diff options
author | H. Peter Anvin <hpa@linux.intel.com> | 2014-06-18 15:26:19 -0700 |
---|---|---|
committer | H. Peter Anvin <hpa@linux.intel.com> | 2014-06-18 15:26:19 -0700 |
commit | 03ab3da3b215bac4ebb093c808d54596e03e3225 (patch) | |
tree | a42534bb7f314b561b362ad0b5af7eff8dbb9726 /arch/x86 | |
parent | 6229ad278ca74acdbc8bd3a3d469322a3de91039 (diff) | |
parent | 7171511eaec5bf23fb06078f59784a3a0626b38f (diff) | |
download | op-kernel-dev-03ab3da3b215bac4ebb093c808d54596e03e3225.zip op-kernel-dev-03ab3da3b215bac4ebb093c808d54596e03e3225.tar.gz |
Merge tag 'v3.16-rc1' into x86/cpufeature
Linux 3.16-rc1
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Diffstat (limited to 'arch/x86')
172 files changed, 4860 insertions, 3319 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 25d2c6f..fcefdda 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -26,7 +26,7 @@ config X86 select ARCH_MIGHT_HAVE_PC_SERIO select HAVE_AOUT if X86_32 select HAVE_UNSTABLE_SCHED_CLOCK - select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_INT128 if X86_64 select ARCH_WANTS_PROT_NUMA_PROT_NONE select HAVE_IDE @@ -41,7 +41,7 @@ config X86 select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS - select HAVE_DMA_CONTIGUOUS if !SWIOTLB + select HAVE_DMA_CONTIGUOUS select HAVE_KRETPROBES select GENERIC_EARLY_IOREMAP select HAVE_OPTPROBES @@ -105,7 +105,7 @@ config X86 select HAVE_ARCH_SECCOMP_FILTER select BUILDTIME_EXTABLE_SORT select GENERIC_CMOS_UPDATE - select HAVE_ARCH_SOFT_DIRTY + select HAVE_ARCH_SOFT_DIRTY if X86_64 select CLOCKSOURCE_WATCHDOG select GENERIC_CLOCKEVENTS select ARCH_CLOCKSOURCE_DATA @@ -121,6 +121,7 @@ config X86 select MODULES_USE_ELF_RELA if X86_64 select CLONE_BACKWARDS if X86_32 select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_QUEUE_RWLOCK select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION select OLD_SIGACTION if X86_32 select COMPAT_OLD_SIGACTION if IA32_EMULATION @@ -261,6 +262,9 @@ config ARCH_HWEIGHT_CFLAGS config ARCH_SUPPORTS_UPROBES def_bool y +config FIX_EARLYCON_MEM + def_bool y + source "init/Kconfig" source "kernel/Kconfig.freezer" @@ -415,7 +419,6 @@ config X86_UV config X86_GOLDFISH bool "Goldfish (Virtual Platform)" - depends on X86_32 depends on X86_EXTENDED_PLATFORM ---help--- Enable support for the Goldfish virtual platform used primarily @@ -831,6 +834,7 @@ config X86_LOCAL_APIC config X86_IO_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI + select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS bool "Reroute for broken boot IRQs" @@ -909,10 +913,27 @@ config VM86 default y depends on X86_32 ---help--- - This option is required by programs like DOSEMU to run 16-bit legacy - code on X86 processors. It also may be needed by software like - XFree86 to initialize some video cards via BIOS. Disabling this - option saves about 6k. + This option is required by programs like DOSEMU to run + 16-bit real mode legacy code on x86 processors. It also may + be needed by software like XFree86 to initialize some video + cards via BIOS. Disabling this option saves about 6K. + +config X86_16BIT + bool "Enable support for 16-bit segments" if EXPERT + default y + ---help--- + This option is required by programs like Wine to run 16-bit + protected mode legacy code on x86 processors. Disabling + this option saves about 300 bytes on i386, or around 6K text + plus 16K runtime memory on x86-64, + +config X86_ESPFIX32 + def_bool y + depends on X86_16BIT && X86_32 + +config X86_ESPFIX64 + def_bool y + depends on X86_16BIT && X86_64 config TOSHIBA tristate "Toshiba Laptop support" @@ -1871,6 +1892,10 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK def_bool y depends on X86_64 || X86_PAE +config ARCH_ENABLE_HUGEPAGE_MIGRATION + def_bool y + depends on X86_64 && HUGETLB_PAGE && MIGRATION + menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER @@ -2375,12 +2400,9 @@ config X86_DMA_REMAP depends on STA2X11 config IOSF_MBI - bool + tristate + default m depends on PCI - ---help--- - To be selected by modules requiring access to the Intel OnChip System - Fabric (IOSF) Sideband MailBox Interface (MBI). For MBI platforms - enumerable by PCI. source "net/Kconfig" diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 4703a6c..0331d76 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -1087,8 +1087,7 @@ struct boot_params *make_boot_params(struct efi_config *c) hdr->type_of_loader = 0x21; /* Convert unicode cmdline to ascii */ - cmdline_ptr = efi_convert_cmdline_to_ascii(sys_table, image, - &options_size); + cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size); if (!cmdline_ptr) goto fail; hdr->cmd_line_ptr = (unsigned long)cmdline_ptr; diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 0d558ee..2884e0c 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -452,7 +452,7 @@ efi32_config: .global efi64_config efi64_config: .fill 11,8,0 - .quad efi_call6 + .quad efi_call .byte 1 #endif /* CONFIG_EFI_STUB */ diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c index f3c57e3..00e788b 100644 --- a/arch/x86/boot/compressed/string.c +++ b/arch/x86/boot/compressed/string.c @@ -1,9 +1,5 @@ -#include "misc.h" #include "../string.c" -/* misc.h might pull in string_32.h which has a macro for memcpy. undef that */ -#undef memcpy - #ifdef CONFIG_X86_32 void *memcpy(void *dest, const void *src, size_t n) { diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 0ca9a5c..84c2234 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -375,8 +375,7 @@ xloadflags: # define XLF0 0 #endif -#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64) && \ - !defined(CONFIG_EFI_MIXED) +#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64) /* kernel/boot_param/ramdisk could be loaded above 4g */ # define XLF1 XLF_CAN_BE_LOADED_ABOVE_4G #else diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 5339040..493f3fd 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -12,14 +12,9 @@ * Very basic string functions */ -#include "boot.h" +#include <linux/types.h> +#include "ctype.h" -/* - * This file gets included in compressed/string.c which might pull in - * string_32.h and which in turn maps memcmp to __builtin_memcmp(). Undo - * that first. - */ -#undef memcmp int memcmp(const void *s1, const void *s2, size_t len) { u8 diff; diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 619e7f7..32d2e70 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -244,7 +244,6 @@ CONFIG_HID_TOPSEED=y CONFIG_HID_PID=y CONFIG_USB_HIDDEV=y CONFIG_USB=y -CONFIG_USB_DEBUG=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 6181c69..a481dd4 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -239,7 +239,6 @@ CONFIG_HID_TOPSEED=y CONFIG_HID_PID=y CONFIG_USB_HIDDEV=y CONFIG_USB=y -CONFIG_USB_DEBUG=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S index 185fad4..5d1e007 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_asm.S +++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S @@ -92,7 +92,7 @@ __clmul_gf128mul_ble: ret ENDPROC(__clmul_gf128mul_ble) -/* void clmul_ghash_mul(char *dst, const be128 *shash) */ +/* void clmul_ghash_mul(char *dst, const u128 *shash) */ ENTRY(clmul_ghash_mul) movups (%rdi), DATA movups (%rsi), SHASH @@ -106,7 +106,7 @@ ENDPROC(clmul_ghash_mul) /* * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, - * const be128 *shash); + * const u128 *shash); */ ENTRY(clmul_ghash_update) cmp $16, %rdx diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c index d785cf2..88bb7ba 100644 --- a/arch/x86/crypto/ghash-clmulni-intel_glue.c +++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c @@ -25,17 +25,17 @@ #define GHASH_BLOCK_SIZE 16 #define GHASH_DIGEST_SIZE 16 -void clmul_ghash_mul(char *dst, const be128 *shash); +void clmul_ghash_mul(char *dst, const u128 *shash); void clmul_ghash_update(char *dst, const char *src, unsigned int srclen, - const be128 *shash); + const u128 *shash); struct ghash_async_ctx { struct cryptd_ahash *cryptd_tfm; }; struct ghash_ctx { - be128 shash; + u128 shash; }; struct ghash_desc_ctx { @@ -68,11 +68,11 @@ static int ghash_setkey(struct crypto_shash *tfm, a = be64_to_cpu(x->a); b = be64_to_cpu(x->b); - ctx->shash.a = (__be64)((b << 1) | (a >> 63)); - ctx->shash.b = (__be64)((a << 1) | (b >> 63)); + ctx->shash.a = (b << 1) | (a >> 63); + ctx->shash.b = (a << 1) | (b >> 63); if (a >> 63) - ctx->shash.b ^= cpu_to_be64(0xc2); + ctx->shash.b ^= ((u64)0xc2) << 56; return 0; } diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c index 2206757..f9e181a 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/ia32/ia32_signal.c @@ -383,8 +383,8 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, } else { /* Return stub is in 32bit vsyscall page */ if (current->mm->context.vdso) - restorer = VDSO32_SYMBOL(current->mm->context.vdso, - sigreturn); + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_sigreturn; else restorer = &frame->retcode; } @@ -462,8 +462,8 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; else - restorer = VDSO32_SYMBOL(current->mm->context.vdso, - rt_sigreturn); + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_rt_sigreturn; put_user_ex(ptr_to_compat(restorer), &frame->pretcode); /* diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h new file mode 100644 index 0000000..6687329 --- /dev/null +++ b/arch/x86/include/asm/acenv.h @@ -0,0 +1,49 @@ +/* + * X86 specific ACPICA environments and implementation + * + * Copyright (C) 2014, Intel Corporation + * Author: Lv Zheng <lv.zheng@intel.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ASM_X86_ACENV_H +#define _ASM_X86_ACENV_H + +#include <asm/special_insns.h> + +/* Asm macros */ + +#define ACPI_FLUSH_CPU_CACHE() wbinvd() + +#ifdef CONFIG_ACPI + +int __acpi_acquire_global_lock(unsigned int *lock); +int __acpi_release_global_lock(unsigned int *lock); + +#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \ + ((Acq) = __acpi_acquire_global_lock(&facs->global_lock)) + +#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \ + ((Acq) = __acpi_release_global_lock(&facs->global_lock)) + +/* + * Math helper asm macros + */ +#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \ + asm("divl %2;" \ + : "=a"(q32), "=d"(r32) \ + : "r"(d32), \ + "0"(n_lo), "1"(n_hi)) + +#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \ + asm("shrl $1,%2 ;" \ + "rcrl $1,%3;" \ + : "=r"(n_hi), "=r"(n_lo) \ + : "0"(n_hi), "1"(n_lo)) + +#endif + +#endif /* _ASM_X86_ACENV_H */ diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index c8c1e70..e06225e 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -32,51 +32,6 @@ #include <asm/mpspec.h> #include <asm/realmode.h> -#define COMPILER_DEPENDENT_INT64 long long -#define COMPILER_DEPENDENT_UINT64 unsigned long long - -/* - * Calling conventions: - * - * ACPI_SYSTEM_XFACE - Interfaces to host OS (handlers, threads) - * ACPI_EXTERNAL_XFACE - External ACPI interfaces - * ACPI_INTERNAL_XFACE - Internal ACPI interfaces - * ACPI_INTERNAL_VAR_XFACE - Internal variable-parameter list interfaces - */ -#define ACPI_SYSTEM_XFACE -#define ACPI_EXTERNAL_XFACE -#define ACPI_INTERNAL_XFACE -#define ACPI_INTERNAL_VAR_XFACE - -/* Asm macros */ - -#define ACPI_FLUSH_CPU_CACHE() wbinvd() - -int __acpi_acquire_global_lock(unsigned int *lock); -int __acpi_release_global_lock(unsigned int *lock); - -#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \ - ((Acq) = __acpi_acquire_global_lock(&facs->global_lock)) - -#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \ - ((Acq) = __acpi_release_global_lock(&facs->global_lock)) - -/* - * Math helper asm macros - */ -#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \ - asm("divl %2;" \ - : "=a"(q32), "=d"(r32) \ - : "r"(d32), \ - "0"(n_lo), "1"(n_hi)) - - -#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \ - asm("shrl $1,%2 ;" \ - "rcrl $1,%3;" \ - : "=r"(n_hi), "=r"(n_lo) \ - : "0"(n_hi), "1"(n_lo)) - #ifdef CONFIG_ACPI extern int acpi_lapic; extern int acpi_ioapic; diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index 4582e8e..7730c1c 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -57,6 +57,12 @@ .long (from) - . ; \ .long (to) - . + 0x7ffffff0 ; \ .popsection + +# define _ASM_NOKPROBE(entry) \ + .pushsection "_kprobe_blacklist","aw" ; \ + _ASM_ALIGN ; \ + _ASM_PTR (entry); \ + .popsection #else # define _ASM_EXTABLE(from,to) \ " .pushsection \"__ex_table\",\"a\"\n" \ @@ -71,6 +77,7 @@ " .long (" #from ") - .\n" \ " .long (" #to ") - . + 0x7ffffff0\n" \ " .popsection\n" +/* For C file, we already have NOKPROBE_SYMBOL macro */ #endif #endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index b17f4f4..6dd1c7d 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -7,6 +7,7 @@ #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> +#include <asm/barrier.h> /* * Atomic operations that C can't guarantee us. Useful for @@ -243,12 +244,6 @@ static inline void atomic_or_long(unsigned long *v1, unsigned long v2) : : "r" ((unsigned)(mask)), "m" (*(addr)) \ : "memory") -/* Atomic operations are already serializing on x86 */ -#define smp_mb__before_atomic_dec() barrier() -#define smp_mb__after_atomic_dec() barrier() -#define smp_mb__before_atomic_inc() barrier() -#define smp_mb__after_atomic_inc() barrier() - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 69bbb48..5c7198c 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -137,6 +137,10 @@ do { \ #endif +/* Atomic operations are already serializing on x86 */ +#define smp_mb__before_atomic() barrier() +#define smp_mb__after_atomic() barrier() + /* * Stop RDTSC speculation. This is needed when you need to use RDTSC * (or get_cycles or vread that possibly accesses the TSC) in a defined diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 9fc1af7..afcd35d 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -15,6 +15,7 @@ #include <linux/compiler.h> #include <asm/alternative.h> #include <asm/rmwcc.h> +#include <asm/barrier.h> #if BITS_PER_LONG == 32 # define _BITOPS_LONG_SHIFT 5 @@ -102,7 +103,7 @@ static inline void __set_bit(long nr, volatile unsigned long *addr) * * clear_bit() is atomic and may not be reordered. However, it does * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit() + * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() * in order to ensure changes are visible on other processors. */ static __always_inline void @@ -156,9 +157,6 @@ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) __clear_bit(nr, addr); } -#define smp_mb__before_clear_bit() barrier() -#define smp_mb__after_clear_bit() barrier() - /** * __change_bit - Toggle a bit in memory * @nr: the bit to change diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h index e6fd8a0..cd00e17 100644 --- a/arch/x86/include/asm/checksum_64.h +++ b/arch/x86/include/asm/checksum_64.h @@ -184,8 +184,15 @@ static inline unsigned add32_with_carry(unsigned a, unsigned b) asm("addl %2,%0\n\t" "adcl $0,%0" : "=r" (a) - : "0" (a), "r" (b)); + : "0" (a), "rm" (b)); return a; } +#define HAVE_ARCH_CSUM_ADD +static inline __wsum csum_add(__wsum csum, __wsum addend) +{ + return (__force __wsum)add32_with_carry((__force unsigned)csum, + (__force unsigned)addend); +} + #endif /* _ASM_X86_CHECKSUM_64_H */ diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h new file mode 100644 index 0000000..e01f7f7 --- /dev/null +++ b/arch/x86/include/asm/cmdline.h @@ -0,0 +1,6 @@ +#ifndef _ASM_X86_CMDLINE_H +#define _ASM_X86_CMDLINE_H + +int cmdline_find_option_bool(const char *cmdline_ptr, const char *option); + +#endif /* _ASM_X86_CMDLINE_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 0869434..1eb5f64 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -1,6 +1,7 @@ #ifndef _ASM_X86_EFI_H #define _ASM_X86_EFI_H +#include <asm/i387.h> /* * We map the EFI regions needed for runtime services non-contiguously, * with preserved alignment on virtual addresses starting from -4G down @@ -27,91 +28,58 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...); -#define efi_call_phys0(f) efi_call_phys(f) -#define efi_call_phys1(f, a1) efi_call_phys(f, a1) -#define efi_call_phys2(f, a1, a2) efi_call_phys(f, a1, a2) -#define efi_call_phys3(f, a1, a2, a3) efi_call_phys(f, a1, a2, a3) -#define efi_call_phys4(f, a1, a2, a3, a4) \ - efi_call_phys(f, a1, a2, a3, a4) -#define efi_call_phys5(f, a1, a2, a3, a4, a5) \ - efi_call_phys(f, a1, a2, a3, a4, a5) -#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6) \ - efi_call_phys(f, a1, a2, a3, a4, a5, a6) /* * Wrap all the virtual calls in a way that forces the parameters on the stack. */ +/* Use this macro if your virtual returns a non-void value */ #define efi_call_virt(f, args...) \ - ((efi_##f##_t __attribute__((regparm(0)))*)efi.systab->runtime->f)(args) - -#define efi_call_virt0(f) efi_call_virt(f) -#define efi_call_virt1(f, a1) efi_call_virt(f, a1) -#define efi_call_virt2(f, a1, a2) efi_call_virt(f, a1, a2) -#define efi_call_virt3(f, a1, a2, a3) efi_call_virt(f, a1, a2, a3) -#define efi_call_virt4(f, a1, a2, a3, a4) \ - efi_call_virt(f, a1, a2, a3, a4) -#define efi_call_virt5(f, a1, a2, a3, a4, a5) \ - efi_call_virt(f, a1, a2, a3, a4, a5) -#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ - efi_call_virt(f, a1, a2, a3, a4, a5, a6) +({ \ + efi_status_t __s; \ + kernel_fpu_begin(); \ + __s = ((efi_##f##_t __attribute__((regparm(0)))*) \ + efi.systab->runtime->f)(args); \ + kernel_fpu_end(); \ + __s; \ +}) + +/* Use this macro if your virtual call does not return any value */ +#define __efi_call_virt(f, args...) \ +({ \ + kernel_fpu_begin(); \ + ((efi_##f##_t __attribute__((regparm(0)))*) \ + efi.systab->runtime->f)(args); \ + kernel_fpu_end(); \ +}) #define efi_ioremap(addr, size, type, attr) ioremap_cache(addr, size) #else /* !CONFIG_X86_32 */ -extern u64 efi_call0(void *fp); -extern u64 efi_call1(void *fp, u64 arg1); -extern u64 efi_call2(void *fp, u64 arg1, u64 arg2); -extern u64 efi_call3(void *fp, u64 arg1, u64 arg2, u64 arg3); -extern u64 efi_call4(void *fp, u64 arg1, u64 arg2, u64 arg3, u64 arg4); -extern u64 efi_call5(void *fp, u64 arg1, u64 arg2, u64 arg3, - u64 arg4, u64 arg5); -extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3, - u64 arg4, u64 arg5, u64 arg6); - -#define efi_call_phys0(f) \ - efi_call0((f)) -#define efi_call_phys1(f, a1) \ - efi_call1((f), (u64)(a1)) -#define efi_call_phys2(f, a1, a2) \ - efi_call2((f), (u64)(a1), (u64)(a2)) -#define efi_call_phys3(f, a1, a2, a3) \ - efi_call3((f), (u64)(a1), (u64)(a2), (u64)(a3)) -#define efi_call_phys4(f, a1, a2, a3, a4) \ - efi_call4((f), (u64)(a1), (u64)(a2), (u64)(a3), \ - (u64)(a4)) -#define efi_call_phys5(f, a1, a2, a3, a4, a5) \ - efi_call5((f), (u64)(a1), (u64)(a2), (u64)(a3), \ - (u64)(a4), (u64)(a5)) -#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6) \ - efi_call6((f), (u64)(a1), (u64)(a2), (u64)(a3), \ - (u64)(a4), (u64)(a5), (u64)(a6)) - -#define _efi_call_virtX(x, f, ...) \ +#define EFI_LOADER_SIGNATURE "EL64" + +extern u64 asmlinkage efi_call(void *fp, ...); + +#define efi_call_phys(f, args...) efi_call((f), args) + +#define efi_call_virt(f, ...) \ ({ \ efi_status_t __s; \ \ efi_sync_low_kernel_mappings(); \ preempt_disable(); \ - __s = efi_call##x((void *)efi.systab->runtime->f, __VA_ARGS__); \ + __kernel_fpu_begin(); \ + __s = efi_call((void *)efi.systab->runtime->f, __VA_ARGS__); \ + __kernel_fpu_end(); \ preempt_enable(); \ __s; \ }) -#define efi_call_virt0(f) \ - _efi_call_virtX(0, f) -#define efi_call_virt1(f, a1) \ - _efi_call_virtX(1, f, (u64)(a1)) -#define efi_call_virt2(f, a1, a2) \ - _efi_call_virtX(2, f, (u64)(a1), (u64)(a2)) -#define efi_call_virt3(f, a1, a2, a3) \ - _efi_call_virtX(3, f, (u64)(a1), (u64)(a2), (u64)(a3)) -#define efi_call_virt4(f, a1, a2, a3, a4) \ - _efi_call_virtX(4, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4)) -#define efi_call_virt5(f, a1, a2, a3, a4, a5) \ - _efi_call_virtX(5, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5)) -#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6) \ - _efi_call_virtX(6, f, (u64)(a1), (u64)(a2), (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) +/* + * All X86_64 virt calls return non-void values. Thus, use non-void call for + * virt calls that would be void on X86_32. + */ +#define __efi_call_virt(f, args...) efi_call_virt(f, args) extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, u32 type, u64 attribute); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 2c71182..1a055c8 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -75,7 +75,12 @@ typedef struct user_fxsr_struct elf_fpxregset_t; #include <asm/vdso.h> -extern unsigned int vdso_enabled; +#ifdef CONFIG_X86_64 +extern unsigned int vdso64_enabled; +#endif +#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +extern unsigned int vdso32_enabled; +#endif /* * This is used to ensure we don't load something for the wrong architecture. @@ -269,9 +274,9 @@ extern int force_personality32; struct task_struct; -#define ARCH_DLINFO_IA32(vdso_enabled) \ +#define ARCH_DLINFO_IA32 \ do { \ - if (vdso_enabled) { \ + if (vdso32_enabled) { \ NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ } \ @@ -281,7 +286,7 @@ do { \ #define STACK_RND_MASK (0x7ff) -#define ARCH_DLINFO ARCH_DLINFO_IA32(vdso_enabled) +#define ARCH_DLINFO ARCH_DLINFO_IA32 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ @@ -292,16 +297,17 @@ do { \ #define ARCH_DLINFO \ do { \ - if (vdso_enabled) \ + if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ - (unsigned long)current->mm->context.vdso); \ + (unsigned long __force)current->mm->context.vdso); \ } while (0) +/* As a historical oddity, the x32 and x86_64 vDSOs are controlled together. */ #define ARCH_DLINFO_X32 \ do { \ - if (vdso_enabled) \ + if (vdso64_enabled) \ NEW_AUX_ENT(AT_SYSINFO_EHDR, \ - (unsigned long)current->mm->context.vdso); \ + (unsigned long __force)current->mm->context.vdso); \ } while (0) #define AT_SYSINFO 32 @@ -310,7 +316,7 @@ do { \ if (test_thread_flag(TIF_X32)) \ ARCH_DLINFO_X32; \ else \ - ARCH_DLINFO_IA32(sysctl_vsyscall32) + ARCH_DLINFO_IA32 #define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) @@ -319,18 +325,17 @@ else \ #define VDSO_CURRENT_BASE ((unsigned long)current->mm->context.vdso) #define VDSO_ENTRY \ - ((unsigned long)VDSO32_SYMBOL(VDSO_CURRENT_BASE, vsyscall)) + ((unsigned long)current->mm->context.vdso + \ + selected_vdso32->sym___kernel_vsyscall) struct linux_binprm; #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 extern int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp); -extern int x32_setup_additional_pages(struct linux_binprm *bprm, - int uses_interp); - -extern int syscall32_setup_pages(struct linux_binprm *, int exstack); -#define compat_arch_setup_additional_pages syscall32_setup_pages +extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); +#define compat_arch_setup_additional_pages compat_arch_setup_additional_pages extern unsigned long arch_randomize_brk(struct mm_struct *mm); #define arch_randomize_brk arch_randomize_brk diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h new file mode 100644 index 0000000..99efebb --- /dev/null +++ b/arch/x86/include/asm/espfix.h @@ -0,0 +1,16 @@ +#ifndef _ASM_X86_ESPFIX_H +#define _ASM_X86_ESPFIX_H + +#ifdef CONFIG_X86_64 + +#include <asm/percpu.h> + +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +extern void init_espfix_bsp(void); +extern void init_espfix_ap(void); + +#endif /* CONFIG_X86_64 */ + +#endif /* _ASM_X86_ESPFIX_H */ diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 43f482a..b0910f9 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -24,7 +24,7 @@ #include <linux/threads.h> #include <asm/kmap_types.h> #else -#include <asm/vsyscall.h> +#include <uapi/asm/vsyscall.h> #endif /* @@ -41,7 +41,8 @@ extern unsigned long __FIXADDR_TOP; #define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) #else -#define FIXADDR_TOP (VSYSCALL_END-PAGE_SIZE) +#define FIXADDR_TOP (round_up(VSYSCALL_ADDR + PAGE_SIZE, 1<<PMD_SHIFT) - \ + PAGE_SIZE) #endif @@ -68,11 +69,7 @@ enum fixed_addresses { #ifdef CONFIG_X86_32 FIX_HOLE, #else - VSYSCALL_LAST_PAGE, - VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE - + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1, - VVAR_PAGE, - VSYSCALL_HPET, + VSYSCALL_PAGE = (FIXADDR_TOP - VSYSCALL_ADDR) >> PAGE_SHIFT, #ifdef CONFIG_PARAVIRT_CLOCK PVCLOCK_FIXMAP_BEGIN, PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1, diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h index cea1c76..115e368 100644 --- a/arch/x86/include/asm/fpu-internal.h +++ b/arch/x86/include/asm/fpu-internal.h @@ -87,22 +87,22 @@ static inline int is_x32_frame(void) static __always_inline __pure bool use_eager_fpu(void) { - return static_cpu_has(X86_FEATURE_EAGER_FPU); + return static_cpu_has_safe(X86_FEATURE_EAGER_FPU); } static __always_inline __pure bool use_xsaveopt(void) { - return static_cpu_has(X86_FEATURE_XSAVEOPT); + return static_cpu_has_safe(X86_FEATURE_XSAVEOPT); } static __always_inline __pure bool use_xsave(void) { - return static_cpu_has(X86_FEATURE_XSAVE); + return static_cpu_has_safe(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { - return static_cpu_has(X86_FEATURE_FXSR); + return static_cpu_has_safe(X86_FEATURE_FXSR); } static inline void fx_finit(struct i387_fxsave_struct *fx) @@ -293,7 +293,7 @@ static inline int restore_fpu_checking(struct task_struct *tsk) /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception is pending. Clear the x87 state here by setting it to fixed values. "m" is a random variable that should be in L1 */ - if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) { + if (unlikely(static_cpu_has_safe(X86_FEATURE_FXSAVE_LEAK))) { asm volatile( "fnclex\n\t" "emms\n\t" diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index a307b75..4615906 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -190,8 +190,8 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void); #define trace_interrupt interrupt #endif -#define VECTOR_UNDEFINED -1 -#define VECTOR_RETRIGGERED -2 +#define VECTOR_UNDEFINED (-1) +#define VECTOR_RETRIGGERED (-2) typedef int vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 459e50a..90f97b4 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -168,8 +168,6 @@ extern int save_ioapic_entries(void); extern void mask_ioapic_entries(void); extern int restore_ioapic_entries(void); -extern int get_nr_irqs_gsi(void); - extern void setup_ioapic_ids_from_mpc(void); extern void setup_ioapic_ids_from_mpc_nocheck(void); diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 8e71c79..57995f0 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -50,6 +50,32 @@ #define BT_MBI_PCIE_READ 0x00 #define BT_MBI_PCIE_WRITE 0x01 +/* Quark available units */ +#define QRK_MBI_UNIT_HBA 0x00 +#define QRK_MBI_UNIT_HB 0x03 +#define QRK_MBI_UNIT_RMU 0x04 +#define QRK_MBI_UNIT_MM 0x05 +#define QRK_MBI_UNIT_MMESRAM 0x05 +#define QRK_MBI_UNIT_SOC 0x31 + +/* Quark read/write opcodes */ +#define QRK_MBI_HBA_READ 0x10 +#define QRK_MBI_HBA_WRITE 0x11 +#define QRK_MBI_HB_READ 0x10 +#define QRK_MBI_HB_WRITE 0x11 +#define QRK_MBI_RMU_READ 0x10 +#define QRK_MBI_RMU_WRITE 0x11 +#define QRK_MBI_MM_READ 0x10 +#define QRK_MBI_MM_WRITE 0x11 +#define QRK_MBI_MMESRAM_READ 0x12 +#define QRK_MBI_MMESRAM_WRITE 0x13 +#define QRK_MBI_SOC_READ 0x06 +#define QRK_MBI_SOC_WRITE 0x07 + +#if IS_ENABLED(CONFIG_IOSF_MBI) + +bool iosf_mbi_available(void); + /** * iosf_mbi_read() - MailBox Interface read command * @port: port indicating subunit being accessed @@ -87,4 +113,33 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr); */ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); +#else /* CONFIG_IOSF_MBI is not enabled */ +static inline +bool iosf_mbi_available(void) +{ + return false; +} + +static inline +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} +#endif /* CONFIG_IOSF_MBI */ + #endif /* IOSF_MBI_SYMS_H */ diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index d806b22..b7747c4 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -103,4 +103,7 @@ static inline bool setup_remapped_irq(int irq, } #endif /* CONFIG_IRQ_REMAP */ +#define dmar_alloc_hwirq() irq_alloc_hwirq(-1) +#define dmar_free_hwirq irq_free_hwirq + #endif /* __X86_IRQ_REMAPPING_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h index 9454c16..53cdfb2 100644 --- a/arch/x86/include/asm/kprobes.h +++ b/arch/x86/include/asm/kprobes.h @@ -116,4 +116,6 @@ struct kprobe_ctlblk { extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); extern int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data); +extern int kprobe_int3_handler(struct pt_regs *regs); +extern int kprobe_debug_handler(struct pt_regs *regs); #endif /* _ASM_X86_KPROBES_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 24ec121..a04fe4e 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -189,7 +189,6 @@ struct x86_emulate_ops { void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt); ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr); int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val); - void (*set_rflags)(struct x86_emulate_ctxt *ctxt, ulong val); int (*cpl)(struct x86_emulate_ctxt *ctxt); int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7de069af..4931415 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -50,11 +50,7 @@ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) -#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1) -#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD)) -#define CR3_PCID_ENABLED_RESERVED_BITS 0xFFFFFF0000000000ULL -#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \ - 0xFFFFFF0000000000ULL) +#define CR3_L_MODE_RESERVED_BITS 0xFFFFFF0000000000ULL #define CR4_RESERVED_BITS \ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ @@ -134,7 +130,6 @@ enum kvm_reg_ex { VCPU_EXREG_PDPTR = NR_VCPU_REGS, VCPU_EXREG_CR3, VCPU_EXREG_RFLAGS, - VCPU_EXREG_CPL, VCPU_EXREG_SEGMENTS, }; diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 6e4ce2d..958b90f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -176,8 +176,6 @@ int mce_available(struct cpuinfo_x86 *c); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); -extern atomic_t mce_entry; - typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS); DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index b59827e..64dc362 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -25,6 +25,7 @@ struct cpu_signature { struct device; enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; +extern bool dis_ucode_ldr; struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 5f55e69..876e74e 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -18,7 +18,7 @@ typedef struct { #endif struct mutex lock; - void *vdso; + void __user *vdso; } mm_context_t; #ifdef CONFIG_SMP diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8de6d9c..6782051 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_PAGE_64_DEFS_H #define _ASM_X86_PAGE_64_DEFS_H -#define THREAD_SIZE_ORDER 1 +#define THREAD_SIZE_ORDER 2 #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #define CURRENT_MASK (~(THREAD_SIZE - 1)) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 96ae4f4..0892ea0 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -68,7 +68,6 @@ void pcibios_config_init(void); void pcibios_scan_root(int bus); void pcibios_set_master(struct pci_dev *dev); -void pcibios_penalize_isa_irq(int irq, int active); struct irq_routing_table *pcibios_get_irq_routing_table(void); int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 0d193e2..206a87f 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -62,66 +62,14 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi return ((value >> rightshift) & mask) << leftshift; } -#ifdef CONFIG_MEM_SOFT_DIRTY - -/* - * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE, _PAGE_BIT_SOFT_DIRTY and - * _PAGE_BIT_PROTNONE are taken, split up the 28 bits of offset - * into this range. - */ -#define PTE_FILE_MAX_BITS 28 -#define PTE_FILE_SHIFT1 (_PAGE_BIT_PRESENT + 1) -#define PTE_FILE_SHIFT2 (_PAGE_BIT_FILE + 1) -#define PTE_FILE_SHIFT3 (_PAGE_BIT_PROTNONE + 1) -#define PTE_FILE_SHIFT4 (_PAGE_BIT_SOFT_DIRTY + 1) -#define PTE_FILE_BITS1 (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1) -#define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1) -#define PTE_FILE_BITS3 (PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1) - -#define PTE_FILE_MASK1 ((1U << PTE_FILE_BITS1) - 1) -#define PTE_FILE_MASK2 ((1U << PTE_FILE_BITS2) - 1) -#define PTE_FILE_MASK3 ((1U << PTE_FILE_BITS3) - 1) - -#define PTE_FILE_LSHIFT2 (PTE_FILE_BITS1) -#define PTE_FILE_LSHIFT3 (PTE_FILE_BITS1 + PTE_FILE_BITS2) -#define PTE_FILE_LSHIFT4 (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3) - -static __always_inline pgoff_t pte_to_pgoff(pte_t pte) -{ - return (pgoff_t) - (pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1, 0) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2, PTE_FILE_LSHIFT2) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT3, PTE_FILE_MASK3, PTE_FILE_LSHIFT3) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT4, -1UL, PTE_FILE_LSHIFT4)); -} - -static __always_inline pte_t pgoff_to_pte(pgoff_t off) -{ - return (pte_t){ - .pte_low = - pte_bitop(off, 0, PTE_FILE_MASK1, PTE_FILE_SHIFT1) + - pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2, PTE_FILE_SHIFT2) + - pte_bitop(off, PTE_FILE_LSHIFT3, PTE_FILE_MASK3, PTE_FILE_SHIFT3) + - pte_bitop(off, PTE_FILE_LSHIFT4, -1UL, PTE_FILE_SHIFT4) + - _PAGE_FILE, - }; -} - -#else /* CONFIG_MEM_SOFT_DIRTY */ - /* * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken, * split up the 29 bits of offset into this range. */ #define PTE_FILE_MAX_BITS 29 #define PTE_FILE_SHIFT1 (_PAGE_BIT_PRESENT + 1) -#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define PTE_FILE_SHIFT2 (_PAGE_BIT_FILE + 1) #define PTE_FILE_SHIFT3 (_PAGE_BIT_PROTNONE + 1) -#else -#define PTE_FILE_SHIFT2 (_PAGE_BIT_PROTNONE + 1) -#define PTE_FILE_SHIFT3 (_PAGE_BIT_FILE + 1) -#endif #define PTE_FILE_BITS1 (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1) #define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1) @@ -150,16 +98,9 @@ static __always_inline pte_t pgoff_to_pte(pgoff_t off) }; } -#endif /* CONFIG_MEM_SOFT_DIRTY */ - /* Encode and de-code a swap entry */ -#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) -#else -#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1) -#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1) -#endif #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index b459ddf..0ec0560 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -131,7 +131,8 @@ static inline int pte_exec(pte_t pte) static inline int pte_special(pte_t pte) { - return pte_flags(pte) & _PAGE_SPECIAL; + return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) == + (_PAGE_PRESENT|_PAGE_SPECIAL); } static inline unsigned long pte_pfn(pte_t pte) @@ -296,6 +297,7 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SOFT_DIRTY; @@ -331,6 +333,8 @@ static inline int pte_file_soft_dirty(pte_t pte) return pte_flags(pte) & _PAGE_SOFT_DIRTY; } +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. @@ -452,6 +456,12 @@ static inline int pte_present(pte_t a) _PAGE_NUMA); } +#define pte_present_nonuma pte_present_nonuma +static inline int pte_present_nonuma(pte_t a) +{ + return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); +} + #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { @@ -858,23 +868,25 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, { } +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } +#endif #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e22c1db..5be9063 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -143,12 +143,12 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define pte_unmap(pte) ((void)(pte))/* NOP */ /* Encode and de-code a swap entry */ -#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) -#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) +#ifdef CONFIG_NUMA_BALANCING +/* Automatic NUMA balancing needs to be distinguishable from swap entries */ +#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 2) #else -#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1) -#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1) +#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) #endif #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index c883bf7..7166e25 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t; #define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) #define MODULES_END _AC(0xffffffffff000000, UL) #define MODULES_LEN (MODULES_END - MODULES_VADDR) +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) #define EARLY_DYNAMIC_PAGE_TABLES 64 diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index eb3d449..f216963 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -16,15 +16,26 @@ #define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */ #define _PAGE_BIT_PAT 7 /* on 4KB pages */ #define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ -#define _PAGE_BIT_UNUSED1 9 /* available for programmer */ -#define _PAGE_BIT_IOMAP 10 /* flag used to indicate IO mapping */ -#define _PAGE_BIT_HIDDEN 11 /* hidden by kmemcheck */ +#define _PAGE_BIT_SOFTW1 9 /* available for programmer */ +#define _PAGE_BIT_SOFTW2 10 /* " */ +#define _PAGE_BIT_SOFTW3 11 /* " */ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ -#define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1 -#define _PAGE_BIT_CPA_TEST _PAGE_BIT_UNUSED1 -#define _PAGE_BIT_SPLITTING _PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */ +#define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ +#define _PAGE_BIT_IOMAP _PAGE_BIT_SOFTW2 /* flag used to indicate IO mapping */ +#define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ +#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ #define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ +/* + * Swap offsets on configurations that allow automatic NUMA balancing use the + * bits after _PAGE_BIT_GLOBAL. To uniquely distinguish NUMA hinting PTEs from + * swap entries, we use the first bit after _PAGE_BIT_GLOBAL and shrink the + * maximum possible swap space from 16TB to 8TB. + */ +#define _PAGE_BIT_NUMA (_PAGE_BIT_GLOBAL+1) + /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ #define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL @@ -40,7 +51,7 @@ #define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY) #define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE) #define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) -#define _PAGE_UNUSED1 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1) +#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) #define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP) #define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) @@ -61,8 +72,6 @@ * they do not conflict with each other. */ -#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_HIDDEN - #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY) #else @@ -70,6 +79,21 @@ #endif /* + * _PAGE_NUMA distinguishes between a numa hinting minor fault and a page + * that is not present. The hinting fault gathers numa placement statistics + * (see pte_numa()). The bit is always zero when the PTE is not present. + * + * The bit picked must be always zero when the pmd is present and not + * present, so that we don't lose information when we set it while + * atomically clearing the present bit. + */ +#ifdef CONFIG_NUMA_BALANCING +#define _PAGE_NUMA (_AT(pteval_t, 1) << _PAGE_BIT_NUMA) +#else +#define _PAGE_NUMA (_AT(pteval_t, 0)) +#endif + +/* * Tracking soft dirty bit when a page goes to a swap is tricky. * We need a bit which can be stored in pte _and_ not conflict * with swap entry format. On x86 bits 6 and 7 are *not* involved @@ -94,26 +118,6 @@ #define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE) #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -/* - * _PAGE_NUMA indicates that this page will trigger a numa hinting - * minor page fault to gather numa placement statistics (see - * pte_numa()). The bit picked (8) is within the range between - * _PAGE_FILE (6) and _PAGE_PROTNONE (8) bits. Therefore, it doesn't - * require changes to the swp entry format because that bit is always - * zero when the pte is not present. - * - * The bit picked must be always zero when the pmd is present and not - * present, so that we don't lose information when we set it while - * atomically clearing the present bit. - * - * Because we shared the same bit (8) with _PAGE_PROTNONE this can be - * interpreted as _PAGE_NUMA only in places that _PAGE_PROTNONE - * couldn't reach, like handle_mm_fault() (see access_error in - * arch/x86/mm/fault.c, the vma protection must not be PROT_NONE for - * handle_mm_fault() to be invoked). - */ -#define _PAGE_NUMA _PAGE_PROTNONE - #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ _PAGE_ACCESSED | _PAGE_DIRTY) #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ @@ -122,8 +126,8 @@ /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY) -#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) + _PAGE_SOFT_DIRTY | _PAGE_NUMA) +#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA) #define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT) #define _PAGE_CACHE_WB (0) diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 6fd3fd7..a90f897 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -12,8 +12,6 @@ void ia32_syscall(void); void ia32_cstar_target(void); void ia32_sysenter_target(void); -void syscall32_cpu_init(void); - void x86_configure_nx(void); void x86_report_nx(void); diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h new file mode 100644 index 0000000..70f46f0 --- /dev/null +++ b/arch/x86/include/asm/qrwlock.h @@ -0,0 +1,17 @@ +#ifndef _ASM_X86_QRWLOCK_H +#define _ASM_X86_QRWLOCK_H + +#include <asm-generic/qrwlock_types.h> + +#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE) +#define queue_write_unlock queue_write_unlock +static inline void queue_write_unlock(struct qrwlock *lock) +{ + barrier(); + ACCESS_ONCE(*(u8 *)&lock->cnts) = 0; +} +#endif + +#include <asm-generic/qrwlock.h> + +#endif /* _ASM_X86_QRWLOCK_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 9264f04..ff4e7b2 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -59,6 +59,8 @@ static inline void x86_ce4100_early_setup(void) { } #ifndef _SETUP +#include <asm/espfix.h> + /* * This is set up by the setup-routine at boot-time */ diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 35e67a4..31eab86 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -92,12 +92,6 @@ static inline int __gen_sigismember(sigset_t *set, int _sig) ? __const_sigismember((set), (sig)) \ : __gen_sigismember((set), (sig))) -static inline int sigfindinword(unsigned long word) -{ - asm("bsfl %1,%0" : "=r"(word) : "rm"(word) : "cc"); - return word; -} - struct pt_regs; #else /* __i386__ */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 0f62f54..54f1c80 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -187,6 +187,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock) cpu_relax(); } +#ifndef CONFIG_QUEUE_RWLOCK /* * Read-write spinlocks, allowing multiple readers * but only one writer. @@ -269,6 +270,9 @@ static inline void arch_write_unlock(arch_rwlock_t *rw) asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0" : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory"); } +#else +#include <asm/qrwlock.h> +#endif /* CONFIG_QUEUE_RWLOCK */ #define arch_read_lock_flags(lock, flags) arch_read_lock(lock) #define arch_write_lock_flags(lock, flags) arch_write_lock(lock) diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h index 4f1bea1..73c4c00 100644 --- a/arch/x86/include/asm/spinlock_types.h +++ b/arch/x86/include/asm/spinlock_types.h @@ -34,6 +34,10 @@ typedef struct arch_spinlock { #define __ARCH_SPIN_LOCK_UNLOCKED { { 0 } } +#ifdef CONFIG_QUEUE_RWLOCK +#include <asm-generic/qrwlock_types.h> +#else #include <asm/rwlock.h> +#endif #endif /* _ASM_X86_SPINLOCK_TYPES_H */ diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index 977f176..ab05d73 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -29,4 +29,11 @@ static inline void pci_swiotlb_late_init(void) static inline void dma_mark_clean(void *addr, size_t size) {} +extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs); +extern void x86_swiotlb_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + struct dma_attrs *attrs); + #endif /* _ASM_X86_SWIOTLB_H */ diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h index 05af3b3..f28a24b 100644 --- a/arch/x86/include/asm/sync_bitops.h +++ b/arch/x86/include/asm/sync_bitops.h @@ -41,7 +41,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr) * * sync_clear_bit() is atomic and may not be reordered. However, it does * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit() + * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() * in order to ensure changes are visible on other processors. */ static inline void sync_clear_bit(long nr, volatile unsigned long *addr) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 47e5de2..8540538 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -83,6 +83,7 @@ struct thread_info { #define TIF_FORK 18 /* ret_from_fork */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ +#define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ @@ -106,6 +107,7 @@ struct thread_info { #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) #define _TIF_NOHZ (1 << TIF_NOHZ) +#define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) @@ -191,8 +193,6 @@ static inline struct thread_info *current_thread_info(void) * have to worry about atomic accesses. */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ -#define TS_POLLING 0x0004 /* idle task polling need_resched, - skip sending interrupt */ #define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 58d66fe..bc8352e 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -68,12 +68,17 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long); dotraplinkage void do_stack_segment(struct pt_regs *, long); #ifdef CONFIG_X86_64 dotraplinkage void do_double_fault(struct pt_regs *, long); -asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *); +asmlinkage struct pt_regs *sync_regs(struct pt_regs *); #endif dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); #ifdef CONFIG_TRACING dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long); +#else +static inline void trace_do_page_fault(struct pt_regs *regs, unsigned long error) +{ + do_page_fault(regs, error); +} #endif dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long); dotraplinkage void do_coprocessor_error(struct pt_regs *, long); @@ -98,7 +103,6 @@ static inline int get_si_code(unsigned long condition) extern int panic_on_unrecovered_nmi; -void math_error(struct pt_regs *, int, int); void math_emulate(struct math_emu_info *); #ifndef CONFIG_X86_32 asmlinkage void smp_thermal_interrupt(void); diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 3f556c6..2b19caa 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -41,7 +41,6 @@ # define __ARCH_WANT_SYS_OLD_GETRLIMIT # define __ARCH_WANT_SYS_OLD_UNAME # define __ARCH_WANT_SYS_PAUSE -# define __ARCH_WANT_SYS_SGETMASK # define __ARCH_WANT_SYS_SIGNAL # define __ARCH_WANT_SYS_SIGPENDING # define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 3087ea9..74f4c2f 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -33,15 +33,27 @@ typedef u8 uprobe_opcode_t; #define UPROBE_SWBP_INSN 0xcc #define UPROBE_SWBP_INSN_SIZE 1 +struct uprobe_xol_ops; + struct arch_uprobe { - u16 fixups; union { u8 insn[MAX_UINSN_BYTES]; u8 ixol[MAX_UINSN_BYTES]; }; -#ifdef CONFIG_X86_64 - unsigned long rip_rela_target_address; -#endif + + const struct uprobe_xol_ops *ops; + + union { + struct { + s32 offs; + u8 ilen; + u8 opc1; + } branch; + struct { + u8 fixups; + u8 ilen; + } defparam; + }; }; struct arch_uprobe_task { diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index a30836c..c63e925 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -5,7 +5,7 @@ * * SGI UV architectural definitions * - * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_HUB_H @@ -204,16 +204,6 @@ static inline int is_uvx_hub(void) return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE; } -static inline int is_uv2_1_hub(void) -{ - return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE; -} - -static inline int is_uv2_2_hub(void) -{ - return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE + 1; -} - union uvh_apicid { unsigned long v; struct uvh_apicid_s { diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index e42249b..ddd8db6 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -5,7 +5,7 @@ * * SGI UV MMR definitions * - * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_MMRS_H @@ -2803,6 +2803,46 @@ union uv1h_lb_target_physical_apic_id_mask_u { }; /* ========================================================================= */ +/* UV3H_GR0_GAM_GR_CONFIG */ +/* ========================================================================= */ +#define UV3H_GR0_GAM_GR_CONFIG 0xc00028UL + +#define UV3H_GR0_GAM_GR_CONFIG_M_SKT_SHFT 0 +#define UV3H_GR0_GAM_GR_CONFIG_SUBSPACE_SHFT 10 +#define UV3H_GR0_GAM_GR_CONFIG_M_SKT_MASK 0x000000000000003fUL +#define UV3H_GR0_GAM_GR_CONFIG_SUBSPACE_MASK 0x0000000000000400UL + +union uv3h_gr0_gam_gr_config_u { + unsigned long v; + struct uv3h_gr0_gam_gr_config_s { + unsigned long m_skt:6; /* RW */ + unsigned long undef_6_9:4; /* Undefined */ + unsigned long subspace:1; /* RW */ + unsigned long reserved:53; + } s3; +}; + +/* ========================================================================= */ +/* UV3H_GR1_GAM_GR_CONFIG */ +/* ========================================================================= */ +#define UV3H_GR1_GAM_GR_CONFIG 0x1000028UL + +#define UV3H_GR1_GAM_GR_CONFIG_M_SKT_SHFT 0 +#define UV3H_GR1_GAM_GR_CONFIG_SUBSPACE_SHFT 10 +#define UV3H_GR1_GAM_GR_CONFIG_M_SKT_MASK 0x000000000000003fUL +#define UV3H_GR1_GAM_GR_CONFIG_SUBSPACE_MASK 0x0000000000000400UL + +union uv3h_gr1_gam_gr_config_u { + unsigned long v; + struct uv3h_gr1_gam_gr_config_s { + unsigned long m_skt:6; /* RW */ + unsigned long undef_6_9:4; /* Undefined */ + unsigned long subspace:1; /* RW */ + unsigned long reserved:53; + } s3; +}; + +/* ========================================================================= */ /* UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR */ /* ========================================================================= */ #define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x1603000UL diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h index d1dc554..30be253 100644 --- a/arch/x86/include/asm/vdso.h +++ b/arch/x86/include/asm/vdso.h @@ -3,63 +3,51 @@ #include <asm/page_types.h> #include <linux/linkage.h> +#include <linux/init.h> -#ifdef __ASSEMBLER__ +#ifndef __ASSEMBLER__ -#define DEFINE_VDSO_IMAGE(symname, filename) \ -__PAGE_ALIGNED_DATA ; \ - .globl symname##_start, symname##_end ; \ - .align PAGE_SIZE ; \ - symname##_start: ; \ - .incbin filename ; \ - symname##_end: ; \ - .align PAGE_SIZE /* extra data here leaks to userspace. */ ; \ - \ -.previous ; \ - \ - .globl symname##_pages ; \ - .bss ; \ - .align 8 ; \ - .type symname##_pages, @object ; \ - symname##_pages: ; \ - .zero (symname##_end - symname##_start + PAGE_SIZE - 1) / PAGE_SIZE * (BITS_PER_LONG / 8) ; \ - .size symname##_pages, .-symname##_pages +#include <linux/mm_types.h> -#else +struct vdso_image { + void *data; + unsigned long size; /* Always a multiple of PAGE_SIZE */ -#define DECLARE_VDSO_IMAGE(symname) \ - extern char symname##_start[], symname##_end[]; \ - extern struct page *symname##_pages[] + /* text_mapping.pages is big enough for data/size page pointers */ + struct vm_special_mapping text_mapping; -#if defined CONFIG_X86_32 || defined CONFIG_COMPAT + unsigned long alt, alt_len; -#include <asm/vdso32.h> + unsigned long sym_end_mapping; /* Total size of the mapping */ -DECLARE_VDSO_IMAGE(vdso32_int80); -#ifdef CONFIG_COMPAT -DECLARE_VDSO_IMAGE(vdso32_syscall); + unsigned long sym_vvar_page; + unsigned long sym_hpet_page; + unsigned long sym_VDSO32_NOTE_MASK; + unsigned long sym___kernel_sigreturn; + unsigned long sym___kernel_rt_sigreturn; + unsigned long sym___kernel_vsyscall; + unsigned long sym_VDSO32_SYSENTER_RETURN; +}; + +#ifdef CONFIG_X86_64 +extern const struct vdso_image vdso_image_64; +#endif + +#ifdef CONFIG_X86_X32 +extern const struct vdso_image vdso_image_x32; #endif -DECLARE_VDSO_IMAGE(vdso32_sysenter); -/* - * Given a pointer to the vDSO image, find the pointer to VDSO32_name - * as that symbol is defined in the vDSO sources or linker script. - */ -#define VDSO32_SYMBOL(base, name) \ -({ \ - extern const char VDSO32_##name[]; \ - (void __user *)(VDSO32_##name + (unsigned long)(base)); \ -}) +#if defined CONFIG_X86_32 || defined CONFIG_COMPAT +extern const struct vdso_image vdso_image_32_int80; +#ifdef CONFIG_COMPAT +extern const struct vdso_image vdso_image_32_syscall; #endif +extern const struct vdso_image vdso_image_32_sysenter; -/* - * These symbols are defined with the addresses in the vsyscall page. - * See vsyscall-sigreturn.S. - */ -extern void __user __kernel_sigreturn; -extern void __user __kernel_rt_sigreturn; +extern const struct vdso_image *selected_vdso32; +#endif -void __init patch_vdso32(void *vdso, size_t len); +extern void __init init_vdso_image(const struct vdso_image *image); #endif /* __ASSEMBLER__ */ diff --git a/arch/x86/include/asm/vdso32.h b/arch/x86/include/asm/vdso32.h deleted file mode 100644 index 7efb701..0000000 --- a/arch/x86/include/asm/vdso32.h +++ /dev/null @@ -1,11 +0,0 @@ -#ifndef _ASM_X86_VDSO32_H -#define _ASM_X86_VDSO32_H - -#define VDSO_BASE_PAGE 0 -#define VDSO_VVAR_PAGE 1 -#define VDSO_HPET_PAGE 2 -#define VDSO_PAGES 3 -#define VDSO_PREV_PAGES 2 -#define VDSO_OFFSET(x) ((x) * PAGE_SIZE) - -#endif diff --git a/arch/x86/include/asm/vvar.h b/arch/x86/include/asm/vvar.h index 081d909..5d2b9ad 100644 --- a/arch/x86/include/asm/vvar.h +++ b/arch/x86/include/asm/vvar.h @@ -29,31 +29,13 @@ #else -#ifdef BUILD_VDSO32 +extern char __vvar_page; #define DECLARE_VVAR(offset, type, name) \ extern type vvar_ ## name __attribute__((visibility("hidden"))); #define VVAR(name) (vvar_ ## name) -#else - -extern char __vvar_page; - -/* Base address of vvars. This is not ABI. */ -#ifdef CONFIG_X86_64 -#define VVAR_ADDRESS (-10*1024*1024 - 4096) -#else -#define VVAR_ADDRESS (&__vvar_page) -#endif - -#define DECLARE_VVAR(offset, type, name) \ - static type const * const vvaraddr_ ## name = \ - (void *)(VVAR_ADDRESS + (offset)); - -#define VVAR(name) (*vvaraddr_ ## name) -#endif - #define DEFINE_VVAR(type, name) \ type name \ __attribute__((section(".vvar_" #name), aligned(16))) __visible diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index e709884..ca08a27 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -343,7 +343,7 @@ HYPERVISOR_memory_op(unsigned int cmd, void *arg) } static inline int -HYPERVISOR_multicall(void *call_list, int nr_calls) +HYPERVISOR_multicall(void *call_list, uint32_t nr_calls) { return _hypercall2(int, multicall, call_list, nr_calls); } diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index fd9cb76..3400dba 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -54,6 +54,9 @@ typedef unsigned long xen_pfn_t; #define PRI_xen_pfn "lx" typedef unsigned long xen_ulong_t; #define PRI_xen_ulong "lx" +typedef long xen_long_t; +#define PRI_xen_long "lx" + /* Guest handles for primitive C types. */ __DEFINE_GUEST_HANDLE(uchar, unsigned char); __DEFINE_GUEST_HANDLE(uint, unsigned int); diff --git a/arch/x86/include/uapi/asm/vsyscall.h b/arch/x86/include/uapi/asm/vsyscall.h index 85dc1b3..b97dd6e 100644 --- a/arch/x86/include/uapi/asm/vsyscall.h +++ b/arch/x86/include/uapi/asm/vsyscall.h @@ -7,11 +7,6 @@ enum vsyscall_num { __NR_vgetcpu, }; -#define VSYSCALL_START (-10UL << 20) -#define VSYSCALL_SIZE 1024 -#define VSYSCALL_END (-2UL << 20) -#define VSYSCALL_MAPPED_PAGES 1 -#define VSYSCALL_ADDR(vsyscall_nr) (VSYSCALL_START+VSYSCALL_SIZE*(vsyscall_nr)) - +#define VSYSCALL_ADDR (-10UL << 20) #endif /* _UAPI_ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f4d9600..047f9ff 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -26,9 +26,11 @@ obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o +obj-$(CONFIG_X86_64) += mcount_64.o obj-y += syscall_$(BITS).o vsyscall_gtod.o obj-$(CONFIG_X86_64) += vsyscall_64.o obj-$(CONFIG_X86_64) += vsyscall_emu_64.o +obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o topology.o kdebugfs.o diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index df94598..703130f 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -5,7 +5,6 @@ #include <linux/mutex.h> #include <linux/list.h> #include <linux/stringify.h> -#include <linux/kprobes.h> #include <linux/mm.h> #include <linux/vmalloc.h> #include <linux/memory.h> @@ -551,7 +550,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode, * * Note: Must be called under text_mutex. */ -void *__kprobes text_poke(void *addr, const void *opcode, size_t len) +void *text_poke(void *addr, const void *opcode, size_t len) { unsigned long flags; char *vaddr; diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index b574b29..8e3842f 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -512,7 +512,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, struct dma_attrs *attrs) { gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL); - free_pages((unsigned long)vaddr, get_order(size)); + dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr) diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 9fa8aa0..76164e1 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -10,6 +10,8 @@ * * Copyright 2002 Andi Kleen, SuSE Labs. */ +#define pr_fmt(fmt) "AGP: " fmt + #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> @@ -75,14 +77,13 @@ static u32 __init allocate_aperture(void) addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, aper_size, aper_size); if (!addr) { - printk(KERN_ERR - "Cannot allocate aperture memory hole (%lx,%uK)\n", - addr, aper_size>>10); + pr_err("Cannot allocate aperture memory hole [mem %#010lx-%#010lx] (%uKB)\n", + addr, addr + aper_size - 1, aper_size >> 10); return 0; } memblock_reserve(addr, aper_size); - printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n", - aper_size >> 10, addr); + pr_info("Mapping aperture over RAM [mem %#010lx-%#010lx] (%uKB)\n", + addr, addr + aper_size - 1, aper_size >> 10); register_nosave_region(addr >> PAGE_SHIFT, (addr+aper_size) >> PAGE_SHIFT); @@ -126,10 +127,11 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order) u64 aper; u32 old_order; - printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", bus, slot, func); + pr_info("pci 0000:%02x:%02x:%02x: AGP bridge\n", bus, slot, func); apsizereg = read_pci_config_16(bus, slot, func, cap + 0x14); if (apsizereg == 0xffffffff) { - printk(KERN_ERR "APSIZE in AGP bridge unreadable\n"); + pr_err("pci 0000:%02x:%02x.%d: APSIZE unreadable\n", + bus, slot, func); return 0; } @@ -153,16 +155,18 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order) * On some sick chips, APSIZE is 0. It means it wants 4G * so let double check that order, and lets trust AMD NB settings: */ - printk(KERN_INFO "Aperture from AGP @ %Lx old size %u MB\n", - aper, 32 << old_order); + pr_info("pci 0000:%02x:%02x.%d: AGP aperture [bus addr %#010Lx-%#010Lx] (old size %uMB)\n", + bus, slot, func, aper, aper + (32ULL << (old_order + 20)) - 1, + 32 << old_order); if (aper + (32ULL<<(20 + *order)) > 0x100000000ULL) { - printk(KERN_INFO "Aperture size %u MB (APSIZE %x) is not right, using settings from NB\n", - 32 << *order, apsizereg); + pr_info("pci 0000:%02x:%02x.%d: AGP aperture size %uMB (APSIZE %#x) is not right, using settings from NB\n", + bus, slot, func, 32 << *order, apsizereg); *order = old_order; } - printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n", - aper, 32 << *order, apsizereg); + pr_info("pci 0000:%02x:%02x.%d: AGP aperture [bus addr %#010Lx-%#010Lx] (%uMB, APSIZE %#x)\n", + bus, slot, func, aper, aper + (32ULL << (*order + 20)) - 1, + 32 << *order, apsizereg); if (!aperture_valid(aper, (32*1024*1024) << *order, 32<<20)) return 0; @@ -218,7 +222,7 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp) } } } - printk(KERN_INFO "No AGP bridge found\n"); + pr_info("No AGP bridge found\n"); return 0; } @@ -310,7 +314,8 @@ void __init early_gart_iommu_check(void) if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { /* reserve it, so we can reuse it in second kernel */ - printk(KERN_INFO "update e820 for GART\n"); + pr_info("e820: reserve [mem %#010Lx-%#010Lx] for GART\n", + aper_base, aper_base + aper_size - 1); e820_add_region(aper_base, aper_size, E820_RESERVED); update_e820(); } @@ -354,7 +359,7 @@ int __init gart_iommu_hole_init(void) !early_pci_allowed()) return -ENODEV; - printk(KERN_INFO "Checking aperture...\n"); + pr_info("Checking aperture...\n"); if (!fallback_aper_force) agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp); @@ -395,8 +400,9 @@ int __init gart_iommu_hole_init(void) aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff; aper_base <<= 25; - printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n", - node, aper_base, aper_size >> 20); + pr_info("Node %d: aperture [bus addr %#010Lx-%#010Lx] (%uMB)\n", + node, aper_base, aper_base + aper_size - 1, + aper_size >> 20); node++; if (!aperture_valid(aper_base, aper_size, 64<<20)) { @@ -407,9 +413,9 @@ int __init gart_iommu_hole_init(void) if (!no_iommu && max_pfn > MAX_DMA32_PFN && !printed_gart_size_msg) { - printk(KERN_ERR "you are using iommu with agp, but GART size is less than 64M\n"); - printk(KERN_ERR "please increase GART size in your BIOS setup\n"); - printk(KERN_ERR "if BIOS doesn't have that option, contact your HW vendor!\n"); + pr_err("you are using iommu with agp, but GART size is less than 64MB\n"); + pr_err("please increase GART size in your BIOS setup\n"); + pr_err("if BIOS doesn't have that option, contact your HW vendor!\n"); printed_gart_size_msg = 1; } } else { @@ -446,13 +452,10 @@ out: force_iommu || valid_agp || fallback_aper_force) { - printk(KERN_INFO - "Your BIOS doesn't leave a aperture memory hole\n"); - printk(KERN_INFO - "Please enable the IOMMU option in the BIOS setup\n"); - printk(KERN_INFO - "This costs you %d MB of RAM\n", - 32 << fallback_aper_order); + pr_info("Your BIOS doesn't leave a aperture memory hole\n"); + pr_info("Please enable the IOMMU option in the BIOS setup\n"); + pr_info("This costs you %dMB of RAM\n", + 32 << fallback_aper_order); aper_order = fallback_aper_order; aper_alloc = allocate_aperture(); diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index a698d71..c3fcb5d 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -57,10 +57,10 @@ void arch_trigger_all_cpu_backtrace(void) } clear_bit(0, &backtrace_flag); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); } -static int __kprobes +static int arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) { int cpu; @@ -80,6 +80,7 @@ arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs) return NMI_DONE; } +NOKPROBE_SYMBOL(arch_trigger_all_cpu_backtrace_handler); static int __init register_trigger_all_cpu_backtrace(void) { diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 992060e..81e08ef 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -206,9 +206,6 @@ int __init arch_early_irq_init(void) count = ARRAY_SIZE(irq_cfgx); node = cpu_to_node(0); - /* Make sure the legacy interrupts are marked in the bitmap */ - irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs); - for (i = 0; i < count; i++) { irq_set_chip_data(i, &cfg[i]); zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node); @@ -281,18 +278,6 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) return cfg; } -static int alloc_irqs_from(unsigned int from, unsigned int count, int node) -{ - return irq_alloc_descs_from(from, count, node); -} - -static void free_irq_at(unsigned int at, struct irq_cfg *cfg) -{ - free_irq_cfg(at, cfg); - irq_free_desc(at); -} - - struct io_apic { unsigned int index; unsigned int unused[3]; @@ -2312,7 +2297,7 @@ int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask, int err; if (!config_enabled(CONFIG_SMP)) - return -1; + return -EPERM; if (!cpumask_intersects(mask, cpu_online_mask)) return -EINVAL; @@ -2343,7 +2328,7 @@ int native_ioapic_set_affinity(struct irq_data *data, int ret; if (!config_enabled(CONFIG_SMP)) - return -1; + return -EPERM; raw_spin_lock_irqsave(&ioapic_lock, flags); ret = __ioapic_set_affinity(data, mask, &dest); @@ -2916,98 +2901,39 @@ static int __init ioapic_init_ops(void) device_initcall(ioapic_init_ops); /* - * Dynamic irq allocate and deallocation + * Dynamic irq allocate and deallocation. Should be replaced by irq domains! */ -unsigned int __create_irqs(unsigned int from, unsigned int count, int node) +int arch_setup_hwirq(unsigned int irq, int node) { - struct irq_cfg **cfg; + struct irq_cfg *cfg; unsigned long flags; - int irq, i; - - if (from < nr_irqs_gsi) - from = nr_irqs_gsi; + int ret; - cfg = kzalloc_node(count * sizeof(cfg[0]), GFP_KERNEL, node); + cfg = alloc_irq_cfg(irq, node); if (!cfg) - return 0; - - irq = alloc_irqs_from(from, count, node); - if (irq < 0) - goto out_cfgs; - - for (i = 0; i < count; i++) { - cfg[i] = alloc_irq_cfg(irq + i, node); - if (!cfg[i]) - goto out_irqs; - } + return -ENOMEM; raw_spin_lock_irqsave(&vector_lock, flags); - for (i = 0; i < count; i++) - if (__assign_irq_vector(irq + i, cfg[i], apic->target_cpus())) - goto out_vecs; + ret = __assign_irq_vector(irq, cfg, apic->target_cpus()); raw_spin_unlock_irqrestore(&vector_lock, flags); - for (i = 0; i < count; i++) { - irq_set_chip_data(irq + i, cfg[i]); - irq_clear_status_flags(irq + i, IRQ_NOREQUEST); - } - - kfree(cfg); - return irq; - -out_vecs: - for (i--; i >= 0; i--) - __clear_irq_vector(irq + i, cfg[i]); - raw_spin_unlock_irqrestore(&vector_lock, flags); -out_irqs: - for (i = 0; i < count; i++) - free_irq_at(irq + i, cfg[i]); -out_cfgs: - kfree(cfg); - return 0; -} - -unsigned int create_irq_nr(unsigned int from, int node) -{ - return __create_irqs(from, 1, node); -} - -int create_irq(void) -{ - int node = cpu_to_node(0); - unsigned int irq_want; - int irq; - - irq_want = nr_irqs_gsi; - irq = create_irq_nr(irq_want, node); - - if (irq == 0) - irq = -1; - - return irq; + if (!ret) + irq_set_chip_data(irq, cfg); + else + free_irq_cfg(irq, cfg); + return ret; } -void destroy_irq(unsigned int irq) +void arch_teardown_hwirq(unsigned int irq) { struct irq_cfg *cfg = irq_get_chip_data(irq); unsigned long flags; - irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE); - free_remapped_irq(irq); - raw_spin_lock_irqsave(&vector_lock, flags); __clear_irq_vector(irq, cfg); raw_spin_unlock_irqrestore(&vector_lock, flags); - free_irq_at(irq, cfg); -} - -void destroy_irqs(unsigned int irq, unsigned int count) -{ - unsigned int i; - - for (i = 0; i < count; i++) - destroy_irq(irq + i); + free_irq_cfg(irq, cfg); } /* @@ -3075,9 +3001,11 @@ msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) struct irq_cfg *cfg = data->chip_data; struct msi_msg msg; unsigned int dest; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; __get_cached_msi_msg(data->msi_desc, &msg); @@ -3136,8 +3064,8 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - unsigned int irq, irq_want; struct msi_desc *msidesc; + unsigned int irq; int node, ret; /* Multiple MSI vectors only supported with interrupt remapping */ @@ -3145,28 +3073,25 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 1; node = dev_to_node(&dev->dev); - irq_want = nr_irqs_gsi; + list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = create_irq_nr(irq_want, node); - if (irq == 0) + irq = irq_alloc_hwirq(node); + if (!irq) return -ENOSPC; - irq_want = irq + 1; - ret = setup_msi_irq(dev, msidesc, irq, 0); - if (ret < 0) - goto error; + if (ret < 0) { + irq_free_hwirq(irq); + return ret; + } + } return 0; - -error: - destroy_irq(irq); - return ret; } void native_teardown_msi_irq(unsigned int irq) { - destroy_irq(irq); + irq_free_hwirq(irq); } #ifdef CONFIG_DMAR_TABLE @@ -3177,9 +3102,11 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_cfg *cfg = data->chip_data; unsigned int dest, irq = data->irq; struct msi_msg msg; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; dmar_msi_read(irq, &msg); @@ -3226,9 +3153,11 @@ static int hpet_msi_set_affinity(struct irq_data *data, struct irq_cfg *cfg = data->chip_data; struct msi_msg msg; unsigned int dest; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; hpet_msi_read(data->handler_data, &msg); @@ -3295,9 +3224,11 @@ ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force) { struct irq_cfg *cfg = data->chip_data; unsigned int dest; + int ret; - if (__ioapic_set_affinity(data, mask, &dest)) - return -1; + ret = __ioapic_set_affinity(data, mask, &dest); + if (ret) + return ret; target_ht_irq(data->irq, dest, cfg->vector); return IRQ_SET_MASK_OK_NOCOPY; @@ -3420,11 +3351,6 @@ static void __init probe_nr_irqs_gsi(void) printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi); } -int get_nr_irqs_gsi(void) -{ - return nr_irqs_gsi; -} - unsigned int arch_dynirq_lower_bound(unsigned int from) { return from < nr_irqs_gsi ? nr_irqs_gsi : from; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 7834389..293b41d 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -5,7 +5,7 @@ * * SGI UV APIC functions (note: not an Intel compatible APIC) * - * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved. */ #include <linux/cpumask.h> #include <linux/hardirq.h> @@ -440,6 +440,20 @@ static __initdata struct redir_addr redir_addrs[] = { {UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR}, }; +static unsigned char get_n_lshift(int m_val) +{ + union uv3h_gr0_gam_gr_config_u m_gr_config; + + if (is_uv1_hub()) + return m_val; + + if (is_uv2_hub()) + return m_val == 40 ? 40 : 39; + + m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG); + return m_gr_config.s3.m_skt; +} + static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) { union uvh_rh_gam_alias210_overlay_config_2_mmr_u alias; @@ -849,6 +863,7 @@ void __init uv_system_init(void) int gnode_extra, min_pnode = 999999, max_pnode = -1; unsigned long mmr_base, present, paddr; unsigned short pnode_mask; + unsigned char n_lshift; char *hub = (is_uv1_hub() ? "UV1" : (is_uv2_hub() ? "UV2" : "UV3")); @@ -860,6 +875,7 @@ void __init uv_system_init(void) m_val = m_n_config.s.m_skt; n_val = m_n_config.s.n_skt; pnode_mask = (1 << n_val) - 1; + n_lshift = get_n_lshift(m_val); mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; @@ -867,8 +883,9 @@ void __init uv_system_init(void) node_id.v = uv_read_local_mmr(UVH_NODE_ID); gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1; gnode_upper = ((unsigned long)gnode_extra << m_val); - pr_info("UV: N:%d M:%d pnode_mask:0x%x gnode_upper/extra:0x%lx/0x%x\n", - n_val, m_val, pnode_mask, gnode_upper, gnode_extra); + pr_info("UV: N:%d M:%d pnode_mask:0x%x gnode_upper/extra:0x%lx/0x%x n_lshift 0x%x\n", + n_val, m_val, pnode_mask, gnode_upper, gnode_extra, + n_lshift); pr_info("UV: global MMR base 0x%lx\n", mmr_base); @@ -935,8 +952,7 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision; uv_cpu_hub_info(cpu)->m_shift = 64 - m_val; - uv_cpu_hub_info(cpu)->n_lshift = is_uv2_1_hub() ? - (m_val == 40 ? 40 : 39) : m_val; + uv_cpu_hub_info(cpu)->n_lshift = n_lshift; pnode = uv_apicid_to_pnode(apicid); blade = boot_pnode_to_blade(pnode); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 3ab0343..f3a1f04 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -844,21 +844,10 @@ static int apm_do_idle(void) int polling; int err = 0; - polling = !!(current_thread_info()->status & TS_POLLING); - if (polling) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - } if (!need_resched()) { idled = 1; ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err); } - if (polling) - current_thread_info()->status |= TS_POLLING; if (!idled) return 0; diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index e7c4b97..188a8c5 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -8,6 +8,7 @@ #include <linux/delay.h> #include <linux/sched.h> #include <linux/init.h> +#include <linux/kprobes.h> #include <linux/kgdb.h> #include <linux/smp.h> #include <linux/io.h> @@ -20,6 +21,7 @@ #include <asm/processor.h> #include <asm/debugreg.h> #include <asm/sections.h> +#include <asm/vsyscall.h> #include <linux/topology.h> #include <linux/cpumask.h> #include <asm/pgtable.h> @@ -962,6 +964,38 @@ static void vgetcpu_set_mode(void) else vgetcpu_mode = VGETCPU_LSL; } + +/* May not be __init: called during resume */ +static void syscall32_cpu_init(void) +{ + /* Load these always in case some future AMD CPU supports + SYSENTER from compat mode too. */ + wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); + + wrmsrl(MSR_CSTAR, ia32_cstar_target); +} +#endif + +#ifdef CONFIG_X86_32 +void enable_sep_cpu(void) +{ + int cpu = get_cpu(); + struct tss_struct *tss = &per_cpu(init_tss, cpu); + + if (!boot_cpu_has(X86_FEATURE_SEP)) { + put_cpu(); + return; + } + + tss->x86_tss.ss1 = __KERNEL_CS; + tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss; + wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0); + wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0); + wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0); + put_cpu(); +} #endif void __init identify_boot_cpu(void) @@ -1169,6 +1203,7 @@ int is_debug_stack(unsigned long addr) (addr <= __get_cpu_var(debug_stack_addr) && addr > (__get_cpu_var(debug_stack_addr) - DEBUG_STKSZ)); } +NOKPROBE_SYMBOL(is_debug_stack); DEFINE_PER_CPU(u32, debug_idt_ctr); @@ -1177,6 +1212,7 @@ void debug_stack_set_zero(void) this_cpu_inc(debug_idt_ctr); load_current_idt(); } +NOKPROBE_SYMBOL(debug_stack_set_zero); void debug_stack_reset(void) { @@ -1185,6 +1221,7 @@ void debug_stack_reset(void) if (this_cpu_dec_return(debug_idt_ctr) == 0) load_current_idt(); } +NOKPROBE_SYMBOL(debug_stack_reset); #else /* CONFIG_X86_64 */ diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 68317c8..bb92f38 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -60,8 +60,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define SPINUNIT 100 /* 100ns */ -atomic_t mce_entry; - DEFINE_PER_CPU(unsigned, mce_exception_count); struct mce_bank *mce_banks __read_mostly; @@ -704,8 +702,7 @@ static int mce_timed_out(u64 *t) if (!mca_cfg.monarch_timeout) goto out; if ((s64)*t < SPINUNIT) { - /* CHECKME: Make panic default for 1 too? */ - if (mca_cfg.tolerant < 1) + if (mca_cfg.tolerant <= 1) mce_panic("Timeout synchronizing machine check over CPUs", NULL, NULL); cpu_missing = 1; @@ -1041,8 +1038,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); char *msg = "Unknown"; - atomic_inc(&mce_entry); - this_cpu_inc(mce_exception_count); if (!cfg->banks) @@ -1172,7 +1167,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_report_event(regs); mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); out: - atomic_dec(&mce_entry); sync_core(); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -2437,32 +2431,65 @@ static __init int mcheck_init_device(void) int err; int i = 0; - if (!mce_available(&boot_cpu_data)) - return -EIO; + if (!mce_available(&boot_cpu_data)) { + err = -EIO; + goto err_out; + } - zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL); + if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) { + err = -ENOMEM; + goto err_out; + } mce_init_banks(); err = subsys_system_register(&mce_subsys, NULL); if (err) - return err; + goto err_out_mem; cpu_notifier_register_begin(); for_each_online_cpu(i) { err = mce_device_create(i); if (err) { cpu_notifier_register_done(); - return err; + goto err_device_create; } } - register_syscore_ops(&mce_syscore_ops); __register_hotcpu_notifier(&mce_cpu_notifier); cpu_notifier_register_done(); + register_syscore_ops(&mce_syscore_ops); + /* register character device /dev/mcelog */ - misc_register(&mce_chrdev_device); + err = misc_register(&mce_chrdev_device); + if (err) + goto err_register; + + return 0; + +err_register: + unregister_syscore_ops(&mce_syscore_ops); + + cpu_notifier_register_begin(); + __unregister_hotcpu_notifier(&mce_cpu_notifier); + cpu_notifier_register_done(); + +err_device_create: + /* + * We didn't keep track of which devices were created above, but + * even if we had, the set of online cpus might have changed. + * Play safe and remove for every possible cpu, since + * mce_device_remove() will do the right thing. + */ + for_each_possible_cpu(i) + mce_device_remove(i); + +err_out_mem: + free_cpumask_var(mce_device_initialized); + +err_out: + pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); return err; } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 15c9876..dd9d619 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -97,6 +97,9 @@ MODULE_LICENSE("GPL"); static struct microcode_ops *microcode_ops; +bool dis_ucode_ldr; +module_param(dis_ucode_ldr, bool, 0); + /* * Synchronization. * @@ -546,6 +549,9 @@ static int __init microcode_init(void) struct cpuinfo_x86 *c = &cpu_data(0); int error; + if (dis_ucode_ldr) + return 0; + if (c->x86_vendor == X86_VENDOR_INTEL) microcode_ops = init_intel_microcode(); else if (c->x86_vendor == X86_VENDOR_AMD) diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index be7f851..5f28a64 100644 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c @@ -17,9 +17,11 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> +#include <asm/microcode.h> #include <asm/microcode_intel.h> #include <asm/microcode_amd.h> #include <asm/processor.h> +#include <asm/cmdline.h> #define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) #define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u') @@ -72,10 +74,33 @@ static int x86_family(void) return x86; } +static bool __init check_loader_disabled_bsp(void) +{ +#ifdef CONFIG_X86_32 + const char *cmdline = (const char *)__pa_nodebug(boot_command_line); + const char *opt = "dis_ucode_ldr"; + const char *option = (const char *)__pa_nodebug(opt); + bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr); + +#else /* CONFIG_X86_64 */ + const char *cmdline = boot_command_line; + const char *option = "dis_ucode_ldr"; + bool *res = &dis_ucode_ldr; +#endif + + if (cmdline_find_option_bool(cmdline, option)) + *res = true; + + return *res; +} + void __init load_ucode_bsp(void) { int vendor, x86; + if (check_loader_disabled_bsp()) + return; + if (!have_cpuid_p()) return; @@ -96,10 +121,22 @@ void __init load_ucode_bsp(void) } } +static bool check_loader_disabled_ap(void) +{ +#ifdef CONFIG_X86_32 + return __pa_nodebug(dis_ucode_ldr); +#else + return dis_ucode_ldr; +#endif +} + void load_ucode_ap(void) { int vendor, x86; + if (check_loader_disabled_ap()) + return; + if (!have_cpuid_p()) return; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 76f98fe..a450373 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -132,15 +132,6 @@ static void __init ms_hyperv_init_platform(void) lapic_timer_frequency = hv_lapic_frequency; printk(KERN_INFO "HyperV: LAPIC Timer Frequency: %#x\n", lapic_timer_frequency); - - /* - * On Hyper-V, when we are booting off an EFI firmware stack, - * we do not have many legacy devices including PIC, PIT etc. - */ - if (efi_enabled(EFI_BOOT)) { - printk(KERN_INFO "HyperV: Using null_legacy_pic\n"); - legacy_pic = &null_legacy_pic; - } } #endif diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index ae407f7..2bdfbff 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -303,15 +303,6 @@ int x86_setup_perfctr(struct perf_event *event) hwc->sample_period = x86_pmu.max_period; hwc->last_period = hwc->sample_period; local64_set(&hwc->period_left, hwc->sample_period); - } else { - /* - * If we have a PMU initialized but no APIC - * interrupts, we cannot sample hardware - * events (user-space has to fall back and - * sample via a hrtimer based software event): - */ - if (!x86_pmu.apic) - return -EOPNOTSUPP; } if (attr->type == PERF_TYPE_RAW) @@ -721,6 +712,7 @@ int perf_assign_events(struct perf_event **events, int n, return sched.state.unassigned; } +EXPORT_SYMBOL_GPL(perf_assign_events); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { @@ -1292,7 +1284,7 @@ void perf_events_lapic_init(void) apic_write(APIC_LVTPC, APIC_DM_NMI); } -static int __kprobes +static int perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) { u64 start_clock; @@ -1310,6 +1302,7 @@ perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs) return ret; } +NOKPROBE_SYMBOL(perf_event_nmi_handler); struct event_constraint emptyconstraint; struct event_constraint unconstrained; @@ -1365,6 +1358,15 @@ static void __init pmu_check_apic(void) x86_pmu.apic = 0; pr_info("no APIC, boot with the \"lapic\" boot parameter to force-enable it.\n"); pr_info("no hardware sampling interrupt available.