arch.debug_ptr), guest_ctxt); + __debug_cond_restore_host_state(vcpu); + + return exit_code; +} + +__alias(__guest_run) int __kvm_vcpu_run(struct kvm_vcpu *vcpu); + +static const char __hyp_panic_string[] = "HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n"; + +void __hyp_text __noreturn __hyp_panic(void) +{ + unsigned long str_va = (unsigned long)__hyp_panic_string; + u64 spsr = read_sysreg(spsr_el2); + u64 elr = read_sysreg(elr_el2); + u64 par = read_sysreg(par_el1); + + if (read_sysreg(vttbr_el2)) { + struct kvm_vcpu *vcpu; + struct kvm_cpu_context *host_ctxt; + + vcpu = (struct kvm_vcpu *)read_sysreg(tpidr_el2); + host_ctxt = kern_hyp_va(vcpu->arch.host_cpu_context); + __deactivate_traps(vcpu); + __deactivate_vm(vcpu); + __sysreg_restore_state(host_ctxt); + } + + /* Call panic for real */ + __hyp_do_panic(hyp_kern_va(str_va), + spsr, elr, + read_sysreg(esr_el2), read_sysreg(far_el2), + read_sysreg(hpfar_el2), par, + (void *)read_sysreg(tpidr_el2)); + + unreachable(); +} diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c new file mode 100644 index 000000000000..425630980229 --- /dev/null +++ b/arch/arm64/kvm/hyp/sysreg-sr.c @@ -0,0 +1,138 @@ +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> + +#include "hyp.h" + +/* ctxt is already in the HYP VA space */ +void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt) +{ + ctxt->sys_regs[MPIDR_EL1] = read_sysreg(vmpidr_el2); + ctxt->sys_regs[CSSELR_EL1] = read_sysreg(csselr_el1); + ctxt->sys_regs[SCTLR_EL1] = read_sysreg(sctlr_el1); + ctxt->sys_regs[ACTLR_EL1] = read_sysreg(actlr_el1); + ctxt->sys_regs[CPACR_EL1] = read_sysreg(cpacr_el1); + ctxt->sys_regs[TTBR0_EL1] = read_sysreg(ttbr0_el1); + ctxt->sys_regs[TTBR1_EL1] = read_sysreg(ttbr1_el1); + ctxt->sys_regs[TCR_EL1] = read_sysreg(tcr_el1); + ctxt->sys_regs[ESR_EL1] = read_sysreg(esr_el1); + ctxt->sys_regs[AFSR0_EL1] = read_sysreg(afsr0_el1); + ctxt->sys_regs[AFSR1_EL1] = read_sysreg(afsr1_el1); + ctxt->sys_regs[FAR_EL1] = read_sysreg(far_el1); + ctxt->sys_regs[MAIR_EL1] = read_sysreg(mair_el1); + ctxt->sys_regs[VBAR_EL1] = read_sysreg(vbar_el1); + ctxt->sys_regs[CONTEXTIDR_EL1] = read_sysreg(contextidr_el1); + ctxt->sys_regs[TPIDR_EL0] = read_sysreg(tpidr_el0); + ctxt->sys_regs[TPIDRRO_EL0] = read_sysreg(tpidrro_el0); + ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1); + ctxt->sys_regs[AMAIR_EL1] = read_sysreg(amair_el1); + ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg(cntkctl_el1); + ctxt->sys_regs[PAR_EL1] = read_sysreg(par_el1); + ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1); + + ctxt->gp_regs.regs.sp = read_sysreg(sp_el0); + ctxt->gp_regs.regs.pc = read_sysreg(elr_el2); + ctxt->gp_regs.regs.pstate = read_sysreg(spsr_el2); + ctxt->gp_regs.sp_el1 = read_sysreg(sp_el1); + ctxt->gp_regs.elr_el1 = read_sysreg(elr_el1); + ctxt->gp_regs.spsr[KVM_SPSR_EL1]= read_sysreg(spsr_el1); +} + +void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt) +{ + write_sysreg(ctxt->sys_regs[MPIDR_EL1], vmpidr_el2); + write_sysreg(ctxt->sys_regs[CSSELR_EL1], csselr_el1); + write_sysreg(ctxt->sys_regs[SCTLR_EL1], sctlr_el1); + write_sysreg(ctxt->sys_regs[ACTLR_EL1], actlr_el1); + write_sysreg(ctxt->sys_regs[CPACR_EL1], cpacr_el1); + write_sysreg(ctxt->sys_regs[TTBR0_EL1], ttbr0_el1); + write_sysreg(ctxt->sys_regs[TTBR1_EL1], ttbr1_el1); + write_sysreg(ctxt->sys_regs[TCR_EL1], tcr_el1); + write_sysreg(ctxt->sys_regs[ESR_EL1], esr_el1); + write_sysreg(ctxt->sys_regs[AFSR0_EL1], afsr0_el1); + write_sysreg(ctxt->sys_regs[AFSR1_EL1], afsr1_el1); + write_sysreg(ctxt->sys_regs[FAR_EL1], far_el1); + write_sysreg(ctxt->sys_regs[MAIR_EL1], mair_el1); + write_sysreg(ctxt->sys_regs[VBAR_EL1], vbar_el1); + write_sysreg(ctxt->sys_regs[CONTEXTIDR_EL1], contextidr_el1); + write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0); + write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0); + write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1); + write_sysreg(ctxt->sys_regs[AMAIR_EL1], amair_el1); + write_sysreg(ctxt->sys_regs[CNTKCTL_EL1], cntkctl_el1); + write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1); + write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1); + + write_sysreg(ctxt->gp_regs.regs.sp, sp_el0); + write_sysreg(ctxt->gp_regs.regs.pc, elr_el2); + write_sysreg(ctxt->gp_regs.regs.pstate, spsr_el2); + write_sysreg(ctxt->gp_regs.sp_el1, sp_el1); + write_sysreg(ctxt->gp_regs.elr_el1, elr_el1); + write_sysreg(ctxt->gp_regs.spsr[KVM_SPSR_EL1], spsr_el1); +} + +void __hyp_text __sysreg32_save_state(struct kvm_vcpu *vcpu) +{ + u64 *spsr, *sysreg; + + if (read_sysreg(hcr_el2) & HCR_RW) + return; + + spsr = vcpu->arch.ctxt.gp_regs.spsr; + sysreg = vcpu->arch.ctxt.sys_regs; + + spsr[KVM_SPSR_ABT] = read_sysreg(spsr_abt); + spsr[KVM_SPSR_UND] = read_sysreg(spsr_und); + spsr[KVM_SPSR_IRQ] = read_sysreg(spsr_irq); + spsr[KVM_SPSR_FIQ] = read_sysreg(spsr_fiq); + + sysreg[DACR32_EL2] = read_sysreg(dacr32_el2); + sysreg[IFSR32_EL2] = read_sysreg(ifsr32_el2); + + if (__fpsimd_enabled()) + sysreg[FPEXC32_EL2] = read_sysreg(fpexc32_el2); + + if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY) + sysreg[DBGVCR32_EL2] = read_sysreg(dbgvcr32_el2); +} + +void __hyp_text __sysreg32_restore_state(struct kvm_vcpu *vcpu) +{ + u64 *spsr, *sysreg; + + if (read_sysreg(hcr_el2) & HCR_RW) + return; + + spsr = vcpu->arch.ctxt.gp_regs.spsr; + sysreg = vcpu->arch.ctxt.sys_regs; + + write_sysreg(spsr[KVM_SPSR_ABT], spsr_abt); + write_sysreg(spsr[KVM_SPSR_UND], spsr_und); + write_sysreg(spsr[KVM_SPSR_IRQ], spsr_irq); + write_sysreg(spsr[KVM_SPSR_FIQ], spsr_fiq); + + write_sysreg(sysreg[DACR32_EL2], dacr32_el2); + write_sysreg(sysreg[IFSR32_EL2], ifsr32_el2); + + if (vcpu->arch.debug_flags & KVM_ARM64_DEBUG_DIRTY) + write_sysreg(sysreg[DBGVCR32_EL2], dbgvcr32_el2); +} diff --git a/arch/arm64/kvm/hyp/timer-sr.c b/arch/arm64/kvm/hyp/timer-sr.c new file mode 100644 index 000000000000..1051e5d7320f --- /dev/null +++ b/arch/arm64/kvm/hyp/timer-sr.c @@ -0,0 +1,71 @@ +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <clocksource/arm_arch_timer.h> +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_mmu.h> + +#include "hyp.h" + +/* vcpu is already in the HYP VA space */ +void __hyp_text __timer_save_state(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = kern_hyp_va(vcpu->kvm); + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + u64 val; + + if (kvm->arch.timer.enabled) { + timer->cntv_ctl = read_sysreg(cntv_ctl_el0); + timer->cntv_cval = read_sysreg(cntv_cval_el0); + } + + /* Disable the virtual timer */ + write_sysreg(0, cntv_ctl_el0); + + /* Allow physical timer/counter access for the host */ + val = read_sysreg(cnthctl_el2); + val |= CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN; + write_sysreg(val, cnthctl_el2); + + /* Clear cntvoff for the host */ + write_sysreg(0, cntvoff_el2); +} + +void __hyp_text __timer_restore_state(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = kern_hyp_va(vcpu->kvm); + struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu; + u64 val; + + /* + * Disallow physical timer access for the guest + * Physical counter access is allowed + */ + val = read_sysreg(cnthctl_el2); + val &= ~CNTHCTL_EL1PCEN; + val |= CNTHCTL_EL1PCTEN; + write_sysreg(val, cnthctl_el2); + + if (kvm->arch.timer.enabled) { + write_sysreg(kvm->arch.timer.cntvoff, cntvoff_el2); + write_sysreg(timer->cntv_cval, cntv_cval_el0); + isb(); + write_sysreg(timer->cntv_ctl, cntv_ctl_el0); + } +} diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c new file mode 100644 index 000000000000..2a7e0d838698 --- /dev/null +++ b/arch/arm64/kvm/hyp/tlb.c @@ -0,0 +1,80 @@ +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "hyp.h" + +static void __hyp_text __tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa) +{ + dsb(ishst); + + /* Switch to requested VMID */ + kvm = kern_hyp_va(kvm); + write_sysreg(kvm->arch.vttbr, vttbr_el2); + isb(); + + /* + * We could do so much better if we had the VA as well. + * Instead, we invalidate Stage-2 for this IPA, and the + * whole of Stage-1. Weep... + */ + ipa >>= 12; + asm volatile("tlbi ipas2e1is, %0" : : "r" (ipa)); + + /* + * We have to ensure completion of the invalidation at Stage-2, + * since a table walk on another CPU could refill a TLB with a + * complete (S1 + S2) walk based on the old Stage-2 mapping if + * the Stage-1 invalidation happened first. + */ + dsb(ish); + asm volatile("tlbi vmalle1is" : : ); + dsb(ish); + isb(); + + write_sysreg(0, vttbr_el2); +} + +__alias(__tlb_flush_vmid_ipa) void __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, + phys_addr_t ipa); + +static void __hyp_text __tlb_flush_vmid(struct kvm *kvm) +{ + dsb(ishst); + + /* Switch to requested VMID */ + kvm = kern_hyp_va(kvm); + write_sysreg(kvm->arch.vttbr, vttbr_el2); + isb(); + + asm volatile("tlbi vmalls12e1is" : : ); + dsb(ish); + isb(); + + write_sysreg(0, vttbr_el2); +} + +__alias(__tlb_flush_vmid) void __kvm_tlb_flush_vmid(struct kvm *kvm); + +static void __hyp_text __tlb_flush_vm_context(void) +{ + dsb(ishst); + asm volatile("tlbi alle1is \n" + "ic ialluis ": : ); + dsb(ish); +} + +__alias(__tlb_flush_vm_context) void __kvm_flush_vm_context(void); diff --git a/arch/arm64/kvm/hyp/vgic-v2-sr.c b/arch/arm64/kvm/hyp/vgic-v2-sr.c new file mode 100644 index 000000000000..e71761238cfc --- /dev/null +++ b/arch/arm64/kvm/hyp/vgic-v2-sr.c @@ -0,0 +1,84 @@ +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/compiler.h> +#include <linux/irqchip/arm-gic.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_mmu.h> + +#include "hyp.h" + +/* vcpu is already in the HYP VA space */ +void __hyp_text __vgic_v2_save_state(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = kern_hyp_va(vcpu->kvm); + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + struct vgic_dist *vgic = &kvm->arch.vgic; + void __iomem *base = kern_hyp_va(vgic->vctrl_base); + u32 eisr0, eisr1, elrsr0, elrsr1; + int i, nr_lr; + + if (!base) + return; + + nr_lr = vcpu->arch.vgic_cpu.nr_lr; + cpu_if->vgic_vmcr = readl_relaxed(base + GICH_VMCR); + cpu_if->vgic_misr = readl_relaxed(base + GICH_MISR); + eisr0 = readl_relaxed(base + GICH_EISR0); + elrsr0 = readl_relaxed(base + GICH_ELRSR0); + if (unlikely(nr_lr > 32)) { + eisr1 = readl_relaxed(base + GICH_EISR1); + elrsr1 = readl_relaxed(base + GICH_ELRSR1); + } else { + eisr1 = elrsr1 = 0; + } +#ifdef CONFIG_CPU_BIG_ENDIAN + cpu_if->vgic_eisr = ((u64)eisr0 << 32) | eisr1; + cpu_if->vgic_elrsr = ((u64)elrsr0 << 32) | elrsr1; +#else + cpu_if->vgic_eisr = ((u64)eisr1 << 32) | eisr0; + cpu_if->vgic_elrsr = ((u64)elrsr1 << 32) | elrsr0; +#endif + cpu_if->vgic_apr = readl_relaxed(base + GICH_APR); + + writel_relaxed(0, base + GICH_HCR); + + for (i = 0; i < nr_lr; i++) + cpu_if->vgic_lr[i] = readl_relaxed(base + GICH_LR0 + (i * 4)); +} + +/* vcpu is already in the HYP VA space */ +void __hyp_text __vgic_v2_restore_state(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = kern_hyp_va(vcpu->kvm); + struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2; + struct vgic_dist *vgic = &kvm->arch.vgic; + void __iomem *base = kern_hyp_va(vgic->vctrl_base); + int i, nr_lr; + + if (!base) + return; + + writel_relaxed(cpu_if->vgic_hcr, base + GICH_HCR); + writel_relaxed(cpu_if->vgic_vmcr, base + GICH_VMCR); + writel_relaxed(cpu_if->vgic_apr, base + GICH_APR); + + nr_lr = vcpu->arch.vgic_cpu.nr_lr; + for (i = 0; i < nr_lr; i++) + writel_relaxed(cpu_if->vgic_lr[i], base + GICH_LR0 + (i * 4)); +} diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c new file mode 100644 index 000000000000..9142e082f5f3 --- /dev/null +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -0,0 +1,228 @@ +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include <linux/compiler.h> +#include <linux/irqchip/arm-gic-v3.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_mmu.h> + +#include "hyp.h" + +#define vtr_to_max_lr_idx(v) ((v) & 0xf) +#define vtr_to_nr_pri_bits(v) (((u32)(v) >> 29) + 1) + +#define read_gicreg(r) \ + ({ \ + u64 reg; \ + asm volatile("mrs_s %0, " __stringify(r) : "=r" (reg)); \ + reg; \ + }) + +#define write_gicreg(v,r) \ + do { \ + u64 __val = (v); \ + asm volatile("msr_s " __stringify(r) ", %0" : : "r" (__val));\ + } while (0) + +/* vcpu is already in the HYP VA space */ +void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu) +{ + struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; + u64 val; + u32 max_lr_idx, nr_pri_bits; + + /* + * Make sure stores to the GIC via the memory mapped interface + * are now visible to the system register interface. + */ + dsb(st); + + cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2); + cpu_if->vgic_misr = read_gicreg(ICH_MISR_EL2); + cpu_if->vgic_eisr = read_gicreg(ICH_EISR_EL2); + cpu_if->vgic_elrsr = read_gicreg(ICH_ELSR_EL2); + + write_gicreg(0, ICH_HCR_EL2); + val = read_gicreg(ICH_VTR_EL2); + max_lr_idx = vtr_to_max_lr_idx(val); + nr_pri_bits = vtr_to_nr_pri_bits(val); + + switch (max_lr_idx) { + case 15: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)] = read_gicreg(ICH_LR15_EL2); + case 14: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)] = read_gicreg(ICH_LR14_EL2); + case 13: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)] = read_gicreg(ICH_LR13_EL2); + case 12: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)] = read_gicreg(ICH_LR12_EL2); + case 11: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)] = read_gicreg(ICH_LR11_EL2); + case 10: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)] = read_gicreg(ICH_LR10_EL2); + case 9: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)] = read_gicreg(ICH_LR9_EL2); + case 8: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)] = read_gicreg(ICH_LR8_EL2); + case 7: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)] = read_gicreg(ICH_LR7_EL2); + case 6: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)] = read_gicreg(ICH_LR6_EL2); + case 5: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)] = read_gicreg(ICH_LR5_EL2); + case 4: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)] = read_gicreg(ICH_LR4_EL2); + case 3: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)] = read_gicreg(ICH_LR3_EL2); + case 2: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)] = read_gicreg(ICH_LR2_EL2); + case 1: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)] = read_gicreg(ICH_LR1_EL2); + case 0: + cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)] = read_gicreg(ICH_LR0_EL2); + } + + switch (nr_pri_bits) { + case 7: + cpu_if->vgic_ap0r[3] = read_gicreg(ICH_AP0R3_EL2); + cpu_if->vgic_ap0r[2] = read_gicreg(ICH_AP0R2_EL2); + case 6: + cpu_if->vgic_ap0r[1] = read_gicreg(ICH_AP0R1_EL2); + default: + cpu_if->vgic_ap0r[0] = read_gicreg(ICH_AP0R0_EL2); + } + + switch (nr_pri_bits) { + case 7: + cpu_if->vgic_ap1r[3] = read_gicreg(ICH_AP1R3_EL2); + cpu_if->vgic_ap1r[2] = read_gicreg(ICH_AP1R2_EL2); + case 6: + cpu_if->vgic_ap1r[1] = read_gicreg(ICH_AP1R1_EL2); + default: + cpu_if->vgic_ap1r[0] = read_gicreg(ICH_AP1R0_EL2); + } + + val = read_gicreg(ICC_SRE_EL2); + write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2); + isb(); /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */ + write_gicreg(1, ICC_SRE_EL1); +} + +void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) +{ + struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; + u64 val; + u32 max_lr_idx, nr_pri_bits; + + /* + * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a + * Group0 interrupt (as generated in GICv2 mode) to be + * delivered as a FIQ to the guest, with potentially fatal + * consequences. So we must make sure that ICC_SRE_EL1 has + * been actually programmed with the value we want before + * starting to mess with the rest of the GIC. + */ + write_gicreg(cpu_if->vgic_sre, ICC_SRE_EL1); + isb(); + + write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2); + write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2); + + val = read_gicreg(ICH_VTR_EL2); + max_lr_idx = vtr_to_max_lr_idx(val); + nr_pri_bits = vtr_to_nr_pri_bits(val); + + switch (nr_pri_bits) { + case 7: + write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2); + write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2); + case 6: + write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2); + default: + write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2); + } + + switch (nr_pri_bits) { + case 7: + write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2); + write_gicreg(cpu_if->vgic_ap0r[2], ICH_AP0R2_EL2); + case 6: + write_gicreg(cpu_if->vgic_ap0r[1], ICH_AP0R1_EL2); + default: + write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2); + } + + switch (max_lr_idx) { + case 15: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)], ICH_LR15_EL2); + case 14: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(14)], ICH_LR14_EL2); + case 13: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(13)], ICH_LR13_EL2); + case 12: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(12)], ICH_LR12_EL2); + case 11: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(11)], ICH_LR11_EL2); + case 10: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(10)], ICH_LR10_EL2); + case 9: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(9)], ICH_LR9_EL2); + case 8: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(8)], ICH_LR8_EL2); + case 7: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(7)], ICH_LR7_EL2); + case 6: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(6)], ICH_LR6_EL2); + case 5: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(5)], ICH_LR5_EL2); + case 4: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(4)], ICH_LR4_EL2); + case 3: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(3)], ICH_LR3_EL2); + case 2: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(2)], ICH_LR2_EL2); + case 1: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(1)], ICH_LR1_EL2); + case 0: + write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(0)], ICH_LR0_EL2); + } + + /* + * Ensures that the above will have reached the + * (re)distributors. This ensure the guest will read the + * correct values from the memory-mapped interface. + */ + isb(); + dsb(sy); + + /* + * Prevent the guest from touching the GIC system registers if + * SRE isn't enabled for GICv3 emulation. + */ + if (!cpu_if->vgic_sre) { + write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE, + ICC_SRE_EL2); + } +} + +static u64 __hyp_text __vgic_v3_read_ich_vtr_el2(void) +{ + return read_gicreg(ICH_VTR_EL2); +} + +__alias(__vgic_v3_read_ich_vtr_el2) u64 __vgic_v3_get_ich_vtr_el2(void); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index d2650e84faf2..eec3598b4184 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -29,6 +29,7 @@ #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kvm_arm.h> +#include <asm/kvm_asm.h> #include <asm/kvm_coproc.h> #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> @@ -219,9 +220,9 @@ static bool trap_debug_regs(struct kvm_vcpu *vcpu, * All writes will set the KVM_ARM64_DEBUG_DIRTY flag to ensure the * hyp.S code switches between host and guest values in future. */ -static inline void reg_to_dbg(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - u64 *dbg_reg) +static void reg_to_dbg(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + u64 *dbg_reg) { u64 val = p->regval; @@ -234,18 +235,18 @@ static inline void reg_to_dbg(struct kvm_vcpu *vcpu, vcpu->arch.debug_flags |= KVM_ARM64_DEBUG_DIRTY; } -static inline void dbg_to_reg(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - u64 *dbg_reg) +static void dbg_to_reg(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + u64 *dbg_reg) { p->regval = *dbg_reg; if (p->is_32bit) p->regval &= 0xffffffffUL; } -static inline bool trap_bvr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) +static bool trap_bvr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; @@ -279,15 +280,15 @@ static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, return 0; } -static inline void reset_bvr(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) +static void reset_bvr(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) { vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val; } -static inline bool trap_bcr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) +static bool trap_bcr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; @@ -322,15 +323,15 @@ static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, return 0; } -static inline void reset_bcr(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) +static void reset_bcr(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) { vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val; } -static inline bool trap_wvr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) +static bool trap_wvr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; @@ -365,15 +366,15 @@ static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, return 0; } -static inline void reset_wvr(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) +static void reset_wvr(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) { vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val; } -static inline bool trap_wcr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) +static bool trap_wcr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; @@ -407,8 +408,8 @@ static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, return 0; } -static inline void reset_wcr(struct kvm_vcpu *vcpu, - const struct sys_reg_desc *rd) +static void reset_wcr(struct kvm_vcpu *vcpu, + const struct sys_reg_desc *rd) { vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val; } @@ -722,9 +723,9 @@ static bool trap_debug32(struct kvm_vcpu *vcpu, * system is in. */ -static inline bool trap_xvr(struct kvm_vcpu *vcpu, - struct sys_reg_params *p, - const struct sys_reg_desc *rd) +static bool trap_xvr(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *rd) { u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; diff --git a/arch/arm64/kvm/vgic-v2-switch.S b/arch/arm64/kvm/vgic-v2-switch.S deleted file mode 100644 index 3f000712a85d..000000000000 --- a/arch/arm64/kvm/vgic-v2-switch.S +++ /dev/null @@ -1,134 +0,0 @@ -/* - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/linkage.h> -#include <linux/irqchip/arm-gic.h> - -#include <asm/assembler.h> -#include <asm/memory.h> -#include <asm/asm-offsets.h> -#include <asm/kvm.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_arm.h> -#include <asm/kvm_mmu.h> - - .text - .pushsection .hyp.text, "ax" - -/* - * Save the VGIC CPU state into memory - * x0: Register pointing to VCPU struct - * Do not corrupt x1!!! - */ -ENTRY(__save_vgic_v2_state) -__save_vgic_v2_state: - /* Get VGIC VCTRL base into x2 */ - ldr x2, [x0, #VCPU_KVM] - kern_hyp_va x2 - ldr x2, [x2, #KVM_VGIC_VCTRL] - kern_hyp_va x2 - cbz x2, 2f // disabled - - /* Compute the address of struct vgic_cpu */ - add x3, x0, #VCPU_VGIC_CPU - - /* Save all interesting registers */ - ldr w5, [x2, #GICH_VMCR] - ldr w6, [x2, #GICH_MISR] - ldr w7, [x2, #GICH_EISR0] - ldr w8, [x2, #GICH_EISR1] - ldr w9, [x2, #GICH_ELRSR0] - ldr w10, [x2, #GICH_ELRSR1] - ldr w11, [x2, #GICH_APR] -CPU_BE( rev w5, w5 ) -CPU_BE( rev w6, w6 ) -CPU_BE( rev w7, w7 ) -CPU_BE( rev w8, w8 ) -CPU_BE( rev w9, w9 ) -CPU_BE( rev w10, w10 ) -CPU_BE( rev w11, w11 ) - - str w5, [x3, #VGIC_V2_CPU_VMCR] - str w6, [x3, #VGIC_V2_CPU_MISR] -CPU_LE( str w7, [x3, #VGIC_V2_CPU_EISR] ) -CPU_LE( str w8, [x3, #(VGIC_V2_CPU_EISR + 4)] ) -CPU_LE( str w9, [x3, #VGIC_V2_CPU_ELRSR] ) -CPU_LE( str w10, [x3, #(VGIC_V2_CPU_ELRSR + 4)] ) -CPU_BE( str w7, [x3, #(VGIC_V2_CPU_EISR + 4)] ) -CPU_BE( str w8, [x3, #VGIC_V2_CPU_EISR] ) -CPU_BE( str w9, [x3, #(VGIC_V2_CPU_ELRSR + 4)] ) -CPU_BE( str w10, [x3, #VGIC_V2_CPU_ELRSR] ) - str w11, [x3, #VGIC_V2_CPU_APR] - - /* Clear GICH_HCR */ - str wzr, [x2, #GICH_HCR] - - /* Save list registers */ - add x2, x2, #GICH_LR0 - ldr w4, [x3, #VGIC_CPU_NR_LR] - add x3, x3, #VGIC_V2_CPU_LR -1: ldr w5, [x2], #4 -CPU_BE( rev w5, w5 ) - str w5, [x3], #4 - sub w4, w4, #1 - cbnz w4, 1b -2: - ret -ENDPROC(__save_vgic_v2_state) - -/* - * Restore the VGIC CPU state from memory - * x0: Register pointing to VCPU struct - */ -ENTRY(__restore_vgic_v2_state) -__restore_vgic_v2_state: - /* Get VGIC VCTRL base into x2 */ - ldr x2, [x0, #VCPU_KVM] - kern_hyp_va x2 - ldr x2, [x2, #KVM_VGIC_VCTRL] - kern_hyp_va x2 - cbz x2, 2f // disabled - - /* Compute the address of struct vgic_cpu */ - add x3, x0, #VCPU_VGIC_CPU - - /* We only restore a minimal set of registers */ - ldr w4, [x3, #VGIC_V2_CPU_HCR] - ldr w5, [x3, #VGIC_V2_CPU_VMCR] - ldr w6, [x3, #VGIC_V2_CPU_APR] -CPU_BE( rev w4, w4 ) -CPU_BE( rev w5, w5 ) -CPU_BE( rev w6, w6 ) - - str w4, [x2, #GICH_HCR] - str w5, [x2, #GICH_VMCR] - str w6, [x2, #GICH_APR] - - /* Restore list registers */ - add x2, x2, #GICH_LR0 - ldr w4, [x3, #VGIC_CPU_NR_LR] - add x3, x3, #VGIC_V2_CPU_LR -1: ldr w5, [x3], #4 -CPU_BE( rev w5, w5 ) - str w5, [x2], #4 - sub w4, w4, #1 - cbnz w4, 1b -2: - ret -ENDPROC(__restore_vgic_v2_state) - - .popsection diff --git a/arch/arm64/kvm/vgic-v3-switch.S b/arch/arm64/kvm/vgic-v3-switch.S deleted file mode 100644 index 3c20730ddff5..000000000000 --- a/arch/arm64/kvm/vgic-v3-switch.S +++ /dev/null @@ -1,269 +0,0 @@ -/* - * Copyright (C) 2012,2013 - ARM Ltd - * Author: Marc Zyngier <marc.zyngier@arm.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program. If not, see <http://www.gnu.org/licenses/>. - */ - -#include <linux/linkage.h> -#include <linux/irqchip/arm-gic-v3.h> - -#include <asm/assembler.h> -#include <asm/memory.h> -#include <asm/asm-offsets.h> -#include <asm/kvm.h> -#include <asm/kvm_asm.h> -#include <asm/kvm_arm.h> - - .text - .pushsection .hyp.text, "ax" - -/* - * We store LRs in reverse order to let the CPU deal with streaming - * access. Use this macro to make it look saner... - */ -#define LR_OFFSET(n) (VGIC_V3_CPU_LR + (15 - n) * 8) - -/* - * Save the VGIC CPU state into memory - * x0: Register pointing to VCPU struct - * Do not corrupt x1!!! - */ -.macro save_vgic_v3_state - // Compute the address of struct vgic_cpu - add x3, x0, #VCPU_VGIC_CPU - - // Make sure stores to the GIC via the memory mapped interface - // are now visible to the system register interface - dsb st - - // Save all interesting registers - mrs_s x5, ICH_VMCR_EL2 - mrs_s x6, ICH_MISR_EL2 - mrs_s x7, ICH_EISR_EL2 - mrs_s x8, ICH_ELSR_EL2 - - str w5, [x3, #VGIC_V3_CPU_VMCR] - str w6, [x3, #VGIC_V3_CPU_MISR] - str w7, [x3, #VGIC_V3_CPU_EISR] - str w8, [x3, #VGIC_V3_CPU_ELRSR] - - msr_s ICH_HCR_EL2, xzr - - mrs_s x21, ICH_VTR_EL2 - mvn w22, w21 - ubfiz w23, w22, 2, 4 // w23 = (15 - ListRegs) * 4 - - adr x24, 1f - add x24, x24, x23 - br x24 - -1: - mrs_s x20, ICH_LR15_EL2 - mrs_s x19, ICH_LR14_EL2 - mrs_s x18, ICH_LR13_EL2 - mrs_s x17, ICH_LR12_EL2 - mrs_s x16, ICH_LR11_EL2 - mrs_s x15, ICH_LR10_EL2 - mrs_s x14, ICH_LR9_EL2 - mrs_s x13, ICH_LR8_EL2 - mrs_s x12, ICH_LR7_EL2 - mrs_s x11, ICH_LR6_EL2 - mrs_s x10, ICH_LR5_EL2 - mrs_s x9, ICH_LR4_EL2 - mrs_s x8, ICH_LR3_EL2 - mrs_s x7, ICH_LR2_EL2 - mrs_s x6, ICH_LR1_EL2 - mrs_s x5, ICH_LR0_EL2 - - adr x24, 1f - add x24, x24, x23 - br x24 - -1: - str x20, [x3, #LR_OFFSET(15)] - str x19, [x3, #LR_OFFSET(14)] - str x18, [x3, #LR_OFFSET(13)] - str x17, [x3, #LR_OFFSET(12)] - str x16, [x3, #LR_OFFSET(11)] - str x15, [x3, #LR_OFFSET(10)] - str x14, [x3, #LR_OFFSET(9)] - str x13, [x3, #LR_OFFSET(8)] - str x12, [x3, #LR_OFFSET(7)] - str x11, [x3, #LR_OFFSET(6)] - str x10, [x3, #LR_OFFSET(5)] - str x9, [x3, #LR_OFFSET(4)] - str x8, [x3, #LR_OFFSET(3)] - str x7, [x3, #LR_OFFSET(2)] - str x6, [x3, #LR_OFFSET(1)] - str x5, [x3, #LR_OFFSET(0)] - - tbnz w21, #29, 6f // 6 bits - tbz w21, #30, 5f // 5 bits - // 7 bits - mrs_s x20, ICH_AP0R3_EL2 - str w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)] - mrs_s x19, ICH_AP0R2_EL2 - str w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)] -6: mrs_s x18, ICH_AP0R1_EL2 - str w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)] -5: mrs_s x17, ICH_AP0R0_EL2 - str w17, [x3, #VGIC_V3_CPU_AP0R] - - tbnz w21, #29, 6f // 6 bits - tbz w21, #30, 5f // 5 bits - // 7 bits - mrs_s x20, ICH_AP1R3_EL2 - str w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)] - mrs_s x19, ICH_AP1R2_EL2 - str w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)] -6: mrs_s x18, ICH_AP1R1_EL2 - str w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)] -5: mrs_s x17, ICH_AP1R0_EL2 - str w17, [x3, #VGIC_V3_CPU_AP1R] - - // Restore SRE_EL1 access and re-enable SRE at EL1. - mrs_s x5, ICC_SRE_EL2 - orr x5, x5, #ICC_SRE_EL2_ENABLE - msr_s ICC_SRE_EL2, x5 - isb - mov x5, #1 - msr_s ICC_SRE_EL1, x5 -.endm - -/* - * Restore the VGIC CPU state from memory - * x0: Register pointing to VCPU struct - */ -.macro restore_vgic_v3_state - // Compute the address of struct vgic_cpu - add x3, x0, #VCPU_VGIC_CPU - - // Restore all interesting registers - ldr w4, [x3, #VGIC_V3_CPU_HCR] - ldr w5, [x3, #VGIC_V3_CPU_VMCR] - ldr w25, [x3, #VGIC_V3_CPU_SRE] - - msr_s ICC_SRE_EL1, x25 - - // make sure SRE is valid before writing the other registers - isb - - msr_s ICH_HCR_EL2, x4 - msr_s ICH_VMCR_EL2, x5 - - mrs_s x21, ICH_VTR_EL2 - - tbnz w21, #29, 6f // 6 bits - tbz w21, #30, 5f // 5 bits - // 7 bits - ldr w20, [x3, #(VGIC_V3_CPU_AP1R + 3*4)] - msr_s ICH_AP1R3_EL2, x20 - ldr w19, [x3, #(VGIC_V3_CPU_AP1R + 2*4)] - msr_s ICH_AP1R2_EL2, x19 -6: ldr w18, [x3, #(VGIC_V3_CPU_AP1R + 1*4)] - msr_s ICH_AP1R1_EL2, x18 -5: ldr w17, [x3, #VGIC_V3_CPU_AP1R] - msr_s ICH_AP1R0_EL2, x17 - - tbnz w21, #29, 6f // 6 bits - tbz w21, #30, 5f // 5 bits - // 7 bits - ldr w20, [x3, #(VGIC_V3_CPU_AP0R + 3*4)] - msr_s ICH_AP0R3_EL2, x20 - ldr w19, [x3, #(VGIC_V3_CPU_AP0R + 2*4)] - msr_s ICH_AP0R2_EL2, x19 -6: ldr w18, [x3, #(VGIC_V3_CPU_AP0R + 1*4)] - msr_s ICH_AP0R1_EL2, x18 -5: ldr w17, [x3, #VGIC_V3_CPU_AP0R] - msr_s ICH_AP0R0_EL2, x17 - - and w22, w21, #0xf - mvn w22, w21 - ubfiz w23, w22, 2, 4 // w23 = (15 - ListRegs) * 4 - - adr x24, 1f - add x24, x24, x23 - br x24 - -1: - ldr x20, [x3, #LR_OFFSET(15)] - ldr x19, [x3, #LR_OFFSET(14)] - ldr x18, [x3, #LR_OFFSET(13)] - ldr x17, [x3, #LR_OFFSET(12)] - ldr x16, [x3, #LR_OFFSET(11)] - ldr x15, [x3, #LR_OFFSET(10)] - ldr x14, [x3, #LR_OFFSET(9)] - ldr x13, [x3, #LR_OFFSET(8)] - ldr x12, [x3, #LR_OFFSET(7)] - ldr x11, [x3, #LR_OFFSET(6)] - ldr x10, [x3, #LR_OFFSET(5)] - ldr x9, [x3, #LR_OFFSET(4)] - ldr x8, [x3, #LR_OFFSET(3)] - ldr x7, [x3, #LR_OFFSET(2)] - ldr x6, [x3, #LR_OFFSET(1)] - ldr x5, [x3, #LR_OFFSET(0)] - - adr x24, 1f - add x24, x24, x23 - br x24 - -1: - msr_s ICH_LR15_EL2, x20 - msr_s ICH_LR14_EL2, x19 - msr_s ICH_LR13_EL2, x18 - msr_s ICH_LR12_EL2, x17 - msr_s ICH_LR11_EL2, x16 - msr_s ICH_LR10_EL2, x15 - msr_s ICH_LR9_EL2, x14 - msr_s ICH_LR8_EL2, x13 - msr_s ICH_LR7_EL2, x12 - msr_s ICH_LR6_EL2, x11 - msr_s ICH_LR5_EL2, x10 - msr_s ICH_LR4_EL2, x9 - msr_s ICH_LR3_EL2, x8 - msr_s ICH_LR2_EL2, x7 - msr_s ICH_LR1_EL2, x6 - msr_s ICH_LR0_EL2, x5 - - // Ensure that the above will have reached the - // (re)distributors. This ensure the guest will read - // the correct values from the memory-mapped interface. - isb - dsb sy - - // Prevent the guest from touching the GIC system registers - // if SRE isn't enabled for GICv3 emulation - cbnz x25, 1f - mrs_s x5, ICC_SRE_EL2 - and x5, x5, #~ICC_SRE_EL2_ENABLE - msr_s ICC_SRE_EL2, x5 -1: -.endm - -ENTRY(__save_vgic_v3_state) - save_vgic_v3_state - ret -ENDPROC(__save_vgic_v3_state) - -ENTRY(__restore_vgic_v3_state) - restore_vgic_v3_state - ret -ENDPROC(__restore_vgic_v3_state) - -ENTRY(__vgic_v3_get_ich_vtr_el2) - mrs_s x0, ICH_VTR_EL2 - ret -ENDPROC(__vgic_v3_get_ich_vtr_el2) - - .popsection diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S index cfa44a6adc0a..6df07069a025 100644 --- a/arch/arm64/mm/cache.S +++ b/arch/arm64/mm/cache.S @@ -81,26 +81,32 @@ ENDPROC(__flush_cache_user_range) /* * __flush_dcache_area(kaddr, size) * - * Ensure that the data held in the page kaddr is written back to the - * page in question. + * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * are cleaned and invalidated to the PoC. * * - kaddr - kernel address * - size - size in question */ ENTRY(__flush_dcache_area) - dcache_line_size x2, x3 - add x1, x0, x1 - sub x3, x2, #1 - bic x0, x0, x3 -1: dc civac, x0 // clean & invalidate D line / unified line - add x0, x0, x2 - cmp x0, x1 - b.lo 1b - dsb sy + dcache_by_line_op civac, sy, x0, x1, x2, x3 ret ENDPIPROC(__flush_dcache_area) /* + * __clean_dcache_area_pou(kaddr, size) + * + * Ensure that any D-cache lines for the interval [kaddr, kaddr+size) + * are cleaned to the PoU. + * + * - kaddr - kernel address + * - size - size in question + */ +ENTRY(__clean_dcache_area_pou) + dcache_by_line_op cvau, ish, x0, x1, x2, x3 + ret +ENDPROC(__clean_dcache_area_pou) + +/* * __inval_cache_range(start, end) * - start - start address of region * - end - end address of region diff --git a/arch/arm64/mm/copypage.c b/arch/arm64/mm/copypage.c index 13bbc3be6f5a..22e4cb4d6f53 100644 --- a/arch/arm64/mm/copypage.c +++ b/arch/arm64/mm/copypage.c @@ -24,8 +24,9 @@ void __cpu_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr) { + struct page *page = virt_to_page(kto); copy_page(kto, kfrom); - __flush_dcache_area(kto, PAGE_SIZE); + flush_dcache_page(page); } EXPORT_SYMBOL_GPL(__cpu_copy_user_page); diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 7963aa4b5d28..331c4ca6205c 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -40,7 +40,7 @@ static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, static struct gen_pool *atomic_pool; #define DEFAULT_DMA_COHERENT_POOL_SIZE SZ_256K -static size_t atomic_pool_size = DEFAULT_DMA_COHERENT_POOL_SIZE; +static size_t atomic_pool_size __initdata = DEFAULT_DMA_COHERENT_POOL_SIZE; static int __init early_coherent_pool(char *p) { @@ -896,7 +896,7 @@ static int __iommu_attach_notifier(struct notifier_block *nb, return 0; } -static int register_iommu_dma_ops_notifier(struct bus_type *bus) +static int __init register_iommu_dma_ops_notifier(struct bus_type *bus) { struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL); int ret; diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index c26b804015e8..46649d6e6c5a 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -34,19 +34,24 @@ void flush_cache_range(struct vm_area_struct *vma, unsigned long start, __flush_icache_all(); } +static void sync_icache_aliases(void *kaddr, unsigned long len) +{ + unsigned long addr = (unsigned long)kaddr; + + if (icache_is_aliasing()) { + __clean_dcache_area_pou(kaddr, len); + __flush_icache_all(); + } else { + flush_icache_range(addr, addr + len); + } +} + static void flush_ptrace_access(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *kaddr, unsigned long len) { - if (vma->vm_flags & VM_EXEC) { - unsigned long addr = (unsigned long)kaddr; - if (icache_is_aliasing()) { - __flush_dcache_area(kaddr, len); - __flush_icache_all(); - } else { - flush_icache_range(addr, addr + len); - } - } + if (vma->vm_flags & VM_EXEC) + sync_icache_aliases(kaddr, len); } /* @@ -74,13 +79,11 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr) if (!page_mapping(page)) return; - if (!test_and_set_bit(PG_dcache_clean, &page->flags)) { - __flush_dcache_area(page_address(page), - PAGE_SIZE << compound_order(page)); + if (!test_and_set_bit(PG_dcache_clean, &page->flags)) + sync_icache_aliases(page_address(page), + PAGE_SIZE << compound_order(page)); + else if (icache_is_aivivt()) __flush_icache_all(); - } else if (icache_is_aivivt()) { - __flush_icache_all(); - } } /* diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 383b03ff38f8..82d607c3614e 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -41,17 +41,289 @@ int pud_huge(pud_t pud) #endif } +static int find_num_contig(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte, size_t *pgsize) +{ + pgd_t *pgd = pgd_offset(mm, addr); + pud_t *pud; + pmd_t *pmd; + + *pgsize = PAGE_SIZE; + if (!pte_cont(pte)) + return 1; + if (!pgd_present(*pgd)) { + VM_BUG_ON(!pgd_present(*pgd)); + return 1; + } + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) { + VM_BUG_ON(!pud_present(*pud)); + return 1; + } + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) { + VM_BUG_ON(!pmd_present(*pmd)); + return 1; + } + if ((pte_t *)pmd == ptep) { + *pgsize = PMD_SIZE; + return CONT_PMDS; + } + return CONT_PTES; +} + +void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pte) +{ + size_t pgsize; + int i; + int ncontig = find_num_contig(mm, addr, ptep, pte, &pgsize); + unsigned long pfn; + pgprot_t hugeprot; + + if (ncontig == 1) { + set_pte_at(mm, addr, ptep, pte); + return; + } + + pfn = pte_pfn(pte); + hugeprot = __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); + for (i = 0; i < ncontig; i++) { + pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep, + pte_val(pfn_pte(pfn, hugeprot))); + set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot)); + ptep++; + pfn += pgsize >> PAGE_SHIFT; + addr += pgsize; + } +} + +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pte_t *pte = NULL; + + pr_debug("%s: addr:0x%lx sz:0x%lx\n", __func__, addr, sz); + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (!pud) + return NULL; + + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else if (sz == (PAGE_SIZE * CONT_PTES)) { + pmd_t *pmd = pmd_alloc(mm, pud, addr); + + WARN_ON(addr & (sz - 1)); + /* + * Note that if this code were ever ported to the + * 32-bit arm platform then it will cause trouble in + * the case where CONFIG_HIGHPTE is set, since there + * will be no pte_unmap() to correspond with this + * pte_alloc_map(). + */ + pte = pte_alloc_map(mm, NULL, pmd, addr); + } else if (sz == PMD_SIZE) { + if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && + pud_none(*pud)) + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); + } else if (sz == (PMD_SIZE * CONT_PMDS)) { + pmd_t *pmd; + + pmd = pmd_alloc(mm, pud, addr); + WARN_ON(addr & (sz - 1)); + return (pte_t *)pmd; + } + + pr_debug("%s: addr:0x%lx sz:0x%lx ret pte=%p/0x%llx\n", __func__, addr, + sz, pte, pte_val(*pte)); + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd = NULL; + pte_t *pte = NULL; + + pgd = pgd_offset(mm, addr); + pr_debug("%s: addr:0x%lx pgd:%p\n", __func__, addr, pgd); + if (!pgd_present(*pgd)) + return NULL; + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) + return NULL; + + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) + return NULL; + + if (pte_cont(pmd_pte(*pmd))) { + pmd = pmd_offset( + pud, (addr & CONT_PMD_MASK)); + return (pte_t *)pmd; + } + if (pmd_huge(*pmd)) + return (pte_t *)pmd; + pte = pte_offset_kernel(pmd, addr); + if (pte_present(*pte) && pte_cont(*pte)) { + pte = pte_offset_kernel( + pmd, (addr & CONT_PTE_MASK)); + return pte; + } + return NULL; +} + +pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma, + struct page *page, int writable) +{ + size_t pagesize = huge_page_size(hstate_vma(vma)); + + if (pagesize == CONT_PTE_SIZE) { + entry = pte_mkcont(entry); + } else if (pagesize == CONT_PMD_SIZE) { + entry = pmd_pte(pmd_mkcont(pte_pmd(entry))); + } else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) { + pr_warn("%s: unrecognized huge page size 0x%lx\n", + __func__, pagesize); + } + return entry; +} + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + pte_t pte; + + if (pte_cont(*ptep)) { + int ncontig, i; + size_t pgsize; + pte_t *cpte; + bool is_dirty = false; + + cpte = huge_pte_offset(mm, addr); + ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); + /* save the 1st pte to return */ + pte = ptep_get_and_clear(mm, addr, cpte); + for (i = 1; i < ncontig; ++i) { + /* + * If HW_AFDBM is enabled, then the HW could + * turn on the dirty bit for any of the page + * in the set, so check them all. + */ + ++cpte; + if (pte_dirty(ptep_get_and_clear(mm, addr, cpte))) + is_dirty = true; + } + if (is_dirty) + return pte_mkdirty(pte); + else + return pte; + } else { + return ptep_get_and_clear(mm, addr, ptep); + } +} + +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty) +{ + pte_t *cpte; + + if (pte_cont(pte)) { + int ncontig, i, changed = 0; + size_t pgsize = 0; + unsigned long pfn = pte_pfn(pte); + /* Select all bits except the pfn */ + pgprot_t hugeprot = + __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ + pte_val(pte)); + + cpte = huge_pte_offset(vma->vm_mm, addr); + pfn = pte_pfn(*cpte); + ncontig = find_num_contig(vma->vm_mm, addr, cpte, + *cpte, &pgsize); + for (i = 0; i < ncontig; ++i, ++cpte) { + changed = ptep_set_access_flags(vma, addr, cpte, + pfn_pte(pfn, + hugeprot), + dirty); + pfn += pgsize >> PAGE_SHIFT; + } + return changed; + } else { + return ptep_set_access_flags(vma, addr, ptep, pte, dirty); + } +} + +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + if (pte_cont(*ptep)) { + int ncontig, i; + pte_t *cpte; + size_t pgsize = 0; + + cpte = huge_pte_offset(mm, addr); + ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize); + for (i = 0; i < ncontig; ++i, ++cpte) + ptep_set_wrprotect(mm, addr, cpte); + } else { + ptep_set_wrprotect(mm, addr, ptep); + } +} + +void huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ + if (pte_cont(*ptep)) { + int ncontig, i; + pte_t *cpte; + size_t pgsize = 0; + + cpte = huge_pte_offset(vma->vm_mm, addr); + ncontig = find_num_contig(vma->vm_mm, addr, cpte, + *cpte, &pgsize); + for (i = 0; i < ncontig; ++i, ++cpte) + ptep_clear_flush(vma, addr, cpte); + } else { + ptep_clear_flush(vma, addr, ptep); + } +} + static __init int setup_hugepagesz(char *opt) { unsigned long ps = memparse(opt, &opt); + if (ps == PMD_SIZE) { hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); } else if (ps == PUD_SIZE) { hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + } else if (ps == (PAGE_SIZE * CONT_PTES)) { + hugetlb_add_hstate(CONT_PTE_SHIFT); + } else if (ps == (PMD_SIZE * CONT_PMDS)) { + hugetlb_add_hstate((PMD_SHIFT + CONT_PMD_SHIFT) - PAGE_SHIFT); } else { - pr_err("hugepagesz: Unsupported page size %lu M\n", ps >> 20); + pr_err("hugepagesz: Unsupported page size %lu K\n", ps >> 10); return 0; } return 1; } __setup("hugepagesz=", setup_hugepagesz); + +#ifdef CONFIG_ARM64_64K_PAGES +static __init int add_default_hugepagesz(void) +{ + if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL) + hugetlb_add_hstate(CONT_PMD_SHIFT); + return 0; +} +arch_initcall(add_default_hugepagesz); +#endif diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 17bf39ac83ba..f3b061e67bfe 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -71,7 +71,7 @@ early_param("initrd", early_initrd); * currently assumes that for memory starting above 4G, 32-bit devices will * use a DMA offset. */ -static phys_addr_t max_zone_dma_phys(void) +static phys_addr_t __init max_zone_dma_phys(void) { phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32); return min(offset + (1ULL << 32), memblock_end_of_DRAM()); @@ -120,17 +120,17 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) #ifdef CONFIG_HAVE_ARCH_PFN_VALID int pfn_valid(unsigned long pfn) { - return memblock_is_memory(pfn << PAGE_SHIFT); + return memblock_is_map_memory(pfn << PAGE_SHIFT); } EXPORT_SYMBOL(pfn_valid); #endif #ifndef CONFIG_SPARSEMEM -static void arm64_memory_present(void) +static void __init arm64_memory_present(void) { } #else -static void arm64_memory_present(void) +static void __init arm64_memory_present(void) { struct memblock_region *reg; @@ -360,7 +360,6 @@ void free_initmem(void) { fixup_init(); free_initmem_default(0); - free_alternatives_memory(); } #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 873e363048c6..58faeaa7fbdc 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -251,6 +251,14 @@ static void __create_mapping(struct mm_struct *mm, pgd_t *pgd, { unsigned long addr, length, end, next; + /* + * If the virtual and physical address don't have the same offset + * within a page, we cannot map the region as the caller expects. + */ + if (WARN_ON((phys ^ virt) & ~PAGE_MASK)) + return; + + phys &= PAGE_MASK; addr = virt & PAGE_MASK; length = PAGE_ALIGN(size + (virt & ~PAGE_MASK)); @@ -280,7 +288,7 @@ static void __init create_mapping(phys_addr_t phys, unsigned long virt, &phys, virt); return; } - __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), phys, virt, + __create_mapping(&init_mm, pgd_offset_k(virt), phys, virt, size, prot, early_alloc); } @@ -301,7 +309,7 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt, return; } - return __create_mapping(&init_mm, pgd_offset_k(virt & PAGE_MASK), + return __create_mapping(&init_mm, pgd_offset_k(virt), phys, virt, size, prot, late_alloc); } @@ -372,6 +380,8 @@ static void __init map_mem(void) if (start >= end) break; + if (memblock_is_nomap(reg)) + continue; if (ARM64_SWAPPER_USES_SECTION_MAPS) { /* @@ -456,6 +466,9 @@ void __init paging_init(void) empty_zero_page = virt_to_page(zero_page); + /* Ensure the zero page is visible to the page table walker */ + dsb(ishst); + /* * TTBR0 is only used for the identity mapping at this stage. Make it * point to zero page to avoid speculatively fetching new entries. diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index cb3ba1b812e7..ae11d4e03d0e 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -46,14 +46,14 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) kmem_cache_free(pgd_cache, pgd); } -static int __init pgd_cache_init(void) +void __init pgd_cache_init(void) { + if (PGD_SIZE == PAGE_SIZE) + return; + /* * Naturally aligned pgds required by the architecture. */ - if (PGD_SIZE != PAGE_SIZE) - pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE, - SLAB_PANIC, NULL); - return 0; + pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_SIZE, + SLAB_PANIC, NULL); } -core_initcall(pgd_cache_init); diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S index 4c4d93c4bf65..146bd99a7532 100644 --- a/arch/arm64/mm/proc-macros.S +++ b/arch/arm64/mm/proc-macros.S @@ -62,3 +62,25 @@ bfi \valreg, \tmpreg, #TCR_T0SZ_OFFSET, #TCR_TxSZ_WIDTH #endif .endm + +/* + * Macro to perform a data cache maintenance for the interval + * [kaddr, kaddr + size) + * + * op: operation passed to dc instruction + * domain: domain used in dsb instruciton + * kaddr: starting virtual address of the region + * size: size of the region + * Corrupts: kaddr, size, tmp1, tmp2 + */ + .macro dcache_by_line_op op, domain, kaddr, size, tmp1, tmp2 + dcache_line_size \tmp1, \tmp2 + add \size, \kaddr, \size + sub \tmp2, \tmp1, #1 + bic \kaddr, \kaddr, \tmp2 +9998: dc \op, \kaddr + add \kaddr, \kaddr, \tmp1 + cmp \kaddr, \size + b.lo 9998b + dsb \domain + .endm diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index cacecc4ad3e5..a3d867e723b4 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -117,6 +117,7 @@ ENTRY(cpu_do_resume) */ ubfx x11, x11, #1, #1 msr oslar_el1, x11 + msr pmuserenr_el0, xzr // Disable PMU access from EL0 mov x0, x12 dsb nsh // Make sure local tlb invalidation completed isb @@ -139,8 +140,6 @@ ENTRY(cpu_do_switch_mm) ret ENDPROC(cpu_do_switch_mm) - .section ".text.init", #alloc, #execinstr - /* * __cpu_setup * @@ -155,6 +154,7 @@ ENTRY(__cpu_setup) msr cpacr_el1, x0 // Enable FP/ASIMD mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 + msr pmuserenr_el0, xzr // Disable PMU access from EL0 /* * Memory region attributes for LPAE: * diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index b162ad70effc..7658612d915c 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -152,8 +152,6 @@ static void build_prologue(struct jit_ctx *ctx) const u8 r8 = bpf2a64[BPF_REG_8]; const u8 r9 = bpf2a64[BPF_REG_9]; const u8 fp = bpf2a64[BPF_REG_FP]; - const u8 ra = bpf2a64[BPF_REG_A]; - const u8 rx = bpf2a64[BPF_REG_X]; const u8 tmp1 = bpf2a64[TMP_REG_1]; const u8 tmp2 = bpf2a64[TMP_REG_2]; @@ -200,10 +198,6 @@ static void build_prologue(struct jit_ctx *ctx) /* Set up function call stack */ emit(A64_SUB_I(1, A64_SP, A64_SP, STACK_SIZE), ctx); - - /* Clear registers A and X */ - emit_a64_mov_i64(ra, 0, ctx); - emit_a64_mov_i64(rx, 0, ctx); } static void build_epilogue(struct jit_ctx *ctx) diff --git a/arch/arm64/xen/hypercall.S b/arch/arm64/xen/hypercall.S index 8bbe9401f4f0..70df80e8da2c 100644 --- a/arch/arm64/xen/hypercall.S +++ b/arch/arm64/xen/hypercall.S @@ -80,6 +80,7 @@ HYPERCALL2(memory_op); HYPERCALL2(physdev_op); HYPERCALL3(vcpu_op); HYPERCALL1(tmem_op); +HYPERCALL1(platform_op_raw); HYPERCALL2(multicall); ENTRY(privcmd_call) diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h index 2b65ed6b277c..9de0796240a0 100644 --- a/arch/avr32/include/uapi/asm/socket.h +++ b/arch/avr32/include/uapi/asm/socket.h @@ -85,4 +85,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _UAPI__ASM_AVR32_SOCKET_H */ diff --git a/arch/blackfin/include/asm/cmpxchg.h b/arch/blackfin/include/asm/cmpxchg.h index c05868cc61c1..253928854299 100644 --- a/arch/blackfin/include/asm/cmpxchg.h +++ b/arch/blackfin/include/asm/cmpxchg.h @@ -128,6 +128,5 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, #endif /* !CONFIG_SMP */ #define xchg(ptr, x) ((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr)))) -#define tas(ptr) ((void)xchg((ptr), 1)) #endif /* __ARCH_BLACKFIN_CMPXCHG__ */ diff --git a/arch/blackfin/include/asm/uaccess.h b/arch/blackfin/include/asm/uaccess.h index 90612a7f2cf3..12f5d6851bbc 100644 --- a/arch/blackfin/include/asm/uaccess.h +++ b/arch/blackfin/include/asm/uaccess.h @@ -168,12 +168,6 @@ static inline int bad_user_access_length(void) #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user -#define copy_to_user_ret(to, from, n, retval) ({ if (copy_to_user(to, from, n))\ - return retval; }) - -#define copy_from_user_ret(to, from, n, retval) ({ if (copy_from_user(to, from, n))\ - return retval; }) - static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c index 2de71e8c104b..f35525b55819 100644 --- a/arch/blackfin/mach-bf561/boards/ezkit.c +++ b/arch/blackfin/mach-bf561/boards/ezkit.c @@ -443,7 +443,7 @@ static const struct ppi_info ppi_info = { }; #if IS_ENABLED(CONFIG_VIDEO_ADV7183) -#include <media/adv7183.h> +#include <media/i2c/adv7183.h> static struct v4l2_input adv7183_inputs[] = { { .index = 0, diff --git a/arch/blackfin/mach-bf609/boards/ezkit.c b/arch/blackfin/mach-bf609/boards/ezkit.c index 2c61fc0c98f9..c7928d8ebb82 100644 --- a/arch/blackfin/mach-bf609/boards/ezkit.c +++ b/arch/blackfin/mach-bf609/boards/ezkit.c @@ -933,7 +933,7 @@ static struct bfin_capture_config bfin_capture_data = { #endif #if IS_ENABLED(CONFIG_VIDEO_ADV7842) -#include <media/adv7842.h> +#include <media/i2c/adv7842.h> static struct v4l2_input adv7842_inputs[] = { { @@ -1084,7 +1084,7 @@ static const struct ppi_info ppi_info = { }; #if IS_ENABLED(CONFIG_VIDEO_ADV7511) -#include <media/adv7511.h> +#include <media/i2c/adv7511.h> static struct v4l2_output adv7511_outputs[] = { { @@ -1125,7 +1125,7 @@ static struct bfin_display_config bfin_display_data = { #endif #if IS_ENABLED(CONFIG_VIDEO_ADV7343) -#include <media/adv7343.h> +#include <media/i2c/adv7343.h> static struct v4l2_output adv7343_outputs[] = { { diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 945544ec603e..64465e7e2245 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -4,6 +4,7 @@ generic-y += auxvec.h generic-y += barrier.h generic-y += bitsperlong.h generic-y += bugs.h +generic-y += clkdev.h generic-y += cputime.h generic-y += current.h generic-y += device.h diff --git a/arch/c6x/include/asm/clkdev.h b/arch/c6x/include/asm/clkdev.h deleted file mode 100644 index 76a070b1c2e5..000000000000 --- a/arch/c6x/include/asm/clkdev.h +++ /dev/null @@ -1,22 +0,0 @@ -#ifndef _ASM_CLKDEV_H -#define _ASM_CLKDEV_H - -#include <linux/slab.h> - -struct clk; - -static inline int __clk_get(struct clk *clk) -{ - return 1; -} - -static inline void __clk_put(struct clk *clk) -{ -} - -static inline struct clk_lookup_alloc *__clkdev_alloc(size_t size) -{ - return kzalloc(size, GFP_KERNEL); -} - -#endif /* _ASM_CLKDEV_H */ diff --git a/arch/c6x/include/asm/cmpxchg.h b/arch/c6x/include/asm/cmpxchg.h index b27c8cefb8c3..93d0a5a047a2 100644 --- a/arch/c6x/include/asm/cmpxchg.h +++ b/arch/c6x/include/asm/cmpxchg.h @@ -47,8 +47,6 @@ static inline unsigned int __xchg(unsigned int x, volatile void *ptr, int size) #define xchg(ptr, x) \ ((__typeof__(*(ptr)))__xchg((unsigned int)(x), (void *) (ptr), \ sizeof(*(ptr)))) -#define tas(ptr) xchg((ptr), 1) - #include <asm-generic/cmpxchg-local.h> diff --git a/arch/frv/include/asm/cmpxchg.h b/arch/frv/include/asm/cmpxchg.h index 5b04dd0aecab..a899765102ea 100644 --- a/arch/frv/include/asm/cmpxchg.h +++ b/arch/frv/include/asm/cmpxchg.h @@ -69,8 +69,6 @@ extern uint32_t __xchg_32(uint32_t i, volatile void *v); #endif -#define tas(ptr) (xchg((ptr), 1)) - /*****************************************************************************/ /* * compare and conditionally exchange value with memory diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h index 4823ad125578..f02e4849ae83 100644 --- a/arch/frv/include/uapi/asm/socket.h +++ b/arch/frv/include/uapi/asm/socket.h @@ -85,5 +85,8 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index dd3ac75776ad..2e20333cbce9 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -17,6 +17,7 @@ config H8300 select HAVE_MEMBLOCK select HAVE_DMA_ATTRS select CLKSRC_OF + select H8300_TMR8 config RWSEM_GENERIC_SPINLOCK def_bool y diff --git a/arch/h8300/include/asm/io.h b/arch/h8300/include/asm/io.h index bb837cded268..f0e14f3a800d 100644 --- a/arch/h8300/include/asm/io.h +++ b/arch/h8300/include/asm/io.h @@ -3,40 +3,45 @@ #ifdef __KERNEL__ -#include <asm-generic/io.h> - /* H8/300 internal I/O functions */ -static inline unsigned char ctrl_inb(unsigned long addr) + +#define __raw_readb __raw_readb +static inline u8 __raw_readb(const volatile void __iomem *addr) { - return *(volatile unsigned char *)addr; + return *(volatile u8 *)addr; } -static inline unsigned short ctrl_inw(unsigned long addr) +#define __raw_readw __raw_readw +static inline u16 __raw_readw(const volatile void __iomem *addr) { - return *(volatile unsigned short *)addr; + return *(volatile u16 *)addr; } -static inline unsigned long ctrl_inl(unsigned long addr) +#define __raw_readl __raw_readl +static inline u32 __raw_readl(const volatile void __iomem *addr) { - return *(volatile unsigned long *)addr; + return *(volatile u32 *)addr; } -static inline void ctrl_outb(unsigned char b, unsigned long addr) +#define __raw_writeb __raw_writeb +static inline void __raw_writeb(u8 b, const volatile void __iomem *addr) { - *(volatile unsigned char *)addr = b; + *(volatile u8 *)addr = b; } -static inline void ctrl_outw(unsigned short b, unsigned long addr) +#define __raw_writew __raw_writew +static inline void __raw_writew(u16 b, const volatile void __iomem *addr) { - *(volatile unsigned short *)addr = b; + *(volatile u16 *)addr = b; } -static inline void ctrl_outl(unsigned long b, unsigned long addr) +#define __raw_writel __raw_writel +static inline void __raw_writel(u32 b, const volatile void __iomem *addr) { - *(volatile unsigned long *)addr = b; + *(volatile u32 *)addr = b; } -static inline void ctrl_bclr(int b, unsigned char *addr) +static inline void ctrl_bclr(int b, void __iomem *addr) { if (__builtin_constant_p(b)) __asm__("bclr %1,%0" : "+WU"(*addr): "i"(b)); @@ -44,7 +49,7 @@ static inline void ctrl_bclr(int b, unsigned char *addr) __asm__("bclr %w1,%0" : "+WU"(*addr): "r"(b)); } -static inline void ctrl_bset(int b, unsigned char *addr) +static inline void ctrl_bset(int b, void __iomem *addr) { if (__builtin_constant_p(b)) __asm__("bset %1,%0" : "+WU"(*addr): "i"(b)); @@ -52,6 +57,8 @@ static inline void ctrl_bset(int b, unsigned char *addr) __asm__("bset %w1,%0" : "+WU"(*addr): "r"(b)); } +#include <asm-generic/io.h> + #endif /* __KERNEL__ */ #endif /* _H8300_IO_H */ diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c index c772abe6d19c..e4985dfa91dc 100644 --- a/arch/h8300/kernel/setup.c +++ b/arch/h8300/kernel/setup.c @@ -207,14 +207,14 @@ device_initcall(device_probe); #define get_wait(base, addr) ({ \ int baddr; \ baddr = ((addr) / 0x200000 * 2); \ - w *= (ctrl_inw((unsigned long)(base) + 2) & (3 << baddr)) + 1; \ + w *= (readw((base) + 2) & (3 << baddr)) + 1; \ }) #endif #if defined(CONFIG_CPU_H8S) #define get_wait(base, addr) ({ \ int baddr; \ baddr = ((addr) / 0x200000 * 16); \ - w *= (ctrl_inl((unsigned long)(base) + 2) & (7 << baddr)) + 1; \ + w *= (readl((base) + 2) & (7 << baddr)) + 1; \ }) #endif @@ -228,8 +228,8 @@ static __init int access_timing(void) bsc = of_find_compatible_node(NULL, NULL, "renesas,h8300-bsc"); base = of_iomap(bsc, 0); - w = (ctrl_inb((unsigned long)base + 0) & bit)?2:1; - if (ctrl_inb((unsigned long)base + 1) & bit) + w = (readb(base + 0) & bit)?2:1; + if (readb(base + 1) & bit) w *= get_wait(base, addr); else w *= 2; diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h index df896a1c41d3..209c4b817c95 100644 --- a/arch/ia64/include/asm/barrier.h +++ b/arch/ia64/include/asm/barrier.h @@ -77,7 +77,7 @@ do { \ ___p1; \ }) -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) /* * The group barrier in front of the rsm & ssm are necessary to ensure diff --git a/arch/ia64/include/asm/percpu.h b/arch/ia64/include/asm/percpu.h index 0ec484d2dcbc..b9295793a5e2 100644 --- a/arch/ia64/include/asm/percpu.h +++ b/arch/ia64/include/asm/percpu.h @@ -6,8 +6,6 @@ * David Mosberger-Tang <davidm@hpl.hp.com> */ -#define PERCPU_ENOUGH_ROOM PERCPU_PAGE_SIZE - #ifdef __ASSEMBLY__ # define THIS_CPU(var) (var) /* use this to mark accesses to per-CPU variables... */ #else /* !