\n"); + + /* + * If we have a PMU initialized but no APIC + * interrupts, we cannot sample hardware + * events (user-space has to fall back and + * sample via a hrtimer based software event): + */ + pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; + } static struct attribute_group x86_pmu_format_group = { diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c index 4c36bbe..cbb1be3e 100644 --- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c +++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c @@ -593,7 +593,7 @@ out: return 1; } -static int __kprobes +static int perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs) { int handled = 0; @@ -606,6 +606,7 @@ perf_ibs_nmi_handler(unsigned int cmd, struct pt_regs *regs) return handled; } +NOKPROBE_SYMBOL(perf_ibs_nmi_handler); static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name) { diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index ae96cfa..980970c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -108,15 +108,31 @@ static u64 precise_store_data(u64 status) return val; } -static u64 precise_store_data_hsw(u64 status) +static u64 precise_store_data_hsw(struct perf_event *event, u64 status) { union perf_mem_data_src dse; + u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK; dse.val = 0; dse.mem_op = PERF_MEM_OP_STORE; dse.mem_lvl = PERF_MEM_LVL_NA; + + /* + * L1 info only valid for following events: + * + * MEM_UOPS_RETIRED.STLB_MISS_STORES + * MEM_UOPS_RETIRED.LOCK_STORES + * MEM_UOPS_RETIRED.SPLIT_STORES + * MEM_UOPS_RETIRED.ALL_STORES + */ + if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0) + return dse.mem_lvl; + if (status & 1) - dse.mem_lvl = PERF_MEM_LVL_L1; + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; + else + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS; + /* Nothing else supported. Sorry. */ return dse.val; } @@ -887,7 +903,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, data.data_src.val = load_latency_data(pebs->dse); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) data.data_src.val = - precise_store_data_hsw(pebs->dse); + precise_store_data_hsw(event, pebs->dse); else data.data_src.val = precise_store_data(pebs->dse); } diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index d82d155..9dd2459 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -384,6 +384,9 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_NO_TX) mask |= X86_BR_NO_TX; + if (br_type & PERF_SAMPLE_BRANCH_COND) + mask |= X86_BR_JCC; + /* * stash actual user request into reg, it may * be used by fixup code for some CPU @@ -678,6 +681,7 @@ static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { * NHM/WSM erratum: must include IND_JMP to capture IND_CALL */ [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP, + [PERF_SAMPLE_BRANCH_COND] = LBR_JCC, }; static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { @@ -689,6 +693,7 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = { [PERF_SAMPLE_BRANCH_ANY_CALL] = LBR_REL_CALL | LBR_IND_CALL | LBR_FAR, [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL, + [PERF_SAMPLE_BRANCH_COND] = LBR_JCC, }; /* core */ diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index d35078e..7db54b5 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -206,23 +206,21 @@ static void __init dtb_apic_setup(void) static void __init x86_flattree_get_config(void) { u32 size, map_len; - struct boot_param_header *dt; + void *dt; if (!initial_dtb) return; - map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), - (u64)sizeof(struct boot_param_header)); + map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128); - dt = early_memremap(initial_dtb, map_len); - size = be32_to_cpu(dt->totalsize); + initial_boot_params = dt = early_memremap(initial_dtb, map_len); + size = of_get_flat_dt_size(); if (map_len < size) { early_iounmap(dt, map_len); - dt = early_memremap(initial_dtb, size); + initial_boot_params = dt = early_memremap(initial_dtb, size); map_len = size; } - initial_boot_params = dt; unflatten_and_copy_device_tree(); early_iounmap(dt, map_len); } diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index d9c12d3..b74ebc7 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -200,7 +200,7 @@ static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; static int die_owner = -1; static unsigned int die_nest_count; -unsigned __kprobes long oops_begin(void) +unsigned long oops_begin(void) { int cpu; unsigned long flags; @@ -223,8 +223,9 @@ unsigned __kprobes long oops_begin(void) return flags; } EXPORT_SYMBOL_GPL(oops_begin); +NOKPROBE_SYMBOL(oops_begin); -void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) +void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { if (regs && kexec_should_crash(current)) crash_kexec(regs); @@ -247,8 +248,9 @@ void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr) panic("Fatal exception"); do_exit(signr); } +NOKPROBE_SYMBOL(oops_end); -int __kprobes __die(const char *str, struct pt_regs *regs, long err) +int __die(const char *str, struct pt_regs *regs, long err) { #ifdef CONFIG_X86_32 unsigned short ss; @@ -291,6 +293,7 @@ int __kprobes __die(const char *str, struct pt_regs *regs, long err) #endif return 0; } +NOKPROBE_SYMBOL(__die); /* * This is gone through when something in the kernel has done something bad diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6cda0ba..2e1a685 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -419,7 +419,7 @@ static size_t __init gen6_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } -static size_t gen8_stolen_size(int num, int slot, int func) +static size_t __init gen8_stolen_size(int num, int slot, int func) { u16 gmch_ctrl; @@ -429,48 +429,73 @@ static size_t gen8_stolen_size(int num, int slot, int func) return gmch_ctrl << 25; /* 32 MB units */ } +static size_t __init chv_stolen_size(int num, int slot, int func) +{ + u16 gmch_ctrl; + + gmch_ctrl = read_pci_config_16(num, slot, func, SNB_GMCH_CTRL); + gmch_ctrl >>= SNB_GMCH_GMS_SHIFT; + gmch_ctrl &= SNB_GMCH_GMS_MASK; + + /* + * 0x0 to 0x10: 32MB increments starting at 0MB + * 0x11 to 0x16: 4MB increments starting at 8MB + * 0x17 to 0x1d: 4MB increments start at 36MB + */ + if (gmch_ctrl < 0x11) + return gmch_ctrl << 25; + else if (gmch_ctrl < 0x17) + return (gmch_ctrl - 0x11 + 2) << 22; + else + return (gmch_ctrl - 0x17 + 9) << 22; +} struct intel_stolen_funcs { size_t (*size)(int num, int slot, int func); u32 (*base)(int num, int slot, int func, size_t size); }; -static const struct intel_stolen_funcs i830_stolen_funcs = { +static const struct intel_stolen_funcs i830_stolen_funcs __initconst = { .base = i830_stolen_base, .size = i830_stolen_size, }; -static const struct intel_stolen_funcs i845_stolen_funcs = { +static const struct intel_stolen_funcs i845_stolen_funcs __initconst = { .base = i845_stolen_base, .size = i830_stolen_size, }; -static const struct intel_stolen_funcs i85x_stolen_funcs = { +static const struct intel_stolen_funcs i85x_stolen_funcs __initconst = { .base = i85x_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs i865_stolen_funcs = { +static const struct intel_stolen_funcs i865_stolen_funcs __initconst = { .base = i865_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen3_stolen_funcs = { +static const struct intel_stolen_funcs gen3_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen3_stolen_size, }; -static const struct intel_stolen_funcs gen6_stolen_funcs = { +static const struct intel_stolen_funcs gen6_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen6_stolen_size, }; -static const struct intel_stolen_funcs gen8_stolen_funcs = { +static const struct intel_stolen_funcs gen8_stolen_funcs __initconst = { .base = intel_stolen_base, .size = gen8_stolen_size, }; -static struct pci_device_id intel_stolen_ids[] __initdata = { +static const struct intel_stolen_funcs chv_stolen_funcs __initconst = { + .base = intel_stolen_base, + .size = chv_stolen_size, +}; + +static const struct pci_device_id intel_stolen_ids[] __initconst = { INTEL_I830_IDS(&i830_stolen_funcs), INTEL_I845G_IDS(&i845_stolen_funcs), INTEL_I85X_IDS(&i85x_stolen_funcs), @@ -496,7 +521,8 @@ static struct pci_device_id intel_stolen_ids[] __initdata = { INTEL_HSW_D_IDS(&gen6_stolen_funcs), INTEL_HSW_M_IDS(&gen6_stolen_funcs), INTEL_BDW_M_IDS(&gen8_stolen_funcs), - INTEL_BDW_D_IDS(&gen8_stolen_funcs) + INTEL_BDW_D_IDS(&gen8_stolen_funcs), + INTEL_CHV_IDS(&chv_stolen_funcs), }; static void __init intel_graphics_stolen(int num, int slot, int func) diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S index a2a4f46..f0da82b 100644 --- a/arch/x86/kernel/entry_32.S +++ b/arch/x86/kernel/entry_32.S @@ -315,10 +315,6 @@ ENTRY(ret_from_kernel_thread) ENDPROC(ret_from_kernel_thread) /* - * Interrupt exit functions should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" -/* * Return to user mode is not as complex as all this looks, * but we want the default path for a system call return to * go as quickly as possible which is why some of this is @@ -372,10 +368,6 @@ need_resched: END(resume_kernel) #endif CFI_ENDPROC -/* - * End of kprobes section - */ - .popsection /* SYSENTER_RETURN points to after the "sysenter" instruction in the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ @@ -495,10 +487,6 @@ sysexit_audit: PTGS_TO_GS_EX ENDPROC(ia32_sysenter_target) -/* - * syscall stub including irq exit should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" # system call handler stub ENTRY(system_call) RING0_INT_FRAME # can't unwind into user space anyway @@ -527,6 +515,7 @@ syscall_exit: restore_all: TRACE_IRQS_IRET restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS # Warning: PT_OLDSS(%esp) contains the wrong/random values if we # are returning to the kernel. @@ -537,6 +526,7 @@ restore_all_notrace: cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax CFI_REMEMBER_STATE je ldt_ss # returning to user-space with LDT SS +#endif restore_nocheck: RESTORE_REGS 4 # skip orig_eax/error_code irq_return: @@ -549,13 +539,9 @@ ENTRY(iret_exc) .previous _ASM_EXTABLE(irq_return,iret_exc) +#ifdef CONFIG_X86_ESPFIX32 CFI_RESTORE_STATE ldt_ss: - larl PT_OLDSS(%esp), %eax - jnz restore_nocheck - testl $0x00400000, %eax # returning to 32bit stack? - jnz restore_nocheck # allright, normal return - #ifdef CONFIG_PARAVIRT /* * The kernel can't run on a non-flat stack if paravirt mode @@ -597,6 +583,7 @@ ldt_ss: lss (%esp), %esp /* switch to espfix segment */ CFI_ADJUST_CFA_OFFSET -8 jmp restore_nocheck +#endif CFI_ENDPROC ENDPROC(system_call) @@ -691,10 +678,6 @@ syscall_badsys: jmp resume_userspace END(syscall_badsys) CFI_ENDPROC -/* - * End of kprobes section - */ - .popsection .macro FIXUP_ESPFIX_STACK /* @@ -704,6 +687,7 @@ END(syscall_badsys) * the high word of the segment base from the GDT and swiches to the * normal stack and adjusts ESP with the matching offset. */ +#ifdef CONFIG_X86_ESPFIX32 /* fixup the stack */ mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ @@ -713,8 +697,10 @@ END(syscall_badsys) pushl_cfi %eax lss (%esp), %esp /* switch to the normal stack segment */ CFI_ADJUST_CFA_OFFSET -8 +#endif .endm .macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 movl %ss, %eax /* see if on espfix stack */ cmpw $__ESPFIX_SS, %ax @@ -725,6 +711,7 @@ END(syscall_badsys) /* switch to normal stack */ FIXUP_ESPFIX_STACK 27: +#endif .endm /* @@ -781,10 +768,6 @@ common_interrupt: ENDPROC(common_interrupt) CFI_ENDPROC -/* - * Irq entries should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" #define BUILD_INTERRUPT3(name, nr, fn) \ ENTRY(name) \ RING0_INT_FRAME; \ @@ -961,10 +944,6 @@ ENTRY(spurious_interrupt_bug) jmp error_code CFI_ENDPROC END(spurious_interrupt_bug) -/* - * End of kprobes section - */ - .popsection #ifdef CONFIG_XEN /* Xen doesn't set %esp to be precisely what the normal sysenter @@ -1239,11 +1218,6 @@ return_to_handler: jmp *%ecx #endif -/* - * Some functions should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" - #ifdef CONFIG_TRACING ENTRY(trace_page_fault) RING0_EC_FRAME @@ -1355,11 +1329,13 @@ END(debug) ENTRY(nmi) RING0_INT_FRAME ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 pushl_cfi %eax movl %ss, %eax cmpw $__ESPFIX_SS, %ax popl_cfi %eax je nmi_espfix_stack +#endif cmpl $ia32_sysenter_target,(%esp) je nmi_stack_fixup pushl_cfi %eax @@ -1399,6 +1375,7 @@ nmi_debug_stack_check: FIX_STACK 24, nmi_stack_correct, 1 jmp nmi_stack_correct +#ifdef CONFIG_X86_ESPFIX32 nmi_espfix_stack: /* We have a RING0_INT_FRAME here. * @@ -1420,6 +1397,7 @@ nmi_espfix_stack: lss 12+4(%esp), %esp # back to espfix stack CFI_ADJUST_CFA_OFFSET -24 jmp irq_return +#endif CFI_ENDPROC END(nmi) @@ -1453,7 +1431,3 @@ ENTRY(async_page_fault) END(async_page_fault) #endif -/* - * End of kprobes section - */ - .popsection diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index 1e96c36..b25ca96 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -36,7 +36,7 @@ * - FIXUP_TOP_OF_STACK/RESTORE_TOP_OF_STACK - Fix up the hardware stack * frame that is otherwise undefined after a SYSCALL * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging. - * - errorentry/paranoidentry/zeroentry - Define exception entry points. + * - idtentry - Define exception entry points. */ #include <linux/linkage.h> @@ -53,11 +53,11 @@ #include <asm/page_types.h> #include <asm/irqflags.h> #include <asm/paravirt.h> -#include <asm/ftrace.h> #include <asm/percpu.h> #include <asm/asm.h> #include <asm/context_tracking.h> #include <asm/smap.h> +#include <asm/pgtable_types.h> #include <linux/err.h> /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ @@ -69,209 +69,6 @@ .code64 .section .entry.text, "ax" -#ifdef CONFIG_FUNCTION_TRACER - -#ifdef CC_USING_FENTRY -# define function_hook __fentry__ -#else -# define function_hook mcount -#endif - -#ifdef CONFIG_DYNAMIC_FTRACE - -ENTRY(function_hook) - retq -END(function_hook) - -/* skip is set if stack has been adjusted */ -.macro ftrace_caller_setup skip=0 - MCOUNT_SAVE_FRAME \skip - - /* Load the ftrace_ops into the 3rd parameter */ - movq function_trace_op(%rip), %rdx - - /* Load ip into the first parameter */ - movq RIP(%rsp), %rdi - subq $MCOUNT_INSN_SIZE, %rdi - /* Load the parent_ip into the second parameter */ -#ifdef CC_USING_FENTRY - movq SS+16(%rsp), %rsi -#else - movq 8(%rbp), %rsi -#endif -.endm - -ENTRY(ftrace_caller) - /* Check if tracing was disabled (quick check) */ - cmpl $0, function_trace_stop - jne ftrace_stub - - ftrace_caller_setup - /* regs go into 4th parameter (but make it NULL) */ - movq $0, %rcx - -GLOBAL(ftrace_call) - call ftrace_stub - - MCOUNT_RESTORE_FRAME -ftrace_return: - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -GLOBAL(ftrace_graph_call) - jmp ftrace_stub -#endif - -GLOBAL(ftrace_stub) - retq -END(ftrace_caller) - -ENTRY(ftrace_regs_caller) - /* Save the current flags before compare (in SS location)*/ - pushfq - - /* Check if tracing was disabled (quick check) */ - cmpl $0, function_trace_stop - jne ftrace_restore_flags - - /* skip=8 to skip flags saved in SS */ - ftrace_caller_setup 8 - - /* Save the rest of pt_regs */ - movq %r15, R15(%rsp) - movq %r14, R14(%rsp) - movq %r13, R13(%rsp) - movq %r12, R12(%rsp) - movq %r11, R11(%rsp) - movq %r10, R10(%rsp) - movq %rbp, RBP(%rsp) - movq %rbx, RBX(%rsp) - /* Copy saved flags */ - movq SS(%rsp), %rcx - movq %rcx, EFLAGS(%rsp) - /* Kernel segments */ - movq $__KERNEL_DS, %rcx - movq %rcx, SS(%rsp) - movq $__KERNEL_CS, %rcx - movq %rcx, CS(%rsp) - /* Stack - skipping return address */ - leaq SS+16(%rsp), %rcx - movq %rcx, RSP(%rsp) - - /* regs go into 4th parameter */ - leaq (%rsp), %rcx - -GLOBAL(ftrace_regs_call) - call ftrace_stub - - /* Copy flags back to SS, to restore them */ - movq EFLAGS(%rsp), %rax - movq %rax, SS(%rsp) - - /* Handlers can change the RIP */ - movq RIP(%rsp), %rax - movq %rax, SS+8(%rsp) - - /* restore the rest of pt_regs */ - movq R15(%rsp), %r15 - movq R14(%rsp), %r14 - movq R13(%rsp), %r13 - movq R12(%rsp), %r12 - movq R10(%rsp), %r10 - movq RBP(%rsp), %rbp - movq RBX(%rsp), %rbx - - /* skip=8 to skip flags saved in SS */ - MCOUNT_RESTORE_FRAME 8 - - /* Restore flags */ - popfq - - jmp ftrace_return -ftrace_restore_flags: - popfq - jmp ftrace_stub - -END(ftrace_regs_caller) - - -#else /* ! CONFIG_DYNAMIC_FTRACE */ - -ENTRY(function_hook) - cmpl $0, function_trace_stop - jne ftrace_stub - - cmpq $ftrace_stub, ftrace_trace_function - jnz trace - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER - cmpq $ftrace_stub, ftrace_graph_return - jnz ftrace_graph_caller - - cmpq $ftrace_graph_entry_stub, ftrace_graph_entry - jnz ftrace_graph_caller -#endif - -GLOBAL(ftrace_stub) - retq - -trace: - MCOUNT_SAVE_FRAME - - movq RIP(%rsp), %rdi -#ifdef CC_USING_FENTRY - movq SS+16(%rsp), %rsi -#else - movq 8(%rbp), %rsi -#endif - subq $MCOUNT_INSN_SIZE, %rdi - - call *ftrace_trace_function - - MCOUNT_RESTORE_FRAME - - jmp ftrace_stub -END(function_hook) -#endif /* CONFIG_DYNAMIC_FTRACE */ -#endif /* CONFIG_FUNCTION_TRACER */ - -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -ENTRY(ftrace_graph_caller) - MCOUNT_SAVE_FRAME - -#ifdef CC_USING_FENTRY - leaq SS+16(%rsp), %rdi - movq $0, %rdx /* No framepointers needed */ -#else - leaq 8(%rbp), %rdi - movq (%rbp), %rdx -#endif - movq RIP(%rsp), %rsi - subq $MCOUNT_INSN_SIZE, %rsi - - call prepare_ftrace_return - - MCOUNT_RESTORE_FRAME - - retq -END(ftrace_graph_caller) - -GLOBAL(return_to_handler) - subq $24, %rsp - - /* Save the return values */ - movq %rax, (%rsp) - movq %rdx, 8(%rsp) - movq %rbp, %rdi - - call ftrace_return_to_handler - - movq %rax, %rdi - movq 8(%rsp), %rdx - movq (%rsp), %rax - addq $24, %rsp - jmp *%rdi -#endif - #ifndef CONFIG_PREEMPT #define retint_kernel retint_restore_args @@ -487,8 +284,6 @@ ENDPROC(native_usergs_sysret64) TRACE_IRQS_OFF .endm -/* save complete stack frame */ - .pushsection .kprobes.text, "ax" ENTRY(save_paranoid) XCPT_FRAME 1 RDI+8 cld @@ -517,7 +312,6 @@ ENTRY(save_paranoid) 1: ret CFI_ENDPROC END(save_paranoid) - .popsection /* * A newly forked process directly context switches into this address. @@ -975,10 +769,6 @@ END(interrupt) call \func .endm -/* - * Interrupt entry/exit should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" /* * The interrupt stubs push (~vector+0x80) onto the stack and * then jump to common_interrupt. @@ -1040,8 +830,18 @@ restore_args: RESTORE_ARGS 1,8,1 irq_return: + /* + * Are we returning to a stack segment from the LDT? Note: in + * 64-bit mode SS:RSP on the exception stack is always valid. + */ +#ifdef CONFIG_X86_ESPFIX64 + testb $4,(SS-RIP)(%rsp) + jnz irq_return_ldt +#endif + +irq_return_iret: INTERRUPT_RETURN - _ASM_EXTABLE(irq_return, bad_iret) + _ASM_EXTABLE(irq_return_iret, bad_iret) #ifdef CONFIG_PARAVIRT ENTRY(native_iret) @@ -1049,6 +849,32 @@ ENTRY(native_iret) _ASM_EXTABLE(native_iret, bad_iret) #endif +#ifdef CONFIG_X86_ESPFIX64 +irq_return_ldt: + pushq_cfi %rax + pushq_cfi %rdi + SWAPGS + movq PER_CPU_VAR(espfix_waddr),%rdi + movq %rax,(0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp),%rax /* RIP */ + movq %rax,(1*8)(%rdi) + movq (3*8)(%rsp),%rax /* CS */ + movq %rax,(2*8)(%rdi) + movq (4*8)(%rsp),%rax /* RFLAGS */ + movq %rax,(3*8)(%rdi) + movq (6*8)(%rsp),%rax /* SS */ + movq %rax,(5*8)(%rdi) + movq (5*8)(%rsp),%rax /* RSP */ + movq %rax,(4*8)(%rdi) + andl $0xffff0000,%eax + popq_cfi %rdi + orq PER_CPU_VAR(espfix_stack),%rax + SWAPGS + movq %rax,%rsp + popq_cfi %rax + jmp irq_return_iret +#endif + .section .fixup,"ax" bad_iret: /* @@ -1110,13 +936,44 @@ ENTRY(retint_kernel) call preempt_schedule_irq jmp exit_intr #endif - CFI_ENDPROC END(common_interrupt) -/* - * End of kprobes section - */ - .popsection + + /* + * If IRET takes a fault on the espfix stack, then we + * end up promoting it to a doublefault. In that case, + * modify the stack to make it look like we just entered + * the #GP handler from user space, similar to bad_iret. + */ +#ifdef CONFIG_X86_ESPFIX64 + ALIGN +__do_double_fault: + XCPT_FRAME 1 RDI+8 + movq RSP(%rdi),%rax /* Trap on the espfix stack? */ + sarq $PGDIR_SHIFT,%rax + cmpl $ESPFIX_PGD_ENTRY,%eax + jne do_double_fault /* No, just deliver the fault */ + cmpl $__KERNEL_CS,CS(%rdi) + jne do_double_fault + movq RIP(%rdi),%rax + cmpq $irq_return_iret,%rax +#ifdef CONFIG_PARAVIRT + je 1f + cmpq $native_iret,%rax +#endif + jne do_double_fault /* This shouldn't happen... */ +1: + movq PER_CPU_VAR(kernel_stack),%rax + subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */ + movq %rax,RSP(%rdi) + movq $0,(%rax) /* Missing (lost) #GP error code */ + movq $general_protection,RIP(%rdi) + retq + CFI_ENDPROC +END(__do_double_fault) +#else +# define __do_double_fault do_double_fault +#endif /* * APIC interrupts. @@ -1203,125 +1060,100 @@ apicinterrupt IRQ_WORK_VECTOR \ /* * Exception entry points. */ -.macro zeroentry sym do_sym -ENTRY(\sym) - INTR_FRAME - ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 - call error_entry - DEFAULT_FRAME 0 - movq %rsp,%rdi /* pt_regs pointer */ - xorl %esi,%esi /* no error code */ - call \do_sym - jmp error_exit /* %ebx: no swapgs flag */ - CFI_ENDPROC -END(\sym) -.endm +#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) -.macro paranoidzeroentry sym do_sym +.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) - INTR_FRAME - ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 - call save_paranoid - TRACE_IRQS_OFF - movq %rsp,%rdi /* pt_regs pointer */ - xorl %esi,%esi /* no error code */ - call \do_sym - jmp paranoid_exit /* %ebx: no swapgs flag */ - CFI_ENDPROC -END(\sym) -.endm + /* Sanity check */ + .if \shift_ist != -1 && \paranoid == 0 + .error "using shift_ist requires paranoid=1" + .endif -#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) -.macro paranoidzeroentry_ist sym do_sym ist -ENTRY(\sym) + .if \has_error_code + XCPT_FRAME + .else INTR_FRAME - ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 - call save_paranoid - TRACE_IRQS_OFF_DEBUG - movq %rsp,%rdi /* pt_regs pointer */ - xorl %esi,%esi /* no error code */ - subq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) - call \do_sym - addq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) - jmp paranoid_exit /* %ebx: no swapgs flag */ - CFI_ENDPROC -END(\sym) -.endm + .endif -.macro errorentry sym do_sym -ENTRY(\sym) - XCPT_FRAME ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME + + .ifeq \has_error_code + pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ + .endif + subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 + + .if \paranoid + call save_paranoid + .else call error_entry + .endif + DEFAULT_FRAME 0 + + .if \paranoid + .if \shift_ist != -1 + TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ + .else + TRACE_IRQS_OFF + .endif + .endif + movq %rsp,%rdi /* pt_regs pointer */ + + .if \has_error_code movq ORIG_RAX(%rsp),%rsi /* get error code */ movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + .else + xorl %esi,%esi /* no error code */ + .endif + + .if \shift_ist != -1 + subq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist) + .endif + call \do_sym + + .if \shift_ist != -1 + addq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist) + .endif + + .if \paranoid + jmp paranoid_exit /* %ebx: no swapgs flag */ + .else jmp error_exit /* %ebx: no swapgs flag */ + .endif + CFI_ENDPROC END(\sym) .endm #ifdef CONFIG_TRACING -.macro trace_errorentry sym do_sym -errorentry trace(\sym) trace(\do_sym) -errorentry \sym \do_sym +.macro trace_idtentry sym do_sym has_error_code:req +idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code +idtentry \sym \do_sym has_error_code=\has_error_code .endm #else -.macro trace_errorentry sym do_sym -errorentry \sym \do_sym +.macro trace_idtentry sym do_sym has_error_code:req +idtentry \sym \do_sym has_error_code=\has_error_code .endm #endif - /* error code is on the stack already */ -.macro paranoiderrorentry sym do_sym -ENTRY(\sym) - XCPT_FRAME - ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 - call save_paranoid - DEFAULT_FRAME 0 - TRACE_IRQS_OFF - movq %rsp,%rdi /* pt_regs pointer */ - movq ORIG_RAX(%rsp),%rsi /* get error code */ - movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ - call \do_sym - jmp paranoid_exit /* %ebx: no swapgs flag */ - CFI_ENDPROC -END(\sym) -.endm - -zeroentry divide_error do_divide_error -zeroentry overflow do_overflow -zeroentry bounds do_bounds -zeroentry invalid_op do_invalid_op -zeroentry device_not_available do_device_not_available -paranoiderrorentry double_fault do_double_fault -zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun -errorentry invalid_TSS do_invalid_TSS -errorentry segment_not_present do_segment_not_present -zeroentry spurious_interrupt_bug do_spurious_interrupt_bug -zeroentry coprocessor_error do_coprocessor_error -errorentry alignment_check do_alignment_check -zeroentry simd_coprocessor_error do_simd_coprocessor_error +idtentry divide_error do_divide_error has_error_code=0 +idtentry overflow do_overflow has_error_code=0 +idtentry bounds do_bounds has_error_code=0 +idtentry invalid_op do_invalid_op has_error_code=0 +idtentry device_not_available do_device_not_available has_error_code=0 +idtentry double_fault __do_double_fault has_error_code=1 paranoid=1 +idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 +idtentry invalid_TSS do_invalid_TSS has_error_code=1 +idtentry segment_not_present do_segment_not_present has_error_code=1 +idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0 +idtentry coprocessor_error do_coprocessor_error has_error_code=0 +idtentry alignment_check do_alignment_check has_error_code=1 +idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 /* Reload gs selector with exception handling */ @@ -1371,7 +1203,7 @@ ENTRY(do_softirq_own_stack) END(do_softirq_own_stack) #ifdef CONFIG_XEN -zeroentry xen_hypervisor_callback xen_do_hypervisor_callback +idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 /* * A note on the "critical region" in our callback handler. @@ -1477,26 +1309,21 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ hyperv_callback_vector hyperv_vector_handler #endif /* CONFIG_HYPERV */ -/* - * Some functions should be protected against kprobes - */ - .pushsection .kprobes.text, "ax" - -paranoidzeroentry_ist debug do_debug DEBUG_STACK -paranoidzeroentry_ist int3 do_int3 DEBUG_STACK -paranoiderrorentry stack_segment do_stack_segment +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry stack_segment do_stack_segment has_error_code=1 paranoid=1 #ifdef CONFIG_XEN -zeroentry xen_debug do_debug -zeroentry xen_int3 do_int3 -errorentry xen_stack_segment do_stack_segment +idtentry xen_debug do_debug has_error_code=0 +idtentry xen_int3 do_int3 has_error_code=0 +idtentry xen_stack_segment do_stack_segment has_error_code=1 #endif -errorentry general_protection do_general_protection -trace_errorentry page_fault do_page_fault +idtentry general_protection do_general_protection has_error_code=1 +trace_idtentry page_fault do_page_fault has_error_code=1 #ifdef CONFIG_KVM_GUEST -errorentry async_page_fault do_async_page_fault +idtentry async_page_fault do_async_page_fault has_error_code=1 #endif #ifdef CONFIG_X86_MCE -paranoidzeroentry machine_check *machine_check_vector(%rip) +idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) #endif /* @@ -1601,7 +1428,7 @@ error_sti: */ error_kernelspace: incl %ebx - leaq irq_return(%rip),%rcx + leaq irq_return_iret(%rip),%rcx cmpq %rcx,RIP+8(%rsp) je error_swapgs movl %ecx,%eax /* zero extend */ @@ -1898,7 +1725,3 @@ ENTRY(ignore_sysret) CFI_ENDPROC END(ignore_sysret) -/* - * End of kprobes section - */ - .popsection diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c new file mode 100644 index 0000000..6afbb16 --- /dev/null +++ b/arch/x86/kernel/espfix_64.c @@ -0,0 +1,209 @@ +/* ----------------------------------------------------------------------- * + * + * Copyright 2014 Intel Corporation; author: H. Peter Anvin + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * ----------------------------------------------------------------------- */ + +/* + * The IRET instruction, when returning to a 16-bit segment, only + * restores the bottom 16 bits of the user space stack pointer. This + * causes some 16-bit software to break, but it also leaks kernel state + * to user space. + * + * This works around this by creating percpu "ministacks", each of which + * is mapped 2^16 times 64K apart. When we detect that the return SS is + * on the LDT, we copy the IRET frame to the ministack and use the + * relevant alias to return to userspace. The ministacks are mapped + * readonly, so if the IRET fault we promote #GP to #DF which is an IST + * vector and thus has its own stack; we then do the fixup in the #DF + * handler. + * + * This file sets up the ministacks and the related page tables. The + * actual ministack invocation is in entry_64.S. + */ + +#include <linux/init.h> +#include <linux/init_task.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/gfp.h> +#include <linux/random.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/setup.h> +#include <asm/espfix.h> + +/* + * Note: we only need 6*8 = 48 bytes for the espfix stack, but round + * it up to a cache line to avoid unnecessary sharing. + */ +#define ESPFIX_STACK_SIZE (8*8UL) +#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) + +/* There is address space for how many espfix pages? */ +#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) + +#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) +#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS +# error "Need more than one PGD for the ESPFIX hack" +#endif + +#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) + +/* This contains the *bottom* address of the espfix stack */ +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +/* Initialization mutex - should this be a spinlock? */ +static DEFINE_MUTEX(espfix_init_mutex); + +/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */ +#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE) +static void *espfix_pages[ESPFIX_MAX_PAGES]; + +static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD] + __aligned(PAGE_SIZE); + +static unsigned int page_random, slot_random; + +/* + * This returns the bottom address of the espfix stack for a specific CPU. + * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case + * we have to account for some amount of padding at the end of each page. + */ +static inline unsigned long espfix_base_addr(unsigned int cpu) +{ + unsigned long page, slot; + unsigned long addr; + + page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random; + slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE; + addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE); + addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16); + addr += ESPFIX_BASE_ADDR; + return addr; +} + +#define PTE_STRIDE (65536/PAGE_SIZE) +#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE) +#define ESPFIX_PMD_CLONES PTRS_PER_PMD +#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES)) + +#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX) + +static void init_espfix_random(void) +{ + unsigned long rand; + + /* + * This is run before the entropy pools are initialized, + * but this is hopefully better than nothing. + */ + if (!arch_get_random_long(&rand)) { + /* The constant is an arbitrary large prime */ + rdtscll(rand); + rand *= 0xc345c6b72fd16123UL; + } + + slot_random = rand % ESPFIX_STACKS_PER_PAGE; + page_random = (rand / ESPFIX_STACKS_PER_PAGE) + & (ESPFIX_PAGE_SPACE - 1); +} + +void __init init_espfix_bsp(void) +{ + pgd_t *pgd_p; + pteval_t ptemask; + + ptemask = __supported_pte_mask; + + /* Install the espfix pud into the kernel page directory */ + pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; + pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); + + /* Randomize the locations */ + init_espfix_random(); + + /* The rest is the same as for any other processor */ + init_espfix_ap(); +} + +void init_espfix_ap(void) +{ + unsigned int cpu, page; + unsigned long addr; + pud_t pud, *pud_p; + pmd_t pmd, *pmd_p; + pte_t pte, *pte_p; + int n; + void *stack_page; + pteval_t ptemask; + + /* We only have to do this once... */ + if (likely(this_cpu_read(espfix_stack))) + return; /* Already initialized */ + + cpu = smp_processor_id(); + addr = espfix_base_addr(cpu); + page = cpu/ESPFIX_STACKS_PER_PAGE; + + /* Did another CPU already set this up? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (likely(stack_page)) + goto done; + + mutex_lock(&espfix_init_mutex); + + /* Did we race on the lock? */ + stack_page = ACCESS_ONCE(espfix_pages[page]); + if (stack_page) + goto unlock_done; + + ptemask = __supported_pte_mask; + + pud_p = &espfix_pud_page[pud_index(addr)]; + pud = *pud_p; + if (!pud_present(pud)) { + pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); + pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pud(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PUD_CLONES; n++) + set_pud(&pud_p[n], pud); + } + + pmd_p = pmd_offset(&pud, addr); + pmd = *pmd_p; + if (!pmd_present(pmd)) { + pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); + pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); + paravirt_alloc_pmd(&init_mm, __pa(pte_p) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PMD_CLONES; n++) + set_pmd(&pmd_p[n], pmd); + } + + pte_p = pte_offset_kernel(&pmd, addr); + stack_page = (void *)__get_free_page(GFP_KERNEL); + pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); + paravirt_alloc_pte(&init_mm, __pa(stack_page) >> PAGE_SHIFT); + for (n = 0; n < ESPFIX_PTE_CLONES; n++) + set_pte(&pte_p[n*PTE_STRIDE], pte); + + /* Job is done for this CPU and any CPU which shares this page */ + ACCESS_ONCE(espfix_pages[page]) = stack_page; + +unlock_done: + mutex_unlock(&espfix_init_mutex); +done: + this_cpu_write(espfix_stack, addr); + this_cpu_write(espfix_waddr, (unsigned long)stack_page + + (addr & ~PAGE_MASK)); +} diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 52819e8..cbc4a91 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -297,16 +297,7 @@ int ftrace_int3_handler(struct pt_regs *regs) static int ftrace_write(unsigned long ip, const char *val, int size) { - /* - * On x86_64, kernel text mappings are mapped read-only with - * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead - * of the kernel text mapping to modify the kernel text. - * - * For 32bit kernels, these mappings are same and we can use - * kernel identity mapping to modify code. - */ - if (within(ip, (unsigned long)_text, (unsigned long)_etext)) - ip = (unsigned long)__va(__pa_symbol(ip)); + ip = text_ip_addr(ip); if (probe_kernel_write((void *)ip, val, size)) return -EPERM; @@ -349,40 +340,14 @@ static int add_brk_on_nop(struct dyn_ftrace *rec) return add_break(rec->ip, old); } -/* - * If the record has the FTRACE_FL_REGS set, that means that it - * wants to convert to a callback that saves all regs. If FTRACE_FL_REGS - * is not not set, then it wants to convert to the normal callback. - */ -static unsigned long get_ftrace_addr(struct dyn_ftrace *rec) -{ - if (rec->flags & FTRACE_FL_REGS) - return (unsigned long)FTRACE_REGS_ADDR; - else - return (unsigned long)FTRACE_ADDR; -} - -/* - * The FTRACE_FL_REGS_EN is set when the record already points to - * a function that saves all the regs. Basically the '_EN' version - * represents the current state of the function. - */ -static unsigned long get_ftrace_old_addr(struct dyn_ftrace *rec) -{ - if (rec->flags & FTRACE_FL_REGS_EN) - return (unsigned long)FTRACE_REGS_ADDR; - else - return (unsigned long)FTRACE_ADDR; -} - static int add_breakpoints(struct dyn_ftrace *rec, int enable) { unsigned long ftrace_addr; int ret; - ret = ftrace_test_record(rec, enable); + ftrace_addr = ftrace_get_addr_curr(rec); - ftrace_addr = get_ftrace_addr(rec); + ret = ftrace_test_record(rec, enable); switch (ret) { case FTRACE_UPDATE_IGNORE: @@ -392,10 +357,7 @@ static int add_breakpoints(struct dyn_ftrace *rec, int enable) /* converting nop to call */ return add_brk_on_nop(rec); - case FTRACE_UPDATE_MODIFY_CALL_REGS: case FTRACE_UPDATE_MODIFY_CALL: - ftrace_addr = get_ftrace_old_addr(rec); - /* fall through */ case FTRACE_UPDATE_MAKE_NOP: /* converting a call to a nop */ return add_brk_on_call(rec, ftrace_addr); @@ -440,14 +402,14 @@ static int remove_breakpoint(struct dyn_ftrace *rec) * If not, don't touch the breakpoint, we make just create * a disaster. */ - ftrace_addr = get_ftrace_addr(rec); + ftrace_addr = ftrace_get_addr_new(rec); nop = ftrace_call_replace(ip, ftrace_addr); if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) == 0) goto update; /* Check both ftrace_addr and ftrace_old_addr */ - ftrace_addr = get_ftrace_old_addr(rec); + ftrace_addr = ftrace_get_addr_curr(rec); nop = ftrace_call_replace(ip, ftrace_addr); if (memcmp(&ins[1], &nop[1], MCOUNT_INSN_SIZE - 1) != 0) @@ -491,13 +453,12 @@ static int add_update(struct dyn_ftrace *rec, int enable) ret = ftrace_test_record(rec, enable); - ftrace_addr = get_ftrace_addr(rec); + ftrace_addr = ftrace_get_addr_new(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; - case FTRACE_UPDATE_MODIFY_CALL_REGS: case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ @@ -538,13 +499,12 @@ static int finish_update(struct dyn_ftrace *rec, int enable) ret = ftrace_update_record(rec, enable); - ftrace_addr = get_ftrace_addr(rec); + ftrace_addr = ftrace_get_addr_new(rec); switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; - case FTRACE_UPDATE_MODIFY_CALL_REGS: case FTRACE_UPDATE_MODIFY_CALL: case FTRACE_UPDATE_MAKE_CALL: /* converting nop to call */ @@ -621,8 +581,8 @@ void ftrace_replace_code(int enable) return; remove_breakpoints: + pr_warn("Failed on %s (%d):\n", report, count); ftrace_bug(ret, rec ? rec->ip : 0); - printk(KERN_WARNING "Failed on %s (%d):\n", report, count); for_ftrace_rec_iter(iter) { rec = ftrace_rec_iter_record(iter); /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 068054f..eda1a86 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -172,7 +172,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - if (console_loglevel == 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) early_printk("Kernel alive\n"); clear_page(init_level4_pgt); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 4177bfb..319bcb9 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -74,9 +74,6 @@ static inline void hpet_writel(unsigned int d, unsigned int a) static inline void hpet_set_mapping(void) { hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE); -#ifdef CONFIG_X86_64 - __set_fixmap(VSYSCALL_HPET, hpet_address, PAGE_KERNEL_VVAR_NOCACHE); -#endif } static inline void hpet_clear_mapping(void) @@ -479,7 +476,7 @@ static int hpet_msi_next_event(unsigned long delta, static int hpet_setup_msi_irq(unsigned int irq) { if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) { - destroy_irq(irq); + irq_free_hwirq(irq); return -EINVAL; } return 0; @@ -487,9 +484,8 @@ static int hpet_setup_msi_irq(unsigned int irq) static int hpet_assign_irq(struct hpet_dev *dev) { - unsigned int irq; + unsigned int irq = irq_alloc_hwirq(-1); - irq = create_irq_nr(0, -1); if (!irq) return -EINVAL; diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c index a67b47c..5f9cf20 100644 --- a/arch/x86/kernel/hw_breakpoint.c +++ b/arch/x86/kernel/hw_breakpoint.c @@ -32,7 +32,6 @@ #include <linux/irqflags.h> #include <linux/notifier.h> #include <linux/kallsyms.h> -#include <linux/kprobes.h> #include <linux/percpu.h> #include <linux/kdebug.h> #include <linux/kernel.h> @@ -424,7 +423,7 @@ EXPORT_SYMBOL_GPL(hw_breakpoint_restore); * NOTIFY_STOP returned for all other cases * */ -static int __kprobes hw_breakpoint_handler(struct die_args *args) +static int hw_breakpoint_handler(struct die_args *args) { int i, cpu, rc = NOTIFY_STOP; struct perf_event *bp; @@ -511,7 +510,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args) /* * Handle debug exception notifications. */ -int __kprobes hw_breakpoint_exceptions_notify( +int hw_breakpoint_exceptions_notify( struct notifier_block *unused, unsigned long val, void *data) { if (val != DIE_DEBUG) diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 2e977b5..8af81710 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -299,13 +299,31 @@ static void unmask_8259A(void) static void init_8259A(int auto_eoi) { unsigned long flags; + unsigned char probe_val = ~(1 << PIC_CASCADE_IR); + unsigned char new_val; i8259A_auto_eoi = auto_eoi; raw_spin_lock_irqsave(&i8259A_lock, flags); - outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ + /* + * Check to see if we have a PIC. + * Mask all except the cascade and read + * back the value we just wrote. If we don't + * have a PIC, we will read 0xff as opposed to the + * value we wrote. + */ outb(0xff, PIC_SLAVE_IMR); /* mask all of 8259A-2 */ + outb(probe_val, PIC_MASTER_IMR); + new_val = inb(PIC_MASTER_IMR); + if (new_val != probe_val) { + printk(KERN_INFO "Using NULL legacy PIC\n"); + legacy_pic = &null_legacy_pic; + raw_spin_unlock_irqrestore(&i8259A_lock, flags); + return; + } + + outb(0xff, PIC_MASTER_IMR); /* mask all of 8259A-1 */ /* * outb_pic - this has to work on a wide range of PC hardware. diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c index c3aae66..d30acdc 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/kernel/iosf_mbi.c @@ -25,6 +25,9 @@ #include <asm/iosf_mbi.h> +#define PCI_DEVICE_ID_BAYTRAIL 0x0F00 +#define PCI_DEVICE_ID_QUARK_X1000 0x0958 + static DEFINE_SPINLOCK(iosf_mbi_lock); static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) @@ -177,6 +180,13 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) } EXPORT_SYMBOL(iosf_mbi_modify); +bool iosf_mbi_available(void) +{ + /* Mbi isn't hot-pluggable. No remove routine is provided */ + return mbi_pdev; +} +EXPORT_SYMBOL(iosf_mbi_available); + static int iosf_mbi_probe(struct pci_dev *pdev, const struct pci_device_id *unused) { @@ -193,7 +203,8 @@ static int iosf_mbi_probe(struct pci_dev *pdev, } static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids); diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 283a76a..922d285 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -17,6 +17,7 @@ #include <asm/idle.h> #include <asm/mce.h> #include <asm/hw_irq.h> +#include <asm/desc.h> #define CREATE_TRACE_POINTS #include <asm/trace/irq_vectors.h> @@ -334,10 +335,17 @@ int check_irq_vectors_for_cpu_disable(void) for_each_online_cpu(cpu) { if (cpu == this_cpu) continue; - for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; - vector++) { - if (per_cpu(vector_irq, cpu)[vector] < 0) - count++; + /* + * We scan from FIRST_EXTERNAL_VECTOR to first system + * vector. If the vector is marked in the used vectors + * bitmap or an irq is assigned to it, we don't count + * it as available. + */ + for (vector = FIRST_EXTERNAL_VECTOR; + vector < first_system_vector; vector++) { + if (!test_bit(vector, used_vectors) && + per_cpu(vector_irq, cpu)[vector] < 0) + count++; } } @@ -357,6 +365,7 @@ void fixup_irqs(void) struct irq_desc *desc; struct irq_data *data; struct irq_chip *chip; + int ret; for_each_irq_desc(irq, desc) { int break_affinity = 0; @@ -395,10 +404,14 @@ void fixup_irqs(void) if (!irqd_can_move_in_process_context(data) && chip->irq_mask) chip->irq_mask(data); - if (chip->irq_set_affinity) - chip->irq_set_affinity(data, affinity, true); - else if (!