__ASSEMBLY__ */ diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h index 59be3d87f86d..bce29166de1b 100644 --- a/arch/ia64/include/uapi/asm/socket.h +++ b/arch/ia64/include/uapi/asm/socket.h @@ -94,4 +94,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/ia64/kernel/ftrace.c b/arch/ia64/kernel/ftrace.c index 3b0c2aa07857..cee411e647ca 100644 --- a/arch/ia64/kernel/ftrace.c +++ b/arch/ia64/kernel/ftrace.c @@ -97,13 +97,11 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char replaced[MCOUNT_INSN_SIZE]; /* - * Note: Due to modules and __init, code can - * disappear and change, we need to protect against faulting - * as well as code changing. We do this by using the - * probe_kernel_* functions. - * - * No real locking needed, this code is run through - * kstop_machine, or before SMP starts. + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. */ if (!do_check) diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h index 7bc4cb273856..14aa4a6bccf1 100644 --- a/arch/m32r/include/uapi/asm/socket.h +++ b/arch/m32r/include/uapi/asm/socket.h @@ -85,4 +85,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_M32R_SOCKET_H */ diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c index 192b00f098f4..cbd5991fd49a 100644 --- a/arch/m68k/atari/config.c +++ b/arch/m68k/atari/config.c @@ -858,7 +858,7 @@ static struct platform_device *atari_netusbee_devices[] __initdata = { }; #endif /* CONFIG_ATARI_ETHERNEC */ -#ifdef CONFIG_ATARI_SCSI +#if IS_ENABLED(CONFIG_ATARI_SCSI) static const struct resource atari_scsi_st_rsrc[] __initconst = { { .flags = IORESOURCE_IRQ, @@ -910,7 +910,7 @@ int __init atari_platform_init(void) } #endif -#ifdef CONFIG_ATARI_SCSI +#if IS_ENABLED(CONFIG_ATARI_SCSI) if (ATARIHW_PRESENT(ST_SCSI)) platform_device_register_simple("atari_scsi", -1, atari_scsi_st_rsrc, ARRAY_SIZE(atari_scsi_st_rsrc)); diff --git a/arch/m68k/coldfire/gpio.c b/arch/m68k/coldfire/gpio.c index e7e428681ec5..37a83e27c7a6 100644 --- a/arch/m68k/coldfire/gpio.c +++ b/arch/m68k/coldfire/gpio.c @@ -121,7 +121,7 @@ static int mcfgpio_direction_input(struct gpio_chip *chip, unsigned offset) static int mcfgpio_get_value(struct gpio_chip *chip, unsigned offset) { - return __mcfgpio_get_value(offset); + return !!__mcfgpio_get_value(offset); } static int mcfgpio_direction_output(struct gpio_chip *chip, unsigned offset, diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig index 5b4ec541ba7c..fc96e814188e 100644 --- a/arch/m68k/configs/amiga_defconfig +++ b/arch/m68k/configs/amiga_defconfig @@ -276,6 +276,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -532,11 +533,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -559,6 +562,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig index 6e5198e2c124..05c904f08d9d 100644 --- a/arch/m68k/configs/apollo_defconfig +++ b/arch/m68k/configs/apollo_defconfig @@ -274,6 +274,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -372,6 +373,7 @@ CONFIG_INPUT_EVDEV=m # CONFIG_MOUSE_PS2 is not set CONFIG_MOUSE_SERIAL=m CONFIG_SERIO=m +CONFIG_USERIO=m # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set # CONFIG_HW_RANDOM is not set @@ -490,11 +492,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -517,6 +521,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig index f75600b0ca23..d572b731c510 100644 --- a/arch/m68k/configs/atari_defconfig +++ b/arch/m68k/configs/atari_defconfig @@ -274,6 +274,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -512,11 +513,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -539,6 +542,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig index a42d91c389a6..11a30c65ad44 100644 --- a/arch/m68k/configs/bvme6000_defconfig +++ b/arch/m68k/configs/bvme6000_defconfig @@ -272,6 +272,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -483,11 +484,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -510,6 +513,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig index 77f4a11083e9..6630a5154b9d 100644 --- a/arch/m68k/configs/hp300_defconfig +++ b/arch/m68k/configs/hp300_defconfig @@ -274,6 +274,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -375,6 +376,7 @@ CONFIG_MOUSE_SERIAL=m CONFIG_INPUT_MISC=y CONFIG_HP_SDC_RTC=m CONFIG_SERIO_SERPORT=m +CONFIG_USERIO=m # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set # CONFIG_HW_RANDOM is not set @@ -492,11 +494,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -519,6 +523,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig index 5a329f77329b..1d90b71d0903 100644 --- a/arch/m68k/configs/mac_defconfig +++ b/arch/m68k/configs/mac_defconfig @@ -276,6 +276,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -394,6 +395,7 @@ CONFIG_MOUSE_SERIAL=m CONFIG_INPUT_MISC=y CONFIG_INPUT_M68K_BEEP=m CONFIG_SERIO=m +CONFIG_USERIO=m # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set CONFIG_SERIAL_PMACZILOG=y @@ -514,11 +516,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -541,6 +545,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig index 83c80d2030ec..1fd21c1ca87f 100644 --- a/arch/m68k/configs/multi_defconfig +++ b/arch/m68k/configs/multi_defconfig @@ -286,6 +286,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -449,6 +450,7 @@ CONFIG_INPUT_MISC=y CONFIG_INPUT_M68K_BEEP=m CONFIG_HP_SDC_RTC=m CONFIG_SERIO_Q40KBD=y +CONFIG_USERIO=m # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set CONFIG_SERIAL_PMACZILOG=y @@ -594,11 +596,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -621,6 +625,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig index 6cb42c3bf5a2..74e10f79d7b1 100644 --- a/arch/m68k/configs/mvme147_defconfig +++ b/arch/m68k/configs/mvme147_defconfig @@ -271,6 +271,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -483,11 +484,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -510,6 +513,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig index c7508c30330c..7034e716f166 100644 --- a/arch/m68k/configs/mvme16x_defconfig +++ b/arch/m68k/configs/mvme16x_defconfig @@ -272,6 +272,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -483,11 +484,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -510,6 +513,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig index 64b71664a303..f7deb5f702a6 100644 --- a/arch/m68k/configs/q40_defconfig +++ b/arch/m68k/configs/q40_defconfig @@ -272,6 +272,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -385,6 +386,7 @@ CONFIG_MOUSE_SERIAL=m CONFIG_INPUT_MISC=y CONFIG_INPUT_M68K_BEEP=m CONFIG_SERIO_Q40KBD=y +CONFIG_USERIO=m # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set CONFIG_PRINTER=m @@ -505,11 +507,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -532,6 +536,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig index 9a4cab78a2ea..0ce79eb0d805 100644 --- a/arch/m68k/configs/sun3_defconfig +++ b/arch/m68k/configs/sun3_defconfig @@ -269,6 +269,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -369,6 +370,7 @@ CONFIG_INPUT_EVDEV=m CONFIG_KEYBOARD_SUNKBD=y # CONFIG_MOUSE_PS2 is not set CONFIG_MOUSE_SERIAL=m +CONFIG_USERIO=m # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set # CONFIG_HW_RANDOM is not set @@ -484,11 +486,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -510,6 +514,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig index 1a2eaac13dbd..4cb787e4991f 100644 --- a/arch/m68k/configs/sun3x_defconfig +++ b/arch/m68k/configs/sun3x_defconfig @@ -269,6 +269,7 @@ CONFIG_MPLS=y CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_L3_MASTER_DEV=y # CONFIG_WIRELESS is not set # CONFIG_UEVENT_HELPER is not set CONFIG_DEVTMPFS=y @@ -369,6 +370,7 @@ CONFIG_INPUT_EVDEV=m CONFIG_KEYBOARD_SUNKBD=y # CONFIG_MOUSE_PS2 is not set CONFIG_MOUSE_SERIAL=m +CONFIG_USERIO=m # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set # CONFIG_HW_RANDOM is not set @@ -484,11 +486,13 @@ CONFIG_NLS_MAC_INUIT=m CONFIG_NLS_MAC_ROMANIAN=m CONFIG_NLS_MAC_TURKISH=m CONFIG_DLM=m +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set CONFIG_MAGIC_SYSRQ=y CONFIG_ASYNC_RAID6_TEST=m CONFIG_TEST_HEXDUMP=m CONFIG_TEST_STRING_HELPERS=m CONFIG_TEST_KSTRTOX=m +CONFIG_TEST_PRINTF=m CONFIG_TEST_RHASHTABLE=m CONFIG_TEST_LKM=m CONFIG_TEST_USER_COPY=m @@ -511,6 +515,7 @@ CONFIG_CRYPTO_CTS=m CONFIG_CRYPTO_LRW=m CONFIG_CRYPTO_PCBC=m CONFIG_CRYPTO_XTS=m +CONFIG_CRYPTO_KEYWRAP=m CONFIG_CRYPTO_XCBC=m CONFIG_CRYPTO_VMAC=m CONFIG_CRYPTO_MICHAEL_MIC=m diff --git a/arch/m68k/include/asm/mac_psc.h b/arch/m68k/include/asm/mac_psc.h index e5c0d71d1543..923305117a69 100644 --- a/arch/m68k/include/asm/mac_psc.h +++ b/arch/m68k/include/asm/mac_psc.h @@ -209,7 +209,6 @@ #ifndef __ASSEMBLY__ extern volatile __u8 *psc; -extern int psc_present; extern void psc_register_interrupts(void); extern void psc_irq_enable(int); diff --git a/arch/m68k/include/asm/page.h b/arch/m68k/include/asm/page.h index 38b024a0b045..430d4d54c883 100644 --- a/arch/m68k/include/asm/page.h +++ b/arch/m68k/include/asm/page.h @@ -48,6 +48,9 @@ extern unsigned long _ramend; #include <asm/page_no.h> #endif +#define __phys_to_pfn(paddr) ((unsigned long)((paddr) >> PAGE_SHIFT)) +#define __pfn_to_phys(pfn) PFN_PHYS(pfn) + #define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | VM_EXEC | \ VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) diff --git a/arch/m68k/include/asm/uaccess_no.h b/arch/m68k/include/asm/uaccess_no.h index 68bbe9b312f1..1bdf15263754 100644 --- a/arch/m68k/include/asm/uaccess_no.h +++ b/arch/m68k/include/asm/uaccess_no.h @@ -135,10 +135,6 @@ extern int __get_user_bad(void); #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user -#define copy_to_user_ret(to,from,n,retval) ({ if (copy_to_user(to,from,n)) return retval; }) - -#define copy_from_user_ret(to,from,n,retval) ({ if (copy_from_user(to,from,n)) return retval; }) - /* * Copy a null terminated string from userspace. */ diff --git a/arch/m68k/mac/macints.c b/arch/m68k/mac/macints.c index 5c1a6b2ff0af..9f98c0871901 100644 --- a/arch/m68k/mac/macints.c +++ b/arch/m68k/mac/macints.c @@ -174,7 +174,7 @@ void __init mac_init_IRQ(void) oss_register_interrupts(); else via_register_interrupts(); - if (psc_present) + if (psc) psc_register_interrupts(); if (baboon_present) baboon_register_interrupts(); @@ -212,7 +212,7 @@ void mac_irq_enable(struct irq_data *data) case 4: case 5: case 6: - if (psc_present) + if (psc) psc_irq_enable(irq); else if (oss_present) oss_irq_enable(irq); @@ -242,7 +242,7 @@ void mac_irq_disable(struct irq_data *data) case 4: case 5: case 6: - if (psc_present) + if (psc) psc_irq_disable(irq); else if (oss_present) oss_irq_disable(irq); diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c index 2290c0cae48b..cb2b1a3a2b62 100644 --- a/arch/m68k/mac/psc.c +++ b/arch/m68k/mac/psc.c @@ -27,7 +27,6 @@ #define DEBUG_PSC -int psc_present; volatile __u8 *psc; EXPORT_SYMBOL_GPL(psc); @@ -39,7 +38,9 @@ static void psc_debug_dump(void) { int i; - if (!psc_present) return; + if (!psc) + return; + for (i = 0x30 ; i < 0x70 ; i += 0x10) { printk("PSC #%d: IFR = 0x%02X IER = 0x%02X\n", i >> 4, @@ -81,7 +82,6 @@ void __init psc_init(void) && macintosh_config->ident != MAC_MODEL_Q840) { psc = NULL; - psc_present = 0; return; } @@ -91,7 +91,6 @@ void __init psc_init(void) */ psc = (void *) PSC_BASE; - psc_present = 1; printk("PSC detected at %p\n", psc); diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index 2a5f43a68ae3..71884bf01d72 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -171,7 +171,7 @@ static void __init sun3_sched_init(irq_handler_t timer_routine) intersil_clear(); } -#ifdef CONFIG_SUN3_SCSI +#if IS_ENABLED(CONFIG_SUN3_SCSI) static const struct resource sun3_scsi_vme_rsrc[] __initconst = { { diff --git a/arch/metag/kernel/ftrace.c b/arch/metag/kernel/ftrace.c index ed1d685157c2..ac8c039b0318 100644 --- a/arch/metag/kernel/ftrace.c +++ b/arch/metag/kernel/ftrace.c @@ -54,12 +54,11 @@ static int ftrace_modify_code(unsigned long pc, unsigned char *old_code, unsigned char replaced[MCOUNT_INSN_SIZE]; /* - * Note: Due to modules and __init, code can - * disappear and change, we need to protect against faulting - * as well as code changing. - * - * No real locking needed, this code is run through - * kstop_machine. + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index 6d38948f0f1e..c807e32d6d81 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -101,50 +101,13 @@ static void bcm47xx_machine_halt(void) } #ifdef CONFIG_BCM47XX_SSB -static int bcm47xx_get_invariants(struct ssb_bus *bus, - struct ssb_init_invariants *iv) -{ - char buf[20]; - int len, err; - - /* Fill boardinfo structure */ - memset(&iv->boardinfo, 0 , sizeof(struct ssb_boardinfo)); - - len = bcm47xx_nvram_getenv("boardvendor", buf, sizeof(buf)); - if (len > 0) { - err = kstrtou16(strim(buf), 0, &iv->boardinfo.vendor); - if (err) - pr_warn("Couldn't parse nvram board vendor entry with value \"%s\"\n", - buf); - } - if (!iv->boardinfo.vendor) - iv->boardinfo.vendor = SSB_BOARDVENDOR_BCM; - - len = bcm47xx_nvram_getenv("boardtype", buf, sizeof(buf)); - if (len > 0) { - err = kstrtou16(strim(buf), 0, &iv->boardinfo.type); - if (err) - pr_warn("Couldn't parse nvram board type entry with value \"%s\"\n", - buf); - } - - memset(&iv->sprom, 0, sizeof(struct ssb_sprom)); - bcm47xx_fill_sprom(&iv->sprom, NULL, false); - - if (bcm47xx_nvram_getenv("cardbus", buf, sizeof(buf)) >= 0) - iv->has_cardbus_slot = !!simple_strtoul(buf, NULL, 10); - - return 0; -} - static void __init bcm47xx_register_ssb(void) { int err; char buf[100]; struct ssb_mipscore *mcore; - err = ssb_bus_ssbbus_register(&bcm47xx_bus.ssb, SSB_ENUM_BASE, - bcm47xx_get_invariants); + err = ssb_bus_host_soc_register(&bcm47xx_bus.ssb, SSB_ENUM_BASE); if (err) panic("Failed to initialize SSB bus (err %d)", err); diff --git a/arch/mips/boot/dts/brcm/bcm6328.dtsi b/arch/mips/boot/dts/brcm/bcm6328.dtsi index 41891c1e58bd..d52ce3d07f16 100644 --- a/arch/mips/boot/dts/brcm/bcm6328.dtsi +++ b/arch/mips/boot/dts/brcm/bcm6328.dtsi @@ -73,7 +73,6 @@ timer: timer@10000040 { compatible = "syscon"; reg = <0x10000040 0x2c>; - little-endian; }; reboot { diff --git a/arch/mips/boot/dts/brcm/bcm7125.dtsi b/arch/mips/boot/dts/brcm/bcm7125.dtsi index 1a7efa883c5e..4fc7ecee273c 100644 --- a/arch/mips/boot/dts/brcm/bcm7125.dtsi +++ b/arch/mips/boot/dts/brcm/bcm7125.dtsi @@ -98,7 +98,6 @@ sun_top_ctrl: syscon@404000 { compatible = "brcm,bcm7125-sun-top-ctrl", "syscon"; reg = <0x404000 0x60c>; - little-endian; }; reboot { diff --git a/arch/mips/boot/dts/brcm/bcm7346.dtsi b/arch/mips/boot/dts/brcm/bcm7346.dtsi index d4bf52cfcf17..a3039bb53477 100644 --- a/arch/mips/boot/dts/brcm/bcm7346.dtsi +++ b/arch/mips/boot/dts/brcm/bcm7346.dtsi @@ -118,7 +118,6 @@ sun_top_ctrl: syscon@404000 { compatible = "brcm,bcm7346-sun-top-ctrl", "syscon"; reg = <0x404000 0x51c>; - little-endian; }; reboot { diff --git a/arch/mips/boot/dts/brcm/bcm7358.dtsi b/arch/mips/boot/dts/brcm/bcm7358.dtsi index 8e2501694d03..4274ff41ec21 100644 --- a/arch/mips/boot/dts/brcm/bcm7358.dtsi +++ b/arch/mips/boot/dts/brcm/bcm7358.dtsi @@ -112,7 +112,6 @@ sun_top_ctrl: syscon@404000 { compatible = "brcm,bcm7358-sun-top-ctrl", "syscon"; reg = <0x404000 0x51c>; - little-endian; }; reboot { diff --git a/arch/mips/boot/dts/brcm/bcm7360.dtsi b/arch/mips/boot/dts/brcm/bcm7360.dtsi index 7e5f76040fb8..0dcc9163c27b 100644 --- a/arch/mips/boot/dts/brcm/bcm7360.dtsi +++ b/arch/mips/boot/dts/brcm/bcm7360.dtsi @@ -112,7 +112,6 @@ sun_top_ctrl: syscon@404000 { compatible = "brcm,bcm7360-sun-top-ctrl", "syscon"; reg = <0x404000 0x51c>; - little-endian; }; reboot { diff --git a/arch/mips/boot/dts/brcm/bcm7362.dtsi b/arch/mips/boot/dts/brcm/bcm7362.dtsi index c739ea77acb0..2f3f9fc2c478 100644 --- a/arch/mips/boot/dts/brcm/bcm7362.dtsi +++ b/arch/mips/boot/dts/brcm/bcm7362.dtsi @@ -118,7 +118,6 @@ sun_top_ctrl: syscon@404000 { compatible = "brcm,bcm7362-sun-top-ctrl", "syscon"; reg = <0x404000 0x51c>; - little-endian; }; reboot { diff --git a/arch/mips/boot/dts/brcm/bcm7420.dtsi b/arch/mips/boot/dts/brcm/bcm7420.dtsi index 5f55d0a50a28..bee221b3b568 100644 --- a/arch/mips/boot/dts/brcm/bcm7420.dtsi +++ b/arch/mips/boot/dts/brcm/bcm7420.dtsi @@ -99,7 +99,6 @@ sun_top_ctrl: syscon@404000 { compatible = "brcm,bcm7420-sun-top-ctrl", "syscon"; reg = <0x404000 0x60c>; - little-endian; }; reboot { diff --git a/arch/mips/boot/dts/brcm/bcm7425.dtsi b/arch/mips/boot/dts/brcm/bcm7425.dtsi index e24d41ab4e30..571f30f52e3f 100644 --- a/arch/mips/boot/dts/brcm/bcm7425.dtsi +++ b/arch/mips/boot/dts/brcm/bcm7425.dtsi @@ -100,7 +100,6 @@ sun_top_ctrl: syscon@404000 { compatible = "brcm,bcm7425-sun-top-ctrl", "syscon"; reg = <0x404000 0x51c>; - little-endian; }; reboot { diff --git a/arch/mips/boot/dts/brcm/bcm7435.dtsi b/arch/mips/boot/dts/brcm/bcm7435.dtsi index 8b9432cc062b..614ee211f71a 100644 --- a/arch/mips/boot/dts/brcm/bcm7435.dtsi +++ b/arch/mips/boot/dts/brcm/bcm7435.dtsi @@ -114,7 +114,6 @@ sun_top_ctrl: syscon@404000 { compatible = "brcm,bcm7425-sun-top-ctrl", "syscon"; reg = <0x404000 0x51c>; - little-endian; }; reboot { diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index dec3c850f36b..5910fe294e93 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -103,4 +103,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mips/lasat/picvue_proc.c b/arch/mips/lasat/picvue_proc.c index 2bcd8391bc93..b42095880667 100644 --- a/arch/mips/lasat/picvue_proc.c +++ b/arch/mips/lasat/picvue_proc.c @@ -22,7 +22,6 @@ static DEFINE_MUTEX(pvc_mutex); static char pvc_lines[PVC_NLINES][PVC_LINELEN+1]; static int pvc_linedata[PVC_NLINES]; -static struct proc_dir_entry *pvc_display_dir; static char *pvc_linename[PVC_NLINES] = {"line1", "line2"}; #define DISPLAY_DIR_NAME "display" static int scroll_dir, scroll_interval; @@ -169,22 +168,17 @@ void pvc_proc_timerfunc(unsigned long data) static void pvc_proc_cleanup(void) { - int i; - for (i = 0; i < PVC_NLINES; i++) - remove_proc_entry(pvc_linename[i], pvc_display_dir); - remove_proc_entry("scroll", pvc_display_dir); - remove_proc_entry(DISPLAY_DIR_NAME, NULL); - + remove_proc_subtree(DISPLAY_DIR_NAME, NULL); del_timer_sync(&timer); } static int __init pvc_proc_init(void) { - struct proc_dir_entry *proc_entry; + struct proc_dir_entry *dir, *proc_entry; int i; - pvc_display_dir = proc_mkdir(DISPLAY_DIR_NAME, NULL); - if (pvc_display_dir == NULL) + dir = proc_mkdir(DISPLAY_DIR_NAME, NULL); + if (dir == NULL) goto error; for (i = 0; i < PVC_NLINES; i++) { @@ -192,12 +186,12 @@ static int __init pvc_proc_init(void) pvc_linedata[i] = i; } for (i = 0; i < PVC_NLINES; i++) { - proc_entry = proc_create_data(pvc_linename[i], 0644, pvc_display_dir, + proc_entry = proc_create_data(pvc_linename[i], 0644, dir, &pvc_line_proc_fops, &pvc_linedata[i]); if (proc_entry == NULL) goto error; } - proc_entry = proc_create("scroll", 0644, pvc_display_dir, + proc_entry = proc_create("scroll", 0644, dir, &pvc_scroll_proc_fops); if (proc_entry == NULL) goto error; diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index 14568900fc1d..ee3617c0c5e2 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -26,7 +26,7 @@ aflags-vdso := $(ccflags-vdso) \ # the comments on that file. # ifndef CONFIG_CPU_MIPSR6 - ifeq ($(call ld-ifversion, -lt, 22500000, y),y) + ifeq ($(call ld-ifversion, -lt, 225000000, y),y) $(warning MIPS VDSO requires binutils >= 2.25) obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y)) ccflags-vdso += -DDISABLE_MIPS_VDSO diff --git a/arch/mn10300/include/asm/uaccess.h b/arch/mn10300/include/asm/uaccess.h index 537278746a15..20f7bf6de384 100644 --- a/arch/mn10300/include/asm/uaccess.h +++ b/arch/mn10300/include/asm/uaccess.h @@ -110,21 +110,6 @@ extern int fixup_exception(struct pt_regs *regs); #define __put_user(x, ptr) __put_user_nocheck((x), (ptr), sizeof(*(ptr))) #define __get_user(x, ptr) __get_user_nocheck((x), (ptr), sizeof(*(ptr))) -/* - * The "xxx_ret" versions return constant specified in third argument, if - * something bad happens. These macros can be optimized for the - * case of just returning from the function xxx_ret is used. - */ - -#define put_user_ret(x, ptr, ret) \ - ({ if (put_user((x), (ptr))) return (ret); }) -#define get_user_ret(x, ptr, ret) \ - ({ if (get_user((x), (ptr))) return (ret); }) -#define __put_user_ret(x, ptr, ret) \ - ({ if (__put_user((x), (ptr))) return (ret); }) -#define __get_user_ret(x, ptr, ret) \ - ({ if (__get_user((x), (ptr))) return (ret); }) - struct __large_struct { unsigned long buf[100]; }; #define __m(x) (*(struct __large_struct *)(x)) diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h index cab7d6d50051..58b1aa01ab9f 100644 --- a/arch/mn10300/include/uapi/asm/socket.h +++ b/arch/mn10300/include/uapi/asm/socket.h @@ -85,4 +85,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index a5cd40cd8ee1..f9cf1223422c 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -84,4 +84,7 @@ #define SO_ATTACH_BPF 0x402B #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 0x402C +#define SO_ATTACH_REUSEPORT_EBPF 0x402D + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h index 0eca6efc0631..a7af5fb7b914 100644 --- a/arch/powerpc/include/asm/barrier.h +++ b/arch/powerpc/include/asm/barrier.h @@ -34,7 +34,7 @@ #define rmb() __asm__ __volatile__ ("sync" : : : "memory") #define wmb() __asm__ __volatile__ ("sync" : : : "memory") -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) #ifdef __SUBARCH_HAS_LWSYNC # define SMPWMB LWSYNC diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h index 85bc8c0d257b..e3b54dd4f730 100644 --- a/arch/powerpc/include/asm/hvcall.h +++ b/arch/powerpc/include/asm/hvcall.h @@ -258,11 +258,16 @@ #define H_DEL_CONN 0x288 #define H_JOIN 0x298 #define H_VASI_STATE 0x2A4 +#define H_VIOCTL 0x2A8 #define H_ENABLE_CRQ 0x2B0 #define H_GET_EM_PARMS 0x2B8 #define H_SET_MPP 0x2D0 #define H_GET_MPP 0x2D4 +#define H_REG_SUB_CRQ 0x2DC #define H_HOME_NODE_ASSOCIATIVITY 0x2EC +#define H_FREE_SUB_CRQ 0x2E0 +#define H_SEND_SUB_CRQ 0x2E4 +#define H_SEND_SUB_CRQ_INDIRECT 0x2E8 #define H_BEST_ENERGY 0x2F4 #define H_XIRR_X 0x2FC #define H_RANDOM 0x300 @@ -271,6 +276,21 @@ #define H_SET_MODE 0x31C #define MAX_HCALL_OPCODE H_SET_MODE +/* H_VIOCTL functions */ +#define H_GET_VIOA_DUMP_SIZE 0x01 +#define H_GET_VIOA_DUMP 0x02 +#define H_GET_ILLAN_NUM_VLAN_IDS 0x03 +#define H_GET_ILLAN_VLAN_ID_LIST 0x04 +#define H_GET_ILLAN_SWITCH_ID 0x05 +#define H_DISABLE_MIGRATION 0x06 +#define H_ENABLE_MIGRATION 0x07 +#define H_GET_PARTNER_INFO 0x08 +#define H_GET_PARTNER_WWPN_LIST 0x09 +#define H_DISABLE_ALL_VIO_INTS 0x0A +#define H_DISABLE_VIO_INTERRUPT 0x0B +#define H_ENABLE_VIO_INTERRUPT 0x0C + + /* Platform specific hcalls, used by KVM */ #define H_RTAS 0xf000 diff --git a/arch/powerpc/include/asm/icswx.h b/arch/powerpc/include/asm/icswx.h index 9f8402b35115..27e588f6c72e 100644 --- a/arch/powerpc/include/asm/icswx.h +++ b/arch/powerpc/include/asm/icswx.h @@ -164,6 +164,7 @@ struct coprocessor_request_block { #define ICSWX_INITIATED (0x8) #define ICSWX_BUSY (0x4) #define ICSWX_REJECTED (0x2) +#define ICSWX_XERS0 (0x1) /* undefined or set from XERSO. */ static inline int icswx(__be32 ccw, struct coprocessor_request_block *crb) { diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index cfa758c6b4f6..271fefbbe521 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -50,6 +50,10 @@ #define KVM_NR_IRQCHIPS 1 #define KVM_IRQCHIP_NUM_PINS 256 +/* PPC-specific vcpu->requests bit members */ +#define KVM_REQ_WATCHDOG 8 +#define KVM_REQ_EPR_EXIT 9 + #include <linux/mmu_notifier.h> #define KVM_ARCH_WANT_MMU_NOTIFIER diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 2a8ebae0936b..b7c20f0b8fbe 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -274,21 +274,6 @@ do { \ __gu_err; \ }) -#ifndef __powerpc64__ -#define __get_user64_nocheck(x, ptr, size) \ -({ \ - long __gu_err; \ - long long __gu_val; \ - __typeof__(*(ptr)) __user *__gu_addr = (ptr); \ - __chk_user_ptr(ptr); \ - if (!is_kernel_addr((unsigned long)__gu_addr)) \ - might_fault(); \ - __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \ - (x) = (__force __typeof__(*(ptr)))__gu_val; \ - __gu_err; \ -}) -#endif /* __powerpc64__ */ - #define __get_user_check(x, ptr, size) \ ({ \ long __gu_err = -EFAULT; \ diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index c046666038f8..dd54f28ecdec 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -92,4 +92,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_POWERPC_SOCKET_H */ diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c index 32e26526f7e4..0cab9e8c3794 100644 --- a/arch/powerpc/kernel/nvram_64.c +++ b/arch/powerpc/kernel/nvram_64.c @@ -27,6 +27,7 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/kmsg_dump.h> +#include <linux/pagemap.h> #include <linux/pstore.h> #include <linux/zlib.h> #include <asm/uaccess.h> @@ -733,24 +734,10 @@ static void oops_to_nvram(struct kmsg_dumper *dumper, static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin) { - int size; - if (ppc_md.nvram_size == NULL) return -ENODEV; - size = ppc_md.nvram_size(); - - switch (origin) { - case 1: - offset += file->f_pos; - break; - case 2: - offset += size; - break; - } - if (offset < 0) - return -EINVAL; - file->f_pos = offset; - return file->f_pos; + return generic_file_llseek_size(file, offset, origin, MAX_LFS_FILESIZE, + ppc_md.nvram_size()); } diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index a7352b59e6f9..6b352691b8c9 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -314,16 +314,10 @@ static void kvmppc_dump_regs(struct kvm_vcpu *vcpu) static struct kvm_vcpu *kvmppc_find_vcpu(struct kvm *kvm, int id) { - int r; - struct kvm_vcpu *v, *ret = NULL; + struct kvm_vcpu *ret; mutex_lock(&kvm->lock); - kvm_for_each_vcpu(r, v, kvm) { - if (v->vcpu_id == id) { - ret = v; - break; - } - } + ret = kvm_get_vcpu_by_id(kvm, id); mutex_unlock(&kvm->lock); return ret; } diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 64891b081ad5..70fb08da416d 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -512,7 +512,7 @@ static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte) put_page(hpage); } -static int kvmppc_visible_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) +static bool kvmppc_visible_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) { ulong mp_pa = vcpu->arch.magic_page_pa; @@ -521,7 +521,7 @@ static int kvmppc_visible_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) gpa &= ~0xFFFULL; if (unlikely(mp_pa) && unlikely((mp_pa & KVM_PAM) == (gpa & KVM_PAM))) { - return 1; + return true; } return kvm_is_visible_gfn(vcpu->kvm, gpa >> PAGE_SHIFT); diff --git a/arch/powerpc/platforms/82xx/ep8248e.c b/arch/powerpc/platforms/82xx/ep8248e.c index a0cb8bd41958..6781bda117be 100644 --- a/arch/powerpc/platforms/82xx/ep8248e.c +++ b/arch/powerpc/platforms/82xx/ep8248e.c @@ -131,23 +131,15 @@ static int ep8248e_mdio_probe(struct platform_device *ofdev) if (!bus) return -ENOMEM; - bus->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL); - if (bus->irq == NULL) { - ret = -ENOMEM; - goto err_free_bus; - } - bus->name = "ep8248e-mdio-bitbang"; bus->parent = &ofdev->dev; snprintf(bus->id, MII_BUS_ID_SIZE, "%x", res.start); ret = of_mdiobus_register(bus, ofdev->dev.of_node); if (ret) - goto err_free_irq; + goto err_free_bus; return 0; -err_free_irq: - kfree(bus->irq); err_free_bus: free_mdio_bitbang(bus); return ret; diff --git a/arch/powerpc/platforms/pasemi/gpio_mdio.c b/arch/powerpc/platforms/pasemi/gpio_mdio.c index ae3f47b25b18..ddf635000c6b 100644 --- a/arch/powerpc/platforms/pasemi/gpio_mdio.c +++ b/arch/powerpc/platforms/pasemi/gpio_mdio.c @@ -41,7 +41,6 @@ static void __iomem *gpio_regs; struct gpio_priv { int mdc_pin; int mdio_pin; - int mdio_irqs[PHY_MAX_ADDR]; }; #define MDC_PIN(bus) (((struct gpio_priv *)bus->priv)->mdc_pin) @@ -245,8 +244,6 @@ static int gpio_mdio_probe(struct platform_device *ofdev) snprintf(new_bus->id, MII_BUS_ID_SIZE, "%x", *prop); new_bus->priv = priv; - new_bus->irq = priv->mdio_irqs; - prop = of_get_property(np, "mdc-pin", NULL); priv->mdc_pin = *prop; diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c index 610f472f91d1..a1ac80b3041a 100644 --- a/arch/powerpc/sysdev/fsl_pci.c +++ b/arch/powerpc/sysdev/fsl_pci.c @@ -21,10 +21,12 @@ #include <linux/pci.h> #include <linux/delay.h> #include <linux/string.h> +#include <linux/fsl/edac.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/memblock.h> #include <linux/log2.h> +#include <linux/platform_device.h> #include <linux/slab.h> #include <linux/suspend.h> #include <linux/syscore_ops.h> @@ -1255,6 +1257,25 @@ void fsl_pcibios_fixup_phb(struct pci_controller *phb) #endif } +static int add_err_dev(struct platform_device *pdev) +{ + struct platform_device *errdev; + struct mpc85xx_edac_pci_plat_data pd = { + .of_node = pdev->dev.of_node + }; + + errdev = platform_device_register_resndata(&pdev->dev, + "mpc85xx-pci-edac", + PLATFORM_DEVID_AUTO, + pdev->resource, + pdev->num_resources, + &pd, sizeof(pd)); + if (IS_ERR(errdev)) + return PTR_ERR(errdev); + + return 0; +} + static int fsl_pci_probe(struct platform_device *pdev) { struct device_node *node; @@ -1262,8 +1283,13 @@ static int fsl_pci_probe(struct platform_device *pdev) node = pdev->dev.of_node; ret = fsl_add_bridge(pdev, fsl_pci_primary == node); + if (ret) + return ret; - mpc85xx_pci_err_probe(pdev); + ret = add_err_dev(pdev); + if (ret) + dev_err(&pdev->dev, "couldn't register error device: %d\n", + ret); return 0; } diff --git a/arch/powerpc/sysdev/fsl_pci.h b/arch/powerpc/sysdev/fsl_pci.h index c1cec771d5ea..151588530b06 100644 --- a/arch/powerpc/sysdev/fsl_pci.h +++ b/arch/powerpc/sysdev/fsl_pci.h @@ -130,15 +130,6 @@ void fsl_pci_assign_primary(void); static inline void fsl_pci_assign_primary(void) {} #endif -#ifdef CONFIG_EDAC_MPC85XX -int mpc85xx_pci_err_probe(struct platform_device *op); -#else -static inline int mpc85xx_pci_err_probe(struct platform_device *op) -{ - return -ENOTSUPP; -} -#endif - #ifdef CONFIG_FSL_PCI extern int fsl_pci_mcheck_exception(struct pt_regs *); #else diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h index d68e11e0df5e..7ffd0b19135c 100644 --- a/arch/s390/include/asm/barrier.h +++ b/arch/s390/include/asm/barrier.h @@ -36,7 +36,7 @@ #define smp_mb__before_atomic() smp_mb() #define smp_mb__after_atomic() smp_mb() -#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); mb(); } while (0) +#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0) #define smp_store_release(p, v) \ do { \ diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h index bab6739a1154..08e34a5dc909 100644 --- a/arch/s390/include/asm/elf.h +++ b/arch/s390/include/asm/elf.h @@ -104,6 +104,9 @@ #define HWCAP_S390_TE 1024 #define HWCAP_S390_VXRS 2048 +/* Internal bits, not exposed via elf */ +#define HWCAP_INT_SIE 1UL + /* * These are used to set parameters in the core dumps. */ @@ -169,6 +172,10 @@ extern unsigned int vdso_enabled; extern unsigned long elf_hwcap; #define ELF_HWCAP (elf_hwcap) +/* Internal hardware capabilities, not exposed via elf */ + +extern unsigned long int_hwcap; + /* This yields a string that ld.so will use to load implementation specific libraries for optimization. This is more specific in intent than poking at uname or /proc/cpuinfo. diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index efaac2c3bb77..6742414dbd6f 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -25,7 +25,9 @@ #include <asm/fpu/api.h> #include <asm/isc.h> -#define KVM_MAX_VCPUS 64 +#define KVM_S390_BSCA_CPU_SLOTS 64 +#define KVM_S390_ESCA_CPU_SLOTS 248 +#define KVM_MAX_VCPUS KVM_S390_ESCA_CPU_SLOTS #define KVM_USER_MEM_SLOTS 32 /* @@ -37,12 +39,41 @@ #define KVM_IRQCHIP_NUM_PINS 4096 #define KVM_HALT_POLL_NS_DEFAULT 0 +/* s390-specific vcpu->requests bit members */ +#define KVM_REQ_ENABLE_IBS 8 +#define KVM_REQ_DISABLE_IBS 9 + #define SIGP_CTRL_C 0x80 #define SIGP_CTRL_SCN_MASK 0x3f -struct sca_entry { +union bsca_sigp_ctrl { + __u8 value; + struct { + __u8 c : 1; + __u8 r : 1; + __u8 scn : 6; + }; +} __packed; + +union esca_sigp_ctrl { + __u16 value; + struct { + __u8 c : 1; + __u8 reserved: 7; + __u8 scn; + }; +} __packed; + +struct esca_entry { + union esca_sigp_ctrl sigp_ctrl; + __u16 reserved1[3]; + __u64 sda; + __u64 reserved2[6]; +} __packed; + +struct bsca_entry { __u8 reserved0; - __u8 sigp_ctrl; + union bsca_sigp_ctrl sigp_ctrl; __u16 reserved[3]; __u64 sda; __u64 reserved2[2]; @@ -57,14 +88,22 @@ union ipte_control { }; }; -struct sca_block { +struct bsca_block { union ipte_control ipte_control; __u64 reserved[5]; __u64 mcn; __u64 reserved2; - struct sca_entry cpu[64]; + struct bsca_entry cpu[KVM_S390_BSCA_CPU_SLOTS]; } __attribute__((packed)); +struct esca_block { + union ipte_control ipte_control; + __u64 reserved1[7]; + __u64 mcn[4]; + __u64 reserved2[20]; + struct esca_entry cpu[KVM_S390_ESCA_CPU_SLOTS]; +} __packed; + #define CPUSTAT_STOPPED 0x80000000 #define CPUSTAT_WAIT 0x10000000 #define CPUSTAT_ECALL_PEND 0x08000000 @@ -182,7 +221,8 @@ struct kvm_s390_sie_block { __u64 pp; /* 0x01de */ __u8 reserved1e6[2]; /* 0x01e6 */ __u64 itdba; /* 0x01e8 */ - __u8 reserved1f0[16]; /* 0x01f0 */ + __u64 riccbd; /* 0x01f0 */ + __u8 reserved1f8[8]; /* 0x01f8 */ } __attribute__((packed)); struct kvm_s390_itdb { @@ -585,11 +625,14 @@ struct kvm_s390_crypto_cb { }; struct kvm_arch{ - struct sca_block *sca; + void *sca; + int use_esca; + rwlock_t sca_lock; debug_info_t *dbf; struct kvm_s390_float_interrupt float_int; struct kvm_device *flic; struct gmap *gmap; + unsigned long mem_limit; int css_support; int use_irqchip; int use_cmma; diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h index 821dde5f425d..dea883f85d66 100644 --- a/arch/s390/include/asm/sclp.h +++ b/arch/s390/include/asm/sclp.h @@ -29,7 +29,10 @@ struct sclp_ipl_info { struct sclp_core_entry { u8 core_id; - u8 reserved0[2]; + u8 reserved0; + u8 : 4; + u8 sief2 : 1; + u8 : 3; u8 : 3; u8 siif : 1; u8 sigpif : 1; @@ -53,6 +56,9 @@ struct sclp_info { unsigned char has_sigpif : 1; unsigned char has_core_type : 1; unsigned char has_sprp : 1; + unsigned char has_hvs : 1; + unsigned char has_esca : 1; + unsigned char has_sief2 : 1; unsigned int ibc; unsigned int mtid; unsigned int mtid_cp; diff --git a/arch/s390/include/uapi/asm/kvm.h b/arch/s390/include/uapi/asm/kvm.h index ef1a5fcc6c66..fe84bd5fe7ce 100644 --- a/arch/s390/include/uapi/asm/kvm.h +++ b/arch/s390/include/uapi/asm/kvm.h @@ -66,6 +66,8 @@ struct kvm_s390_io_adapter_req { #define KVM_S390_VM_MEM_CLR_CMMA 1 #define KVM_S390_VM_MEM_LIMIT_SIZE 2 +#define KVM_S390_NO_MEM_LIMIT U64_MAX + /* kvm attributes for KVM_S390_VM_TOD */ #define KVM_S390_VM_TOD_LOW 0 #define KVM_S390_VM_TOD_HIGH 1 @@ -151,6 +153,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_ARCH0 (1UL << 4) #define KVM_SYNC_PFAULT (1UL << 5) #define KVM_SYNC_VRS (1UL << 6) +#define KVM_SYNC_RICCB (1UL << 7) /* definition of registers in kvm_run */ struct kvm_sync_regs { __u64 prefix; /* prefix register */ @@ -168,6 +171,8 @@ struct kvm_sync_regs { __u64 vrs[32][2]; /* vector registers */ __u8 reserved[512]; /* for future vector expansion */ __u32 fpc; /* only valid with vector registers */ + __u8 padding[52]; /* riccb needs to be 64byte aligned */ + __u8 riccb[64]; /* runtime instrumentation controls block */ }; #define KVM_REG_S390_TODPR (KVM_REG_S390 | KVM_REG_SIZE_U32 | 0x1) diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h index 296942d56e6a..d02e89d14fef 100644 --- a/arch/s390/include/uapi/asm/socket.h +++ b/arch/s390/include/uapi/asm/socket.h @@ -91,4 +91,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 7ce00e7a709a..647128d5b983 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -61,6 +61,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) "esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp", "edat", "etf3eh", "highgprs", "te", "vx" }; + static const char * const int_hwcap_str[] = { + "sie" + }; unsigned long n = (unsigned long) v - 1; int i; @@ -75,6 +78,9 @@ static int show_cpuinfo(struct seq_file *m, void *v) for (i = 0; i < ARRAY_SIZE(hwcap_str); i++) if (hwcap_str[i] && (elf_hwcap & (1UL << i))) seq_printf(m, "%s ", hwcap_str[i]); + for (i = 0; i < ARRAY_SIZE(int_hwcap_str); i++) + if (int_hwcap_str[i] && (int_hwcap & (1UL << i))) + seq_printf(m, "%s ", int_hwcap_str[i]); seq_puts(m, "\n"); show_cacheinfo(m); } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index c837bcacf218..dc83ae66a730 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -80,6 +80,8 @@ EXPORT_SYMBOL(console_irq); unsigned long elf_hwcap __read_mostly = 0; char elf_platform[ELF_PLATFORM_SIZE]; +unsigned long int_hwcap = 0; + int __initdata memory_end_set; unsigned long __initdata memory_end; unsigned long __initdata max_physmem_end; @@ -793,6 +795,13 @@ static int __init setup_hwcaps(void) strcpy(elf_platform, "z13"); break; } + + /* + * Virtualization support HWCAP_INT_SIE is bit 0. + */ + if (sclp.has_sief2) + int_hwcap |= HWCAP_INT_SIE; + return 0; } arch_initcall(setup_hwcaps); diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 5fbfb88f8477..05f7de9869a9 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -155,10 +155,8 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu) static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) { - struct kvm *kvm = vcpu->kvm; struct kvm_vcpu *tcpu; int tid; - int i; tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4]; vcpu->stat.diagnose_9c++; @@ -167,12 +165,9 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu) if (tid == vcpu->vcpu_id) return 0; - kvm_for_each_vcpu(i, tcpu, kvm) - if (tcpu->vcpu_id == tid) { - kvm_vcpu_yield_to(tcpu); - break; - } - + tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid); + if (tcpu) + kvm_vcpu_yield_to(tcpu); return 0; } diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index a7559f7207df..d30db40437dc 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -259,10 +259,14 @@ struct aste { int ipte_lock_held(struct kvm_vcpu *vcpu) { - union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control; + if (vcpu->arch.sie_block->eca & 1) { + int rc; - if (vcpu->arch.sie_block->eca & 1) - return ic->kh != 0; + read_lock(&vcpu->kvm->arch.sca_lock); + rc = kvm_s390_get_ipte_control(vcpu->kvm)->kh != 0; + read_unlock(&vcpu->kvm->arch.sca_lock); + return rc; + } return vcpu->kvm->arch.ipte_lock_count != 0; } @@ -274,16 +278,20 @@ static void ipte_lock_simple(struct kvm_vcpu *vcpu) vcpu->kvm->arch.ipte_lock_count++; if (vcpu->kvm->arch.ipte_lock_count > 1) goto out; - ic = &vcpu->kvm->arch.sca->ipte_control; +retry: + read_lock(&vcpu->kvm->arch.sca_lock); + ic = kvm_s390_get_ipte_control(vcpu->kvm); do { old = READ_ONCE(*ic); - while (old.k) { + if (old.k) { + read_unlock(&vcpu->kvm->arch.sca_lock); cond_resched(); - old = READ_ONCE(*ic); + goto retry; } new = old; new.k = 1; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + read_unlock(&vcpu->kvm->arch.sca_lock); out: mutex_unlock(&vcpu->kvm->arch.ipte_mutex); } @@ -296,12 +304,14 @@ static void ipte_unlock_simple(struct kvm_vcpu *vcpu) vcpu->kvm->arch.ipte_lock_count--; if (vcpu->kvm->arch.ipte_lock_count) goto out; - ic = &vcpu->kvm->arch.sca->ipte_control; + read_lock(&vcpu->kvm->arch.sca_lock); + ic = kvm_s390_get_ipte_control(vcpu->kvm); do { old = READ_ONCE(*ic); new = old; new.k = 0; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + read_unlock(&vcpu->kvm->arch.sca_lock); wake_up(&vcpu->kvm->arch.ipte_wq); out: mutex_unlock(&vcpu->kvm->arch.ipte_mutex); @@ -311,24 +321,29 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu) { union ipte_control old, new, *ic; - ic = &vcpu->kvm->arch.sca->ipte_control; +retry: + read_lock(&vcpu->kvm->arch.sca_lock); + ic = kvm_s390_get_ipte_control(vcpu->kvm); do { old = READ_ONCE(*ic); - while (old.kg) { + if (old.kg) { + read_unlock(&vcpu->kvm->arch.sca_lock); cond_resched(); - old = READ_ONCE(*ic); + goto retry; } new = old; new.k = 1; new.kh++; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + read_unlock(&vcpu->kvm->arch.sca_lock); } static void ipte_unlock_siif(struct kvm_vcpu *vcpu) { union ipte_control old, new, *ic; - ic = &vcpu->kvm->arch.sca->ipte_control; + read_lock(&vcpu->kvm->arch.sca_lock); + ic = kvm_s390_get_ipte_control(vcpu->kvm); do { old = READ_ONCE(*ic); new = old; @@ -336,6 +351,7 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu) if (!new.kh) new.k = 0; } while (cmpxchg(&ic->val, old.val, new.val) != old.val); + read_unlock(&vcpu->kvm->arch.sca_lock); if (!new.kh) wake_up(&vcpu->kvm->arch.ipte_wq); } diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c index b4a5aa110cec..d53c10753c46 100644 --- a/arch/s390/kvm/intercept.c +++ b/arch/s390/kvm/intercept.c @@ -54,9 +54,6 @@ void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc) static int handle_noop(struct kvm_vcpu *vcpu) { switch (vcpu->arch.sie_block->icptcode) { - case 0x0: - vcpu->stat.exit_null++; - break; case 0x10: vcpu->stat.exit_external_request++; break; @@ -338,8 +335,10 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu) int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu) { + if (kvm_is_ucontrol(vcpu->kvm)) + return -EOPNOTSUPP; + switch (vcpu->arch.sie_block->icptcode) { - case 0x00: case 0x10: case 0x18: return handle_noop(vcpu); diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index 6a75352f453c..62ec925aa196 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -34,6 +34,106 @@ #define PFAULT_DONE 0x0680 #define VIRTIO_PARAM 0x0d00 +/* handle external calls via sigp interpretation facility */ +static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id) +{ + int c, scn; + + if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND)) + return 0; + + read_lock(&vcpu->kvm->arch.sca_lock); + if (vcpu->kvm->arch.use_esca) { + struct esca_block *sca = vcpu->kvm->arch.sca; + union esca_sigp_ctrl sigp_ctrl = + sca->cpu[vcpu->vcpu_id].sigp_ctrl; + + c = sigp_ctrl.c; + scn = sigp_ctrl.scn; + } else { + struct bsca_block *sca = vcpu->kvm->arch.sca; + union bsca_sigp_ctrl sigp_ctrl = + sca->cpu[vcpu->vcpu_id].sigp_ctrl; + + c = sigp_ctrl.c; + scn = sigp_ctrl.scn; + } + read_unlock(&vcpu->kvm->arch.sca_lock); + + if (src_id) + *src_id = scn; + + return c; +} + +static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id) +{ + int expect, rc; + + read_lock(&vcpu->kvm->arch.sca_lock); + if (vcpu->kvm->arch.use_esca) { + struct esca_block *sca = vcpu->kvm->arch.sca; + union esca_sigp_ctrl *sigp_ctrl = + &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); + union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + + new_val.scn = src_id; + new_val.c = 1; + old_val.c = 0; + + expect = old_val.value; + rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value); + } else { + struct bsca_block *sca = vcpu->kvm->arch.sca; + union bsca_sigp_ctrl *sigp_ctrl = + &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); + union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl; + + new_val.scn = src_id; + new_val.c = 1; + old_val.c = 0; + + expect = old_val.value; + rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value); + } + read_unlock(&vcpu->kvm->arch.sca_lock); + + if (rc != expect) { + /* another external call is pending */ + return -EBUSY; + } + atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags); + return 0; +} + +static void sca_clear_ext_call(struct kvm_vcpu *vcpu) +{ + struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; + int rc, expect; + + atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags); + read_lock(&vcpu->kvm->arch.sca_lock); + if (vcpu->kvm->arch.use_esca) { + struct esca_block *sca = vcpu->kvm->arch.sca; + union esca_sigp_ctrl *sigp_ctrl = + &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); + union esca_sigp_ctrl old = *sigp_ctrl; + + expect = old.value; + rc = cmpxchg(&sigp_ctrl->value, old.value, 0); + } else { + struct bsca_block *sca = vcpu->kvm->arch.sca; + union bsca_sigp_ctrl *sigp_ctrl = + &(sca->cpu[vcpu->vcpu_id].sigp_ctrl); + union bsca_sigp_ctrl old = *sigp_ctrl; + + expect = old.value; + rc = cmpxchg(&sigp_ctrl->value, old.value, 0); + } + read_unlock(&vcpu->kvm->arch.sca_lock); + WARN_ON(rc != expect); /* cannot clear? */ +} + int psw_extint_disabled(struct kvm_vcpu *vcpu) { return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT); @@ -792,13 +892,11 @@ static const deliver_irq_t deliver_irq_funcs[] = { int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; - uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; if (!sclp.has_sigpif) return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs); - return (sigp_ctrl & SIGP_CTRL_C) && - (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND); + return sca_ext_call_pending(vcpu, NULL); } int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop) @@ -909,9 +1007,7 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu) memset(&li->irq, 0, sizeof(li->irq)); spin_unlock(&li->lock); - /* clear pending external calls set by sigp interpretation facility */ - atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags); - vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0; + sca_clear_ext_call(vcpu); } int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu) @@ -1003,21 +1099,6 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) return 0; } -static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id) -{ - unsigned char new_val, old_val; - uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; - - new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK); - old_val = *sigp_ctrl & ~SIGP_CTRL_C; - if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) { - /* another external call is pending */ - return -EBUSY; - } - atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags); - return 0; -} - static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) { struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; @@ -1034,7 +1115,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq) return -EINVAL; if (sclp.has_sigpif) - return __inject_extcall_sigpif(vcpu, src_id); + return sca_inject_ext_call(vcpu, src_id); if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs)) return -EBUSY; @@ -2203,7 +2284,7 @@ static void store_local_irq(struct kvm_s390_local_interrupt *li, int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len) { - uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl; + int scn; unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)]; struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int; unsigned long pending_irqs; @@ -2243,14 +2324,12 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len) } } - if ((sigp_ctrl & SIGP_CTRL_C) && - (atomic_read(&vcpu->arch.sie_block->cpuflags) & - CPUSTAT_ECALL_PEND)) { + if (sca_ext_call_pending(vcpu, &scn)) { if (n + sizeof(irq) > len) return -ENOBUFS; memset(&irq, 0, sizeof(irq)); irq.type = KVM_S390_INT_EXTERNAL_CALL; - irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK; + irq.u.extcall.code = scn; if (copy_to_user(&buf[n], &irq, sizeof(irq))) return -EFAULT; n += sizeof(irq); diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 846589281b04..5927c61d322a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -246,7 +246,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_NR_VCPUS: case KVM_CAP_MAX_VCPUS: - r = KVM_MAX_VCPUS; + r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS + : KVM_S390_BSCA_CPU_SLOTS; break; case KVM_CAP_NR_MEMSLOTS: r = KVM_USER_MEM_SLOTS; @@ -257,6 +258,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_VECTOR_REGISTERS: r = MACHINE_HAS_VX; break; + case KVM_CAP_S390_RI: + r = test_facility(64); + break; default: r = 0; } @@ -283,6 +287,8 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm, } /* Section: vm related */ +static void sca_del_vcpu(struct kvm_vcpu *vcpu); + /* * Get (and clear) the dirty memory log for a memory slot. */ @@ -355,6 +361,20 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s", r ? "(not available)" : "(success)"); break; + case KVM_CAP_S390_RI: + r = -EINVAL; + mutex_lock(&kvm->lock); + if (atomic_read(&kvm->online_vcpus)) { + r = -EBUSY; + } else if (test_facility(64)) { + set_kvm_facility(kvm->arch.model.fac->mask, 64); + set_kvm_facility(kvm->arch.model.fac->list, 64); + r = 0; + } + mutex_unlock(&kvm->lock); + VM_EVENT(kvm, 3, "ENABLE: CAP_S390_RI %s", + r ? "(not available)" : "(success)"); + break; case KVM_CAP_S390_USER_STSI: VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI"); kvm->arch.user_stsi = 1; @@ -375,8 +395,8 @@ static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *att case KVM_S390_VM_MEM_LIMIT_SIZE: ret = 0; VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes", - kvm->arch.gmap->asce_end); - if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr)) + kvm->arch.mem_limit); + if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr)) ret = -EFAULT; break; default: @@ -428,9 +448,17 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att if (get_user(new_limit, (u64 __user *)attr->addr)) return -EFAULT; - if (new_limit > kvm->arch.gmap->asce_end) + if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT && + new_limit > kvm->arch.mem_limit) return -E2BIG; + if (!new_limit) + return -EINVAL; + + /* gmap_alloc takes last usable address */ + if (new_limit != KVM_S390_NO_MEM_LIMIT) + new_limit -= 1; + ret = -EBUSY; mutex_lock(&kvm->lock); if (atomic_read(&kvm->online_vcpus) == 0) { @@ -447,7 +475,9 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att } } mutex_unlock(&kvm->lock); - VM_EVENT(kvm, 3, "SET: max guest memory: %lu bytes", new_limit); + VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit); + VM_EVENT(kvm, 3, "New guest asce: 0x%pK", + (void *) kvm->arch.gmap->asce); break; } default: @@ -1024,7 +1054,7 @@ static int kvm_s390_apxa_installed(void) u8 config[128]; int cc; - if (test_facility(2) && test_facility(12)) { + if (test_facility(12)) { cc = kvm_s390_query_ap_config(config); if (cc) @@ -1075,6 +1105,15 @@ static int kvm_s390_crypto_init(struct kvm *kvm) return 0; } +static void sca_dispose(struct kvm *kvm) +{ + if (kvm->arch.use_esca) + free_pages_exact(kvm->arch.sca, sizeof(struct esca_block)); + else + free_page((unsigned long)(kvm->arch.sca)); + kvm->arch.sca = NULL; +} + int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int i, rc; @@ -1098,14 +1137,17 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) rc = -ENOMEM; - kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL); + kvm->arch.use_esca = 0; /* start with basic SCA */ + rwlock_init(&kvm->arch.sca_lock); + kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL); if (!kvm->arch.sca) goto out_err; spin_lock(&kvm_lock); sca_offset += 16; - if (sca_offset + sizeof(struct sca_block) > PAGE_SIZE) + if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE) sca_offset = 0; - kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset); + kvm->arch.sca = (struct bsca_block *) + ((char *) kvm->arch.sca + sca_offset); spin_unlock(&kvm_lock); sprintf(debug_name, "kvm-%u", current->pid); @@ -1157,8 +1199,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) if (type & KVM_VM_S390_UCONTROL) { kvm->arch.gmap = NULL; + kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT; } else { - kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1); + if (sclp.hamax == U64_MAX) + kvm->arch.mem_limit = TASK_MAX_SIZE; + else + kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE, + sclp.hamax + 1); + kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1); if (!kvm->arch.gmap) goto out_err; kvm->arch.gmap->private = kvm; @@ -1170,14 +1218,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm->arch.epoch = 0; spin_lock_init(&kvm->arch.start_stop_lock); - KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid); + KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid); return 0; out_err: kfree(kvm->arch.crypto.crycb); free_page((unsigned long)kvm->arch.model.fac); debug_unregister(kvm->arch.dbf); - free_page((unsigned long)(kvm->arch.sca)); + sca_dispose(kvm); KVM_EVENT(3, "creation of vm failed: %d", rc); return rc; } @@ -1188,14 +1236,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id); kvm_s390_clear_local_irqs(vcpu); kvm_clear_async_pf_completion_queue(vcpu); - if (!kvm_is_ucontrol(vcpu->kvm)) { - clear_bit(63 - vcpu->vcpu_id, - (unsigned long *) &vcpu->kvm->arch.sca->mcn); - if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda == - (__u64) vcpu->arch.sie_block) - vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0; - } - smp_mb(); + if (!kvm_is_ucontrol(vcpu->kvm)) + sca_del_vcpu(vcpu); if (kvm_is_ucontrol(vcpu->kvm)) gmap_free(vcpu->arch.gmap); @@ -1228,14 +1270,14 @@ void kvm_arch_destroy_vm(struct kvm *kvm) { kvm_free_vcpus(kvm); free_page((unsigned long)kvm->arch.model.fac); - free_page((unsigned long)(kvm->arch.sca)); + sca_dispose(kvm); debug_unregister(kvm->arch.dbf); kfree(kvm->arch.crypto.crycb); if (!kvm_is_ucontrol(kvm)) gmap_free(kvm->arch.gmap); kvm_s390_destroy_adapters(kvm); kvm_s390_clear_float_irqs(kvm); - KVM_EVENT(3, "vm 0x%p destroyed", kvm); + KVM_EVENT(3, "vm 0x%pK destroyed", kvm); } /* Section: vcpu related */ @@ -1249,6 +1291,117 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu) return 0; } +static void sca_del_vcpu(struct kvm_vcpu *vcpu) +{ + read_lock(&vcpu->kvm->arch.sca_lock); + if (vcpu->kvm->arch.use_esca) { + struct esca_block *sca = vcpu->kvm->arch.sca; + + clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn); + sca->cpu[vcpu->vcpu_id].sda = 0; + } else { + struct bsca_block *sca = vcpu->kvm->arch.sca; + + clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn); + sca->cpu[vcpu->vcpu_id].sda = 0; + } + read_unlock(&vcpu->kvm->arch.sca_lock); +} + +static void sca_add_vcpu(struct kvm_vcpu *vcpu) +{ + read_lock(&vcpu->kvm->arch.sca_lock); + if (vcpu->kvm->arch.use_esca) { + struct esca_block *sca = vcpu->kvm->arch.sca; + + sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block; + vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32); + vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU; + vcpu->arch.sie_block->ecb2 |= 0x04U; + set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn); + } else { + struct bsca_block *sca = vcpu->kvm->arch.sca; + + sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block; + vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32); + vcpu->arch.sie_block->scaol = (__u32)(__u64)sca; + set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn); + } + read_unlock(&vcpu->kvm->arch.sca_lock); +} + +/* Basic SCA to Extended SCA data copy routines */ +static inline void sca_copy_entry(struct esca_entry *d, struct bsca_entry *s) +{ + d->sda = s->sda; + d->sigp_ctrl.c = s->sigp_ctrl.c; + d->sigp_ctrl.scn = s->sigp_ctrl.scn; +} + +static void sca_copy_b_to_e(struct esca_block *d, struct bsca_block *s) +{ + int i; + + d->ipte_control = s->ipte_control; + d->mcn[0] = s->mcn; + for (i = 0; i < KVM_S390_BSCA_CPU_SLOTS; i++) + sca_copy_entry(&d->cpu[i], &s->cpu[i]); +} + +static int sca_switch_to_extended(struct kvm *kvm) +{ + struct bsca_block *old_sca = kvm->arch.sca; + struct esca_block *new_sca; + struct kvm_vcpu *vcpu; + unsigned int vcpu_idx; + u32 scaol, scaoh; + + new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO); + if (!new_sca) + return -ENOMEM; + + scaoh = (u32)((u64)(new_sca) >> 32); + scaol = (u32)(u64)(new_sca) & ~0x3fU; + + kvm_s390_vcpu_block_all(kvm); + write_lock(&kvm->arch.sca_lock); + + sca_copy_b_to_e(new_sca, old_sca); + + kvm_for_each_vcpu(vcpu_idx, vcpu, kvm) { + vcpu->arch.sie_block->scaoh = scaoh; + vcpu->arch.sie_block->scaol = scaol; + vcpu->arch.sie_block->ecb2 |= 0x04U; + } + kvm->arch.sca = new_sca; + kvm->arch.use_esca = 1; + + write_unlock(&kvm->arch.sca_lock); + kvm_s390_vcpu_unblock_all(kvm); + + free_page((unsigned long)old_sca); + + VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)", + old_sca, kvm->arch.sca); + return 0; +} + +static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id) +{ + int rc; + + if (id < KVM_S390_BSCA_CPU_SLOTS) + return true; + if (!sclp.has_esca) + return false; + + mutex_lock(&kvm->lock); + rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm); + mutex_unlock(&kvm->lock); + + return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS; +} + int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) { vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID; @@ -1259,6 +1412,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) KVM_SYNC_CRS | KVM_SYNC_ARCH0 | KVM_SYNC_PFAULT; + if (test_kvm_facility(vcpu->kvm, 64)) + vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB; if (test_kvm_facility(vcpu->kvm, 129)) vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS; @@ -1369,8 +1524,11 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch; preempt_enable(); mutex_unlock(&vcpu->kvm->lock); - if (!kvm_is_ucontrol(vcpu->kvm)) + if (!kvm_is_ucontrol(vcpu->kvm)) { vcpu->arch.gmap = vcpu->kvm->arch.gmap; + sca_add_vcpu(vcpu); + } + } static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu) @@ -1439,10 +1597,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu) vcpu->arch.sie_block->eca |= 1; if (sclp.has_sigpif) vcpu->arch.sie_block->eca |= 0x10000000U; + if (test_kvm_facility(vcpu->kvm, 64)) + vcpu->arch.sie_block->ecb3 |= 0x01; if (test_kvm_facility(vcpu->kvm, 129)) { vcpu->arch.sie_block->eca |= 0x00020000; vcpu->arch.sie_block->ecd |= 0x20000000; } + vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb; vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE; if (vcpu->kvm->arch.use_cmma) { @@ -1465,7 +1626,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, struct sie_page *sie_page; int rc = -EINVAL; - if (id >= KVM_MAX_VCPUS) + if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id)) goto out; rc = -ENOMEM; @@ -1482,20 +1643,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb; vcpu->arch.sie_block->icpua = id; - if (!kvm_is_ucontrol(kvm)) { - if (!kvm->arch.sca) { - WARN_ON_ONCE(1); - goto out_free_cpu; - } - if (!kvm->arch.sca->cpu[id].sda) - kvm->arch.sca->cpu[id].sda = - (__u64) vcpu->arch.sie_block; - vcpu->arch.sie_block->scaoh = - (__u32)(((__u64)kvm->arch.sca) >> 32); - vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca; - set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn); - } - spin_lock_init(&vcpu->arch.local_int.lock); vcpu->arch.local_int.float_int = &kvm->arch.float_int; vcpu->arch.local_int.wq = &vcpu->wq; @@ -1509,15 +1656,13 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, */ vcpu->arch.guest_fpregs.fprs = kzalloc(sizeof(freg_t) * __NUM_FPRS, GFP_KERNEL); - if (!vcpu->arch.guest_fpregs.fprs) { - rc = -ENOMEM; + if (!vcpu->arch.guest_fpregs.fprs) goto out_free_sie_block; - } rc = kvm_vcpu_init(vcpu, kvm, id); if (rc) goto out_free_sie_block; - VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu, + VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu, vcpu->arch.sie_block); trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block); @@ -2013,7 +2158,8 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu) */ kvm_check_async_pf_completion(vcpu); - memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16); + vcpu->arch.sie_block->gg14 = vcpu->run->s.regs.gprs[14]; + vcpu->arch.sie_block->gg15 = vcpu->run->s.regs.gprs[15]; if (need_resched()) schedule(); @@ -2071,8 +2217,6 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu) static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) { - int rc = -1; - VCPU_EVENT(vcpu, 6, "exit sie icptcode %d", vcpu->arch.sie_block->icptcode); trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode); @@ -2080,40 +2224,36 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason) if (guestdbg_enabled(vcpu)) kvm_s390_restore_guest_per_regs(vcpu); - if (exit_reason >= 0) { - rc = 0; + vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14; + vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15; + + if (vcpu->arch.sie_block->icptcode > 0) { + int rc = kvm_handle_sie_intercept(vcpu); + + if (rc != -EOPNOTSUPP) + return rc; + vcpu->run->exit_reason = KVM_EXIT_S390_SIEIC; + vcpu->run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode; + vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa; + vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb; + return -EREMOTE; + } else if (exit_reason != -EFAULT) { + vcpu->stat.exit_null++; + return 0; } else if (kvm_is_ucontrol(vcpu->kvm)) { vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL; vcpu->run->s390_ucontrol.trans_exc_code = current->thread.gmap_addr; vcpu->run->s390_ucontrol.pgm_code = 0x10; - rc = -EREMOTE; - + return -EREMOTE; } else if (current->thread.gmap_pfault) { trace_kvm_s390_major_guest_pfault(vcpu); current->thread.gmap_pfault = 0; - if (kvm_arch_setup_async_pf(vcpu)) { - rc = 0; - } else { - gpa_t gpa = current->thread.gmap_addr; - rc = kvm_arch_fault_in_page(vcpu, gpa, 1); - } + if (kvm_arch_setup_async_pf(vcpu)) + return 0; + return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1); } - - if (rc == -1) - rc = vcpu_post_run_fault_in_sie(vcpu); - - memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16); - - if (rc == 0) { - if (kvm_is_ucontrol(vcpu->kvm)) - /* Don't exit for host interrupts. */ - rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0; - else - rc = kvm_handle_sie_intercept(vcpu); - } - - return rc; + return vcpu_post_run_fault_in_sie(vcpu); } static int __vcpu_run(struct kvm_vcpu *vcpu) @@ -2233,18 +2373,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) rc = 0; } - if (rc == -EOPNOTSUPP) { - /* intercept cannot be handled in-kernel, prepare kvm-run */ - kvm_run->exit_reason = KVM_EXIT_S390_SIEIC; - kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode; - kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa; - kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb; - rc = 0; - } - if (rc == -EREMOTE) { - /* intercept was handled, but userspace support is needed - * kvm_run has been prepared by the handler */ + /* userspace support is needed, kvm_run has been prepared */ rc = 0; } @@ -2736,6 +2866,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if (mem->memory_size & 0xffffful) return -EINVAL; + if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit) + return -EINVAL; + return 0; } @@ -2767,6 +2900,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, static int __init kvm_s390_init(void) { + if (!sclp.has_sief2) { + pr_info("SIE not available\n"); + return -ENODEV; + } + return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE); } diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index 1e70e00d3c5e..df1abada1f36 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -340,4 +340,11 @@ void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu); void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu); void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu); +/* support for Basic/Extended SCA handling */ +static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm) +{ + struct bsca_block *sca = kvm->arch.sca; /* SCA version doesn't matter */ + + return &sca->ipte_control; +} #endif diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h index cc1d6c68356f..396485bca191 100644 --- a/arch/s390/kvm/trace-s390.h +++ b/arch/s390/kvm/trace-s390.h @@ -55,8 +55,8 @@ TRACE_EVENT(kvm_s390_create_vcpu, __entry->sie_block = sie_block; ), - TP_printk("create cpu %d at %p, sie block at %p", __entry->id, - __entry->vcpu, __entry->sie_block) + TP_printk("create cpu %d at 0x%pK, sie block at 0x%pK", + __entry->id, __entry->vcpu, __entry->sie_block) ); TRACE_EVENT(kvm_s390_destroy_vcpu, @@ -254,7 +254,7 @@ TRACE_EVENT(kvm_s390_enable_css, __entry->kvm = kvm; ), - TP_printk("enabling channel I/O support (kvm @ %p)\n", + TP_printk("enabling channel I/O support (kvm @ %pK)\n", __entry->kvm) ); diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c index 54ef3bc01b43..63b039899a5e 100644 --- a/arch/s390/mm/pgtable.c +++ b/arch/s390/mm/pgtable.c @@ -133,7 +133,7 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit) /** * gmap_alloc - allocate a guest address space * @mm: pointer to the parent mm_struct - * @limit: maximum size of the gmap address space + * @limit: maximum address of the gmap address space * * Returns a guest address space structure. */ @@ -402,7 +402,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from, if ((from | to | len) & (PMD_SIZE - 1)) return -EINVAL; if (len == 0 || from + len < from || to + len < to || - from + len > TASK_MAX_SIZE || to + len > gmap->asce_end) + from + len - 1 > TASK_MAX_SIZE || to + len - 1 > gmap->asce_end) return -EINVAL; flush = 0; diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 9a0c4c22e536..3c0bfc1f2694 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -408,7 +408,7 @@ static void emit_load_skb_data_hlen(struct bpf_jit *jit) * Save registers and create stack frame if necessary. * See stack frame layout desription in "bpf_jit.h"! */ -static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic) +static void bpf_jit_prologue(struct bpf_jit *jit) { if (jit->seen & SEEN_TAIL_CALL) { /* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */ @@ -448,15 +448,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, bool is_classic) /* stg %b1,ST_OFF_SKBP(%r0,%r15) */ EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_SKBP); - /* Clear A (%b0) and X (%b7) registers for converted BPF programs */ - if (is_classic) { - if (REG_SEEN(BPF_REG_A)) - /* lghi %ba,0 */ - EMIT4_IMM(0xa7090000, BPF_REG_A, 0); - if (REG_SEEN(BPF_REG_X)) - /* lghi %bx,0 */ - EMIT4_IMM(0xa7090000, BPF_REG_X, 0); - } } /* @@ -1245,7 +1236,7 @@ static int bpf_jit_prog(struct bpf_jit *jit, struct bpf_prog *fp) jit->lit = jit->lit_start; jit->prg = 0; - bpf_jit_prologue(jit, bpf_prog_was_classic(fp)); + bpf_jit_prologue(jit); for (i = 0; i < fp->len; i += insn_count) { insn_count = bpf_jit_insn(jit, fp, i); if (insn_count < 0) diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index d348f2c09a1e..32da0a6ecec2 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -366,8 +366,7 @@ static void *s390_dma_alloc(struct device *dev, size_t size, pa = page_to_phys(page); memset((void *) pa, 0, size); - map = s390_dma_map_pages(dev, page, pa % PAGE_SIZE, - size, DMA_BIDIRECTIONAL, NULL); + map = s390_dma_map_pages(dev, page, 0, size, DMA_BIDIRECTIONAL, NULL); if (dma_mapping_error(dev, map)) { free_pages(pa, get_order(size)); return NULL; diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c index cbd2a9f02a91..62c3b81300ed 100644 --- a/arch/sh/boards/mach-ap325rxa/setup.c +++ b/arch/sh/boards/mach-ap325rxa/setup.c @@ -27,10 +27,10 @@ #include <linux/gpio.h> #include <linux/videodev2.h> #include <linux/sh_intc.h> -#include <media/ov772x.h> +#include <media/i2c/ov772x.h> #include <media/soc_camera.h> -#include <media/soc_camera_platform.h> -#include <media/sh_mobile_ceu.h> +#include <linux/platform_data/media/soc_camera_platform.h> +#include <media/drv-intf/sh_mobile_ceu.h> #include <video/sh_mobile_lcdc.h> #include <asm/io.h> #include <asm/clock.h> diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c index d531791f06ff..a9c0c07386fd 100644 --- a/arch/sh/boards/mach-ecovec24/setup.c +++ b/arch/sh/boards/mach-ecovec24/setup.c @@ -38,10 +38,10 @@ #include <video/sh_mobile_lcdc.h> #include <sound/sh_fsi.h> #include <sound/simple_card.h> -#include <media/sh_mobile_ceu.h> +#include <media/drv-intf/sh_mobile_ceu.h> #include <media/soc_camera.h> -#include <media/tw9910.h> -#include <media/mt9t112.h> +#include <media/i2c/tw9910.h> +#include <media/i2c/mt9t112.h> #include <asm/heartbeat.h> #include <asm/clock.h> #include <asm/suspend.h> @@ -900,8 +900,8 @@ static struct platform_device irda_device = { .resource = irda_resources, }; -#include <media/ak881x.h> -#include <media/sh_vou.h> +#include <media/i2c/ak881x.h> +#include <media/drv-intf/sh_vou.h> static struct ak881x_pdata ak881x_pdata = { .flags = AK881X_IF_MODE_SLAVE, diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c index 7d997cec09c5..6bd9230e64e3 100644 --- a/arch/sh/boards/mach-kfr2r09/setup.c +++ b/arch/sh/boards/mach-kfr2r09/setup.c @@ -27,9 +27,9 @@ #include <linux/usb/r8a66597.h> #include <linux/videodev2.h> #include <linux/sh_intc.h> -#include <media/rj54n1cb0c.h> +#include <media/i2c/rj54n1cb0c.h> #include <media/soc_camera.h> -#include <media/sh_mobile_ceu.h> +#include <media/drv-intf/sh_mobile_ceu.h> #include <video/sh_mobile_lcdc.h> #include <asm/suspend.h> #include <asm/clock.h> diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c index 29b7c0dcfc51..8f237a5bd9aa 100644 --- a/arch/sh/boards/mach-migor/setup.c +++ b/arch/sh/boards/mach-migor/setup.c @@ -27,10 +27,10 @@ #include <linux/videodev2.h> #include <linux/sh_intc.h> #include <video/sh_mobile_lcdc.h> -#include <media/sh_mobile_ceu.h> -#include <media/ov772x.h> +#include <media/drv-intf/sh_mobile_ceu.h> +#include <media/i2c/ov772x.h> #include <media/soc_camera.h> -#include <media/tw9910.h> +#include <media/i2c/tw9910.h> #include <asm/clock.h> #include <asm/machvec.h> #include <asm/io.h> diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c index 4f6635a075f2..e0e1df136642 100644 --- a/arch/sh/boards/mach-se/7724/setup.c +++ b/arch/sh/boards/mach-se/7724/setup.c @@ -30,7 +30,7 @@ #include <linux/sh_intc.h> #include <linux/videodev2.h> #include <video/sh_mobile_lcdc.h> -#include <media/sh_mobile_ceu.h> +#include <media/drv-intf/sh_mobile_ceu.h> #include <sound/sh_fsi.h> #include <sound/simple_card.h> #include <asm/io.h> @@ -534,8 +534,8 @@ static struct platform_device irda_device = { .resource = irda_resources, }; -#include <media/ak881x.h> -#include <media/sh_vou.h> +#include <media/i2c/ak881x.h> +#include <media/drv-intf/sh_vou.h> static struct ak881x_pdata ak881x_pdata = { .flags = AK881X_IF_MODE_SLAVE, diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c index 079d70e6d74b..38993e09ef03 100644 --- a/arch/sh/kernel/ftrace.c +++ b/arch/sh/kernel/ftrace.c @@ -212,13 +212,11 @@ static int ftrace_modify_code(unsigned long ip, unsigned char *old_code, unsigned char replaced[MCOUNT_INSN_SIZE]; /* - * Note: Due to modules and __init, code can - * disappear and change, we need to protect against faulting - * as well as code changing. We do this by using the - * probe_kernel_* functions. - * - * No real locking needed, this code is run through - * kstop_machine, or before SMP starts. + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ diff --git a/arch/sparc/include/asm/uaccess_32.h b/arch/sparc/include/asm/uaccess_32.h index 64ee103dc29d..57aca2792d29 100644 --- a/arch/sparc/include/asm/uaccess_32.h +++ b/arch/sparc/include/asm/uaccess_32.h @@ -205,31 +205,6 @@ int __put_user_bad(void); __gu_ret; \ }) -#define __get_user_check_ret(x, addr, size, type, retval) ({ \ - register unsigned long __gu_val __asm__ ("l1"); \ - if (__access_ok(addr, size)) { \ - switch (size) { \ - case 1: \ - __get_user_asm_ret(__gu_val, ub, addr, retval); \ - break; \ - case 2: \ - __get_user_asm_ret(__gu_val, uh, addr, retval); \ - break; \ - case 4: \ - __get_user_asm_ret(__gu_val, , addr, retval); \ - break; \ - case 8: \ - __get_user_asm_ret(__gu_val, d, addr, retval); \ - break; \ - default: \ - if (__get_user_bad()) \ - return retval; \ - } \ - x = (__force type) __gu_val; \ - } else \ - return retval; \ -}) - #define __get_user_nocheck(x, addr, size, type) ({ \ register int __gu_ret; \ register unsigned long __gu_val; \ @@ -247,20 +222,6 @@ int __put_user_bad(void); __gu_ret; \ }) -#define __get_user_nocheck_ret(x, addr, size, type, retval) ({ \ - register unsigned long __gu_val __asm__ ("l1"); \ - switch (size) { \ - case 1: __get_user_asm_ret(__gu_val, ub, addr, retval); break; \ - case 2: __get_user_asm_ret(__gu_val, uh, addr, retval); break; \ - case 4: __get_user_asm_ret(__gu_val, , addr, retval); break; \ - case 8: __get_user_asm_ret(__gu_val, d, addr, retval); break; \ - default: \ - if (__get_user_bad()) \ - return retval; \ - } \ - x = (__force type) __gu_val; \ -}) - #define __get_user_asm(x, size, addr, ret) \ __asm__ __volatile__( \ "/* Get user asm, inline. */\n" \ @@ -281,32 +242,6 @@ __asm__ __volatile__( \ : "=&r" (ret), "=&r" (x) : "m" (*__m(addr)), \ "i" (-EFAULT)) -#define __get_user_asm_ret(x, size, addr, retval) \ -if (__builtin_constant_p(retval) && retval == -EFAULT) \ - __asm__ __volatile__( \ - "/* Get user asm ret, inline. */\n" \ - "1:\t" "ld"#size " %1, %0\n\n\t" \ - ".section __ex_table,#alloc\n\t" \ - ".align 4\n\t" \ - ".word 1b,__ret_efault\n\n\t" \ - ".previous\n\t" \ - : "=&r" (x) : "m" (*__m(addr))); \ -else \ - __asm__ __volatile__( \ - "/* Get user asm ret, inline. */\n" \ - "1:\t" "ld"#size " %1, %0\n\n\t" \ - ".section .fixup,#alloc,#execinstr\n\t" \ - ".align 4\n" \ - "3:\n\t" \ - "ret\n\t" \ - " restore %%g0, %2, %%o0\n\n\t" \ - ".previous\n\t" \ - ".section __ex_table,#alloc\n\t" \ - ".align 4\n\t" \ - ".word 1b, 3b\n\n\t" \ - ".previous\n\t" \ - : "=&r" (x) : "m" (*__m(addr)), "i" (retval)) - int __get_user_bad(void); unsigned long __copy_user(void __user *to, const void __user *from, unsigned long size); diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h index ea6e9a20f3ff..e9a51d64974d 100644 --- a/arch/sparc/include/asm/uaccess_64.h +++ b/arch/sparc/include/asm/uaccess_64.h @@ -179,20 +179,6 @@ int __put_user_bad(void); __gu_ret; \ }) -#define __get_user_nocheck_ret(data, addr, size, type, retval) ({ \ - register unsigned long __gu_val __asm__ ("l1"); \ - switch (size) { \ - case 1: __get_user_asm_ret(__gu_val, ub, addr, retval); break; \ - case 2: __get_user_asm_ret(__gu_val, uh, addr, retval); break; \ - case 4: __get_user_asm_ret(__gu_val, uw, addr, retval); break; \ - case 8: __get_user_asm_ret(__gu_val, x, addr, retval); break; \ - default: \ - if (__get_user_bad()) \ - return retval; \ - } \ - data = (__force type) __gu_val; \ -}) - #define __get_user_asm(x, size, addr, ret) \ __asm__ __volatile__( \ "/* Get user asm, inline. */\n" \ @@ -214,32 +200,6 @@ __asm__ __volatile__( \ : "=r" (ret), "=r" (x) : "r" (__m(addr)), \ "i" (-EFAULT)) -#define __get_user_asm_ret(x, size, addr, retval) \ -if (__builtin_constant_p(retval) && retval == -EFAULT) \ - __asm__ __volatile__( \ - "/* Get user asm ret, inline. */\n" \ - "1:\t" "ld"#size "a [%1] %%asi, %0\n\n\t" \ - ".section __ex_table,\"a\"\n\t" \ - ".align 4\n\t" \ - ".word 1b,__ret_efault\n\n\t" \ - ".previous\n\t" \ - : "=r" (x) : "r" (__m(addr))); \ -else \ - __asm__ __volatile__( \ - "/* Get user asm ret, inline. */\n" \ - "1:\t" "ld"#size "a [%1] %%asi, %0\n\n\t" \ - ".section .fixup,#alloc,#execinstr\n\t" \ - ".align 4\n" \ - "3:\n\t" \ - "ret\n\t" \ - " restore %%g0, %2, %%o0\n\n\t" \ - ".previous\n\t" \ - ".section __ex_table,\"a\"\n\t" \ - ".align 4\n\t" \ - ".word 1b, 3b\n\n\t" \ - ".previous\n\t" \ - : "=r" (x) : "r" (__m(addr)), "i" (retval)) - int __get_user_bad(void); unsigned long __must_check ___copy_from_user(void *to, diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index e6a16c40be5f..d270ee91968e 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -81,6 +81,9 @@ #define SO_ATTACH_BPF 0x0034 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 0x0035 +#define SO_ATTACH_REUSEPORT_EBPF 0x0036 + /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x5001 #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 diff --git a/arch/sparc/kernel/idprom.c b/arch/sparc/kernel/idprom.c index 6bd75012109d..f95dd11b75ea 100644 --- a/arch/sparc/kernel/idprom.c +++ b/arch/sparc/kernel/idprom.c @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/init.h> #include <linux/export.h> +#include <linux/etherdevice.h> #include <asm/oplib.h> #include <asm/idprom.h> @@ -60,6 +61,12 @@ static void __init display_system_type(unsigned char machtype) { } #endif + +unsigned char *arch_get_platform_mac_address(void) +{ + return idprom->id_ethaddr; +} + /* Calculate the IDPROM checksum (xor of the data bytes). */ static unsigned char __init calc_idprom_cksum(struct idprom *idprom) { diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 6f80936e0eea..11228861d9b4 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -1033,25 +1033,9 @@ static ssize_t mdesc_read(struct file *file, char __user *buf, static loff_t mdesc_llseek(struct file *file, loff_t offset, int whence) { - struct mdesc_handle *hp; - - switch (whence) { - case SEEK_CUR: - offset += file->f_pos; - break; - case SEEK_SET: - break; - default: - return -EINVAL; - } - - hp = file->private_data; - if (offset > hp->handle_size) - return -EINVAL; - else - file->f_pos = offset; + struct mdesc_handle *hp = file->private_data; - return offset; + return no_seek_end_llseek_size(file, offset, whence, hp->handle_size); } /* mdesc_close() - /dev/mdesc is being closed, release the reference to diff --git a/arch/tile/include/asm/cmpxchg.h b/arch/tile/include/asm/cmpxchg.h index 0ccda3c425be..25d5899497be 100644 --- a/arch/tile/include/asm/cmpxchg.h +++ b/arch/tile/include/asm/cmpxchg.h @@ -127,8 +127,6 @@ long long _atomic64_cmpxchg(long long *v, long long o, long long n); #endif -#define tas(ptr) xchg((ptr), 1) - #endif /* __ASSEMBLY__ */ #endif /* _ASM_TILE_CMPXCHG_H */ diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common index d195a87ca542..cc0013475444 100644 --- a/arch/um/Kconfig.common +++ b/arch/um/Kconfig.common @@ -2,6 +2,7 @@ config UML bool default y select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_SECCOMP_FILTER select HAVE_UID16 select HAVE_FUTEX_CMPXCHG if FUTEX select GENERIC_IRQ_SHOW diff --git a/arch/um/Kconfig.um b/arch/um/Kconfig.um index 28a9885e3a37..4b2ed5858b2e 100644 --- a/arch/um/Kconfig.um +++ b/arch/um/Kconfig.um @@ -104,3 +104,19 @@ config PGTABLE_LEVELS int default 3 if 3_LEVEL_PGTABLES default 2 + +config SECCOMP + def_bool y + prompt "Enable seccomp to safely compute untrusted bytecode" + ---help--- + This kernel feature is useful for number crunching applications + that may need to compute untrusted bytecode during their + execution. By using pipes or other transports made available to + the process as file descriptors supporting the read/write + syscalls, it's possible to isolate those applications in + their own address space using seccomp. Once seccomp is + enabled via prctl(PR_SET_SECCOMP), it cannot be disabled + and the task is only allowed to execute a few safe syscalls + defined by each seccomp mode. + + If unsure, say Y. diff --git a/arch/um/drivers/hostaudio_kern.c b/arch/um/drivers/hostaudio_kern.c index f6b911cc3923..3a4b58730f5f 100644 --- a/arch/um/drivers/hostaudio_kern.c +++ b/arch/um/drivers/hostaudio_kern.c @@ -105,13 +105,9 @@ static ssize_t hostaudio_write(struct file *file, const char __user *buffer, printk(KERN_DEBUG "hostaudio: write called, count = %d\n", count); #endif - kbuf = kmalloc(count, GFP_KERNEL); - if (kbuf == NULL) - return -ENOMEM; - - err = -EFAULT; - if (copy_from_user(kbuf, buffer, count)) - goto out; + kbuf = memdup_user(buffer, count); + if (IS_ERR(kbuf)) + return PTR_ERR(kbuf); err = os_write_file(state->fd, kbuf, count); if (err < 0) diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 29880c9b324e..b821b13d343a 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -748,19 +748,11 @@ static ssize_t mconsole_proc_write(struct file *file, { char *buf; - buf = kmalloc(count + 1, GFP_KERNEL); - if (buf == NULL) - return -ENOMEM; - - if (copy_from_user(buf, buffer, count)) { - count = -EFAULT; - goto out; - } - - buf[count] = '\0'; + buf = memdup_user_nul(buffer, count); + if (IS_ERR(buf)) + return PTR_ERR(buf); mconsole_notify(notify_socket, MCONSOLE_USER_NOTIFY, buf, count); - out: kfree(buf); return count; } diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index e8ab93c3e638..39ba20755e03 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -535,11 +535,7 @@ static int read_cow_bitmap(int fd, void *buf, int offset, int len) { int err; - err = os_seek_file(fd, offset); - if (err < 0) - return err; - - err = os_read_file(fd, buf, len); + err = os_pread_file(fd, buf, len, offset); if (err < 0) return err; @@ -1377,14 +1373,8 @@ static int update_bitmap(struct io_thread_req *req) if(req->cow_offset == -1) return 0; - n = os_seek_file(req->fds[1], req->cow_offset); - if(n < 0){ - printk("do_io - bitmap lseek failed : err = %d\n", -n); - return 1; - } - - n = os_write_file(req->fds[1], &req->bitmap_words, - sizeof(req->bitmap_words)); + n = os_pwrite_file(req->fds[1], &req->bitmap_words, + sizeof(req->bitmap_words), req->cow_offset); if(n != sizeof(req->bitmap_words)){ printk("do_io - bitmap update failed, err = %d fd = %d\n", -n, req->fds[1]); @@ -1399,7 +1389,6 @@ static void do_io(struct io_thread_req *req) char *buf; unsigned long len; int n, nsectors, start, end, bit; - int err; __u64 off; if (req->op == UBD_FLUSH) { @@ -1428,18 +1417,12 @@ static void do_io(struct io_thread_req *req) len = (end - start) * req->sectorsize; buf = &req->buffer[start * req->sectorsize]; - err = os_seek_file(req->fds[bit], off); - if(err < 0){ - printk("do_io - lseek failed : err = %d\n", -err); - req->error = 1; - return; - } if(req->op == UBD_READ){ n = 0; do { buf = &buf[n]; len -= n; - n = os_read_file(req->fds[bit], buf, len); + n = os_pread_file(req->fds[bit], buf, len, off); if (n < 0) { printk("do_io - read failed, err = %d " "fd = %d\n", -n, req->fds[bit]); @@ -1449,7 +1432,7 @@ static void do_io(struct io_thread_req *req) } while((n < len) && (n != 0)); if (n < len) memset(&buf[n], 0, len - n); } else { - n = os_write_file(req->fds[bit], buf, len); + n = os_pwrite_file(req->fds[bit], buf, len, off); if(n != len){ printk("do_io - write failed err = %d " "fd = %d\n", -n, req->fds[bit]); diff --git a/arch/um/include/asm/hardirq.h b/arch/um/include/asm/hardirq.h new file mode 100644 index 000000000000..756f0778e327 --- /dev/null +++ b/arch/um/include/asm/hardirq.h @@ -0,0 +1,23 @@ +#ifndef __ASM_UM_HARDIRQ_H +#define __ASM_UM_HARDIRQ_H + +#include <linux/cache.h> +#include <linux/threads.h> + +typedef struct { + unsigned int __softirq_pending; +} ____cacheline_aligned irq_cpustat_t; + +#include <linux/irq_cpustat.h> /* Standard mappings for irq_cpustat_t above */ +#include <linux/irq.h> + +#ifndef ack_bad_irq +static inline void ack_bad_irq(unsigned int irq) +{ + printk(KERN_CRIT "unexpected IRQ trap at vector %02x\n", irq); +} +#endif + +#define __ARCH_IRQ_EXIT_IRQS_DISABLED 1 + +#endif /* __ASM_UM_HARDIRQ_H */ diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h new file mode 100644 index 000000000000..9fb9cf8cd39a --- /dev/null +++ b/arch/um/include/asm/syscall-generic.h @@ -0,0 +1,138 @@ +/* + * Access to user system call parameters and results + * + * See asm-generic/syscall.h for function descriptions. + * + * Copyright (C) 2015 Mickaël Salaün <mic@digikod.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef __UM_SYSCALL_GENERIC_H +#define __UM_SYSCALL_GENERIC_H + +#include <asm/ptrace.h> +#include <linux/err.h> +#include <linux/sched.h> +#include <sysdep/ptrace.h> + +static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs) +{ + + return PT_REGS_SYSCALL_NR(regs); +} + +static inline void syscall_rollback(struct task_struct *task, + struct pt_regs *regs) +{ + /* do nothing */ +} + +static inline long syscall_get_error(struct task_struct *task, + struct pt_regs *regs) +{ + const long error = regs_return_value(regs); + + return IS_ERR_VALUE(error) ? error : 0; +} + +static inline long syscall_get_return_value(struct task_struct *task, + struct pt_regs *regs) +{ + return regs_return_value(regs); +} + +static inline void syscall_set_return_value(struct task_struct *task, + struct pt_regs *regs, + int error, long val) +{ + PT_REGS_SET_SYSCALL_RETURN(regs, (long) error ?: val); +} + +static inline void syscall_get_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned int i, unsigned int n, + unsigned long *args) +{ + const struct uml_pt_regs *r = ®s->regs; + + switch (i) { + case 0: + if (!n--) + break; + *args++ = UPT_SYSCALL_ARG1(r); + case 1: + if (!n--) + break; + *args++ = UPT_SYSCALL_ARG2(r); + case 2: + if (!n--) + break; + *args++ = UPT_SYSCALL_ARG3(r); + case 3: + if (!n--) + break; + *args++ = UPT_SYSCALL_ARG4(r); + case 4: + if (!n--) + break; + *args++ = UPT_SYSCALL_ARG5(r); + case 5: + if (!n--) + break; + *args++ = UPT_SYSCALL_ARG6(r); + case 6: + if (!n--) + break; + default: + BUG(); + break; + } +} + +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned int i, unsigned int n, + const unsigned long *args) +{ + struct uml_pt_regs *r = ®s->regs; + + switch (i) { + case 0: + if (!n--) + break; + UPT_SYSCALL_ARG1(r) = *args++; + case 1: + if (!n--) + break; + UPT_SYSCALL_ARG2(r) = *args++; + case 2: + if (!n--) + break; + UPT_SYSCALL_ARG3(r) = *args++; + case 3: + if (!n--) + break; + UPT_SYSCALL_ARG4(r) = *args++; + case 4: + if (!n--) + break; + UPT_SYSCALL_ARG5(r) = *args++; + case 5: + if (!n--) + break; + UPT_SYSCALL_ARG6(r) = *args++; + case 6: + if (!n--) + break; + default: + BUG(); + break; + } +} + +/* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */ + +#endif /* __UM_SYSCALL_GENERIC_H */ diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h index 53968aaf76f9..053baff03674 100644 --- a/arch/um/include/asm/thread_info.h +++ b/arch/um/include/asm/thread_info.h @@ -62,11 +62,13 @@ static inline struct thread_info *current_thread_info(void) #define TIF_SYSCALL_AUDIT 6 #define TIF_RESTORE_SIGMASK 7 #define TIF_NOTIFY_RESUME 8 +#define TIF_SECCOMP 9 /* secure computing */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) #define _TIF_MEMDIE (1 << TIF_MEMDIE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +#define _TIF_SECCOMP (1 << TIF_SECCOMP) #endif diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h index 868e6c3f83dd..de5d572225f3 100644 --- a/arch/um/include/shared/os.h +++ b/arch/um/include/shared/os.h @@ -146,6 +146,8 @@ extern int os_read_file(int fd, void *buf, int len); extern int os_write_file(int fd, const void *buf, int count); extern int os_sync_file(int fd); extern int os_file_size(const char *file, unsigned long long *size_out); +extern int os_pread_file(int fd, void *buf, int len, unsigned long long offset); +extern int os_pwrite_file(int fd, const void *buf, int count, unsigned long long offset); extern int os_file_modtime(const char *file, unsigned long *modtime); extern int os_pipe(int *fd, int stream, int close_on_exec); extern int os_set_fd_async(int fd); @@ -282,7 +284,6 @@ extern void initial_thread_cb_skas(void (*proc)(void *), void *arg); extern void halt_skas(void); extern void reboot_skas(void); -extern int get_syscall(struct uml_pt_regs *regs); /* irq.c */ extern int os_waiting_for_events(struct irq_fd *active_fds); diff --git a/arch/um/kernel/skas/syscall.c b/arch/um/kernel/skas/syscall.c index 1683b8efdfda..48b0dcbd87be 100644 --- a/arch/um/kernel/skas/syscall.c +++ b/arch/um/kernel/skas/syscall.c @@ -5,31 +5,38 @@ #include <linux/kernel.h> #include <linux/ptrace.h> +#include <linux/seccomp.h> #include <kern_util.h> #include <sysdep/ptrace.h> +#include <sysdep/ptrace_user.h> #include <sysdep/syscalls.h> -#include <os.h> void handle_syscall(struct uml_pt_regs *r) { struct pt_regs *regs = container_of(r, struct pt_regs, regs); - long result; int syscall; - if (syscall_trace_enter(regs)) { - result = -ENOSYS; + /* Initialize the syscall number and default return value. */ + UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp); + PT_REGS_SET_SYSCALL_RETURN(regs, -ENOSYS); + + /* Do the secure computing check first; failures should be fast. */ + if (secure_computing() == -1) + return; + + if (syscall_trace_enter(regs)) goto out; - } - syscall = get_syscall(r); + /* Update the syscall number after orig_ax has potentially been updated + * with ptrace. + */ + UPT_SYSCALL_NR(r) = PT_SYSCALL_NR(r->gp); + syscall = UPT_SYSCALL_NR(r); - if ((syscall > __NR_syscall_max) || syscall < 0) - result = -ENOSYS; - else - result = EXECUTE_SYSCALL(syscall, regs); + if (syscall >= 0 && syscall <= __NR_syscall_max) + PT_REGS_SET_SYSCALL_RETURN(regs, + EXECUTE_SYSCALL(syscall, regs)); out: - PT_REGS_SET_SYSCALL_RETURN(regs, result); - syscall_trace_leave(regs); } diff --git a/arch/um/os-Linux/file.c b/arch/um/os-Linux/file.c index 26e0164895e4..2db18cbbb0ea 100644 --- a/arch/um/os-Linux/file.c +++ b/arch/um/os-Linux/file.c @@ -264,6 +264,15 @@ int os_read_file(int fd, void *buf, int len) return n; } +int os_pread_file(int fd, void *buf, int len, unsigned long long offset) +{ + int n = pread(fd, buf, len, offset); + + if (n < 0) + return -errno; + return n; +} + int os_write_file(int fd, const void *buf, int len) { int n = write(fd, (void *) buf, len); @@ -282,6 +291,16 @@ int os_sync_file(int fd) return n; } +int os_pwrite_file(int fd, const void *buf, int len, unsigned long long offset) +{ + int n = pwrite(fd, (void *) buf, len, offset); + + if (n < 0) + return -errno; + return n; +} + + int os_file_size(const char *file, unsigned long long *size_out) { struct uml_stat buf; diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c index 897e9ad0c108..8b1767668515 100644 --- a/arch/um/os-Linux/mem.c +++ b/arch/um/os-Linux/mem.c @@ -106,6 +106,17 @@ static int __init make_tempfile(const char *template) } } +#ifdef O_TMPFILE + fd = open(tempdir, O_CLOEXEC | O_RDWR | O_EXCL | O_TMPFILE, 0700); + /* + * If the running system does not support O_TMPFILE flag then retry + * without it. + */ + if (fd != -1 || (errno != EINVAL && errno != EISDIR && + errno != EOPNOTSUPP)) + return fd; +#endif + tempname = malloc(strlen(tempdir) + strlen(template) + 1); if (tempname == NULL) return -1; @@ -142,12 +153,6 @@ static int __init create_tmp_file(unsigned long long len) if (fd < 0) exit(1); - err = fchmod(fd, 0777); - if (err < 0) { - perror("fchmod"); - exit(1); - } - /* * Seek to len - 1 because writing a character there will * increase the file size by one byte, to the desired length. diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index c211153ca69a..7801666514ed 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -62,6 +62,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc) static int signals_enabled; static unsigned int signals_pending; +static unsigned int signals_active = 0; void sig_handler(int sig, struct siginfo *si, mcontext_t *mc) { @@ -101,7 +102,12 @@ void timer_alarm_handler(int sig, struct siginfo *unused_si, mcontext_t *mc) block_signals(); + signals_active |= SIGALRM_MASK; + timer_real_alarm_handler(mc); + + signals_active &= ~SIGALRM_MASK; + set_signals(enabled); } @@ -286,8 +292,16 @@ void unblock_signals(void) if (save_pending & SIGIO_MASK) sig_handler_common(SIGIO, NULL, NULL); - if (save_pending & SIGALRM_MASK) + /* Do not reenter the handler */ + + if ((save_pending & SIGALRM_MASK) && (!(signals_active & SIGALRM_MASK))) timer_real_alarm_handler(NULL); + + /* Rerun the loop only if there is still pending SIGIO and not in TIMER handler */ + + if (!(signals_pending & SIGIO_MASK) && (signals_active & SIGALRM_MASK)) + return; + } } diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c index b856c66ebd3a..23025d645160 100644 --- a/arch/um/os-Linux/skas/process.c +++ b/arch/um/os-Linux/skas/process.c @@ -172,13 +172,6 @@ static void handle_trap(int pid, struct uml_pt_regs *regs, handle_syscall(regs); } -int get_syscall(struct uml_pt_regs *regs) -{ - UPT_SYSCALL_NR(regs) = PT_SYSCALL_NR(regs->gp); - - return UPT_SYSCALL_NR(regs); -} - extern char __syscall_stub_start[]; static int userspace_tramp(void *stack) diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 47f1ff056a54..22a358ef1b0c 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -94,6 +94,8 @@ static int start_ptraced_child(void) { int pid, n, status; + fflush(stdout); + pid = fork(); if (pid == 0) ptrace_child(); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 790aa3ee1afa..ccfededfe470 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -349,6 +349,17 @@ config X86_FEATURE_NAMES If in doubt, say Y. +config X86_FAST_FEATURE_TESTS + bool "Fast CPU feature tests" if EMBEDDED + default y + ---help--- + Some fast-paths in the kernel depend on the capabilities of the CPU. + Say Y here for the kernel to patch in the appropriate code at runtime + based on the capabilities of the CPU. The infrastructure for patching + code at runtime takes up some additional space; space-constrained + embedded systems may wish to say N here to produce smaller, slightly + slower code. + config X86_X2APIC bool "Support x2apic" depends on X86_LOCAL_APIC && X86_64 && (IRQ_REMAP || HYPERVISOR_GUEST) @@ -688,6 +699,14 @@ config PARAVIRT_SPINLOCKS If you are unsure how to answer this question, answer Y. +config QUEUED_LOCK_STAT + bool "Paravirt queued spinlock statistics" + depends on PARAVIRT_SPINLOCKS && DEBUG_FS && QUEUED_SPINLOCKS + ---help--- + Enable the collection of statistical data on the slowpath + behavior of paravirtualized queued spinlocks and report + them on debugfs. + source "arch/x86/xen/Kconfig" config KVM_GUEST diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index 137dfa96aa14..110253ce83af 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -69,7 +69,7 @@ config X86_PTDUMP_CORE def_bool n config X86_PTDUMP - bool "Export kernel pagetable layout to userspace via debugfs" + tristate "Export kernel pagetable layout to userspace via debugfs" depends on DEBUG_KERNEL select DEBUG_FS select X86_PTDUMP_CORE diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c index 722bacea040e..8baaff5af0b5 100644 --- a/arch/x86/crypto/chacha20_glue.c +++ b/arch/x86/crypto/chacha20_glue.c @@ -125,7 +125,7 @@ static struct crypto_alg alg = { static int __init chacha20_simd_mod_init(void) { - if (!cpu_has_ssse3) + if (!boot_cpu_has(X86_FEATURE_SSSE3)) return -ENODEV; #ifdef CONFIG_AS_AVX2 diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c index 81a595d75cf5..0e9871693f24 100644 --- a/arch/x86/crypto/crc32c-intel_glue.c +++ b/arch/x86/crypto/crc32c-intel_glue.c @@ -257,7 +257,7 @@ static int __init crc32c_intel_mod_init(void) if (!x86_match_cpu(crc32c_cpu_id)) return -ENODEV; #ifdef CONFIG_X86_64 - if (cpu_has_pclmulqdq) { + if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) { alg.update = crc32c_pcl_intel_update; alg.finup = crc32c_pcl_intel_finup; alg.digest = crc32c_pcl_intel_digest; diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index 440df0c7a2ee..a69321a77783 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -219,6 +219,29 @@ static int ghash_async_final(struct ahash_request *req) } } +static int ghash_async_import(struct ahash_request *req, const void *in) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + + ghash_async_init(req); + memcpy(dctx, in, sizeof(*dctx)); + return 0; + +} + +static int ghash_async_export(struct ahash_request *req, void *out) +{ + struct ahash_request *cryptd_req = ahash_request_ctx(req); + struct shash_desc *desc = cryptd_shash_desc(cryptd_req); + struct ghash_desc_ctx *dctx = shash_desc_ctx(desc); + + memcpy(out, dctx, sizeof(*dctx)); + return 0; + +} + static int ghash_async_digest(struct ahash_request *req) { struct crypto_ahash *tfm = crypto_ahash_reqtfm(req); @@ -288,8 +311,11 @@ static struct ahash_alg ghash_async_alg = { .final = ghash_async_final, .setkey = ghash_async_setkey, .digest = ghash_async_digest, + .export = ghash_async_export, + .import = ghash_async_import, .halg = { .digestsize = GHASH_DIGEST_SIZE, + .statesize = sizeof(struct ghash_desc_ctx), .base = { .cra_name = "ghash", .cra_driver_name = "ghash-clmulni", diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 3c71dd947c7b..e32206e09868 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -1,3 +1,5 @@ +#include <linux/jump_label.h> + /* x86 function call convention, 64-bit: @@ -232,3 +234,16 @@ For 32-bit we have the following conventions - kernel is built with #endif /* CONFIG_X86_64 */ +/* + * This does 'call enter_from_user_mode' unless we can avoid it based on + * kernel config or using the static jump infrastructure. + */ +.macro CALL_enter_from_user_mode +#ifdef CONFIG_CONTEXT_TRACKING +#ifdef HAVE_JUMP_LABEL + STATIC_JUMP_IF_FALSE .Lafter_call_\@, context_tracking_enabled, def=0 +#endif + call enter_from_user_mode +.Lafter_call_\@: +#endif +.endm diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index f3b6d54e0042..77d8c5112900 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -329,7 +329,8 @@ sysenter_past_esp: * Return back to the vDSO, which will pop ecx and edx. * Don't bother with DS and ES (they already contain __USER_DS). */ - ENABLE_INTERRUPTS_SYSEXIT + sti + sysexit .pushsection .fixup, "ax" 2: movl $0, PT_FS(%esp) @@ -552,11 +553,6 @@ ENTRY(native_iret) iret _ASM_EXTABLE(native_iret, iret_exc) END(native_iret) - -ENTRY(native_irq_enable_sysexit) - sti - sysexit -END(native_irq_enable_sysexit) #endif ENTRY(overflow) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index a55697d19824..9d34d3cfceb6 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -520,9 +520,7 @@ END(irq_entries_start) */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode 1: /* @@ -1066,9 +1064,7 @@ ENTRY(error_entry) * (which can take locks). */ TRACE_IRQS_OFF -#ifdef CONFIG_CONTEXT_TRACKING - call enter_from_user_mode -#endif + CALL_enter_from_user_mode ret .Lerror_entry_done: diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 6a1ae3751e82..ff1c6d61f332 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -18,13 +18,6 @@ .section .entry.text, "ax" -#ifdef CONFIG_PARAVIRT -ENTRY(native_usergs_sysret32) - swapgs - sysretl -ENDPROC(native_usergs_sysret32) -#endif - /* * 32-bit SYSENTER instruction entry. * @@ -103,15 +96,15 @@ ENTRY(entry_SYSENTER_compat) * This needs to happen before enabling interrupts so that * we don't get preempted with NT set. * - * NB.: sysenter_fix_flags is a label with the code under it moved + * NB.: .Lsysenter_fix_flags is a label with the code under it moved * out-of-line as an optimization: NT is unlikely to be set in the * majority of the cases and instead of polluting the I$ unnecessarily, * we're keeping that code behind a branch which will predict as * not-taken and therefore its instructions won't be fetched. */ testl $X86_EFLAGS_NT, EFLAGS(%rsp) - jnz sysenter_fix_flags -sysenter_flags_fixed: + jnz .Lsysenter_fix_flags +.Lsysenter_flags_fixed: /* * User mode is traced as though IRQs are on, and SYSENTER @@ -126,10 +119,10 @@ sysenter_flags_fixed: "jmp .Lsyscall_32_done", X86_FEATURE_XENPV jmp sysret32_from_system_call -sysenter_fix_flags: +.Lsysenter_fix_flags: pushq $X86_EFLAGS_FIXED popfq - jmp sysenter_flags_fixed + jmp .Lsysenter_flags_fixed ENDPROC(entry_SYSENTER_compat) /* @@ -238,7 +231,8 @@ sysret32_from_system_call: xorq %r9, %r9 xorq %r10, %r10 movq RSP-ORIG_RAX(%rsp), %rsp - USERGS_SYSRET32 + swapgs + sysretl END(entry_SYSCALL_compat) /* diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index f17705e1332c..cb713df81180 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -383,3 +383,4 @@ 374 i386 userfaultfd sys_userfaultfd 375 i386 membarrier sys_membarrier 376 i386 mlock2 sys_mlock2 +377 i386 copy_file_range sys_copy_file_range diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 314a90bfc09c..dc1040a50bdc 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -332,6 +332,7 @@ 323 common userfaultfd sys_userfaultfd 324 common membarrier sys_membarrier 325 common mlock2 sys_mlock2 +326 common copy_file_range sys_copy_file_range # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index ca94fa649251..8602f06c759f 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -17,8 +17,10 @@ #include <asm/vvar.h> #include <asm/unistd.h> #include <asm/msr.h> +#include <asm/pvclock.h> #include <linux/math64.h> #include <linux/time.h> +#include <linux/kernel.h> #define gtod (&VVAR(vsyscall_gtod_data)) @@ -36,12 +38,12 @@ static notrace cycle_t vread_hpet(void) } #endif -#ifndef BUILD_VDSO32 +#ifdef CONFIG_PARAVIRT_CLOCK +extern u8 pvclock_page + __attribute__((visibility("hidden"))); +#endif -#include <linux/kernel.h> -#include <asm/vsyscall.h> -#include <asm/fixmap.h> -#include <asm/pvclock.h> +#ifndef BUILD_VDSO32 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { @@ -60,75 +62,6 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } -#ifdef CONFIG_PARAVIRT_CLOCK - -static notrace const struct pvclock_vsyscall_time_info *get_pvti(int cpu) -{ - const struct pvclock_vsyscall_time_info *pvti_base; - int idx = cpu / (PAGE_SIZE/PVTI_SIZE); - int offset = cpu % (PAGE_SIZE/PVTI_SIZE); - - BUG_ON(PVCLOCK_FIXMAP_BEGIN + idx > PVCLOCK_FIXMAP_END); - - pvti_base = (struct pvclock_vsyscall_time_info *) - __fix_to_virt(PVCLOCK_FIXMAP_BEGIN+idx); - - return &pvti_base[offset]; -} - -static notrace cycle_t vread_pvclock(int *mode) -{ - const struct pvclock_vsyscall_time_info *pvti; - cycle_t ret; - u64 last; - u32 version; - u8 flags; - unsigned cpu, cpu1; - - - /* - * 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; - /* TODO: We can put vcpu id into higher bits of pvti.version. - * This will save a couple of cycles by getting rid of - * __getcpu() calls (Gleb). - */ - - pvti = get_pvti(cpu); - - version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); - - /* - * Test we're still on the cpu as well as the version. - * We could have been migrated just after the first - * vgetcpu but before fetching the version, so we - * wouldn't notice a version change. - */ - cpu1 = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1 || - (pvti->pvti.version & 1) || - pvti->pvti.version != version)); - - if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) - *mode = VCLOCK_NONE; - - /* refer to tsc.c read_tsc() comment for rationale */ - last = gtod->cycle_last; - - if (likely(ret >= last)) - return ret; - - return last; -} -#endif #else @@ -162,15 +95,77 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) return ret; } +#endif + #ifdef CONFIG_PARAVIRT_CLOCK +static notrace const struct pvclock_vsyscall_time_info *get_pvti0(void) +{ + return (const struct pvclock_vsyscall_time_info *)&pvclock_page; +} static notrace cycle_t vread_pvclock(int *mode) { - *mode = VCLOCK_NONE; - return 0; -} -#endif + const struct pvclock_vcpu_time_info *pvti = &get_pvti0()->pvti; + cycle_t ret; + u64 tsc, pvti_tsc; + u64 last, delta, pvti_system_time; + u32 version, pvti_tsc_to_system_mul, pvti_tsc_shift; + + /* + * Note: The kernel and hypervisor must guarantee that cpu ID + * number maps 1:1 to per-CPU pvclock time info. + * + * Because the hypervisor is entirely unaware of guest userspace + * preemption, it cannot guarantee that per-CPU pvclock time + * info is updated if the underlying CPU changes or that that + * version is increased whenever underlying CPU changes. + * + * On KVM, we are guaranteed that pvti updates for any vCPU are + * atomic as seen by *all* vCPUs. This is an even stronger + * guarantee than we get with a normal seqlock. + * + * On Xen, we don't appear to have that guarantee, but Xen still + * supplies a valid seqlock using the version field. + + * We only do pvclock vdso timing at all if + * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to + * mean that all vCPUs have matching pvti and that the TSC is + * synced, so we can just look at vCPU 0's pvti. + */ + if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) { + *mode = VCLOCK_NONE; + return 0; + } + + do { + version = pvti->version; + + smp_rmb(); + + tsc = rdtsc_ordered(); + pvti_tsc_to_system_mul = pvti->tsc_to_system_mul; + pvti_tsc_shift = pvti->tsc_shift; + pvti_system_time = pvti->system_time; + pvti_tsc = pvti->tsc_timestamp; + + /* Make sure that the version double-check is last. */ + smp_rmb(); + } while (unlikely((version & 1) || version != pvti->version)); + + delta = tsc - pvti_tsc; + ret = pvti_system_time + + pvclock_scale_delta(delta, pvti_tsc_to_system_mul, + pvti_tsc_shift); + + /* refer to vread_tsc() comment for rationale */ + last = gtod->cycle_last; + + if (likely(ret >= last)) + return ret; + + return last; +} #endif notrace static cycle_t vread_tsc(void) diff --git a/arch/x86/entry/vdso/vdso-layout.lds.S b/arch/x86/entry/vdso/vdso-layout.lds.S index de2c921025f5..4158acc17df0 100644 --- a/arch/x86/entry/vdso/vdso-layout.lds.S +++ b/arch/x86/entry/vdso/vdso-layout.lds.S @@ -25,7 +25,7 @@ SECTIONS * segment. */ - vvar_start = . - 2 * PAGE_SIZE; + vvar_start = . - 3 * PAGE_SIZE; vvar_page = vvar_start; /* Place all vvars at the offsets in asm/vvar.h. */ @@ -36,6 +36,7 @@ SECTIONS #undef EMIT_VVAR hpet_page = vvar_start + PAGE_SIZE; + pvclock_page = vvar_start + 2 * PAGE_SIZE; . = SIZEOF_HEADERS; diff --git a/arch/x86/entry/vdso/vdso2c.c b/arch/x86/entry/vdso/vdso2c.c index 785d9922b106..491020b2826d 100644 --- a/arch/x86/entry/vdso/vdso2c.c +++ b/arch/x86/entry/vdso/vdso2c.c @@ -73,6 +73,7 @@ enum { sym_vvar_start, sym_vvar_page, sym_hpet_page, + sym_pvclock_page, sym_VDSO_FAKE_SECTION_TABLE_START, sym_VDSO_FAKE_SECTION_TABLE_END, }; @@ -80,6 +81,7 @@ enum { const int special_pages[] = { sym_vvar_page, sym_hpet_page, + sym_pvclock_page, }; struct vdso_sym { @@ -91,6 +93,7 @@ struct vdso_sym required_syms[] = { [sym_vvar_start] = {"vvar_start", true}, [sym_vvar_page] = {"vvar_page", true}, [sym_hpet_page] = {"hpet_page", true}, + [sym_pvclock_page] = {"pvclock_page", true}, [sym_VDSO_FAKE_SECTION_TABLE_START] = { "VDSO_FAKE_SECTION_TABLE_START", false }, diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 64df47148160..b8f69e264ac4 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -12,6 +12,7 @@ #include <linux/random.h> #include <linux/elf.h> #include <linux/cpu.h> +#include <asm/pvclock.h> #include <asm/vgtod.h> #include <asm/proto.h> #include <asm/vdso.h> @@ -100,6 +101,7 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) .name = "[vvar]", .pages = no_pages, }; + struct pvclock_vsyscall_time_info *pvti; if (calculate_addr) { addr = vdso_addr(current->mm->start_stack, @@ -169,6 +171,18 @@ static int map_vdso(const struct vdso_image *image, bool calculate_addr) } #endif + pvti = pvclock_pvti_cpu0_va(); + if (pvti && image->sym_pvclock_page) { + ret = remap_pfn_range(vma, + text_start + image->sym_pvclock_page, + __pa(pvti) >> PAGE_SHIFT, + PAGE_SIZE, + PAGE_READONLY); + + if (ret) + goto up_fail; + } + up_fail: if (ret) current->mm->context.vdso = NULL; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index a30316bf801a..c80f6b6f3da2 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -23,6 +23,11 @@ #define APIC_VERBOSE 1 #define APIC_DEBUG 2 +/* Macros for apic_extnmi which controls external NMI masking */ +#define APIC_EXTNMI_BSP 0 /* Default */ +#define APIC_EXTNMI_ALL 1 +#define APIC_EXTNMI_NONE 2 + /* * Define the default level of output to be very little * This can be turned up by using apic=verbose for more @@ -303,6 +308,7 @@ struct apic { unsigned int *apicid); /* ipi */ + void (*send_IPI)(int cpu, int vector); void (*send_IPI_mask)(const struct cpumask *mask, int vector); void (*send_IPI_mask_allbutself)(const struct cpumask *mask, int vector); diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index ae5fb83e6d91..3e8674288198 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index a11c30b77fb5..a984111135b1 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -3,7 +3,6 @@ #include <linux/compiler.h> #include <linux/types.h> -#include <asm/processor.h> //#include <asm/cmpxchg.h> /* An 64bit atomic type */ diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h index 0d467b338835..a8303ebe089f 100644 --- a/arch/x86/include/asm/calgary.h +++ b/arch/x86/include/asm/calgary.h @@ -31,7 +31,7 @@ #include <asm/types.h> struct iommu_table { - struct cal_chipset_ops *chip_ops; /* chipset specific funcs */ + const struct cal_chipset_ops *chip_ops; /* chipset specific funcs */ unsigned long it_base; /* mapped address of tce table */ unsigned long it_hint; /* Hint for next alloc */ unsigned long *it_map; /* A simple allocation bitmap for now */ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index f7e142926481..e4959d023af8 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -109,6 +109,6 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) #endif -#define system_has_cmpxchg_double() cpu_has_cx8 +#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX8) #endif /* _ASM_X86_CMPXCHG_32_H */ diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 1af94697aae5..caa23a34c963 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -18,6 +18,6 @@ static inline void set_64bit(volatile u64 *ptr, u64 val) cmpxchg_local((ptr), (o), (n)); \ }) -#define system_has_cmpxchg_double() cpu_has_cx16 +#define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16) #endif /* _ASM_X86_CMPXCHG_64_H */ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index bf2caa1dedc5..678637ad7476 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -36,4 +36,7 @@ extern int _debug_hotplug_cpu(int cpu, int action); int mwait_usable(const struct cpuinfo_x86 *); +unsigned int x86_family(unsigned int sig); +unsigned int x86_model(unsigned int sig); +unsigned int x86_stepping(unsigned int sig); #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index f7ba9fbf12ee..7ad8c9464297 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -12,7 +12,7 @@ #include <asm/disabled-features.h> #endif -#define NCAPINTS 14 /* N 32-bit words worth of info */ +#define NCAPINTS 16 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -181,22 +181,17 @@ /* * Auxiliary flags: Linux defined - For features scattered in various - * CPUID levels like 0x6, 0xA etc, word 7 + * CPUID levels like 0x6, 0xA etc, word 7. + * + * Reuse free bits when adding new feature flags! */ -#define X86_FEATURE_IDA ( 7*32+ 0) /* Intel Dynamic Acceleration */ -#define X86_FEATURE_ARAT ( 7*32+ 1) /* Always Running APIC Timer */ + #define X86_FEATURE_CPB ( 7*32+ 2) /* AMD Core Performance Boost */ #define X86_FEATURE_EPB ( 7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ -#define X86_FEATURE_PLN ( 7*32+ 5) /* Intel Power Limit Notification */ -#define X86_FEATURE_PTS ( 7*32+ 6) /* Intel Package Thermal Status */ -#define X86_FEATURE_DTHERM ( 7*32+ 7) /* Digital Thermal Sensor */ + #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ -#define X86_FEATURE_HWP ( 7*32+ 10) /* "hwp" Intel HWP */ -#define X86_FEATURE_HWP_NOTIFY ( 7*32+ 11) /* Intel HWP_NOTIFY */ -#define X86_FEATURE_HWP_ACT_WINDOW ( 7*32+ 12) /* Intel HWP_ACT_WINDOW */ -#define X86_FEATURE_HWP_EPP ( 7*32+13) /* Intel HWP_EPP */ -#define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */ + #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ /* Virtualization flags: Linux defined, word 8 */ @@ -205,16 +200,7 @@ #define X86_FEATURE_FLEXPRIORITY ( 8*32+ 2) /* Intel FlexPriority */ #define X86_FEATURE_EPT ( 8*32+ 3) /* Intel Extended Page Table */ #define X86_FEATURE_VPID ( 8*32+ 4) /* Intel Virtual Processor ID */ -#define X86_FEATURE_NPT ( 8*32+ 5) /* AMD Nested Page Table support */ -#define X86_FEATURE_LBRV ( 8*32+ 6) /* AMD LBR Virtualization support */ -#define X86_FEATURE_SVML ( 8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ -#define X86_FEATURE_NRIPS ( 8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ -#define X86_FEATURE_TSCRATEMSR ( 8*32+ 9) /* "tsc_scale" AMD TSC scaling support */ -#define X86_FEATURE_VMCBCLEAN ( 8*32+10) /* "vmcb_clean" AMD VMCB clean bits support */ -#define X86_FEATURE_FLUSHBYASID ( 8*32+11) /* AMD flush-by-ASID support */ -#define X86_FEATURE_DECODEASSISTS ( 8*32+12) /* AMD Decode Assists support */ -#define X86_FEATURE_PAUSEFILTER ( 8*32+13) /* AMD filtered pause intercept */ -#define X86_FEATURE_PFTHRESHOLD ( 8*32+14) /* AMD pause filter threshold */ + #define X86_FEATURE_VMMCALL ( 8*32+15) /* Prefer vmmcall to vmcall */ #define X86_FEATURE_XENPV ( 8*32+16) /* "" Xen paravirtual guest */ @@ -259,6 +245,30 @@ /* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */ #define X86_FEATURE_CLZERO (13*32+0) /* CLZERO instruction */ +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (eax), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* HWP Package Level Request */ + +/* AMD SVM Feature Identification, CPUID level 0x8000000a (edx), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* pause filter threshold */ + /* * BUG word(s) */ @@ -279,6 +289,26 @@ #include <asm/asm.h> #include <linux/bitops.h> +enum cpuid_leafs +{ + CPUID_1_EDX = 0, + CPUID_8000_0001_EDX, + CPUID_8086_0001_EDX, + CPUID_LNX_1, + CPUID_1_ECX, + CPUID_C000_0001_EDX, + CPUID_8000_0001_ECX, + CPUID_LNX_2, + CPUID_LNX_3, + CPUID_7_0_EBX, + CPUID_D_1_EAX, + CPUID_F_0_EDX, + CPUID_F_1_EDX, + CPUID_8000_0008_EBX, + CPUID_6_EAX, + CPUID_8000_000A_EDX, +}; + #ifdef CONFIG_X86_FEATURE_NAMES extern const char * const x86_cap_flags[NCAPINTS*32]; extern const char * const x86_power_flags[32]; @@ -356,60 +386,31 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; } while (0) #define cpu_has_fpu boot_cpu_has(X86_FEATURE_FPU) -#define cpu_has_de boot_cpu_has(X86_FEATURE_DE) #define cpu_has_pse boot_cpu_has(X86_FEATURE_PSE) #define cpu_has_tsc boot_cpu_has(X86_FEATURE_TSC) #define cpu_has_pge boot_cpu_has(X86_FEATURE_PGE) #define cpu_has_apic boot_cpu_has(X86_FEATURE_APIC) -#define cpu_has_sep boot_cpu_has(X86_FEATURE_SEP) -#define cpu_has_mtrr boot_cpu_has(X86_FEATURE_MTRR) -#define cpu_has_mmx boot_cpu_has(X86_FEATURE_MMX) #define cpu_has_fxsr boot_cpu_has(X86_FEATURE_FXSR) #define cpu_has_xmm boot_cpu_has(X86_FEATURE_XMM) #define cpu_has_xmm2 boot_cpu_has(X86_FEATURE_XMM2) -#define cpu_has_xmm3 boot_cpu_has(X86_FEATURE_XMM3) -#define cpu_has_ssse3 boot_cpu_has(X86_FEATURE_SSSE3) #define cpu_has_aes boot_cpu_has(X86_FEATURE_AES) #define cpu_has_avx boot_cpu_has(X86_FEATURE_AVX) #define cpu_has_avx2 boot_cpu_has(X86_FEATURE_AVX2) -#define cpu_has_ht boot_cpu_has(X86_FEATURE_HT) -#define cpu_has_nx boot_cpu_has(X86_FEATURE_NX) -#define cpu_has_xstore boot_cpu_has(X86_FEATURE_XSTORE) -#define cpu_has_xstore_enabled boot_cpu_has(X86_FEATURE_XSTORE_EN) -#define cpu_has_xcrypt boot_cpu_has(X86_FEATURE_XCRYPT) -#define cpu_has_xcrypt_enabled boot_cpu_has(X86_FEATURE_XCRYPT_EN) -#define cpu_has_ace2 boot_cpu_has(X86_FEATURE_ACE2) -#define cpu_has_ace2_enabled boot_cpu_has(X86_FEATURE_ACE2_EN) -#define cpu_has_phe boot_cpu_has(X86_FEATURE_PHE) -#define cpu_has_phe_enabled boot_cpu_has(X86_FEATURE_PHE_EN) -#define cpu_has_pmm boot_cpu_has(X86_FEATURE_PMM) -#define cpu_has_pmm_enabled boot_cpu_has(X86_FEATURE_PMM_EN) -#define cpu_has_ds boot_cpu_has(X86_FEATURE_DS) -#define cpu_has_pebs boot_cpu_has(X86_FEATURE_PEBS) #define cpu_has_clflush boot_cpu_has(X86_FEATURE_CLFLUSH) -#define cpu_has_bts boot_cpu_has(X86_FEATURE_BTS) #define cpu_has_gbpages boot_cpu_has(X86_FEATURE_GBPAGES) #define cpu_has_arch_perfmon boot_cpu_has(X86_FEATURE_ARCH_PERFMON) #define cpu_has_pat boot_cpu_has(X86_FEATURE_PAT) -#define cpu_has_xmm4_1 boot_cpu_has(X86_FEATURE_XMM4_1) -#define cpu_has_xmm4_2 boot_cpu_has(X86_FEATURE_XMM4_2) #define cpu_has_x2apic boot_cpu_has(X86_FEATURE_X2APIC) #define cpu_has_xsave boot_cpu_has(X86_FEATURE_XSAVE) -#define cpu_has_xsaveopt boot_cpu_has(X86_FEATURE_XSAVEOPT) #define cpu_has_xsaves boot_cpu_has(X86_FEATURE_XSAVES) #define cpu_has_osxsave boot_cpu_has(X86_FEATURE_OSXSAVE) #define cpu_has_hypervisor boot_cpu_has(X86_FEATURE_HYPERVISOR) -#define cpu_has_pclmulqdq boot_cpu_has(X86_FEATURE_PCLMULQDQ) -#define cpu_has_perfctr_core boot_cpu_has(X86_FEATURE_PERFCTR_CORE) -#define cpu_has_perfctr_nb boot_cpu_has(X86_FEATURE_PERFCTR_NB) -#define cpu_has_perfctr_l2 boot_cpu_has(X86_FEATURE_PERFCTR_L2) -#define cpu_has_cx8 boot_cpu_has(X86_FEATURE_CX8) -#define cpu_has_cx16 boot_cpu_has(X86_FEATURE_CX16) -#define cpu_has_eager_fpu boot_cpu_has(X86_FEATURE_EAGER_FPU) -#define cpu_has_topoext boot_cpu_has(X86_FEATURE_TOPOEXT) -#define cpu_has_bpext boot_cpu_has(X86_FEATURE_BPEXT) - -#if __GNUC__ >= 4 +/* + * Do not add any more of those clumsy macros - use static_cpu_has_safe() for + * fast paths and boot_cpu_has() otherwise! + */ + +#if __GNUC__ >= 4 && defined(CONFIG_X86_FAST_FEATURE_TESTS) extern void warn_pre_alternatives(void); extern bool __static_cpu_has_safe(u16 bit); diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index f80d70009ff8..6d7d0e52ed5a 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -19,7 +19,6 @@ #include <asm/acpi.h> #include <asm/apicdef.h> #include <asm/page.h> -#include <asm/pvclock.h> #ifdef CONFIG_X86_32 #include <linux/threads.h> #include <asm/kmap_types.h> @@ -72,10 +71,6 @@ enum fixed_addresses { #ifdef CONFIG_X86_VSYSCALL_EMULATION VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT, #endif -#ifdef CONFIG_PARAVIRT_CLOCK - PVCLOCK_FIXMAP_BEGIN, - PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, -#endif #endif FIX_DBGP_BASE, FIX_EARLYCON_MEM_BASE, diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 3c3550c3a4a3..eadcdd5bb946 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -224,18 +224,67 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) #define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" #define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" -/* xstate instruction fault handler: */ -#define xstate_fault(__err) \ - \ - ".section .fixup,\"ax\"\n" \ - \ - "3: movl $-2,%[_err]\n" \ - " jmp 2b\n" \ - \ - ".previous\n" \ - \ - _ASM_EXTABLE(1b, 3b) \ - : [_err] "=r" (__err) +#define XSTATE_OP(op, st, lmask, hmask, err) \ + asm volatile("1:" op "\n\t" \ + "xor %[err], %[err]\n" \ + "2:\n\t" \ + ".pushsection .fixup,\"ax\"\n\t" \ + "3: movl $-2,%[err]\n\t" \ + "jmp 2b\n\t" \ + ".popsection\n\t" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * If XSAVES is enabled, it replaces XSAVEOPT because it supports a compact + * format and supervisor states in addition to modified optimization in + * XSAVEOPT. + * + * Otherwise, if XSAVEOPT is enabled, XSAVEOPT replaces XSAVE because XSAVEOPT + * supports modified optimization which is not supported by XSAVE. + * + * We use XSAVE as a fallback. + * + * The 661 label is defined in the ALTERNATIVE* macros as the address of the + * original instruction which gets replaced. We need to use it here as the + * address of the instruction where we might get an exception at. + */ +#define XSTATE_XSAVE(st, lmask, hmask, err) \ + asm volatile(ALTERNATIVE_2(XSAVE, \ + XSAVEOPT, X86_FEATURE_XSAVEOPT, \ + XSAVES, X86_FEATURE_XSAVES) \ + "\n" \ + "xor %[err], %[err]\n" \ + "3:\n" \ + ".pushsection .fixup,\"ax\"\n" \ + "4: movl $-2, %[err]\n" \ + "jmp 3b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(661b, 4b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") + +/* + * Use XRSTORS to restore context if it is enabled. XRSTORS supports compact + * XSAVE area format. + */ +#define XSTATE_XRESTORE(st, lmask, hmask, err) \ + asm volatile(ALTERNATIVE(XRSTOR, \ + XRSTORS, X86_FEATURE_XSAVES) \ + "\n" \ + "xor %[err], %[err]\n" \ + "3:\n" \ + ".pushsection .fixup,\"ax\"\n" \ + "4: movl $-2, %[err]\n" \ + "jmp 3b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(661b, 4b) \ + : [err] "=r" (err) \ + : "D" (st), "m" (*st), "a" (lmask), "d" (hmask) \ + : "memory") /* * This function is called only during boot time when x86 caps are not set @@ -246,22 +295,14 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; WARN_ON(system_state != SYSTEM_BOOTING); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XSAVES"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + XSTATE_OP(XSAVES, xstate, lmask, hmask, err); else - asm volatile("1:"XSAVE"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + XSTATE_OP(XSAVE, xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); @@ -276,22 +317,14 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; WARN_ON(system_state != SYSTEM_BOOTING); - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XRSTORS"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + if (static_cpu_has_safe(X86_FEATURE_XSAVES)) + XSTATE_OP(XRSTORS, xstate, lmask, hmask, err); else - asm volatile("1:"XRSTOR"\n\t" - "2:\n\t" - xstate_fault(err) - : "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); /* We should never fault when copying from a kernel buffer: */ WARN_ON_FPU(err); @@ -305,33 +338,11 @@ static inline void copy_xregs_to_kernel(struct xregs_state *xstate) u64 mask = -1; u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; WARN_ON(!alternatives_patched); - /* - * If xsaves is enabled, xsaves replaces xsaveopt because - * it supports compact format and supervisor states in addition to - * modified optimization in xsaveopt. - * - * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave - * because xsaveopt supports modified optimization which is not - * supported by xsave. - * - * If none of xsaves and xsaveopt is enabled, use xsave. - */ - alternative_input_2( - "1:"XSAVE, - XSAVEOPT, - X86_FEATURE_XSAVEOPT, - XSAVES, - X86_FEATURE_XSAVES, - [xstate] "D" (xstate), "a" (lmask), "d" (hmask) : - "memory"); - asm volatile("2:\n\t" - xstate_fault(err) - : "0" (err) - : "memory"); + XSTATE_XSAVE(xstate, lmask, hmask, err); /* We should never fault when copying to a kernel buffer: */ WARN_ON_FPU(err); @@ -344,23 +355,9 @@ static inline void copy_kernel_to_xregs(struct xregs_state *xstate, u64 mask) { u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; + int err; - /* - * Use xrstors to restore context if it is enabled. xrstors supports - * compacted format of xsave area which is not supported by xrstor. - */ - alternative_input( - "1: " XRSTOR, - XRSTORS, - X86_FEATURE_XSAVES, - "D" (xstate), "m" (*xstate), "a" (lmask), "d" (hmask) - : "memory"); - - asm volatile("2:\n" - xstate_fault(err) - : "0" (err) - : "memory"); + XSTATE_XRESTORE(xstate, lmask, hmask, err); /* We should never fault when copying from a kernel buffer: */ WARN_ON_FPU(err); @@ -388,12 +385,10 @@ static inline int copy_xregs_to_user(struct xregs_state __user *buf) if (unlikely(err)) return -EFAULT; - __asm__ __volatile__(ASM_STAC "\n" - "1:"XSAVE"\n" - "2: " ASM_CLAC "\n" - xstate_fault(err) - : "D" (buf), "a" (-1), "d" (-1), "0" (err) - : "memory"); + stac(); + XSTATE_OP(XSAVE, buf, -1, -1, err); + clac(); + return err; } @@ -405,14 +400,12 @@ static inline int copy_user_to_xregs(struct xregs_state __user *buf, u64 mask) struct xregs_state *xstate = ((__force struct xregs_state *)buf); u32 lmask = mask; u32 hmask = mask >> 32; - int err = 0; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XRSTOR"\n" - "2: " ASM_CLAC "\n" - xstate_fault(err) - : "D" (xstate), "a" (lmask), "d" (hmask), "0" (err) - : "memory"); /* memory required? */ + int err; + + stac(); + XSTATE_OP(XRSTOR, xstate, lmask, hmask, err); + clac(); + return err; } diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h new file mode 100644 index 000000000000..e1a411786bf5 --- /dev/null +++ b/arch/x86/include/asm/intel_pt.h @@ -0,0 +1,10 @@ +#ifndef _ASM_X86_INTEL_PT_H +#define _ASM_X86_INTEL_PT_H + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) +void cpu_emergency_stop_pt(void); +#else +static inline void cpu_emergency_stop_pt(void) {} +#endif + +#endif /* _ASM_X86_INTEL_PT_H */ diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h index 615fa9061b57..cfc9a0d2d07c 100644 --- a/arch/x86/include/asm/ipi.h +++ b/arch/x86/include/asm/ipi.h @@ -119,6 +119,8 @@ static inline void native_apic_mem_write(APIC_ICR, cfg); } +extern void default_send_IPI_single(int cpu, int vector); +extern void default_send_IPI_single_phys(int cpu, int vector); extern void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector); extern void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 5daeca3d0f9e..adc54c12cbd1 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -1,12 +1,18 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H -#ifndef __ASSEMBLY__ - -#include <linux/stringify.h> -#include <linux/types.h> -#include <asm/nops.h> -#include <asm/asm.h> +#ifndef HAVE_JUMP_LABEL +/* + * For better or for worse, if jump labels (the gcc extension) are missing, + * then the entire static branch patching infrastructure is compiled out. + * If that happens, the code in here will malfunction. Raise a compiler + * error instead. + * + * In theory, jump labels and the static branch patching infrastructure + * could be decoupled to fix this. + */ +#error asm/jump_label.h included on a non-jump-label kernel +#endif #define JUMP_LABEL_NOP_SIZE 5 @@ -16,6 +22,14 @@ # define STATIC_KEY_INIT_NOP GENERIC_NOP5_ATOMIC #endif +#include <asm/asm.h> +#include <asm/nops.h> + +#ifndef __ASSEMBLY__ + +#include <linux/stringify.h> +#include <linux/types.h> + static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { asm_volatile_goto("1:" @@ -59,5 +73,40 @@ struct jump_entry { jump_label_t key; }; -#endif /* __ASSEMBLY__ */ +#else /* __ASSEMBLY__ */ + +.macro STATIC_JUMP_IF_TRUE target, key, def +.Lstatic_jump_\@: + .if \def + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .else + .byte STATIC_KEY_INIT_NOP + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + .popsection +.endm + +.macro STATIC_JUMP_IF_FALSE target, key, def +.Lstatic_jump_\@: + .if \def + .byte STATIC_KEY_INIT_NOP + .else + /* Equivalent to "jmp.d32 \target" */ + .byte 0xe9 + .long \target - .Lstatic_jump_after_\@ +.Lstatic_jump_after_\@: + .endif + .pushsection __jump_table, "aw" + _ASM_ALIGN + _ASM_PTR .Lstatic_jump_\@, \target, \key + 1 + .popsection +.endm + +#endif /* __ASSEMBLY__ */ + #endif diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 30cfd64295a0..44adbb819041 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -25,6 +25,7 @@ #include <linux/pvclock_gtod.h> #include <linux/clocksource.h> #include <linux/irqbypass.h> +#include <linux/hyperv.h> #include <asm/pvclock-abi.h> #include <asm/desc.h> @@ -45,6 +46,31 @@ #define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS +/* x86-specific vcpu->requests bit members */ +#define KVM_REQ_MIGRATE_TIMER 8 +#define KVM_REQ_REPORT_TPR_ACCESS 9 +#define KVM_REQ_TRIPLE_FAULT 10 +#define KVM_REQ_MMU_SYNC 11 +#define KVM_REQ_CLOCK_UPDATE 12 +#define KVM_REQ_DEACTIVATE_FPU 13 +#define KVM_REQ_EVENT 14 +#define KVM_REQ_APF_HALT 15 +#define KVM_REQ_STEAL_UPDATE 16 +#define KVM_REQ_NMI 17 +#define KVM_REQ_PMU 18 +#define KVM_REQ_PMI 19 +#define KVM_REQ_SMI 20 +#define KVM_REQ_MASTERCLOCK_UPDATE 21 +#define KVM_REQ_MCLOCK_INPROGRESS 22 +#define KVM_REQ_SCAN_IOAPIC 23 +#define KVM_REQ_GLOBAL_CLOCK_UPDATE 24 +#define KVM_REQ_APIC_PAGE_RELOAD 25 +#define KVM_REQ_HV_CRASH 26 +#define KVM_REQ_IOAPIC_EOI_EXIT 27 +#define KVM_REQ_HV_RESET 28 +#define KVM_REQ_HV_EXIT 29 +#define KVM_REQ_HV_STIMER 30 + #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ @@ -213,6 +239,10 @@ union kvm_mmu_page_role { }; }; +struct kvm_rmap_head { + unsigned long val; +}; + struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; @@ -230,7 +260,7 @@ struct kvm_mmu_page { bool unsync; int root_count; /* Currently serving as active root */ unsigned int unsync_children; - unsigned long parent_ptes; /* Reverse mapping for parent_pte */ + struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ /* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen. */ unsigned long mmu_valid_gen; @@ -374,10 +404,38 @@ struct kvm_mtrr { struct list_head head; }; +/* Hyper-V SynIC timer */ +struct kvm_vcpu_hv_stimer { + struct hrtimer timer; + int index; + u64 config; + u64 count; + u64 exp_time; + struct hv_message msg; + bool msg_pending; +}; + +/* Hyper-V synthetic interrupt controller (SynIC)*/ +struct kvm_vcpu_hv_synic { + u64 version; + u64 control; + u64 msg_page; + u64 evt_page; + atomic64_t sint[HV_SYNIC_SINT_COUNT]; + atomic_t sint_to_gsi[HV_SYNIC_SINT_COUNT]; + DECLARE_BITMAP(auto_eoi_bitmap, 256); + DECLARE_BITMAP(vec_bitmap, 256); + bool active; +}; + /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { u64 hv_vapic; s64 runtime_offset; + struct kvm_vcpu_hv_synic synic; + struct kvm_hyperv_exit exit; + struct kvm_vcpu_hv_stimer stimer[HV_SYNIC_STIMER_COUNT]; + DECLARE_BITMAP(stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); }; struct kvm_vcpu_arch { @@ -400,7 +458,8 @@ struct kvm_vcpu_arch { u64 efer; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ - u64 eoi_exit_bitmap[4]; + bool apicv_active; + DECLARE_BITMAP(ioapic_handled_vectors, 256); unsigned long apic_attention; int32_t apic_arb_prio; int mp_state; @@ -589,7 +648,7 @@ struct kvm_lpage_info { }; struct kvm_arch_memory_slot { - unsigned long *rmap[KVM_NR_PAGE_SIZES]; + struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES]; struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; }; @@ -831,10 +890,11 @@ struct kvm_x86_ops { void (*enable_nmi_window)(struct kvm_vcpu *vcpu); void (*enable_irq_window)(struct kvm_vcpu *vcpu); void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); - int (*cpu_uses_apicv)(struct kvm_vcpu *vcpu); + bool (*get_enable_apicv)(void); + void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr); void (*hwapic_isr_update)(struct kvm *kvm, int isr); - void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu); + void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); @@ -1086,6 +1146,8 @@ gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); +void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu); + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code, @@ -1231,6 +1293,9 @@ u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc); unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu); bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip); +void kvm_make_mclock_inprogress_request(struct kvm *kvm); +void kvm_make_scan_ioapic_request(struct kvm *kvm); + void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, struct kvm_async_pf *work); void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 34e62b1dcfce..1e1b07a5a738 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_MICROCODE_H #define _ASM_X86_MICROCODE_H +#include <asm/cpu.h> #include <linux/earlycpio.h> #define native_rdmsr(msr, val1, val2) \ @@ -95,14 +96,14 @@ static inline void __exit exit_amd_microcode(void) {} /* * In early loading microcode phase on BSP, boot_cpu_data is not set up yet. - * x86_vendor() gets vendor id for BSP. + * x86_cpuid_vendor() gets vendor id for BSP. * * In 32 bit AP case, accessing boot_cpu_data needs linear address. To simplify - * coding, we still use x86_vendor() to get vendor id for AP. + * coding, we still use x86_cpuid_vendor() to get vendor id for AP. * - * x86_vendor() gets vendor information directly from CPUID. + * x86_cpuid_vendor() gets vendor information directly from CPUID. */ -static inline int x86_vendor(void) +static inline int x86_cpuid_vendor(void) { u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; @@ -118,40 +119,14 @@ static inline int x86_vendor(void) return X86_VENDOR_UNKNOWN; } -static inline unsigned int __x86_family(unsigned int sig) -{ - unsigned int x86; - - x86 = (sig >> 8) & 0xf; - - if (x86 == 0xf) - x86 += (sig >> 20) & 0xff; - - return x86; -} - -static inline unsigned int x86_family(void) +static inline unsigned int x86_cpuid_family(void) { u32 eax = 0x00000001; u32 ebx, ecx = 0, edx; native_cpuid(&eax, &ebx, &ecx, &edx); - return __x86_family(eax); -} - -static inline unsigned int x86_model(unsigned int sig) -{ - unsigned int x86, model; - - x86 = __x86_family(sig); - - model = (sig >> 4) & 0xf; - - if (x86 == 0x6 || x86 == 0xf) - model += ((sig >> 16) & 0xf) << 4; - - return model; + return x86_family(eax); } #ifdef CONFIG_MICROCODE diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index 93724cc62177..eb4b09b41df5 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -1,7 +1,13 @@ #ifndef _ASM_X86_MSI_H #define _ASM_X86_MSI_H #include <asm/hw_irq.h> +#include <asm/irqdomain.h> typedef struct irq_alloc_info msi_alloc_info_t; +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg); + +void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc); + #endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 690b4027e17c..b05402ef3b84 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -321,6 +321,7 @@ #define MSR_F15H_PERF_CTR 0xc0010201 #define MSR_F15H_NB_PERF_CTL 0xc0010240 #define MSR_F15H_NB_PERF_CTR 0xc0010241 +#define MSR_F15H_IC_CFG 0xc0011021 /* Fam 10h MSRs */ #define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h new file mode 100644 index 000000000000..7567225747d8 --- /dev/null +++ b/arch/x86/include/asm/msr-trace.h @@ -0,0 +1,57 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM msr + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE msr-trace + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/ + +#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MSR_H + +#include <linux/tracepoint.h> + +/* + * Tracing for x86 model specific registers. Directly maps to the + * RDMSR/WRMSR instructions. + */ + +DECLARE_EVENT_CLASS(msr_trace_class, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed), + TP_STRUCT__entry( + __field( unsigned, msr ) + __field( u64, val ) + __field( int, failed ) + ), + TP_fast_assign( + __entry->msr = msr; + __entry->val = val; + __entry->failed = failed; + ), + TP_printk("%x, value %llx%s", + __entry->msr, + __entry->val, + __entry->failed ? " #GP" : "") +); + +DEFINE_EVENT(msr_trace_class, read_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, write_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, rdpmc, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +#endif /* _TRACE_MSR_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 77d8b284e4a7..93fb7c1cffda 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -32,6 +32,16 @@ struct msr_regs_info { int err; }; +struct saved_msr { + bool valid; + struct msr_info info; +}; + +struct saved_msrs { + unsigned int num; + struct saved_msr *array; +}; + static inline unsigned long long native_read_tscp(unsigned int *aux) { unsigned long low, high; @@ -57,11 +67,34 @@ static inline unsigned long long native_read_tscp(unsigned int *aux) #define EAX_EDX_RET(val, low, high) "=A" (val) #endif +#ifdef CONFIG_TRACEPOINTS +/* + * Be very careful with includes. This header is prone to include loops. + */ +#include <asm/atomic.h> +#include <linux/tracepoint-defs.h> + +extern struct tracepoint __tracepoint_read_msr; +extern struct tracepoint __tracepoint_write_msr; +extern struct tracepoint __tracepoint_rdpmc; +#define msr_tracepoint_active(t) static_key_false(&(t).key) +extern void do_trace_write_msr(unsigned msr, u64 val, int failed); +extern void do_trace_read_msr(unsigned msr, u64 val, int failed); +extern void do_trace_rdpmc(unsigned msr, u64 val, int failed); +#else +#define msr_tracepoint_active(t) false +static inline void do_trace_write_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_read_msr(unsigned msr, u64 val, int failed) {} +static inline void do_trace_rdpmc(unsigned msr, u64 val, int failed) {} +#endif + static inline unsigned long long native_read_msr(unsigned int msr) { DECLARE_ARGS(val, low, high); asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } @@ -78,6 +111,8 @@ static inline unsigned long long native_read_msr_safe(unsigned int msr, _ASM_EXTABLE(2b, 3b) : [err] "=r" (*err), EAX_EDX_RET(val, low, high) : "c" (msr), [fault] "i" (-EIO)); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err); return EAX_EDX_VAL(val, low, high); } @@ -85,6 +120,8 @@ static inline void native_write_msr(unsigned int msr, unsigned low, unsigned high) { asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), 0); } /* Can be uninlined because referenced by paravirt */ @@ -102,6 +139,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr, : "c" (msr), "0" (low), "d" (high), [fault] "i" (-EIO) : "memory"); + if (msr_tracepoint_active(__tracepoint_read_msr)) + do_trace_write_msr(msr, ((u64)high << 32 | low), err); return err; } @@ -160,6 +199,8 @@ static inline unsigned long long native_read_pmc(int counter) DECLARE_ARGS(val, low, high); asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter)); + if (msr_tracepoint_active(__tracepoint_rdpmc)) + do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0); return EAX_EDX_VAL(val, low, high); } @@ -190,7 +231,7 @@ static inline void wrmsr(unsigned msr, unsigned low, unsigned high) static inline void wrmsrl(unsigned msr, u64 val) { - native_write_msr(msr, (u32)val, (u32)(val >> 32)); + native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32)); } /* wrmsr with exception handling */ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index cc071c6f7d4d..7bd0099384ca 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -5,9 +5,9 @@ #include <linux/types.h> /* PAGE_SHIFT determines the page size */ -#define PAGE_SHIFT 12 -#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) -#define PAGE_MASK (~(PAGE_SIZE-1)) +#define PAGE_SHIFT 12 +#define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) +#define PAGE_MASK (~(PAGE_SIZE-1)) #define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT) #define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1)) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index c759b3cca663..f6192502149e 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -291,15 +291,6 @@ static inline void slow_down_io(void) #endif } -#ifdef CONFIG_SMP -static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip, - unsigned long start_esp) -{ - PVOP_VCALL3(pv_apic_ops.startup_ipi_hook, - phys_apicid, start_eip, start_esp); -} -#endif - static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { @@ -381,23 +372,6 @@ static inline void pte_update(struct mm_struct *mm, unsigned long addr, { PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep); } -static inline void pmd_update(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) -{ - PVOP_VCALL3(pv_mmu_ops.pmd_update, mm, addr, pmdp); -} - -static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) -{ - PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep); -} - -static inline void pmd_update_defer(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp) -{ - PVOP_VCALL3(pv_mmu_ops.pmd_update_defer, mm, addr, pmdp); -} static inline pte_t __pte(pteval_t val) { @@ -928,23 +902,11 @@ extern void default_banner(void); call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) -#define USERGS_SYSRET32 \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32)) - #ifdef CONFIG_X86_32 #define GET_CR0_INTO_EAX \ push %ecx; push %edx; \ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \ pop %edx; pop %ecx - -#define ENABLE_INTERRUPTS_SYSEXIT \ - PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit), \ - CLBR_NONE, \ - jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit)) - - #else /* !CONFIG_X86_32 */ /* diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 3d44191185f8..77db5616a473 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -162,15 +162,6 @@ struct pv_cpu_ops { u64 (*read_pmc)(int counter); -#ifdef CONFIG_X86_32 - /* - * Atomically enable interrupts and return to userspace. This - * is only used in 32-bit kernels. 64-bit kernels use - * usergs_sysret32 instead. - */ - void (*irq_enable_sysexit)(void); -#endif - /* * Switch to usermode gs and return to 64-bit usermode using * sysret. Only used in 64-bit kernels to return to 64-bit @@ -179,14 +170,6 @@ struct pv_cpu_ops { */ void (*usergs_sysret64)(void); - /* - * Switch to usermode gs and return to 32-bit usermode using - * sysret. Used to return to 32-on-64 compat processes. - * Other usermode register state, including %esp, must already - * be restored. - */ - void (*usergs_sysret32)(void); - /* Normal iret. Jump to this with the standard iret stack frame set up. */ void (*iret)(void); @@ -220,14 +203,6 @@ struct pv_irq_ops { #endif }; -struct pv_apic_ops { -#ifdef CONFIG_X86_LOCAL_APIC - void (*startup_ipi_hook)(int phys_apicid, - unsigned long start_eip, - unsigned long start_esp); -#endif -}; - struct pv_mmu_ops { unsigned long (*read_cr2)(void); void (*write_cr2)(unsigned long); @@ -279,12 +254,6 @@ struct pv_mmu_ops { pmd_t *pmdp, pmd_t pmdval); void (*pte_update)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); - void (*pte_update_defer)(struct mm_struct *mm, - unsigned long addr, pte_t *ptep); - void (*pmd_update)(struct mm_struct *mm, unsigned long addr, - pmd_t *pmdp); - void (*pmd_update_defer)(struct mm_struct *mm, - unsigned long addr, pmd_t *pmdp); pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr, pte_t *ptep); @@ -359,7 +328,6 @@ struct paravirt_patch_template { struct pv_time_ops pv_time_ops; struct pv_cpu_ops pv_cpu_ops; struct pv_irq_ops pv_irq_ops; - struct pv_apic_ops pv_apic_ops; struct pv_mmu_ops pv_mmu_ops; struct pv_lock_ops pv_lock_ops; }; @@ -369,7 +337,6 @@ extern struct pv_init_ops pv_init_ops; extern struct pv_time_ops pv_time_ops; extern struct pv_cpu_ops pv_cpu_ops; extern struct pv_irq_ops pv_irq_ops; -extern struct pv_apic_ops pv_apic_ops; extern struct pv_mmu_ops pv_mmu_ops; extern struct pv_lock_ops pv_lock_ops; @@ -407,10 +374,8 @@ extern struct pv_lock_ops pv_lock_ops; __visible extern const char start_##ops##_##name[], end_##ops##_##name[]; \ asm(NATIVE_LABEL("start_", ops, name) code NATIVE_LABEL("end_", ops, name)) -unsigned paravirt_patch_nop(void); unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len); unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len); -unsigned paravirt_patch_ignore(unsigned len); unsigned paravirt_patch_call(void *insnbuf, const void *target, u16 tgt_clobbers, unsigned long addr, u16 site_clobbers, diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 6ec0c8b2e9df..d3eee663c41f 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -69,9 +69,6 @@ extern struct mm_struct *pgd_page_get_mm(struct page *page); #define pmd_clear(pmd) native_pmd_clear(pmd) #define pte_update(mm, addr, ptep) do { } while (0) -#define pte_update_defer(mm, addr, ptep) do { } while (0) -#define pmd_update(mm, addr, ptep) do { } while (0) -#define pmd_update_defer(mm, addr, ptep) do { } while (0) #define pgd_val(x) native_pgd_val(x) #define __pgd(x) native_make_pgd(x) @@ -731,14 +728,9 @@ static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr, * updates should either be sets, clears, or set_pte_atomic for P->P * transitions, which means this hook should only be called for user PTEs. * This hook implies a P->P protection or access change has taken place, which - * requires a subsequent TLB flush. The notification can optionally be delayed - * until the TLB flush event by using the pte_update_defer form of the - * interface, but care must be taken to assure that the flush happens while - * still holding the same page table lock so that the shadow and primary pages - * do not become out of sync on SMP. + * requires a subsequent TLB flush. */ #define pte_update(mm, addr, ptep) do { } while (0) -#define pte_update_defer(mm, addr, ptep) do { } while (0) #endif /* @@ -830,9 +822,7 @@ static inline int pmd_write(pmd_t pmd) static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - pmd_t pmd = native_pmdp_get_and_clear(pmdp); - pmd_update(mm, addr, pmdp); - return pmd; + return native_pmdp_get_and_clear(pmdp); } #define __HAVE_ARCH_PMDP_SET_WRPROTECT @@ -840,7 +830,6 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp); - pmd_update(mm, addr, pmdp); } /* diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 7a6bed5c08bc..fdcc04020636 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -4,6 +4,15 @@ #include <linux/clocksource.h> #include <asm/pvclock-abi.h> +#ifdef CONFIG_KVM_GUEST +extern struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void); +#else +static inline struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return NULL; +} +#endif + /* some helper functions for xen and kvm pv clock sources */ cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); @@ -91,10 +100,5 @@ struct pvclock_vsyscall_time_info { } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) -#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1) - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size); -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu); #endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index b002e711ba88..9f92c180ed2f 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -1,6 +1,65 @@ #ifndef __ASM_QSPINLOCK_PARAVIRT_H #define __ASM_QSPINLOCK_PARAVIRT_H +/* + * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit + * registers. For i386, however, only 1 32-bit register needs to be saved + * and restored. So an optimized version of __pv_queued_spin_unlock() is + * hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit. + */ +#ifdef CONFIG_64BIT + +PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath); +#define __pv_queued_spin_unlock __pv_queued_spin_unlock +#define PV_UNLOCK "__raw_callee_save___pv_queued_spin_unlock" +#define PV_UNLOCK_SLOWPATH "__raw_callee_save___pv_queued_spin_unlock_slowpath" + +/* + * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock + * which combines the registers saving trunk and the body of the following + * C code: + * + * void __pv_queued_spin_unlock(struct qspinlock *lock) + * { + * struct __qspinlock *l = (void *)lock; + * u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); + * + * if (likely(lockval == _Q_LOCKED_VAL)) + * return; + * pv_queued_spin_unlock_slowpath(lock, lockval); + * } + * + * For x86-64, + * rdi = lock (first argument) + * rsi = lockval (second argument) + * rdx = internal variable (set to 0) + */ +asm (".pushsection .text;" + ".globl " PV_UNLOCK ";" + ".align 4,0x90;" + PV_UNLOCK ": " + "push %rdx;" + "mov $0x1,%eax;" + "xor %edx,%edx;" + "lock cmpxchg %dl,(%rdi);" + "cmp $0x1,%al;" + "jne .slowpath;" + "pop %rdx;" + "ret;" + ".slowpath: " + "push %rsi;" + "movzbl %al,%esi;" + "call " PV_UNLOCK_SLOWPATH ";" + "pop %rsi;" + "pop %rdx;" + "ret;" + ".size " PV_UNLOCK ", .-" PV_UNLOCK ";" + ".popsection"); + +#else /* CONFIG_64BIT */ + +extern void __pv_queued_spin_unlock(struct qspinlock *lock); PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock); +#endif /* CONFIG_64BIT */ #endif diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index a82c4f1b4d83..2cb1cc253d51 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -25,5 +25,6 @@ void __noreturn machine_real_restart(unsigned int type); typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); void nmi_shootdown_cpus(nmi_shootdown_cb callback); +void run_crash_ipi_callback(struct pt_regs *regs); #endif /* _ASM_X86_REBOOT_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 222a6a3ca2b5..dfcf0727623b 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -21,15 +21,6 @@ extern int smp_num_siblings; extern unsigned int num_processors; -static inline bool cpu_has_ht_siblings(void) -{ - bool has_siblings = false; -#ifdef CONFIG_SMP - has_siblings = cpu_has_ht && smp_num_siblings > 1; -#endif - return has_siblings; -} - DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); /* cpus sharing the last level cache: */ @@ -74,9 +65,6 @@ struct smp_ops { extern void set_cpu_sibling_map(int cpu); #ifdef CONFIG_SMP -#ifndef CONFIG_PARAVIRT -#define startup_ipi_hook(phys_apicid, start_eip, start_esp) do { } while (0) -#endif extern struct smp_ops smp_ops; static inline void smp_send_stop(void) diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index d1793f06854d..8e9dbe7b73a1 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -15,6 +15,7 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4; u64 misc_enable; bool misc_enable_saved; + struct saved_msrs saved_msrs; struct desc_ptr gdt_desc; struct desc_ptr idt; u16 ldt; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 7ebf0ebe4e68..6136a18152af 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -24,6 +24,7 @@ struct saved_context { unsigned long cr0, cr2, cr3, cr4, cr8; u64 misc_enable; bool misc_enable_saved; + struct saved_msrs saved_msrs; unsigned long efer; u16 gdt_pad; /* Unused */ struct desc_ptr gdt_desc; diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 09b1b0ab94b7..660458af425d 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -745,5 +745,14 @@ copy_to_user(void __user *to, const void *from, unsigned long n) #undef __copy_from_user_overflow #undef __copy_to_user_overflow +/* + * We rely on the nested NMI work to allow atomic faults from the NMI path; the + * nested NMI paths are careful to preserve CR2. + * + * Caller must use pagefault_enable/disable, or run in interrupt context, + * and also do a uaccess_ok() check + */ +#define __copy_from_user_nmi __copy_from_user_inatomic + #endif /* _ASM_X86_UACCESS_H */ diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index 756de9190aec..deabaf9759b6 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -22,6 +22,7 @@ struct vdso_image { long sym_vvar_page; long sym_hpet_page; + long sym_pvclock_page; long sym_VDSO32_NOTE_MASK; long sym___kernel_sigreturn; long sym___kernel_rt_sigreturn; diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index cd0fc0cc78bc..1ae89a2721d6 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -82,13 +82,11 @@ struct x86_init_paging { * struct x86_init_timers - platform specific timer setup * @setup_perpcu_clockev: set up the per cpu clock event device for the * boot cpu - * @tsc_pre_init: platform function called before TSC init * @timer_init: initialize the platform timer (default PIT/HPET) * @wallclock_init: init the wallclock device */ struct x86_init_timers { void (*setup_percpu_clockev)(void); - void (*tsc_pre_init)(void); void (*timer_init)(void); void (*wallclock_init)(void); }; diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 4c20dd333412..3bcdcc84259d 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -310,10 +310,10 @@ HYPERVISOR_mca(struct xen_mc *mc_op) } static inline int -HYPERVISOR_dom0_op(struct xen_platform_op *platform_op) +HYPERVISOR_platform_op(struct xen_platform_op *op) { - platform_op->interface_version = XENPF_INTERFACE_VERSION; - return _hypercall1(int, dom0_op, platform_op); + op->interface_version = XENPF_INTERFACE_VERSION; + return _hypercall1(int, platform_op, op); } static inline int diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h index 5a08bc8bff33..c54beb44c4c1 100644 --- a/arch/x86/include/asm/xor_32.h +++ b/arch/x86/include/asm/xor_32.h @@ -553,7 +553,7 @@ do { \ if (cpu_has_xmm) { \ xor_speed(&xor_block_pIII_sse); \ xor_speed(&xor_block_sse_pf64); \ - } else if (cpu_has_mmx) { \ + } else if (boot_cpu_has(X86_FEATURE_MMX)) { \ xor_speed(&xor_block_pII_mmx); \ xor_speed(&xor_block_p5_mmx); \ } else { \ diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h index 040d4083c24f..7956412d09bd 100644 --- a/arch/x86/include/uapi/asm/hyperv.h +++ b/arch/x86/include/uapi/asm/hyperv.h @@ -269,4 +269,96 @@ typedef struct _HV_REFERENCE_TSC_PAGE { #define HV_SYNIC_SINT_AUTO_EOI (1ULL << 17) #define HV_SYNIC_SINT_VECTOR_MASK (0xFF) +#define HV_SYNIC_STIMER_COUNT (4) + +/* Define synthetic interrupt controller message constants. */ +#define HV_MESSAGE_SIZE (256) +#define HV_MESSAGE_PAYLOAD_BYTE_COUNT (240) +#define HV_MESSAGE_PAYLOAD_QWORD_COUNT (30) + +/* Define hypervisor message types. */ +enum hv_message_type { + HVMSG_NONE = 0x00000000, + + /* Memory access messages. */ + HVMSG_UNMAPPED_GPA = 0x80000000, + HVMSG_GPA_INTERCEPT = 0x80000001, + + /* Timer notification messages. */ + HVMSG_TIMER_EXPIRED = 0x80000010, + + /* Error messages. */ + HVMSG_INVALID_VP_REGISTER_VALUE = 0x80000020, + HVMSG_UNRECOVERABLE_EXCEPTION = 0x80000021, + HVMSG_UNSUPPORTED_FEATURE = 0x80000022, + + /* Trace buffer complete messages. */ + HVMSG_EVENTLOG_BUFFERCOMPLETE = 0x80000040, + + /* Platform-specific processor intercept messages. */ + HVMSG_X64_IOPORT_INTERCEPT = 0x80010000, + HVMSG_X64_MSR_INTERCEPT = 0x80010001, + HVMSG_X64_CPUID_INTERCEPT = 0x80010002, + HVMSG_X64_EXCEPTION_INTERCEPT = 0x80010003, + HVMSG_X64_APIC_EOI = 0x80010004, + HVMSG_X64_LEGACY_FP_ERROR = 0x80010005 +}; + +/* Define synthetic interrupt controller message flags. */ +union hv_message_flags { + __u8 asu8; + struct { + __u8 msg_pending:1; + __u8 reserved:7; + }; +}; + +/* Define port identifier type. */ +union hv_port_id { + __u32 asu32; + struct { + __u32 id:24; + __u32 reserved:8; + } u; +}; + +/* Define synthetic interrupt controller message header. */ +struct hv_message_header { + __u32 message_type; + __u8 payload_size; + union hv_message_flags message_flags; + __u8 reserved[2]; + union { + __u64 sender; + union hv_port_id port; + }; +}; + +/* Define synthetic interrupt controller message format. */ +struct hv_message { + struct hv_message_header header; + union { + __u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; + } u; +}; + +/* Define the synthetic interrupt message page layout. */ +struct hv_message_page { + struct hv_message sint_message[HV_SYNIC_SINT_COUNT]; +}; + +/* Define timer message payload structure. */ +struct hv_timer_message_payload { + __u32 timer_index; + __u32 reserved; + __u64 expiration_time; /* When the timer expired */ + __u64 delivery_time; /* When the message was delivered */ +}; + +#define HV_STIMER_ENABLE (1ULL << 0) +#define HV_STIMER_PERIODIC (1ULL << 1) +#define HV_STIMER_LAZY (1ULL << 2) +#define HV_STIMER_AUTOENABLE (1ULL << 3) +#define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) + #endif diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h index 03429da2fa80..2184943341bf 100644 --- a/arch/x86/include/uapi/asm/mce.h +++ b/arch/x86/include/uapi/asm/mce.h @@ -16,7 +16,7 @@ struct mce { __u8 cpuvendor; /* cpu vendor as encoded in system.h */ __u8 inject_flags; /* software inject flags */ __u8 severity; - __u8 usable_addr; + __u8 pad; __u32 cpuid; /* CPUID 1 EAX */ __u8 cs; /* code segment */ __u8 bank; /* machine check bank */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 2f69e3b184f6..8a5cddac7d44 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -82,6 +82,12 @@ physid_mask_t phys_cpu_present_map; static unsigned int disabled_cpu_apicid __read_mostly = BAD_APICID; /* + * This variable controls which CPUs receive external NMIs. By default, + * external NMIs are delivered only to the BSP. + */ +static int apic_extnmi = APIC_EXTNMI_BSP; + +/* * Map cpu index to physical APIC ID */ DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID); @@ -1161,6 +1167,8 @@ void __init init_bsp_APIC(void) value = APIC_DM_NMI; if (!lapic_is_integrated()) /* 82489DX */ value |= APIC_LVT_LEVEL_TRIGGER; + if (apic_extnmi == APIC_EXTNMI_NONE) + value |= APIC_LVT_MASKED; apic_write(APIC_LVT1, value); } @@ -1378,9 +1386,11 @@ void setup_local_APIC(void) apic_write(APIC_LVT0, value); /* - * only the BP should see the LINT1 NMI signal, obviously. + * Only the BSP sees the LINT1 NMI signal by default. This can be + * modified by apic_extnmi= boot option. */ - if (!cpu) + if ((!cpu && apic_extnmi != APIC_EXTNMI_NONE) || + apic_extnmi == APIC_EXTNMI_ALL) value = APIC_DM_NMI; else value = APIC_DM_NMI | APIC_LVT_MASKED; @@ -2270,6 +2280,7 @@ static struct { unsigned int apic_tmict; unsigned int apic_tdcr; unsigned int apic_thmr; + unsigned int apic_cmci; } apic_pm_state; static int lapic_suspend(void) @@ -2299,6 +2310,10 @@ static int lapic_suspend(void) if (maxlvt >= 5) apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_pm_state.apic_cmci = apic_read(APIC_LVTCMCI); +#endif local_irq_save(flags); disable_local_APIC(); @@ -2355,10 +2370,14 @@ static void lapic_resume(void) apic_write(APIC_SPIV, apic_pm_state.apic_spiv); apic_write(APIC_LVT0, apic_pm_state.apic_lvt0); apic_write(APIC_LVT1, apic_pm_state.apic_lvt1); -#if defined(CONFIG_X86_MCE_INTEL) +#ifdef CONFIG_X86_THERMAL_VECTOR if (maxlvt >= 5) apic_write(APIC_LVTTHMR, apic_pm_state.apic_thmr); #endif +#ifdef CONFIG_X86_MCE_INTEL + if (maxlvt >= 6) + apic_write(APIC_LVTCMCI, apic_pm_state.apic_cmci); +#endif if (maxlvt >= 4) apic_write(APIC_LVTPC, apic_pm_state.apic_lvtpc); apic_write(APIC_LVTT, apic_pm_state.apic_lvtt); @@ -2548,3 +2567,23 @@ static int __init apic_set_disabled_cpu_apicid(char *arg) return 0; } early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid); + +static int __init apic_set_extnmi(char *arg) +{ + if (!arg) + return -EINVAL; + + if (!strncmp("all", arg, 3)) + apic_extnmi = APIC_EXTNMI_ALL; + else if (!strncmp("none", arg, 4)) + apic_extnmi = APIC_EXTNMI_NONE; + else if (!strncmp("bsp", arg, 3)) + apic_extnmi = APIC_EXTNMI_BSP; + else { + pr_warn("Unknown external NMI delivery mode `%s' ignored\n", arg); + return -EINVAL; + } + + return 0; +} +early_param("apic_extnmi", apic_set_extnmi); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index f92ab36979a2..9968f30cca3e 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -185,6 +185,7 @@ static struct apic apic_flat = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = flat_send_IPI_mask, .send_IPI_mask_allbutself = flat_send_IPI_mask_allbutself, .send_IPI_allbutself = flat_send_IPI_allbutself, @@ -230,17 +231,6 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return 0; } -static void physflat_send_IPI_mask(const struct cpumask *cpumask, int vector) -{ - default_send_IPI_mask_sequence_phys(cpumask, vector); -} - -static void physflat_send_IPI_mask_allbutself(const struct cpumask *cpumask, - int vector) -{ - default_send_IPI_mask_allbutself_phys(cpumask, vector); -} - static void physflat_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -248,7 +238,7 @@ static void physflat_send_IPI_allbutself(int vector) static void physflat_send_IPI_all(int vector) { - physflat_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int physflat_probe(void) @@ -292,8 +282,9 @@ static struct apic apic_physflat = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = physflat_send_IPI_mask, - .send_IPI_mask_allbutself = physflat_send_IPI_mask_allbutself, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, + .