(warned++)) - set_affinity = 0; + if (chip->irq_set_affinity) { + ret = chip->irq_set_affinity(data, affinity, true); + if (ret == -ENOSPC) + pr_crit("IRQ %d set affinity failed because there are no available vectors. The device assigned to this IRQ is unstable.\n", irq); + } else { + if (!(warned++)) + set_affinity = 0; + } /* * We unmask if the irq was not marked masked by the diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 61b17dc..7596df6 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -112,7 +112,8 @@ struct kretprobe_blackpoint kretprobe_blacklist[] = { const int kretprobe_blacklist_size = ARRAY_SIZE(kretprobe_blacklist); -static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) +static nokprobe_inline void +__synthesize_relative_insn(void *from, void *to, u8 op) { struct __arch_relative_insn { u8 op; @@ -125,21 +126,23 @@ static void __kprobes __synthesize_relative_insn(void *from, void *to, u8 op) } /* Insert a jump instruction at address 'from', which jumps to address 'to'.*/ -void __kprobes synthesize_reljump(void *from, void *to) +void synthesize_reljump(void *from, void *to) { __synthesize_relative_insn(from, to, RELATIVEJUMP_OPCODE); } +NOKPROBE_SYMBOL(synthesize_reljump); /* Insert a call instruction at address 'from', which calls address 'to'.*/ -void __kprobes synthesize_relcall(void *from, void *to) +void synthesize_relcall(void *from, void *to) { __synthesize_relative_insn(from, to, RELATIVECALL_OPCODE); } +NOKPROBE_SYMBOL(synthesize_relcall); /* * Skip the prefixes of the instruction. */ -static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) +static kprobe_opcode_t *skip_prefixes(kprobe_opcode_t *insn) { insn_attr_t attr; @@ -154,12 +157,13 @@ static kprobe_opcode_t *__kprobes skip_prefixes(kprobe_opcode_t *insn) #endif return insn; } +NOKPROBE_SYMBOL(skip_prefixes); /* * Returns non-zero if opcode is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -int __kprobes can_boost(kprobe_opcode_t *opcodes) +int can_boost(kprobe_opcode_t *opcodes) { kprobe_opcode_t opcode; kprobe_opcode_t *orig_opcodes = opcodes; @@ -260,7 +264,7 @@ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long add } /* Check if paddr is at an instruction boundary */ -static int __kprobes can_probe(unsigned long paddr) +static int can_probe(unsigned long paddr) { unsigned long addr, __addr, offset = 0; struct insn insn; @@ -299,7 +303,7 @@ static int __kprobes can_probe(unsigned long paddr) /* * Returns non-zero if opcode modifies the interrupt flag. */ -static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) +static int is_IF_modifier(kprobe_opcode_t *insn) { /* Skip prefixes */ insn = skip_prefixes(insn); @@ -322,7 +326,7 @@ static int __kprobes is_IF_modifier(kprobe_opcode_t *insn) * If not, return null. * Only applicable to 64-bit x86. */ -int __kprobes __copy_instruction(u8 *dest, u8 *src) +int __copy_instruction(u8 *dest, u8 *src) { struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; @@ -365,7 +369,7 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src) return insn.length; } -static int __kprobes arch_copy_kprobe(struct kprobe *p) +static int arch_copy_kprobe(struct kprobe *p) { int ret; @@ -392,7 +396,7 @@ static int __kprobes arch_copy_kprobe(struct kprobe *p) return 0; } -int __kprobes arch_prepare_kprobe(struct kprobe *p) +int arch_prepare_kprobe(struct kprobe *p) { if (alternatives_text_reserved(p->addr, p->addr)) return -EINVAL; @@ -407,17 +411,17 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p) return arch_copy_kprobe(p); } -void __kprobes arch_arm_kprobe(struct kprobe *p) +void arch_arm_kprobe(struct kprobe *p) { text_poke(p->addr, ((unsigned char []){BREAKPOINT_INSTRUCTION}), 1); } -void __kprobes arch_disarm_kprobe(struct kprobe *p) +void arch_disarm_kprobe(struct kprobe *p) { text_poke(p->addr, &p->opcode, 1); } -void __kprobes arch_remove_kprobe(struct kprobe *p) +void arch_remove_kprobe(struct kprobe *p) { if (p->ainsn.insn) { free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1)); @@ -425,7 +429,8 @@ void __kprobes arch_remove_kprobe(struct kprobe *p) } } -static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) +static nokprobe_inline void +save_previous_kprobe(struct kprobe_ctlblk *kcb) { kcb->prev_kprobe.kp = kprobe_running(); kcb->prev_kprobe.status = kcb->kprobe_status; @@ -433,7 +438,8 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) kcb->prev_kprobe.saved_flags = kcb->kprobe_saved_flags; } -static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) +static nokprobe_inline void +restore_previous_kprobe(struct kprobe_ctlblk *kcb) { __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); kcb->kprobe_status = kcb->prev_kprobe.status; @@ -441,8 +447,9 @@ static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) kcb->kprobe_saved_flags = kcb->prev_kprobe.saved_flags; } -static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +static nokprobe_inline void +set_current_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { __this_cpu_write(current_kprobe, p); kcb->kprobe_saved_flags = kcb->kprobe_old_flags @@ -451,7 +458,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF; } -static void __kprobes clear_btf(void) +static nokprobe_inline void clear_btf(void) { if (test_thread_flag(TIF_BLOCKSTEP)) { unsigned long debugctl = get_debugctlmsr(); @@ -461,7 +468,7 @@ static void __kprobes clear_btf(void) } } -static void __kprobes restore_btf(void) +static nokprobe_inline void restore_btf(void) { if (test_thread_flag(TIF_BLOCKSTEP)) { unsigned long debugctl = get_debugctlmsr(); @@ -471,8 +478,7 @@ static void __kprobes restore_btf(void) } } -void __kprobes -arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) +void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) { unsigned long *sara = stack_addr(regs); @@ -481,9 +487,10 @@ arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; } +NOKPROBE_SYMBOL(arch_prepare_kretprobe); -static void __kprobes -setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb, int reenter) +static void setup_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) { if (setup_detour_execution(p, regs, reenter)) return; @@ -519,22 +526,24 @@ setup_singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *k else regs->ip = (unsigned long)p->ainsn.insn; } +NOKPROBE_SYMBOL(setup_singlestep); /* * We have reentered the kprobe_handler(), since another probe was hit while * within the handler. We save the original kprobes variables and just single * step on the instruction of the new probe without calling any user handlers. */ -static int __kprobes -reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) +static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { switch (kcb->kprobe_status) { case KPROBE_HIT_SSDONE: case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SS: kprobes_inc_nmissed_count(p); setup_singlestep(p, regs, kcb, 1); break; - case KPROBE_HIT_SS: + case KPROBE_REENTER: /* A probe has been hit in the codepath leading up to, or just * after, single-stepping of a probed instruction. This entire * codepath should strictly reside in .kprobes.text section. @@ -553,12 +562,13 @@ reenter_kprobe(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb return 1; } +NOKPROBE_SYMBOL(reenter_kprobe); /* * Interrupts are disabled on entry as trap3 is an interrupt gate and they * remain disabled throughout this function. */ -static int __kprobes kprobe_handler(struct pt_regs *regs) +int kprobe_int3_handler(struct pt_regs *regs) { kprobe_opcode_t *addr; struct kprobe *p; @@ -621,12 +631,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs) preempt_enable_no_resched(); return 0; } +NOKPROBE_SYMBOL(kprobe_int3_handler); /* * When a retprobed function returns, this code saves registers and * calls trampoline_handler() runs, which calls the kretprobe's handler. */ -static void __used __kprobes kretprobe_trampoline_holder(void) +static void __used kretprobe_trampoline_holder(void) { asm volatile ( ".global kretprobe_trampoline\n" @@ -657,11 +668,13 @@ static void __used __kprobes kretprobe_trampoline_holder(void) #endif " ret\n"); } +NOKPROBE_SYMBOL(kretprobe_trampoline_holder); +NOKPROBE_SYMBOL(kretprobe_trampoline); /* * Called from kretprobe_trampoline */ -__visible __used __kprobes void *trampoline_handler(struct pt_regs *regs) +__visible __used void *trampoline_handler(struct pt_regs *regs) { struct kretprobe_instance *ri = NULL; struct hlist_head *head, empty_rp; @@ -747,6 +760,7 @@ __visible __used __kprobes void *trampoline_handler(struct pt_regs *regs) } return (void *)orig_ret_address; } +NOKPROBE_SYMBOL(trampoline_handler); /* * Called after single-stepping. p->addr is the address of the @@ -775,8 +789,8 @@ __visible __used __kprobes void *trampoline_handler(struct pt_regs *regs) * jump instruction after the copied instruction, that jumps to the next * instruction after the probepoint. */ -static void __kprobes -resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb) +static void resume_execution(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { unsigned long *tos = stack_addr(regs); unsigned long copy_ip = (unsigned long)p->ainsn.insn; @@ -851,12 +865,13 @@ resume_execution(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *k no_change: restore_btf(); } +NOKPROBE_SYMBOL(resume_execution); /* * Interrupts are disabled on entry as trap1 is an interrupt gate and they * remain disabled throughout this function. */ -static int __kprobes post_kprobe_handler(struct pt_regs *regs) +int kprobe_debug_handler(struct pt_regs *regs) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -891,8 +906,9 @@ out: return 1; } +NOKPROBE_SYMBOL(kprobe_debug_handler); -int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) +int kprobe_fault_handler(struct pt_regs *regs, int trapnr) { struct kprobe *cur = kprobe_running(); struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -949,12 +965,13 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr) return 0; } +NOKPROBE_SYMBOL(kprobe_fault_handler); /* * Wrapper routine for handling exceptions. */ -int __kprobes -kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *data) +int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, + void *data) { struct die_args *args = data; int ret = NOTIFY_DONE; @@ -962,22 +979,7 @@ kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *d if (args->regs && user_mode_vm(args->regs)) return ret; - switch (val) { - case DIE_INT3: - if (kprobe_handler(args->regs)) - ret = NOTIFY_STOP; - break; - case DIE_DEBUG: - if (post_kprobe_handler(args->regs)) { - /* - * Reset the BS bit in dr6 (pointed by args->err) to - * denote completion of processing - */ - (*(unsigned long *)ERR_PTR(args->err)) &= ~DR_STEP; - ret = NOTIFY_STOP; - } - break; - case DIE_GPF: + if (val == DIE_GPF) { /* * To be potentially processing a kprobe fault and to * trust the result from kprobe_running(), we have @@ -986,14 +988,12 @@ kprobe_exceptions_notify(struct notifier_block *self, unsigned long val, void *d if (!preemptible() && kprobe_running() && kprobe_fault_handler(args->regs, args->trapnr)) ret = NOTIFY_STOP; - break; - default: - break; } return ret; } +NOKPROBE_SYMBOL(kprobe_exceptions_notify); -int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) { struct jprobe *jp = container_of(p, struct jprobe, kp); unsigned long addr; @@ -1017,8 +1017,9 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) regs->ip = (unsigned long)(jp->entry); return 1; } +NOKPROBE_SYMBOL(setjmp_pre_handler); -void __kprobes jprobe_return(void) +void jprobe_return(void) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); @@ -1034,8 +1035,10 @@ void __kprobes jprobe_return(void) " nop \n"::"b" (kcb->jprobe_saved_sp):"memory"); } +NOKPROBE_SYMBOL(jprobe_return); +NOKPROBE_SYMBOL(jprobe_return_end); -int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); u8 *addr = (u8 *) (regs->ip - 1); @@ -1063,13 +1066,22 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) } return 0; } +NOKPROBE_SYMBOL(longjmp_break_handler); + +bool arch_within_kprobe_blacklist(unsigned long addr) +{ + return (addr >= (unsigned long)__kprobes_text_start && + addr < (unsigned long)__kprobes_text_end) || + (addr >= (unsigned long)__entry_text_start && + addr < (unsigned long)__entry_text_end); +} int __init arch_init_kprobes(void) { return 0; } -int __kprobes arch_trampoline_kprobe(struct kprobe *p) +int arch_trampoline_kprobe(struct kprobe *p) { return 0; } diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index 23ef5c5..717b02a 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -25,8 +25,9 @@ #include "common.h" -static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +static nokprobe_inline +int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { /* * Emulate singlestep (and also recover regs->ip) @@ -41,18 +42,19 @@ static int __skip_singlestep(struct kprobe *p, struct pt_regs *regs, return 1; } -int __kprobes skip_singlestep(struct kprobe *p, struct pt_regs *regs, - struct kprobe_ctlblk *kcb) +int skip_singlestep(struct kprobe *p, struct pt_regs *regs, + struct kprobe_ctlblk *kcb) { if (kprobe_ftrace(p)) return __skip_singlestep(p, regs, kcb); else return 0; } +NOKPROBE_SYMBOL(skip_singlestep); /* Ftrace callback handler for kprobes */ -void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, - struct ftrace_ops *ops, struct pt_regs *regs) +void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) { struct kprobe *p; struct kprobe_ctlblk *kcb; @@ -84,8 +86,9 @@ void __kprobes kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, end: local_irq_restore(flags); } +NOKPROBE_SYMBOL(kprobe_ftrace_handler); -int __kprobes arch_prepare_kprobe_ftrace(struct kprobe *p) +int arch_prepare_kprobe_ftrace(struct kprobe *p) { p->ainsn.insn = NULL; p->ainsn.boostable = -1; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 898160b..f304773 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -77,7 +77,7 @@ found: } /* Insert a move instruction which sets a pointer to eax/rdi (1st arg). */ -static void __kprobes synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) +static void synthesize_set_arg1(kprobe_opcode_t *addr, unsigned long val) { #ifdef CONFIG_X86_64 *addr++ = 0x48; @@ -138,7 +138,8 @@ asm ( #define INT3_SIZE sizeof(kprobe_opcode_t) /* Optimized kprobe call back function: called from optinsn */ -static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) +static void +optimized_callback(struct optimized_kprobe *op, struct pt_regs *regs) { struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); unsigned long flags; @@ -168,8 +169,9 @@ static void __kprobes optimized_callback(struct optimized_kprobe *op, struct pt_ } local_irq_restore(flags); } +NOKPROBE_SYMBOL(optimized_callback); -static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) +static int copy_optimized_instructions(u8 *dest, u8 *src) { int len = 0, ret; @@ -189,7 +191,7 @@ static int __kprobes copy_optimized_instructions(u8 *dest, u8 *src) } /* Check whether insn is indirect jump */ -static int __kprobes insn_is_indirect_jump(struct insn *insn) +static int insn_is_indirect_jump(struct insn *insn) { return ((insn->opcode.bytes[0] == 0xff && (X86_MODRM_REG(insn->modrm.value) & 6) == 4) || /* Jump */ @@ -224,7 +226,7 @@ static int insn_jump_into_range(struct insn *insn, unsigned long start, int len) } /* Decode whole function to ensure any instructions don't jump into target */ -static int __kprobes can_optimize(unsigned long paddr) +static int can_optimize(unsigned long paddr) { unsigned long addr, size = 0, offset = 0; struct insn insn; @@ -275,7 +277,7 @@ static int __kprobes can_optimize(unsigned long paddr) } /* Check optimized_kprobe can actually be optimized. */ -int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) +int arch_check_optimized_kprobe(struct optimized_kprobe *op) { int i; struct kprobe *p; @@ -290,15 +292,15 @@ int __kprobes arch_check_optimized_kprobe(struct optimized_kprobe *op) } /* Check the addr is within the optimized instructions. */ -int __kprobes -arch_within_optimized_kprobe(struct optimized_kprobe *op, unsigned long addr) +int arch_within_optimized_kprobe(struct optimized_kprobe *op, + unsigned long addr) { return ((unsigned long)op->kp.addr <= addr && (unsigned long)op->kp.addr + op->optinsn.size > addr); } /* Free optimized instruction slot */ -static __kprobes +static void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) { if (op->optinsn.insn) { @@ -308,7 +310,7 @@ void __arch_remove_optimized_kprobe(struct optimized_kprobe *op, int dirty) } } -void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) +void arch_remove_optimized_kprobe(struct optimized_kprobe *op) { __arch_remove_optimized_kprobe(op, 1); } @@ -318,7 +320,7 @@ void __kprobes arch_remove_optimized_kprobe(struct optimized_kprobe *op) * Target instructions MUST be relocatable (checked inside) * This is called when new aggr(opt)probe is allocated or reused. */ -int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) +int arch_prepare_optimized_kprobe(struct optimized_kprobe *op) { u8 *buf; int ret; @@ -372,7 +374,7 @@ int __kprobes arch_prepare_optimized_kprobe(struct optimized_kprobe *op) * Replace breakpoints (int3) with relative jumps. * Caller must call with locking kprobe_mutex and text_mutex. */ -void __kprobes arch_optimize_kprobes(struct list_head *oplist) +void arch_optimize_kprobes(struct list_head *oplist) { struct optimized_kprobe *op, *tmp; u8 insn_buf[RELATIVEJUMP_SIZE]; @@ -398,7 +400,7 @@ void __kprobes arch_optimize_kprobes(struct list_head *oplist) } /* Replace a relative jump with a breakpoint (int3). */ -void __kprobes arch_unoptimize_kprobe(struct optimized_kprobe *op) +void arch_unoptimize_kprobe(struct optimized_kprobe *op) { u8 insn_buf[RELATIVEJUMP_SIZE]; @@ -424,8 +426,7 @@ extern void arch_unoptimize_kprobes(struct list_head *oplist, } } -int __kprobes -setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) +int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) { struct optimized_kprobe *op; @@ -441,3 +442,4 @@ setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter) } return 0; } +NOKPROBE_SYMBOL(setup_detour_execution); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 0331cb3..3dd8e2c 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -251,15 +251,16 @@ u32 kvm_read_and_reset_pf_reason(void) return reason; } EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason); +NOKPROBE_SYMBOL(kvm_read_and_reset_pf_reason); -dotraplinkage void __kprobes +dotraplinkage void do_async_page_fault(struct pt_regs *regs, unsigned long error_code) { enum ctx_state prev_state; switch (kvm_read_and_reset_pf_reason()) { default: - do_page_fault(regs, error_code); + trace_do_page_fault(regs, error_code); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ @@ -276,6 +277,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) break; } } +NOKPROBE_SYMBOL(do_async_page_fault); static void __init paravirt_ops_setup(void) { diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index dcbbaa1..c37886d 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -20,8 +20,6 @@ #include <asm/mmu_context.h> #include <asm/syscalls.h> -int sysctl_ldt16 = 0; - #ifdef CONFIG_SMP static void flush_ldt(void *current_mm) { @@ -231,16 +229,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) } } - /* - * On x86-64 we do not support 16-bit segments due to - * IRET leaking the high bits of the kernel stack address. - */ -#ifdef CONFIG_X86_64 - if (!ldt_info.seg_32bit && !sysctl_ldt16) { + if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { error = -EINVAL; goto out_unlock; } -#endif fill_ldt(&ldt, &ldt_info); if (oldmode) diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S new file mode 100644 index 0000000..c050a01 --- /dev/null +++ b/arch/x86/kernel/mcount_64.S @@ -0,0 +1,217 @@ +/* + * linux/arch/x86_64/mcount_64.S + * + * Copyright (C) 2014 Steven Rostedt, Red Hat Inc + */ + +#include <linux/linkage.h> +#include <asm/ptrace.h> +#include <asm/ftrace.h> + + + .code64 + .section .entry.text, "ax" + + +#ifdef CONFIG_FUNCTION_TRACER + +#ifdef CC_USING_FENTRY +# define function_hook __fentry__ +#else +# define function_hook mcount +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE + +ENTRY(function_hook) + retq +END(function_hook) + +/* skip is set if stack has been adjusted */ +.macro ftrace_caller_setup skip=0 + MCOUNT_SAVE_FRAME \skip + + /* Load the ftrace_ops into the 3rd parameter */ + movq function_trace_op(%rip), %rdx + + /* Load ip into the first parameter */ + movq RIP(%rsp), %rdi + subq $MCOUNT_INSN_SIZE, %rdi + /* Load the parent_ip into the second parameter */ +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else + movq 8(%rbp), %rsi +#endif +.endm + +ENTRY(ftrace_caller) + /* Check if tracing was disabled (quick check) */ + cmpl $0, function_trace_stop + jne ftrace_stub + + ftrace_caller_setup + /* regs go into 4th parameter (but make it NULL) */ + movq $0, %rcx + +GLOBAL(ftrace_call) + call ftrace_stub + + MCOUNT_RESTORE_FRAME +ftrace_return: + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +GLOBAL(ftrace_graph_call) + jmp ftrace_stub +#endif + +GLOBAL(ftrace_stub) + retq +END(ftrace_caller) + +ENTRY(ftrace_regs_caller) + /* Save the current flags before compare (in SS location)*/ + pushfq + + /* Check if tracing was disabled (quick check) */ + cmpl $0, function_trace_stop + jne ftrace_restore_flags + + /* skip=8 to skip flags saved in SS */ + ftrace_caller_setup 8 + + /* Save the rest of pt_regs */ + movq %r15, R15(%rsp) + movq %r14, R14(%rsp) + movq %r13, R13(%rsp) + movq %r12, R12(%rsp) + movq %r11, R11(%rsp) + movq %r10, R10(%rsp) + movq %rbp, RBP(%rsp) + movq %rbx, RBX(%rsp) + /* Copy saved flags */ + movq SS(%rsp), %rcx + movq %rcx, EFLAGS(%rsp) + /* Kernel segments */ + movq $__KERNEL_DS, %rcx + movq %rcx, SS(%rsp) + movq $__KERNEL_CS, %rcx + movq %rcx, CS(%rsp) + /* Stack - skipping return address */ + leaq SS+16(%rsp), %rcx + movq %rcx, RSP(%rsp) + + /* regs go into 4th parameter */ + leaq (%rsp), %rcx + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + /* Copy flags back to SS, to restore them */ + movq EFLAGS(%rsp), %rax + movq %rax, SS(%rsp) + + /* Handlers can change the RIP */ + movq RIP(%rsp), %rax + movq %rax, SS+8(%rsp) + + /* restore the rest of pt_regs */ + movq R15(%rsp), %r15 + movq R14(%rsp), %r14 + movq R13(%rsp), %r13 + movq R12(%rsp), %r12 + movq R10(%rsp), %r10 + movq RBP(%rsp), %rbp + movq RBX(%rsp), %rbx + + /* skip=8 to skip flags saved in SS */ + MCOUNT_RESTORE_FRAME 8 + + /* Restore flags */ + popfq + + jmp ftrace_return +ftrace_restore_flags: + popfq + jmp ftrace_stub + +END(ftrace_regs_caller) + + +#else /* ! CONFIG_DYNAMIC_FTRACE */ + +ENTRY(function_hook) + cmpl $0, function_trace_stop + jne ftrace_stub + + cmpq $ftrace_stub, ftrace_trace_function + jnz trace + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + cmpq $ftrace_stub, ftrace_graph_return + jnz ftrace_graph_caller + + cmpq $ftrace_graph_entry_stub, ftrace_graph_entry + jnz ftrace_graph_caller +#endif + +GLOBAL(ftrace_stub) + retq + +trace: + MCOUNT_SAVE_FRAME + + movq RIP(%rsp), %rdi +#ifdef CC_USING_FENTRY + movq SS+16(%rsp), %rsi +#else + movq 8(%rbp), %rsi +#endif + subq $MCOUNT_INSN_SIZE, %rdi + + call *ftrace_trace_function + + MCOUNT_RESTORE_FRAME + + jmp ftrace_stub +END(function_hook) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + MCOUNT_SAVE_FRAME + +#ifdef CC_USING_FENTRY + leaq SS+16(%rsp), %rdi + movq $0, %rdx /* No framepointers needed */ +#else + leaq 8(%rbp), %rdi + movq (%rbp), %rdx +#endif + movq RIP(%rsp), %rsi + subq $MCOUNT_INSN_SIZE, %rsi + + call prepare_ftrace_return + + MCOUNT_RESTORE_FRAME + + retq +END(ftrace_graph_caller) + +GLOBAL(return_to_handler) + subq $24, %rsp + + /* Save the return values */ + movq %rax, (%rsp) + movq %rdx, 8(%rsp) + movq %rbp, %rdi + + call ftrace_return_to_handler + + movq %rax, %rdi + movq 8(%rsp), %rdx + movq (%rsp), %rax + addq $24, %rsp + jmp *%rdi +#endif diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index b4872b9..c3e985d 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -110,7 +110,7 @@ static void nmi_max_handler(struct irq_work *w) a->handler, whole_msecs, decimal_msecs); } -static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) +static int nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b) { struct nmi_desc *desc = nmi_to_desc(type); struct nmiaction *a; @@ -146,6 +146,7 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2 /* return total number of NMI events handled */ return handled; } +NOKPROBE_SYMBOL(nmi_handle); int __register_nmi_handler(unsigned int type, struct nmiaction *action) { @@ -208,7 +209,7 @@ void unregister_nmi_handler(unsigned int type, const char *name) } EXPORT_SYMBOL_GPL(unregister_nmi_handler); -static __kprobes void +static void pci_serr_error(unsigned char reason, struct pt_regs *regs) { /* check to see if anyone registered against these types of errors */ @@ -238,8 +239,9 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs) reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR; outb(reason, NMI_REASON_PORT); } +NOKPROBE_SYMBOL(pci_serr_error); -static __kprobes void +static void io_check_error(unsigned char reason, struct pt_regs *regs) { unsigned long i; @@ -269,8 +271,9 @@ io_check_error(unsigned char reason, struct pt_regs *regs) reason &= ~NMI_REASON_CLEAR_IOCHK; outb(reason, NMI_REASON_PORT); } +NOKPROBE_SYMBOL(io_check_error); -static __kprobes void +static void unknown_nmi_error(unsigned char reason, struct pt_regs *regs) { int handled; @@ -298,11 +301,12 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) pr_emerg("Dazed and confused, but trying to continue\n"); } +NOKPROBE_SYMBOL(unknown_nmi_error); static DEFINE_PER_CPU(bool, swallow_nmi); static DEFINE_PER_CPU(unsigned long, last_nmi_rip); -static __kprobes void default_do_nmi(struct pt_regs *regs) +static void default_do_nmi(struct pt_regs *regs) { unsigned char reason = 0; int handled; @@ -401,6 +405,7 @@ static __kprobes void default_do_nmi(struct pt_regs *regs) else unknown_nmi_error(reason, regs); } +NOKPROBE_SYMBOL(default_do_nmi); /* * NMIs can hit breakpoints which will cause it to lose its @@ -520,7 +525,7 @@ static inline void nmi_nesting_postprocess(void) } #endif -dotraplinkage notrace __kprobes void +dotraplinkage notrace void do_nmi(struct pt_regs *regs, long error_code) { nmi_nesting_preprocess(regs); @@ -537,6 +542,7 @@ do_nmi(struct pt_regs *regs, long error_code) /* On i386, may loop back to preprocess */ nmi_nesting_postprocess(); } +NOKPROBE_SYMBOL(do_nmi); void stop_nmi(void) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 1b10af8..548d25f 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -23,6 +23,7 @@ #include <linux/efi.h> #include <linux/bcd.h> #include <linux/highmem.h> +#include <linux/kprobes.h> #include <asm/bug.h> #include <asm/paravirt.h> @@ -389,6 +390,11 @@ __visible struct pv_cpu_ops pv_cpu_ops = { .end_context_switch = paravirt_nop, }; +/* At this point, native_get/set_debugreg has real function entries */ +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, diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index f7d0672..a25e202 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -97,12 +97,17 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_mask = dma_alloc_coherent_mask(dev, flag); - flag |= __GFP_ZERO; + flag &= ~__GFP_ZERO; again: page = NULL; /* CMA can be used only in the context which permits sleeping */ - if (flag & __GFP_WAIT) + if (flag & __GFP_WAIT) { page = dma_alloc_from_contiguous(dev, count, get_order(size)); + if (page && page_to_phys(page) + size > dma_mask) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } + } /* fallback */ if (!page) page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); @@ -120,7 +125,7 @@ again: return NULL; } - + memset(page_address(page), 0, size); *dma_addr = addr; return page_address(page); } diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 6c483ba..77dd0ad 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -14,7 +14,7 @@ #include <asm/iommu_table.h> int swiotlb __read_mostly; -static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, +void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags, struct dma_attrs *attrs) { @@ -28,11 +28,14 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } -static void x86_swiotlb_free_coherent(struct device *dev, size_t size, +void x86_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, struct dma_attrs *attrs) { - swiotlb_free_coherent(dev, size, vaddr, dma_addr); + if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr))) + swiotlb_free_coherent(dev, size, vaddr, dma_addr); + else + dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } static struct dma_map_ops swiotlb_dma_ops = { diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 898d077..ca5b02d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -413,12 +413,11 @@ void set_personality_ia32(bool x32) set_thread_flag(TIF_ADDR32); /* Mark the associated mm as containing 32-bit tasks. */ - if (current->mm) - current->mm->context.ia32_compat = 1; - if (x32) { clear_thread_flag(TIF_IA32); set_thread_flag(TIF_X32); + if (current->mm) + current->mm->context.ia32_compat = TIF_X32; current->personality &= ~READ_IMPLIES_EXEC; /* is_compat_task() uses the presence of the x32 syscall bit flag to determine compat status */ @@ -426,6 +425,8 @@ void set_personality_ia32(bool x32) } else { set_thread_flag(TIF_IA32); clear_thread_flag(TIF_X32); + if (current->mm) + current->mm->context.ia32_compat = TIF_IA32; current->personality |= force_personality32; /* Prepare the first "return" to user space */ current_thread_info()->status |= TS_COMPAT; diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 09c76d2..78a0e62 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); memblock_set_current_limit(get_max_mapped()); - dma_contiguous_reserve(0); + dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 9e5de68..a0da58d 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -298,7 +298,8 @@ __setup_frame(int sig, struct ksignal *ksig, sigset_t *set, } if (current->mm->context.vdso) - restorer = VDSO32_SYMBOL(current->mm->context.vdso, sigreturn); + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_sigreturn; else restorer = &frame->retcode; if (ksig->ka.sa.sa_flags & SA_RESTORER) @@ -361,7 +362,8 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig, save_altstack_ex(&frame->uc.uc_stack, regs->sp); /* Set up to return from userspace. */ - restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn); + restorer = current->mm->context.vdso + + selected_vdso32->sym___kernel_sigreturn; if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; put_user_ex(restorer, &frame->pretcode); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 3482693..5492798 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -244,6 +244,13 @@ static void notrace start_secondary(void *unused) check_tsc_sync_target(); /* + * Enable the espfix hack for this CPU + */ +#ifdef CONFIG_X86_ESPFIX64 + init_espfix_ap(); +#endif + + /* * We need to hold vector_lock so there the set of online cpus * does not change while we are assigning vectors to cpus. Holding * this lock ensures we don't half assign or remove an irq from a cpu. @@ -859,9 +866,6 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) /* was set by cpu_init() */ cpumask_clear_cpu(cpu, cpu_initialized_mask); - - set_cpu_present(cpu, false); - per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; } /* mark "stuck" area as not stuck */ @@ -921,7 +925,7 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle) err = do_boot_cpu(apicid, cpu, tidle); if (err) { - pr_debug("do_boot_cpu failed %d\n", err); + pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu); return -EIO; } diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f73b5d4..c6eb418 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -23,6 +23,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/ptrace.h> +#include <linux/uprobes.h> #include <linux/string.h> #include <linux/delay.h> #include <linux/errno.h> @@ -106,7 +107,7 @@ static inline void preempt_conditional_cli(struct pt_regs *regs) preempt_count_dec(); } -static int __kprobes +static nokprobe_inline int do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, struct pt_regs *regs, long error_code) { @@ -136,7 +137,38 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str, return -1; } -static void __kprobes +static siginfo_t *fill_trap_info(struct pt_regs *regs, int signr, int trapnr, + siginfo_t *info) +{ + unsigned long siaddr; + int sicode; + + switch (trapnr) { + default: + return SEND_SIG_PRIV; + + case X86_TRAP_DE: + sicode = FPE_INTDIV; + siaddr = uprobe_get_trap_addr(regs); + break; + case X86_TRAP_UD: + sicode = ILL_ILLOPN; + siaddr = uprobe_get_trap_addr(regs); + break; + case X86_TRAP_AC: + sicode = BUS_ADRALN; + siaddr = 0; + break; + } + + info->si_signo = signr; + info->si_errno = 0; + info->si_code = sicode; + info->si_addr = (void __user *)siaddr; + return info; +} + +static void do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, long error_code, siginfo_t *info) { @@ -168,60 +200,43 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, } #endif - if (info) - force_sig_info(signr, info, tsk); - else - force_sig(signr, tsk); + force_sig_info(signr, info ?: SEND_SIG_PRIV, tsk); } +NOKPROBE_SYMBOL(do_trap); -#define DO_ERROR(trapnr, signr, str, name) \ -dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ -{ \ - enum ctx_state prev_state; \ - \ - prev_state = exception_enter(); \ - if (notify_die(DIE_TRAP, str, regs, error_code, \ - trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(prev_state); \ - return; \ - } \ - conditional_sti(regs); \ - do_trap(trapnr, signr, str, regs, error_code, NULL); \ - exception_exit(prev_state); \ +static void do_error_trap(struct pt_regs *regs, long error_code, char *str, + unsigned long trapnr, int signr) +{ + enum ctx_state prev_state = exception_enter(); + siginfo_t info; + + if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, signr) != + NOTIFY_STOP) { + conditional_sti(regs); + do_trap(trapnr, signr, str, regs, error_code, + fill_trap_info(regs, signr, trapnr, &info)); + } + + exception_exit(prev_state); } -#define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ +#define DO_ERROR(trapnr, signr, str, name) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - siginfo_t info; \ - enum ctx_state prev_state; \ - \ - info.si_signo = signr; \ - info.si_errno = 0; \ - info.si_code = sicode; \ - info.si_addr = (void __user *)siaddr; \ - prev_state = exception_enter(); \ - if (notify_die(DIE_TRAP, str, regs, error_code, \ - trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(prev_state); \ - return; \ - } \ - conditional_sti(regs); \ - do_trap(trapnr, signr, str, regs, error_code, &info); \ - exception_exit(prev_state); \ + do_error_trap(regs, error_code, str, trapnr, signr); \ } -DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, regs->ip ) -DO_ERROR (X86_TRAP_OF, SIGSEGV, "overflow", overflow ) -DO_ERROR (X86_TRAP_BR, SIGSEGV, "bounds", bounds ) -DO_ERROR_INFO(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op, ILL_ILLOPN, regs->ip ) -DO_ERROR (X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun", coprocessor_segment_overrun ) -DO_ERROR (X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS ) -DO_ERROR (X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present ) +DO_ERROR(X86_TRAP_DE, SIGFPE, "divide error", divide_error) +DO_ERROR(X86_TRAP_OF, SIGSEGV, "overflow", overflow) +DO_ERROR(X86_TRAP_BR, SIGSEGV, "bounds", bounds) +DO_ERROR(X86_TRAP_UD, SIGILL, "invalid opcode", invalid_op) +DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",coprocessor_segment_overrun) +DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS) +DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present) #ifdef CONFIG_X86_32 -DO_ERROR (X86_TRAP_SS, SIGBUS, "stack segment", stack_segment ) +DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment) #endif -DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, BUS_ADRALN, 0 ) +DO_ERROR(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check) #ifdef CONFIG_X86_64 /* Runs on IST stack */ @@ -263,7 +278,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) } #endif -dotraplinkage void __kprobes +dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; @@ -305,13 +320,14 @@ do_general_protection(struct pt_regs *regs, long error_code) pr_cont("\n"); } - force_sig(SIGSEGV, tsk); + force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); exit: exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_general_protection); /* May run on IST stack. */ -dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code) +dotraplinkage void notrace do_int3(struct pt_regs *regs, long error_code) { enum ctx_state prev_state; @@ -327,13 +343,18 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co if (poke_int3_handler(regs)) return; - prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) goto exit; #endif /* CONFIG_KGDB_LOW_LEVEL_TRAP */ +#ifdef CONFIG_KPROBES + if (kprobe_int3_handler(regs)) + return; +#endif + prev_state = exception_enter(); + if (notify_die(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) goto exit; @@ -350,6 +371,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co exit: exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_int3); #ifdef CONFIG_X86_64 /* @@ -357,7 +379,7 @@ exit: * for scheduling or signal handling. The actual stack switch is done in * entry.S */ -asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) +asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs) { struct pt_regs *regs = eregs; /* Did already sync */ @@ -376,6 +398,7 @@ asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) *regs = *eregs; return regs; } +NOKPROBE_SYMBOL(sync_regs); #endif /* @@ -402,7 +425,7 @@ asmlinkage __visible __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) * * May run on IST stack. */ -dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) +dotraplinkage void do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; enum ctx_state prev_state; @@ -410,8 +433,6 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) unsigned long dr6; int si_code; - prev_state = exception_enter(); - get_debugreg(dr6, 6); /* Filter out all the reserved bits which are preset to 1 */ @@ -440,6 +461,12 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) /* Store the virtualized DR6 value */ tsk->thread.debugreg6 = dr6; +#ifdef CONFIG_KPROBES + if (kprobe_debug_handler(regs)) + goto exit; +#endif + prev_state = exception_enter(); + if (notify_die(DIE_DEBUG, "debug", regs, (long)&dr6, error_code, SIGTRAP) == NOTIFY_STOP) goto exit; @@ -482,13 +509,14 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) exit: exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_debug); /* * Note that we play around with the 'TS' bit in an attempt to get * the correct behaviour even in the presence of the asynchronous * IRQ13 behaviour */ -void math_error(struct pt_regs *regs, int error_code, int trapnr) +static void math_error(struct pt_regs *regs, int error_code, int trapnr) { struct task_struct *task = current; siginfo_t info; @@ -518,7 +546,7 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) task->thread.error_code = error_code; info.si_signo = SIGFPE; info.si_errno = 0; - info.si_addr = (void __user *)regs->ip; + info.si_addr = (void __user *)uprobe_get_trap_addr(regs); if (trapnr == X86_TRAP_MF) { unsigned short cwd, swd; /* @@ -645,7 +673,7 @@ void math_state_restore(void) */ if (unlikely(restore_fpu_checking(tsk))) { drop_init_fpu(tsk); - force_sig(SIGSEGV, tsk); + force_sig_info(SIGSEGV, SEND_SIG_PRIV, tsk); return; } @@ -653,7 +681,7 @@ void math_state_restore(void) } EXPORT_SYMBOL_GPL(math_state_restore); -dotraplinkage void __kprobes +dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code) { enum ctx_state prev_state; @@ -679,6 +707,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) #endif exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_device_not_available); #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 2ed8459..5d1cbfe 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -32,20 +32,20 @@ /* Post-execution fixups. */ -/* No fixup needed */ -#define UPROBE_FIX_NONE 0x0 - /* Adjust IP back to vicinity of actual insn */ -#define UPROBE_FIX_IP 0x1 +#define UPROBE_FIX_IP 0x01 /* Adjust the return address of a call insn */ -#define UPROBE_FIX_CALL 0x2 +#define UPROBE_FIX_CALL 0x02 /* Instruction will modify TF, don't change it */ -#define UPROBE_FIX_SETF 0x4 +#define UPROBE_FIX_SETF 0x04 -#define UPROBE_FIX_RIP_AX 0x8000 -#define UPROBE_FIX_RIP_CX 0x4000 +#define UPROBE_FIX_RIP_SI 0x08 +#define UPROBE_FIX_RIP_DI 0x10 +#define UPROBE_FIX_RIP_BX 0x20 +#define UPROBE_FIX_RIP_MASK \ + (UPROBE_FIX_RIP_SI | UPROBE_FIX_RIP_DI | UPROBE_FIX_RIP_BX) #define UPROBE_TRAP_NR UINT_MAX @@ -53,7 +53,7 @@ #define OPCODE1(insn) ((insn)->opcode.bytes[0]) #define OPCODE2(insn) ((insn)->opcode.bytes[1]) #define OPCODE3(insn) ((insn)->opcode.bytes[2]) -#define MODRM_REG(insn) X86_MODRM_REG(insn->modrm.value) +#define MODRM_REG(insn) X86_MODRM_REG((insn)->modrm.value) #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ @@ -67,6 +67,7 @@ * to keep gcc from statically optimizing it out, as variable_test_bit makes * some versions of gcc to think only *(unsigned long*) is used. */ +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) static volatile u32 good_insns_32[256 / 32] = { /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ /* ---------------------------------------------- */ @@ -89,33 +90,12 @@ static volatile u32 good_insns_32[256 / 32] = { /* ---------------------------------------------- */ /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ }; +#else +#define good_insns_32 NULL +#endif -/* Using this for both 64-bit and 32-bit apps */ -static volatile u32 good_2byte_insns[256 / 32] = { - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ - /* ---------------------------------------------- */ - W(0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1) | /* 00 */ - W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* 10 */ - W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */ - W(0x30, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */ - W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */ - W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */ - W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 60 */ - W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */ - W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */ - W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */ - W(0xa0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1) | /* a0 */ - W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* b0 */ - W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */ - W(0xd0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */ - W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* e0 */ - W(0xf0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0) /* f0 */ - /* ---------------------------------------------- */ - /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ -}; - -#ifdef CONFIG_X86_64 /* Good-instruction tables for 64-bit apps */ +#if defined(CONFIG_X86_64) static volatile u32 good_insns_64[256 / 32] = { /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ /* ---------------------------------------------- */ @@ -138,7 +118,33 @@ static volatile u32 good_insns_64[256 / 32] = { /* ---------------------------------------------- */ /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ }; +#else +#define good_insns_64 NULL #endif + +/* Using this for both 64-bit and 32-bit apps */ +static volatile u32 good_2byte_insns[256 / 32] = { + /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ + /* ---------------------------------------------- */ + W(0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1) | /* 00 */ + W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* 10 */ + W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */ + W(0x30, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */ + W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */ + W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */ + W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 60 */ + W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */ + W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */ + W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */ + W(0xa0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1) | /* a0 */ + W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* b0 */ + W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */ + W(0xd0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */ + W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* e0 */ + W(0xf0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0) /* f0 */ + /* ---------------------------------------------- */ + /* 0 1 2 3 4 5 6 7 8 9 a b c d e f */ +}; #undef W /* @@ -209,16 +215,25 @@ static bool is_prefix_bad(struct insn *insn) return false; } -static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn) +static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool x86_64) { - insn_init(insn, auprobe->insn, false); + u32 volatile *good_insns; + + insn_init(insn, auprobe->insn, x86_64); + /* has the side-effect of processing the entire instruction */ + insn_get_length(insn); + if (WARN_ON_ONCE(!insn_complete(insn))) + return -ENOEXEC; - /* Skip good instruction prefixes; reject "bad" ones. */ - insn_get_opcode(insn); if (is_prefix_bad(insn)) return -ENOTSUPP; - if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_32)) + if (x86_64) + good_insns = good_insns_64; + else + good_insns = good_insns_32; + + if (test_bit(OPCODE1(insn), (unsigned long *)good_insns)) return 0; if (insn->opcode.nbytes == 2) { @@ -229,72 +244,19 @@ static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn) return -ENOTSUPP; } -/* - * Figure out which fixups arch_uprobe_post_xol() will need to perform, and - * annotate arch_uprobe->fixups accordingly. To start with, - * arch_uprobe->fixups is either zero or it reflects rip-related fixups. - */ -static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn) +#ifdef CONFIG_X86_64 +static inline bool is_64bit_mm(struct mm_struct *mm) { - bool fix_ip = true, fix_call = false; /* defaults */ - int reg; - - insn_get_opcode(insn); /* should be a nop */ - - switch (OPCODE1(insn)) { - case 0x9d: - /* popf */ - auprobe->fixups |= UPROBE_FIX_SETF; - break; - case 0xc3: /* ret/lret */ - case 0xcb: - case 0xc2: - case 0xca: - /* ip is correct */ - fix_ip = false; - break; - case 0xe8: /* call relative - Fix return addr */ - fix_call = true; - break; - case 0x9a: /* call absolute - Fix return addr, not ip */ - fix_call = true; - fix_ip = false; - break; - case 0xff: - insn_get_modrm(insn); - reg = MODRM_REG(insn); - if (reg == 2 || reg == 3) { - /* call or lcall, indirect */ - /* Fix return addr; ip is correct. */ - fix_call = true; - fix_ip = false; - } else if (reg == 4 || reg == 5) { - /* jmp or ljmp, indirect */ - /* ip is correct. */ - fix_ip = false; - } - break; - case 0xea: /* jmp absolute -- ip is correct */ - fix_ip = false; - break; - default: - break; - } - if (fix_ip) - auprobe->fixups |= UPROBE_FIX_IP; - if (fix_call) - auprobe->fixups |= UPROBE_FIX_CALL; + return !config_enabled(CONFIG_IA32_EMULATION) || + !(mm->context.ia32_compat == TIF_IA32); } - -#ifdef CONFIG_X86_64 /* * If arch_uprobe->insn doesn't use rip-relative addressing, return * immediately. Otherwise, rewrite the instruction so that it accesses * its memory operand indirectly through a scratch register. Set - * arch_uprobe->fixups and arch_uprobe->rip_rela_target_address - * accordingly. (The contents of the scratch register will be saved - * before we single-step the modified instruction, and restored - * afterward.) + * defparam->fixups accordingly. (The contents of the scratch register + * will be saved before we single-step the modified instruction, + * and restored afterward). * * We do this because a rip-relative instruction can access only a * relatively small area (+/- 2 GB from the instruction), and the XOL @@ -305,248 +267,513 @@ static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn) * * Some useful facts about rip-relative instructions: * - * - There's always a modrm byte. + * - There's always a modrm byte with bit layout "00 reg 101". * - There's never a SIB byte. * - The displacement is always 4 bytes. + * - REX.B=1 bit in REX prefix, which normally extends r/m field, + * has no effect on rip-relative mode. It doesn't make modrm byte + * with r/m=101 refer to register 1101 = R13. */ -static void -handle_riprel_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn) +static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) { u8 *cursor; u8 reg; + u8 reg2; - if (mm->context.ia32_compat) - return; - - auprobe->rip_rela_target_address = 0x0; if (!insn_rip_relative(insn)) return; /* - * insn_rip_relative() would have decoded rex_prefix, modrm. + * insn_rip_relative() would have decoded rex_prefix, vex_prefix, modrm. * Clear REX.b bit (extension of MODRM.rm field): - * we want to encode rax/rcx, not r8/r9. + * we want to encode low numbered reg, not r8+. */ if (insn->rex_prefix.nbytes) { cursor = auprobe->insn + insn_offset_rex_prefix(insn); - *cursor &= 0xfe; /* Clearing REX.B bit */ + /* REX byte has 0100wrxb layout, clearing REX.b bit */ + *cursor &= 0xfe; + } + /* + * Similar treatment for VEX3 prefix. + * TODO: add XOP/EVEX treatment when insn decoder supports them + */ + if (insn->vex_prefix.nbytes == 3) { + /* + * vex2: c5 rvvvvLpp (has no b bit) + * vex3/xop: c4/8f rxbmmmmm wvvvvLpp + * evex: 62 rxbR00mm wvvvv1pp zllBVaaa + * (evex will need setting of both b and x since + * in non-sib encoding evex.x is 4th bit of MODRM.rm) + * Setting VEX3.b (setting because it has inverted meaning): + */ + cursor = auprobe->insn + insn_offset_vex_prefix(insn) + 1; + *cursor |= 0x20; } /* + * Convert from rip-relative addressing to register-relative addressing + * via a scratch register. + * + * This is tricky since there are insns with modrm byte + * which also use registers not encoded in modrm byte: + * [i]div/[i]mul: implicitly use dx:ax + * shift ops: implicitly use cx + * cmpxchg: implicitly uses ax + * cmpxchg8/16b: implicitly uses dx:ax and bx:cx + * Encoding: 0f c7/1 modrm + * The code below thinks that reg=1 (cx), chooses si as scratch. + * mulx: implicitly uses dx: mulx r/m,r1,r2 does r1:r2 = dx * r/m. + * First appeared in Haswell (BMI2 insn). It is vex-encoded. + * Example where none of bx,cx,dx can be used as scratch reg: + * c4 e2 63 f6 0d disp32 mulx disp32(%rip),%ebx,%ecx + * [v]pcmpistri: implicitly uses cx, xmm0 + * [v]pcmpistrm: implicitly uses xmm0 + * [v]pcmpestri: implicitly uses ax, dx, cx, xmm0 + * [v]pcmpestrm: implicitly uses ax, dx, xmm0 + * Evil SSE4.2 string comparison ops from hell. + * maskmovq/[v]maskmovdqu: implicitly uses (ds:rdi) as destination. + * Encoding: 0f f7 modrm, 66 0f f7 modrm, vex-encoded: c5 f9 f7 modrm. + * Store op1, byte-masked by op2 msb's in each byte, to (ds:rdi). + * AMD says it has no 3-operand form (vex.vvvv must be 1111) + * and that it can have only register operands, not mem + * (its modrm byte must have mode=11). + * If these restrictions will ever be lifted, + * we'll need code to prevent selection of di as scratch reg! + * + * Summary: I don't know any insns with modrm byte which + * use SI register implicitly. DI register is used only + * by one insn (maskmovq) and BX register is used + * only by one too (cmpxchg8b). + * BP is stack-segment based (may be a problem?). + * AX, DX, CX are off-limits (many implicit users). + * SP is unusable (it's stack pointer - think about "pop mem"; + * also, rsp+disp32 needs sib encoding -> insn length change). + */ + + reg = MODRM_REG(insn); /* Fetch modrm.reg */ + reg2 = 0xff; /* Fetch vex.vvvv */ + if (insn->vex_prefix.nbytes == 2) + reg2 = insn->vex_prefix.bytes[1]; + else if (insn->vex_prefix.nbytes == 3) + reg2 = insn->vex_prefix.bytes[2]; + /* + * TODO: add XOP, EXEV vvvv reading. + * + * vex.vvvv field is in bits 6-3, bits are inverted. + * But in 32-bit mode, high-order bit may be ignored. + * Therefore, let's consider only 3 low-order bits. + */ + reg2 = ((reg2 >> 3) & 0x7) ^ 0x7; + /* + * Register numbering is ax,cx,dx,bx, sp,bp,si,di, r8..r15. + * + * Choose scratch reg. Order is important: must not select bx + * if we can use si (cmpxchg8b case!) + */ + if (reg != 6 && reg2 != 6) { + reg2 = 6; + auprobe->defparam.fixups |= UPROBE_FIX_RIP_SI; + } else if (reg != 7 && reg2 != 7) { + reg2 = 7; + auprobe->defparam.fixups |= UPROBE_FIX_RIP_DI; + /* TODO (paranoia): force maskmovq to not use di */ + } else { + reg2 = 3; + auprobe->defparam.fixups |= UPROBE_FIX_RIP_BX; + } + /* * Point cursor at the modrm byte. The next 4 bytes are the * displacement. Beyond the displacement, for some instructions, * is the immediate operand. */ cursor = auprobe->insn + insn_offset_modrm(insn); - insn_get_length(insn); - /* - * Convert from rip-relative addressing to indirect addressing - * via a scratch register. Change the r/m field from 0x5 (%rip) - * to 0x0 (%rax) or 0x1 (%rcx), and squeeze out the offset field. + * Change modrm from "00 reg 101" to "10 reg reg2". Example: + * 89 05 disp32 mov %eax,disp32(%rip) becomes + * 89 86 disp32 mov %eax,disp32(%rsi) */ - reg = MODRM_REG(insn); - if (reg == 0) { - /* - * The register operand (if any) is either the A register - * (%rax, %eax, etc.) or (if the 0x4 bit is set in the - * REX prefix) %r8. In any case, we know the C register - * is NOT the register operand, so we use %rcx (register - * #1) for the scratch register. - */ - auprobe->fixups = UPROBE_FIX_RIP_CX; - /* Change modrm from 00 000 101 to 00 000 001. */ - *cursor = 0x1; - } else { - /* Use %rax (register #0) for the scratch register. */ - auprobe->fixups = UPROBE_FIX_RIP_AX; - /* Change modrm from 00 xxx 101 to 00 xxx 000 */ - *cursor = (reg << 3); - } - - /* Target address = address of next instruction + (signed) offset */ - auprobe->rip_rela_target_address = (long)insn->length + insn->displacement.value; - - /* Displacement field is gone; slide immediate field (if any) over. */ - if (insn->immediate.nbytes) { - cursor++; - memmove(cursor, cursor + insn->displacement.nbytes, insn->immediate.nbytes); - } - return; + *cursor = 0x80 | (reg << 3) | reg2; } -static int validate_insn_64bits(struct arch_uprobe *auprobe, struct insn *insn) +static inline unsigned long * +scratch_reg(struct arch_uprobe *auprobe, struct pt_regs *regs) { - insn_init(insn, auprobe->insn, true); - - /* Skip good instruction prefixes; reject "bad" ones. */ - insn_get_opcode(insn); - if (is_prefix_bad(insn)) - return -ENOTSUPP; + if (auprobe->defparam.fixups & UPROBE_FIX_RIP_SI) + return ®s->si; + if (auprobe->defparam.fixups & UPROBE_FIX_RIP_DI) + return ®s->di; + return ®s->bx; +} - if (test_bit(OPCODE1(insn), (unsigned long *)good_insns_64)) - return 0; +/* + * If we're emulating a rip-relative instruction, save the contents + * of the scratch register and store the target address in that register. + */ +static void riprel_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + if (auprobe->defparam.fixups & UPROBE_FIX_RIP_MASK) { + struct uprobe_task *utask = current->utask; + unsigned long *sr = scratch_reg(auprobe, regs); - if (insn->opcode.nbytes == 2) { - if (test_bit(OPCODE2(insn), (unsigned long *)good_2byte_insns)) - return 0; + utask->autask.saved_scratch_register = *sr; + *sr = utask->vaddr + auprobe->defparam.ilen; } - return -ENOTSUPP; } -static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn) +static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { - if (mm->context.ia32_compat) - return validate_insn_32bits(auprobe, insn); - return validate_insn_64bits(auprobe, insn); + if (auprobe->defparam.fixups & UPROBE_FIX_RIP_MASK) { + struct uprobe_task *utask = current->utask; + unsigned long *sr = scratch_reg(auprobe, regs); + + *sr = utask->autask.saved_scratch_register; + } } #else /* 32-bit: */ -static void handle_riprel_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn) +static inline bool is_64bit_mm(struct mm_struct *mm) { - /* No RIP-relative addressing on 32-bit */ + return false; } - -static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn) +/* + * No RIP-relative addressing on 32-bit + */ +static void riprel_analyze(struct arch_uprobe *auprobe, struct insn *insn) +{ +} +static void riprel_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ +} +static void riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { - return validate_insn_32bits(auprobe, insn); } #endif /* CONFIG_X86_64 */ -/** - * arch_uprobe_analyze_insn - instruction analysis including validity and fixups. - * @mm: the probed address space. - * @arch_uprobe: the probepoint information. - * @addr: virtual address at which to install the probepoint - * Return 0 on success or a -ve number on error. - */ -int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr) +struct uprobe_xol_ops { + bool (*emulate)(struct arch_uprobe *, struct pt_regs *); + int (*pre_xol)(struct arch_uprobe *, struct pt_regs *); + int (*post_xol)(struct arch_uprobe *, struct pt_regs *); + void (*abort)(struct arch_uprobe *, struct pt_regs *); +}; + +static inline int sizeof_long(void) { - int ret; - struct insn insn; + return is_ia32_task() ? 4 : 8; +} - auprobe->fixups = 0; - ret = validate_insn_bits(auprobe, mm, &insn); - if (ret != 0) - return ret; +static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + riprel_pre_xol(auprobe, regs); + return 0; +} - handle_riprel_insn(auprobe, mm, &insn); - prepare_fixups(auprobe, &insn); +static int push_ret_address(struct pt_regs *regs, unsigned long ip) +{ + unsigned long new_sp = regs->sp - sizeof_long(); + if (copy_to_user((void __user *)new_sp, &ip, sizeof_long())) + return -EFAULT; + + regs->sp = new_sp; return 0; } -#ifdef CONFIG_X86_64 /* - * If we're emulating a rip-relative instruction, save the contents - * of the scratch register and store the target address in that register. + * We have to fix things up as follows: + * + * Typically, the new ip is relative to the copied instruction. We need + * to make it relative to the original instruction (FIX_IP). Exceptions + * are return instructions and absolute or indirect jump or call instructions. + * + * If the single-stepped instruction was a call, the return address that + * is atop the stack is the address following the copied instruction. We + * need to make it the address following the original instruction (FIX_CALL). + * + * If the original instruction was a rip-relative instruction such as + * "movl %edx,0xnnnn(%rip)", we have instead executed an equivalent + * instruction using a scratch register -- e.g., "movl %edx,0xnnnn(%rsi)". + * We need to restore the contents of the scratch register + * (FIX_RIP_reg). */ -static void -pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs, - struct arch_uprobe_task *autask) -{ - if (auprobe->fixups & UPROBE_FIX_RIP_AX) { - autask->saved_scratch_register = regs->ax; - regs->ax = current->utask->vaddr; - regs->ax += auprobe->rip_rela_target_address; - } else if (auprobe->fixups & UPROBE_FIX_RIP_CX) { - autask->saved_scratch_register = regs->cx; - regs->cx = current->utask->vaddr; - regs->cx += auprobe->rip_rela_target_address; +static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + riprel_post_xol(auprobe, regs); + if (auprobe->defparam.fixups & UPROBE_FIX_IP) { + long correction = utask->vaddr - utask->xol_vaddr; + regs->ip += correction; + } else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) { + regs->sp += sizeof_long(); /* Pop incorrect return address */ + if (push_ret_address(regs, utask->vaddr + auprobe->defparam.ilen)) + return -ERESTART; } + /* popf; tell the caller to not touch TF */ + if (auprobe->defparam.fixups & UPROBE_FIX_SETF) + utask->autask.saved_tf = true; + + return 0; } -#else -static void -pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs, - struct arch_uprobe_task *autask) + +static void default_abort_op(struct arch_uprobe *auprobe, struct pt_regs *regs) { - /* No RIP-relative addressing on 32-bit */ + riprel_post_xol(auprobe, regs); } -#endif -/* - * arch_uprobe_pre_xol - prepare to execute out of line. - * @auprobe: the probepoint information. - * @regs: reflects the saved user state of current task. - */ -int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +static struct uprobe_xol_ops default_xol_ops = { + .pre_xol = default_pre_xol_op, + .post_xol = default_post_xol_op, + .abort = default_abort_op, +}; + +static bool branch_is_call(struct arch_uprobe *auprobe) { - struct arch_uprobe_task *autask; + return auprobe->branch.opc1 == 0xe8; +} - autask = ¤t->utask->autask; - autask->saved_trap_nr = current->thread.trap_nr; - current->thread.trap_nr = UPROBE_TRAP_NR; - regs->ip = current->utask->xol_vaddr; - pre_xol_rip_insn(auprobe, regs, autask); +#define CASE_COND \ + COND(70, 71, XF(OF)) \ + COND(72, 73, XF(CF)) \ + COND(74, 75, XF(ZF)) \ + COND(78, 79, XF(SF)) \ + COND(7a, 7b, XF(PF)) \ + COND(76, 77, XF(CF) || XF(ZF)) \ + COND(7c, 7d, XF(SF) != XF(OF)) \ + COND(7e, 7f, XF(ZF) || XF(SF) != XF(OF)) - autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); - regs->flags |= X86_EFLAGS_TF; - if (test_tsk_thread_flag(current, TIF_BLOCKSTEP)) - set_task_blockstep(current, false); +#define COND(op_y, op_n, expr) \ + case 0x ## op_y: DO((expr) != 0) \ + case 0x ## op_n: DO((expr) == 0) - return 0; +#define XF(xf) (!!(flags & X86_EFLAGS_ ## xf)) + +static bool is_cond_jmp_opcode(u8 opcode) +{ + switch (opcode) { + #define DO(expr) \ + return true; + CASE_COND + #undef DO + + default: + return false; + } } -/* - * This function is called by arch_uprobe_post_xol() to adjust the return - * address pushed by a call instruction executed out of line. - */ -static int adjust_ret_addr(unsigned long sp, long correction) +static bool check_jmp_cond(struct arch_uprobe *auprobe, struct pt_regs *regs) { - int rasize, ncopied; - long ra = 0; + unsigned long flags = regs->flags; - if (is_ia32_task()) - rasize = 4; - else - rasize = 8; + switch (auprobe->branch.opc1) { + #define DO(expr) \ + return expr; + CASE_COND + #undef DO - ncopied = copy_from_user(&ra, (void __user *)sp, rasize); - if (unlikely(ncopied)) - return -EFAULT; + default: /* not a conditional jmp */ + return true; + } +} - ra += correction; - ncopied = copy_to_user((void __user *)sp, &ra, rasize); - if (unlikely(ncopied)) - return -EFAULT; +#undef XF +#undef COND +#undef CASE_COND - return 0; +static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + unsigned long new_ip = regs->ip += auprobe->branch.ilen; + unsigned long offs = (long)auprobe->branch.offs; + + if (branch_is_call(auprobe)) { + /* + * If it fails we execute this (mangled, see the comment in + * branch_clear_offset) insn out-of-line. In the likely case + * this should trigger the trap, and the probed application + * should die or restart the same insn after it handles the + * signal, arch_uprobe_post_xol() won't be even called. + * + * But there is corner case, see the comment in ->post_xol(). + */ + if (push_ret_address(regs, new_ip)) + return false; + } else if (!check_jmp_cond(auprobe, regs)) { + offs = 0; + } + + regs->ip = new_ip + offs; + return true; } -#ifdef CONFIG_X86_64 -static bool is_riprel_insn(struct arch_uprobe *auprobe) +static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) { - return ((auprobe->fixups & (UPROBE_FIX_RIP_AX | UPROBE_FIX_RIP_CX)) != 0); + BUG_ON(!branch_is_call(auprobe)); + /* + * We can only get here if branch_emulate_op() failed to push the ret + * address _and_ another thread expanded our stack before the (mangled) + * "call" insn was executed out-of-line. Just restore ->sp and restart. + * We could also restore ->ip and try to call branch_emulate_op() again. + */ + regs->sp += sizeof_long(); + return -ERESTART; +} + +static void branch_clear_offset(struct arch_uprobe *auprobe, struct insn *insn) +{ + /* + * Turn this insn into "call 1f; 1:", this is what we will execute + * out-of-line if ->emulate() fails. We only need this to generate + * a trap, so that the probed task receives the correct signal with + * the properly filled siginfo. + * + * But see the comment in ->post_xol(), in the unlikely case it can + * succeed. So we need to ensure that the new ->ip can not fall into + * the non-canonical area and trigger #GP. + * + * We could turn it into (say) "pushf", but then we would need to + * divorce ->insn[] and ->ixol[]. We need to preserve the 1st byte + * of ->insn[] for set_orig_insn(). + */ + memset(auprobe->insn + insn_offset_immediate(insn), + 0, insn->immediate.nbytes); } -static void -handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs, long *correction) +static struct uprobe_xol_ops branch_xol_ops = { + .emulate = branch_emulate_op, + .post_xol = branch_post_xol_op, +}; + +/* Returns -ENOSYS if branch_xol_ops doesn't handle this insn */ +static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) { - if (is_riprel_insn(auprobe)) { - struct arch_uprobe_task *autask; + u8 opc1 = OPCODE1(insn); + int i; - autask = ¤t->utask->autask; - if (auprobe->fixups & UPROBE_FIX_RIP_AX) - regs->ax = autask->saved_scratch_register; - else - regs->cx = autask->saved_scratch_register; + switch (opc1) { + case 0xeb: /* jmp 8 */ + case 0xe9: /* jmp 32 */ + case 0x90: /* prefix* + nop; same as jmp with .offs = 0 */ + break; + + case 0xe8: /* call relative */ + branch_clear_offset(auprobe, insn); + break; + case 0x0f: + if (insn->opcode.nbytes != 2) + return -ENOSYS; /* - * The original instruction includes a displacement, and so - * is 4 bytes longer than what we've just single-stepped. - * Fall through to handle stuff like "jmpq *...(%rip)" and - * "callq *...(%rip)". + * If it is a "near" conditional jmp, OPCODE2() - 0x10 matches + * OPCODE1() of the "short" jmp which checks the same condition. */ - if (correction) - *correction += 4; + opc1 = OPCODE2(insn) - 0x10; + default: + if (!is_cond_jmp_opcode(opc1)) + return -ENOSYS; + } + + /* + * 16-bit overrides such as CALLW (66 e8 nn nn) are not supported. + * Intel and AMD behavior differ in 64-bit mode: Intel ignores 66 prefix. + * No one uses these insns, reject any branch insns with such prefix. + */ + for (i = 0; i < insn->prefixes.nbytes; i++) { + if (insn->prefixes.bytes[i] == 0x66) + return -ENOTSUPP; } + + auprobe->branch.opc1 = opc1; + auprobe->branch.ilen = insn->length; + auprobe->branch.offs = insn->immediate.value; + + auprobe->ops = &branch_xol_ops; + return 0; } -#else -static void -handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs, long *correction) + +/** + * arch_uprobe_analyze_insn - instruction analysis including validity and fixups. + * @mm: the probed address space. + * @arch_uprobe: the probepoint information. + * @addr: virtual address at which to install the probepoint + * Return 0 on success or a -ve number on error. + */ +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr) { - /* No RIP-relative addressing on 32-bit */ + struct insn insn; + u8 fix_ip_or_call = UPROBE_FIX_IP; + int ret; + + ret = uprobe_init_insn(auprobe, &insn, is_64bit_mm(mm)); + if (ret) + return ret; + + ret = branch_setup_xol_ops(auprobe, &insn); + if (ret != -ENOSYS) + return ret; + + /* + * Figure out which fixups default_post_xol_op() will need to perform, + * and annotate defparam->fixups accordingly. + */ + switch (OPCODE1(&insn)) { + case 0x9d: /* popf */ + auprobe->defparam.fixups |= UPROBE_FIX_SETF; + break; + case 0xc3: /* ret or lret -- ip is correct */ + case 0xcb: + case 0xc2: + case 0xca: + case 0xea: /* jmp absolute -- ip is correct */ + fix_ip_or_call = 0; + break; + case 0x9a: /* call absolute - Fix return addr, not ip */ + fix_ip_or_call = UPROBE_FIX_CALL; + break; + case 0xff: + switch (MODRM_REG(&insn)) { + case 2: case 3: /* call or lcall, indirect */ + fix_ip_or_call = UPROBE_FIX_CALL; + break; + case 4: case 5: /* jmp or ljmp, indirect */ + fix_ip_or_call = 0; + break; + } + /* fall through */ + default: + riprel_analyze(auprobe, &insn); + } + + auprobe->defparam.ilen = insn.length; + auprobe->defparam.fixups |= fix_ip_or_call; + + auprobe->ops = &default_xol_ops; + return 0; +} + +/* + * arch_uprobe_pre_xol - prepare to execute out of line. + * @auprobe: the probepoint information. + * @regs: reflects the saved user state of current task. + */ +int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + if (auprobe->ops->pre_xol) { + int err = auprobe->ops->pre_xol(auprobe, regs); + if (err) + return err; + } + + regs->ip = utask->xol_vaddr; + utask->autask.saved_trap_nr = current->thread.trap_nr; + current->thread.trap_nr = UPROBE_TRAP_NR; + + utask->autask.saved_tf = !!(regs->flags & X86_EFLAGS_TF); + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(current, TIF_BLOCKSTEP)) + set_task_blockstep(current, false); + + return 0; } -#endif /* * If xol insn itself traps and generates a signal(Say, @@ -572,53 +799,42 @@ bool arch_uprobe_xol_was_trapped(struct task_struct *t) * single-step, we single-stepped a copy of the instruction. * * This function prepares to resume execution after the single-step. - * We have to fix things up as follows: - * - * Typically, the new ip is relative to the copied instruction. We need - * to make it relative to the original instruction (FIX_IP). Exceptions - * are return instructions and absolute or indirect jump or call instructions. - * - * If the single-stepped instruction was a call, the return address that - * is atop the stack is the address following the copied instruction. We - * need to make it the address following the original instruction (FIX_CALL). - * - * If the original instruction was a rip-relative instruction such as - * "movl %edx,0xnnnn(%rip)", we have instead executed an equivalent - * instruction using a scratch register -- e.g., "movl %edx,(%rax)". - * We need to restore the contents of the scratch register and adjust - * the ip, keeping in mind that the instruction we executed is 4 bytes - * shorter than the original instruction (since we squeezed out the offset - * field). (FIX_RIP_AX or FIX_RIP_CX) */ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { - struct uprobe_task *utask; - long correction; - int result = 0; + struct uprobe_task *utask = current->utask; + bool send_sigtrap = utask->autask.saved_tf; + int err = 0; WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR); - - utask = current->utask; current->thread.trap_nr = utask->autask.saved_trap_nr; - correction = (long)(utask->vaddr - utask->xol_vaddr); - handle_riprel_post_xol(auprobe, regs, &correction); - if (auprobe->fixups & UPROBE_FIX_IP) - regs->ip += correction; - - if (auprobe->fixups & UPROBE_FIX_CALL) - result = adjust_ret_addr(regs->sp, correction); + if (auprobe->ops->post_xol) { + err = auprobe->ops->post_xol(auprobe, regs); + if (err) { + /* + * Restore ->ip for restart or post mortem analysis. + * ->post_xol() must not return -ERESTART unless this + * is really possible. + */ + regs->ip = utask->vaddr; + if (err == -ERESTART) + err = 0; + send_sigtrap = false; + } + } /* * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP * so we can get an extra SIGTRAP if we do not clear TF. We need * to examine the opcode to make it right. */ - if (utask->autask.saved_tf) + if (send_sigtrap) send_sig(SIGTRAP, current, 0); - else if (!(auprobe->fixups & UPROBE_FIX_SETF)) + + if (!utask->autask.saved_tf) regs->flags &= ~X86_EFLAGS_TF; - return result; + return err; } /* callback routine for handling exceptions. */ @@ -652,41 +868,27 @@ int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, /* * This function gets called when XOL instruction either gets trapped or - * the thread has a fatal signal, so reset the instruction pointer to its - * probed address. + * the thread has a fatal signal. Reset the instruction pointer to its + * probed address for the potential restart or for post mortem analysis. */ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { struct uprobe_task *utask = current->utask; - current->thread.trap_nr = utask->autask.saved_trap_nr; - handle_riprel_post_xol(auprobe, regs, NULL); - instruction_pointer_set(regs, utask->vaddr); + if (auprobe->ops->abort) + auprobe->ops->abort(auprobe, regs); + current->thread.trap_nr = utask->autask.saved_trap_nr; + regs->ip = utask->vaddr; /* clear TF if it was set by us in arch_uprobe_pre_xol() */ if (!utask->autask.saved_tf) regs->flags &= ~X86_EFLAGS_TF; } -/* - * Skip these instructions as per the currently known x86 ISA. - * rep=0x66*; nop=0x90 - */ static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) { - int i; - - for (i = 0; i < MAX_UINSN_BYTES; i++) { - if (auprobe->insn[i] == 0x66) - continue; - - if (auprobe->insn[i] == 0x90) { - regs->ip += i + 1; - return true; - } - - break; - } + if (auprobe->ops->emulate) + return auprobe->ops->emulate(auprobe, regs); return false; } @@ -701,23 +903,21 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) { - int rasize, ncopied; + int rasize = sizeof_long(), nleft; unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */ - rasize = is_ia32_task() ? 4 : 8; - ncopied = copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize); - if (unlikely(ncopied)) + if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize)) return -1; /* check whether address has been already hijacked */ if (orig_ret_vaddr == trampoline_vaddr) return orig_ret_vaddr; - ncopied = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize); - if (likely(!ncopied)) + nleft = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize); + if (likely(!nleft)) return orig_ret_vaddr; - if (ncopied != rasize) { + if (nleft != rasize) { pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, " "%%ip=%#lx\n", current->pid, regs->sp, regs->ip); diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c index 8b3b3eb..ea5b570 100644 --- a/arch/x86/kernel/vsyscall_64.c +++ b/arch/x86/kernel/vsyscall_64.c @@ -91,7 +91,7 @@ static int addr_to_vsyscall_nr(unsigned long addr) { int nr; - if ((addr & ~0xC00UL) != VSYSCALL_START) + if ((addr & ~0xC00UL) != VSYSCALL_ADDR) return -EINVAL; nr = (addr & 0xC00UL) >> 10; @@ -330,24 +330,17 @@ void __init map_vsyscall(void) { extern char __vsyscall_page; unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page); - unsigned long physaddr_vvar_page = __pa_symbol(&__vvar_page); - __set_fixmap(VSYSCALL_FIRST_PAGE, physaddr_vsyscall, + __set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall, vsyscall_mode == NATIVE ? PAGE_KERNEL_VSYSCALL : PAGE_KERNEL_VVAR); - BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_FIRST_PAGE) != - (unsigned long)VSYSCALL_START); - - __set_fixmap(VVAR_PAGE, physaddr_vvar_page, PAGE_KERNEL_VVAR); - BUILD_BUG_ON((unsigned long)__fix_to_virt(VVAR_PAGE) != - (unsigned long)VVAR_ADDRESS); + BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) != + (unsigned long)VSYSCALL_ADDR); } static int __init vsyscall_init(void) { - BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE)); - cpu_notifier_register_begin(); on_each_cpu(cpu_vsyscall_init, NULL, 1); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index f47a104..38a0afe 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -283,6 +283,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); /* cpuid 1.ecx */ const u32 kvm_supported_word4_x86_features = + /* NOTE: MONITOR (and MWAIT) are emulated as NOP, + * but *not* advertised to guests via CPUID ! */ F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | 0 /* DS-CPL, VMX, SMX, EST */ | 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | @@ -495,6 +497,13 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_supported_word6_x86_features; cpuid_mask(&entry->ecx, 6); break; + case 0x80000007: /* Advanced power management */ + /* invariant TSC is CPUID.80000007H:EDX[8] */ + entry->edx &= (1 << 8); + /* mask against host */ + entry->edx &= boot_cpu_data.x86_power; + entry->eax = entry->ebx = entry->ecx = 0; + break; case 0x80000008: { unsigned g_phys_as = (entry->eax >> 16) & 0xff; unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); @@ -525,7 +534,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ case 6: /* Thermal management */ - case 0x80000007: /* Advanced power management */ case 0xC0000002: case 0xC0000003: case 0xC0000004: @@ -726,6 +734,7 @@ int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) not_found: return 36; } +EXPORT_SYMBOL_GPL(cpuid_maxphyaddr); /* * If no match is found, check whether we exceed the vCPU's limit diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index eeecbed..f908731 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -88,4 +88,11 @@ static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_X2APIC)); } +static inline bool guest_cpuid_has_gbpages(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + return best && (best->edx & bit(X86_FEATURE_GBPAGES)); +} #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 205b17e..e4e833d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -161,6 +161,7 @@ #define Fastop ((u64)1 << 44) /* Use opcode::u.fastop */ #define NoWrite ((u64)1 << 45) /* No writeback */ #define SrcWrite ((u64)1 << 46) /* Write back src operand */ +#define NoMod ((u64)1 << 47) /* Mod field is ignored */ #define DstXacc (DstAccLo | SrcAccHi | SrcWrite) @@ -1077,7 +1078,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_rm |= (ctxt->modrm & 0x07); ctxt->modrm_seg = VCPU_SREG_DS; - if (ctxt->modrm_mod == 3) { + if (ctxt->modrm_mod == 3 || (ctxt->d & NoMod)) { op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, @@ -1324,7 +1325,8 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, rc->end = n * size; } - if (ctxt->rep_prefix && !(ctxt->eflags & EFLG_DF)) { + if (ctxt->rep_prefix && (ctxt->d & String) && + !(ctxt->eflags & EFLG_DF)) { ctxt->dst.data = rc->data + rc->pos; ctxt->dst.type = OP_MEM_STR; ctxt->dst.count = (rc->end - rc->pos) / size; @@ -1409,11 +1411,11 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, } /* Does not support long mode */ -static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, - u16 selector, int seg) +static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, + u16 selector, int seg, u8 cpl, bool in_task_switch) { struct desc_struct seg_desc, old_desc; - u8 dpl, rpl, cpl; + u8 dpl, rpl; unsigned err_vec = GP_VECTOR; u32 err_code = 0; bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ @@ -1441,7 +1443,6 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, } rpl = selector & 3; - cpl = ctxt->ops->cpl(ctxt); /* NULL selector is not valid for TR, CS and SS (except for long mode) */ if ((seg == VCPU_SREG_CS @@ -1486,6 +1487,9 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto exception; break; case VCPU_SREG_CS: + if (in_task_switch && rpl != dpl) + goto exception; + if (!