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_phys, .send_IPI_allbutself = physflat_send_IPI_allbutself, .send_IPI_all = physflat_send_IPI_all, .send_IPI_self = apic_send_IPI_self, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 0d96749cfcac..331a7a07c48f 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -30,6 +30,7 @@ #include <asm/e820.h> static void noop_init_apic_ldr(void) { } +static void noop_send_IPI(int cpu, int vector) { } static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_allbutself(int vector) { } @@ -144,6 +145,7 @@ struct apic apic_noop = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = noop_send_IPI, .send_IPI_mask = noop_send_IPI_mask, .send_IPI_mask_allbutself = noop_send_IPI_mask_allbutself, .send_IPI_allbutself = noop_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 2bd2292a316d..c80c02c6ec49 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -273,6 +273,7 @@ static const struct apic apic_numachip1 __refconst = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, .send_IPI_allbutself = numachip_send_IPI_allbutself, @@ -324,6 +325,7 @@ static const struct apic apic_numachip2 __refconst = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = numachip_send_IPI_one, .send_IPI_mask = numachip_send_IPI_mask, .send_IPI_mask_allbutself = numachip_send_IPI_mask_allbutself, .send_IPI_allbutself = numachip_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 971cf8875939..cf9bd896c12d 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -96,11 +96,6 @@ static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -static inline void bigsmp_send_IPI_mask(const struct cpumask *mask, int vector) -{ - default_send_IPI_mask_sequence_phys(mask, vector); -} - static void bigsmp_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -108,7 +103,7 @@ static void bigsmp_send_IPI_allbutself(int vector) static void bigsmp_send_IPI_all(int vector) { - bigsmp_send_IPI_mask(cpu_online_mask, vector); + default_send_IPI_mask_sequence_phys(cpu_online_mask, vector); } static int dmi_bigsmp; /* can be set by dmi scanners */ @@ -180,7 +175,8 @@ static struct apic apic_bigsmp = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, - .send_IPI_mask = bigsmp_send_IPI_mask, + .send_IPI = default_send_IPI_single_phys, + .send_IPI_mask = default_send_IPI_mask_sequence_phys, .send_IPI_mask_allbutself = NULL, .send_IPI_allbutself = bigsmp_send_IPI_allbutself, .send_IPI_all = bigsmp_send_IPI_all, diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index 62071569bd50..eb45fc9b6124 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -18,6 +18,16 @@ #include <asm/proto.h> #include <asm/ipi.h> +void default_send_IPI_single_phys(int cpu, int vector) +{ + unsigned long flags; + + local_irq_save(flags); + __default_send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, cpu), + vector, APIC_DEST_PHYSICAL); + local_irq_restore(flags); +} + void default_send_IPI_mask_sequence_phys(const struct cpumask *mask, int vector) { unsigned long query_cpu; @@ -55,6 +65,14 @@ void default_send_IPI_mask_allbutself_phys(const struct cpumask *mask, local_irq_restore(flags); } +/* + * Helper function for APICs which insist on cpumasks + */ +void default_send_IPI_single(int cpu, int vector) +{ + apic->send_IPI_mask(cpumask_of(cpu), vector); +} + #ifdef CONFIG_X86_32 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 5f1feb6854af..ade25320df96 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -96,8 +96,8 @@ static irq_hw_number_t pci_msi_get_hwirq(struct msi_domain_info *info, return arg->msi_hwirq; } -static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, - int nvec, msi_alloc_info_t *arg) +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg) { struct pci_dev *pdev = to_pci_dev(dev); struct msi_desc *desc = first_pci_msi_entry(pdev); @@ -113,11 +113,13 @@ static int pci_msi_prepare(struct irq_domain *domain, struct device *dev, return 0; } +EXPORT_SYMBOL_GPL(pci_msi_prepare); -static void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +void pci_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { arg->msi_hwirq = pci_msi_domain_calc_hwirq(arg->msi_dev, desc); } +EXPORT_SYMBOL_GPL(pci_msi_set_desc); static struct msi_domain_ops pci_msi_domain_ops = { .get_hwirq = pci_msi_get_hwirq, diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 7694ae6c1199..f316e34abb42 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -105,6 +105,7 @@ static struct apic apic_default = { .cpu_mask_to_apicid_and = flat_cpu_mask_to_apicid_and, + .send_IPI = default_send_IPI_single, .send_IPI_mask = default_send_IPI_mask_logical, .send_IPI_mask_allbutself = default_send_IPI_mask_allbutself_logical, .send_IPI_allbutself = default_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 861bc59c8f25..908cb37da171 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -29,6 +29,7 @@ struct apic_chip_data { }; struct irq_domain *x86_vector_domain; +EXPORT_SYMBOL_GPL(x86_vector_domain); static DEFINE_RAW_SPINLOCK(vector_lock); static cpumask_var_t vector_cpumask; static struct irq_chip lapic_controller; @@ -66,6 +67,7 @@ struct irq_cfg *irqd_cfg(struct irq_data *irq_data) return data ? &data->cfg : NULL; } +EXPORT_SYMBOL_GPL(irqd_cfg); struct irq_cfg *irq_cfg(unsigned int irq) { diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index cc8311c4d298..aca8b75c1552 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -23,6 +23,14 @@ static inline u32 x2apic_cluster(int cpu) return per_cpu(x86_cpu_to_logical_apicid, cpu) >> 16; } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_logical_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -266,6 +274,7 @@ static struct apic apic_x2apic_cluster = { .cpu_mask_to_apicid_and = x2apic_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 662e9150ea6f..a1242e2c12e6 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -36,6 +36,14 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id) return x2apic_enabled() && (x2apic_phys || x2apic_fadt_phys()); } +static void x2apic_send_IPI(int cpu, int vector) +{ + u32 dest = per_cpu(x86_cpu_to_apicid, cpu); + + x2apic_wrmsr_fence(); + __x2apic_send_IPI_dest(dest, vector, APIC_DEST_PHYSICAL); +} + static void __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest) { @@ -122,6 +130,7 @@ static struct apic apic_x2apic_phys = { .cpu_mask_to_apicid_and = default_cpu_mask_to_apicid_and, + .send_IPI = x2apic_send_IPI, .send_IPI_mask = x2apic_send_IPI_mask, .send_IPI_mask_allbutself = x2apic_send_IPI_mask_allbutself, .send_IPI_allbutself = x2apic_send_IPI_allbutself, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 4a139465f1d4..d760c6bb37b5 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -406,6 +406,7 @@ static struct apic __refdata apic_x2apic_uv_x = { .cpu_mask_to_apicid_and = uv_cpu_mask_to_apicid_and, + .send_IPI = uv_send_IPI_one, .send_IPI_mask = uv_send_IPI_mask, .send_IPI_mask_allbutself = uv_send_IPI_mask_allbutself, .send_IPI_allbutself = uv_send_IPI_allbutself, diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 439df975bc7a..84a7524b202c 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -65,9 +65,6 @@ void common(void) { OFFSET(PV_IRQ_irq_disable, pv_irq_ops, irq_disable); OFFSET(PV_IRQ_irq_enable, pv_irq_ops, irq_enable); OFFSET(PV_CPU_iret, pv_cpu_ops, iret); -#ifdef CONFIG_X86_32 - OFFSET(PV_CPU_irq_enable_sysexit, pv_cpu_ops, irq_enable_sysexit); -#endif OFFSET(PV_CPU_read_cr0, pv_cpu_ops, read_cr0); OFFSET(PV_MMU_read_cr2, pv_mmu_ops, read_cr2); #endif diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index d8f42f902a0f..f2edafb5f24e 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -23,7 +23,6 @@ int main(void) { #ifdef CONFIG_PARAVIRT OFFSET(PV_IRQ_adjust_exception_frame, pv_irq_ops, adjust_exception_frame); - OFFSET(PV_CPU_usergs_sysret32, pv_cpu_ops, usergs_sysret32); OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64); OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs); BLANK(); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index a8816b325162..e678ddeed030 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -304,7 +304,7 @@ static void amd_get_topology(struct cpuinfo_x86 *c) int cpu = smp_processor_id(); /* get information required for multi-node processors */ - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { u32 eax, ebx, ecx, edx; cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); @@ -678,9 +678,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c) * Disable it on the affected CPUs. */ if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) { - if (!rdmsrl_safe(0xc0011021, &value) && !(value & 0x1E)) { + if (!rdmsrl_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) { value |= 0x1E; - wrmsrl_safe(0xc0011021, value); + wrmsrl_safe(MSR_F15H_IC_CFG, value); } } } @@ -922,7 +922,7 @@ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) void set_dr_addr_mask(unsigned long mask, int dr) { - if (!cpu_has_bpext) + if (!boot_cpu_has(X86_FEATURE_BPEXT)) return; switch (dr) { diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index d8fba5c15fbd..ae20be6e483c 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -43,7 +43,7 @@ static void init_c3(struct cpuinfo_x86 *c) /* store Centaur Extended Feature Flags as * word 5 of the CPU capability bit array */ - c->x86_capability[5] = cpuid_edx(0xC0000001); + c->x86_capability[CPUID_C000_0001_EDX] = cpuid_edx(0xC0000001); } #ifdef CONFIG_X86_32 /* Cyrix III family needs CX8 & PGE explicitly enabled. */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c2b7522cbf35..37830de8f60a 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -581,14 +581,9 @@ void cpu_detect(struct cpuinfo_x86 *c) u32 junk, tfms, cap0, misc; cpuid(0x00000001, &tfms, &misc, &junk, &cap0); - c->x86 = (tfms >> 8) & 0xf; - c->x86_model = (tfms >> 4) & 0xf; - c->x86_mask = tfms & 0xf; - - if (c->x86 == 0xf) - c->x86 += (tfms >> 20) & 0xff; - if (c->x86 >= 0x6) - c->x86_model += ((tfms >> 16) & 0xf) << 4; + c->x86 = x86_family(tfms); + c->x86_model = x86_model(tfms); + c->x86_mask = x86_stepping(tfms); if (cap0 & (1<<19)) { c->x86_clflush_size = ((misc >> 8) & 0xff) * 8; @@ -599,50 +594,47 @@ void cpu_detect(struct cpuinfo_x86 *c) void get_cpu_cap(struct cpuinfo_x86 *c) { - u32 tfms, xlvl; - u32 ebx; + u32 eax, ebx, ecx, edx; /* Intel-defined flags: level 0x00000001 */ if (c->cpuid_level >= 0x00000001) { - u32 capability, excap; + cpuid(0x00000001, &eax, &ebx, &ecx, &edx); - cpuid(0x00000001, &tfms, &ebx, &excap, &capability); - c->x86_capability[0] = capability; - c->x86_capability[4] = excap; + c->x86_capability[CPUID_1_ECX] = ecx; + c->x86_capability[CPUID_1_EDX] = edx; } /* Additional Intel-defined flags: level 0x00000007 */ if (c->cpuid_level >= 0x00000007) { - u32 eax, ebx, ecx, edx; - cpuid_count(0x00000007, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[9] = ebx; + c->x86_capability[CPUID_7_0_EBX] = ebx; + + c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006); } /* Extended state features: level 0x0000000d */ if (c->cpuid_level >= 0x0000000d) { - u32 eax, ebx, ecx, edx; - cpuid_count(0x0000000d, 1, &eax, &ebx, &ecx, &edx); - c->x86_capability[10] = eax; + c->x86_capability[CPUID_D_1_EAX] = eax; } /* Additional Intel-defined flags: level 0x0000000F */ if (c->cpuid_level >= 0x0000000F) { - u32 eax, ebx, ecx, edx; /* QoS sub-leaf, EAX=0Fh, ECX=0 */ cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx); - c->x86_capability[11] = edx; + c->x86_capability[CPUID_F_0_EDX] = edx; + if (cpu_has(c, X86_FEATURE_CQM_LLC)) { /* will be overridden if occupancy monitoring exists */ c->x86_cache_max_rmid = ebx; /* QoS sub-leaf, EAX=0Fh, ECX=1 */ cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx); - c->x86_capability[12] = edx; + c->x86_capability[CPUID_F_1_EDX] = edx; + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) { c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; @@ -654,22 +646,24 @@ void get_cpu_cap(struct cpuinfo_x86 *c) } /* AMD-defined flags: level 0x80000001 */ - xlvl = cpuid_eax(0x80000000); - c->extended_cpuid_level = xlvl; + eax = cpuid_eax(0x80000000); + c->extended_cpuid_level = eax; - if ((xlvl & 0xffff0000) == 0x80000000) { - if (xlvl >= 0x80000001) { - c->x86_capability[1] = cpuid_edx(0x80000001); - c->x86_capability[6] = cpuid_ecx(0x80000001); + if ((eax & 0xffff0000) == 0x80000000) { + if (eax >= 0x80000001) { + cpuid(0x80000001, &eax, &ebx, &ecx, &edx); + + c->x86_capability[CPUID_8000_0001_ECX] = ecx; + c->x86_capability[CPUID_8000_0001_EDX] = edx; } } if (c->extended_cpuid_level >= 0x80000008) { - u32 eax = cpuid_eax(0x80000008); + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); c->x86_virt_bits = (eax >> 8) & 0xff; c->x86_phys_bits = eax & 0xff; - c->x86_capability[13] = cpuid_ebx(0x80000008); + c->x86_capability[CPUID_8000_0008_EBX] = ebx; } #ifdef CONFIG_X86_32 else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) @@ -679,6 +673,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) if (c->extended_cpuid_level >= 0x80000007) c->x86_power = cpuid_edx(0x80000007); + if (c->extended_cpuid_level >= 0x8000000a) + c->x86_capability[CPUID_8000_000A_EDX] = cpuid_edx(0x8000000a); + init_scattered_cpuid_features(c); } @@ -1185,7 +1182,7 @@ void syscall_init(void) * They both write to the same internal register. STAR allows to * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip. */ - wrmsrl(MSR_STAR, ((u64)__USER32_CS)<<48 | ((u64)__KERNEL_CS)<<32); + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); #ifdef CONFIG_IA32_EMULATION @@ -1443,7 +1440,9 @@ void cpu_init(void) printk(KERN_INFO "Initializing CPU#%d\n", cpu); - if (cpu_feature_enabled(X86_FEATURE_VME) || cpu_has_tsc || cpu_has_de) + if (cpu_feature_enabled(X86_FEATURE_VME) || + cpu_has_tsc || + boot_cpu_has(X86_FEATURE_DE)) cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); load_current_idt(); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 209ac1e7d1f0..565648bc1a0a 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -445,7 +445,8 @@ static void init_intel(struct cpuinfo_x86 *c) if (cpu_has_xmm2) set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC); - if (cpu_has_ds) { + + if (boot_cpu_has(X86_FEATURE_DS)) { unsigned int l1; rdmsr(MSR_IA32_MISC_ENABLE, l1, l2); if (!(l1 & (1<<11))) diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c index e38d338a6447..0b6c52388cf4 100644 --- a/arch/x86/kernel/cpu/intel_cacheinfo.c +++ b/arch/x86/kernel/cpu/intel_cacheinfo.c @@ -591,7 +591,7 @@ cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf) unsigned edx; if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { - if (cpu_has_topoext) + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) cpuid_count(0x8000001d, index, &eax.full, &ebx.full, &ecx.full, &edx); else @@ -637,7 +637,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) void init_amd_cacheinfo(struct cpuinfo_x86 *c) { - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { num_cache_leaves = find_num_cache_leaves(c); } else if (c->extended_cpuid_level >= 0x80000006) { if (cpuid_edx(0x80000006) & 0xf000) @@ -809,7 +809,7 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, struct cacheinfo *this_leaf; int i, sibling; - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { unsigned int apicid, nshared, first, last; this_leaf = this_cpu_ci->info_list + index; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 7e8a736d09db..a006f4cd792b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -114,7 +114,6 @@ static struct work_struct mce_work; static struct irq_work mce_irq_work; static void (*quirk_no_way_out)(int bank, struct mce *m, struct pt_regs *regs); -static int mce_usable_address(struct mce *m); /* * CPU/chipset specific EDAC code can register a notifier call here to print @@ -475,6 +474,28 @@ static void mce_report_event(struct pt_regs *regs) irq_work_queue(&mce_irq_work); } +/* + * Check if the address reported by the CPU is in a format we can parse. + * It would be possible to add code for most other cases, but all would + * be somewhat complicated (e.g. segment offset would require an instruction + * parser). So only support physical addresses up to page granuality for now. + */ +static int mce_usable_address(struct mce *m) +{ + if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) + return 0; + + /* Checks after this one are Intel-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 1; + + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) + return 0; + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) + return 0; + return 1; +} + static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -484,7 +505,7 @@ static int srao_decode_notifier(struct notifier_block *nb, unsigned long val, if (!mce) return NOTIFY_DONE; - if (mce->usable_addr && (mce->severity == MCE_AO_SEVERITY)) { + if (mce_usable_address(mce) && (mce->severity == MCE_AO_SEVERITY)) { pfn = mce->addr >> PAGE_SHIFT; memory_failure(pfn, MCE_VECTOR, 0); } @@ -522,10 +543,10 @@ static bool memory_error(struct mce *m) struct cpuinfo_x86 *c = &boot_cpu_data; if (c->x86_vendor == X86_VENDOR_AMD) { - /* - * coming soon - */ - return false; + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + return (xec == 0x0 || xec == 0x8); } else if (c->x86_vendor == X86_VENDOR_INTEL) { /* * Intel SDM Volume 3B - 15.9.2 Compound Error Codes @@ -567,7 +588,7 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); */ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) { - bool error_logged = false; + bool error_seen = false; struct mce m; int severity; int i; @@ -601,6 +622,8 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC))) continue; + error_seen = true; + mce_read_aux(&m, i); if (!(flags & MCP_TIMESTAMP)) @@ -608,27 +631,24 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) severity = mce_severity(&m, mca_cfg.tolerant, NULL, false); - /* - * In the cases where we don't have a valid address after all, - * do not add it into the ring buffer. - */ - if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) { - if (m.status & MCI_STATUS_ADDRV) { + if (severity == MCE_DEFERRED_SEVERITY && memory_error(&m)) + if (m.status & MCI_STATUS_ADDRV) m.severity = severity; - m.usable_addr = mce_usable_address(&m); - - if (!mce_gen_pool_add(&m)) - mce_schedule_work(); - } - } /* * Don't get the IP here because it's unlikely to * have anything to do with the actual error location. */ - if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) { - error_logged = true; + if (!(flags & MCP_DONTLOG) && !mca_cfg.dont_log_ce) mce_log(&m); + else if (mce_usable_address(&m)) { + /* + * Although we skipped logging this, we still want + * to take action. Add to the pool so the registered + * notifiers will see it. + */ + if (!mce_gen_pool_add(&m)) + mce_schedule_work(); } /* @@ -644,7 +664,7 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) sync_core(); - return error_logged; + return error_seen; } EXPORT_SYMBOL_GPL(machine_check_poll); @@ -931,23 +951,6 @@ reset: return ret; } -/* - * Check if the address reported by the CPU is in a format we can parse. - * It would be possible to add code for most other cases, but all would - * be somewhat complicated (e.g. segment offset would require an instruction - * parser). So only support physical addresses up to page granuality for now. - */ -static int mce_usable_address(struct mce *m) -{ - if (!(m->status & MCI_STATUS_MISCV) || !(m->status & MCI_STATUS_ADDRV)) - return 0; - if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) - return 0; - if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) - return 0; - return 1; -} - static void mce_clear_state(unsigned long *toclear) { int i; @@ -1100,7 +1103,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) /* assuming valid severity level != 0 */ m.severity = severity; - m.usable_addr = mce_usable_address(&m); mce_log(&m); diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b3e94ef461fd..faec7120c508 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -129,8 +129,8 @@ void __init load_ucode_bsp(void) if (!have_cpuid_p()) return; - vendor = x86_vendor(); - family = x86_family(); + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); switch (vendor) { case X86_VENDOR_INTEL: @@ -165,8 +165,8 @@ void load_ucode_ap(void) if (!have_cpuid_p()) return; - vendor = x86_vendor(); - family = x86_family(); + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); switch (vendor) { case X86_VENDOR_INTEL: @@ -206,8 +206,8 @@ void reload_early_microcode(void) { int vendor, family; - vendor = x86_vendor(); - family = x86_family(); + vendor = x86_cpuid_vendor(); + family = x86_cpuid_family(); switch (vendor) { case X86_VENDOR_INTEL: diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index ce47402eb2f9..ee81c544ee0d 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -145,10 +145,10 @@ matching_model_microcode(struct microcode_header_intel *mc_header, int ext_sigcount, i; struct extended_signature *ext_sig; - fam = __x86_family(sig); + fam = x86_family(sig); model = x86_model(sig); - fam_ucode = __x86_family(mc_header->sig); + fam_ucode = x86_family(mc_header->sig); model_ucode = x86_model(mc_header->sig); if (fam == fam_ucode && model == model_ucode) @@ -163,7 +163,7 @@ matching_model_microcode(struct microcode_header_intel *mc_header, ext_sigcount = ext_header->count; for (i = 0; i < ext_sigcount; i++) { - fam_ucode = __x86_family(ext_sig->sig); + fam_ucode = x86_family(ext_sig->sig); model_ucode = x86_model(ext_sig->sig); if (fam == fam_ucode && model == model_ucode) @@ -365,7 +365,7 @@ static int collect_cpu_info_early(struct ucode_cpu_info *uci) native_cpuid(&eax, &ebx, &ecx, &edx); csig.sig = eax; - family = __x86_family(csig.sig); + family = x86_family(csig.sig); model = x86_model(csig.sig); if ((model >= 5) || (family > 6)) { @@ -521,16 +521,12 @@ static bool __init load_builtin_intel_microcode(struct cpio_data *cp) { #ifdef CONFIG_X86_64 unsigned int eax = 0x00000001, ebx, ecx = 0, edx; - unsigned int family, model, stepping; char name[30]; native_cpuid(&eax, &ebx, &ecx, &edx); - family = __x86_family(eax); - model = x86_model(eax); - stepping = eax & 0xf; - - sprintf(name, "intel-ucode/%02x-%02x-%02x", family, model, stepping); + sprintf(name, "intel-ucode/%02x-%02x-%02x", + x86_family(eax), x86_model(eax), x86_stepping(eax)); return get_builtin_firmware(cp, name); #else diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 70d7c93f4550..0d98503c2245 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -593,9 +593,16 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size, unsigned long x_remove_base, unsigned long x_remove_size, int i) { - static struct range range_new[RANGE_NUM]; + /* + * range_new should really be an automatic variable, but + * putting 4096 bytes on the stack is frowned upon, to put it + * mildly. It is safe to make it a static __initdata variable, + * since mtrr_calc_range_state is only called during init and + * there's no way it will call itself recursively. + */ + static struct range range_new[RANGE_NUM] __initdata; unsigned long range_sums_new; - static int nr_range_new; + int nr_range_new; int num_reg; /* Convert ranges to var ranges state: */ diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 3b533cf37c74..c870af161008 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -349,7 +349,7 @@ static void get_fixed_ranges(mtrr_type *frs) void mtrr_save_fixed_ranges(void *info) { - if (cpu_has_mtrr) + if (boot_cpu_has(X86_FEATURE_MTRR)) get_fixed_ranges(mtrr_state.fixed_ranges); } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index f891b4750f04..5c3d149ee91c 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -682,7 +682,7 @@ void __init mtrr_bp_init(void) phys_addr = 32; - if (cpu_has_mtrr) { + if (boot_cpu_has(X86_FEATURE_MTRR)) { mtrr_if = &generic_mtrr_ops; size_or_mask = SIZE_OR_MASK_BITS(36); size_and_mask = 0x00f00000; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 2bf79d7c97df..1b443db2db50 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -482,6 +482,9 @@ int x86_pmu_hw_config(struct perf_event *event) /* Support for IP fixup */ if (x86_pmu.lbr_nr || x86_pmu.intel_cap.pebs_format >= 2) precise++; + + if (x86_pmu.pebs_prec_dist) + precise++; } if (event->attr.precise_ip > precise) @@ -1531,6 +1534,7 @@ static void __init filter_events(struct attribute **attrs) { struct device_attribute *d; struct perf_pmu_events_attr *pmu_attr; + int offset = 0; int i, j; for (i = 0; attrs[i]; i++) { @@ -1539,7 +1543,7 @@ static void __init filter_events(struct attribute **attrs) /* str trumps id */ if (pmu_attr->event_str) continue; - if (x86_pmu.event_map(i)) + if (x86_pmu.event_map(i + offset)) continue; for (j = i; attrs[j]; j++) @@ -1547,6 +1551,14 @@ static void __init filter_events(struct attribute **attrs) /* Check the shifted attr. */ i--; + + /* + * event_map() is index based, the attrs array is organized + * by increasing event index. If we shift the events, then + * we need to compensate for the event_map(), otherwise + * we are looking up the wrong event in the map + */ + offset++; } } @@ -2250,12 +2262,19 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) ss_base = get_segment_base(regs->ss); fp = compat_ptr(ss_base + regs->bp); + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = 0; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 8)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+4, 4); if (bytes != 0) break; @@ -2265,6 +2284,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry *entry) perf_callchain_store(entry, cs_base + frame.return_address); fp = compat_ptr(ss_base + frame.next_frame); } + pagefault_enable(); return 1; } #else @@ -2302,12 +2322,19 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) if (perf_callchain_user32(regs, entry)) return; + pagefault_disable(); while (entry->nr < PERF_MAX_STACK_DEPTH) { unsigned long bytes; frame.next_frame = NULL; frame.return_address = 0; - bytes = copy_from_user_nmi(&frame, fp, sizeof(frame)); + if (!access_ok(VERIFY_READ, fp, 16)) + break; + + bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8); + if (bytes != 0) + break; + bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8); if (bytes != 0) break; @@ -2315,8 +2342,9 @@ perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs) break; perf_callchain_store(entry, frame.return_address); - fp = frame.next_frame; + fp = (void __user *)frame.next_frame; } + pagefault_enable(); } /* diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index d0e35ebb2adb..7bb61e32fb29 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -14,17 +14,7 @@ #include <linux/perf_event.h> -#if 0 -#undef wrmsrl -#define wrmsrl(msr, val) \ -do { \ - unsigned int _msr = (msr); \ - u64 _val = (val); \ - trace_printk("wrmsrl(%x, %Lx)\n", (unsigned int)(_msr), \ - (unsigned long long)(_val)); \ - native_write_msr((_msr), (u32)(_val), (u32)(_val >> 32)); \ -} while (0) -#endif +/* To enable MSR tracing please use the generic trace points. */ /* * | NHM/WSM | SNB | @@ -318,6 +308,10 @@ struct cpu_hw_events { #define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +/* Constraint on specific umask bit only + event */ +#define INTEL_UBIT_EVENT_CONSTRAINT(c, n) \ + EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|(c)) + /* Like UEVENT_CONSTRAINT, but match flags too */ #define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) @@ -589,7 +583,8 @@ struct x86_pmu { bts_active :1, pebs :1, pebs_active :1, - pebs_broken :1; + pebs_broken :1, + pebs_prec_dist :1; int pebs_record_size; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; @@ -907,6 +902,8 @@ void intel_pmu_lbr_init_hsw(void); void intel_pmu_lbr_init_skl(void); +void intel_pmu_lbr_init_knl(void); + int intel_pmu_setup_lbr_filter(struct perf_event *event); void intel_pt_interrupt(void); diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index 1cee5d2d7ece..58610539b048 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -18,7 +18,7 @@ static __initconst const u64 amd_hw_cache_event_ids [ C(RESULT_MISS) ] = 0x0141, /* Data Cache Misses */ }, [ C(OP_WRITE) ] = { - [ C(RESULT_ACCESS) ] = 0x0142, /* Data Cache Refills :system */ + [ C(RESULT_ACCESS) ] = 0, [ C(RESULT_MISS) ] = 0, }, [ C(OP_PREFETCH) ] = { @@ -160,7 +160,7 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) if (offset) return offset; - if (!cpu_has_perfctr_core) + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) offset = index; else offset = index << 1; @@ -652,7 +652,7 @@ static __initconst const struct x86_pmu amd_pmu = { static int __init amd_core_pmu_init(void) { - if (!cpu_has_perfctr_core) + if (!boot_cpu_has(X86_FEATURE_PERFCTR_CORE)) return 0; switch (boot_cpu_data.x86) { diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c index cc6cedb8f25d..49742746a6c9 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -523,10 +523,10 @@ static int __init amd_uncore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) goto fail_nodev; - if (!cpu_has_topoext) + if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) goto fail_nodev; - if (cpu_has_perfctr_nb) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) { amd_uncore_nb = alloc_percpu(struct amd_uncore *); if (!amd_uncore_nb) { ret = -ENOMEM; @@ -540,7 +540,7 @@ static int __init amd_uncore_init(void) ret = 0; } - if (cpu_has_perfctr_l2) { + if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) { amd_uncore_l2 = alloc_percpu(struct amd_uncore *); if (!amd_uncore_l2) { ret = -ENOMEM; @@ -583,10 +583,11 @@ fail_online: /* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */ amd_uncore_nb = amd_uncore_l2 = NULL; - if (cpu_has_perfctr_l2) + + if (boot_cpu_has(X86_FEATURE_PERFCTR_L2)) perf_pmu_unregister(&amd_l2_pmu); fail_l2: - if (cpu_has_perfctr_nb) + if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) perf_pmu_unregister(&amd_nb_pmu); if (amd_uncore_l2) free_percpu(amd_uncore_l2); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index e2a430021e46..a667078a5180 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -185,6 +185,14 @@ struct event_constraint intel_skl_event_constraints[] = { EVENT_CONSTRAINT_END }; +static struct extra_reg intel_knl_extra_regs[] __read_mostly = { + INTEL_UEVENT_EXTRA_REG(0x01b7, + MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0), + INTEL_UEVENT_EXTRA_REG(0x02b7, + MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1), + EVENT_EXTRA_END +}; + static struct extra_reg intel_snb_extra_regs[] __read_mostly = { /* must define OFFCORE_RSP_X first, see intel_fixup_er() */ INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), @@ -255,7 +263,7 @@ struct event_constraint intel_bdw_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ INTEL_UEVENT_CONSTRAINT(0x148, 0x4), /* L1D_PEND_MISS.PENDING */ - INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ + INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_MISS */ EVENT_CONSTRAINT_END }; @@ -1457,6 +1465,42 @@ static __initconst const u64 slm_hw_cache_event_ids }, }; +#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */ +#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */ +#define KNL_MCDRAM_LOCAL BIT_ULL(21) +#define KNL_MCDRAM_FAR BIT_ULL(22) +#define KNL_DDR_LOCAL BIT_ULL(23) +#define KNL_DDR_FAR BIT_ULL(24) +#define KNL_DRAM_ANY (KNL_MCDRAM_LOCAL | KNL_MCDRAM_FAR | \ + KNL_DDR_LOCAL | KNL_DDR_FAR) +#define KNL_L2_READ SLM_DMND_READ +#define KNL_L2_WRITE SLM_DMND_WRITE +#define KNL_L2_PREFETCH SLM_DMND_PREFETCH +#define KNL_L2_ACCESS SLM_LLC_ACCESS +#define KNL_L2_MISS (KNL_OT_L2_HITE | KNL_OT_L2_HITF | \ + KNL_DRAM_ANY | SNB_SNP_ANY | \ + SNB_NON_DRAM) + +static __initconst const u64 knl_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)] = KNL_L2_READ | KNL_L2_ACCESS, + [C(RESULT_MISS)] = 0, + }, + [C(OP_WRITE)] = { + [C(RESULT_ACCESS)] = KNL_L2_WRITE | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_WRITE | KNL_L2_MISS, + }, + [C(OP_PREFETCH)] = { + [C(RESULT_ACCESS)] = KNL_L2_PREFETCH | KNL_L2_ACCESS, + [C(RESULT_MISS)] = KNL_L2_PREFETCH | KNL_L2_MISS, + }, + }, +}; + /* * Use from PMIs where the LBRs are already disabled. */ @@ -2475,6 +2519,44 @@ static void intel_pebs_aliases_snb(struct perf_event *event) } } +static void intel_pebs_aliases_precdist(struct perf_event *event) +{ + if ((event->hw.config & X86_RAW_EVENT_MASK) == 0x003c) { + /* + * Use an alternative encoding for CPU_CLK_UNHALTED.THREAD_P + * (0x003c) so that we can use it with PEBS. + * + * The regular CPU_CLK_UNHALTED.THREAD_P event (0x003c) isn't + * PEBS capable. However we can use INST_RETIRED.PREC_DIST + * (0x01c0), which is a PEBS capable event, to get the same + * count. + * + * The PREC_DIST event has special support to minimize sample + * shadowing effects. One drawback is that it can be + * only programmed on counter 1, but that seems like an + * acceptable trade off. + */ + u64 alt_config = X86_CONFIG(.event=0xc0, .umask=0x01, .inv=1, .cmask=16); + + alt_config |= (event->hw.config & ~X86_RAW_EVENT_MASK); + event->hw.config = alt_config; + } +} + +static void intel_pebs_aliases_ivb(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_snb(event); + return intel_pebs_aliases_precdist(event); +} + +static void intel_pebs_aliases_skl(struct perf_event *event) +{ + if (event->attr.precise_ip < 3) + return intel_pebs_aliases_core2(event); + return intel_pebs_aliases_precdist(event); +} + static unsigned long intel_pmu_free_running_flags(struct perf_event *event) { unsigned long flags = x86_pmu.free_running_flags; @@ -3332,6 +3414,7 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_gen_event_constraints; x86_pmu.pebs_constraints = intel_atom_pebs_event_constraints; + x86_pmu.pebs_aliases = intel_pebs_aliases_core2; pr_cont("Atom events, "); break; @@ -3431,7 +3514,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; if (boot_cpu_data.x86_model == 62) x86_pmu.extra_regs = intel_snbep_extra_regs; else @@ -3464,7 +3548,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_hsw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3499,7 +3584,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_bdw_event_constraints; x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints; x86_pmu.extra_regs = intel_snbep_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_ivb; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; @@ -3511,6 +3597,24 @@ __init int intel_pmu_init(void) pr_cont("Broadwell events, "); break; + case 87: /* Knights Landing Xeon Phi */ + memcpy(hw_cache_event_ids, + slm_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hw_cache_extra_regs, + knl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + intel_pmu_lbr_init_knl(); + + x86_pmu.event_constraints = intel_slm_event_constraints; + x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints; + x86_pmu.extra_regs = intel_knl_extra_regs; + + /* all extra regs are per-cpu when HT is on */ + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + + pr_cont("Knights Landing events, "); + break; + case 78: /* 14nm Skylake Mobile */ case 94: /* 14nm Skylake Desktop */ x86_pmu.late_ack = true; @@ -3521,7 +3625,8 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_skl_event_constraints; x86_pmu.pebs_constraints = intel_skl_pebs_event_constraints; x86_pmu.extra_regs = intel_skl_extra_regs; - x86_pmu.pebs_aliases = intel_pebs_aliases_snb; + x86_pmu.pebs_aliases = intel_pebs_aliases_skl; + x86_pmu.pebs_prec_dist = true; /* all extra regs are per-cpu when HT is on */ x86_pmu.flags |= PMU_FL_HAS_RSP_1; x86_pmu.flags |= PMU_FL_NO_HT_SHARING; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index 5db1c7755548..10602f0a438f 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -620,6 +620,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1), /* MEM_LOAD_RETIRED.* */ /* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x01), + /* Allow all events as PEBS with no flags */ + INTEL_ALL_EVENT_CONSTRAINT(0, 0x1), EVENT_CONSTRAINT_END }; @@ -686,6 +688,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -700,6 +704,8 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { INTEL_PLD_CONSTRAINT(0x01cd, 0xf), /* MEM_TRANS_RETIRED.* */ /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x11d0, 0xf), /* MEM_UOPS_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_XLD(0x21d0, 0xf), /* MEM_UOPS_RETIRED.LOCK_LOADS */ @@ -718,9 +724,10 @@ struct event_constraint intel_hsw_pebs_event_constraints[] = { struct event_constraint intel_skl_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x2), /* INST_RETIRED.PREC_DIST */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(0x01c2, 0xf), /* UOPS_RETIRED.ALL */ - /* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */ - INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf), + /* INST_RETIRED.PREC_DIST, inv=1, cmask=16 (cycles:ppp). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c0, 0x2), + /* INST_RETIRED.TOTAL_CYCLES_PS (inv=1, cmask=16) (cycles:p). */ + INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x0f), INTEL_PLD_CONSTRAINT(0x1cd, 0xf), /* MEM_TRANS_RETIRED.* */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ @@ -1101,6 +1108,13 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) void *at; u64 pebs_status; + /* + * fmt0 does not have a status bitfield (does not use + * perf_record_nhm format) + */ + if (x86_pmu.intel_cap.pebs_format < 1) + return base; + if (base == NULL) return NULL; @@ -1186,7 +1200,7 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs) if (!event->attr.precise_ip) return; - n = (top - at) / x86_pmu.pebs_record_size; + n = top - at; if (n <= 0) return; @@ -1230,12 +1244,21 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs) pebs_status = p->status & cpuc->pebs_enabled; pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1; + /* + * On some CPUs the PEBS status can be zero when PEBS is + * racing with clearing of GLOBAL_STATUS. + * + * Normally we would drop that record, but in the + * case when there is only a single active PEBS event + * we can assume it's for that event. + */ + if (!pebs_status && cpuc->pebs_enabled && + !(cpuc->pebs_enabled & (cpuc->pebs_enabled-1))) + pebs_status = cpuc->pebs_enabled; + bit = find_first_bit((unsigned long *)&pebs_status, x86_pmu.max_pebs_events); - if (WARN(bit >= x86_pmu.max_pebs_events, - "PEBS record without PEBS event! status=%Lx pebs_enabled=%Lx active_mask=%Lx", - (unsigned long long)p->status, (unsigned long long)cpuc->pebs_enabled, - *(unsigned long long *)cpuc->active_mask)) + if (bit >= x86_pmu.max_pebs_events) continue; /* diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index 659f01e165d5..653f88d25987 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -42,6 +42,13 @@ static enum { #define LBR_FAR_BIT 8 /* do not capture far branches */ #define LBR_CALL_STACK_BIT 9 /* enable call stack */ +/* + * Following bit only exists in Linux; we mask it out before writing it to + * the actual MSR. But it helps the constraint perf code to understand + * that this is a separate configuration. + */ +#define LBR_NO_INFO_BIT 63 /* don't read LBR_INFO. */ + #define LBR_KERNEL (1 << LBR_KERNEL_BIT) #define LBR_USER (1 << LBR_USER_BIT) #define LBR_JCC (1 << LBR_JCC_BIT) @@ -52,6 +59,7 @@ static enum { #define LBR_IND_JMP (1 << LBR_IND_JMP_BIT) #define LBR_FAR (1 << LBR_FAR_BIT) #define LBR_CALL_STACK (1 << LBR_CALL_STACK_BIT) +#define LBR_NO_INFO (1ULL << LBR_NO_INFO_BIT) #define LBR_PLM (LBR_KERNEL | LBR_USER) @@ -152,8 +160,8 @@ static void __intel_pmu_lbr_enable(bool pmi) * did not change. */ if (cpuc->lbr_sel) - lbr_select = cpuc->lbr_sel->config; - if (!pmi) + lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask; + if (!pmi && cpuc->lbr_sel) wrmsrl(MSR_LBR_SELECT, lbr_select); rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl); @@ -422,6 +430,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc) */ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) { + bool need_info = false; unsigned long mask = x86_pmu.lbr_nr - 1; int lbr_format = x86_pmu.intel_cap.lbr_format; u64 tos = intel_pmu_lbr_tos(); @@ -429,8 +438,11 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) int out = 0; int num = x86_pmu.lbr_nr; - if (cpuc->lbr_sel->config & LBR_CALL_STACK) - num = tos; + if (cpuc->lbr_sel) { + need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO); + if (cpuc->lbr_sel->config & LBR_CALL_STACK) + num = tos; + } for (i = 0; i < num; i++) { unsigned long lbr_idx = (tos - i) & mask; @@ -442,7 +454,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc) rdmsrl(x86_pmu.lbr_from + lbr_idx, from); rdmsrl(x86_pmu.lbr_to + lbr_idx, to); - if (lbr_format == LBR_FORMAT_INFO) { + if (lbr_format == LBR_FORMAT_INFO && need_info) { u64 info; rdmsrl(MSR_LBR_INFO_0 + lbr_idx, info); @@ -590,6 +602,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) if (v != LBR_IGN) mask |= v; } + reg = &event->hw.branch_reg; reg->idx = EXTRA_REG_LBR; @@ -600,6 +613,11 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event) */ reg->config = mask ^ x86_pmu.lbr_sel_mask; + if ((br_type & PERF_SAMPLE_BRANCH_NO_CYCLES) && + (br_type & PERF_SAMPLE_BRANCH_NO_FLAGS) && + (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)) + reg->config |= LBR_NO_INFO; + return 0; } @@ -1028,3 +1046,17 @@ void __init intel_pmu_lbr_init_atom(void) */ pr_cont("8-deep LBR, "); } + +/* Knights Landing */ +void intel_pmu_lbr_init_knl(void) +{ + x86_pmu.lbr_nr = 8; + x86_pmu.lbr_tos = MSR_LBR_TOS; + x86_pmu.lbr_from = MSR_LBR_NHM_FROM; + x86_pmu.lbr_to = MSR_LBR_NHM_TO; + + x86_pmu.lbr_sel_mask = LBR_SEL_MASK; + x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + pr_cont("8-deep LBR, "); +} diff --git a/arch/x86/kernel/cpu/perf_event_intel_pt.c b/arch/x86/kernel/cpu/perf_event_intel_pt.c index 868e1194337f..c0bbd1033b7c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_pt.c +++ b/arch/x86/kernel/cpu/perf_event_intel_pt.c @@ -27,6 +27,7 @@ #include <asm/perf_event.h> #include <asm/insn.h> #include <asm/io.h> +#include <asm/intel_pt.h> #include "perf_event.h" #include "intel_pt.h" @@ -1122,6 +1123,14 @@ static int pt_event_init(struct perf_event *event) return 0; } +void cpu_emergency_stop_pt(void) +{ + struct pt *pt = this_cpu_ptr(&pt_ctx); + + if (pt->handle.event) + pt_event_stop(pt->handle.event, PERF_EF_UPDATE); +} + static __init int pt_init(void) { int ret, cpu, prior_warn = 0; diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c index ed446bdcbf31..24a351ad628d 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c +++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c @@ -63,7 +63,7 @@ #define INTEL_RAPL_PP1 0x4 /* pseudo-encoding */ #define NR_RAPL_DOMAINS 0x4 -static const char *rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { +static const char *const rapl_domain_names[NR_RAPL_DOMAINS] __initconst = { "pp0-core", "package", "dram", @@ -109,11 +109,11 @@ static struct kobj_attribute format_attr_##_var = \ #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */ -#define RAPL_EVENT_ATTR_STR(_name, v, str) \ -static struct perf_pmu_events_attr event_attr_##v = { \ - .attr = __ATTR(_name, 0444, rapl_sysfs_show, NULL), \ - .id = 0, \ - .event_str = str, \ +#define RAPL_EVENT_ATTR_STR(_name, v, str) \ +static struct perf_pmu_events_attr event_attr_##v = { \ + .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ + .id = 0, \ + .event_str = str, \ }; struct rapl_pmu { @@ -405,19 +405,6 @@ static struct attribute_group rapl_pmu_attr_group = { .attrs = rapl_pmu_attrs, }; -static ssize_t rapl_sysfs_show(struct device *dev, - struct device_attribute *attr, - char *page) -{ - struct perf_pmu_events_attr *pmu_attr = \ - container_of(attr, struct perf_pmu_events_attr, attr); - - if (pmu_attr->event_str) - return sprintf(page, "%s", pmu_attr->event_str); - - return 0; -} - RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01"); RAPL_EVENT_ATTR_STR(energy-pkg , rapl_pkg, "event=0x02"); RAPL_EVENT_ATTR_STR(energy-ram , rapl_ram, "event=0x03"); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index 61215a69b03d..f97f8075bf04 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -884,6 +884,15 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id * each box has a different function id. */ pmu = &type->pmus[UNCORE_PCI_DEV_IDX(id->driver_data)]; + /* Knights Landing uses a common PCI device ID for multiple instances of + * an uncore PMU device type. There is only one entry per device type in + * the knl_uncore_pci_ids table inspite of multiple devices present for + * some device types. Hence PCI device idx would be 0 for all devices. + * So increment pmu pointer to point to an unused array element. + */ + if (boot_cpu_data.x86_model == 87) + while (pmu->func_id >= 0) + pmu++; if (pmu->func_id < 0) pmu->func_id = pdev->devfn; else @@ -966,6 +975,7 @@ static int __init uncore_pci_init(void) case 63: /* Haswell-EP */ ret = hswep_uncore_pci_init(); break; + case 79: /* BDX-EP */ case 86: /* BDX-DE */ ret = bdx_uncore_pci_init(); break; @@ -982,6 +992,9 @@ static int __init uncore_pci_init(void) case 61: /* Broadwell */ ret = bdw_uncore_pci_init(); break; + case 87: /* Knights Landing */ + ret = knl_uncore_pci_init(); + break; default: return 0; } @@ -1287,9 +1300,13 @@ static int __init uncore_cpu_init(void) case 63: /* Haswell-EP */ hswep_uncore_cpu_init(); break; + case 79: /* BDX-EP */ case 86: /* BDX-DE */ bdx_uncore_cpu_init(); break; + case 87: /* Knights Landing */ + knl_uncore_cpu_init(); + break; default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index 2f0a4a98e16b..07aa2d6bd710 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -338,6 +338,7 @@ int hsw_uncore_pci_init(void); int bdw_uncore_pci_init(void); void snb_uncore_cpu_init(void); void nhm_uncore_cpu_init(void); +int snb_pci2phy_map_init(int devid); /* perf_event_intel_uncore_snbep.c */ int snbep_uncore_pci_init(void); @@ -348,6 +349,8 @@ int hswep_uncore_pci_init(void); void hswep_uncore_cpu_init(void); int bdx_uncore_pci_init(void); void bdx_uncore_cpu_init(void); +int knl_uncore_pci_init(void); +void knl_uncore_cpu_init(void); /* perf_event_intel_uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c index 845256158a10..0b934820fafd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snb.c @@ -417,7 +417,7 @@ static void snb_uncore_imc_event_del(struct perf_event *event, int flags) } } -static int snb_pci2phy_map_init(int devid) +int snb_pci2phy_map_init(int devid) { struct pci_dev *dev = NULL; struct pci2phy_map *map; diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c index f0f4fcba252e..33acb884ccf1 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c @@ -209,31 +209,98 @@ #define HSWEP_PCU_MSR_PMON_BOX_CTL 0x710 #define HSWEP_PCU_MSR_PMON_BOX_FILTER 0x715 +/* KNL Ubox */ +#define KNL_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_U_MSR_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) +/* KNL CHA */ +#define KNL_CHA_MSR_OFFSET 0xc +#define KNL_CHA_MSR_PMON_CTL_QOR (1 << 16) +#define KNL_CHA_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_CBO_MSR_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +#define KNL_CHA_MSR_PMON_BOX_FILTER_TID 0x1ff +#define KNL_CHA_MSR_PMON_BOX_FILTER_STATE (7 << 18) +#define KNL_CHA_MSR_PMON_BOX_FILTER_OP (0xfffffe2aULL << 32) + +/* KNL EDC/MC UCLK */ +#define KNL_UCLK_MSR_PMON_CTR0_LOW 0x400 +#define KNL_UCLK_MSR_PMON_CTL0 0x420 +#define KNL_UCLK_MSR_PMON_BOX_CTL 0x430 +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW 0x44c +#define KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL 0x454 +#define KNL_PMON_FIXED_CTL_EN 0x1 + +/* KNL EDC */ +#define KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW 0xa00 +#define KNL_EDC0_ECLK_MSR_PMON_CTL0 0xa20 +#define KNL_EDC0_ECLK_MSR_PMON_BOX_CTL 0xa30 +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW 0xa3c +#define KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL 0xa44 + +/* KNL MC */ +#define KNL_MC0_CH0_MSR_PMON_CTR0_LOW 0xb00 +#define KNL_MC0_CH0_MSR_PMON_CTL0 0xb20 +#define KNL_MC0_CH0_MSR_PMON_BOX_CTL 0xb30 +#define KNL_MC0_CH0_MSR_PMON_FIXED_LOW 0xb3c +#define KNL_MC0_CH0_MSR_PMON_FIXED_CTL 0xb44 + +/* KNL IRP */ +#define KNL_IRP_PCI_PMON_BOX_CTL 0xf0 +#define KNL_IRP_PCI_PMON_RAW_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ + KNL_CHA_MSR_PMON_CTL_QOR) +/* KNL PCU */ +#define KNL_PCU_PMON_CTL_EV_SEL_MASK 0x0000007f +#define KNL_PCU_PMON_CTL_USE_OCC_CTR (1 << 7) +#define KNL_PCU_MSR_PMON_CTL_TRESH_MASK 0x3f000000 +#define KNL_PCU_MSR_PMON_RAW_EVENT_MASK \ + (KNL_PCU_PMON_CTL_EV_SEL_MASK | \ + KNL_PCU_PMON_CTL_USE_OCC_CTR | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_CBO_PMON_CTL_TID_EN | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PMON_CTL_INVERT | \ + KNL_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); +DEFINE_UNCORE_FORMAT_ATTR(event2, event, "config:0-6"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); +DEFINE_UNCORE_FORMAT_ATTR(use_occ_ctr, use_occ_ctr, "config:7"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); +DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); DEFINE_UNCORE_FORMAT_ATTR(inv, inv, "config:23"); DEFINE_UNCORE_FORMAT_ATTR(thresh8, thresh, "config:24-31"); +DEFINE_UNCORE_FORMAT_ATTR(thresh6, thresh, "config:24-29"); DEFINE_UNCORE_FORMAT_ATTR(thresh5, thresh, "config:24-28"); DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); +DEFINE_UNCORE_FORMAT_ATTR(occ_edge_det, occ_edge_det, "config:31"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid2, filter_tid, "config1:0"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid3, filter_tid, "config1:0-5"); +DEFINE_UNCORE_FORMAT_ATTR(filter_tid4, filter_tid, "config1:0-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_cid, filter_cid, "config1:5"); DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_link2, filter_link, "config1:6-8"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link3, filter_link, "config1:12"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_state3, filter_state, "config1:17-23"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state4, filter_state, "config1:18-20"); +DEFINE_UNCORE_FORMAT_ATTR(filter_local, filter_local, "config1:33"); +DEFINE_UNCORE_FORMAT_ATTR(filter_all_op, filter_all_op, "config1:35"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nnm, filter_nnm, "config1:37"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc3, filter_opc, "config1:41-60"); DEFINE_UNCORE_FORMAT_ATTR(filter_nc, filter_nc, "config1:62"); DEFINE_UNCORE_FORMAT_ATTR(filter_c6, filter_c6, "config1:61"); DEFINE_UNCORE_FORMAT_ATTR(filter_isoc, filter_isoc, "config1:63"); @@ -315,8 +382,9 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct pe static void snbep_uncore_pci_init_box(struct intel_uncore_box *box) { struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); - pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT); + pci_write_config_dword(pdev, box_ctl, SNBEP_PMON_BOX_CTL_INT); } static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box) @@ -1728,6 +1796,419 @@ int ivbep_uncore_pci_init(void) } /* end of IvyTown uncore support */ +/* KNL uncore support */ +static struct attribute *knl_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute_group knl_uncore_ubox_format_group = { + .name = "format", + .attrs = knl_uncore_ubox_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = HSWEP_U_MSR_PMON_CTR0, + .event_ctl = HSWEP_U_MSR_PMON_CTL0, + .event_mask = KNL_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = HSWEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = HSWEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_ubox_format_group, +}; + +static struct attribute *knl_uncore_cha_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid4.attr, + &format_attr_filter_link3.attr, + &format_attr_filter_state4.attr, + &format_attr_filter_local.attr, + &format_attr_filter_all_op.attr, + &format_attr_filter_nnm.attr, + &format_attr_filter_opc3.attr, + &format_attr_filter_nc.attr, + &format_attr_filter_isoc.attr, + NULL, +}; + +static struct attribute_group knl_uncore_cha_format_group = { + .name = "format", + .attrs = knl_uncore_cha_formats_attr, +}; + +static struct event_constraint knl_uncore_cha_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x11, 0x1), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x1), + UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + EVENT_CONSTRAINT_END +}; + +static struct extra_reg knl_uncore_cha_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x3d, 0xff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x35, 0xff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x36, 0xff, 0x4), + EVENT_EXTRA_END +}; + +static u64 knl_cha_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x4) + mask |= KNL_CHA_MSR_PMON_BOX_FILTER_OP; + return mask; +} + +static struct event_constraint * +knl_cha_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, knl_cha_filter_mask); +} + +static int knl_cha_hw_config(struct intel_uncore_box *box, + struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = knl_uncore_cha_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = HSWEP_C0_MSR_PMON_BOX_FILTER0 + + KNL_CHA_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & knl_cha_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void hswep_cbox_enable_event(struct intel_uncore_box *box, + struct perf_event *event); + +static struct intel_uncore_ops knl_uncore_cha_ops = { + .init_box = snbep_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = hswep_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = knl_cha_hw_config, + .get_constraint = knl_cha_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type knl_uncore_cha = { + .name = "cha", + .num_counters = 4, + .num_boxes = 38, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_C0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, + .event_mask = KNL_CHA_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = KNL_CHA_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = knl_uncore_cha_constraints, + .ops = &knl_uncore_cha_ops, + .format_group = &knl_uncore_cha_format_group, +}; + +static struct attribute *knl_uncore_pcu_formats_attr[] = { + &format_attr_event2.attr, + &format_attr_use_occ_ctr.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_inv.attr, + &format_attr_thresh6.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge_det.attr, + NULL, +}; + +static struct attribute_group knl_uncore_pcu_format_group = { + .name = "format", + .attrs = knl_uncore_pcu_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = HSWEP_PCU_MSR_PMON_CTR0, + .event_ctl = HSWEP_PCU_MSR_PMON_CTL0, + .event_mask = KNL_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_PCU_MSR_PMON_BOX_CTL, + .ops = &snbep_uncore_msr_ops, + .format_group = &knl_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *knl_msr_uncores[] = { + &knl_uncore_ubox, + &knl_uncore_cha, + &knl_uncore_pcu, + NULL, +}; + +void knl_uncore_cpu_init(void) +{ + uncore_msr_uncores = knl_msr_uncores; +} + +static void knl_uncore_imc_enable_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + int box_ctl = uncore_pci_box_ctl(box); + + pci_write_config_dword(pdev, box_ctl, 0); +} + +static void knl_uncore_imc_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; + + if ((event->attr.config & SNBEP_PMON_CTL_EV_SEL_MASK) + == UNCORE_FIXED_EVENT) + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | KNL_PMON_FIXED_CTL_EN); + else + pci_write_config_dword(pdev, hwc->config_base, + hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops knl_uncore_imc_ops = { + .init_box = snbep_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = knl_uncore_imc_enable_box, + .read_counter = snbep_uncore_pci_read_counter, + .enable_event = knl_uncore_imc_enable_event, + .disable_event = snbep_uncore_pci_disable_event, +}; + +static struct intel_uncore_type knl_uncore_imc_uclk = { + .name = "imc_uclk", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_imc_dclk = { + .name = "imc", + .num_counters = 4, + .num_boxes = 6, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_MC0_CH0_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_MC0_CH0_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_MC0_CH0_MSR_PMON_FIXED_LOW, + .fixed_ctl = KNL_MC0_CH0_MSR_PMON_FIXED_CTL, + .box_ctl = KNL_MC0_CH0_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_uclk = { + .name = "edc_uclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_UCLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_UCLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_UCLK_MSR_PMON_UCLK_FIXED_LOW, + .fixed_ctl = KNL_UCLK_MSR_PMON_UCLK_FIXED_CTL, + .box_ctl = KNL_UCLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct intel_uncore_type knl_uncore_edc_eclk = { + .name = "edc_eclk", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .perf_ctr = KNL_EDC0_ECLK_MSR_PMON_CTR0_LOW, + .event_ctl = KNL_EDC0_ECLK_MSR_PMON_CTL0, + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .fixed_ctr = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_LOW, + .fixed_ctl = KNL_EDC0_ECLK_MSR_PMON_ECLK_FIXED_CTL, + .box_ctl = KNL_EDC0_ECLK_MSR_PMON_BOX_CTL, + .ops = &knl_uncore_imc_ops, + .format_group = &snbep_uncore_format_group, +}; + +static struct event_constraint knl_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type knl_uncore_m2pcie = { + .name = "m2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .constraints = knl_uncore_m2pcie_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + +static struct attribute *knl_uncore_irp_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_qor.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group knl_uncore_irp_format_group = { + .name = "format", + .attrs = knl_uncore_irp_formats_attr, +}; + +static struct intel_uncore_type knl_uncore_irp = { + .name = "irp", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = KNL_IRP_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = KNL_IRP_PCI_PMON_BOX_CTL, + .ops = &snbep_uncore_pci_ops, + .format_group = &knl_uncore_irp_format_group, +}; + +enum { + KNL_PCI_UNCORE_MC_UCLK, + KNL_PCI_UNCORE_MC_DCLK, + KNL_PCI_UNCORE_EDC_UCLK, + KNL_PCI_UNCORE_EDC_ECLK, + KNL_PCI_UNCORE_M2PCIE, + KNL_PCI_UNCORE_IRP, +}; + +static struct intel_uncore_type *knl_pci_uncores[] = { + [KNL_PCI_UNCORE_MC_UCLK] = &knl_uncore_imc_uclk, + [KNL_PCI_UNCORE_MC_DCLK] = &knl_uncore_imc_dclk, + [KNL_PCI_UNCORE_EDC_UCLK] = &knl_uncore_edc_uclk, + [KNL_PCI_UNCORE_EDC_ECLK] = &knl_uncore_edc_eclk, + [KNL_PCI_UNCORE_M2PCIE] = &knl_uncore_m2pcie, + [KNL_PCI_UNCORE_IRP] = &knl_uncore_irp, + NULL, +}; + +/* + * KNL uses a common PCI device ID for multiple instances of an Uncore PMU + * device type. prior to KNL, each instance of a PMU device type had a unique + * device ID. + * + * PCI Device ID Uncore PMU Devices + * ---------------------------------- + * 0x7841 MC0 UClk, MC1 UClk + * 0x7843 MC0 DClk CH 0, MC0 DClk CH 1, MC0 DClk CH 2, + * MC1 DClk CH 0, MC1 DClk CH 1, MC1 DClk CH 2 + * 0x7833 EDC0 UClk, EDC1 UClk, EDC2 UClk, EDC3 UClk, + * EDC4 UClk, EDC5 UClk, EDC6 UClk, EDC7 UClk + * 0x7835 EDC0 EClk, EDC1 EClk, EDC2 EClk, EDC3 EClk, + * EDC4 EClk, EDC5 EClk, EDC6 EClk, EDC7 EClk + * 0x7817 M2PCIe + * 0x7814 IRP +*/ + +static const struct pci_device_id knl_uncore_pci_ids[] = { + { /* MC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7841), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_UCLK, 0), + }, + { /* MC DClk Channel */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7843), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_MC_DCLK, 0), + }, + { /* EDC UClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7833), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_UCLK, 0), + }, + { /* EDC EClk */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7835), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_EDC_ECLK, 0), + }, + { /* M2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7817), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_M2PCIE, 0), + }, + { /* IRP */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7814), + .driver_data = UNCORE_PCI_DEV_DATA(KNL_PCI_UNCORE_IRP, 0), + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver knl_uncore_pci_driver = { + .name = "knl_uncore", + .id_table = knl_uncore_pci_ids, +}; + +int knl_uncore_pci_init(void) +{ + int ret; + + /* All KNL PCI based PMON units are on the same PCI bus except IRP */ + ret = snb_pci2phy_map_init(0x7814); /* IRP */ + if (ret) + return ret; + ret = snb_pci2phy_map_init(0x7817); /* M2PCIe */ + if (ret) + return ret; + uncore_pci_uncores = knl_pci_uncores; + uncore_pci_driver = &knl_uncore_pci_driver; + return 0; +} + +/* end of KNL uncore support */ + /* Haswell-EP uncore support */ static struct attribute *hswep_uncore_ubox_formats_attr[] = { &format_attr_event.attr, @@ -2338,7 +2819,7 @@ int hswep_uncore_pci_init(void) } /* end of Haswell-EP uncore support */ -/* BDX-DE uncore support */ +/* BDX uncore support */ static struct intel_uncore_type bdx_uncore_ubox = { .name = "ubox", @@ -2360,13 +2841,14 @@ static struct event_constraint bdx_uncore_cbox_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x09, 0x3), UNCORE_EVENT_CONSTRAINT(0x11, 0x1), UNCORE_EVENT_CONSTRAINT(0x36, 0x1), + UNCORE_EVENT_CONSTRAINT(0x3e, 0x1), EVENT_CONSTRAINT_END }; static struct intel_uncore_type bdx_uncore_cbox = { .name = "cbox", .num_counters = 4, - .num_boxes = 8, + .num_boxes = 24, .perf_ctr_bits = 48, .event_ctl = HSWEP_C0_MSR_PMON_CTL0, .perf_ctr = HSWEP_C0_MSR_PMON_CTR0, @@ -2379,9 +2861,24 @@ static struct intel_uncore_type bdx_uncore_cbox = { .format_group = &hswep_uncore_cbox_format_group, }; +static struct intel_uncore_type bdx_uncore_sbox = { + .name = "sbox", + .num_counters = 4, + .num_boxes = 4, + .perf_ctr_bits = 48, + .event_ctl = HSWEP_S0_MSR_PMON_CTL0, + .perf_ctr = HSWEP_S0_MSR_PMON_CTR0, + .event_mask = HSWEP_S_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = HSWEP_S0_MSR_PMON_BOX_CTL, + .msr_offset = HSWEP_SBOX_MSR_OFFSET, + .ops = &hswep_uncore_sbox_msr_ops, + .format_group = &hswep_uncore_sbox_format_group, +}; + static struct intel_uncore_type *bdx_msr_uncores[] = { &bdx_uncore_ubox, &bdx_uncore_cbox, + &bdx_uncore_sbox, &hswep_uncore_pcu, NULL, }; @@ -2396,7 +2893,7 @@ void bdx_uncore_cpu_init(void) static struct intel_uncore_type bdx_uncore_ha = { .name = "ha", .num_counters = 4, - .num_boxes = 1, + .num_boxes = 2, .perf_ctr_bits = 48, SNBEP_UNCORE_PCI_COMMON_INIT(), }; @@ -2404,7 +2901,7 @@ static struct intel_uncore_type bdx_uncore_ha = { static struct intel_uncore_type bdx_uncore_imc = { .name = "imc", .num_counters = 5, - .num_boxes = 2, + .num_boxes = 8, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, @@ -2424,6 +2921,19 @@ static struct intel_uncore_type bdx_uncore_irp = { .format_group = &snbep_uncore_format_group, }; +static struct intel_uncore_type bdx_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 = SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &snbep_uncore_qpi_ops, + .format_group = &snbep_uncore_qpi_format_group, +}; static struct event_constraint bdx_uncore_r2pcie_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x10, 0x3), @@ -2432,6 +2942,8 @@ static struct event_constraint bdx_uncore_r2pcie_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x23, 0x1), UNCORE_EVENT_CONSTRAINT(0x25, 0x1), UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), EVENT_CONSTRAINT_END }; @@ -2445,18 +2957,65 @@ static struct intel_uncore_type bdx_uncore_r2pcie = { SNBEP_UNCORE_PCI_COMMON_INIT(), }; +static struct event_constraint bdx_uncore_r3qpi_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x01, 0x7), + UNCORE_EVENT_CONSTRAINT(0x07, 0x7), + UNCORE_EVENT_CONSTRAINT(0x08, 0x7), + UNCORE_EVENT_CONSTRAINT(0x09, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0a, 0x7), + UNCORE_EVENT_CONSTRAINT(0x0e, 0x7), + UNCORE_EVENT_CONSTRAINT(0x10, 0x3), + UNCORE_EVENT_CONSTRAINT(0x11, 0x3), + UNCORE_EVENT_CONSTRAINT(0x13, 0x1), + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x15, 0x3), + UNCORE_EVENT_CONSTRAINT(0x1f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x20, 0x3), + UNCORE_EVENT_CONSTRAINT(0x21, 0x3), + UNCORE_EVENT_CONSTRAINT(0x22, 0x3), + UNCORE_EVENT_CONSTRAINT(0x23, 0x3), + UNCORE_EVENT_CONSTRAINT(0x25, 0x3), + UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), + UNCORE_EVENT_CONSTRAINT(0x33, 0x3), + UNCORE_EVENT_CONSTRAINT(0x34, 0x3), + UNCORE_EVENT_CONSTRAINT(0x36, 0x3), + UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), + EVENT_CONSTRAINT_END +}; + +static struct intel_uncore_type bdx_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 3, + .perf_ctr_bits = 48, + .constraints = bdx_uncore_r3qpi_constraints, + SNBEP_UNCORE_PCI_COMMON_INIT(), +}; + enum { BDX_PCI_UNCORE_HA, BDX_PCI_UNCORE_IMC, BDX_PCI_UNCORE_IRP, + BDX_PCI_UNCORE_QPI, BDX_PCI_UNCORE_R2PCIE, + BDX_PCI_UNCORE_R3QPI, }; static struct intel_uncore_type *bdx_pci_uncores[] = { [BDX_PCI_UNCORE_HA] = &bdx_uncore_ha, [BDX_PCI_UNCORE_IMC] = &bdx_uncore_imc, [BDX_PCI_UNCORE_IRP] = &bdx_uncore_irp, + [BDX_PCI_UNCORE_QPI] = &bdx_uncore_qpi, [BDX_PCI_UNCORE_R2PCIE] = &bdx_uncore_r2pcie, + [BDX_PCI_UNCORE_R3QPI] = &bdx_uncore_r3qpi, NULL, }; @@ -2465,6 +3024,10 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f30), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 0), }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f38), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_HA, 1), + }, { /* MC0 Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb0), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 0), @@ -2473,14 +3036,74 @@ static const struct pci_device_id bdx_uncore_pci_ids[] = { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb1), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 1), }, + { /* MC0 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 2), + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fb5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 3), + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd0), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 4), + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd1), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 5), + }, + { /* MC1 Channel 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd4), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 6), + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6fd5), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IMC, 7), + }, { /* IRP */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f39), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_IRP, 0), }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f32), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 0), + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f33), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 1), + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3a), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_QPI, 2), + }, { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f34), .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R2PCIE, 0), }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f36), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 0), + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f37), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 1), + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f3e), + .driver_data = UNCORE_PCI_DEV_DATA(BDX_PCI_UNCORE_R3QPI, 2), + }, + { /* QPI Port 0 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f86), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 0), + }, + { /* QPI Port 1 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f96), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 1), + }, + { /* QPI Port 2 filter */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x6f46), + .driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV, 2), + }, { /* end: all zeroes */ } }; @@ -2500,4 +3123,4 @@ int bdx_uncore_pci_init(void) return 0; } -/* end of BDX-DE uncore support */ +/* end of BDX uncore support */ diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 136ac74dee82..819d94982e07 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -33,28 +33,27 @@ static int __init x86_rdrand_setup(char *s) __setup("nordrand", x86_rdrand_setup); /* - * Force a reseed cycle; we are architecturally guaranteed a reseed - * after no more than 512 128-bit chunks of random data. This also - * acts as a test of the CPU capability. + * RDRAND has Built-In-Self-Test (BIST) that runs on every invocation. + * Run the instruction a few times as a sanity check. + * If it fails, it is simple to disable RDRAND here. */ -#define RESEED_LOOP ((512*128)/sizeof(unsigned long)) +#define SANITY_CHECK_LOOPS 8 void x86_init_rdrand(struct cpuinfo_x86 *c) { #ifdef CONFIG_ARCH_RANDOM unsigned long tmp; - int i, count, ok; + int i; if (!cpu_has(c, X86_FEATURE_RDRAND)) - return; /* Nothing to do */ + return; - for (count = i = 0; i < RESEED_LOOP; i++) { - ok = rdrand_long(&tmp); - if (ok) - count++; + for (i = 0; i < SANITY_CHECK_LOOPS; i++) { + if (!rdrand_long(&tmp)) { + clear_cpu_cap(c, X86_FEATURE_RDRAND); + printk_once(KERN_WARNING "rdrand: disabled\n"); + return; + } } - - if (count != RESEED_LOOP) - clear_cpu_cap(c, X86_FEATURE_RDRAND); #endif } diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 608fb26c7254..8cb57df9398d 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -31,32 +31,12 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) const struct cpuid_bit *cb; static const struct cpuid_bit cpuid_bits[] = { - { X86_FEATURE_DTHERM, CR_EAX, 0, 0x00000006, 0 }, - { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006, 0 }, - { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006, 0 }, - { X86_FEATURE_PLN, CR_EAX, 4, 0x00000006, 0 }, - { X86_FEATURE_PTS, CR_EAX, 6, 0x00000006, 0 }, - { X86_FEATURE_HWP, CR_EAX, 7, 0x00000006, 0 }, - { X86_FEATURE_HWP_NOTIFY, CR_EAX, 8, 0x00000006, 0 }, - { X86_FEATURE_HWP_ACT_WINDOW, CR_EAX, 9, 0x00000006, 0 }, - { X86_FEATURE_HWP_EPP, CR_EAX,10, 0x00000006, 0 }, - { X86_FEATURE_HWP_PKG_REQ, CR_EAX,11, 0x00000006, 0 }, { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 }, - { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a, 0 }, - { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, - { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, - { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a, 0 }, - { X86_FEATURE_TSCRATEMSR, CR_EDX, 4, 0x8000000a, 0 }, - { X86_FEATURE_VMCBCLEAN, CR_EDX, 5, 0x8000000a, 0 }, - { X86_FEATURE_FLUSHBYASID, CR_EDX, 6, 0x8000000a, 0 }, - { X86_FEATURE_DECODEASSISTS, CR_EDX, 7, 0x8000000a, 0 }, - { X86_FEATURE_PAUSEFILTER, CR_EDX,10, 0x8000000a, 0 }, - { X86_FEATURE_PFTHRESHOLD, CR_EDX,12, 0x8000000a, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c index 3fa0e5ad86b4..252da7aceca6 100644 --- a/arch/x86/kernel/cpu/transmeta.c +++ b/arch/x86/kernel/cpu/transmeta.c @@ -12,7 +12,7 @@ static void early_init_transmeta(struct cpuinfo_x86 *c) xlvl = cpuid_eax(0x80860000); if ((xlvl & 0xffff0000) == 0x80860000) { if (xlvl >= 0x80860001) - c->x86_capability[2] = cpuid_edx(0x80860001); + c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001); } } @@ -82,7 +82,7 @@ static void init_transmeta(struct cpuinfo_x86 *c) /* Unhide possibly hidden capability flags */ rdmsr(0x80860004, cap_mask, uk); wrmsr(0x80860004, ~0, uk); - c->x86_capability[0] = cpuid_edx(0x00000001); + c->x86_capability[CPUID_1_EDX] = cpuid_edx(0x00000001); wrmsr(0x80860004, cap_mask, uk); /* All Transmeta CPUs have a constant TSC */ diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index bd3507da39f0..2836de390f95 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -58,28 +58,6 @@ static void cpuid_smp_cpuid(void *cmd_block) &cmd->eax, &cmd->ebx, &cmd->ecx, &cmd->edx); } -static loff_t cpuid_seek(struct file *file, loff_t offset, int orig) -{ - loff_t ret; - struct inode *inode = file->f_mapping->host; - - mutex_lock(&inode->i_mutex); - switch (orig) { - case 0: - file->f_pos = offset; - ret = file->f_pos; - break; - case 1: - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } - mutex_unlock(&inode->i_mutex); - return ret; -} - static ssize_t cpuid_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -132,7 +110,7 @@ static int cpuid_open(struct inode *inode, struct file *file) */ static const struct file_operations cpuid_fops = { .owner = THIS_MODULE, - .llseek = cpuid_seek, + .llseek = no_seek_end_llseek, .read = cpuid_read, .open = cpuid_open, }; diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 2c1910f6717e..58f34319b29a 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -35,6 +35,7 @@ #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/virtext.h> +#include <asm/intel_pt.h> /* Alignment required for elf header segment */ #define ELF_CORE_HEADER_ALIGN 4096 @@ -125,6 +126,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + disable_local_APIC(); } @@ -169,6 +175,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs) cpu_emergency_vmxoff(); cpu_emergency_svm_disable(); + /* + * Disable Intel PT to stop its logging + */ + cpu_emergency_stop_pt(); + #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index be39b5fde4b9..7b2978ab30df 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -12,7 +12,7 @@ */ static void fpu__init_cpu_ctx_switch(void) { - if (!cpu_has_eager_fpu) + if (!boot_cpu_has(X86_FEATURE_EAGER_FPU)) stts(); else clts(); @@ -143,9 +143,18 @@ static void __init fpu__init_system_generic(void) unsigned int xstate_size; EXPORT_SYMBOL_GPL(xstate_size); -/* Enforce that 'MEMBER' is the last field of 'TYPE': */ +/* Get alignment of the TYPE. */ +#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test) + +/* + * Enforce that 'MEMBER' is the last field of 'TYPE'. + * + * Align the computed size with alignment of the TYPE, + * because that's how C aligns structs. + */ #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ - BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER)) + BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \ + TYPE_ALIGN(TYPE))) /* * We append the 'struct fpu' to the task_struct: @@ -188,7 +197,7 @@ static void __init fpu__init_task_struct_size(void) */ static void __init fpu__init_system_xstate_size_legacy(void) { - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -278,7 +287,7 @@ __setup("eagerfpu=", eager_fpu_setup); */ static void __init fpu__init_system_ctx_switch(void) { - static bool on_boot_cpu = 1; + static bool on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -287,7 +296,7 @@ static void __init fpu__init_system_ctx_switch(void) current_thread_info()->status = 0; /* Auto enable eagerfpu for xsaveopt */ - if (cpu_has_xsaveopt && eagerfpu != DISABLE) + if (boot_cpu_has(X86_FEATURE_XSAVEOPT) && eagerfpu != DISABLE) eagerfpu = ENABLE; if (xfeatures_mask & XFEATURE_MASK_EAGER) { diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 70fc312221fc..40f100285984 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -297,7 +297,7 @@ static void __init setup_xstate_comp(void) */ static void __init setup_init_fpu_buf(void) { - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; WARN_ON_FPU(!on_boot_cpu); on_boot_cpu = 0; @@ -608,7 +608,7 @@ static void fpu__init_disable_system_xstate(void) void __init fpu__init_system_xstate(void) { unsigned int eax, ebx, ecx, edx; - static int on_boot_cpu = 1; + static int on_boot_cpu __initdata = 1; int err; WARN_ON_FPU(!on_boot_cpu); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 311bcf338f07..29408d6d6626 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -105,14 +105,14 @@ ftrace_modify_code_direct(unsigned long ip, unsigned const char *old_code, { unsigned char replaced[MCOUNT_INSN_SIZE]; + ftrace_expected = old_code; + /* - * Note: Due to modules and __init, code can - * disappear and change, we need to protect against faulting - * as well as code changing. We do this by using the - * probe_kernel_* functions. - * - * No real locking needed, this code is run through - * kstop_machine, or before SMP starts. + * Note: + * We are paranoid about modifying text, as if a bug was to happen, it + * could cause us to read or write to someplace that could cause harm. + * Carefully read and modify the code with probe_kernel_*(), and make + * sure what we read is what we expected it to be before modifying it. */ /* read the text we want to modify */ @@ -154,6 +154,8 @@ int ftrace_make_nop(struct module *mod, if (addr == MCOUNT_ADDR) return ftrace_modify_code_direct(rec->ip, old, new); + ftrace_expected = NULL; + /* Normal cases use add_brk_on_nop */ WARN_ONCE(1, "invalid use of ftrace_make_nop"); return -EINVAL; @@ -220,6 +222,7 @@ int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, unsigned long addr) { WARN_ON(1); + ftrace_expected = NULL; return -EINVAL; } @@ -314,6 +317,8 @@ static int add_break(unsigned long ip, const char *old) if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE)) return -EFAULT; + ftrace_expected = old; + /* Make sure it is what we expect it to be */ if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0) return -EINVAL; @@ -413,6 +418,8 @@ static int remove_breakpoint(struct dyn_ftrace *rec) ftrace_addr = ftrace_get_addr_curr(rec); nop = ftrace_call_replace(ip, ftrace_addr); + ftrace_expected = nop; + if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) return -EINVAL; } diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index 50a3fad5b89f..2bcfb5f2bc44 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -300,6 +300,10 @@ static int arch_build_bp_info(struct perf_event *bp) return -EINVAL; if (bp->attr.bp_addr & (bp->attr.bp_len - 1)) return -EINVAL; + + if (!boot_cpu_has(X86_FEATURE_BPEXT)) + return -EOPNOTSUPP; + /* * It's impossible to use a range breakpoint to fake out * user vs kernel detection because bp_len - 1 can't @@ -307,8 +311,6 @@ static int arch_build_bp_info(struct perf_event *bp) * breakpoints, then we'll have to check for kprobe-blacklisted * addresses anywhere in the range. */ - if (!cpu_has_bpext) - return -EOPNOTSUPP; info->mask = bp->attr.bp_len - 1; info->len = X86_BREAKPOINT_LEN_1; } diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 2bd81e302427..72cef58693c7 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -45,6 +45,11 @@ early_param("no-kvmclock", parse_no_kvmclock); static struct pvclock_vsyscall_time_info *hv_clock; static struct pvclock_wall_clock wall_clock; +struct pvclock_vsyscall_time_info *pvclock_pvti_cpu0_va(void) +{ + return hv_clock; +} + /* * The wallclock is the time of day when we booted. Since then, some time may * have elapsed since the hypervisor wrote the data. So we try to account for @@ -305,7 +310,6 @@ int __init kvm_setup_vsyscall_timeinfo(void) { #ifdef CONFIG_X86_64 int cpu; - int ret; u8 flags; struct pvclock_vcpu_time_info *vcpu_time; unsigned int size; @@ -325,11 +329,6 @@ int __init kvm_setup_vsyscall_timeinfo(void) return 1; } - if ((ret = pvclock_init_vsyscall(hv_clock, size))) { - put_cpu(); - return ret; - } - put_cpu(); kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK; diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 113e70784854..64f9616f93f1 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -45,28 +45,6 @@ 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_inode(file); - - mutex_lock(&inode->i_mutex); - switch (orig) { - case SEEK_SET: - file->f_pos = offset; - ret = file->f_pos; - break; - case SEEK_CUR: - file->f_pos += offset; - ret = file->f_pos; - break; - default: - ret = -EINVAL; - } - mutex_unlock(&inode->i_mutex); - return ret; -} - static ssize_t msr_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -194,7 +172,7 @@ static int msr_open(struct inode *inode, struct file *file) */ static const struct file_operations msr_fops = { .owner = THIS_MODULE, - .llseek = msr_seek, + .llseek = no_seek_end_llseek, .read = msr_read, .write = msr_write, .open = msr_open, diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 697f90db0e37..8a2cdd736fa4 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -29,6 +29,7 @@ #include <asm/mach_traps.h> #include <asm/nmi.h> #include <asm/x86_init.h> +#include <asm/reboot.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -231,7 +232,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) #endif if (panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); @@ -255,8 +256,16 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason, smp_processor_id()); show_regs(regs); - if (panic_on_io_nmi) - panic("NMI IOCK error: Not continuing"); + if (panic_on_io_nmi) { + nmi_panic(regs, "NMI IOCK error: Not continuing"); + + /* + * If we end up here, it means we have received an NMI while + * processing panic(). Simply return without delaying and + * re-enabling NMIs. + */ + return; + } /* Re-enable the IOCK line, wait for a few seconds */ reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK; @@ -297,7 +306,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) pr_emerg("Do you have a strange power saving mode enabled?\n"); if (unknown_nmi_panic || panic_on_unrecovered_nmi) - panic("NMI: Not continuing"); + nmi_panic(regs, "NMI: Not continuing"); pr_emerg("Dazed and confused, but trying to continue\n"); } @@ -348,8 +357,19 @@ static void default_do_nmi(struct pt_regs *regs) return; } - /* Non-CPU-specific NMI: NMI sources can be processed on any CPU */ - raw_spin_lock(&nmi_reason_lock); + /* + * Non-CPU-specific NMI: NMI sources can be processed on any CPU. + * + * Another CPU may be processing panic routines while holding + * nmi_reason_lock. Check if the CPU issued the IPI for crash dumping, + * and if so, call its callback directly. If there is no CPU preparing + * crash dump, we simply loop here. + */ + while (!raw_spin_trylock(&nmi_reason_lock)) { + run_crash_ipi_callback(regs); + cpu_relax(); + } + reason = x86_platform.get_nmi_reason(); if (reason & NMI_REASON_MASK) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index c2130aef3f9d..f08ac28b8136 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -74,16 +74,6 @@ void __init default_banner(void) /* Undefined instruction for dealing with missing ops pointers. */ static const unsigned char ud2a[] = { 0x0f, 0x0b }; -unsigned paravirt_patch_nop(void) -{ - return 0; -} - -unsigned paravirt_patch_ignore(unsigned len) -{ - return len; -} - struct branch { unsigned char opcode; u32 delta; @@ -133,7 +123,6 @@ static void *get_call_destination(u8 type) .pv_time_ops = pv_time_ops, .pv_cpu_ops = pv_cpu_ops, .pv_irq_ops = pv_irq_ops, - .pv_apic_ops = pv_apic_ops, .pv_mmu_ops = pv_mmu_ops, #ifdef CONFIG_PARAVIRT_SPINLOCKS .pv_lock_ops = pv_lock_ops, @@ -152,8 +141,7 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, /* If there's no function, patch it with a ud2a (BUG) */ ret = paravirt_patch_insns(insnbuf, len, ud2a, ud2a+sizeof(ud2a)); else if (opfunc == _paravirt_nop) - /* If the operation is a nop, then nop the callsite */ - ret = paravirt_patch_nop(); + ret = 0; /* identity functions just return their single argument */ else if (opfunc == _paravirt_ident_32) @@ -162,10 +150,6 @@ unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf, ret = paravirt_patch_ident_64(insnbuf, len); else if (type == PARAVIRT_PATCH(pv_cpu_ops.iret) || -#ifdef CONFIG_X86_32 - type == PARAVIRT_PATCH(pv_cpu_ops.irq_enable_sysexit) || -#endif - type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret32) || type == PARAVIRT_PATCH(pv_cpu_ops.usergs_sysret64)) /* If operation requires a jmp, then jmp */ ret = paravirt_patch_jmp(insnbuf, opfunc, addr, len); @@ -220,8 +204,6 @@ static u64 native_steal_clock(int cpu) /* These are in entry.S */ extern void native_iret(void); -extern void native_irq_enable_sysexit(void); -extern void native_usergs_sysret32(void); extern void native_usergs_sysret64(void); static struct resource reserve_ioports = { @@ -379,13 +361,7 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .load_sp0 = native_load_sp0, -#if defined(CONFIG_X86_32) - .irq_enable_sysexit = native_irq_enable_sysexit, -#endif #ifdef CONFIG_X86_64 -#ifdef CONFIG_IA32_EMULATION - .usergs_sysret32 = native_usergs_sysret32, -#endif .usergs_sysret64 = native_usergs_sysret64, #endif .iret = native_iret, @@ -403,12 +379,6 @@ NOKPROBE_SYMBOL(native_get_debugreg); NOKPROBE_SYMBOL(native_set_debugreg); NOKPROBE_SYMBOL(native_load_idt); -struct pv_apic_ops pv_apic_ops = { -#ifdef CONFIG_X86_LOCAL_APIC - .startup_ipi_hook = paravirt_nop, -#endif -}; - #if defined(CONFIG_X86_32) && !defined(CONFIG_X86_PAE) /* 32-bit pagetable entries */ #define PTE_IDENT __PV_IS_CALLEE_SAVE(_paravirt_ident_32) @@ -444,9 +414,6 @@ struct pv_mmu_ops pv_mmu_ops = { .set_pmd = native_set_pmd, .set_pmd_at = native_set_pmd_at, .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, - .pmd_update = paravirt_nop, - .pmd_update_defer = paravirt_nop, .ptep_modify_prot_start = __ptep_modify_prot_start, .ptep_modify_prot_commit = __ptep_modify_prot_commit, @@ -492,6 +459,5 @@ struct pv_mmu_ops pv_mmu_ops = { EXPORT_SYMBOL_GPL(pv_time_ops); EXPORT_SYMBOL (pv_cpu_ops); EXPORT_SYMBOL (pv_mmu_ops); -EXPORT_SYMBOL_GPL(pv_apic_ops); EXPORT_SYMBOL_GPL(pv_info); EXPORT_SYMBOL (pv_irq_ops); diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c index c89f50a76e97..158dc0650d5d 100644 --- a/arch/x86/kernel/paravirt_patch_32.c +++ b/arch/x86/kernel/paravirt_patch_32.c @@ -5,7 +5,6 @@ DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); DEF_NATIVE(pv_irq_ops, restore_fl, "push %eax; popf"); DEF_NATIVE(pv_irq_ops, save_fl, "pushf; pop %eax"); DEF_NATIVE(pv_cpu_ops, iret, "iret"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "sti; sysexit"); DEF_NATIVE(pv_mmu_ops, read_cr2, "mov %cr2, %eax"); DEF_NATIVE(pv_mmu_ops, write_cr3, "mov %eax, %cr3"); DEF_NATIVE(pv_mmu_ops, read_cr3, "mov %cr3, %eax"); @@ -46,7 +45,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, restore_fl); PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_cpu_ops, iret); - PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); PATCH_SITE(pv_mmu_ops, read_cr2); PATCH_SITE(pv_mmu_ops, read_cr3); PATCH_SITE(pv_mmu_ops, write_cr3); diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c index 8aa05583bc42..e70087a04cc8 100644 --- a/arch/x86/kernel/paravirt_patch_64.c +++ b/arch/x86/kernel/paravirt_patch_64.c @@ -13,9 +13,7 @@ DEF_NATIVE(pv_mmu_ops, flush_tlb_single, "invlpg (%rdi)"); DEF_NATIVE(pv_cpu_ops, clts, "clts"); DEF_NATIVE(pv_cpu_ops, wbinvd, "wbinvd"); -DEF_NATIVE(pv_cpu_ops, irq_enable_sysexit, "swapgs; sti; sysexit"); DEF_NATIVE(pv_cpu_ops, usergs_sysret64, "swapgs; sysretq"); -DEF_NATIVE(pv_cpu_ops, usergs_sysret32, "swapgs; sysretl"); DEF_NATIVE(pv_cpu_ops, swapgs, "swapgs"); DEF_NATIVE(, mov32, "mov %edi, %eax"); @@ -55,7 +53,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, PATCH_SITE(pv_irq_ops, save_fl); PATCH_SITE(pv_irq_ops, irq_enable); PATCH_SITE(pv_irq_ops, irq_disable); - PATCH_SITE(pv_cpu_ops, usergs_sysret32); PATCH_SITE(pv_cpu_ops, usergs_sysret64); PATCH_SITE(pv_cpu_ops, swapgs); PATCH_SITE(pv_mmu_ops, read_cr2); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 0497f719977d..833b1d329c47 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -180,13 +180,13 @@ static void calioc2_dump_error_regs(struct iommu_table *tbl); static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl); static void get_tce_space_from_tar(void); -static struct cal_chipset_ops calgary_chip_ops = { +static const struct cal_chipset_ops calgary_chip_ops = { .handle_quirks = calgary_handle_quirks, .tce_cache_blast = calgary_tce_cache_blast, .dump_error_regs = calgary_dump_error_regs }; -static struct cal_chipset_ops calioc2_chip_ops = { +static const struct cal_chipset_ops calioc2_chip_ops = { .handle_quirks = calioc2_handle_quirks, .tce_cache_blast = calioc2_tce_cache_blast, .dump_error_regs = calioc2_dump_error_regs diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index adf0392d549a..7c577a178859 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -88,7 +88,7 @@ int __init pci_swiotlb_detect_4gb(void) { /* don't initialize swiotlb if iommu=off (no_iommu=1) */ #ifdef CONFIG_X86_64 - if (!no_iommu && max_pfn > MAX_DMA32_PFN) + if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN) swiotlb = 1; #endif return swiotlb; diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index e835d263a33b..b9d99e0f82c4 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -125,7 +125,7 @@ void release_thread(struct task_struct *dead_task) if (dead_task->mm->context.ldt) { pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n", dead_task->comm, - dead_task->mm->context.ldt, + dead_task->mm->context.ldt->entries, dead_task->mm->context.ldt->size); BUG(); } diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 558f50edebca..32e9d9cbb884 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -124,21 +124,6 @@ const char *regs_query_register_name(unsigned int offset) return NULL; } -static const int arg_offs_table[] = { -#ifdef CONFIG_X86_32 - [0] = offsetof(struct pt_regs, ax), - [1] = offsetof(struct pt_regs, dx), - [2] = offsetof(struct pt_regs, cx) -#else /* CONFIG_X86_64 */ - [0] = offsetof(struct pt_regs, di), - [1] = offsetof(struct pt_regs, si), - [2] = offsetof(struct pt_regs, dx), - [3] = offsetof(struct pt_regs, cx), - [4] = offsetof(struct pt_regs, r8), - [5] = offsetof(struct pt_regs, r9) -#endif -}; - /* * does not yet catch signals sent when the child dies. * in exit.c or in signal.c. diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 2f355d229a58..99bfc025111d 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -140,27 +140,3 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } - -#ifdef CONFIG_X86_64 -/* - * Initialize the generic pvclock vsyscall state. This will allocate - * a/some page(s) for the per-vcpu pvclock information, set up a - * fixmap mapping for the page(s) - */ - -int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, - int size) -{ - int idx; - - WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - - 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); - } - - return 0; -} -#endif diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 02693dd9a079..d64889aa2d46 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -718,6 +718,7 @@ static int crashing_cpu; static nmi_shootdown_cb shootdown_callback; static atomic_t waiting_for_crash_ipi; +static int crash_ipi_issued; static int crash_nmi_callback(unsigned int val, struct pt_regs *regs) { @@ -780,6 +781,9 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) smp_send_nmi_allbutself(); + /* Kick CPUs looping in NMI context. */ + WRITE_ONCE(crash_ipi_issued, 1); + msecs = 1000; /* Wait at most a second for the other cpus to stop */ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { mdelay(1); @@ -788,9 +792,35 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback) /* Leave the nmi callback set */ } + +/* + * Check if the crash dumping IPI got issued and if so, call its callback + * directly. This function is used when we have already been in NMI handler. + * It doesn't return. + */ +void run_crash_ipi_callback(struct pt_regs *regs) +{ + if (crash_ipi_issued) + crash_nmi_callback(0, regs); +} + +/* Override the weak function in kernel/panic.c */ +void nmi_panic_self_stop(struct pt_regs *regs) +{ + while (1) { + /* If no CPU is preparing crash dump, we simply loop here. */ + run_crash_ipi_callback(regs); + cpu_relax(); + } +} + #else /* !CONFIG_SMP */ void nmi_shootdown_cpus(nmi_shootdown_cb callback) { /* No other CPUs to shoot down */ } + +void run_crash_ipi_callback(struct pt_regs *regs) +{ +} #endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d2bbe343fda7..d3d80e6d42a2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1048,6 +1048,8 @@ void __init setup_arch(char **cmdline_p) if (mtrr_trim_uncached_memory(max_pfn)) max_pfn = e820_end_of_ram_pfn(); + max_possible_pfn = max_pfn; + #ifdef CONFIG_X86_32 /* max_low_pfn get updated here */ find_low_pfn_range(); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 12c8286206ce..658777cf3851 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -125,12 +125,12 @@ static void native_smp_send_reschedule(int cpu) WARN_ON(1); return; } - apic->send_IPI_mask(cpumask_of(cpu), RESCHEDULE_VECTOR); + apic->send_IPI(cpu, RESCHEDULE_VECTOR); } void native_send_call_func_single_ipi(int cpu) { - apic->send_IPI_mask(cpumask_of(cpu), CALL_FUNCTION_SINGLE_VECTOR); + apic->send_IPI(cpu, CALL_FUNCTION_SINGLE_VECTOR); } void native_send_call_func_ipi(const struct cpumask *mask) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index fbabe4fcc7fb..24d57f77b3c1 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -304,7 +304,7 @@ do { \ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (cpu_has_topoext) { + if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; if (c->phys_proc_id == o->phys_proc_id && @@ -630,13 +630,6 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) num_starts = 0; /* - * Paravirt / VMI wants a startup IPI hook here to set up the - * target processor state. - */ - startup_ipi_hook(phys_apicid, (unsigned long) start_secondary, - stack_start); - - /* * Run STARTUP IPI loop. */ pr_debug("#startup loops: %d\n", num_starts); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index c7c4d9c51e99..3d743da828d3 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1185,8 +1185,6 @@ void __init tsc_init(void) u64 lpj; int cpu; - x86_init.timers.tsc_pre_init(); - if (!cpu_has_tsc) { setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER); return; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 524619351961..483231ebbb0b 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -357,8 +357,10 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus) tss = &per_cpu(cpu_tss, get_cpu()); /* make room for real-mode segments */ tsk->thread.sp0 += 16; - if (cpu_has_sep) + + if (static_cpu_has_safe(X86_FEATURE_SEP)) tsk->thread.sysenter_cs = 0; + load_sp0(tss, &tsk->thread); put_cpu(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 3839628d962e..dad5fe9633a3 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -68,7 +68,6 @@ struct x86_init_ops x86_init __initdata = { .timers = { .setup_percpu_clockev = setup_boot_APIC_clock, - .tsc_pre_init = x86_init_noop, .timer_init = hpet_time_init, .wallclock_init = x86_init_noop, }, diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 3f5c48ddba45..c8eda1498121 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -2,6 +2,7 @@ #define ARCH_X86_KVM_CPUID_H #include "x86.h" +#include <asm/cpu.h> int kvm_update_cpuid(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, @@ -178,4 +179,37 @@ static inline bool guest_cpuid_has_nrips(struct kvm_vcpu *vcpu) } #undef BIT_NRIPS +static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_family(best->eax); +} + +static inline int guest_cpuid_model(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_model(best->eax); +} + +static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + if (!best) + return -1; + + return x86_stepping(best->eax); +} + #endif diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 62cf8c915e95..c58ba67175ac 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -23,13 +23,665 @@ #include "x86.h" #include "lapic.h" +#include "ioapic.h" #include "hyperv.h" #include <linux/kvm_host.h> +#include <linux/highmem.h> +#include <asm/apicdef.h> #include <trace/events/kvm.h> #include "trace.h" +static inline u64 synic_read_sint(struct kvm_vcpu_hv_synic *synic, int sint) +{ + return atomic64_read(&synic->sint[sint]); +} + +static inline int synic_get_sint_vector(u64 sint_value) +{ + if (sint_value & HV_SYNIC_SINT_MASKED) + return -1; + return sint_value & HV_SYNIC_SINT_VECTOR_MASK; +} + +static bool synic_has_vector_connected(struct kvm_vcpu_hv_synic *synic, + int vector) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { + if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector) + return true; + } + return false; +} + +static bool synic_has_vector_auto_eoi(struct kvm_vcpu_hv_synic *synic, + int vector) +{ + int i; + u64 sint_value; + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { + sint_value = synic_read_sint(synic, i); + if (synic_get_sint_vector(sint_value) == vector && + sint_value & HV_SYNIC_SINT_AUTO_EOI) + return true; + } + return false; +} + +static int synic_set_sint(struct kvm_vcpu_hv_synic *synic, int sint, + u64 data, bool host) +{ + int vector; + + vector = data & HV_SYNIC_SINT_VECTOR_MASK; + if (vector < 16 && !host) + return 1; + /* + * Guest may configure multiple SINTs to use the same vector, so + * we maintain a bitmap of vectors handled by synic, and a + * bitmap of vectors with auto-eoi behavior. The bitmaps are + * updated here, and atomically queried on fast paths. + */ + + atomic64_set(&synic->sint[sint], data); + + if (synic_has_vector_connected(synic, vector)) + __set_bit(vector, synic->vec_bitmap); + else + __clear_bit(vector, synic->vec_bitmap); + + if (synic_has_vector_auto_eoi(synic, vector)) + __set_bit(vector, synic->auto_eoi_bitmap); + else + __clear_bit(vector, synic->auto_eoi_bitmap); + + /* Load SynIC vectors into EOI exit bitmap */ + kvm_make_request(KVM_REQ_SCAN_IOAPIC, synic_to_vcpu(synic)); + return 0; +} + +static struct kvm_vcpu_hv_synic *synic_get(struct kvm *kvm, u32 vcpu_id) +{ + struct kvm_vcpu *vcpu; + struct kvm_vcpu_hv_synic *synic; + + if (vcpu_id >= atomic_read(&kvm->online_vcpus)) + return NULL; + vcpu = kvm_get_vcpu(kvm, vcpu_id); + if (!vcpu) + return NULL; + synic = vcpu_to_synic(vcpu); + return (synic->active) ? synic : NULL; +} + +static void synic_clear_sint_msg_pending(struct kvm_vcpu_hv_synic *synic, + u32 sint) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct page *page; + gpa_t gpa; + struct hv_message *msg; + struct hv_message_page *msg_page; + + gpa = synic->msg_page & PAGE_MASK; + page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); + if (is_error_page(page)) { + vcpu_err(vcpu, "Hyper-V SynIC can't get msg page, gpa 0x%llx\n", + gpa); + return; + } + msg_page = kmap_atomic(page); + + msg = &msg_page->sint_message[sint]; + msg->header.message_flags.msg_pending = 0; + + kunmap_atomic(msg_page); + kvm_release_page_dirty(page); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); +} + +static void kvm_hv_notify_acked_sint(struct kvm_vcpu *vcpu, u32 sint) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv_stimer *stimer; + int gsi, idx, stimers_pending; + + trace_kvm_hv_notify_acked_sint(vcpu->vcpu_id, sint); + + if (synic->msg_page & HV_SYNIC_SIMP_ENABLE) + synic_clear_sint_msg_pending(synic, sint); + + /* Try to deliver pending Hyper-V SynIC timers messages */ + stimers_pending = 0; + for (idx = 0; idx < ARRAY_SIZE(hv_vcpu->stimer); idx++) { + stimer = &hv_vcpu->stimer[idx]; + if (stimer->msg_pending && + (stimer->config & HV_STIMER_ENABLE) && + HV_STIMER_SINT(stimer->config) == sint) { + set_bit(stimer->index, + hv_vcpu->stimer_pending_bitmap); + stimers_pending++; + } + } + if (stimers_pending) + kvm_make_request(KVM_REQ_HV_STIMER, vcpu); + + idx = srcu_read_lock(&kvm->irq_srcu); + gsi = atomic_read(&synic->sint_to_gsi[sint]); + if (gsi != -1) + kvm_notify_acked_gsi(kvm, gsi); + srcu_read_unlock(&kvm->irq_srcu, idx); +} + +static void synic_exit(struct kvm_vcpu_hv_synic *synic, u32 msr) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv; + + hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNIC; + hv_vcpu->exit.u.synic.msr = msr; + hv_vcpu->exit.u.synic.control = synic->control; + hv_vcpu->exit.u.synic.evt_page = synic->evt_page; + hv_vcpu->exit.u.synic.msg_page = synic->msg_page; + + kvm_make_request(KVM_REQ_HV_EXIT, vcpu); +} + +static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, + u32 msr, u64 data, bool host) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + int ret; + + if (!synic->active) + return 1; + + trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host); + + ret = 0; + switch (msr) { + case HV_X64_MSR_SCONTROL: + synic->control = data; + if (!host) + synic_exit(synic, msr); + break; + case HV_X64_MSR_SVERSION: + if (!host) { + ret = 1; + break; + } + synic->version = data; + break; + case HV_X64_MSR_SIEFP: + if (data & HV_SYNIC_SIEFP_ENABLE) + if (kvm_clear_guest(vcpu->kvm, + data & PAGE_MASK, PAGE_SIZE)) { + ret = 1; + break; + } + synic->evt_page = data; + if (!host) + synic_exit(synic, msr); + break; + case HV_X64_MSR_SIMP: + if (data & HV_SYNIC_SIMP_ENABLE) + if (kvm_clear_guest(vcpu->kvm, + data & PAGE_MASK, PAGE_SIZE)) { + ret = 1; + break; + } + synic->msg_page = data; + if (!host) + synic_exit(synic, msr); + break; + case HV_X64_MSR_EOM: { + int i; + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) + kvm_hv_notify_acked_sint(vcpu, i); + break; + } + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + ret = synic_set_sint(synic, msr - HV_X64_MSR_SINT0, data, host); + break; + default: + ret = 1; + break; + } + return ret; +} + +static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata) +{ + int ret; + + if (!synic->active) + return 1; + + ret = 0; + switch (msr) { + case HV_X64_MSR_SCONTROL: + *pdata = synic->control; + break; + case HV_X64_MSR_SVERSION: + *pdata = synic->version; + break; + case HV_X64_MSR_SIEFP: + *pdata = synic->evt_page; + break; + case HV_X64_MSR_SIMP: + *pdata = synic->msg_page; + break; + case HV_X64_MSR_EOM: + *pdata = 0; + break; + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + *pdata = atomic64_read(&synic->sint[msr - HV_X64_MSR_SINT0]); + break; + default: + ret = 1; + break; + } + return ret; +} + +int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct kvm_lapic_irq irq; + int ret, vector; + + if (sint >= ARRAY_SIZE(synic->sint)) + return -EINVAL; + + vector = synic_get_sint_vector(synic_read_sint(synic, sint)); + if (vector < 0) + return -ENOENT; + + memset(&irq, 0, sizeof(irq)); + irq.dest_id = kvm_apic_id(vcpu->arch.apic); + irq.dest_mode = APIC_DEST_PHYSICAL; + irq.delivery_mode = APIC_DM_FIXED; + irq.vector = vector; + irq.level = 1; + + ret = kvm_irq_delivery_to_apic(vcpu->kvm, NULL, &irq, NULL); + trace_kvm_hv_synic_set_irq(vcpu->vcpu_id, sint, irq.vector, ret); + return ret; +} + +int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint) +{ + struct kvm_vcpu_hv_synic *synic; + + synic = synic_get(kvm, vcpu_id); + if (!synic) + return -EINVAL; + + return synic_set_irq(synic, sint); +} + +void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) +{ + struct kvm_vcpu_hv_synic *synic = vcpu_to_synic(vcpu); + int i; + + trace_kvm_hv_synic_send_eoi(vcpu->vcpu_id, vector); + + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) + if (synic_get_sint_vector(synic_read_sint(synic, i)) == vector) + kvm_hv_notify_acked_sint(vcpu, i); +} + +static int kvm_hv_set_sint_gsi(struct kvm *kvm, u32 vcpu_id, u32 sint, int gsi) +{ + struct kvm_vcpu_hv_synic *synic; + + synic = synic_get(kvm, vcpu_id); + if (!synic) + return -EINVAL; + + if (sint >= ARRAY_SIZE(synic->sint_to_gsi)) + return -EINVAL; + + atomic_set(&synic->sint_to_gsi[sint], gsi); + return 0; +} + +void kvm_hv_irq_routing_update(struct kvm *kvm) +{ + struct kvm_irq_routing_table *irq_rt; + struct kvm_kernel_irq_routing_entry *e; + u32 gsi; + + irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu, + lockdep_is_held(&kvm->irq_lock)); + + for (gsi = 0; gsi < irq_rt->nr_rt_entries; gsi++) { + hlist_for_each_entry(e, &irq_rt->map[gsi], link) { + if (e->type == KVM_IRQ_ROUTING_HV_SINT) + kvm_hv_set_sint_gsi(kvm, e->hv_sint.vcpu, + e->hv_sint.sint, gsi); + } + } +} + +static void synic_init(struct kvm_vcpu_hv_synic *synic) +{ + int i; + + memset(synic, 0, sizeof(*synic)); + synic->version = HV_SYNIC_VERSION_1; + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) { + atomic64_set(&synic->sint[i], HV_SYNIC_SINT_MASKED); + atomic_set(&synic->sint_to_gsi[i], -1); + } +} + +static u64 get_time_ref_counter(struct kvm *kvm) +{ + return div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); +} + +static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, + bool vcpu_kick) +{ + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + + set_bit(stimer->index, + vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap); + kvm_make_request(KVM_REQ_HV_STIMER, vcpu); + if (vcpu_kick) + kvm_vcpu_kick(vcpu); +} + +static void stimer_cleanup(struct kvm_vcpu_hv_stimer *stimer) +{ + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + + trace_kvm_hv_stimer_cleanup(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index); + + hrtimer_cancel(&stimer->timer); + clear_bit(stimer->index, + vcpu_to_hv_vcpu(vcpu)->stimer_pending_bitmap); + stimer->msg_pending = false; + stimer->exp_time = 0; +} + +static enum hrtimer_restart stimer_timer_callback(struct hrtimer *timer) +{ + struct kvm_vcpu_hv_stimer *stimer; + + stimer = container_of(timer, struct kvm_vcpu_hv_stimer, timer); + trace_kvm_hv_stimer_callback(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index); + stimer_mark_pending(stimer, true); + + return HRTIMER_NORESTART; +} + +/* + * stimer_start() assumptions: + * a) stimer->count is not equal to 0 + * b) stimer->config has HV_STIMER_ENABLE flag + */ +static int stimer_start(struct kvm_vcpu_hv_stimer *stimer) +{ + u64 time_now; + ktime_t ktime_now; + + time_now = get_time_ref_counter(stimer_to_vcpu(stimer)->kvm); + ktime_now = ktime_get(); + + if (stimer->config & HV_STIMER_PERIODIC) { + if (stimer->exp_time) { + if (time_now >= stimer->exp_time) { + u64 remainder; + + div64_u64_rem(time_now - stimer->exp_time, + stimer->count, &remainder); + stimer->exp_time = + time_now + (stimer->count - remainder); + } + } else + stimer->exp_time = time_now + stimer->count; + + trace_kvm_hv_stimer_start_periodic( + stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, + time_now, stimer->exp_time); + + hrtimer_start(&stimer->timer, + ktime_add_ns(ktime_now, + 100 * (stimer->exp_time - time_now)), + HRTIMER_MODE_ABS); + return 0; + } + stimer->exp_time = stimer->count; + if (time_now >= stimer->count) { + /* + * Expire timer according to Hypervisor Top-Level Functional + * specification v4(15.3.1): + * "If a one shot is enabled and the specified count is in + * the past, it will expire immediately." + */ + stimer_mark_pending(stimer, false); + return 0; + } + + trace_kvm_hv_stimer_start_one_shot(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, + time_now, stimer->count); + + hrtimer_start(&stimer->timer, + ktime_add_ns(ktime_now, 100 * (stimer->count - time_now)), + HRTIMER_MODE_ABS); + return 0; +} + +static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, + bool host) +{ + trace_kvm_hv_stimer_set_config(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, config, host); + + stimer_cleanup(stimer); + if ((stimer->config & HV_STIMER_ENABLE) && HV_STIMER_SINT(config) == 0) + config &= ~HV_STIMER_ENABLE; + stimer->config = config; + stimer_mark_pending(stimer, false); + return 0; +} + +static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, + bool host) +{ + trace_kvm_hv_stimer_set_count(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, count, host); + + stimer_cleanup(stimer); + stimer->count = count; + if (stimer->count == 0) + stimer->config &= ~HV_STIMER_ENABLE; + else if (stimer->config & HV_STIMER_AUTOENABLE) + stimer->config |= HV_STIMER_ENABLE; + stimer_mark_pending(stimer, false); + return 0; +} + +static int stimer_get_config(struct kvm_vcpu_hv_stimer *stimer, u64 *pconfig) +{ + *pconfig = stimer->config; + return 0; +} + +static int stimer_get_count(struct kvm_vcpu_hv_stimer *stimer, u64 *pcount) +{ + *pcount = stimer->count; + return 0; +} + +static int synic_deliver_msg(struct kvm_vcpu_hv_synic *synic, u32 sint, + struct hv_message *src_msg) +{ + struct kvm_vcpu *vcpu = synic_to_vcpu(synic); + struct page *page; + gpa_t gpa; + struct hv_message *dst_msg; + int r; + struct hv_message_page *msg_page; + + if (!(synic->msg_page & HV_SYNIC_SIMP_ENABLE)) + return -ENOENT; + + gpa = synic->msg_page & PAGE_MASK; + page = kvm_vcpu_gfn_to_page(vcpu, gpa >> PAGE_SHIFT); + if (is_error_page(page)) + return -EFAULT; + + msg_page = kmap_atomic(page); + dst_msg = &msg_page->sint_message[sint]; + if (sync_cmpxchg(&dst_msg->header.message_type, HVMSG_NONE, + src_msg->header.message_type) != HVMSG_NONE) { + dst_msg->header.message_flags.msg_pending = 1; + r = -EAGAIN; + } else { + memcpy(&dst_msg->u.payload, &src_msg->u.payload, + src_msg->header.payload_size); + dst_msg->header.message_type = src_msg->header.message_type; + dst_msg->header.payload_size = src_msg->header.payload_size; + r = synic_set_irq(synic, sint); + if (r >= 1) + r = 0; + else if (r == 0) + r = -EFAULT; + } + kunmap_atomic(msg_page); + kvm_release_page_dirty(page); + kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); + return r; +} + +static int stimer_send_msg(struct kvm_vcpu_hv_stimer *stimer) +{ + struct kvm_vcpu *vcpu = stimer_to_vcpu(stimer); + struct hv_message *msg = &stimer->msg; + struct hv_timer_message_payload *payload = + (struct hv_timer_message_payload *)&msg->u.payload; + + payload->expiration_time = stimer->exp_time; + payload->delivery_time = get_time_ref_counter(vcpu->kvm); + return synic_deliver_msg(vcpu_to_synic(vcpu), + HV_STIMER_SINT(stimer->config), msg); +} + +static void stimer_expiration(struct kvm_vcpu_hv_stimer *stimer) +{ + int r; + + stimer->msg_pending = true; + r = stimer_send_msg(stimer); + trace_kvm_hv_stimer_expiration(stimer_to_vcpu(stimer)->vcpu_id, + stimer->index, r); + if (!r) { + stimer->msg_pending = false; + if (!