(seg_desc.type & 8)) goto exception; @@ -1543,6 +1547,13 @@ exception: return X86EMUL_PROPAGATE_FAULT; } +static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, + u16 selector, int seg) +{ + u8 cpl = ctxt->ops->cpl(ctxt); + return __load_segment_descriptor(ctxt, selector, seg, cpl, false); +} + static void write_register_operand(struct operand *op) { /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ @@ -2404,6 +2415,7 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, struct tss_segment_16 *tss) { int ret; + u8 cpl; ctxt->_eip = tss->ip; ctxt->eflags = tss->flag | 2; @@ -2426,23 +2438,25 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS); set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS); + cpl = tss->cs & 3; + /* * Now load segment descriptors. If fault happens at this stage * it is handled in a context of new task */ - ret = load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR); + ret = __load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES); + ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS); + ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS); + ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS); + ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; @@ -2496,7 +2510,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt, static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, struct tss_segment_32 *tss) { - tss->cr3 = ctxt->ops->get_cr(ctxt, 3); + /* CR3 and ldt selector are not saved intentionally */ tss->eip = ctxt->_eip; tss->eflags = ctxt->eflags; tss->eax = reg_read(ctxt, VCPU_REGS_RAX); @@ -2514,13 +2528,13 @@ static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS); tss->fs = get_segment_selector(ctxt, VCPU_SREG_FS); tss->gs = get_segment_selector(ctxt, VCPU_SREG_GS); - tss->ldt_selector = get_segment_selector(ctxt, VCPU_SREG_LDTR); } static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, struct tss_segment_32 *tss) { int ret; + u8 cpl; if (ctxt->ops->set_cr(ctxt, 3, tss->cr3)) return emulate_gp(ctxt, 0); @@ -2539,7 +2553,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, /* * SDM says that segment selectors are loaded before segment - * descriptors + * descriptors. This is important because CPL checks will + * use CS.RPL. */ set_segment_selector(ctxt, tss->ldt_selector, VCPU_SREG_LDTR); set_segment_selector(ctxt, tss->es, VCPU_SREG_ES); @@ -2553,43 +2568,38 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, * If we're switching between Protected Mode and VM86, we need to make * sure to update the mode before loading the segment descriptors so * that the selectors are interpreted correctly. - * - * Need to get rflags to the vcpu struct immediately because it - * influences the CPL which is checked at least when loading the segment - * descriptors and when pushing an error code to the new kernel stack. - * - * TODO Introduce a separate ctxt->ops->set_cpl callback */ - if (ctxt->eflags & X86_EFLAGS_VM) + if (ctxt->eflags & X86_EFLAGS_VM) { ctxt->mode = X86EMUL_MODE_VM86; - else + cpl = 3; + } else { ctxt->mode = X86EMUL_MODE_PROT32; - - ctxt->ops->set_rflags(ctxt, ctxt->eflags); + cpl = tss->cs & 3; + } /* * Now load segment descriptors. If fault happenes at this stage * it is handled in a context of new task */ - ret = load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR); + ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES); + ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS); + ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS); + ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS); + ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS); + ret = __load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS); + ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; @@ -2604,6 +2614,8 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, struct tss_segment_32 tss_seg; int ret; u32 new_tss_base = get_desc_base(new_desc); + u32 eip_offset = offsetof(struct tss_segment_32, eip); + u32 ldt_sel_offset = offsetof(struct tss_segment_32, ldt_selector); ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg, &ctxt->exception); @@ -2613,8 +2625,9 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, save_state_to_tss32(ctxt, &tss_seg); - ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg, - &ctxt->exception); + /* Only GP registers and segment selectors are saved */ + ret = ops->write_std(ctxt, old_tss_base + eip_offset, &tss_seg.eip, + ldt_sel_offset - eip_offset, &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ return ret; @@ -3386,10 +3399,6 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (efer & EFER_LMA) rsvd = CR3_L_MODE_RESERVED_BITS; - else if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PAE) - rsvd = CR3_PAE_RESERVED_BITS; - else if (ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PG) - rsvd = CR3_NONPAE_RESERVED_BITS; if (new_val & rsvd) return emulate_gp(ctxt, 0); @@ -3869,10 +3878,12 @@ static const struct opcode twobyte_table[256] = { N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM), /* 0x20 - 0x2F */ - DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read), - DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read), - IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write), - IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write), + DIP(ModRM | DstMem | Priv | Op3264 | NoMod, cr_read, check_cr_read), + DIP(ModRM | DstMem | Priv | Op3264 | NoMod, dr_read, check_dr_read), + IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_cr_write, cr_write, + check_cr_write), + IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_dr_write, dr_write, + check_dr_write), N, N, N, N, GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29), GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29), diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 484bc87..bd0da43 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -113,6 +113,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) return kvm_get_apic_interrupt(v); /* APIC */ } +EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9736529..0069118 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -360,6 +360,8 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { + /* Note that we never get here with APIC virtualization enabled. */ + if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -371,12 +373,48 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) apic->highest_isr_cache = vec; } +static inline int apic_find_highest_isr(struct kvm_lapic *apic) +{ + int result; + + /* + * Note that isr_count is always 1, and highest_isr_cache + * is always -1, with APIC virtualization enabled. + */ + if (!apic->isr_count) + return -1; + if (likely(apic->highest_isr_cache != -1)) + return apic->highest_isr_cache; + + result = find_highest_vector(apic->regs + APIC_ISR); + ASSERT(result == -1 || result >= 16); + + return result; +} + static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) { - if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + struct kvm_vcpu *vcpu; + if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + return; + + vcpu = apic->vcpu; + + /* + * We do get here for APIC virtualization enabled if the guest + * uses the Hyper-V APIC enlightenment. In this case we may need + * to trigger a new interrupt delivery by writing the SVI field; + * on the other hand isr_count and highest_isr_cache are unused + * and must be left alone. + */ + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, + apic_find_highest_isr(apic)); + else { --apic->isr_count; - BUG_ON(apic->isr_count < 0); - apic->highest_isr_cache = -1; + BUG_ON(apic->isr_count < 0); + apic->highest_isr_cache = -1; + } } int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) @@ -456,22 +494,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static inline int apic_find_highest_isr(struct kvm_lapic *apic) -{ - int result; - - /* Note that isr_count is always 1 with vid enabled */ - if (!apic->isr_count) - return -1; - if (likely(apic->highest_isr_cache != -1)) - return apic->highest_isr_cache; - - result = find_highest_vector(apic->regs + APIC_ISR); - ASSERT(result == -1 || result >= 16); - - return result; -} - void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -1605,6 +1627,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; + /* Note that we never get here with APIC virtualization enabled. */ + if (vector == -1) return -1; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 813d310..9314678 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -22,6 +22,7 @@ #include "mmu.h" #include "x86.h" #include "kvm_cache_regs.h" +#include "cpuid.h" #include <linux/kvm_host.h> #include <linux/types.h> @@ -595,7 +596,8 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) * we always atomicly update it, see the comments in * spte_has_volatile_bits(). */ - if (is_writable_pte(old_spte) && !is_writable_pte(new_spte)) + if (spte_is_locklessly_modifiable(old_spte) && + !is_writable_pte(new_spte)) ret = true; if (!shadow_accessed_mask) @@ -1176,8 +1178,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) /* * Write-protect on the specified @sptep, @pt_protect indicates whether - * spte writ-protection is caused by protecting shadow page table. - * @flush indicates whether tlb need be flushed. + * spte write-protection is caused by protecting shadow page table. * * Note: write protection is difference between drity logging and spte * protection: @@ -1186,10 +1187,9 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) * - for spte protection, the spte can be writable only after unsync-ing * shadow page. * - * Return true if the spte is dropped. + * Return true if tlb need be flushed. */ -static bool -spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect) +static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect) { u64 spte = *sptep; @@ -1199,17 +1199,11 @@ spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect) rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); - if (__drop_large_spte(kvm, sptep)) { - *flush |= true; - return true; - } - if (pt_protect) spte &= ~SPTE_MMU_WRITEABLE; spte = spte & ~PT_WRITABLE_MASK; - *flush |= mmu_spte_update(sptep, spte); - return false; + return mmu_spte_update(sptep, spte); } static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, @@ -1221,11 +1215,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { BUG_ON(!(*sptep & PT_PRESENT_MASK)); - if (spte_write_protect(kvm, sptep, &flush, pt_protect)) { - sptep = rmap_get_first(*rmapp, &iter); - continue; - } + flush |= spte_write_protect(kvm, sptep, pt_protect); sptep = rmap_get_next(&iter); } @@ -2802,9 +2793,9 @@ static bool page_fault_can_be_fast(u32 error_code) } static bool -fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte) +fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + u64 *sptep, u64 spte) { - struct kvm_mmu_page *sp = page_header(__pa(sptep)); gfn_t gfn; WARN_ON(!sp->role.direct); @@ -2830,6 +2821,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, u32 error_code) { struct kvm_shadow_walk_iterator iterator; + struct kvm_mmu_page *sp; bool ret = false; u64 spte = 0ull; @@ -2853,7 +2845,8 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, goto exit; } - if (!is_last_spte(spte, level)) + sp = page_header(__pa(iterator.sptep)); + if (!is_last_spte(spte, sp->role.level)) goto exit; /* @@ -2875,11 +2868,24 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, goto exit; /* + * Do not fix write-permission on the large spte since we only dirty + * the first page into the dirty-bitmap in fast_pf_fix_direct_spte() + * that means other pages are missed if its slot is dirty-logged. + * + * Instead, we let the slow page fault path create a normal spte to + * fix the access. + * + * See the comments in kvm_arch_commit_memory_region(). + */ + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + goto exit; + + /* * Currently, fast page fault only works for direct mapping since * the gfn is not stable for indirect shadow page. * See Documentation/virtual/kvm/locking.txt to get more detail. */ - ret = fast_pf_fix_direct_spte(vcpu, iterator.sptep, spte); + ret = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte); exit: trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, spte, ret); @@ -3511,11 +3517,14 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, { int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; + u64 gbpages_bit_rsvd = 0; context->bad_mt_xwr = 0; if (!context->nx) exb_bit_rsvd = rsvd_bits(63, 63); + if (!guest_cpuid_has_gbpages(vcpu)) + gbpages_bit_rsvd = rsvd_bits(7, 7); switch (context->root_level) { case PT32_ROOT_LEVEL: /* no rsvd bits for 2 level 4K page table entries */ @@ -3538,7 +3547,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, case PT32E_ROOT_LEVEL: context->rsvd_bits_mask[0][2] = rsvd_bits(maxphyaddr, 63) | - rsvd_bits(7, 8) | rsvd_bits(1, 2); /* PDPTE */ + rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */ context->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62); /* PDE */ context->rsvd_bits_mask[0][0] = exb_bit_rsvd | @@ -3550,16 +3559,16 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, break; case PT64_ROOT_LEVEL: context->rsvd_bits_mask[0][3] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8); + rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7); context->rsvd_bits_mask[0][2] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8); + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[0][0] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; context->rsvd_bits_mask[1][2] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 29); context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | @@ -4304,15 +4313,32 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) if (*rmapp) __rmap_write_protect(kvm, rmapp, false); - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - kvm_flush_remote_tlbs(kvm); + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) cond_resched_lock(&kvm->mmu_lock); - } } } - kvm_flush_remote_tlbs(kvm); spin_unlock(&kvm->mmu_lock); + + /* + * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log() + * which do tlb flush out of mmu-lock should be serialized by + * kvm->slots_lock otherwise tlb flush would be missed. + */ + lockdep_assert_held(&kvm->slots_lock); + + /* + * We can flush all the TLBs out of the mmu lock without TLB + * corruption since we just change the spte from writable to + * readonly so that we only need to care the case of changing + * spte from present to present (changing the spte from present + * to nonpresent will flush all the TLBs immediately), in other + * words, the only case we care is mmu_spte_update() where we + * haved checked SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE + * instead of PT_WRITABLE_MASK, that means it does not depend + * on PT_WRITABLE_MASK anymore. + */ + kvm_flush_remote_tlbs(kvm); } #define BATCH_ZAP_PAGES 10 diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 3842e70..b982112 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -104,6 +104,39 @@ static inline int is_present_gpte(unsigned long pte) return pte & PT_PRESENT_MASK; } +/* + * Currently, we have two sorts of write-protection, a) the first one + * write-protects guest page to sync the guest modification, b) another one is + * used to sync dirty bitmap when we do KVM_GET_DIRTY_LOG. The differences + * between these two sorts are: + * 1) the first case clears SPTE_MMU_WRITEABLE bit. + * 2) the first case requires flushing tlb immediately avoiding corrupting + * shadow page table between all vcpus so it should be in the protection of + * mmu-lock. And the another case does not need to flush tlb until returning + * the dirty bitmap to userspace since it only write-protects the page + * logged in the bitmap, that means the page in the dirty bitmap is not + * missed, so it can flush tlb out of mmu-lock. + * + * So, there is the problem: the first case can meet the corrupted tlb caused + * by another case which write-protects pages but without flush tlb + * immediately. In order to making the first case be aware this problem we let + * it flush tlb if we try to write-protect a spte whose SPTE_MMU_WRITEABLE bit + * is set, it works since another case never touches SPTE_MMU_WRITEABLE bit. + * + * Anyway, whenever a spte is updated (only permission and status bits are + * changed) we need to check whether the spte with SPTE_MMU_WRITEABLE becomes + * readonly, if that happens, we need to flush tlb. Fortunately, + * mmu_spte_update() has already handled it perfectly. + * + * The rules to use SPTE_MMU_WRITEABLE and PT_WRITABLE_MASK: + * - if we want to see if it has writable tlb entry or if the spte can be + * writable on the mmu mapping, check SPTE_MMU_WRITEABLE, this is the most + * case, otherwise + * - if we fix page fault on the spte or do write-protection by dirty logging, + * check PT_WRITABLE_MASK. + * + * TODO: introduce APIs to split these two cases. + */ static inline int is_writable_pte(unsigned long pte) { return pte & PT_WRITABLE_MASK; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 123efd3..4107765 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -913,8 +913,7 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, * and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't * used by guest then tlbs are not flushed, so guest is allowed to access the * freed pages. - * We set tlbs_dirty to let the notifier know this change and delay the flush - * until such a case actually happens. + * And we increase kvm->tlbs_dirty to delay tlbs flush in this case. */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -943,7 +942,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return -EINVAL; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { - vcpu->kvm->tlbs_dirty = true; + vcpu->kvm->tlbs_dirty++; continue; } @@ -958,7 +957,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) if (gfn != sp->gfns[i]) { drop_spte(vcpu->kvm, &sp->spt[i]); - vcpu->kvm->tlbs_dirty = true; + vcpu->kvm->tlbs_dirty++; continue; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 5c4f631..cbecaa9 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -108,7 +108,10 @@ static void kvm_perf_overflow(struct perf_event *perf_event, { struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); + if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); + kvm_make_request(KVM_REQ_PMU, pmc->vcpu); + } } static void kvm_perf_overflow_intr(struct perf_event *perf_event, @@ -117,7 +120,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { - kvm_perf_overflow(perf_event, data, regs); + __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); /* * Inject PMI. If vcpu was in a guest mode during NMI PMI diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 7f4f9c2..ec8366c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1338,21 +1338,6 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); } -static void svm_update_cpl(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - int cpl; - - if (!is_protmode(vcpu)) - cpl = 0; - else if (svm->vmcb->save.rflags & X86_EFLAGS_VM) - cpl = 3; - else - cpl = svm->vmcb->save.cs.selector & 0x3; - - svm->vmcb->save.cpl = cpl; -} - static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) { return to_svm(vcpu)->vmcb->save.rflags; @@ -1360,11 +1345,12 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { - unsigned long old_rflags = to_svm(vcpu)->vmcb->save.rflags; - + /* + * Any change of EFLAGS.VM is accompained by a reload of SS + * (caused by either a task switch or an inter-privilege IRET), + * so we do not need to update the CPL here. + */ to_svm(vcpu)->vmcb->save.rflags = rflags; - if ((old_rflags ^ rflags) & X86_EFLAGS_VM) - svm_update_cpl(vcpu); } static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) @@ -1631,8 +1617,15 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; } - if (seg == VCPU_SREG_CS) - svm_update_cpl(vcpu); + + /* + * This is always accurate, except if SYSRET returned to a segment + * with SS.DPL != 3. Intel does not have this quirk, and always + * forces SS.DPL to 3 on sysret, so we ignore that case; fixing it + * would entail passing the CPL to userspace and back. + */ + if (seg == VCPU_SREG_SS) + svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; mark_dirty(svm->vmcb, VMCB_SEG); } @@ -2770,12 +2763,6 @@ static int xsetbv_interception(struct vcpu_svm *svm) return 1; } -static int invalid_op_interception(struct vcpu_svm *svm) -{ - kvm_queue_exception(&svm->vcpu, UD_VECTOR); - return 1; -} - static int task_switch_interception(struct vcpu_svm *svm) { u16 tss_selector; @@ -3287,6 +3274,24 @@ static int pause_interception(struct vcpu_svm *svm) return 1; } +static int nop_interception(struct vcpu_svm *svm) +{ + skip_emulated_instruction(&(svm->vcpu)); + return 1; +} + +static int monitor_interception(struct vcpu_svm *svm) +{ + printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); + return nop_interception(svm); +} + +static int mwait_interception(struct vcpu_svm *svm) +{ + printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); + return nop_interception(svm); +} + static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR0] = cr_interception, [SVM_EXIT_READ_CR3] = cr_interception, @@ -3344,8 +3349,8 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, [SVM_EXIT_WBINVD] = emulate_on_interception, - [SVM_EXIT_MONITOR] = invalid_op_interception, - [SVM_EXIT_MWAIT] = invalid_op_interception, + [SVM_EXIT_MONITOR] = monitor_interception, + [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = pf_interception, }; diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 545245d..33574c9 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -91,16 +91,21 @@ TRACE_EVENT(kvm_hv_hypercall, /* * Tracepoint for PIO. */ + +#define KVM_PIO_IN 0 +#define KVM_PIO_OUT 1 + TRACE_EVENT(kvm_pio, TP_PROTO(unsigned int rw, unsigned int port, unsigned int size, - unsigned int count), - TP_ARGS(rw, port, size, count), + unsigned int count, void *data), + TP_ARGS(rw, port, size, count, data), TP_STRUCT__entry( __field( unsigned int, rw ) __field( unsigned int, port ) __field( unsigned int, size ) __field( unsigned int, count ) + __field( unsigned int, val ) ), TP_fast_assign( @@ -108,11 +113,18 @@ TRACE_EVENT(kvm_pio, __entry->port = port; __entry->size = size; __entry->count = count; + if (size == 1) + __entry->val = *(unsigned char *)data; + else if (size == 2) + __entry->val = *(unsigned short *)data; + else + __entry->val = *(unsigned int *)data; ), - TP_printk("pio_%s at 0x%x size %d count %d", + TP_printk("pio_%s at 0x%x size %d count %d val 0x%x %s", __entry->rw ? "write" : "read", - __entry->port, __entry->size, __entry->count) + __entry->port, __entry->size, __entry->count, __entry->val, + __entry->count > 1 ? "(...)" : "") ); /* diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 33e8c02..801332e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -354,6 +354,7 @@ struct vmcs02_list { struct nested_vmx { /* Has the level1 guest done vmxon? */ bool vmxon; + gpa_t vmxon_ptr; /* The guest-physical address of the current VMCS L1 keeps for L2 */ gpa_t current_vmptr; @@ -413,7 +414,6 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; u8 fail; - u8 cpl; bool nmi_known_unmasked; u32 exit_intr_info; u32 idt_vectoring_info; @@ -2283,7 +2283,7 @@ static __init void nested_vmx_setup_ctls_msrs(void) rdmsr(MSR_IA32_VMX_EXIT_CTLS, nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high); nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; - /* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */ + nested_vmx_exit_ctls_high &= #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | @@ -2291,7 +2291,8 @@ static __init void nested_vmx_setup_ctls_msrs(void) VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT; nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | - VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT; + if (vmx_mpx_supported()) nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; @@ -2353,12 +2354,11 @@ static __init void nested_vmx_setup_ctls_msrs(void) VMX_EPT_INVEPT_BIT; nested_vmx_ept_caps &= vmx_capability.ept; /* - * Since invept is completely emulated we support both global - * and context invalidation independent of what host cpu - * supports + * For nested guests, we don't do anything specific + * for single context invalidation. Hence, only advertise + * support for global context invalidation. */ - nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT | - VMX_EPT_EXTENT_CONTEXT_BIT; + nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT; } else nested_vmx_ept_caps = 0; @@ -3186,10 +3186,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu) fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); - - /* CPL is always 0 when CPU enters protected mode */ - __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - vmx->cpl = 0; } static void fix_rmode_seg(int seg, struct kvm_segment *save) @@ -3591,22 +3587,14 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!is_protmode(vcpu)) + if (unlikely(vmx->rmode.vm86_active)) return 0; - - if (!is_long_mode(vcpu) - && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */ - return 3; - - if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) { - __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - vmx->cpl = vmx_read_guest_seg_selector(vmx, VCPU_SREG_CS) & 3; + else { + int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); + return AR_DPL(ar); } - - return vmx->cpl; } - static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; @@ -3634,8 +3622,6 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; vmx_segment_cache_clear(vmx); - if (seg == VCPU_SREG_CS) - __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { vmx->rmode.segs[seg] = *var; @@ -4564,6 +4550,16 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu) PIN_BASED_EXT_INTR_MASK; } +/* + * In nested virtualization, check if L1 has set + * VM_EXIT_ACK_INTR_ON_EXIT + */ +static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu) +{ + return get_vmcs12(vcpu)->vm_exit_controls & + VM_EXIT_ACK_INTR_ON_EXIT; +} + static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) { return get_vmcs12(vcpu)->pin_based_vm_exec_control & @@ -4878,6 +4874,9 @@ static int handle_exception(struct kvm_vcpu *vcpu) (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { vcpu->arch.dr6 &= ~15; vcpu->arch.dr6 |= dr6; + if (!(dr6 & ~DR6_RESERVED)) /* icebp */ + skip_emulated_instruction(vcpu); + kvm_queue_exception(vcpu, DB_VECTOR); return 1; } @@ -5166,7 +5165,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) return 1; kvm_register_write(vcpu, reg, val); } else - if (kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg])) + if (kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg))) return 1; skip_emulated_instruction(vcpu); @@ -5439,7 +5438,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) } /* clear all local breakpoint enable flags */ - vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55); + vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x55); /* * TODO: What about debug traps on tss switch? @@ -5565,6 +5564,10 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); + if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { + skip_emulated_instruction(vcpu); + return 1; + } ret = handle_mmio_page_fault_common(vcpu, gpa, true); if (likely(ret == RET_MMIO_PF_EMULATE)) @@ -5669,12 +5672,24 @@ static int handle_pause(struct kvm_vcpu *vcpu) return 1; } -static int handle_invalid_op(struct kvm_vcpu *vcpu) +static int handle_nop(struct kvm_vcpu *vcpu) { - kvm_queue_exception(vcpu, UD_VECTOR); + skip_emulated_instruction(vcpu); return 1; } +static int handle_mwait(struct kvm_vcpu *vcpu) +{ + printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); + return handle_nop(vcpu); +} + +static int handle_monitor(struct kvm_vcpu *vcpu) +{ + printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); + return handle_nop(vcpu); +} + /* * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. * We could reuse a single VMCS for all the L2 guests, but we also want the @@ -5812,6 +5827,154 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) } /* + * Decode the memory-address operand of a vmx instruction, as recorded on an + * exit caused by such an instruction (run by a guest hypervisor). + * On success, returns 0. When the operand is invalid, returns 1 and throws + * #UD or #GP. + */ +static int get_vmx_mem_address(struct kvm_vcpu *vcpu, + unsigned long exit_qualification, + u32 vmx_instruction_info, gva_t *ret) +{ + /* + * According to Vol. 3B, "Information for VM Exits Due to Instruction + * Execution", on an exit, vmx_instruction_info holds most of the + * addressing components of the operand. Only the displacement part + * is put in exit_qualification (see 3B, "Basic VM-Exit Information"). + * For how an actual address is calculated from all these components, + * refer to Vol. 1, "Operand Addressing". + */ + int scaling = vmx_instruction_info & 3; + int addr_size = (vmx_instruction_info >> 7) & 7; + bool is_reg = vmx_instruction_info & (1u << 10); + int seg_reg = (vmx_instruction_info >> 15) & 7; + int index_reg = (vmx_instruction_info >> 18) & 0xf; + bool index_is_valid = !(vmx_instruction_info & (1u << 22)); + int base_reg = (vmx_instruction_info >> 23) & 0xf; + bool base_is_valid = !(vmx_instruction_info & (1u << 27)); + + if (is_reg) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + /* Addr = segment_base + offset */ + /* offset = base + [index * scale] + displacement */ + *ret = vmx_get_segment_base(vcpu, seg_reg); + if (base_is_valid) + *ret += kvm_register_read(vcpu, base_reg); + if (index_is_valid) + *ret += kvm_register_read(vcpu, index_reg)<<scaling; + *ret += exit_qualification; /* holds the displacement */ + + if (addr_size == 1) /* 32 bit */ + *ret &= 0xffffffff; + + /* + * TODO: throw #GP (and return 1) in various cases that the VM* + * instructions require it - e.g., offset beyond segment limit, + * unusable or unreadable/unwritable segment, non-canonical 64-bit + * address, and so on. Currently these are not checked. + */ + return 0; +} + +/* + * This function performs the various checks including + * - if it's 4KB aligned + * - No bits beyond the physical address width are set + * - Returns 0 on success or else 1 + * (Intel SDM Section 30.3) + */ +static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, + gpa_t *vmpointer) +{ + gva_t gva; + gpa_t vmptr; + struct x86_exception e; + struct page *page; + struct vcpu_vmx *vmx = to_vmx(vcpu); + int maxphyaddr = cpuid_maxphyaddr(vcpu); + + if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) + return 1; + + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, + sizeof(vmptr), &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } + + switch (exit_reason) { + case EXIT_REASON_VMON: + /* + * SDM 3: 24.11.5 + * The first 4 bytes of VMXON region contain the supported + * VMCS revision identifier + * + * Note - IA32_VMX_BASIC[48] will never be 1 + * for the nested case; + * which replaces physical address width with 32 + * + */ + if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + nested_vmx_failInvalid(vcpu); + skip_emulated_instruction(vcpu); + return 1; + } + + page = nested_get_page(vcpu, vmptr); + if (page == NULL || + *(u32 *)kmap(page) != VMCS12_REVISION) { + nested_vmx_failInvalid(vcpu); + kunmap(page); + skip_emulated_instruction(vcpu); + return 1; + } + kunmap(page); + vmx->nested.vmxon_ptr = vmptr; + break; + case EXIT_REASON_VMCLEAR: + if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + nested_vmx_failValid(vcpu, + VMXERR_VMCLEAR_INVALID_ADDRESS); + skip_emulated_instruction(vcpu); + return 1; + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, + VMXERR_VMCLEAR_VMXON_POINTER); + skip_emulated_instruction(vcpu); + return 1; + } + break; + case EXIT_REASON_VMPTRLD: + if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + nested_vmx_failValid(vcpu, + VMXERR_VMPTRLD_INVALID_ADDRESS); + skip_emulated_instruction(vcpu); + return 1; + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, + VMXERR_VMCLEAR_VMXON_POINTER); + skip_emulated_instruction(vcpu); + return 1; + } + break; + default: + return 1; /* shouldn't happen */ + } + + if (vmpointer) + *vmpointer = vmptr; + return 0; +} + +/* * Emulate the VMXON instruction. * Currently, we just remember that VMX is active, and do not save or even * inspect the argument to VMXON (the so-called "VMXON pointer") because we @@ -5849,6 +6012,10 @@ static int handle_vmon(struct kvm_vcpu *vcpu) kvm_inject_gp(vcpu, 0); return 1; } + + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) + return 1; + if (vmx->nested.vmxon) { nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); skip_emulated_instruction(vcpu); @@ -5971,87 +6138,19 @@ static int handle_vmoff(struct kvm_vcpu *vcpu) return 1; } -/* - * Decode the memory-address operand of a vmx instruction, as recorded on an - * exit caused by such an instruction (run by a guest hypervisor). - * On success, returns 0. When the operand is invalid, returns 1 and throws - * #UD or #GP. - */ -static int get_vmx_mem_address(struct kvm_vcpu *vcpu, - unsigned long exit_qualification, - u32 vmx_instruction_info, gva_t *ret) -{ - /* - * According to Vol. 3B, "Information for VM Exits Due to Instruction - * Execution", on an exit, vmx_instruction_info holds most of the - * addressing components of the operand. Only the displacement part - * is put in exit_qualification (see 3B, "Basic VM-Exit Information"). - * For how an actual address is calculated from all these components, - * refer to Vol. 1, "Operand Addressing". - */ - int scaling = vmx_instruction_info & 3; - int addr_size = (vmx_instruction_info >> 7) & 7; - bool is_reg = vmx_instruction_info & (1u << 10); - int seg_reg = (vmx_instruction_info >> 15) & 7; - int index_reg = (vmx_instruction_info >> 18) & 0xf; - bool index_is_valid = !(vmx_instruction_info & (1u << 22)); - int base_reg = (vmx_instruction_info >> 23) & 0xf; - bool base_is_valid = !(vmx_instruction_info & (1u << 27)); - - if (is_reg) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; - } - - /* Addr = segment_base + offset */ - /* offset = base + [index * scale] + displacement */ - *ret = vmx_get_segment_base(vcpu, seg_reg); - if (base_is_valid) - *ret += kvm_register_read(vcpu, base_reg); - if (index_is_valid) - *ret += kvm_register_read(vcpu, index_reg)<<scaling; - *ret += exit_qualification; /* holds the displacement */ - - if (addr_size == 1) /* 32 bit */ - *ret &= 0xffffffff; - - /* - * TODO: throw #GP (and return 1) in various cases that the VM* - * instructions require it - e.g., offset beyond segment limit, - * unusable or unreadable/unwritable segment, non-canonical 64-bit - * address, and so on. Currently these are not checked. - */ - return 0; -} - /* Emulate the VMCLEAR instruction */ static int handle_vmclear(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - gva_t gva; gpa_t vmptr; struct vmcs12 *vmcs12; struct page *page; - struct x86_exception e; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) - return 1; - - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, - sizeof(vmptr), &e)) { - kvm_inject_page_fault(vcpu, &e); - return 1; - } - - if (!IS_ALIGNED(vmptr, PAGE_SIZE)) { - nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS); - skip_emulated_instruction(vcpu); + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr)) return 1; - } if (vmptr == vmx->nested.current_vmptr) { nested_release_vmcs12(vmx); @@ -6372,29 +6471,14 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) static int handle_vmptrld(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - gva_t gva; gpa_t vmptr; - struct x86_exception e; u32 exec_control; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) - return 1; - - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, - sizeof(vmptr), &e)) { - kvm_inject_page_fault(vcpu, &e); - return 1; - } - - if (!IS_ALIGNED(vmptr, PAGE_SIZE)) { - nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS); - skip_emulated_instruction(vcpu); + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr)) return 1; - } if (vmx->nested.current_vmptr != vmptr) { struct vmcs12 *new_vmcs12; @@ -6471,7 +6555,6 @@ static int handle_invept(struct kvm_vcpu *vcpu) struct { u64 eptp, gpa; } operand; - u64 eptp_mask = ((1ull << 51) - 1) & PAGE_MASK; if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) { @@ -6511,16 +6594,13 @@ static int handle_invept(struct kvm_vcpu *vcpu) } switch (type) { - case VMX_EPT_EXTENT_CONTEXT: - if ((operand.eptp & eptp_mask) != - (nested_ept_get_cr3(vcpu) & eptp_mask)) - break; case VMX_EPT_EXTENT_GLOBAL: kvm_mmu_sync_roots(vcpu); kvm_mmu_flush_tlb(vcpu); nested_vmx_succeed(vcpu); break; default: + /* Trap single context invalidation invept calls */ BUG_ON(1); break; } @@ -6571,8 +6651,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, - [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op, - [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op, + [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, + [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, [EXIT_REASON_INVEPT] = handle_invept, }; @@ -7413,7 +7493,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_CPL) | (1 << VCPU_EXREG_PDPTR) | (1 << VCPU_EXREG_SEGMENTS) | (1 << VCPU_EXREG_CR3)); @@ -7778,7 +7857,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) exec_control = vmcs12->pin_based_vm_exec_control; exec_control |= vmcs_config.pin_based_exec_ctrl; - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + exec_control &= ~(PIN_BASED_VMX_PREEMPTION_TIMER | + PIN_BASED_POSTED_INTR); vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control); vmx->nested.preemption_timer_expired = false; @@ -7815,7 +7895,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (!vmx->rdtscp_enabled) exec_control &= ~SECONDARY_EXEC_RDTSCP; /* Take the following fields only from vmcs12 */ - exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | + SECONDARY_EXEC_APIC_REGISTER_VIRT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -8598,6 +8680,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, exit_qualification); + if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + && nested_exit_intr_ack_set(vcpu)) { + int irq = kvm_cpu_get_interrupt(vcpu); + WARN_ON(irq < 0); + vmcs12->vm_exit_intr_info = irq | + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; + } + trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, vmcs12->idt_vectoring_info_field, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b6c0bac..f32a025 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -106,6 +106,8 @@ EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); static u32 tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); +static bool backwards_tsc_observed = false; + #define KVM_NR_SHARED_MSRS 16 struct kvm_shared_msrs_global { @@ -702,25 +704,11 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu)) { - if (kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) { - if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS) - return 1; - } else - if (cr3 & CR3_L_MODE_RESERVED_BITS) - return 1; - } else { - if (is_pae(vcpu)) { - if (cr3 & CR3_PAE_RESERVED_BITS) - return 1; - if (is_paging(vcpu) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) - return 1; - } - /* - * We don't check reserved bits in nonpae mode, because - * this isn't enforced, and VMware depends on this. - */ - } + if (cr3 & CR3_L_MODE_RESERVED_BITS) + return 1; + } else if (is_pae(vcpu) && is_paging(vcpu) && + !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + return 1; vcpu->arch.cr3 = cr3; __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); @@ -1486,7 +1474,8 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) &ka->master_kernel_ns, &ka->master_cycle_now); - ka->use_master_clock = host_tsc_clocksource & vcpus_matched; + ka->use_master_clock = host_tsc_clocksource && vcpus_matched + && !backwards_tsc_observed; if (ka->use_master_clock) atomic_set(&kvm_guest_has_master_clock, 1); @@ -1932,6 +1921,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { vcpu->arch.hv_vapic = data; + if (kvm_lapic_enable_pv_eoi(vcpu, 0)) + return 1; break; } gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; @@ -1942,6 +1933,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) return 1; vcpu->arch.hv_vapic = data; mark_page_dirty(vcpu->kvm, gfn); + if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) + return 1; break; } case HV_X64_MSR_EOI: @@ -2644,6 +2637,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_IRQ_INJECT_STATUS: case KVM_CAP_IRQFD: case KVM_CAP_IOEVENTFD: + case KVM_CAP_IOEVENTFD_NO_LENGTH: case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: @@ -3646,11 +3640,19 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) offset = i * BITS_PER_LONG; kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask); } - if (is_dirty) - kvm_flush_remote_tlbs(kvm); spin_unlock(&kvm->mmu_lock); + /* See the comments in kvm_mmu_slot_remove_write_access(). */ + lockdep_assert_held(&kvm->slots_lock); + + /* + * All the TLBs can be flushed out of mmu lock, see the comments in + * kvm_mmu_slot_remove_write_access(). + */ + if (is_dirty) + kvm_flush_remote_tlbs(kvm); + r = -EFAULT; if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) goto out; @@ -4486,8 +4488,6 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, unsigned short port, void *val, unsigned int count, bool in) { - trace_kvm_pio(!in, port, size, count); - vcpu->arch.pio.port = port; vcpu->arch.pio.in = in; vcpu->arch.pio.count = count; @@ -4522,6 +4522,7 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, if (ret) { data_avail: memcpy(val, vcpu->arch.pio_data, size * count); + trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data); vcpu->arch.pio.count = 0; return 1; } @@ -4536,6 +4537,7 @@ static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); memcpy(vcpu->arch.pio_data, val, size * count); + trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); } @@ -4647,11 +4649,6 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) return res; } -static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val) -{ - kvm_set_rflags(emul_to_vcpu(ctxt), val); -} - static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt)); @@ -4836,7 +4833,6 @@ static const struct x86_emulate_ops emulate_ops = { .set_idt = emulator_set_idt, .get_cr = emulator_get_cr, .set_cr = emulator_set_cr, - .set_rflags = emulator_set_rflags, .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, @@ -4902,7 +4898,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) ctxt->eip = kvm_rip_read(vcpu); ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : - cs_l ? X86EMUL_MODE_PROT64 : + (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; ctxt->guest_mode = is_guest_mode(vcpu); @@ -6945,6 +6941,7 @@ int kvm_arch_hardware_enable(void *garbage) */ if (backwards_tsc) { u64 delta_cyc = max_tsc - local_tsc; + backwards_tsc_observed = true; list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.tsc_offset_adjustment += delta_cyc; @@ -7329,8 +7326,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); /* * Write protect all pages for dirty logging. - * Existing largepage mappings are destroyed here and new ones will - * not be created until the end of the logging. + * + * All the sptes including the large sptes which point to this + * slot are set to readonly. We can not create any new large + * spte on this slot until the end of the logging. + * + * See the comments in fast_page_fault(). */ if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES)) kvm_mmu_slot_remove_write_access(kvm, mem->slot); diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index eabcb6e..4d4f96a 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 +lib-y := delay.o misc.o cmdline.o lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c new file mode 100644 index 0000000..422db00 --- /dev/null +++ b/arch/x86/lib/cmdline.c @@ -0,0 +1,84 @@ +/* + * This file is part of the Linux kernel, and is made available under + * the terms of the GNU General Public License version 2. + * + * Misc librarized functions for cmdline poking. + */ +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/ctype.h> +#include <asm/setup.h> + +static inline int myisspace(u8 c) +{ + return c <= ' '; /* Close enough approximation */ +} + +/** + * Find a boolean option (like quiet,noapic,nosmp....) + * + * @cmdline: the cmdline string + * @option: option string to look for + * + * Returns the position of that @option (starts counting with 1) + * or 0 on not found. + */ +int cmdline_find_option_bool(const char *cmdline, const char *option) +{ + char c; + int len, pos = 0, wstart = 0; + const char *opptr = NULL; + enum { + st_wordstart = 0, /* Start of word/after whitespace */ + st_wordcmp, /* Comparing this word */ + st_wordskip, /* Miscompare, skip */ + } state = st_wordstart; + + if (!cmdline) + return -1; /* No command line */ + + len = min_t(int, strlen(cmdline), COMMAND_LINE_SIZE); + if (!len) + return 0; + + while (len--) { + c = *(char *)cmdline++; + pos++; + + switch (state) { + case st_wordstart: + if (!c) + return 0; + else if (myisspace(c)) + break; + + state = st_wordcmp; + opptr = option; + wstart = pos; + /* fall through */ + + case st_wordcmp: + if (!*opptr) + if (!c || myisspace(c)) + return wstart; + else + state = st_wordskip; + else if (!c) + return 0; + else if (c != *opptr++) + state = st_wordskip; + else if (!len) /* last word and is matching */ + return wstart; + break; + + case st_wordskip: + if (!c) + return 0; + else if (myisspace(c)) + state = st_wordstart; + break; + } + } + + return 0; /* Buffer overrun */ +} diff --git a/arch/x86/lib/thunk_32.S b/arch/x86/lib/thunk_32.S index 2930ae0..28f85c91 100644 --- a/arch/x86/lib/thunk_32.S +++ b/arch/x86/lib/thunk_32.S @@ -4,8 +4,8 @@ * (inspired by Andi Kleen's thunk_64.S) * Subject to the GNU public license, v.2. No warranty of any kind. */ - #include <linux/linkage.h> + #include <asm/asm.h> #ifdef CONFIG_TRACE_IRQFLAGS /* put return address in eax (arg1) */ @@ -22,6 +22,7 @@ popl %ecx popl %eax ret + _ASM_NOKPROBE(\name) .endm thunk_ra trace_hardirqs_on_thunk,trace_hardirqs_on_caller diff --git a/arch/x86/lib/thunk_64.S b/arch/x86/lib/thunk_64.S index a63efd6..92d9fea 100644 --- a/arch/x86/lib/thunk_64.S +++ b/arch/x86/lib/thunk_64.S @@ -8,6 +8,7 @@ #include <linux/linkage.h> #include <asm/dwarf2.h> #include <asm/calling.h> +#include <asm/asm.h> /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ .macro THUNK name, func, put_ret_addr_in_rdi=0 @@ -25,6 +26,7 @@ call \func jmp restore CFI_ENDPROC + _ASM_NOKPROBE(\name) .endm #ifdef CONFIG_TRACE_IRQFLAGS @@ -43,3 +45,4 @@ restore: RESTORE_ARGS ret CFI_ENDPROC + _ASM_NOKPROBE(restore) diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 20621d7..167ffca 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -30,12 +30,14 @@ struct pg_state { unsigned long start_address; unsigned long current_address; const struct addr_marker *marker; + unsigned long lines; bool to_dmesg; }; struct addr_marker { unsigned long start_address; const char *name; + unsigned long max_lines; }; /* indices for address_markers; keep sync'd w/ address_markers below */ @@ -46,6 +48,7 @@ enum address_markers_idx { LOW_KERNEL_NR, VMALLOC_START_NR, VMEMMAP_START_NR, + ESPFIX_START_NR, HIGH_KERNEL_NR, MODULES_VADDR_NR, MODULES_END_NR, @@ -68,6 +71,7 @@ static struct addr_marker address_markers[] = { { PAGE_OFFSET, "Low Kernel Mapping" }, { VMALLOC_START, "vmalloc() Area" }, { VMEMMAP_START, "Vmemmap" }, + { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, { __START_KERNEL_map, "High Kernel Mapping" }, { MODULES_VADDR, "Modules" }, { MODULES_END, "End Modules" }, @@ -182,7 +186,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, pgprot_t new_prot, int level) { pgprotval_t prot, cur; - static const char units[] = "KMGTPE"; + static const char units[] = "BKMGTPE"; /* * If we have a "break" in the series, we need to flush the state that @@ -197,6 +201,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, st->current_prot = new_prot; st->level = level; st->marker = address_markers; + st->lines = 0; pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", st->marker->name); } else if (prot != cur || level != st->level || @@ -208,17 +213,24 @@ static void note_page(struct seq_file *m, struct pg_state *st, /* * Now print the actual finished series */ - pt_dump_seq_printf(m, st->to_dmesg, "0x%0*lx-0x%0*lx ", - width, st->start_address, - width, st->current_address); - - delta = (st->current_address - st->start_address) >> 10; - while (!(delta & 1023) && unit[1]) { - delta >>= 10; - unit++; + if (!st->marker->max_lines || + st->lines < st->marker->max_lines) { + pt_dump_seq_printf(m, st->to_dmesg, + "0x%0*lx-0x%0*lx ", + width, st->start_address, + width, st->current_address); + + delta = st->current_address - st->start_address; + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ", + delta, *unit); + printk_prot(m, st->current_prot, st->level, + st->to_dmesg); } - pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ", delta, *unit); - printk_prot(m, st->current_prot, st->level, st->to_dmesg); + st->lines++; /* * We print markers for special areas of address space, @@ -226,7 +238,17 @@ static void note_page(struct seq_file *m, struct pg_state *st, * This helps in the interpretation. */ if (st->current_address >= st->marker[1].start_address) { + if (st->marker->max_lines && + st->lines > st->marker->max_lines) { + unsigned long nskip = + st->lines - st->marker->max_lines; + pt_dump_seq_printf(m, st->to_dmesg, + "... %lu entr%s skipped ... \n", + nskip, + nskip == 1 ? "y" : "ies"); + } st->marker++; + st->lines = 0; pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n", st->marker->name); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 8e57229..36642793 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -8,7 +8,7 @@ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/module.h> /* search_exception_table */ #include <linux/bootmem.h> /* max_low_pfn */ -#include <linux/kprobes.h> /* __kprobes, ... */ +#include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ #include <linux/mmiotrace.h> /* kmmio_handler, ... */ #include <linux/perf_event.h> /* perf_sw_event */ #include <linux/hugetlb.h> /* hstate_index_to_shift */ @@ -18,7 +18,8 @@ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/pgalloc.h> /* pgd_*(), ... */ #include <asm/kmemcheck.h> /* kmemcheck_*(), ... */ -#include <asm/fixmap.h> /* VSYSCALL_START */ +#include <asm/fixmap.h> /* VSYSCALL_ADDR */ +#include <asm/vsyscall.h> /* emulate_vsyscall */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -45,7 +46,7 @@ enum x86_pf_error_code { * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ -static inline int __kprobes +static nokprobe_inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) @@ -54,7 +55,7 @@ kmmio_fault(struct pt_regs *regs, unsigned long addr) return 0; } -static inline int __kprobes kprobes_fault(struct pt_regs *regs) +static nokprobe_inline int kprobes_fault(struct pt_regs *regs) { int ret = 0; @@ -261,7 +262,7 @@ void vmalloc_sync_all(void) * * Handle a fault on the vmalloc or module mapping area */ -static noinline __kprobes int vmalloc_fault(unsigned long address) +static noinline int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; @@ -291,6 +292,7 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) return 0; } +NOKPROBE_SYMBOL(vmalloc_fault); /* * Did it hit the DOS screen memory VA from vm86 mode? @@ -358,7 +360,7 @@ void vmalloc_sync_all(void) * * This assumes no large pages in there. */ -static noinline __kprobes int vmalloc_fault(unsigned long address) +static noinline int vmalloc_fault(unsigned long address) { pgd_t *pgd, *pgd_ref; pud_t *pud, *pud_ref; @@ -425,6 +427,7 @@ static noinline __kprobes int vmalloc_fault(unsigned long address) return 0; } +NOKPROBE_SYMBOL(vmalloc_fault); #ifdef CONFIG_CPU_SUP_AMD static const char errata93_warning[] = @@ -771,7 +774,7 @@ __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, * emulation. */ if (unlikely((error_code & PF_INSTR) && - ((address & ~0xfff) == VSYSCALL_START))) { + ((address & ~0xfff) == VSYSCALL_ADDR))) { if (emulate_vsyscall(regs, address)) return; } @@ -927,7 +930,7 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. */ -static noinline __kprobes int +static noinline int spurious_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; @@ -975,6 +978,7 @@ spurious_fault(unsigned long error_code, unsigned long address) return ret; } +NOKPROBE_SYMBOL(spurious_fault); int show_unhandled_signals = 1; @@ -1030,7 +1034,7 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs) * {,trace_}do_page_fault() have notrace on. Having this an actual function * guarantees there's a function trace entry. */ -static void __kprobes noinline +static noinline void __do_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { @@ -1253,8 +1257,9 @@ good_area: up_read(&mm->mmap_sem); } +NOKPROBE_SYMBOL(__do_page_fault); -dotraplinkage void __kprobes notrace +dotraplinkage void notrace do_page_fault(struct pt_regs *regs, unsigned long error_code) { unsigned long address = read_cr2(); /* Get the faulting address */ @@ -1272,10 +1277,12 @@ do_page_fault(struct pt_regs *regs, unsigned long error_code) __do_page_fault(regs, error_code, address); exception_exit(prev_state); } +NOKPROBE_SYMBOL(do_page_fault); #ifdef CONFIG_TRACING -static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs, - unsigned long error_code) +static nokprobe_inline void +trace_page_fault_entries(unsigned long address, struct pt_regs *regs, + unsigned long error_code) { if (user_mode(regs)) trace_page_fault_user(address, regs, error_code); @@ -1283,7 +1290,7 @@ static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs trace_page_fault_kernel(address, regs, error_code); } -dotraplinkage void __kprobes notrace +dotraplinkage void notrace trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) { /* @@ -1300,4 +1307,5 @@ trace_do_page_fault(struct pt_regs *regs, unsigned long error_code) __do_page_fault(regs, error_code, address); exception_exit(prev_state); } +NOKPROBE_SYMBOL(trace_do_page_fault); #endif /* CONFIG_TRACING */ diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8c9f647..8b977eb 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { return NULL; } - -int pmd_huge_support(void) -{ - return 0; -} #else struct page * @@ -80,11 +75,6 @@ int pud_huge(pud_t pud) { return !!(pud_val(pud) & _PAGE_PSE); } - -int pmd_huge_support(void) -{ - return 1; -} #endif #ifdef CONFIG_HUGETLB_PAGE diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f35c66c..df1a992 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1055,8 +1055,8 @@ void __init mem_init(void) after_bootmem = 1; /* Register memory areas for /proc/kcore */ - kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START, - VSYSCALL_END - VSYSCALL_START, KCORE_OTHER); + kclist_add(&kcore_vsyscall, (void *)VSYSCALL_ADDR, + PAGE_SIZE, KCORE_OTHER); mem_init_print_info(NULL); } @@ -1185,11 +1185,19 @@ int kern_addr_valid(unsigned long addr) * covers the 64bit vsyscall page now. 32bit has a real VMA now and does * not need special handling anymore: */ +static const char *gate_vma_name(struct vm_area_struct *vma) +{ + return "[vsyscall]"; +} +static struct vm_operations_struct gate_vma_ops = { + .name = gate_vma_name, +}; static struct vm_area_struct gate_vma = { - .vm_start = VSYSCALL_START, - .vm_end = VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE), + .vm_start = VSYSCALL_ADDR, + .vm_end = VSYSCALL_ADDR + PAGE_SIZE, .vm_page_prot = PAGE_READONLY_EXEC, - .vm_flags = VM_READ | VM_EXEC + .vm_flags = VM_READ | VM_EXEC, + .vm_ops = &gate_vma_ops, }; struct vm_area_struct *get_gate_vma(struct mm_struct *mm) @@ -1218,29 +1226,46 @@ int in_gate_area(struct mm_struct *mm, unsigned long addr) */ int in_gate_area_no_mm(unsigned long addr) { - return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END); + return (addr & PAGE_MASK) == VSYSCALL_ADDR; } -const char *arch_vma_name(struct vm_area_struct *vma) +static unsigned long probe_memory_block_size(void) { - if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) - return "[vdso]"; - if (vma == &gate_vma) - return "[vsyscall]"; - return NULL; -} + /* start from 2g */ + unsigned long bz = 1UL<<31; #ifdef CONFIG_X86_UV -unsigned long memory_block_size_bytes(void) -{ if (is_uv_system()) { printk(KERN_INFO "UV: memory block size 2GB\n"); return 2UL * 1024 * 1024 * 1024; } - return MIN_MEMORY_BLOCK_SIZE; -} #endif + /* less than 64g installed */ + if ((max_pfn << PAGE_SHIFT) < (16UL << 32)) + return MIN_MEMORY_BLOCK_SIZE; + + /* get the tail size */ + while (bz > MIN_MEMORY_BLOCK_SIZE) { + if (!((max_pfn << PAGE_SHIFT) & (bz - 1))) + break; + bz >>= 1; + } + + printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20); + + return bz; +} + +static unsigned long memory_block_size_probed; +unsigned long memory_block_size_bytes(void) +{ + if (!memory_block_size_probed) + memory_block_size_probed = probe_memory_block_size(); + + return memory_block_size_probed; +} + #ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Initialise the sparsemem vmemmap using huge-pages at the PMD level. diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 597ac15..baff1da 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -50,6 +50,21 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, return err; } +static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, + void *arg) +{ + unsigned long i; + + for (i = 0; i < nr_pages; ++i) + if (pfn_valid(start_pfn + i) && + !PageReserved(pfn_to_page(start_pfn + i))) + return 1; + + WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn); + + return 0; +} + /* * Remap an arbitrary physical address space into the kernel virtual * address space. Needed when the kernel wants to access high addresses @@ -93,14 +108,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ + pfn = phys_addr >> PAGE_SHIFT; last_pfn = last_addr >> PAGE_SHIFT; - for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) { - int is_ram = page_is_ram(pfn); - - if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) - return NULL; - WARN_ON_ONCE(is_ram); - } + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) + return NULL; /* * Mappings have to be page-aligned @@ -355,6 +367,12 @@ void __init early_ioremap_init(void) { pmd_t *pmd; +#ifdef CONFIG_X86_64 + BUILD_BUG_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1)); +#else + WARN_ON((fix_to_virt(0) + PAGE_SIZE) & ((1 << PMD_SHIFT) - 1)); +#endif + early_ioremap_setup(); pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 1d045f9..a32b706 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -559,7 +559,7 @@ static void __init numa_clear_kernel_node_hotplug(void) int i, nid; nodemask_t numa_kernel_nodes = NODE_MASK_NONE; unsigned long start, end; - struct memblock_type *type = &memblock.reserved; + struct memblock_region *r; /* * At this time, all memory regions reserved by memblock are @@ -573,8 +573,8 @@ static void __init numa_clear_kernel_node_hotplug(void) } /* Mark all kernel nodes. */ - for (i = 0; i < type->cnt; i++) - node_set(type->regions[i].nid, numa_kernel_nodes); + for_each_memblock(reserved, r) + node_set(r->nid, numa_kernel_nodes); /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ for (i = 0; i < numa_meminfo.nr_blks; i++) { diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 461bc82..6629f39 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -35,7 +35,7 @@ enum { static int pte_testbit(pte_t pte) { - return pte_flags(pte) & _PAGE_UNUSED1; + return pte_flags(pte) & _PAGE_SOFTW1; } struct split_state { diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index c96314a..6fb6927 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -399,13 +399,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - int young; - - young = ptep_test_and_clear_young(vma, address, ptep); - if (young) - flush_tlb_page(vma, address); - - return young; + /* + * On x86 CPUs, clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -449,9 +456,9 @@ void __init reserve_top_address(unsigned long reserve) { #ifdef CONFIG_X86_32 BUG_ON(fixmaps_set > 0); - printk(KERN_INFO "Reserving virtual address space above 0x%08x\n", - (int)-reserve); - __FIXADDR_TOP = -reserve - PAGE_SIZE; + __FIXADDR_TOP = round_down(-reserve, 1 << PMD_SHIFT) - PAGE_SIZE; + printk(KERN_INFO "Reserving virtual address space above 0x%08lx (rounded to 0x%08lx)\n", + -reserve, __FIXADDR_TOP + PAGE_SIZE); #endif } diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S index 0149575..6440221 100644 --- a/arch/x86/net/bpf_jit.S +++ b/arch/x86/net/bpf_jit.S @@ -12,13 +12,16 @@ /* * Calling convention : - * rdi : skb pointer + * rbx : skb pointer (callee saved) * esi : offset of byte(s) to fetch in skb (can be scratched) - * r8 : copy of skb->data + * r10 : copy of skb->data * r9d : hlen = skb->len - skb->data_len */ -#define SKBDATA %r8 +#define SKBDATA %r10 #define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */ +#define MAX_BPF_STACK (512 /* from filter.h */ + \ + 32 /* space for rbx,r13,r14,r15 */ + \ + 8 /* space for skb_copy_bits */) sk_load_word: .globl sk_load_word @@ -68,53 +71,31 @@ sk_load_byte_positive_offset: movzbl (SKBDATA,%rsi),%eax ret -/** - * sk_load_byte_msh - BPF_S_LDX_B_MSH helper - * - * Implements BPF_S_LDX_B_MSH : ldxb 4*([offset]&0xf) - * Must preserve A accumulator (%eax) - * Inputs : %esi is the offset value - */ -sk_load_byte_msh: - .globl sk_load_byte_msh - test %esi,%esi - js bpf_slow_path_byte_msh_neg - -sk_load_byte_msh_positive_offset: - .globl sk_load_byte_msh_positive_offset - cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte_msh */ - jle bpf_slow_path_byte_msh - movzbl (SKBDATA,%rsi),%ebx - and $15,%bl - shl $2,%bl - ret - /* rsi contains offset and can be scratched */ #define bpf_slow_path_common(LEN) \ - push %rdi; /* save skb */ \ + mov %rbx, %rdi; /* arg1 == skb */ \ push %r9; \ push SKBDATA; \ /* rsi already has offset */ \ mov $LEN,%ecx; /* len */ \ - lea -12(%rbp),%rdx; \ + lea - MAX_BPF_STACK + 32(%rbp),%rdx; \ call skb_copy_bits; \ test %eax,%eax; \ pop SKBDATA; \ - pop %r9; \ - pop %rdi + pop %r9; bpf_slow_path_word: bpf_slow_path_common(4) js bpf_error - mov -12(%rbp),%eax + mov - MAX_BPF_STACK + 32(%rbp),%eax bswap %eax ret bpf_slow_path_half: bpf_slow_path_common(2) js bpf_error - mov -12(%rbp),%ax + mov - MAX_BPF_STACK + 32(%rbp),%ax rol $8,%ax movzwl %ax,%eax ret @@ -122,21 +103,11 @@ bpf_slow_path_half: bpf_slow_path_byte: bpf_slow_path_common(1) js bpf_error - movzbl -12(%rbp),%eax - ret - -bpf_slow_path_byte_msh: - xchg %eax,%ebx /* dont lose A , X is about to be scratched */ - bpf_slow_path_common(1) - js bpf_error - movzbl -12(%rbp),%eax - and $15,%al - shl $2,%al - xchg %eax,%ebx + movzbl - MAX_BPF_STACK + 32(%rbp),%eax ret #define sk_negative_common(SIZE) \ - push %rdi; /* save skb */ \ + mov %rbx, %rdi; /* arg1 == skb */ \ push %r9; \ push SKBDATA; \ /* rsi already has offset */ \ @@ -145,10 +116,8 @@ bpf_slow_path_byte_msh: test %rax,%rax; \ pop SKBDATA; \ pop %r9; \ - pop %rdi; \ jz bpf_error - bpf_slow_path_word_neg: cmp SKF_MAX_NEG_OFF, %esi /* test range */ jl bpf_error /* offset lower -> error */ @@ -179,22 +148,12 @@ sk_load_byte_negative_offset: movzbl (%rax), %eax ret -bpf_slow_path_byte_msh_neg: - cmp SKF_MAX_NEG_OFF, %esi - jl bpf_error -sk_load_byte_msh_negative_offset: - .globl sk_load_byte_msh_negative_offset - xchg %eax,%ebx /* dont lose A , X is about to be scratched */ - sk_negative_common(1) - movzbl (%rax),%eax - and $15,%al - shl $2,%al - xchg %eax,%ebx - ret - bpf_error: # force a return 0 from jit handler - xor %eax,%eax - mov -8(%rbp),%rbx + xor %eax,%eax + mov - MAX_BPF_STACK(%rbp),%rbx + mov - MAX_BPF_STACK + 8(%rbp),%r13 + mov - MAX_BPF_STACK + 16(%rbp),%r14 + mov - MAX_BPF_STACK + 24(%rbp),%r15 leaveq ret diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 6d5663a..99bef86 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1,6 +1,7 @@ /* bpf_jit_comp.c : BPF JIT compiler * * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com) + * Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -14,28 +15,16 @@ #include <linux/if_vlan.h> #include <linux/random.h> -/* - * Conventions : - * EAX : BPF A accumulator - * EBX : BPF X accumulator - * RDI : pointer to skb (first argument given to JIT function) - * RBP : frame pointer (even if CONFIG_FRAME_POINTER=n) - * ECX,EDX,ESI : scratch registers - * r9d : skb->len - skb->data_len (headlen) - * r8 : skb->data - * -8(RBP) : saved RBX value - * -16(RBP)..-80(RBP) : BPF_MEMWORDS values - */ int bpf_jit_enable __read_mostly; /* * assembly code in arch/x86/net/bpf_jit.S */ -extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[]; +extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[]; -extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[]; +extern u8 sk_load_byte_positive_offset[]; extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[]; -extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[]; +extern u8 sk_load_byte_negative_offset[]; static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { @@ -56,30 +45,44 @@ static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) #define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3) #define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4) -#define EMIT1_off32(b1, off) do { EMIT1(b1); EMIT(off, 4);} while (0) - -#define CLEAR_A() EMIT2(0x31, 0xc0) /* xor %eax,%eax */ -#define CLEAR_X() EMIT2(0x31, 0xdb) /* xor %ebx,%ebx */ +#define EMIT1_off32(b1, off) \ + do {EMIT1(b1); EMIT(off, 4); } while (0) +#define EMIT2_off32(b1, b2, off) \ + do {EMIT2(b1, b2); EMIT(off, 4); } while (0) +#define EMIT3_off32(b1, b2, b3, off) \ + do {EMIT3(b1, b2, b3); EMIT(off, 4); } while (0) +#define EMIT4_off32(b1, b2, b3, b4, off) \ + do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0) static inline bool is_imm8(int value) { return value <= 127 && value >= -128; } -static inline bool is_near(int offset) +static inline bool is_simm32(s64 value) { - return offset <= 127 && offset >= -128; + return value == (s64) (s32) value; } -#define EMIT_JMP(offset) \ -do { \ - if (offset) { \ - if (is_near(offset)) \ - EMIT2(0xeb, offset); /* jmp .+off8 */ \ - else \ - EMIT1_off32(0xe9, offset); /* jmp .+off32 */ \ - } \ -} while (0) +/* mov dst, src */ +#define EMIT_mov(DST, SRC) \ + do {if (DST != SRC) \ + EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \ + } while (0) + +static int bpf_size_to_x86_bytes(int bpf_size) +{ + if (bpf_size == BPF_W) + return 4; + else if (bpf_size == BPF_H) + return 2; + else if (bpf_size == BPF_B) + return 1; + else if (bpf_size == BPF_DW) + return 4; /* imm32 */ + else + return 0; +} /* list of x86 cond jumps opcodes (. + s8) * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32) @@ -90,27 +93,8 @@ do { \ #define X86_JNE 0x75 #define X86_JBE 0x76 #define X86_JA 0x77 - -#define EMIT_COND_JMP(op, offset) \ -do { \ - if (is_near(offset)) \ - EMIT2(op, offset); /* jxx .+off8 */ \ - else { \ - EMIT2(0x0f, op + 0x10); \ - EMIT(offset, 4); /* jxx .+off32 */ \ - } \ -} while (0) - -#define COND_SEL(CODE, TOP, FOP) \ - case CODE: \ - t_op = TOP; \ - f_op = FOP; \ - goto cond_branch - - -#define SEEN_DATAREF 1 /* might call external helpers */ -#define SEEN_XREG 2 /* ebx is used */ -#define SEEN_MEM 4 /* use mem[] for temporary storage */ +#define X86_JGE 0x7D +#define X86_JG 0x7F static inline void bpf_flush_icache(void *start, void *end) { @@ -125,26 +109,6 @@ static inline void bpf_flush_icache(void *start, void *end) #define CHOOSE_LOAD_FUNC(K, func) \ ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset) -/* Helper to find the offset of pkt_type in sk_buff - * We want to make sure its still a 3bit field starting at a byte boundary. - */ -#define PKT_TYPE_MAX 7 -static int pkt_type_offset(void) -{ - struct sk_buff skb_probe = { - .pkt_type = ~0, - }; - char *ct = (char *)&skb_probe; - unsigned int off; - - for (off = 0; off < sizeof(struct sk_buff); off++) { - if (ct[off] == PKT_TYPE_MAX) - return off; - } - pr_err_once("Please fix pkt_type_offset(), as pkt_type couldn't be found\n"); - return -1; -} - struct bpf_binary_header { unsigned int pages; /* Note : for security reasons, bpf code will follow a randomly @@ -178,583 +142,771 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen, return header; } -void bpf_jit_compile(struct sk_filter *fp) +/* pick a register outside of BPF range for JIT internal work */ +#define AUX_REG (MAX_BPF_REG + 1) + +/* the following table maps BPF registers to x64 registers. + * x64 register r12 is unused, since if used as base address register + * in load/store instructions, it always needs an extra byte of encoding + */ +static const int reg2hex[] = { + [BPF_REG_0] = 0, /* rax */ + [BPF_REG_1] = 7, /* rdi */ + [BPF_REG_2] = 6, /* rsi */ + [BPF_REG_3] = 2, /* rdx */ + [BPF_REG_4] = 1, /* rcx */ + [BPF_REG_5] = 0, /* r8 */ + [BPF_REG_6] = 3, /* rbx callee saved */ + [BPF_REG_7] = 5, /* r13 callee saved */ + [BPF_REG_8] = 6, /* r14 callee saved */ + [BPF_REG_9] = 7, /* r15 callee saved */ + [BPF_REG_FP] = 5, /* rbp readonly */ + [AUX_REG] = 3, /* r11 temp register */ +}; + +/* is_ereg() == true if BPF register 'reg' maps to x64 r8..r15 + * which need extra byte of encoding. + * rax,rcx,...,rbp have simpler encoding + */ +static inline bool is_ereg(u32 reg) { - u8 temp[64]; - u8 *prog; - unsigned int proglen, oldproglen = 0; - int ilen, i; - int t_offset, f_offset; - u8 t_op, f_op, seen = 0, pass; - u8 *image = NULL; - struct bpf_binary_header *header = NULL; - u8 *func; - int pc_ret0 = -1; /* bpf index of first RET #0 instruction (if any) */ - unsigned int cleanup_addr; /* epilogue code offset */ - unsigned int *addrs; - const struct sock_filter *filter = fp->insns; - int flen = fp->len; + if (reg == BPF_REG_5 || reg == AUX_REG || + (reg >= BPF_REG_7 && reg <= BPF_REG_9)) + return true; + else + return false; +} - if (!bpf_jit_enable) - return; +/* add modifiers if 'reg' maps to x64 registers r8..r15 */ +static inline u8 add_1mod(u8 byte, u32 reg) +{ + if (is_ereg(reg)) + byte |= 1; + return byte; +} - addrs = kmalloc(flen * sizeof(*addrs), GFP_KERNEL); - if (addrs == NULL) - return; +static inline u8 add_2mod(u8 byte, u32 r1, u32 r2) +{ + if (is_ereg(r1)) + byte |= 1; + if (is_ereg(r2)) + byte |= 4; + return byte; +} - /* Before first pass, make a rough estimation of addrs[] - * each bpf instruction is translated to less than 64 bytes +/* encode 'dst_reg' register into x64 opcode 'byte' */ +static inline u8 add_1reg(u8 byte, u32 dst_reg) +{ + return byte + reg2hex[dst_reg]; +} + +/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */ +static inline u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg) +{ + return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3); +} + +struct jit_context { + unsigned int cleanup_addr; /* epilogue code offset */ + bool seen_ld_abs; +}; + +static int do_jit(struct sk_filter *bpf_prog, int *addrs, u8 *image, + int oldproglen, struct jit_context *ctx) +{ + struct sock_filter_int *insn = bpf_prog->insnsi; + int insn_cnt = bpf_prog->len; + u8 temp[64]; + int i; + int proglen = 0; + u8 *prog = temp; + int stacksize = MAX_BPF_STACK + + 32 /* space for rbx, r13, r14, r15 */ + + 8 /* space for skb_copy_bits() buffer */; + + EMIT1(0x55); /* push rbp */ + EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */ + + /* sub rsp, stacksize */ + EMIT3_off32(0x48, 0x81, 0xEC, stacksize); + + /* all classic BPF filters use R6(rbx) save it */ + + /* mov qword ptr [rbp-X],rbx */ + EMIT3_off32(0x48, 0x89, 0x9D, -stacksize); + + /* sk_convert_filter() maps classic BPF register X to R7 and uses R8 + * as temporary, so all tcpdump filters need to spill/fill R7(r13) and + * R8(r14). R9(r15) spill could be made conditional, but there is only + * one 'bpf_error' return path out of helper functions inside bpf_jit.S + * The overhead of extra spill is negligible for any filter other + * than synthetic ones. Therefore not worth adding complexity. */ - for (proglen = 0, i = 0; i < flen; i++) { - proglen += 64; - addrs[i] = proglen; + + /* mov qword ptr [rbp-X],r13 */ + EMIT3_off32(0x4C, 0x89, 0xAD, -stacksize + 8); + /* mov qword ptr [rbp-X],r14 */ + EMIT3_off32(0x4C, 0x89, 0xB5, -stacksize + 16); + /* 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 */ + + if (ctx->seen_ld_abs) { + /* r9d : skb->len - skb->data_len (headlen) + * r10 : skb->data + */ + if (is_imm8(offsetof(struct sk_buff, len))) + /* mov %r9d, off8(%rdi) */ + EMIT4(0x44, 0x8b, 0x4f, + offsetof(struct sk_buff, len)); + else + /* mov %r9d, off32(%rdi) */ + EMIT3_off32(0x44, 0x8b, 0x8f, + offsetof(struct sk_buff, len)); + + if (is_imm8(offsetof(struct sk_buff, data_len))) + /* sub %r9d, off8(%rdi) */ + EMIT4(0x44, 0x2b, 0x4f, + offsetof(struct sk_buff, data_len)); + else + EMIT3_off32(0x44, 0x2b, 0x8f, + offsetof(struct sk_buff, data_len)); + + if (is_imm8(offsetof(struct sk_buff, data))) + /* mov %r10, off8(%rdi) */ + EMIT4(0x4c, 0x8b, 0x57, + offsetof(struct sk_buff, data)); + else + /* mov %r10, off32(%rdi) */ + EMIT3_off32(0x4c, 0x8b, 0x97, + offsetof(struct sk_buff, data)); } - cleanup_addr = proglen; /* epilogue address */ - for (pass = 0; pass < 10; pass++) { - u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen; - /* no prologue/epilogue for trivial filters (RET something) */ - proglen = 0; - prog = temp; + for (i = 0; i < insn_cnt; i++, insn++) { + const s32 imm32 = insn->imm; + u32 dst_reg = insn->dst_reg; + u32 src_reg = insn->src_reg; + u8 b1 = 0, b2 = 0, b3 = 0; + s64 jmp_offset; + u8 jmp_cond; + int ilen; + u8 *func; + + switch (insn->code) { + /* ALU */ + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_X: + switch (BPF_OP(insn->code)) { + case BPF_ADD: b2 = 0x01; break; + case BPF_SUB: b2 = 0x29; break; + case BPF_AND: b2 = 0x21; break; + case BPF_OR: b2 = 0x09; break; + case BPF_XOR: b2 = 0x31; break; + } + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_2mod(0x48, dst_reg, src_reg)); + else if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT1(add_2mod(0x40, dst_reg, src_reg)); + EMIT2(b2, add_2reg(0xC0, dst_reg, src_reg)); + break; - if (seen_or_pass0) { - EMIT4(0x55, 0x48, 0x89, 0xe5); /* push %rbp; mov %rsp,%rbp */ - EMIT4(0x48, 0x83, 0xec, 96); /* subq $96,%rsp */ - /* note : must save %rbx in case bpf_error is hit */ - if (seen_or_pass0 & (SEEN_XREG | SEEN_DATAREF)) - EMIT4(0x48, 0x89, 0x5d, 0xf8); /* mov %rbx, -8(%rbp) */ - if (seen_or_pass0 & SEEN_XREG) - CLEAR_X(); /* make sure we dont leek kernel memory */ - - /* - * If this filter needs to access skb data, - * loads r9 and r8 with : - * r9 = skb->len - skb->data_len - * r8 = skb->data + /* mov dst, src */ + case BPF_ALU64 | BPF_MOV | BPF_X: + EMIT_mov(dst_reg, src_reg); + break; + + /* mov32 dst, src */ + case BPF_ALU | BPF_MOV | BPF_X: + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT1(add_2mod(0x40, dst_reg, src_reg)); + EMIT2(0x89, add_2reg(0xC0, dst_reg, src_reg)); + break; + + /* neg dst */ + case BPF_ALU | BPF_NEG: + case BPF_ALU64 | BPF_NEG: + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_1mod(0x48, dst_reg)); + else if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + EMIT2(0xF7, add_1reg(0xD8, dst_reg)); + break; + + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_ADD | BPF_K: + case BPF_ALU64 | BPF_SUB | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_K: + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_1mod(0x48, dst_reg)); + else if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + + switch (BPF_OP(insn->code)) { + case BPF_ADD: b3 = 0xC0; break; + case BPF_SUB: b3 = 0xE8; break; + case BPF_AND: b3 = 0xE0; break; + case BPF_OR: b3 = 0xC8; break; + case BPF_XOR: b3 = 0xF0; break; + } + + if (is_imm8(imm32)) + EMIT3(0x83, add_1reg(b3, dst_reg), imm32); + else + EMIT2_off32(0x81, add_1reg(b3, dst_reg), imm32); + break; + + case BPF_ALU64 | BPF_MOV | BPF_K: + /* optimization: if imm32 is positive, + * use 'mov eax, imm32' (which zero-extends imm32) + * to save 2 bytes */ - if (seen_or_pass0 & SEEN_DATAREF) { - if (offsetof(struct sk_buff, len) <= 127) - /* mov off8(%rdi),%r9d */ - EMIT4(0x44, 0x8b, 0x4f, offsetof(struct sk_buff, len)); - else { - /* mov off32(%rdi),%r9d */ - EMIT3(0x44, 0x8b, 0x8f); - EMIT(offsetof(struct sk_buff, len), 4); - } - if (is_imm8(offsetof(struct sk_buff, data_len))) - /* sub off8(%rdi),%r9d */ - EMIT4(0x44, 0x2b, 0x4f, offsetof(struct sk_buff, data_len)); - else { - EMIT3(0x44, 0x2b, 0x8f); - EMIT(offsetof(struct sk_buff, data_len), 4); - } + if (imm32 < 0) { + /* 'mov rax, imm32' sign extends imm32 */ + b1 = add_1mod(0x48, dst_reg); + b2 = 0xC7; + b3 = 0xC0; + EMIT3_off32(b1, b2, add_1reg(b3, dst_reg), imm32); + break; + } - if (is_imm8(offsetof(struct sk_buff, data))) - /* mov off8(%rdi),%r8 */ - EMIT4(0x4c, 0x8b, 0x47, offsetof(struct sk_buff, data)); - else { - /* mov off32(%rdi),%r8 */ - EMIT3(0x4c, 0x8b, 0x87); - EMIT(offsetof(struct sk_buff, data), 4); - } + case BPF_ALU | BPF_MOV | BPF_K: + /* mov %eax, imm32 */ + if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + EMIT1_off32(add_1reg(0xB8, dst_reg), imm32); + break; + + /* dst %= src, dst /= src, dst %= imm32, dst /= imm32 */ + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_X: + case BPF_ALU64 | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_K: + case BPF_ALU64 | BPF_DIV | BPF_K: + EMIT1(0x50); /* push rax */ + EMIT1(0x52); /* push rdx */ + + if (BPF_SRC(insn->code) == BPF_X) + /* mov r11, src_reg */ + EMIT_mov(AUX_REG, src_reg); + else + /* mov r11, imm32 */ + EMIT3_off32(0x49, 0xC7, 0xC3, imm32); + + /* mov rax, dst_reg */ + EMIT_mov(BPF_REG_0, dst_reg); + + /* xor edx, edx + * equivalent to 'xor rdx, rdx', but one byte less + */ + EMIT2(0x31, 0xd2); + + if (BPF_SRC(insn->code) == BPF_X) { + /* if (src_reg == 0) return 0 */ + + /* cmp r11, 0 */ + EMIT4(0x49, 0x83, 0xFB, 0x00); + + /* jne .+9 (skip over pop, pop, xor and jmp) */ + EMIT2(X86_JNE, 1 + 1 + 2 + 5); + EMIT1(0x5A); /* pop rdx */ + EMIT1(0x58); /* pop rax */ + EMIT2(0x31, 0xc0); /* xor eax, eax */ + + /* jmp cleanup_addr + * addrs[i] - 11, because there are 11 bytes + * after this insn: div, mov, pop, pop, mov + */ + jmp_offset = ctx->cleanup_addr - (addrs[i] - 11); + EMIT1_off32(0xE9, jmp_offset); } - } - switch (filter[0].code) { - case BPF_S_RET_K: - case BPF_S_LD_W_LEN: - case BPF_S_ANC_PROTOCOL: - case BPF_S_ANC_IFINDEX: - case BPF_S_ANC_MARK: - case BPF_S_ANC_RXHASH: - case BPF_S_ANC_CPU: - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: - case BPF_S_ANC_QUEUE: - case BPF_S_ANC_PKTTYPE: - case BPF_S_LD_W_ABS: - case BPF_S_LD_H_ABS: - case BPF_S_LD_B_ABS: - /* first instruction sets A register (or is RET 'constant') */ + if (BPF_CLASS(insn->code) == BPF_ALU64) + /* div r11 */ + EMIT3(0x49, 0xF7, 0xF3); + else + /* div r11d */ + EMIT3(0x41, 0xF7, 0xF3); + + if (BPF_OP(insn->code) == BPF_MOD) + /* mov r11, rdx */ + EMIT3(0x49, 0x89, 0xD3); + else + /* mov r11, rax */ + EMIT3(0x49, 0x89, 0xC3); + + EMIT1(0x5A); /* pop rdx */ + EMIT1(0x58); /* pop rax */ + + /* mov dst_reg, r11 */ + EMIT_mov(dst_reg, AUX_REG); break; - default: - /* make sure we dont leak kernel information to user */ - CLEAR_A(); /* A = 0 */ - } - for (i = 0; i < flen; i++) { - unsigned int K = filter[i].k; + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_K: + case BPF_ALU64 | BPF_MUL | BPF_X: + EMIT1(0x50); /* push rax */ + EMIT1(0x52); /* push rdx */ + + /* mov r11, dst_reg */ + EMIT_mov(AUX_REG, dst_reg); + + if (BPF_SRC(insn->code) == BPF_X) + /* mov rax, src_reg */ + EMIT_mov(BPF_REG_0, src_reg); + else + /* mov rax, imm32 */ + EMIT3_off32(0x48, 0xC7, 0xC0, imm32); + + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_1mod(0x48, AUX_REG)); + else if (is_ereg(AUX_REG)) + EMIT1(add_1mod(0x40, AUX_REG)); + /* mul(q) r11 */ + EMIT2(0xF7, add_1reg(0xE0, AUX_REG)); + + /* mov r11, rax */ + EMIT_mov(AUX_REG, BPF_REG_0); + + EMIT1(0x5A); /* pop rdx */ + EMIT1(0x58); /* pop rax */ + + /* mov dst_reg, r11 */ + EMIT_mov(dst_reg, AUX_REG); + break; - switch (filter[i].code) { - case BPF_S_ALU_ADD_X: /* A += X; */ - seen |= SEEN_XREG; - EMIT2(0x01, 0xd8); /* add %ebx,%eax */ - break; - case BPF_S_ALU_ADD_K: /* A += K; */ - if (!K) - break; - if (is_imm8(K)) - EMIT3(0x83, 0xc0, K); /* add imm8,%eax */ - else - EMIT1_off32(0x05, K); /* add imm32,%eax */ - break; - case BPF_S_ALU_SUB_X: /* A -= X; */ - seen |= SEEN_XREG; - EMIT2(0x29, 0xd8); /* sub %ebx,%eax */ - break; - case BPF_S_ALU_SUB_K: /* A -= K */ - if (!K) - break; - if (is_imm8(K)) - EMIT3(0x83, 0xe8, K); /* sub imm8,%eax */ - else - EMIT1_off32(0x2d, K); /* sub imm32,%eax */ - break; - case BPF_S_ALU_MUL_X: /* A *= X; */ - seen |= SEEN_XREG; - EMIT3(0x0f, 0xaf, 0xc3); /* imul %ebx,%eax */ - break; - case BPF_S_ALU_MUL_K: /* A *= K */ - if (is_imm8(K)) - EMIT3(0x6b, 0xc0, K); /* imul imm8,%eax,%eax */ - else { - EMIT2(0x69, 0xc0); /* imul imm32,%eax */ - EMIT(K, 4); - } - break; - case BPF_S_ALU_DIV_X: /* A /= X; */ - seen |= SEEN_XREG; - EMIT2(0x85, 0xdb); /* test %ebx,%ebx */ - if (pc_ret0 > 0) { - /* addrs[pc_ret0 - 1] is start address of target - * (addrs[i] - 4) is the address following this jmp - * ("xor %edx,%edx; div %ebx" being 4 bytes long) - */ - EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] - - (addrs[i] - 4)); - } else { - EMIT_COND_JMP(X86_JNE, 2 + 5); - CLEAR_A(); - EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 4)); /* jmp .