(stimer->config & HV_STIMER_PERIODIC)) + stimer->config &= ~HV_STIMER_ENABLE; + } +} + +void kvm_hv_process_stimers(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + struct kvm_vcpu_hv_stimer *stimer; + u64 time_now, exp_time; + int i; + + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) + if (test_and_clear_bit(i, hv_vcpu->stimer_pending_bitmap)) { + stimer = &hv_vcpu->stimer[i]; + if (stimer->config & HV_STIMER_ENABLE) { + exp_time = stimer->exp_time; + + if (exp_time) { + time_now = + get_time_ref_counter(vcpu->kvm); + if (time_now >= exp_time) + stimer_expiration(stimer); + } + + if ((stimer->config & HV_STIMER_ENABLE) && + stimer->count) + stimer_start(stimer); + else + stimer_cleanup(stimer); + } + } +} + +void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + int i; + + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) + stimer_cleanup(&hv_vcpu->stimer[i]); +} + +static void stimer_prepare_msg(struct kvm_vcpu_hv_stimer *stimer) +{ + struct hv_message *msg = &stimer->msg; + struct hv_timer_message_payload *payload = + (struct hv_timer_message_payload *)&msg->u.payload; + + memset(&msg->header, 0, sizeof(msg->header)); + msg->header.message_type = HVMSG_TIMER_EXPIRED; + msg->header.payload_size = sizeof(*payload); + + payload->timer_index = stimer->index; + payload->expiration_time = 0; + payload->delivery_time = 0; +} + +static void stimer_init(struct kvm_vcpu_hv_stimer *stimer, int timer_index) +{ + memset(stimer, 0, sizeof(*stimer)); + stimer->index = timer_index; + hrtimer_init(&stimer->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + stimer->timer.function = stimer_timer_callback; + stimer_prepare_msg(stimer); +} + +void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = vcpu_to_hv_vcpu(vcpu); + int i; + + synic_init(&hv_vcpu->synic); + + bitmap_zero(hv_vcpu->stimer_pending_bitmap, HV_SYNIC_STIMER_COUNT); + for (i = 0; i < ARRAY_SIZE(hv_vcpu->stimer); i++) + stimer_init(&hv_vcpu->stimer[i], i); +} + +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu) +{ + /* + * Hyper-V SynIC auto EOI SINT's are + * not compatible with APICV, so deactivate APICV + */ + kvm_vcpu_deactivate_apicv(vcpu); + vcpu_to_synic(vcpu)->active = true; + return 0; +} + static bool kvm_hv_msr_partition_wide(u32 msr) { bool r = false; @@ -226,6 +878,31 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) return 1; hv->runtime_offset = data - current_task_runtime_100ns(); break; + case HV_X64_MSR_SCONTROL: + case HV_X64_MSR_SVERSION: + case HV_X64_MSR_SIEFP: + case HV_X64_MSR_SIMP: + case HV_X64_MSR_EOM: + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + return synic_set_msr(vcpu_to_synic(vcpu), msr, data, host); + case HV_X64_MSR_STIMER0_CONFIG: + case HV_X64_MSR_STIMER1_CONFIG: + case HV_X64_MSR_STIMER2_CONFIG: + case HV_X64_MSR_STIMER3_CONFIG: { + int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; + + return stimer_set_config(vcpu_to_stimer(vcpu, timer_index), + data, host); + } + case HV_X64_MSR_STIMER0_COUNT: + case HV_X64_MSR_STIMER1_COUNT: + case HV_X64_MSR_STIMER2_COUNT: + case HV_X64_MSR_STIMER3_COUNT: { + int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; + + return stimer_set_count(vcpu_to_stimer(vcpu, timer_index), + data, host); + } default: vcpu_unimpl(vcpu, "Hyper-V uhandled wrmsr: 0x%x data 0x%llx\n", msr, data); @@ -248,11 +925,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case HV_X64_MSR_HYPERCALL: data = hv->hv_hypercall; break; - case HV_X64_MSR_TIME_REF_COUNT: { - data = - div_u64(get_kernel_ns() + kvm->arch.kvmclock_offset, 100); + case HV_X64_MSR_TIME_REF_COUNT: + data = get_time_ref_counter(kvm); break; - } case HV_X64_MSR_REFERENCE_TSC: data = hv->hv_tsc_page; break; @@ -304,6 +979,31 @@ static int kvm_hv_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case HV_X64_MSR_VP_RUNTIME: data = current_task_runtime_100ns() + hv->runtime_offset; break; + case HV_X64_MSR_SCONTROL: + case HV_X64_MSR_SVERSION: + case HV_X64_MSR_SIEFP: + case HV_X64_MSR_SIMP: + case HV_X64_MSR_EOM: + case HV_X64_MSR_SINT0 ... HV_X64_MSR_SINT15: + return synic_get_msr(vcpu_to_synic(vcpu), msr, pdata); + case HV_X64_MSR_STIMER0_CONFIG: + case HV_X64_MSR_STIMER1_CONFIG: + case HV_X64_MSR_STIMER2_CONFIG: + case HV_X64_MSR_STIMER3_CONFIG: { + int timer_index = (msr - HV_X64_MSR_STIMER0_CONFIG)/2; + + return stimer_get_config(vcpu_to_stimer(vcpu, timer_index), + pdata); + } + case HV_X64_MSR_STIMER0_COUNT: + case HV_X64_MSR_STIMER1_COUNT: + case HV_X64_MSR_STIMER2_COUNT: + case HV_X64_MSR_STIMER3_COUNT: { + int timer_index = (msr - HV_X64_MSR_STIMER0_COUNT)/2; + + return stimer_get_count(vcpu_to_stimer(vcpu, timer_index), + pdata); + } default: vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); return 1; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index c7bce559f67b..60eccd4bd1d3 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -24,9 +24,64 @@ #ifndef __ARCH_X86_KVM_HYPERV_H__ #define __ARCH_X86_KVM_HYPERV_H__ +static inline struct kvm_vcpu_hv *vcpu_to_hv_vcpu(struct kvm_vcpu *vcpu) +{ + return &vcpu->arch.hyperv; +} + +static inline struct kvm_vcpu *hv_vcpu_to_vcpu(struct kvm_vcpu_hv *hv_vcpu) +{ + struct kvm_vcpu_arch *arch; + + arch = container_of(hv_vcpu, struct kvm_vcpu_arch, hyperv); + return container_of(arch, struct kvm_vcpu, arch); +} + +static inline struct kvm_vcpu_hv_synic *vcpu_to_synic(struct kvm_vcpu *vcpu) +{ + return &vcpu->arch.hyperv.synic; +} + +static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic) +{ + return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic)); +} + int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host); int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); + bool kvm_hv_hypercall_enabled(struct kvm *kvm); int kvm_hv_hypercall(struct kvm_vcpu *vcpu); +void kvm_hv_irq_routing_update(struct kvm *kvm); +int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); +void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); +int kvm_hv_activate_synic(struct kvm_vcpu *vcpu); + +void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); +void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); + +static inline struct kvm_vcpu_hv_stimer *vcpu_to_stimer(struct kvm_vcpu *vcpu, + int timer_index) +{ + return &vcpu_to_hv_vcpu(vcpu)->stimer[timer_index]; +} + +static inline struct kvm_vcpu *stimer_to_vcpu(struct kvm_vcpu_hv_stimer *stimer) +{ + struct kvm_vcpu_hv *hv_vcpu; + + hv_vcpu = container_of(stimer - stimer->index, struct kvm_vcpu_hv, + stimer[0]); + return hv_vcpu_to_vcpu(hv_vcpu); +} + +static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) +{ + return !bitmap_empty(vcpu->arch.hyperv.stimer_pending_bitmap, + HV_SYNIC_STIMER_COUNT); +} + +void kvm_hv_process_stimers(struct kvm_vcpu *vcpu); + #endif diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 88d0a92d3f94..1facfd60b04a 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -233,7 +233,7 @@ static void kvm_ioapic_inject_all(struct kvm_ioapic *ioapic, unsigned long irr) } -void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors) { struct kvm_ioapic *ioapic = vcpu->kvm->arch.vioapic; union kvm_ioapic_redirect_entry *e; @@ -250,7 +250,7 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) (e->fields.trig_mode == IOAPIC_EDGE_TRIG && kvm_apic_pending_eoi(vcpu, e->fields.vector))) __set_bit(e->fields.vector, - (unsigned long *)eoi_exit_bitmap); + ioapic_handled_vectors); } } spin_unlock(&ioapic->lock); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index 084617d37c74..2d16dc251d81 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -121,7 +121,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src, struct kvm_lapic_irq *irq, unsigned long *dest_map); int kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); int kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state); -void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); -void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); - +void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors); +void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors); #endif diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 097060e33bd6..3982b479bb5f 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -76,7 +76,7 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v) if (kvm_cpu_has_extint(v)) return 1; - if (kvm_vcpu_apic_vid_enabled(v)) + if (kvm_vcpu_apicv_active(v)) return 0; return kvm_apic_has_interrupt(v) != -1; /* LAPIC */ diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 84b96d319909..8fc89efb5250 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -33,6 +33,8 @@ #include "lapic.h" +#include "hyperv.h" + static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -219,6 +221,16 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin, srcu_read_unlock(&kvm->irq_srcu, idx); } +static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) +{ + if (!level) + return -1; + + return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); +} + int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { @@ -257,6 +269,11 @@ int kvm_set_routing_entry(struct kvm_kernel_irq_routing_entry *e, e->msi.address_hi = ue->u.msi.address_hi; e->msi.data = ue->u.msi.data; break; + case KVM_IRQ_ROUTING_HV_SINT: + e->set = kvm_hv_set_sint; + e->hv_sint.vcpu = ue->u.hv_sint.vcpu; + e->hv_sint.sint = ue->u.hv_sint.sint; + break; default: goto out; } @@ -332,14 +349,15 @@ int kvm_setup_empty_irq_routing(struct kvm *kvm) return kvm_set_irq_routing(kvm, empty_routing, 0, 0); } -void kvm_arch_irq_routing_update(struct kvm *kvm) +void kvm_arch_post_irq_routing_update(struct kvm *kvm) { if (ioapic_in_kernel(kvm) || !irqchip_in_kernel(kvm)) return; kvm_make_scan_ioapic_request(kvm); } -void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, + ulong *ioapic_handled_vectors) { struct kvm *kvm = vcpu->kvm; struct kvm_kernel_irq_routing_entry *entry; @@ -369,9 +387,26 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) u32 vector = entry->msi.data & 0xff; __set_bit(vector, - (unsigned long *) eoi_exit_bitmap); + ioapic_handled_vectors); } } } srcu_read_unlock(&kvm->irq_srcu, idx); } + +int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm, + int irq_source_id, int level, bool line_status) +{ + switch (irq->type) { + case KVM_IRQ_ROUTING_HV_SINT: + return kvm_hv_set_sint(irq, kvm, irq_source_id, level, + line_status); + default: + return -EWOULDBLOCK; + } +} + +void kvm_arch_irq_routing_update(struct kvm *kvm) +{ + kvm_hv_irq_routing_update(kvm); +} diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 4d30b865be30..36591faed13b 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -41,6 +41,7 @@ #include "trace.h" #include "x86.h" #include "cpuid.h" +#include "hyperv.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) @@ -128,11 +129,6 @@ static inline int apic_enabled(struct kvm_lapic *apic) (LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \ APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER) -static inline int kvm_apic_id(struct kvm_lapic *apic) -{ - return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; -} - /* The logical map is definitely wrong if we have multiple * modes at the same time. (Physical map is always right.) */ @@ -379,7 +375,8 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) if (!apic->irr_pending) return -1; - kvm_x86_ops->sync_pir_to_irr(apic->vcpu); + if (apic->vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(apic->vcpu); result = apic_search_irr(apic); ASSERT(result == -1 || result >= 16); @@ -392,7 +389,7 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) vcpu = apic->vcpu; - if (unlikely(kvm_vcpu_apic_vid_enabled(vcpu))) { + if (unlikely(vcpu->arch.apicv_active)) { /* try to update RVI */ apic_clear_vector(vec, apic->regs + APIC_IRR); kvm_make_request(KVM_REQ_EVENT, vcpu); @@ -418,7 +415,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * because the processor can modify ISR under the hood. Instead * just set SVI. */ - if (unlikely(kvm_x86_ops->hwapic_isr_update)) + if (unlikely(vcpu->arch.apicv_active)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, vec); else { ++apic->isr_count; @@ -466,7 +463,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * on the other hand isr_count and highest_isr_cache are unused * and must be left alone. */ - if (unlikely(kvm_x86_ops->hwapic_isr_update)) + if (unlikely(vcpu->arch.apicv_active)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); else { @@ -852,7 +849,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic_clear_vector(vector, apic->regs + APIC_TMR); } - if (kvm_x86_ops->deliver_posted_interrupt) + if (vcpu->arch.apicv_active) kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); else { apic_set_irr(vector, apic); @@ -932,7 +929,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2) static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector) { - return test_bit(vector, (ulong *)apic->vcpu->arch.eoi_exit_bitmap); + return test_bit(vector, apic->vcpu->arch.ioapic_handled_vectors); } static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) @@ -974,6 +971,9 @@ static int apic_set_eoi(struct kvm_lapic *apic) apic_clear_isr(vector, apic); apic_update_ppr(apic); + if (test_bit(vector, vcpu_to_synic(apic->vcpu)->vec_bitmap)) + kvm_hv_synic_send_eoi(apic->vcpu, vector); + kvm_ioapic_send_eoi(apic, vector); kvm_make_request(KVM_REQ_EVENT, apic->vcpu); return vector; @@ -1225,7 +1225,7 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) int vec = reg & APIC_VECTOR_MASK; void *bitmap = apic->regs + APIC_ISR; - if (kvm_x86_ops->deliver_posted_interrupt) + if (vcpu->arch.apicv_active) bitmap = apic->regs + APIC_IRR; if (apic_test_vector(vec, bitmap)) @@ -1693,8 +1693,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) apic_set_reg(apic, APIC_ISR + 0x10 * i, 0); apic_set_reg(apic, APIC_TMR + 0x10 * i, 0); } - apic->irr_pending = kvm_vcpu_apic_vid_enabled(vcpu); - apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0; + apic->irr_pending = vcpu->arch.apicv_active; + apic->isr_count = vcpu->arch.apicv_active ? 1 : 0; apic->highest_isr_cache = -1; update_divide_count(apic); atomic_set(&apic->lapic_timer.pending, 0); @@ -1883,6 +1883,12 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) apic_set_isr(vector, apic); apic_update_ppr(apic); apic_clear_irr(vector, apic); + + if (test_bit(vector, vcpu_to_synic(vcpu)->auto_eoi_bitmap)) { + apic_clear_isr(vector, apic); + apic_update_ppr(apic); + } + return vector; } @@ -1906,15 +1912,15 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, update_divide_count(apic); start_apic_timer(apic); apic->irr_pending = true; - apic->isr_count = kvm_x86_ops->hwapic_isr_update ? + apic->isr_count = vcpu->arch.apicv_active ? 1 : count_vectors(apic->regs + APIC_ISR); apic->highest_isr_cache = -1; - if (kvm_x86_ops->hwapic_irr_update) + if (vcpu->arch.apicv_active) { kvm_x86_ops->hwapic_irr_update(vcpu, apic_find_highest_irr(apic)); - if (unlikely(kvm_x86_ops->hwapic_isr_update)) kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); + } kvm_make_request(KVM_REQ_EVENT, vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_rtc_eoi_tracking_restore_one(vcpu); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index fde8e35d5850..41bdb35b4b67 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -143,9 +143,9 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic) return apic->vcpu->arch.apic_base & X2APIC_ENABLE; } -static inline bool kvm_vcpu_apic_vid_enabled(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu) { - return kvm_x86_ops->cpu_uses_apicv(vcpu); + return vcpu->arch.apic && vcpu->arch.apicv_active; } static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) @@ -164,6 +164,11 @@ static inline int kvm_lapic_latched_init(struct kvm_vcpu *vcpu) return kvm_vcpu_has_lapic(vcpu) && test_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); } +static inline int kvm_apic_id(struct kvm_lapic *apic) +{ + return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff; +} + bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector); void wait_lapic_expire(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index e7c2c1428a69..420a5ca3c0ee 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -311,11 +311,6 @@ static int is_large_pte(u64 pte) return pte & PT_PAGE_SIZE_MASK; } -static int is_rmap_spte(u64 pte) -{ - return is_shadow_present_pte(pte); -} - static int is_last_spte(u64 pte, int level) { if (level == PT_PAGE_TABLE_LEVEL) @@ -540,7 +535,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) u64 old_spte = *sptep; bool ret = false; - WARN_ON(!is_rmap_spte(new_spte)); + WARN_ON(!is_shadow_present_pte(new_spte)); if (!is_shadow_present_pte(old_spte)) { mmu_spte_set(sptep, new_spte); @@ -595,7 +590,7 @@ static int mmu_spte_clear_track_bits(u64 *sptep) else old_spte = __update_clear_spte_slow(sptep, 0ull); - if (!is_rmap_spte(old_spte)) + if (!is_shadow_present_pte(old_spte)) return 0; pfn = spte_to_pfn(old_spte); @@ -909,36 +904,35 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn, } /* - * Pte mapping structures: + * About rmap_head encoding: * - * If pte_list bit zero is zero, then pte_list point to the spte. - * - * If pte_list bit zero is one, (then pte_list & ~1) points to a struct + * If the bit zero of rmap_head->val is clear, then it points to the only spte + * in this rmap chain. Otherwise, (rmap_head->val & ~1) points to a struct * pte_list_desc containing more mappings. - * - * Returns the number of pte entries before the spte was added or zero if - * the spte was not added. - * + */ + +/* + * Returns the number of pointers in the rmap chain, not counting the new one. */ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, - unsigned long *pte_list) + struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; int i, count = 0; - if (!*pte_list) { + if (!rmap_head->val) { rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte); - *pte_list = (unsigned long)spte; - } else if (!(*pte_list & 1)) { + rmap_head->val = (unsigned long)spte; + } else if (!(rmap_head->val & 1)) { rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte); desc = mmu_alloc_pte_list_desc(vcpu); - desc->sptes[0] = (u64 *)*pte_list; + desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; - *pte_list = (unsigned long)desc | 1; + rmap_head->val = (unsigned long)desc | 1; ++count; } else { rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte); - desc = (struct pte_list_desc *)(*pte_list & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); while (desc->sptes[PTE_LIST_EXT-1] && desc->more) { desc = desc->more; count += PTE_LIST_EXT; @@ -955,8 +949,9 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, } static void -pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc, - int i, struct pte_list_desc *prev_desc) +pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, + struct pte_list_desc *desc, int i, + struct pte_list_desc *prev_desc) { int j; @@ -967,43 +962,43 @@ pte_list_desc_remove_entry(unsigned long *pte_list, struct pte_list_desc *desc, if (j != 0) return; if (!prev_desc && !desc->more) - *pte_list = (unsigned long)desc->sptes[0]; + rmap_head->val = (unsigned long)desc->sptes[0]; else if (prev_desc) prev_desc->more = desc->more; else - *pte_list = (unsigned long)desc->more | 1; + rmap_head->val = (unsigned long)desc->more | 1; mmu_free_pte_list_desc(desc); } -static void pte_list_remove(u64 *spte, unsigned long *pte_list) +static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; struct pte_list_desc *prev_desc; int i; - if (!*pte_list) { + if (!rmap_head->val) { printk(KERN_ERR "pte_list_remove: %p 0->BUG\n", spte); BUG(); - } else if (!(*pte_list & 1)) { + } else if (!(rmap_head->val & 1)) { rmap_printk("pte_list_remove: %p 1->0\n", spte); - if ((u64 *)*pte_list != spte) { + if ((u64 *)rmap_head->val != spte) { printk(KERN_ERR "pte_list_remove: %p 1->BUG\n", spte); BUG(); } - *pte_list = 0; + rmap_head->val = 0; } else { rmap_printk("pte_list_remove: %p many->many\n", spte); - desc = (struct pte_list_desc *)(*pte_list & ~1ul); + desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); prev_desc = NULL; while (desc) { - for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) + for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) { if (desc->sptes[i] == spte) { - pte_list_desc_remove_entry(pte_list, - desc, i, - prev_desc); + pte_list_desc_remove_entry(rmap_head, + desc, i, prev_desc); return; } + } prev_desc = desc; desc = desc->more; } @@ -1012,28 +1007,8 @@ static void pte_list_remove(u64 *spte, unsigned long *pte_list) } } -typedef void (*pte_list_walk_fn) (u64 *spte); -static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn) -{ - struct pte_list_desc *desc; - int i; - - if (!*pte_list) - return; - - if (!(*pte_list & 1)) - return fn((u64 *)*pte_list); - - desc = (struct pte_list_desc *)(*pte_list & ~1ul); - while (desc) { - for (i = 0; i < PTE_LIST_EXT && desc->sptes[i]; ++i) - fn(desc->sptes[i]); - desc = desc->more; - } -} - -static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, - struct kvm_memory_slot *slot) +static struct kvm_rmap_head *__gfn_to_rmap(gfn_t gfn, int level, + struct kvm_memory_slot *slot) { unsigned long idx; @@ -1041,10 +1016,8 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level, return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx]; } -/* - * Take gfn and return the reverse mapping to it. - */ -static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp) +static struct kvm_rmap_head *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, + struct kvm_mmu_page *sp) { struct kvm_memslots *slots; struct kvm_memory_slot *slot; @@ -1065,24 +1038,24 @@ static bool rmap_can_add(struct kvm_vcpu *vcpu) static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { struct kvm_mmu_page *sp; - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; sp = page_header(__pa(spte)); kvm_mmu_page_set_gfn(sp, spte - sp->spt, gfn); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); - return pte_list_add(vcpu, spte, rmapp); + rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp); + return pte_list_add(vcpu, spte, rmap_head); } static void rmap_remove(struct kvm *kvm, u64 *spte) { struct kvm_mmu_page *sp; gfn_t gfn; - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; sp = page_header(__pa(spte)); gfn = kvm_mmu_page_get_gfn(sp, spte - sp->spt); - rmapp = gfn_to_rmap(kvm, gfn, sp); - pte_list_remove(spte, rmapp); + rmap_head = gfn_to_rmap(kvm, gfn, sp); + pte_list_remove(spte, rmap_head); } /* @@ -1102,19 +1075,26 @@ struct rmap_iterator { * * Returns sptep if found, NULL otherwise. */ -static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter) +static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head, + struct rmap_iterator *iter) { - if (!rmap) + u64 *sptep; + + if (!rmap_head->val) return NULL; - if (!(rmap & 1)) { + if (!(rmap_head->val & 1)) { iter->desc = NULL; - return (u64 *)rmap; + sptep = (u64 *)rmap_head->val; + goto out; } - iter->desc = (struct pte_list_desc *)(rmap & ~1ul); + iter->desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); iter->pos = 0; - return iter->desc->sptes[iter->pos]; + sptep = iter->desc->sptes[iter->pos]; +out: + BUG_ON(!is_shadow_present_pte(*sptep)); + return sptep; } /* @@ -1124,14 +1104,14 @@ static u64 *rmap_get_first(unsigned long rmap, struct rmap_iterator *iter) */ static u64 *rmap_get_next(struct rmap_iterator *iter) { + u64 *sptep; + if (iter->desc) { if (iter->pos < PTE_LIST_EXT - 1) { - u64 *sptep; - ++iter->pos; sptep = iter->desc->sptes[iter->pos]; if (sptep) - return sptep; + goto out; } iter->desc = iter->desc->more; @@ -1139,17 +1119,20 @@ static u64 *rmap_get_next(struct rmap_iterator *iter) if (iter->desc) { iter->pos = 0; /* desc->sptes[0] cannot be NULL */ - return iter->desc->sptes[iter->pos]; + sptep = iter->desc->sptes[iter->pos]; + goto out; } } return NULL; +out: + BUG_ON(!is_shadow_present_pte(*sptep)); + return sptep; } -#define for_each_rmap_spte(_rmap_, _iter_, _spte_) \ - for (_spte_ = rmap_get_first(*_rmap_, _iter_); \ - _spte_ && ({BUG_ON(!is_shadow_present_pte(*_spte_)); 1;}); \ - _spte_ = rmap_get_next(_iter_)) +#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_) \ + for (_spte_ = rmap_get_first(_rmap_head_, _iter_); \ + _spte_; _spte_ = rmap_get_next(_iter_)) static void drop_spte(struct kvm *kvm, u64 *sptep) { @@ -1207,14 +1190,15 @@ static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect) return mmu_spte_update(sptep, spte); } -static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, +static bool __rmap_write_protect(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, bool pt_protect) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_write_protect(kvm, sptep, pt_protect); return flush; @@ -1231,13 +1215,13 @@ static bool spte_clear_dirty(struct kvm *kvm, u64 *sptep) return mmu_spte_update(sptep, spte); } -static bool __rmap_clear_dirty(struct kvm *kvm, unsigned long *rmapp) +static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_clear_dirty(kvm, sptep); return flush; @@ -1254,13 +1238,13 @@ static bool spte_set_dirty(struct kvm *kvm, u64 *sptep) return mmu_spte_update(sptep, spte); } -static bool __rmap_set_dirty(struct kvm *kvm, unsigned long *rmapp) +static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) flush |= spte_set_dirty(kvm, sptep); return flush; @@ -1280,12 +1264,12 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; while (mask) { - rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PT_PAGE_TABLE_LEVEL, slot); - __rmap_write_protect(kvm, rmapp, false); + rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), + PT_PAGE_TABLE_LEVEL, slot); + __rmap_write_protect(kvm, rmap_head, false); /* clear the first set bit */ mask &= mask - 1; @@ -1305,12 +1289,12 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; while (mask) { - rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), - PT_PAGE_TABLE_LEVEL, slot); - __rmap_clear_dirty(kvm, rmapp); + rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), + PT_PAGE_TABLE_LEVEL, slot); + __rmap_clear_dirty(kvm, rmap_head); /* clear the first set bit */ mask &= mask - 1; @@ -1342,28 +1326,27 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) { struct kvm_memory_slot *slot; - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; int i; bool write_protected = false; slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); for (i = PT_PAGE_TABLE_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) { - rmapp = __gfn_to_rmap(gfn, i, slot); - write_protected |= __rmap_write_protect(vcpu->kvm, rmapp, true); + rmap_head = __gfn_to_rmap(gfn, i, slot); + write_protected |= __rmap_write_protect(vcpu->kvm, rmap_head, true); } return write_protected; } -static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp) +static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; bool flush = false; - while ((sptep = rmap_get_first(*rmapp, &iter))) { - BUG_ON(!(*sptep & PT_PRESENT_MASK)); + while ((sptep = rmap_get_first(rmap_head, &iter))) { rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep); drop_spte(kvm, sptep); @@ -1373,14 +1356,14 @@ static bool kvm_zap_rmapp(struct kvm *kvm, unsigned long *rmapp) return flush; } -static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { - return kvm_zap_rmapp(kvm, rmapp); + return kvm_zap_rmapp(kvm, rmap_head); } -static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { @@ -1395,7 +1378,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp, new_pfn = pte_pfn(*ptep); restart: - for_each_rmap_spte(rmapp, &iter, sptep) { + for_each_rmap_spte(rmap_head, &iter, sptep) { rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); @@ -1433,11 +1416,11 @@ struct slot_rmap_walk_iterator { /* output fields. */ gfn_t gfn; - unsigned long *rmap; + struct kvm_rmap_head *rmap; int level; /* private field. */ - unsigned long *end_rmap; + struct kvm_rmap_head *end_rmap; }; static void @@ -1496,7 +1479,7 @@ static int kvm_handle_hva_range(struct kvm *kvm, unsigned long end, unsigned long data, int (*handler)(struct kvm *kvm, - unsigned long *rmapp, + struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, @@ -1540,7 +1523,8 @@ static int kvm_handle_hva_range(struct kvm *kvm, static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, unsigned long data, - int (*handler)(struct kvm *kvm, unsigned long *rmapp, + int (*handler)(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data)) @@ -1563,7 +1547,7 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp); } -static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { @@ -1573,18 +1557,19 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp, BUG_ON(!shadow_accessed_mask); - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) { if (*sptep & shadow_accessed_mask) { young = 1; clear_bit((ffs(shadow_accessed_mask) - 1), (unsigned long *)sptep); } + } trace_kvm_age_page(gfn, level, slot, young); return young; } -static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, +static int kvm_test_age_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { @@ -1600,11 +1585,12 @@ static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp, if (!shadow_accessed_mask) goto out; - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) { if (*sptep & shadow_accessed_mask) { young = 1; break; } + } out: return young; } @@ -1613,14 +1599,14 @@ out: static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; struct kvm_mmu_page *sp; sp = page_header(__pa(spte)); - rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp); + rmap_head = gfn_to_rmap(vcpu->kvm, gfn, sp); - kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, gfn, sp->role.level, 0); + kvm_unmap_rmapp(vcpu->kvm, rmap_head, NULL, gfn, sp->role.level, 0); kvm_flush_remote_tlbs(vcpu->kvm); } @@ -1720,8 +1706,7 @@ static void drop_parent_pte(struct kvm_mmu_page *sp, mmu_spte_clear_no_track(parent_pte); } -static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, - u64 *parent_pte, int direct) +static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, int direct) { struct kvm_mmu_page *sp; @@ -1737,8 +1722,6 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, * this feature. See the comments in kvm_zap_obsolete_pages(). */ list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); - sp->parent_ptes = 0; - mmu_page_add_parent_pte(vcpu, sp, parent_pte); kvm_mod_used_mmu_pages(vcpu->kvm, +1); return sp; } @@ -1746,7 +1729,12 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, static void mark_unsync(u64 *spte); static void kvm_mmu_mark_parents_unsync(struct kvm_mmu_page *sp) { - pte_list_walk(&sp->parent_ptes, mark_unsync); + u64 *sptep; + struct rmap_iterator iter; + + for_each_rmap_spte(&sp->parent_ptes, &iter, sptep) { + mark_unsync(sptep); + } } static void mark_unsync(u64 *spte) @@ -1806,6 +1794,13 @@ static int mmu_pages_add(struct kvm_mmu_pages *pvec, struct kvm_mmu_page *sp, return (pvec->nr == KVM_PAGE_ARRAY_NR); } +static inline void clear_unsync_child_bit(struct kvm_mmu_page *sp, int idx) +{ + --sp->unsync_children; + WARN_ON((int)sp->unsync_children < 0); + __clear_bit(idx, sp->unsync_child_bitmap); +} + static int __mmu_unsync_walk(struct kvm_mmu_page *sp, struct kvm_mmu_pages *pvec) { @@ -1815,8 +1810,10 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, struct kvm_mmu_page *child; u64 ent = sp->spt[i]; - if (!is_shadow_present_pte(ent) || is_large_pte(ent)) - goto clear_child_bitmap; + if (!is_shadow_present_pte(ent) || is_large_pte(ent)) { + clear_unsync_child_bit(sp, i); + continue; + } child = page_header(ent & PT64_BASE_ADDR_MASK); @@ -1825,28 +1822,21 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, return -ENOSPC; ret = __mmu_unsync_walk(child, pvec); - if (!ret) - goto clear_child_bitmap; - else if (ret > 0) + if (!ret) { + clear_unsync_child_bit(sp, i); + continue; + } else if (ret > 0) { nr_unsync_leaf += ret; - else + } else return ret; } else if (child->unsync) { nr_unsync_leaf++; if (mmu_pages_add(pvec, child, i)) return -ENOSPC; } else - goto clear_child_bitmap; - - continue; - -clear_child_bitmap: - __clear_bit(i, sp->unsync_child_bitmap); - sp->unsync_children--; - WARN_ON((int)sp->unsync_children < 0); + clear_unsync_child_bit(sp, i); } - return nr_unsync_leaf; } @@ -2009,9 +1999,7 @@ static void mmu_pages_clear_parents(struct mmu_page_path *parents) if (!sp) return; - --sp->unsync_children; - WARN_ON((int)sp->unsync_children < 0); - __clear_bit(idx, sp->unsync_child_bitmap); + clear_unsync_child_bit(sp, idx); level++; } while (level < PT64_ROOT_LEVEL-1 && !sp->unsync_children); } @@ -2053,14 +2041,6 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, } } -static void init_shadow_page_table(struct kvm_mmu_page *sp) -{ - int i; - - for (i = 0; i < PT64_ENT_PER_PAGE; ++i) - sp->spt[i] = 0ull; -} - static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) { sp->write_flooding_count = 0; @@ -2083,8 +2063,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gva_t gaddr, unsigned level, int direct, - unsigned access, - u64 *parent_pte) + unsigned access) { union kvm_mmu_page_role role; unsigned quadrant; @@ -2116,21 +2095,18 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, if (sp->unsync && kvm_sync_page_transient(vcpu, sp)) break; - mmu_page_add_parent_pte(vcpu, sp, parent_pte); - if (sp->unsync_children) { + if (sp->unsync_children) kvm_make_request(KVM_REQ_MMU_SYNC, vcpu); - kvm_mmu_mark_parents_unsync(sp); - } else if (sp->unsync) - kvm_mmu_mark_parents_unsync(sp); __clear_sp_write_flooding_count(sp); trace_kvm_mmu_get_page(sp, false); return sp; } + ++vcpu->kvm->stat.mmu_cache_miss; - sp = kvm_mmu_alloc_page(vcpu, parent_pte, direct); - if (!sp) - return sp; + + sp = kvm_mmu_alloc_page(vcpu, direct); + sp->gfn = gfn; sp->role = role; hlist_add_head(&sp->hash_link, @@ -2144,7 +2120,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, account_shadowed(vcpu->kvm, sp); } sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen; - init_shadow_page_table(sp); + clear_page(sp->spt); trace_kvm_mmu_get_page(sp, true); return sp; } @@ -2198,7 +2174,8 @@ 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, bool accessed) +static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep, + struct kvm_mmu_page *sp) { u64 spte; @@ -2206,12 +2183,14 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp, bool accessed) VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK); spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK | - shadow_user_mask | shadow_x_mask; - - if (accessed) - spte |= shadow_accessed_mask; + shadow_user_mask | shadow_x_mask | shadow_accessed_mask; mmu_spte_set(sptep, spte); + + mmu_page_add_parent_pte(vcpu, sp, sptep); + + if (sp->unsync_children || sp->unsync) + mark_unsync(sptep); } static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, @@ -2270,17 +2249,12 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm, mmu_page_zap_pte(kvm, sp, sp->spt + i); } -static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte) -{ - mmu_page_remove_parent_pte(sp, parent_pte); -} - static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { u64 *sptep; struct rmap_iterator iter; - while ((sptep = rmap_get_first(sp->parent_ptes, &iter))) + while ((sptep = rmap_get_first(&sp->parent_ptes, &iter))) drop_parent_pte(sp, sptep); } @@ -2564,18 +2538,18 @@ done: return ret; } -static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, - unsigned pte_access, int write_fault, int *emulate, - int level, gfn_t gfn, pfn_t pfn, bool speculative, - bool host_writable) +static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access, + int write_fault, int level, gfn_t gfn, pfn_t pfn, + bool speculative, bool host_writable) { int was_rmapped = 0; int rmap_count; + bool emulate = false; pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__, *sptep, write_fault, gfn); - if (is_rmap_spte(*sptep)) { + if (is_shadow_present_pte(*sptep)) { /* * If we overwrite a PTE page pointer with a 2MB PMD, unlink * the parent of the now unreachable PTE. @@ -2600,12 +2574,12 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (set_spte(vcpu, sptep, pte_access, level, gfn, pfn, speculative, true, host_writable)) { if (write_fault) - *emulate = 1; + emulate = true; kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu); } - if (unlikely(is_mmio_spte(*sptep) && emulate)) - *emulate = 1; + if (unlikely(is_mmio_spte(*sptep))) + emulate = true; pgprintk("%s: setting spte %llx\n", __func__, *sptep); pgprintk("instantiating %s PTE (%s) at %llx (%llx) addr %p\n", @@ -2624,6 +2598,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } kvm_release_pfn_clean(pfn); + + return emulate; } static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, @@ -2658,9 +2634,8 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu, return -1; for (i = 0; i < ret; i++, gfn++, start++) - mmu_set_spte(vcpu, start, access, 0, NULL, - sp->role.level, gfn, page_to_pfn(pages[i]), - true, true); + mmu_set_spte(vcpu, start, access, 0, sp->role.level, gfn, + page_to_pfn(pages[i]), true, true); return 0; } @@ -2708,9 +2683,8 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) __direct_pte_prefetch(vcpu, sp, sptep); } -static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, - int map_writable, int level, gfn_t gfn, pfn_t pfn, - bool prefault) +static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable, + int level, gfn_t gfn, pfn_t pfn, bool prefault) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; @@ -2722,9 +2696,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) { if (iterator.level == level) { - mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, - write, &emulate, level, gfn, pfn, - prefault, map_writable); + emulate = mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, + write, level, gfn, pfn, prefault, + map_writable); direct_pte_prefetch(vcpu, iterator.sptep); ++vcpu->stat.pf_fixed; break; @@ -2737,10 +2711,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write, base_addr &= PT64_LVL_ADDR_MASK(iterator.level); pseudo_gfn = base_addr >> PAGE_SHIFT; sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr, - iterator.level - 1, - 1, ACC_ALL, iterator.sptep); + iterator.level - 1, 1, ACC_ALL); - link_shadow_page(iterator.sptep, sp, true); + link_shadow_page(vcpu, iterator.sptep, sp); } } return emulate; @@ -2919,7 +2892,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, * If the mapping has been changed, let the vcpu fault on the * same address again. */ - if (!is_rmap_spte(spte)) { + if (!is_shadow_present_pte(spte)) { ret = true; goto exit; } @@ -3018,11 +2991,9 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code, make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, v, write, map_writable, level, gfn, pfn, - prefault); + r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); - return r; out_unlock: @@ -3097,8 +3068,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) { spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); - sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, - 1, ACC_ALL, NULL); + sp = kvm_mmu_get_page(vcpu, 0, 0, PT64_ROOT_LEVEL, 1, ACC_ALL); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); vcpu->arch.mmu.root_hpa = __pa(sp->spt); @@ -3110,9 +3080,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, i << (30 - PAGE_SHIFT), - i << 30, - PT32_ROOT_LEVEL, 1, ACC_ALL, - NULL); + i << 30, PT32_ROOT_LEVEL, 1, ACC_ALL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); @@ -3149,7 +3117,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); sp = kvm_mmu_get_page(vcpu, root_gfn, 0, PT64_ROOT_LEVEL, - 0, ACC_ALL, NULL); + 0, ACC_ALL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); @@ -3182,9 +3150,8 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) } spin_lock(&vcpu->kvm->mmu_lock); make_mmu_pages_available(vcpu); - sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, - PT32_ROOT_LEVEL, 0, - ACC_ALL, NULL); + sp = kvm_mmu_get_page(vcpu, root_gfn, i << 30, PT32_ROOT_LEVEL, + 0, ACC_ALL); root = __pa(sp->spt); ++sp->root_count; spin_unlock(&vcpu->kvm->mmu_lock); @@ -3531,8 +3498,7 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code, make_mmu_pages_available(vcpu); if (likely(!force_pt_level)) transparent_hugepage_adjust(vcpu, &gfn, &pfn, &level); - r = __direct_map(vcpu, gpa, write, map_writable, - level, gfn, pfn, prefault); + r = __direct_map(vcpu, write, map_writable, level, gfn, pfn, prefault); spin_unlock(&vcpu->kvm->mmu_lock); return r; @@ -4058,10 +4024,12 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu) g_context->inject_page_fault = kvm_inject_page_fault; /* - * Note that arch.mmu.gva_to_gpa translates l2_gva to l1_gpa. The - * translation of l2_gpa to l1_gpa addresses is done using the - * arch.nested_mmu.gva_to_gpa function. Basically the gva_to_gpa - * functions between mmu and nested_mmu are swapped. + * Note that arch.mmu.gva_to_gpa translates l2_gpa to l1_gpa using + * L1's nested page tables (e.g. EPT12). The nested translation + * of l2_gva to l1_gpa is done by arch.nested_mmu.gva_to_gpa using + * L2's page tables as the first level of translation and L1's + * nested page tables as the second level of translation. Basically + * the gva_to_gpa functions between mmu and nested_mmu are swapped. */ if (!is_paging(vcpu)) { g_context->nx = false; @@ -4495,7 +4463,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu) } /* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_level_handler) (struct kvm *kvm, unsigned long *rmap); +typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head); /* The caller should hold mmu-lock before calling this function. */ static bool @@ -4589,9 +4557,10 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) spin_unlock(&kvm->mmu_lock); } -static bool slot_rmap_write_protect(struct kvm *kvm, unsigned long *rmapp) +static bool slot_rmap_write_protect(struct kvm *kvm, + struct kvm_rmap_head *rmap_head) { - return __rmap_write_protect(kvm, rmapp, false); + return __rmap_write_protect(kvm, rmap_head, false); } void kvm_mmu_slot_remove_write_access(struct kvm *kvm, @@ -4627,7 +4596,7 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, } static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, - unsigned long *rmapp) + struct kvm_rmap_head *rmap_head) { u64 *sptep; struct rmap_iterator iter; @@ -4636,7 +4605,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, struct kvm_mmu_page *sp; restart: - for_each_rmap_spte(rmapp, &iter, sptep) { + for_each_rmap_spte(rmap_head, &iter, sptep) { sp = page_header(__pa(sptep)); pfn = spte_to_pfn(*sptep); diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 03d518e499a6..1cee3ec20dd2 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -129,7 +129,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level) static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) { static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; struct kvm_mmu_page *rev_sp; struct kvm_memslots *slots; struct kvm_memory_slot *slot; @@ -150,8 +150,8 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep) return; } - rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot); - if (!*rmapp) { + rmap_head = __gfn_to_rmap(gfn, rev_sp->role.level, slot); + if (!rmap_head->val) { if (!__ratelimit(&ratelimit_state)) return; audit_printk(kvm, "no rmap for writable spte %llx\n", @@ -183,7 +183,7 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp) return; for (i = 0; i < PT64_ENT_PER_PAGE; ++i) { - if (!is_rmap_spte(sp->spt[i])) + if (!is_shadow_present_pte(sp->spt[i])) continue; inspect_spte_has_rmap(kvm, sp->spt + i); @@ -192,7 +192,7 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp) static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) { - unsigned long *rmapp; + struct kvm_rmap_head *rmap_head; u64 *sptep; struct rmap_iterator iter; struct kvm_memslots *slots; @@ -203,13 +203,14 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp) slots = kvm_memslots_for_spte_role(kvm, sp->role); slot = __gfn_to_memslot(slots, sp->gfn); - rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); + rmap_head = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot); - for_each_rmap_spte(rmapp, &iter, sptep) + for_each_rmap_spte(rmap_head, &iter, sptep) { if (is_writable_pte(*sptep)) audit_printk(kvm, "shadow page has writable " "mappings: gfn %llx role %x\n", sp->gfn, sp->role.word); + } } static void audit_sp(struct kvm *kvm, struct kvm_mmu_page *sp) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 3058a22a658d..91e939b486d1 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -475,8 +475,8 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, * we call mmu_set_spte() with host_writable = true because * pte_prefetch_gfn_to_pfn always gets a writable pfn. */ - mmu_set_spte(vcpu, spte, pte_access, 0, NULL, PT_PAGE_TABLE_LEVEL, - gfn, pfn, true, true); + mmu_set_spte(vcpu, spte, pte_access, 0, PT_PAGE_TABLE_LEVEL, gfn, pfn, + true, true); return true; } @@ -556,7 +556,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, struct kvm_mmu_page *sp = NULL; struct kvm_shadow_walk_iterator it; unsigned direct_access, access = gw->pt_access; - int top_level, emulate = 0; + int top_level, emulate; direct_access = gw->pte_access; @@ -587,7 +587,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, if (!is_shadow_present_pte(*it.sptep)) { table_gfn = gw->table_gfn[it.level - 2]; sp = kvm_mmu_get_page(vcpu, table_gfn, addr, it.level-1, - false, access, it.sptep); + false, access); } /* @@ -598,7 +598,7 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, goto out_gpte_changed; if (sp) - link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK); + link_shadow_page(vcpu, it.sptep, sp); } for (; @@ -617,20 +617,18 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, direct_gfn = gw->gfn & ~(KVM_PAGES_PER_HPAGE(it.level) - 1); sp = kvm_mmu_get_page(vcpu, direct_gfn, addr, it.level-1, - true, direct_access, it.sptep); - link_shadow_page(it.sptep, sp, PT_GUEST_ACCESSED_MASK); + true, direct_access); + link_shadow_page(vcpu, it.sptep, sp); } clear_sp_write_flooding_count(it.sptep); - mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, &emulate, - it.level, gw->gfn, pfn, prefault, map_writable); + emulate = mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, + it.level, gw->gfn, pfn, prefault, map_writable); FNAME(pte_prefetch)(vcpu, gw, it.sptep); return emulate; out_gpte_changed: - if (sp) - kvm_mmu_put_page(sp, it.sptep); kvm_release_pfn_clean(pfn); return 0; } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 899c40f826dd..c13a64b7d789 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -86,6 +86,7 @@ static const u32 host_save_user_msrs[] = { MSR_FS_BASE, #endif MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, + MSR_TSC_AUX, }; #define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs) @@ -135,6 +136,7 @@ struct vcpu_svm { uint64_t asid_generation; uint64_t sysenter_esp; uint64_t sysenter_eip; + uint64_t tsc_aux; u64 next_rip; @@ -1238,6 +1240,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) wrmsrl(MSR_AMD64_TSC_RATIO, tsc_ratio); } } + /* This assumes that the kernel never uses MSR_TSC_AUX */ + if (static_cpu_has(X86_FEATURE_RDTSCP)) + wrmsrl(MSR_TSC_AUX, svm->tsc_aux); } static void svm_vcpu_put(struct kvm_vcpu *vcpu) @@ -3024,6 +3029,11 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_SYSENTER_ESP: msr_info->data = svm->sysenter_esp; break; + case MSR_TSC_AUX: + if (!boot_cpu_has(X86_FEATURE_RDTSCP)) + return 1; + msr_info->data = svm->tsc_aux; + break; /* * Nobody will change the following 5 values in the VMCB so we can * safely return them on rdmsr. They will always be 0 until LBRV is @@ -3053,6 +3063,23 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_UCODE_REV: msr_info->data = 0x01000065; break; + case MSR_F15H_IC_CFG: { + + int family, model; + + family = guest_cpuid_family(vcpu); + model = guest_cpuid_model(vcpu); + + if (family < 0 || model < 0) + return kvm_get_msr_common(vcpu, msr_info); + + msr_info->data = 0; + + if (family == 0x15 && + (model >= 0x2 && model < 0x20)) + msr_info->data = 0x1E; + } + break; default: return kvm_get_msr_common(vcpu, msr_info); } @@ -3145,6 +3172,18 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->sysenter_esp = data; svm->vmcb->save.sysenter_esp = data; break; + case MSR_TSC_AUX: + if (!boot_cpu_has(X86_FEATURE_RDTSCP)) + return 1; + + /* + * This is rare, so we update the MSR here instead of using + * direct_access_msrs. Doing that would require a rdmsr in + * svm_vcpu_put. + */ + svm->tsc_aux = data; + wrmsrl(MSR_TSC_AUX, svm->tsc_aux); + break; case MSR_IA32_DEBUGCTLMSR: if (!boot_cpu_has(X86_FEATURE_LBRV)) { vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", @@ -3561,12 +3600,16 @@ static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) return; } -static int svm_cpu_uses_apicv(struct kvm_vcpu *vcpu) +static bool svm_get_enable_apicv(void) { - return 0; + return false; } -static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu) +static void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ +} + +static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { return; } @@ -4037,7 +4080,7 @@ static int svm_get_lpage_level(void) static bool svm_rdtscp_supported(void) { - return false; + return boot_cpu_has(X86_FEATURE_RDTSCP); } static bool svm_invpcid_supported(void) @@ -4328,7 +4371,8 @@ static struct kvm_x86_ops svm_x86_ops = { .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, - .cpu_uses_apicv = svm_cpu_uses_apicv, + .get_enable_apicv = svm_get_enable_apicv, + .refresh_apicv_exec_ctrl = svm_refresh_apicv_exec_ctrl, .load_eoi_exitmap = svm_load_eoi_exitmap, .sync_pir_to_irr = svm_sync_pir_to_irr, diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 120302511802..ad9f6a23f139 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -268,7 +268,7 @@ TRACE_EVENT(kvm_inj_virq, #define kvm_trace_sym_exc \ EXS(DE), EXS(DB), EXS(BP), EXS(OF), EXS(BR), EXS(UD), EXS(NM), \ EXS(DF), EXS(TS), EXS(NP), EXS(SS), EXS(GP), EXS(PF), \ - EXS(MF), EXS(MC) + EXS(MF), EXS(AC), EXS(MC) /* * Tracepoint for kvm interrupt injection: @@ -1025,6 +1025,269 @@ TRACE_EVENT(kvm_pi_irte_update, __entry->pi_desc_addr) ); +/* + * Tracepoint for kvm_hv_notify_acked_sint. + */ +TRACE_EVENT(kvm_hv_notify_acked_sint, + TP_PROTO(int vcpu_id, u32 sint), + TP_ARGS(vcpu_id, sint), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, sint) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->sint = sint; + ), + + TP_printk("vcpu_id %d sint %u", __entry->vcpu_id, __entry->sint) +); + +/* + * Tracepoint for synic_set_irq. + */ +TRACE_EVENT(kvm_hv_synic_set_irq, + TP_PROTO(int vcpu_id, u32 sint, int vector, int ret), + TP_ARGS(vcpu_id, sint, vector, ret), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, sint) + __field(int, vector) + __field(int, ret) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->sint = sint; + __entry->vector = vector; + __entry->ret = ret; + ), + + TP_printk("vcpu_id %d sint %u vector %d ret %d", + __entry->vcpu_id, __entry->sint, __entry->vector, + __entry->ret) +); + +/* + * Tracepoint for kvm_hv_synic_send_eoi. + */ +TRACE_EVENT(kvm_hv_synic_send_eoi, + TP_PROTO(int vcpu_id, int vector), + TP_ARGS(vcpu_id, vector), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, sint) + __field(int, vector) + __field(int, ret) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->vector = vector; + ), + + TP_printk("vcpu_id %d vector %d", __entry->vcpu_id, __entry->vector) +); + +/* + * Tracepoint for synic_set_msr. + */ +TRACE_EVENT(kvm_hv_synic_set_msr, + TP_PROTO(int vcpu_id, u32 msr, u64 data, bool host), + TP_ARGS(vcpu_id, msr, data, host), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(u32, msr) + __field(u64, data) + __field(bool, host) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->msr = msr; + __entry->data = data; + __entry->host = host + ), + + TP_printk("vcpu_id %d msr 0x%x data 0x%llx host %d", + __entry->vcpu_id, __entry->msr, __entry->data, __entry->host) +); + +/* + * Tracepoint for stimer_set_config. + */ +TRACE_EVENT(kvm_hv_stimer_set_config, + TP_PROTO(int vcpu_id, int timer_index, u64 config, bool host), + TP_ARGS(vcpu_id, timer_index, config, host), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, config) + __field(bool, host) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->config = config; + __entry->host = host; + ), + + TP_printk("vcpu_id %d timer %d config 0x%llx host %d", + __entry->vcpu_id, __entry->timer_index, __entry->config, + __entry->host) +); + +/* + * Tracepoint for stimer_set_count. + */ +TRACE_EVENT(kvm_hv_stimer_set_count, + TP_PROTO(int vcpu_id, int timer_index, u64 count, bool host), + TP_ARGS(vcpu_id, timer_index, count, host), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, count) + __field(bool, host) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->count = count; + __entry->host = host; + ), + + TP_printk("vcpu_id %d timer %d count %llu host %d", + __entry->vcpu_id, __entry->timer_index, __entry->count, + __entry->host) +); + +/* + * Tracepoint for stimer_start(periodic timer case). + */ +TRACE_EVENT(kvm_hv_stimer_start_periodic, + TP_PROTO(int vcpu_id, int timer_index, u64 time_now, u64 exp_time), + TP_ARGS(vcpu_id, timer_index, time_now, exp_time), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, time_now) + __field(u64, exp_time) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->time_now = time_now; + __entry->exp_time = exp_time; + ), + + TP_printk("vcpu_id %d timer %d time_now %llu exp_time %llu", + __entry->vcpu_id, __entry->timer_index, __entry->time_now, + __entry->exp_time) +); + +/* + * Tracepoint for stimer_start(one-shot timer case). + */ +TRACE_EVENT(kvm_hv_stimer_start_one_shot, + TP_PROTO(int vcpu_id, int timer_index, u64 time_now, u64 count), + TP_ARGS(vcpu_id, timer_index, time_now, count), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(u64, time_now) + __field(u64, count) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->time_now = time_now; + __entry->count = count; + ), + + TP_printk("vcpu_id %d timer %d time_now %llu count %llu", + __entry->vcpu_id, __entry->timer_index, __entry->time_now, + __entry->count) +); + +/* + * Tracepoint for stimer_timer_callback. + */ +TRACE_EVENT(kvm_hv_stimer_callback, + TP_PROTO(int vcpu_id, int timer_index), + TP_ARGS(vcpu_id, timer_index), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + ), + + TP_printk("vcpu_id %d timer %d", + __entry->vcpu_id, __entry->timer_index) +); + +/* + * Tracepoint for stimer_expiration. + */ +TRACE_EVENT(kvm_hv_stimer_expiration, + TP_PROTO(int vcpu_id, int timer_index, int msg_send_result), + TP_ARGS(vcpu_id, timer_index, msg_send_result), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + __field(int, msg_send_result) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + __entry->msg_send_result = msg_send_result; + ), + + TP_printk("vcpu_id %d timer %d msg send result %d", + __entry->vcpu_id, __entry->timer_index, + __entry->msg_send_result) +); + +/* + * Tracepoint for stimer_cleanup. + */ +TRACE_EVENT(kvm_hv_stimer_cleanup, + TP_PROTO(int vcpu_id, int timer_index), + TP_ARGS(vcpu_id, timer_index), + + TP_STRUCT__entry( + __field(int, vcpu_id) + __field(int, timer_index) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->timer_index = timer_index; + ), + + TP_printk("vcpu_id %d timer %d", + __entry->vcpu_id, __entry->timer_index) +); + #endif /* _TRACE_KVM_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 44976a596fa6..04d61d496b14 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -19,6 +19,7 @@ #include "irq.h" #include "mmu.h" #include "cpuid.h" +#include "lapic.h" #include <linux/kvm_host.h> #include <linux/module.h> @@ -862,7 +863,6 @@ static void kvm_cpu_vmxon(u64 addr); static void kvm_cpu_vmxoff(void); static bool vmx_mpx_supported(void); static bool vmx_xsaves_supported(void); -static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu); 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); @@ -870,7 +870,6 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); static bool guest_state_valid(struct kvm_vcpu *vcpu); static u32 vmx_segment_access_rights(struct kvm_segment *var); -static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu); static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx); static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx); static int alloc_identity_pagetable(struct kvm *kvm); @@ -1448,7 +1447,51 @@ static inline void ept_sync_context(u64 eptp) } } -static __always_inline unsigned long vmcs_readl(unsigned long field) +static __always_inline void vmcs_check16(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000, + "16-bit accessor invalid for 64-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, + "16-bit accessor invalid for 64-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, + "16-bit accessor invalid for 32-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, + "16-bit accessor invalid for natural width field"); +} + +static __always_inline void vmcs_check32(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0, + "32-bit accessor invalid for 16-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, + "32-bit accessor invalid for natural width field"); +} + +static __always_inline void vmcs_check64(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0, + "64-bit accessor invalid for 16-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, + "64-bit accessor invalid for 64-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, + "64-bit accessor invalid for 32-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x6000, + "64-bit accessor invalid for natural width field"); +} + +static __always_inline void vmcs_checkl(unsigned long field) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0, + "Natural width accessor invalid for 16-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000, + "Natural width accessor invalid for 64-bit field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2001, + "Natural width accessor invalid for 64-bit high field"); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x4000, + "Natural width accessor invalid for 32-bit field"); +} + +static __always_inline unsigned long __vmcs_readl(unsigned long field) { unsigned long value; @@ -1459,23 +1502,32 @@ static __always_inline unsigned long vmcs_readl(unsigned long field) static __always_inline u16 vmcs_read16(unsigned long field) { - return vmcs_readl(field); + vmcs_check16(field); + return __vmcs_readl(field); } static __always_inline u32 vmcs_read32(unsigned long field) { - return vmcs_readl(field); + vmcs_check32(field); + return __vmcs_readl(field); } static __always_inline u64 vmcs_read64(unsigned long field) { + vmcs_check64(field); #ifdef CONFIG_X86_64 - return vmcs_readl(field); + return __vmcs_readl(field); #else - return vmcs_readl(field) | ((u64)vmcs_readl(field+1) << 32); + return __vmcs_readl(field) | ((u64)__vmcs_readl(field+1) << 32); #endif } +static __always_inline unsigned long vmcs_readl(unsigned long field) +{ + vmcs_checkl(field); + return __vmcs_readl(field); +} + static noinline void vmwrite_error(unsigned long field, unsigned long value) { printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n", @@ -1483,7 +1535,7 @@ static noinline void vmwrite_error(unsigned long field, unsigned long value) dump_stack(); } -static void vmcs_writel(unsigned long field, unsigned long value) +static __always_inline void __vmcs_writel(unsigned long field, unsigned long value) { u8 error; @@ -1493,33 +1545,46 @@ static void vmcs_writel(unsigned long field, unsigned long value) vmwrite_error(field, value); } -static void vmcs_write16(unsigned long field, u16 value) +static __always_inline void vmcs_write16(unsigned long field, u16 value) { - vmcs_writel(field, value); + vmcs_check16(field); + __vmcs_writel(field, value); } -static void vmcs_write32(unsigned long field, u32 value) +static __always_inline void vmcs_write32(unsigned long field, u32 value) { - vmcs_writel(field, value); + vmcs_check32(field); + __vmcs_writel(field, value); } -static void vmcs_write64(unsigned long field, u64 value) +static __always_inline void vmcs_write64(unsigned long field, u64 value) { - vmcs_writel(field, value); + vmcs_check64(field); + __vmcs_writel(field, value); #ifndef CONFIG_X86_64 asm volatile (""); - vmcs_writel(field+1, value >> 32); + __vmcs_writel(field+1, value >> 32); #endif } -static void vmcs_clear_bits(unsigned long field, u32 mask) +static __always_inline void vmcs_writel(unsigned long field, unsigned long value) { - vmcs_writel(field, vmcs_readl(field) & ~mask); + vmcs_checkl(field); + __vmcs_writel(field, value); } -static void vmcs_set_bits(unsigned long field, u32 mask) +static __always_inline void vmcs_clear_bits(unsigned long field, u32 mask) { - vmcs_writel(field, vmcs_readl(field) | mask); + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, + "vmcs_clear_bits does not support 64-bit fields"); + __vmcs_writel(field, __vmcs_readl(field) & ~mask); +} + +static __always_inline void vmcs_set_bits(unsigned long field, u32 mask) +{ + BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, + "vmcs_set_bits does not support 64-bit fields"); + __vmcs_writel(field, __vmcs_readl(field) | mask); } static inline void vm_entry_controls_init(struct vcpu_vmx *vmx, u32 val) @@ -2498,7 +2563,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; - if (vmx_cpu_uses_apicv(&vmx->vcpu)) + if (kvm_vcpu_apicv_active(&vmx->vcpu)) vmx->nested.nested_vmx_pinbased_ctls_high |= PIN_BASED_POSTED_INTR; @@ -4462,9 +4527,9 @@ static void vmx_disable_intercept_msr_write_x2apic(u32 msr) msr, MSR_TYPE_W); } -static int vmx_cpu_uses_apicv(struct kvm_vcpu *vcpu) +static bool vmx_get_enable_apicv(void) { - return enable_apicv && lapic_in_kernel(vcpu); + return enable_apicv; } static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu) @@ -4586,11 +4651,6 @@ static void vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) kvm_apic_update_irr(vcpu, vmx->pi_desc.pir); } -static void vmx_sync_pir_to_irr_dummy(struct kvm_vcpu *vcpu) -{ - return; -} - /* * Set up the vmcs's constant host-state fields, i.e., host-state fields that * will not change in the lifetime of the guest. @@ -4660,11 +4720,18 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx) { u32 pin_based_exec_ctrl = vmcs_config.pin_based_exec_ctrl; - if (!vmx_cpu_uses_apicv(&vmx->vcpu)) + if (!kvm_vcpu_apicv_active(&vmx->vcpu)) pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR; return pin_based_exec_ctrl; } +static void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + + vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx)); +} + static u32 vmx_exec_control(struct vcpu_vmx *vmx) { u32 exec_control = vmcs_config.cpu_based_exec_ctrl; @@ -4703,7 +4770,7 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST; if (!ple_gap) exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING; - if (!vmx_cpu_uses_apicv(&vmx->vcpu)) + if (!kvm_vcpu_apicv_active(&vmx->vcpu)) exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT | SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY); exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE; @@ -4767,7 +4834,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write32(SECONDARY_VM_EXEC_CONTROL, vmx_secondary_exec_control(vmx)); - if (vmx_cpu_uses_apicv(&vmx->vcpu)) { + if (kvm_vcpu_apicv_active(&vmx->vcpu)) { vmcs_write64(EOI_EXIT_BITMAP0, 0); vmcs_write64(EOI_EXIT_BITMAP1, 0); vmcs_write64(EOI_EXIT_BITMAP2, 0); @@ -4775,7 +4842,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx) vmcs_write16(GUEST_INTR_STATUS, 0); - vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc))); } @@ -4867,7 +4934,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) seg_setup(VCPU_SREG_CS); vmcs_write16(GUEST_CS_SELECTOR, 0xf000); - vmcs_write32(GUEST_CS_BASE, 0xffff0000); + vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); seg_setup(VCPU_SREG_DS); seg_setup(VCPU_SREG_ES); @@ -4903,7 +4970,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); - vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0); + vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); setup_msrs(vmx); @@ -4919,7 +4986,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); - if (vmx_cpu_uses_apicv(vcpu)) + if (kvm_vcpu_apicv_active(vcpu)) memset(&vmx->pi_desc, 0, sizeof(struct pi_desc)); if (vmx->vpid != 0) @@ -6203,15 +6270,6 @@ static __init int hardware_setup(void) kvm_tsc_scaling_ratio_frac_bits = 48; } - if (enable_apicv) - kvm_x86_ops->update_cr8_intercept = NULL; - else { - kvm_x86_ops->hwapic_irr_update = NULL; - kvm_x86_ops->hwapic_isr_update = NULL; - kvm_x86_ops->deliver_posted_interrupt = NULL; - kvm_x86_ops->sync_pir_to_irr = vmx_sync_pir_to_irr_dummy; - } - vmx_disable_intercept_for_msr(MSR_FS_BASE, false); vmx_disable_intercept_for_msr(MSR_GS_BASE, false); vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true); @@ -7901,7 +7959,7 @@ static void dump_vmcs(void) u32 pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL); u32 secondary_exec_control = 0; unsigned long cr4 = vmcs_readl(GUEST_CR4); - u64 efer = vmcs_readl(GUEST_IA32_EFER); + u64 efer = vmcs_read64(GUEST_IA32_EFER); int i, n; if (cpu_has_secondary_exec_ctrls()) @@ -7917,10 +7975,10 @@ static void dump_vmcs(void) if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) && (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA)) { - pr_err("PDPTR0 = 0x%016lx PDPTR1 = 0x%016lx\n", - vmcs_readl(GUEST_PDPTR0), vmcs_readl(GUEST_PDPTR1)); - pr_err("PDPTR2 = 0x%016lx PDPTR3 = 0x%016lx\n", - vmcs_readl(GUEST_PDPTR2), vmcs_readl(GUEST_PDPTR3)); + pr_err("PDPTR0 = 0x%016llx PDPTR1 = 0x%016llx\n", + vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1)); + pr_err("PDPTR2 = 0x%016llx PDPTR3 = 0x%016llx\n", + vmcs_read64(GUEST_PDPTR2), vmcs_read64(GUEST_PDPTR3)); } pr_err("RSP = 0x%016lx RIP = 0x%016lx\n", vmcs_readl(GUEST_RSP), vmcs_readl(GUEST_RIP)); @@ -7941,16 +7999,16 @@ static void dump_vmcs(void) vmx_dump_sel("TR: ", GUEST_TR_SELECTOR); if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) || (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER))) - pr_err("EFER = 0x%016llx PAT = 0x%016lx\n", - efer, vmcs_readl(GUEST_IA32_PAT)); - pr_err("DebugCtl = 0x%016lx DebugExceptions = 0x%016lx\n", - vmcs_readl(GUEST_IA32_DEBUGCTL), + pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", + efer, vmcs_read64(GUEST_IA32_PAT)); + pr_err("DebugCtl = 0x%016llx DebugExceptions = 0x%016lx\n", + vmcs_read64(GUEST_IA32_DEBUGCTL), vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS)); if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) - pr_err("PerfGlobCtl = 0x%016lx\n", - vmcs_readl(GUEST_IA32_PERF_GLOBAL_CTRL)); + pr_err("PerfGlobCtl = 0x%016llx\n", + vmcs_read64(GUEST_IA32_PERF_GLOBAL_CTRL)); if (vmentry_ctl & VM_ENTRY_LOAD_BNDCFGS) - pr_err("BndCfgS = 0x%016lx\n", vmcs_readl(GUEST_BNDCFGS)); + pr_err("BndCfgS = 0x%016llx\n", vmcs_read64(GUEST_BNDCFGS)); pr_err("Interruptibility = %08x ActivityState = %08x\n", vmcs_read32(GUEST_INTERRUPTIBILITY_INFO), vmcs_read32(GUEST_ACTIVITY_STATE)); @@ -7979,11 +8037,12 @@ static void dump_vmcs(void) vmcs_read32(HOST_IA32_SYSENTER_CS), vmcs_readl(HOST_IA32_SYSENTER_EIP)); if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER)) - pr_err("EFER = 0x%016lx PAT = 0x%016lx\n", - vmcs_readl(HOST_IA32_EFER), vmcs_readl(HOST_IA32_PAT)); + pr_err("EFER = 0x%016llx PAT = 0x%016llx\n", + vmcs_read64(HOST_IA32_EFER), + vmcs_read64(HOST_IA32_PAT)); if (vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) - pr_err("PerfGlobCtl = 0x%016lx\n", - vmcs_readl(HOST_IA32_PERF_GLOBAL_CTRL)); + pr_err("PerfGlobCtl = 0x%016llx\n", + vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL)); pr_err("*** Control State ***\n"); pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n", @@ -8006,16 +8065,16 @@ static void dump_vmcs(void) pr_err("IDTVectoring: info=%08x errcode=%08x\n", vmcs_read32(IDT_VECTORING_INFO_FIELD), vmcs_read32(IDT_VECTORING_ERROR_CODE)); - pr_err("TSC Offset = 0x%016lx\n", vmcs_readl(TSC_OFFSET)); + pr_err("TSC Offset = 0x%016llx\n", vmcs_read64(TSC_OFFSET)); if (secondary_exec_control & SECONDARY_EXEC_TSC_SCALING) - pr_err("TSC Multiplier = 0x%016lx\n", - vmcs_readl(TSC_MULTIPLIER)); + pr_err("TSC Multiplier = 0x%016llx\n", + vmcs_read64(TSC_MULTIPLIER)); if (cpu_based_exec_ctrl & CPU_BASED_TPR_SHADOW) pr_err("TPR Threshold = 0x%02x\n", vmcs_read32(TPR_THRESHOLD)); if (pin_based_exec_ctrl & PIN_BASED_POSTED_INTR) pr_err("PostedIntrVec = 0x%02x\n", vmcs_read16(POSTED_INTR_NV)); if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT)) - pr_err("EPT pointer = 0x%016lx\n", vmcs_readl(EPT_POINTER)); + pr_err("EPT pointer = 0x%016llx\n", vmcs_read64(EPT_POINTER)); n = vmcs_read32(CR3_TARGET_COUNT); for (i = 0; i + 1 < n; i += 4) pr_err("CR3 target%u=%016lx target%u=%016lx\n", @@ -8154,7 +8213,7 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) * apicv */ if (!cpu_has_vmx_virtualize_x2apic_mode() || - !vmx_cpu_uses_apicv(vcpu)) + !kvm_vcpu_apicv_active(vcpu)) return; if (!cpu_need_tpr_shadow(vcpu)) @@ -8259,10 +8318,9 @@ static void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) } } -static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu) +static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) { - u64 *eoi_exit_bitmap = vcpu->arch.eoi_exit_bitmap; - if (!vmx_cpu_uses_apicv(vcpu)) + if (!kvm_vcpu_apicv_active(vcpu)) return; vmcs_write64(EOI_EXIT_BITMAP0, eoi_exit_bitmap[0]); @@ -8932,7 +8990,8 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu) best->ebx &= ~bit(X86_FEATURE_INVPCID); } - vmcs_set_secondary_exec_control(secondary_exec_ctl); + if (cpu_has_secondary_exec_ctrls()) + vmcs_set_secondary_exec_control(secondary_exec_ctl); if (static_cpu_has(X86_FEATURE_PCOMMIT) && nested) { if (guest_cpuid_has_pcommit(vcpu)) @@ -9508,7 +9567,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) */ vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv; vmx->nested.pi_pending = false; - vmcs_write64(POSTED_INTR_NV, POSTED_INTR_VECTOR); + vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR); vmcs_write64(POSTED_INTR_DESC_ADDR, page_to_phys(vmx->nested.pi_desc_page) + (unsigned long)(vmcs12->posted_intr_desc_addr & @@ -10169,7 +10228,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * Additionally, restore L2's PDPTR to vmcs12. */ if (enable_ept) { - vmcs12->guest_cr3 = vmcs_read64(GUEST_CR3); + vmcs12->guest_cr3 = vmcs_readl(GUEST_CR3); vmcs12->guest_pdptr0 = vmcs_read64(GUEST_PDPTR0); vmcs12->guest_pdptr1 = vmcs_read64(GUEST_PDPTR1); vmcs12->guest_pdptr2 = vmcs_read64(GUEST_PDPTR2); @@ -10805,7 +10864,8 @@ static struct kvm_x86_ops vmx_x86_ops = { .update_cr8_intercept = update_cr8_intercept, .set_virtual_x2apic_mode = vmx_set_virtual_x2apic_mode, .set_apic_access_page_addr = vmx_set_apic_access_page_addr, - .cpu_uses_apicv = vmx_cpu_uses_apicv, + .get_enable_apicv = vmx_get_enable_apicv, + .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 97592e190413..f53f5b13c677 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -951,7 +951,7 @@ static u32 msrs_to_save[] = { 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_FEATURE_CONTROL, MSR_IA32_BNDCFGS + MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX, }; static unsigned num_msrs_to_save; @@ -966,6 +966,8 @@ static u32 emulated_msrs[] = { HV_X64_MSR_RESET, HV_X64_MSR_VP_INDEX, HV_X64_MSR_VP_RUNTIME, + HV_X64_MSR_SCONTROL, + HV_X64_MSR_STIMER0_CONFIG, HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, @@ -1167,7 +1169,8 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) ++version; - kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); + if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version))) + return; /* * The guest calculates current wall clock time by adding @@ -1683,6 +1686,11 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) #endif } +void kvm_make_mclock_inprogress_request(struct kvm *kvm) +{ + kvm_make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); +} + static void kvm_gen_update_masterclock(struct kvm *kvm) { #ifdef CONFIG_X86_64 @@ -2198,6 +2206,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: + case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); case MSR_IA32_BBL_CR_CTL3: @@ -2402,6 +2411,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4: case HV_X64_MSR_CRASH_CTL: + case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT: return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data); break; @@ -2541,6 +2551,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -2693,6 +2704,11 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu) return kvm_arch_has_noncoherent_dma(vcpu->kvm); } +static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu) +{ + set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests); +} + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Address WBINVD may be executed by guest */ @@ -2748,7 +2764,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { - kvm_x86_ops->sync_pir_to_irr(vcpu); + if (vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); + memcpy(s->regs, vcpu->arch.apic->regs, sizeof *s); return 0; @@ -3191,6 +3209,20 @@ static int kvm_set_guest_paused(struct kvm_vcpu *vcpu) return 0; } +static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, + struct kvm_enable_cap *cap) +{ + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_HYPERV_SYNIC: + return kvm_hv_activate_synic(vcpu); + default: + return -EINVAL; + } +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -3455,6 +3487,15 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_set_guest_paused(vcpu); goto out; } + case KVM_ENABLE_CAP: { + struct kvm_enable_cap cap; + + r = -EFAULT; + if (copy_from_user(&cap, argp, sizeof(cap))) + goto out; + r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap); + break; + } default: r = -EINVAL; } @@ -4006,16 +4047,17 @@ static void kvm_init_msr_list(void) /* * Even MSRs that are valid in the host may not be exposed - * to the guests in some cases. We could work around this - * in VMX with the generic MSR save/load machinery, but it - * is not really worthwhile since it will really only - * happen with nested virtualization. + * to the guests in some cases. */ switch (msrs_to_save[i]) { case MSR_IA32_BNDCFGS: if (!kvm_x86_ops->mpx_supported()) continue; break; + case MSR_TSC_AUX: + if (!kvm_x86_ops->rdtscp_supported()) + continue; + break; default: break; } @@ -5872,6 +5914,12 @@ static void kvm_pv_kick_cpu_op(struct kvm *kvm, unsigned long flags, int apicid) kvm_irq_delivery_to_apic(kvm, NULL, &lapic_irq, NULL); } +void kvm_vcpu_deactivate_apicv(struct kvm_vcpu *vcpu) +{ + vcpu->arch.apicv_active = false; + kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu); +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; @@ -5965,6 +6013,9 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) if (!vcpu->arch.apic) return; + if (vcpu->arch.apicv_active) + return; + if (!vcpu->arch.apic->vapic_addr) max_irr = kvm_lapic_find_highest_irr(vcpu); else @@ -6301,20 +6352,30 @@ static void process_smi(struct kvm_vcpu *vcpu) kvm_mmu_reset_context(vcpu); } +void kvm_make_scan_ioapic_request(struct kvm *kvm) +{ + kvm_make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); +} + static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) { + u64 eoi_exit_bitmap[4]; + if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - memset(vcpu->arch.eoi_exit_bitmap, 0, 256 / 8); + bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); if (irqchip_split(vcpu->kvm)) - kvm_scan_ioapic_routes(vcpu, vcpu->arch.eoi_exit_bitmap); + kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { - kvm_x86_ops->sync_pir_to_irr(vcpu); - kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap); + if (vcpu->arch.apicv_active) + kvm_x86_ops->sync_pir_to_irr(vcpu); + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } - kvm_x86_ops->load_eoi_exitmap(vcpu); + bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, + vcpu_to_synic(vcpu)->vec_bitmap, 256); + kvm_x86_ops->load_eoi_exitmap(vcpu, eoi_exit_bitmap); } static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu) @@ -6422,7 +6483,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); if (test_bit(vcpu->arch.pending_ioapic_eoi, - (void *) vcpu->arch.eoi_exit_bitmap)) { + vcpu->arch.ioapic_handled_vectors)) { vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI; vcpu->run->eoi.vector = vcpu->arch.pending_ioapic_eoi; @@ -6446,6 +6507,20 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) r = 0; goto out; } + if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) { + vcpu->run->exit_reason = KVM_EXIT_HYPERV; + vcpu->run->hyperv = vcpu->arch.hyperv.exit; + r = 0; + goto out; + } + + /* + * KVM_REQ_HV_STIMER has to be processed after + * KVM_REQ_CLOCK_UPDATE, because Hyper-V SynIC timers + * depend on the guest clock being up-to-date + */ + if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) + kvm_hv_process_stimers(vcpu); } /* @@ -6457,7 +6532,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * Update architecture specific hints for APIC * virtual interrupt delivery. */ - if (kvm_x86_ops->hwapic_irr_update) + if (vcpu->arch.apicv_active) kvm_x86_ops->hwapic_irr_update(vcpu, kvm_lapic_find_highest_irr(vcpu)); } @@ -7528,6 +7603,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) BUG_ON(vcpu->kvm == NULL); kvm = vcpu->kvm; + vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(); vcpu->arch.pv.pv_unhalted = false; vcpu->arch.emulate_ctxt.ops = &emulate_ops; if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_reset_bsp(vcpu)) @@ -7585,6 +7661,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) vcpu->arch.pending_external_vector = -1; + kvm_hv_vcpu_init(vcpu); + return 0; fail_free_mce_banks: @@ -7603,6 +7681,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { int idx; + kvm_hv_vcpu_uninit(vcpu); kvm_pmu_destroy(vcpu); kfree(vcpu->arch.mce_banks); kvm_free_lapic(vcpu); @@ -7997,6 +8076,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) kvm_cpu_has_interrupt(vcpu)) return true; + if (kvm_hv_has_stimer_pending(vcpu)) + return true; + return false; } diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index a43b2eafc466..4ba229ac3f4f 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -1473,7 +1473,6 @@ __init void lguest_init(void) pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode; pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu; pv_mmu_ops.pte_update = lguest_pte_update; - pv_mmu_ops.pte_update_defer = lguest_pte_update; #ifdef CONFIG_X86_LOCAL_APIC /* APIC read/write intercepts */ diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f2587888d987..a501fa25da41 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 misc.o cmdline.o +lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o diff --git a/arch/x86/lib/cpu.c b/arch/x86/lib/cpu.c new file mode 100644 index 000000000000..aa417a97511c --- /dev/null +++ b/arch/x86/lib/cpu.c @@ -0,0 +1,35 @@ +#include <linux/module.h> + +unsigned int x86_family(unsigned int sig) +{ + unsigned int x86; + + x86 = (sig >> 8) & 0xf; + + if (x86 == 0xf) + x86 += (sig >> 20) & 0xff; + + return x86; +} +EXPORT_SYMBOL_GPL(x86_family); + +unsigned int x86_model(unsigned int sig) +{ + unsigned int fam, model; + + fam = x86_family(sig); + + model = (sig >> 4) & 0xf; + + if (fam >= 0x6) + model += ((sig >> 16) & 0xf) << 4; + + return model; +} +EXPORT_SYMBOL_GPL(x86_model); + +unsigned int x86_stepping(unsigned int sig) +{ + return sig & 0xf; +} +EXPORT_SYMBOL_GPL(x86_stepping); diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 43623739c7cf..004c861b1648 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -1,6 +1,8 @@ #include <linux/module.h> #include <linux/preempt.h> #include <asm/msr.h> +#define CREATE_TRACE_POINTS +#include <asm/msr-trace.h> struct msr *msrs_alloc(void) { @@ -108,3 +110,27 @@ int msr_clear_bit(u32 msr, u8 bit) { return __flip_bit(msr, bit, false); } + +#ifdef CONFIG_TRACEPOINTS +void do_trace_write_msr(unsigned msr, u64 val, int failed) +{ + trace_write_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_write_msr); +EXPORT_TRACEPOINT_SYMBOL(write_msr); + +void do_trace_read_msr(unsigned msr, u64 val, int failed) +{ + trace_read_msr(msr, val, failed); +} +EXPORT_SYMBOL(do_trace_read_msr); +EXPORT_TRACEPOINT_SYMBOL(read_msr); + +void do_trace_rdpmc(unsigned counter, u64 val, int failed) +{ + trace_rdpmc(counter, val, failed); +} +EXPORT_SYMBOL(do_trace_rdpmc); +EXPORT_TRACEPOINT_SYMBOL(rdpmc); + +#endif diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 65c47fda26fc..f9d38a48e3c8 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -15,6 +15,7 @@ obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o obj-$(CONFIG_X86_PTDUMP_CORE) += dump_pagetables.o +obj-$(CONFIG_X86_PTDUMP) += debug_pagetables.o obj-$(CONFIG_HIGHMEM) += highmem_32.o diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c new file mode 100644 index 000000000000..bfcffdf6c577 --- /dev/null +++ b/arch/x86/mm/debug_pagetables.c @@ -0,0 +1,46 @@ +#include <linux/debugfs.h> +#include <linux/module.h> +#include <linux/seq_file.h> +#include <asm/pgtable.h> + +static int ptdump_show(struct seq_file *m, void *v) +{ + ptdump_walk_pgd_level(m, NULL); + return 0; +} + +static int ptdump_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show, NULL); +} + +static const struct file_operations ptdump_fops = { + .owner = THIS_MODULE, + .open = ptdump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static struct dentry *pe; + +static int __init pt_dump_debug_init(void) +{ + pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL, + &ptdump_fops); + if (!pe) + return -ENOMEM; + + return 0; +} + +static void __exit pt_dump_debug_exit(void) +{ + debugfs_remove_recursive(pe); +} + +module_init(pt_dump_debug_init); +module_exit(pt_dump_debug_exit); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>"); +MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables"); diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 0f1c6fc3ddd8..4a6f1d9b5106 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -426,38 +426,15 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) { ptdump_walk_pgd_level_core(m, pgd, false); } +EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level); void ptdump_walk_pgd_level_checkwx(void) { ptdump_walk_pgd_level_core(NULL, NULL, true); } -#ifdef CONFIG_X86_PTDUMP -static int ptdump_show(struct seq_file *m, void *v) +static int __init pt_dump_init(void) { - ptdump_walk_pgd_level(m, NULL); - return 0; -} - -static int ptdump_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, ptdump_show, NULL); -} - -static const struct file_operations ptdump_fops = { - .open = ptdump_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; -#endif - -static int pt_dump_init(void) -{ -#ifdef CONFIG_X86_PTDUMP - struct dentry *pe; -#endif - #ifdef CONFIG_X86_32 /* Not a compile-time constant on x86-32 */ address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; @@ -468,13 +445,6 @@ static int pt_dump_init(void) address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; #endif -#ifdef CONFIG_X86_PTDUMP - pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL, - &ptdump_fops); - if (!pe) - return -ENOMEM; -#endif - return 0; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index b9c78f3bcd67..0d8d53d1f5cc 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -194,8 +194,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, * Check if the request spans more than any BAR in the iomem resource * tree. */ - WARN_ONCE(iomem_map_sanity_check(unaligned_phys_addr, unaligned_size), - KERN_INFO "Info: mapping multiple BARs. Your kernel is fine."); + if (iomem_map_sanity_check(unaligned_phys_addr, unaligned_size)) + pr_warn("caller %pS mapping multiple BARs\n", caller); return ret_addr; err_free_area: diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a3137a4feed1..6000ad7f560c 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -129,14 +129,16 @@ within(unsigned long addr, unsigned long start, unsigned long end) */ void clflush_cache_range(void *vaddr, unsigned int size) { - unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1; + const unsigned long clflush_size = boot_cpu_data.x86_clflush_size; + void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1)); void *vend = vaddr + size; - void *p; + + if (p >= vend) + return; mb(); - for (p = (void *)((unsigned long)vaddr & ~clflush_mask); - p < vend; p += boot_cpu_data.x86_clflush_size) + for (; p < vend; p += clflush_size) clflushopt(p); mb(); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 188e3e07eeeb..031782e74231 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -586,7 +586,7 @@ int free_memtype(u64 start, u64 end) entry = rbt_memtype_erase(start, end); spin_unlock(&memtype_lock); - if (!entry) { + if (IS_ERR(entry)) { pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n", current->comm, current->pid, start, end - 1); return -EINVAL; @@ -992,6 +992,16 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, vma->vm_flags &= ~VM_PAT; } +/* + * untrack_pfn_moved is called, while mremapping a pfnmap for a new region, + * with the old vma after its pfnmap page table has been removed. The new + * vma has a new pfnmap to the same pfn & cache type with VM_PAT set. + */ +void untrack_pfn_moved(struct vm_area_struct *vma) +{ + vma->vm_flags &= ~VM_PAT; +} + pgprot_t pgprot_writecombine(pgprot_t prot) { return __pgprot(pgprot_val(prot) | diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index 63931080366a..2f7702253ccf 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -98,8 +98,13 @@ static struct memtype *memtype_rb_lowest_match(struct rb_root *root, return last_lower; /* Returns NULL if there is no overlap */ } -static struct memtype *memtype_rb_exact_match(struct rb_root *root, - u64 start, u64 end) +enum { + MEMTYPE_EXACT_MATCH = 0, + MEMTYPE_END_MATCH = 1 +}; + +static struct memtype *memtype_rb_match(struct rb_root *root, + u64 start, u64 end, int match_type) { struct memtype *match; @@ -107,7 +112,12 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root, while (match != NULL && match->start < end) { struct rb_node *node; - if (match->start == start && match->end == end) + if ((match_type == MEMTYPE_EXACT_MATCH) && + (match->start == start) && (match->end == end)) + return match; + + if ((match_type == MEMTYPE_END_MATCH) && + (match->start < start) && (match->end == end)) return match; node = rb_next(&match->rb); @@ -117,7 +127,7 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root, match = NULL; } - return NULL; /* Returns NULL if there is no exact match */ + return NULL; /* Returns NULL if there is no match */ } static int memtype_rb_check_conflict(struct rb_root *root, @@ -210,12 +220,36 @@ struct memtype *rbt_memtype_erase(u64 start, u64 end) { struct memtype *data; - data = memtype_rb_exact_match(&memtype_rbroot, start, end); - if (!data) - goto out; + /* + * Since the memtype_rbroot tree allows overlapping ranges, + * rbt_memtype_erase() checks with EXACT_MATCH first, i.e. free + * a whole node for the munmap case. If no such entry is found, + * it then checks with END_MATCH, i.e. shrink the size of a node + * from the end for the mremap case. + */ + data = memtype_rb_match(&memtype_rbroot, start, end, + MEMTYPE_EXACT_MATCH); + if (!data) { + data = memtype_rb_match(&memtype_rbroot, start, end, + MEMTYPE_END_MATCH); + if (!data) + return ERR_PTR(-EINVAL); + } + + if (data->start == start) { + /* munmap: erase this node */ + rb_erase_augmented(&data->rb, &memtype_rbroot, + &memtype_rb_augment_cb); + } else { + /* mremap: update the end value of this node */ + rb_erase_augmented(&data->rb, &memtype_rbroot, + &memtype_rb_augment_cb); + data->end = start; + data->subtree_max_end = data->end; + memtype_rb_insert(&memtype_rbroot, data); + return NULL; + } - rb_erase_augmented(&data->rb, &memtype_rbroot, &memtype_rb_augment_cb); -out: return data; } diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index fb0a9dd1d6e4..ee9c2e3a7199 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -414,7 +414,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, if (changed && dirty) { *ptep = entry; - pte_update_defer(vma->vm_mm, address, ptep); + pte_update(vma->vm_mm, address, ptep); } return changed; @@ -431,7 +431,6 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, if (changed && dirty) { *pmdp = entry; - pmd_update_defer(vma->vm_mm, address, pmdp); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -469,9 +468,6 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, (unsigned long *)pmdp); - if (ret) - pmd_update(vma->vm_mm, addr, pmdp); - return ret; } #endif @@ -518,7 +514,6 @@ void pmdp_splitting_flush(struct vm_area_struct *vma, set = !test_and_set_bit(_PAGE_BIT_SPLITTING, (unsigned long *)pmdp); if (set) { - pmd_update(vma->vm_mm, address, pmdp); /* need tlb flush only to serialize against gup-fast */ flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c index 90555bf60aa4..92e2eacb3321 100644 --- a/arch/x86/mm/setup_nx.c +++ b/arch/x86/mm/setup_nx.c @@ -31,7 +31,7 @@ early_param("noexec", noexec_setup); void x86_configure_nx(void) { - if (cpu_has_nx && !disable_nx) + if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx) __supported_pte_mask |= _PAGE_NX; else __supported_pte_mask &= ~_PAGE_NX; @@ -39,7 +39,7 @@ void x86_configure_nx(void) void __init x86_report_nx(void) { - if (!cpu_has_nx) { + if (!boot_cpu_has(X86_FEATURE_NX)) { printk(KERN_NOTICE "Notice: NX (Execute Disable) protection " "missing in CPU!\n"); } else { diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index c2aea63bee20..b5f821881465 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -203,6 +203,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n", (unsigned long long)start, (unsigned long long)end - 1); + max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1)); + return 0; out_err_bad_srat: bad_srat(); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 75991979f667..4286f3618bd0 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -193,7 +193,7 @@ struct jit_context { 32 /* space for rbx, r13, r14, r15 */ + \ 8 /* space for skb_copy_bits() buffer */) -#define PROLOGUE_SIZE 51 +#define PROLOGUE_SIZE 48 /* emit x64 prologue code for BPF program and check it's size. * bpf_tail_call helper will skip it while jumping into another program @@ -229,11 +229,15 @@ static void emit_prologue(u8 **pprog) /* mov qword ptr [rbp-X],r15 */ EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24); - /* clear A and X registers */ - EMIT2(0x31, 0xc0); /* xor eax, eax */ - EMIT3(0x4D, 0x31, 0xED); /* xor r13, r13 */ + /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls + * we need to reset the counter to 0. It's done in two instructions, + * resetting rax register to 0 (xor on eax gets 0 extended), and + * moving it to the counter location. + */ - /* clear tail_cnt: mov qword ptr [rbp-X], rax */ + /* xor eax, eax */ + EMIT2(0x31, 0xc0); + /* mov qword ptr [rbp-X], rax */ EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32); BUILD_BUG_ON(cnt != PROLOGUE_SIZE); @@ -455,6 +459,18 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } case BPF_ALU | BPF_MOV | BPF_K: + /* optimization: if imm32 is zero, use 'xor <dst>,<dst>' + * to save 3 bytes. + */ + if (imm32 == 0) { + if (is_ereg(dst_reg)) + EMIT1(add_2mod(0x40, dst_reg, dst_reg)); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT2(b2, add_2reg(b3, dst_reg, dst_reg)); + break; + } + /* mov %eax, imm32 */ if (is_ereg(dst_reg)) EMIT1(add_1mod(0x40, dst_reg)); @@ -469,6 +485,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, return -EINVAL; } + /* optimization: if imm64 is zero, use 'xor <dst>,<dst>' + * to save 7 bytes. + */ + if (insn[0].imm == 0 && insn[1].imm == 0) { + b1 = add_2mod(0x48, dst_reg, dst_reg); + b2 = 0x31; /* xor */ + b3 = 0xC0; + EMIT3(b1, b2, add_2reg(b3, dst_reg, dst_reg)); + + insn++; + i++; + break; + } + /* movabsq %rax, imm64 */ EMIT2(add_1mod(0x48, dst_reg), add_1reg(0xB8, dst_reg)); EMIT(insn[0].imm, 4); diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 327f21c3bde1..8dd80050d705 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -28,6 +28,7 @@ #include <linux/nmi.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/clocksource.h> #include <asm/apic.h> #include <asm/current.h> diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 9ab52791fed5..d5f64996394a 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -23,6 +23,7 @@ #include <asm/debugreg.h> #include <asm/cpu.h> #include <asm/mmu_context.h> +#include <linux/dmi.h> #ifdef CONFIG_X86_32 __visible unsigned long saved_context_ebx; @@ -32,6 +33,29 @@ __visible unsigned long saved_context_eflags; #endif struct saved_context saved_context; +static void msr_save_context(struct saved_context *ctxt) +{ + struct saved_msr *msr = ctxt->saved_msrs.array; + struct saved_msr *end = msr + ctxt->saved_msrs.num; + + while (msr < end) { + msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + msr++; + } +} + +static void msr_restore_context(struct saved_context *ctxt) +{ + struct saved_msr *msr = ctxt->saved_msrs.array; + struct saved_msr *end = msr + ctxt->saved_msrs.num; + + while (msr < end) { + if (msr->valid) + wrmsrl(msr->info.msr_no, msr->info.reg.q); + msr++; + } +} + /** * __save_processor_state - save CPU registers before creating a * hibernation image and before restoring the memory state from it @@ -111,6 +135,7 @@ static void __save_processor_state(struct saved_context *ctxt) #endif ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE, &ctxt->misc_enable); + msr_save_context(ctxt); } /* Needed by apm.c */ @@ -229,6 +254,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) x86_platform.restore_sched_clock_state(); mtrr_bp_restore(); perf_restore_debug_store(); + msr_restore_context(ctxt); } /* Needed by apm.c */ @@ -320,3 +346,69 @@ static int __init bsp_pm_check_init(void) } core_initcall(bsp_pm_check_init); + +static int msr_init_context(const u32 *msr_id, const int total_num) +{ + int i = 0; + struct saved_msr *msr_array; + + if (saved_context.saved_msrs.array || saved_context.saved_msrs.num > 0) { + pr_err("x86/pm: MSR quirk already applied, please check your DMI match table.\n"); + return -EINVAL; + } + + msr_array = kmalloc_array(total_num, sizeof(struct saved_msr), GFP_KERNEL); + if (!msr_array) { + pr_err("x86/pm: Can not allocate memory to save/restore MSRs during suspend.\n"); + return -ENOMEM; + } + + for (i = 0; i < total_num; i++) { + msr_array[i].info.msr_no = msr_id[i]; + msr_array[i].valid = false; + msr_array[i].info.reg.q = 0; + } + saved_context.saved_msrs.num = total_num; + saved_context.saved_msrs.array = msr_array; + + return 0; +} + +/* + * The following section is a quirk framework for problematic BIOSen: + * Sometimes MSRs are modified by the BIOSen after suspended to + * RAM, this might cause unexpected behavior after wakeup. + * Thus we save/restore these specified MSRs across suspend/resume + * in order to work around it. + * + * For any further problematic BIOSen/platforms, + * please add your own function similar to msr_initialize_bdw. + */ +static int msr_initialize_bdw(const struct dmi_system_id *d) +{ + /* Add any extra MSR ids into this array. */ + u32 bdw_msr_id[] = { MSR_IA32_THERM_CONTROL }; + + pr_info("x86/pm: %s detected, MSR saving is needed during suspending.\n", d->ident); + return msr_init_context(bdw_msr_id, ARRAY_SIZE(bdw_msr_id)); +} + +static struct dmi_system_id msr_save_dmi_table[] = { + { + .callback = msr_initialize_bdw, + .ident = "BROADWELL BDX_EP", + .matches = { + DMI_MATCH(DMI_PRODUCT_NAME, "GRANTLEY"), + DMI_MATCH(DMI_PRODUCT_VERSION, "E63448-400"), + }, + }, + {} +}; + +static int pm_check_save_msr(void) +{ + dmi_check_system(msr_save_dmi_table); + return 0; +} + +device_initcall(pm_check_save_msr); diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index a8fecc226946..3ee2bb6b440b 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -17,7 +17,7 @@ obj-y = bug.o bugs_$(BITS).o delay.o fault.o ksyms.o ldt.o \ ifeq ($(CONFIG_X86_32),y) obj-y += checksum_32.o -obj-$(CONFIG_BINFMT_ELF) += elfcore.o +obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h index 81d6562ce01d..11ab90dc5f14 100644 --- a/arch/x86/um/asm/syscall.h +++ b/arch/x86/um/asm/syscall.h @@ -1,6 +1,7 @@ #ifndef __UM_ASM_SYSCALL_H #define __UM_ASM_SYSCALL_H +#include <asm/syscall-generic.h> #include <uapi/linux/audit.h> typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long, diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index a29756f2d940..47c78d5e5c32 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -68,6 +68,7 @@ static const int reg_offsets[] = { [EFL] = HOST_EFLAGS, [UESP] = HOST_SP, [SS] = HOST_SS, + [ORIG_EAX] = HOST_ORIG_AX, }; int putreg(struct task_struct *child, int regno, unsigned long value) @@ -83,6 +84,7 @@ int putreg(struct task_struct *child, int regno, unsigned long value) case EAX: case EIP: case UESP: + case ORIG_EAX: break; case FS: if (value && (value & 3) != 3) @@ -108,9 +110,6 @@ int putreg(struct task_struct *child, int regno, unsigned long value) value &= FLAG_MASK; child->thread.regs.regs.gp[HOST_EFLAGS] |= value; return 0; - case ORIG_EAX: - child->thread.regs.regs.syscall = value; - return 0; default : panic("Bad register in putreg() : %d\n", regno); } @@ -143,8 +142,6 @@ unsigned long getreg(struct task_struct *child, int regno) regno >>= 2; switch (regno) { - case ORIG_EAX: - return child->thread.regs.regs.syscall; case FS: case GS: case DS: @@ -163,6 +160,7 @@ unsigned long getreg(struct task_struct *child, int regno) case EDI: case EBP: case EFL: + case ORIG_EAX: break; default: panic("Bad register in getreg() : %d\n", regno); diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index acda713ab5be..abf4901c917b 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -64,7 +64,7 @@ static u32 xen_apic_read(u32 reg) if (reg != APIC_ID) return 0; - ret = HYPERVISOR_dom0_op(&op); + ret = HYPERVISOR_platform_op(&op); if (ret) return 0; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index b7de78bdc09c..d09e4c9d7cc5 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -415,7 +415,7 @@ static bool __init xen_check_mwait(void) set_xen_guest_handle(op.u.set_pminfo.pdc, buf); - if ((HYPERVISOR_dom0_op(&op) == 0) && + if ((HYPERVISOR_platform_op(&op) == 0) && (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) { cpuid_leaf5_ecx_val = cx; cpuid_leaf5_edx_val = dx; @@ -1229,10 +1229,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .iret = xen_iret, #ifdef CONFIG_X86_64 - .usergs_sysret32 = xen_sysret32, .usergs_sysret64 = xen_sysret64, -#else - .irq_enable_sysexit = xen_sysexit, #endif .load_tr_desc = paravirt_nop, @@ -1265,12 +1262,6 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .end_context_switch = xen_end_context_switch, }; -static const struct pv_apic_ops xen_apic_ops __initconst = { -#ifdef CONFIG_X86_LOCAL_APIC - .startup_ipi_hook = paravirt_nop, -#endif -}; - static void xen_reboot(int reason) { struct sched_shutdown r = { .reason = reason }; @@ -1374,7 +1365,7 @@ static void __init xen_boot_params_init_edd(void) info->params.length = sizeof(info->params); set_xen_guest_handle(op.u.firmware_info.u.disk_info.edd_params, &info->params); - ret = HYPERVISOR_dom0_op(&op); + ret = HYPERVISOR_platform_op(&op); if (ret) break; @@ -1392,7 +1383,7 @@ static void __init xen_boot_params_init_edd(void) op.u.firmware_info.type = XEN_FW_DISK_MBR_SIGNATURE; for (nr = 0; nr < EDD_MBR_SIG_MAX; nr++) { op.u.firmware_info.index = nr; - ret = HYPERVISOR_dom0_op(&op); + ret = HYPERVISOR_platform_op(&op); if (ret) break; mbr_signature[nr] = op.u.firmware_info.u.disk_mbr_signature.mbr_signature; @@ -1538,7 +1529,6 @@ asmlinkage __visible void __init xen_start_kernel(void) if (xen_initial_domain()) pv_info.features |= PV_SUPPORTED_RTC; pv_init_ops = xen_init_ops; - pv_apic_ops = xen_apic_ops; if (!xen_pvh_domain()) { pv_cpu_ops = xen_cpu_ops; @@ -1700,7 +1690,7 @@ asmlinkage __visible void __init xen_start_kernel(void) xen_start_info->console.domU.mfn = 0; xen_start_info->console.domU.evtchn = 0; - if (HYPERVISOR_dom0_op(&op) == 0) + if (HYPERVISOR_platform_op(&op) == 0) boot_params.kbd_status = op.u.firmware_info.u.kbd_shift_flags; /* Make sure ACS will be enabled */ diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index cb5e266a8bf7..c913ca4f6958 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2436,7 +2436,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = { .flush_tlb_others = xen_flush_tlb_others, .pte_update = paravirt_nop, - .pte_update_defer = paravirt_nop, .pgd_alloc = xen_pgd_alloc, .pgd_free = xen_pgd_free, diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index df0c40559583..7f664c416faf 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -34,7 +34,8 @@ static void xen_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; - xen_hvm_init_shared_info(); + if (!suspend_cancelled) + xen_hvm_init_shared_info(); xen_callback_vector(); xen_unplug_emulated_devices(); if (xen_feature(XENFEAT_hvm_safe_pvclock)) { diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index f1ba6a092854..a0a4e554c6f1 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -16,6 +16,7 @@ #include <linux/gfp.h> #include <linux/slab.h> #include <linux/pvclock_gtod.h> +#include <linux/timekeeper_internal.h> #include <asm/pvclock.h> #include <asm/xen/hypervisor.h> @@ -32,86 +33,12 @@ #define TIMER_SLOP 100000 #define NS_PER_TICK (1000000000LL / HZ) -/* runstate info updated by Xen */ -static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate); - /* snapshots of runstate info */ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot); /* unused ns of stolen time */ static DEFINE_PER_CPU(u64, xen_residual_stolen); -/* return an consistent snapshot of 64-bit time/counter value */ -static u64 get64(const u64 *p) -{ - u64 ret; - - if (BITS_PER_LONG < 64) { - u32 *p32 = (u32 *)p; - u32 h, l; - - /* - * Read high then low, and then make sure high is - * still the same; this will only loop if low wraps - * and carries into high. - * XXX some clean way to make this endian-proof? - */ - do { - h = p32[1]; - barrier(); - l = p32[0]; - barrier(); - } while (p32[1] != h); - - ret = (((u64)h) << 32) | l; - } else - ret = *p; - - return ret; -} - -/* - * Runstate accounting - */ -static void get_runstate_snapshot(struct vcpu_runstate_info *res) -{ - u64 state_time; - struct vcpu_runstate_info *state; - - BUG_ON(preemptible()); - - state = this_cpu_ptr(&xen_runstate); - - /* - * The runstate info is always updated by the hypervisor on - * the current CPU, so there's no need to use anything - * stronger than a compiler barrier when fetching it. - */ - do { - state_time = get64(&state->state_entry_time); - barrier(); - *res = *state; - barrier(); - } while (get64(&state->state_entry_time) != state_time); -} - -/* return true when a vcpu could run but has no real cpu to run on */ -bool xen_vcpu_stolen(int vcpu) -{ - return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable; -} - -void xen_setup_runstate_info(int cpu) -{ - struct vcpu_register_runstate_memory_area area; - - area.addr.v = &per_cpu(xen_runstate, cpu); - - if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area, - cpu, &area)) - BUG(); -} - static void do_stolen_accounting(void) { struct vcpu_runstate_info state; @@ -119,7 +46,7 @@ static void do_stolen_accounting(void) s64 runnable, offline, stolen; cputime_t ticks; - get_runstate_snapshot(&state); + xen_get_runstate_snapshot(&state); WARN_ON(state.state != RUNSTATE_running); @@ -194,26 +121,46 @@ static int xen_pvclock_gtod_notify(struct notifier_block *nb, unsigned long was_set, void *priv) { /* Protected by the calling core code serialization */ - static struct timespec next_sync; + static struct timespec64 next_sync; struct xen_platform_op op; - struct timespec now; + struct timespec64 now; + struct timekeeper *tk = priv; + static bool settime64_supported = true; + int ret; - now = __current_kernel_time(); + now.tv_sec = tk->xtime_sec; + now.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); /* * We only take the expensive HV call when the clock was set * or when the 11 minutes RTC synchronization time elapsed. */ - if (!was_set && timespec_compare(&now, &next_sync) < 0) + if (!was_set && timespec64_compare(&now, &next_sync) < 0) return NOTIFY_OK; - op.cmd = XENPF_settime; - op.u.settime.secs = now.tv_sec; - op.u.settime.nsecs = now.tv_nsec; - op.u.settime.system_time = xen_clocksource_read(); +again: + if (settime64_supported) { + op.cmd = XENPF_settime64; + op.u.settime64.mbz = 0; + op.u.settime64.secs = now.tv_sec; + op.u.settime64.nsecs = now.tv_nsec; + op.u.settime64.system_time = xen_clocksource_read(); + } else { + op.cmd = XENPF_settime32; + op.u.settime32.secs = now.tv_sec; + op.u.settime32.nsecs = now.tv_nsec; + op.u.settime32.system_time = xen_clocksource_read(); + } + + ret = HYPERVISOR_platform_op(&op); - (void)HYPERVISOR_dom0_op(&op); + if (ret == -ENOSYS && settime64_supported) { + settime64_supported = false; + goto again; + } + if (ret < 0) + return NOTIFY_BAD; /* * Move the next drift compensation time 11 minutes diff --git a/arch/x86/xen/xen-asm_32.S b/arch/x86/xen/xen-asm_32.S index fd92a64d748e..feb6d40a0860 100644 --- a/arch/x86/xen/xen-asm_32.S +++ b/arch/x86/xen/xen-asm_32.S @@ -35,20 +35,6 @@ check_events: ret /* - * We can't use sysexit directly, because we're not running in ring0. - * But we can easily fake it up using iret. Assuming xen_sysexit is - * jumped to with a standard stack frame, we can just strip it back to - * a standard iret frame and use iret. - */ -ENTRY(xen_sysexit) - movl PT_EAX(%esp), %eax /* Shouldn't be necessary? */ - orl $X86_EFLAGS_IF, PT_EFLAGS(%esp) - lea PT_EIP(%esp), %esp - - jmp xen_iret -ENDPROC(xen_sysexit) - -/* * This is run where a normal iret would be run, with the same stack setup: * 8: eflags * 4: cs diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index f22667abf7b9..cc8acc410ddb 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -68,25 +68,6 @@ ENTRY(xen_sysret64) ENDPATCH(xen_sysret64) RELOC(xen_sysret64, 1b+1) -ENTRY(xen_sysret32) - /* - * We're already on the usermode stack at this point, but - * still with the kernel gs, so we can easily switch back - */ - movq %rsp, PER_CPU_VAR(rsp_scratch) - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - - pushq $__USER32_DS - pushq PER_CPU_VAR(rsp_scratch) - pushq %r11 - pushq $__USER32_CS - pushq %rcx - - pushq $0 -1: jmp hypercall_iret -ENDPATCH(xen_sysret32) -RELOC(xen_sysret32, 1b+1) - /* * Xen handles syscall callbacks much like ordinary exceptions, which * means we have: diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1399423f3418..4140b070f2e9 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -139,9 +139,6 @@ DECL_ASM(void, xen_restore_fl_direct, unsigned long); /* These are not functions, and cannot be called normally */ __visible void xen_iret(void); -#ifdef CONFIG_X86_32 -__visible void xen_sysexit(void); -#endif __visible void xen_sysret32(void); __visible void xen_sysret64(void); __visible void xen_adjust_exception_frame(void); diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h index 4120af086160..fd3b96d1153f 100644 --- a/arch/xtensa/include/uapi/asm/socket.h +++ b/arch/xtensa/include/uapi/asm/socket.h @@ -96,4 +96,7 @@ #define SO_ATTACH_BPF 50 #define SO_DETACH_BPF SO_DETACH_FILTER +#define SO_ATTACH_REUSEPORT_CBPF 51 +#define SO_ATTACH_REUSEPORT_EBPF 52 + #endif /* _XTENSA_SOCKET_H */ diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index 3c3ace2c46b6..f58a4e6472cb 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -227,16 +227,12 @@ static ssize_t proc_read_simdisk(struct file *file, char __user *buf, static ssize_t proc_write_simdisk(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - char *tmp = kmalloc(count + 1, GFP_KERNEL); + char *tmp = memdup_user_nul(buf, count); struct simdisk *dev = PDE_DATA(file_inode(file)); int err; - if (tmp == NULL) - return -ENOMEM; - if (copy_from_user(tmp, buf, count)) { - err = -EFAULT; - goto out_free; - } + if (IS_ERR(tmp)) + return PTR_ERR(tmp); err = simdisk_detach(dev); if (err != 0) @@ -244,8 +240,6 @@ static ssize_t proc_write_simdisk(struct file *file, const char __user *buf, if (count > 0 && tmp[count - 1] == '\n') tmp[count - 1] = 0; - else - tmp[count] = 0; if (tmp[0]) err = simdisk_attach(dev, tmp); |