+off32 */ - } - EMIT4(0x31, 0xd2, 0xf7, 0xf3); /* xor %edx,%edx; div %ebx */ - break; - case BPF_S_ALU_MOD_X: /* A %= X; */ - seen |= SEEN_XREG; - EMIT2(0x85, 0xdb); /* test %ebx,%ebx */ - if (pc_ret0 > 0) { - /* addrs[pc_ret0 - 1] is start address of target - * (addrs[i] - 6) is the address following this jmp - * ("xor %edx,%edx; div %ebx;mov %edx,%eax" being 6 bytes long) - */ - EMIT_COND_JMP(X86_JE, addrs[pc_ret0 - 1] - - (addrs[i] - 6)); - } else { - EMIT_COND_JMP(X86_JNE, 2 + 5); - CLEAR_A(); - EMIT1_off32(0xe9, cleanup_addr - (addrs[i] - 6)); /* jmp .+off32 */ - } - EMIT2(0x31, 0xd2); /* xor %edx,%edx */ - EMIT2(0xf7, 0xf3); /* div %ebx */ - EMIT2(0x89, 0xd0); /* mov %edx,%eax */ - break; - case BPF_S_ALU_MOD_K: /* A %= K; */ - if (K == 1) { - CLEAR_A(); - break; - } - EMIT2(0x31, 0xd2); /* xor %edx,%edx */ - EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */ - EMIT2(0xf7, 0xf1); /* div %ecx */ - EMIT2(0x89, 0xd0); /* mov %edx,%eax */ - break; - case BPF_S_ALU_DIV_K: /* A /= K */ - if (K == 1) - break; - EMIT2(0x31, 0xd2); /* xor %edx,%edx */ - EMIT1(0xb9);EMIT(K, 4); /* mov imm32,%ecx */ - EMIT2(0xf7, 0xf1); /* div %ecx */ - break; - case BPF_S_ALU_AND_X: - seen |= SEEN_XREG; - EMIT2(0x21, 0xd8); /* and %ebx,%eax */ - break; - case BPF_S_ALU_AND_K: - if (K >= 0xFFFFFF00) { - EMIT2(0x24, K & 0xFF); /* and imm8,%al */ - } else if (K >= 0xFFFF0000) { - EMIT2(0x66, 0x25); /* and imm16,%ax */ - EMIT(K, 2); - } else { - EMIT1_off32(0x25, K); /* and imm32,%eax */ - } - break; - case BPF_S_ALU_OR_X: - seen |= SEEN_XREG; - EMIT2(0x09, 0xd8); /* or %ebx,%eax */ - break; - case BPF_S_ALU_OR_K: - if (is_imm8(K)) - EMIT3(0x83, 0xc8, K); /* or imm8,%eax */ - else - EMIT1_off32(0x0d, K); /* or imm32,%eax */ - break; - case BPF_S_ANC_ALU_XOR_X: /* A ^= X; */ - case BPF_S_ALU_XOR_X: - seen |= SEEN_XREG; - EMIT2(0x31, 0xd8); /* xor %ebx,%eax */ - break; - case BPF_S_ALU_XOR_K: /* A ^= K; */ - if (K == 0) - break; - if (is_imm8(K)) - EMIT3(0x83, 0xf0, K); /* xor imm8,%eax */ - else - EMIT1_off32(0x35, K); /* xor imm32,%eax */ - break; - case BPF_S_ALU_LSH_X: /* A <<= X; */ - seen |= SEEN_XREG; - EMIT4(0x89, 0xd9, 0xd3, 0xe0); /* mov %ebx,%ecx; shl %cl,%eax */ - break; - case BPF_S_ALU_LSH_K: - if (K == 0) - break; - else if (K == 1) - EMIT2(0xd1, 0xe0); /* shl %eax */ - else - EMIT3(0xc1, 0xe0, K); - break; - case BPF_S_ALU_RSH_X: /* A >>= X; */ - seen |= SEEN_XREG; - EMIT4(0x89, 0xd9, 0xd3, 0xe8); /* mov %ebx,%ecx; shr %cl,%eax */ - break; - case BPF_S_ALU_RSH_K: /* A >>= K; */ - if (K == 0) - break; - else if (K == 1) - EMIT2(0xd1, 0xe8); /* shr %eax */ - else - EMIT3(0xc1, 0xe8, K); - break; - case BPF_S_ALU_NEG: - EMIT2(0xf7, 0xd8); /* neg %eax */ - break; - case BPF_S_RET_K: - if (!K) { - if (pc_ret0 == -1) - pc_ret0 = i; - CLEAR_A(); - } else { - EMIT1_off32(0xb8, K); /* mov $imm32,%eax */ - } - /* fallinto */ - case BPF_S_RET_A: - if (seen_or_pass0) { - if (i != flen - 1) { - EMIT_JMP(cleanup_addr - addrs[i]); - break; - } - if (seen_or_pass0 & SEEN_XREG) - EMIT4(0x48, 0x8b, 0x5d, 0xf8); /* mov -8(%rbp),%rbx */ - EMIT1(0xc9); /* leaveq */ - } - EMIT1(0xc3); /* ret */ - break; - case BPF_S_MISC_TAX: /* X = A */ - seen |= SEEN_XREG; - EMIT2(0x89, 0xc3); /* mov %eax,%ebx */ - break; - case BPF_S_MISC_TXA: /* A = X */ - seen |= SEEN_XREG; - EMIT2(0x89, 0xd8); /* mov %ebx,%eax */ - break; - case BPF_S_LD_IMM: /* A = K */ - if (!K) - CLEAR_A(); - else - EMIT1_off32(0xb8, K); /* mov $imm32,%eax */ - break; - case BPF_S_LDX_IMM: /* X = K */ - seen |= SEEN_XREG; - if (!K) - CLEAR_X(); + /* shifts */ + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_ARSH | BPF_K: + case BPF_ALU64 | BPF_LSH | BPF_K: + case BPF_ALU64 | BPF_RSH | BPF_K: + case BPF_ALU64 | BPF_ARSH | BPF_K: + if (BPF_CLASS(insn->code) == BPF_ALU64) + EMIT1(add_1mod(0x48, dst_reg)); + else if (is_ereg(dst_reg)) + EMIT1(add_1mod(0x40, dst_reg)); + + switch (BPF_OP(insn->code)) { + case BPF_LSH: b3 = 0xE0; break; + case BPF_RSH: b3 = 0xE8; break; + case BPF_ARSH: b3 = 0xF8; break; + } + EMIT3(0xC1, add_1reg(b3, dst_reg), imm32); + break; + + case BPF_ALU | BPF_END | BPF_FROM_BE: + switch (imm32) { + case 16: + /* emit 'ror %ax, 8' to swap lower 2 bytes */ + EMIT1(0x66); + if (is_ereg(dst_reg)) + EMIT1(0x41); + EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8); + break; + case 32: + /* emit 'bswap eax' to swap lower 4 bytes */ + if (is_ereg(dst_reg)) + EMIT2(0x41, 0x0F); else - EMIT1_off32(0xbb, K); /* mov $imm32,%ebx */ - break; - case BPF_S_LD_MEM: /* A = mem[K] : mov off8(%rbp),%eax */ - seen |= SEEN_MEM; - EMIT3(0x8b, 0x45, 0xf0 - K*4); - break; - case BPF_S_LDX_MEM: /* X = mem[K] : mov off8(%rbp),%ebx */ - seen |= SEEN_XREG | SEEN_MEM; - EMIT3(0x8b, 0x5d, 0xf0 - K*4); - break; - case BPF_S_ST: /* mem[K] = A : mov %eax,off8(%rbp) */ - seen |= SEEN_MEM; - EMIT3(0x89, 0x45, 0xf0 - K*4); - break; - case BPF_S_STX: /* mem[K] = X : mov %ebx,off8(%rbp) */ - seen |= SEEN_XREG | SEEN_MEM; - EMIT3(0x89, 0x5d, 0xf0 - K*4); - break; - case BPF_S_LD_W_LEN: /* A = skb->len; */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, len) != 4); - if (is_imm8(offsetof(struct sk_buff, len))) - /* mov off8(%rdi),%eax */ - EMIT3(0x8b, 0x47, offsetof(struct sk_buff, len)); - else { - EMIT2(0x8b, 0x87); - EMIT(offsetof(struct sk_buff, len), 4); - } - break; - case BPF_S_LDX_W_LEN: /* X = skb->len; */ - seen |= SEEN_XREG; - if (is_imm8(offsetof(struct sk_buff, len))) - /* mov off8(%rdi),%ebx */ - EMIT3(0x8b, 0x5f, offsetof(struct sk_buff, len)); - else { - EMIT2(0x8b, 0x9f); - EMIT(offsetof(struct sk_buff, len), 4); - } - break; - case BPF_S_ANC_PROTOCOL: /* A = ntohs(skb->protocol); */ - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); - if (is_imm8(offsetof(struct sk_buff, protocol))) { - /* movzwl off8(%rdi),%eax */ - EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, protocol)); - } else { - EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */ - EMIT(offsetof(struct sk_buff, protocol), 4); - } - EMIT2(0x86, 0xc4); /* ntohs() : xchg %al,%ah */ - break; - case BPF_S_ANC_IFINDEX: - if (is_imm8(offsetof(struct sk_buff, dev))) { - /* movq off8(%rdi),%rax */ - EMIT4(0x48, 0x8b, 0x47, offsetof(struct sk_buff, dev)); - } else { - EMIT3(0x48, 0x8b, 0x87); /* movq off32(%rdi),%rax */ - EMIT(offsetof(struct sk_buff, dev), 4); - } - EMIT3(0x48, 0x85, 0xc0); /* test %rax,%rax */ - EMIT_COND_JMP(X86_JE, cleanup_addr - (addrs[i] - 6)); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - EMIT2(0x8b, 0x80); /* mov off32(%rax),%eax */ - EMIT(offsetof(struct net_device, ifindex), 4); - break; - case BPF_S_ANC_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); - if (is_imm8(offsetof(struct sk_buff, mark))) { - /* mov off8(%rdi),%eax */ - EMIT3(0x8b, 0x47, offsetof(struct sk_buff, mark)); - } else { - EMIT2(0x8b, 0x87); - EMIT(offsetof(struct sk_buff, mark), 4); - } - break; - case BPF_S_ANC_RXHASH: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); - if (is_imm8(offsetof(struct sk_buff, hash))) { - /* mov off8(%rdi),%eax */ - EMIT3(0x8b, 0x47, offsetof(struct sk_buff, hash)); - } else { - EMIT2(0x8b, 0x87); - EMIT(offsetof(struct sk_buff, hash), 4); - } - break; - case BPF_S_ANC_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); - if (is_imm8(offsetof(struct sk_buff, queue_mapping))) { - /* movzwl off8(%rdi),%eax */ - EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, queue_mapping)); - } else { - EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */ - EMIT(offsetof(struct sk_buff, queue_mapping), 4); - } - break; - case BPF_S_ANC_CPU: -#ifdef CONFIG_SMP - EMIT4(0x65, 0x8b, 0x04, 0x25); /* mov %gs:off32,%eax */ - EMIT((u32)(unsigned long)&cpu_number, 4); /* A = smp_processor_id(); */ -#else - CLEAR_A(); -#endif + EMIT1(0x0F); + EMIT1(add_1reg(0xC8, dst_reg)); break; - case BPF_S_ANC_VLAN_TAG: - case BPF_S_ANC_VLAN_TAG_PRESENT: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); - if (is_imm8(offsetof(struct sk_buff, vlan_tci))) { - /* movzwl off8(%rdi),%eax */ - EMIT4(0x0f, 0xb7, 0x47, offsetof(struct sk_buff, vlan_tci)); - } else { - EMIT3(0x0f, 0xb7, 0x87); /* movzwl off32(%rdi),%eax */ - EMIT(offsetof(struct sk_buff, vlan_tci), 4); - } - BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); - if (filter[i].code == BPF_S_ANC_VLAN_TAG) { - EMIT3(0x80, 0xe4, 0xef); /* and $0xef,%ah */ - } else { - EMIT3(0xc1, 0xe8, 0x0c); /* shr $0xc,%eax */ - EMIT3(0x83, 0xe0, 0x01); /* and $0x1,%eax */ - } - break; - case BPF_S_ANC_PKTTYPE: - { - int off = pkt_type_offset(); - - if (off < 0) - goto out; - if (is_imm8(off)) { - /* movzbl off8(%rdi),%eax */ - EMIT4(0x0f, 0xb6, 0x47, off); - } else { - /* movbl off32(%rdi),%eax */ - EMIT3(0x0f, 0xb6, 0x87); - EMIT(off, 4); - } - EMIT3(0x83, 0xe0, PKT_TYPE_MAX); /* and $0x7,%eax */ + case 64: + /* emit 'bswap rax' to swap 8 bytes */ + EMIT3(add_1mod(0x48, dst_reg), 0x0F, + add_1reg(0xC8, dst_reg)); break; } - case BPF_S_LD_W_ABS: - func = CHOOSE_LOAD_FUNC(K, sk_load_word); -common_load: seen |= SEEN_DATAREF; - t_offset = func - (image + addrs[i]); - EMIT1_off32(0xbe, K); /* mov imm32,%esi */ - EMIT1_off32(0xe8, t_offset); /* call */ - break; - case BPF_S_LD_H_ABS: - func = CHOOSE_LOAD_FUNC(K, sk_load_half); - goto common_load; - case BPF_S_LD_B_ABS: - func = CHOOSE_LOAD_FUNC(K, sk_load_byte); - goto common_load; - case BPF_S_LDX_B_MSH: - func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh); - seen |= SEEN_DATAREF | SEEN_XREG; - t_offset = func - (image + addrs[i]); - EMIT1_off32(0xbe, K); /* mov imm32,%esi */ - EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */ - break; - case BPF_S_LD_W_IND: - func = sk_load_word; -common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG; - t_offset = func - (image + addrs[i]); - if (K) { - if (is_imm8(K)) { - EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */ - } else { - EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */ - EMIT(K, 4); - } - } else { - EMIT2(0x89,0xde); /* mov %ebx,%esi */ - } - EMIT1_off32(0xe8, t_offset); /* call sk_load_xxx_ind */ - break; - case BPF_S_LD_H_IND: - func = sk_load_half; - goto common_load_ind; - case BPF_S_LD_B_IND: - func = sk_load_byte; - goto common_load_ind; - case BPF_S_JMP_JA: - t_offset = addrs[i + K] - addrs[i]; - EMIT_JMP(t_offset); - break; - COND_SEL(BPF_S_JMP_JGT_K, X86_JA, X86_JBE); - COND_SEL(BPF_S_JMP_JGE_K, X86_JAE, X86_JB); - COND_SEL(BPF_S_JMP_JEQ_K, X86_JE, X86_JNE); - COND_SEL(BPF_S_JMP_JSET_K,X86_JNE, X86_JE); - COND_SEL(BPF_S_JMP_JGT_X, X86_JA, X86_JBE); - COND_SEL(BPF_S_JMP_JGE_X, X86_JAE, X86_JB); - COND_SEL(BPF_S_JMP_JEQ_X, X86_JE, X86_JNE); - COND_SEL(BPF_S_JMP_JSET_X,X86_JNE, X86_JE); - -cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; - t_offset = addrs[i + filter[i].jt] - addrs[i]; - - /* same targets, can avoid doing the test :) */ - if (filter[i].jt == filter[i].jf) { - EMIT_JMP(t_offset); - break; - } + break; + + case BPF_ALU | BPF_END | BPF_FROM_LE: + break; + + /* ST: *(u8*)(dst_reg + off) = imm */ + case BPF_ST | BPF_MEM | BPF_B: + if (is_ereg(dst_reg)) + EMIT2(0x41, 0xC6); + else + EMIT1(0xC6); + goto st; + case BPF_ST | BPF_MEM | BPF_H: + if (is_ereg(dst_reg)) + EMIT3(0x66, 0x41, 0xC7); + else + EMIT2(0x66, 0xC7); + goto st; + case BPF_ST | BPF_MEM | BPF_W: + if (is_ereg(dst_reg)) + EMIT2(0x41, 0xC7); + else + EMIT1(0xC7); + goto st; + case BPF_ST | BPF_MEM | BPF_DW: + EMIT2(add_1mod(0x48, dst_reg), 0xC7); + +st: if (is_imm8(insn->off)) + EMIT2(add_1reg(0x40, dst_reg), insn->off); + else + EMIT1_off32(add_1reg(0x80, dst_reg), insn->off); + + EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(insn->code))); + break; + + /* STX: *(u8*)(dst_reg + off) = src_reg */ + case BPF_STX | BPF_MEM | BPF_B: + /* emit 'mov byte ptr [rax + off], al' */ + if (is_ereg(dst_reg) || is_ereg(src_reg) || + /* have to add extra byte for x86 SIL, DIL regs */ + src_reg == BPF_REG_1 || src_reg == BPF_REG_2) + EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); + else + EMIT1(0x88); + goto stx; + case BPF_STX | BPF_MEM | BPF_H: + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT3(0x66, add_2mod(0x40, dst_reg, src_reg), 0x89); + else + EMIT2(0x66, 0x89); + goto stx; + case BPF_STX | BPF_MEM | BPF_W: + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x89); + else + EMIT1(0x89); + goto stx; + case BPF_STX | BPF_MEM | BPF_DW: + EMIT2(add_2mod(0x48, dst_reg, src_reg), 0x89); +stx: if (is_imm8(insn->off)) + EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off); + else + EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), + insn->off); + break; + + /* LDX: dst_reg = *(u8*)(src_reg + off) */ + case BPF_LDX | BPF_MEM | BPF_B: + /* emit 'movzx rax, byte ptr [rax + off]' */ + EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6); + goto ldx; + case BPF_LDX | BPF_MEM | BPF_H: + /* emit 'movzx rax, word ptr [rax + off]' */ + EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7); + goto ldx; + case BPF_LDX | BPF_MEM | BPF_W: + /* emit 'mov eax, dword ptr [rax+0x14]' */ + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B); + else + EMIT1(0x8B); + goto ldx; + case BPF_LDX | BPF_MEM | BPF_DW: + /* emit 'mov rax, qword ptr [rax+0x14]' */ + EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B); +ldx: /* if insn->off == 0 we can save one extra byte, but + * special case of x86 r13 which always needs an offset + * is not worth the hassle + */ + if (is_imm8(insn->off)) + EMIT2(add_2reg(0x40, src_reg, dst_reg), insn->off); + else + EMIT1_off32(add_2reg(0x80, src_reg, dst_reg), + insn->off); + break; + + /* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */ + case BPF_STX | BPF_XADD | BPF_W: + /* emit 'lock add dword ptr [rax + off], eax' */ + if (is_ereg(dst_reg) || is_ereg(src_reg)) + EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01); + else + EMIT2(0xF0, 0x01); + goto xadd; + case BPF_STX | BPF_XADD | BPF_DW: + EMIT3(0xF0, add_2mod(0x48, dst_reg, src_reg), 0x01); +xadd: if (is_imm8(insn->off)) + EMIT2(add_2reg(0x40, dst_reg, src_reg), insn->off); + else + EMIT1_off32(add_2reg(0x80, dst_reg, src_reg), + insn->off); + break; + + /* call */ + case BPF_JMP | BPF_CALL: + func = (u8 *) __bpf_call_base + imm32; + jmp_offset = func - (image + addrs[i]); + if (ctx->seen_ld_abs) { + EMIT2(0x41, 0x52); /* push %r10 */ + EMIT2(0x41, 0x51); /* push %r9 */ + /* need to adjust jmp offset, since + * pop %r9, pop %r10 take 4 bytes after call insn + */ + jmp_offset += 4; + } + if (!imm32 || !is_simm32(jmp_offset)) { + pr_err("unsupported bpf func %d addr %p image %p\n", + imm32, func, image); + return -EINVAL; + } + EMIT1_off32(0xE8, jmp_offset); + if (ctx->seen_ld_abs) { + EMIT2(0x41, 0x59); /* pop %r9 */ + EMIT2(0x41, 0x5A); /* pop %r10 */ + } + break; + + /* cond jump */ + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_X: + /* cmp dst_reg, src_reg */ + EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x39, + add_2reg(0xC0, dst_reg, src_reg)); + goto emit_cond_jmp; + + case BPF_JMP | BPF_JSET | BPF_X: + /* test dst_reg, src_reg */ + EMIT3(add_2mod(0x48, dst_reg, src_reg), 0x85, + add_2reg(0xC0, dst_reg, src_reg)); + goto emit_cond_jmp; + + case BPF_JMP | BPF_JSET | BPF_K: + /* test dst_reg, imm32 */ + EMIT1(add_1mod(0x48, dst_reg)); + EMIT2_off32(0xF7, add_1reg(0xC0, dst_reg), imm32); + goto emit_cond_jmp; + + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSGE | BPF_K: + /* cmp dst_reg, imm8/32 */ + EMIT1(add_1mod(0x48, dst_reg)); + + if (is_imm8(imm32)) + EMIT3(0x83, add_1reg(0xF8, dst_reg), imm32); + else + EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32); + +emit_cond_jmp: /* convert BPF opcode to x86 */ + switch (BPF_OP(insn->code)) { + case BPF_JEQ: + jmp_cond = X86_JE; + break; + case BPF_JSET: + case BPF_JNE: + jmp_cond = X86_JNE; + break; + case BPF_JGT: + /* GT is unsigned '>', JA in x86 */ + jmp_cond = X86_JA; + break; + case BPF_JGE: + /* GE is unsigned '>=', JAE in x86 */ + jmp_cond = X86_JAE; + break; + case BPF_JSGT: + /* signed '>', GT in x86 */ + jmp_cond = X86_JG; + break; + case BPF_JSGE: + /* signed '>=', GE in x86 */ + jmp_cond = X86_JGE; + break; + default: /* to silence gcc warning */ + return -EFAULT; + } + jmp_offset = addrs[i + insn->off] - addrs[i]; + if (is_imm8(jmp_offset)) { + EMIT2(jmp_cond, jmp_offset); + } else if (is_simm32(jmp_offset)) { + EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset); + } else { + pr_err("cond_jmp gen bug %llx\n", jmp_offset); + return -EFAULT; + } + + break; - switch (filter[i].code) { - case BPF_S_JMP_JGT_X: - case BPF_S_JMP_JGE_X: - case BPF_S_JMP_JEQ_X: - seen |= SEEN_XREG; - EMIT2(0x39, 0xd8); /* cmp %ebx,%eax */ - break; - case BPF_S_JMP_JSET_X: - seen |= SEEN_XREG; - EMIT2(0x85, 0xd8); /* test %ebx,%eax */ - break; - case BPF_S_JMP_JEQ_K: - if (K == 0) { - EMIT2(0x85, 0xc0); /* test %eax,%eax */ - break; - } - case BPF_S_JMP_JGT_K: - case BPF_S_JMP_JGE_K: - if (K <= 127) - EMIT3(0x83, 0xf8, K); /* cmp imm8,%eax */ + case BPF_JMP | BPF_JA: + jmp_offset = addrs[i + insn->off] - addrs[i]; + if (!jmp_offset) + /* optimize out nop jumps */ + break; +emit_jmp: + if (is_imm8(jmp_offset)) { + EMIT2(0xEB, jmp_offset); + } else if (is_simm32(jmp_offset)) { + EMIT1_off32(0xE9, jmp_offset); + } else { + pr_err("jmp gen bug %llx\n", jmp_offset); + return -EFAULT; + } + break; + + case BPF_LD | BPF_IND | BPF_W: + func = sk_load_word; + goto common_load; + case BPF_LD | BPF_ABS | BPF_W: + func = CHOOSE_LOAD_FUNC(imm32, sk_load_word); +common_load: ctx->seen_ld_abs = true; + jmp_offset = func - (image + addrs[i]); + if (!func || !is_simm32(jmp_offset)) { + pr_err("unsupported bpf func %d addr %p image %p\n", + imm32, func, image); + return -EINVAL; + } + if (BPF_MODE(insn->code) == BPF_ABS) { + /* mov %esi, imm32 */ + EMIT1_off32(0xBE, imm32); + } else { + /* mov %rsi, src_reg */ + EMIT_mov(BPF_REG_2, src_reg); + if (imm32) { + if (is_imm8(imm32)) + /* add %esi, imm8 */ + EMIT3(0x83, 0xC6, imm32); else - EMIT1_off32(0x3d, K); /* cmp imm32,%eax */ - break; - case BPF_S_JMP_JSET_K: - if (K <= 0xFF) - EMIT2(0xa8, K); /* test imm8,%al */ - else if (!(K & 0xFFFF00FF)) - EMIT3(0xf6, 0xc4, K >> 8); /* test imm8,%ah */ - else if (K <= 0xFFFF) { - EMIT2(0x66, 0xa9); /* test imm16,%ax */ - EMIT(K, 2); - } else { - EMIT1_off32(0xa9, K); /* test imm32,%eax */ - } - break; + /* add %esi, imm32 */ + EMIT2_off32(0x81, 0xC6, imm32); } - if (filter[i].jt != 0) { - if (filter[i].jf && f_offset) - t_offset += is_near(f_offset) ? 2 : 5; - EMIT_COND_JMP(t_op, t_offset); - if (filter[i].jf) - EMIT_JMP(f_offset); - break; - } - EMIT_COND_JMP(f_op, f_offset); - break; - default: - /* hmm, too complex filter, give up with jit compiler */ - goto out; } - ilen = prog - temp; - if (image) { - if (unlikely(proglen + ilen > oldproglen)) { - pr_err("bpb_jit_compile fatal error\n"); - kfree(addrs); - module_free(NULL, header); - return; - } - memcpy(image + proglen, temp, ilen); + /* skb pointer is in R6 (%rbx), it will be copied into + * %rdi if skb_copy_bits() call is necessary. + * sk_load_* helpers also use %r10 and %r9d. + * See bpf_jit.S + */ + EMIT1_off32(0xE8, jmp_offset); /* call */ + break; + + case BPF_LD | BPF_IND | BPF_H: + func = sk_load_half; + goto common_load; + case BPF_LD | BPF_ABS | BPF_H: + func = CHOOSE_LOAD_FUNC(imm32, sk_load_half); + goto common_load; + case BPF_LD | BPF_IND | BPF_B: + func = sk_load_byte; + goto common_load; + case BPF_LD | BPF_ABS | BPF_B: + func = CHOOSE_LOAD_FUNC(imm32, sk_load_byte); + goto common_load; + + case BPF_JMP | BPF_EXIT: + if (i != insn_cnt - 1) { + jmp_offset = ctx->cleanup_addr - addrs[i]; + goto emit_jmp; } - proglen += ilen; - addrs[i] = proglen; - prog = temp; + /* update cleanup_addr */ + ctx->cleanup_addr = proglen; + /* mov rbx, qword ptr [rbp-X] */ + EMIT3_off32(0x48, 0x8B, 0x9D, -stacksize); + /* mov r13, qword ptr [rbp-X] */ + EMIT3_off32(0x4C, 0x8B, 0xAD, -stacksize + 8); + /* mov r14, qword ptr [rbp-X] */ + EMIT3_off32(0x4C, 0x8B, 0xB5, -stacksize + 16); + /* mov r15, qword ptr [rbp-X] */ + EMIT3_off32(0x4C, 0x8B, 0xBD, -stacksize + 24); + + EMIT1(0xC9); /* leave */ + EMIT1(0xC3); /* ret */ + break; + + default: + /* By design x64 JIT should support all BPF instructions + * This error will be seen if new instruction was added + * to interpreter, but not to JIT + * or if there is junk in sk_filter + */ + pr_err("bpf_jit: unknown opcode %02x\n", insn->code); + return -EINVAL; } - /* last bpf instruction is always a RET : - * use it to give the cleanup instruction(s) addr - */ - cleanup_addr = proglen - 1; /* ret */ - if (seen_or_pass0) - cleanup_addr -= 1; /* leaveq */ - if (seen_or_pass0 & SEEN_XREG) - cleanup_addr -= 4; /* mov -8(%rbp),%rbx */ + ilen = prog - temp; + if (image) { + if (unlikely(proglen + ilen > oldproglen)) { + pr_err("bpf_jit_compile fatal error\n"); + return -EFAULT; + } + memcpy(image + proglen, temp, ilen); + } + proglen += ilen; + addrs[i] = proglen; + prog = temp; + } + return proglen; +} + +void bpf_jit_compile(struct sk_filter *prog) +{ +} + +void bpf_int_jit_compile(struct sk_filter *prog) +{ + struct bpf_binary_header *header = NULL; + int proglen, oldproglen = 0; + struct jit_context ctx = {}; + u8 *image = NULL; + int *addrs; + int pass; + int i; + + if (!bpf_jit_enable) + return; + + if (!prog || !prog->len) + return; + + addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL); + if (!addrs) + return; + + /* Before first pass, make a rough estimation of addrs[] + * each bpf instruction is translated to less than 64 bytes + */ + for (proglen = 0, i = 0; i < prog->len; i++) { + proglen += 64; + addrs[i] = proglen; + } + ctx.cleanup_addr = proglen; + + for (pass = 0; pass < 10; pass++) { + proglen = do_jit(prog, addrs, image, oldproglen, &ctx); + if (proglen <= 0) { + image = NULL; + if (header) + module_free(NULL, header); + goto out; + } if (image) { if (proglen != oldproglen) - pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", proglen, oldproglen); + pr_err("bpf_jit: proglen=%d != oldproglen=%d\n", + proglen, oldproglen); break; } if (proglen == oldproglen) { @@ -766,17 +918,16 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; } if (bpf_jit_enable > 1) - bpf_jit_dump(flen, proglen, pass, image); + bpf_jit_dump(prog->len, proglen, 0, image); if (image) { bpf_flush_icache(header, image + proglen); set_memory_ro((unsigned long)header, header->pages); - fp->bpf_func = (void *)image; - fp->jited = 1; + prog->bpf_func = (void *)image; + prog->jited = 1; } out: kfree(addrs); - return; } static void bpf_jit_free_deferred(struct work_struct *work) diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 01edac6..5075371 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -489,8 +489,12 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) } node = acpi_get_node(device->handle); - if (node == NUMA_NO_NODE) + if (node == NUMA_NO_NODE) { node = x86_pci_root_bus_node(busnum); + if (node != 0 && node != NUMA_NO_NODE) + dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n", + node); + } if (node != NUMA_NO_NODE && !node_online(node)) node = NUMA_NO_NODE; diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index e88f4c5..c20d2cc 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -11,27 +11,33 @@ #include "bus_numa.h" -/* - * This discovers the pcibus <-> node mapping on AMD K8. - * also get peer root bus resource for io,mmio - */ +#define AMD_NB_F0_NODE_ID 0x60 +#define AMD_NB_F0_UNIT_ID 0x64 +#define AMD_NB_F1_CONFIG_MAP_REG 0xe0 + +#define RANGE_NUM 16 +#define AMD_NB_F1_CONFIG_MAP_RANGES 4 -struct pci_hostbridge_probe { +struct amd_hostbridge { u32 bus; u32 slot; - u32 vendor; u32 device; }; -static struct pci_hostbridge_probe pci_probes[] __initdata = { - { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1100 }, - { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 }, - { 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 }, - { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1300 }, +/* + * IMPORTANT NOTE: + * hb_probes[] and early_root_info_init() is in maintenance mode. + * It only supports K8, Fam10h, Fam11h, and Fam15h_00h-0fh . + * Future processor will rely on information in ACPI. + */ +static struct amd_hostbridge hb_probes[] __initdata = { + { 0, 0x18, 0x1100 }, /* K8 */ + { 0, 0x18, 0x1200 }, /* Family10h */ + { 0xff, 0, 0x1200 }, /* Family10h */ + { 0, 0x18, 0x1300 }, /* Family11h */ + { 0, 0x18, 0x1600 }, /* Family15h */ }; -#define RANGE_NUM 16 - static struct pci_root_info __init *find_pci_root_info(int node, int link) { struct pci_root_info *info; @@ -45,12 +51,12 @@ static struct pci_root_info __init *find_pci_root_info(int node, int link) } /** - * early_fill_mp_bus_to_node() + * early_root_info_init() * called before pcibios_scan_root and pci_scan_bus - * fills the mp_bus_to_cpumask array based according to the LDT Bus Number - * Registers found in the K8 northbridge + * fills the mp_bus_to_cpumask array based according + * to the LDT Bus Number Registers found in the northbridge. */ -static int __init early_fill_mp_bus_info(void) +static int __init early_root_info_init(void) { int i; unsigned bus; @@ -75,19 +81,21 @@ static int __init early_fill_mp_bus_info(void) return -1; found = false; - for (i = 0; i < ARRAY_SIZE(pci_probes); i++) { + for (i = 0; i < ARRAY_SIZE(hb_probes); i++) { u32 id; u16 device; u16 vendor; - bus = pci_probes[i].bus; - slot = pci_probes[i].slot; + bus = hb_probes[i].bus; + slot = hb_probes[i].slot; id = read_pci_config(bus, slot, 0, PCI_VENDOR_ID); - vendor = id & 0xffff; device = (id>>16) & 0xffff; - if (pci_probes[i].vendor == vendor && - pci_probes[i].device == device) { + + if (vendor != PCI_VENDOR_ID_AMD) + continue; + + if (hb_probes[i].device == device) { found = true; break; } @@ -96,10 +104,16 @@ static int __init early_fill_mp_bus_info(void) if (!found) return 0; - for (i = 0; i < 4; i++) { + /* + * We should learn topology and routing information from _PXM and + * _CRS methods in the ACPI namespace. We extract node numbers + * here to work around BIOSes that don't supply _PXM. + */ + for (i = 0; i < AMD_NB_F1_CONFIG_MAP_RANGES; i++) { int min_bus; int max_bus; - reg = read_pci_config(bus, slot, 1, 0xe0 + (i << 2)); + reg = read_pci_config(bus, slot, 1, + AMD_NB_F1_CONFIG_MAP_REG + (i << 2)); /* Check if that register is enabled for bus range */ if ((reg & 7) != 3) @@ -113,10 +127,21 @@ static int __init early_fill_mp_bus_info(void) info = alloc_pci_root_info(min_bus, max_bus, node, link); } + /* + * The following code extracts routing information for use on old + * systems where Linux doesn't automatically use host bridge _CRS + * methods (or when the user specifies "pci=nocrs"). + * + * We only do this through Fam11h, because _CRS should be enough on + * newer systems. + */ + if (boot_cpu_data.x86 > 0x11) + return 0; + /* get the default node and link for left over res */ - reg = read_pci_config(bus, slot, 0, 0x60); + reg = read_pci_config(bus, slot, 0, AMD_NB_F0_NODE_ID); def_node = (reg >> 8) & 0x07; - reg = read_pci_config(bus, slot, 0, 0x64); + reg = read_pci_config(bus, slot, 0, AMD_NB_F0_UNIT_ID); def_link = (reg >> 8) & 0x03; memset(range, 0, sizeof(range)); @@ -363,7 +388,7 @@ static int __init pci_io_ecs_init(void) int cpu; /* assume all cpus from fam10h have IO ECS */ - if (boot_cpu_data.x86 < 0x10) + if (boot_cpu_data.x86 < 0x10) return 0; /* Try the PCI method first. */ @@ -387,7 +412,7 @@ static int __init amd_postcore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return 0; - early_fill_mp_bus_info(); + early_root_info_init(); pci_io_ecs_init(); return 0; diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c index 614392c..bb461cf 100644 --- a/arch/x86/pci/broadcom_bus.c +++ b/arch/x86/pci/broadcom_bus.c @@ -60,8 +60,8 @@ static void __init cnb20le_res(u8 bus, u8 slot, u8 func) word1 = read_pci_config_16(bus, slot, func, 0xc4); word2 = read_pci_config_16(bus, slot, func, 0xc6); if (word1 != word2) { - res.start = (word1 << 16) | 0x0000; - res.end = (word2 << 16) | 0xffff; + res.start = ((resource_size_t) word1 << 16) | 0x0000; + res.end = ((resource_size_t) word2 << 16) | 0xffff; res.flags = IORESOURCE_MEM | IORESOURCE_PREFETCH; update_res(info, res.start, res.end, res.flags, 0); } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 94ae9ae..b5e6026 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -6,6 +6,7 @@ #include <linux/dmi.h> #include <linux/pci.h> #include <linux/vgaarb.h> +#include <asm/hpet.h> #include <asm/pci_x86.h> static void pci_fixup_i450nx(struct pci_dev *d) @@ -337,9 +338,7 @@ static void pci_fixup_video(struct pci_dev *pdev) * type BRIDGE, or CARDBUS. Host to PCI controllers use * PCI header type NORMAL. */ - if (bridge - && ((bridge->hdr_type == PCI_HEADER_TYPE_BRIDGE) - || (bridge->hdr_type == PCI_HEADER_TYPE_CARDBUS))) { + if (bridge && (pci_is_bridge(bridge))) { pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, &config); if (!(config & PCI_BRIDGE_CTL_VGA)) @@ -526,6 +525,19 @@ static void sb600_disable_hpet_bar(struct pci_dev *dev) } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, 0x4385, sb600_disable_hpet_bar); +#ifdef CONFIG_HPET_TIMER +static void sb600_hpet_quirk(struct pci_dev *dev) +{ + struct resource *r = &dev->resource[1]; + + if (r->flags & IORESOURCE_MEM && r->start == hpet_address) { + r->flags |= IORESOURCE_PCI_FIXED; + dev_info(&dev->dev, "reg 0x14 contains HPET; making it immovable\n"); + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, 0x4385, sb600_hpet_quirk); +#endif + /* * Twinhead H12Y needs us to block out a region otherwise we map devices * there and any access kills the box. diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index db6b1ab..a19ed92 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -271,11 +271,16 @@ static void pcibios_allocate_dev_resources(struct pci_dev *dev, int pass) "BAR %d: reserving %pr (d=%d, p=%d)\n", idx, r, disabled, pass); if (pci_claim_resource(dev, idx) < 0) { - /* We'll assign a new address later */ - pcibios_save_fw_addr(dev, - idx, r->start); - r->end -= r->start; - r->start = 0; + if (r->flags & IORESOURCE_PCI_FIXED) { + dev_info(&dev->dev, "BAR %d %pR is immovable\n", + idx, r); + } else { + /* We'll assign a new address later */ + pcibios_save_fw_addr(dev, + idx, r->start); + r->end -= r->start; + r->start = 0; + } } } } @@ -356,6 +361,12 @@ static int __init pcibios_assign_resources(void) return 0; } +/** + * called in fs_initcall (one below subsys_initcall), + * give a chance for motherboard reserve resources + */ +fs_initcall(pcibios_assign_resources); + void pcibios_resource_survey_bus(struct pci_bus *bus) { dev_printk(KERN_DEBUG, &bus->dev, "Allocating resources\n"); @@ -392,12 +403,6 @@ void __init pcibios_resource_survey(void) ioapic_insert_resources(); } -/** - * called in fs_initcall (one below subsys_initcall), - * give a chance for motherboard reserve resources - */ -fs_initcall(pcibios_assign_resources); - static const struct vm_operations_struct pci_mmap_ops = { .access = generic_access_phys, }; diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 9d8a509..5ceda85 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -173,9 +173,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, { void *vaddr; - vaddr = dma_generic_alloc_coherent(dev, size, dma_handle, flags, attrs); - if (!vaddr) - vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, flags); + vaddr = x86_swiotlb_alloc_coherent(dev, size, dma_handle, flags, attrs); *dma_handle = p2a(*dma_handle, to_pci_dev(dev)); return vaddr; } @@ -183,7 +181,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, /* We have our own dma_ops: the same as swiotlb but from alloc (above) */ static struct dma_map_ops sta2x11_dma_ops = { .alloc = sta2x11_swiotlb_alloc_coherent, - .free = swiotlb_free_coherent, + .free = x86_swiotlb_free_coherent, .map_page = swiotlb_map_page, .unmap_page = swiotlb_unmap_page, .map_sg = swiotlb_map_sg_attrs, diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 3781dd3..87fc96b 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -110,7 +110,7 @@ static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc) efi_status_t status; spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt2(get_time, tm, tc); + status = efi_call_virt(get_time, tm, tc); spin_unlock_irqrestore(&rtc_lock, flags); return status; } @@ -121,7 +121,7 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm) efi_status_t status; spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt1(set_time, tm); + status = efi_call_virt(set_time, tm); spin_unlock_irqrestore(&rtc_lock, flags); return status; } @@ -134,8 +134,7 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled, efi_status_t status; spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt3(get_wakeup_time, - enabled, pending, tm); + status = efi_call_virt(get_wakeup_time, enabled, pending, tm); spin_unlock_irqrestore(&rtc_lock, flags); return status; } @@ -146,8 +145,7 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) efi_status_t status; spin_lock_irqsave(&rtc_lock, flags); - status = efi_call_virt2(set_wakeup_time, - enabled, tm); + status = efi_call_virt(set_wakeup_time, enabled, tm); spin_unlock_irqrestore(&rtc_lock, flags); return status; } @@ -158,17 +156,17 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name, unsigned long *data_size, void *data) { - return efi_call_virt5(get_variable, - name, vendor, attr, - data_size, data); + return efi_call_virt(get_variable, + name, vendor, attr, + data_size, data); } static efi_status_t virt_efi_get_next_variable(unsigned long *name_size, efi_char16_t *name, efi_guid_t *vendor) { - return efi_call_virt3(get_next_variable, - name_size, name, vendor); + return efi_call_virt(get_next_variable, + name_size, name, vendor); } static efi_status_t virt_efi_set_variable(efi_char16_t *name, @@ -177,9 +175,9 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name, unsigned long data_size, void *data) { - return efi_call_virt5(set_variable, - name, vendor, attr, - data_size, data); + return efi_call_virt(set_variable, + name, vendor, attr, + data_size, data); } static efi_status_t virt_efi_query_variable_info(u32 attr, @@ -190,13 +188,13 @@ static efi_status_t virt_efi_query_variable_info(u32 attr, if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; - return efi_call_virt4(query_variable_info, attr, storage_space, - remaining_space, max_variable_size); + return efi_call_virt(query_variable_info, attr, storage_space, + remaining_space, max_variable_size); } static efi_status_t virt_efi_get_next_high_mono_count(u32 *count) { - return efi_call_virt1(get_next_high_mono_count, count); + return efi_call_virt(get_next_high_mono_count, count); } static void virt_efi_reset_system(int reset_type, @@ -204,8 +202,8 @@ static void virt_efi_reset_system(int reset_type, unsigned long data_size, efi_char16_t *data) { - efi_call_virt4(reset_system, reset_type, status, - data_size, data); + __efi_call_virt(reset_system, reset_type, status, + data_size, data); } static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules, @@ -215,7 +213,7 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules, if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; - return efi_call_virt3(update_capsule, capsules, count, sg_list); + return efi_call_virt(update_capsule, capsules, count, sg_list); } static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules, @@ -226,8 +224,8 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules, if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) return EFI_UNSUPPORTED; - return efi_call_virt4(query_capsule_caps, capsules, count, max_size, - reset_type); + return efi_call_virt(query_capsule_caps, capsules, count, max_size, + reset_type); } static efi_status_t __init phys_efi_set_virtual_address_map( @@ -239,9 +237,9 @@ static efi_status_t __init phys_efi_set_virtual_address_map( efi_status_t status; efi_call_phys_prelog(); - status = efi_call_phys4(efi_phys.set_virtual_address_map, - memory_map_size, descriptor_size, - descriptor_version, virtual_map); + status = efi_call_phys(efi_phys.set_virtual_address_map, + memory_map_size, descriptor_size, + descriptor_version, virtual_map); efi_call_phys_epilog(); return status; } @@ -919,6 +917,9 @@ static void __init save_runtime_map(void) void *tmp, *p, *q = NULL; int count = 0; + if (efi_enabled(EFI_OLD_MEMMAP)) + return; + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index e0984ef..5fcda72 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -73,84 +73,7 @@ 2: .endm -ENTRY(efi_call0) - SAVE_XMM - subq $32, %rsp - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call0) - -ENTRY(efi_call1) - SAVE_XMM - subq $32, %rsp - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call1) - -ENTRY(efi_call2) - SAVE_XMM - subq $32, %rsp - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call2) - -ENTRY(efi_call3) - SAVE_XMM - subq $32, %rsp - mov %rcx, %r8 - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call3) - -ENTRY(efi_call4) - SAVE_XMM - subq $32, %rsp - mov %r8, %r9 - mov %rcx, %r8 - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $32, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call4) - -ENTRY(efi_call5) - SAVE_XMM - subq $48, %rsp - mov %r9, 32(%rsp) - mov %r8, %r9 - mov %rcx, %r8 - mov %rsi, %rcx - SWITCH_PGT - call *%rdi - RESTORE_PGT - addq $48, %rsp - RESTORE_XMM - ret -ENDPROC(efi_call5) - -ENTRY(efi_call6) +ENTRY(efi_call) SAVE_XMM mov (%rsp), %rax mov 8(%rax), %rax @@ -166,7 +89,7 @@ ENTRY(efi_call6) addq $48, %rsp RESTORE_XMM ret -ENDPROC(efi_call6) +ENDPROC(efi_call) #ifdef CONFIG_EFI_MIXED diff --git a/arch/x86/platform/intel-mid/device_libs/Makefile b/arch/x86/platform/intel-mid/device_libs/Makefile index 097e7a7..af9307f 100644 --- a/arch/x86/platform/intel-mid/device_libs/Makefile +++ b/arch/x86/platform/intel-mid/device_libs/Makefile @@ -20,3 +20,4 @@ obj-$(subst m,y,$(CONFIG_DRM_MEDFIELD)) += platform_tc35876x.o obj-$(subst m,y,$(CONFIG_SERIAL_MRST_MAX3110)) += platform_max3111.o # MISC Devices obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o +obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_wdt.o diff --git a/arch/x86/platform/intel-mid/device_libs/platform_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c new file mode 100644 index 0000000..973cf3b --- /dev/null +++ b/arch/x86/platform/intel-mid/device_libs/platform_wdt.c @@ -0,0 +1,72 @@ +/* + * platform_wdt.c: Watchdog platform library file + * + * (C) Copyright 2014 Intel Corporation + * Author: David Cohen <david.a.cohen@linux.intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/platform_device.h> +#include <linux/platform_data/intel-mid_wdt.h> +#include <asm/intel-mid.h> +#include <asm/io_apic.h> + +#define TANGIER_EXT_TIMER0_MSI 15 + +static struct platform_device wdt_dev = { + .name = "intel_mid_wdt", + .id = -1, +}; + +static int tangier_probe(struct platform_device *pdev) +{ + int ioapic; + int irq; + struct intel_mid_wdt_pdata *pdata = pdev->dev.platform_data; + struct io_apic_irq_attr irq_attr = { 0 }; + + if (!pdata) + return -EINVAL; + + irq = pdata->irq; + ioapic = mp_find_ioapic(irq); + if (ioapic >= 0) { + int ret; + irq_attr.ioapic = ioapic; + irq_attr.ioapic_pin = irq; + irq_attr.trigger = 1; + /* irq_attr.polarity = 0; -> Active high */ + ret = io_apic_set_pci_routing(NULL, irq, &irq_attr); + if (ret) + return ret; + } else { + dev_warn(&pdev->dev, "cannot find interrupt %d in ioapic\n", + irq); + return -EINVAL; + } + + return 0; +} + +static struct intel_mid_wdt_pdata tangier_pdata = { + .irq = TANGIER_EXT_TIMER0_MSI, + .probe = tangier_probe, +}; + +static int __init register_mid_wdt(void) +{ + if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) { + wdt_dev.dev.platform_data = &tangier_pdata; + return platform_device_register(&wdt_dev); + } + + return -ENODEV; +} + +rootfs_initcall(register_mid_wdt); diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index 7666121..1584cbe 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -39,7 +39,7 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5) */ return BIOS_STATUS_UNIMPLEMENTED; - ret = efi_call6((void *)__va(tab->function), (u64)which, + ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5); return ret; } diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index acf7752..b233681 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -238,11 +238,9 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, unsigned long mmr_offset, int limit) { - int irq, ret; + int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade)); - irq = create_irq_nr(NR_IRQS_LEGACY, uv_blade_to_memory_nid(mmr_blade)); - - if (irq <= 0) + if (!irq) return -EBUSY; ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset, @@ -250,7 +248,7 @@ int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, if (ret == irq) uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade); else - destroy_irq(irq); + irq_free_hwirq(irq); return ret; } @@ -285,6 +283,6 @@ void uv_teardown_irq(unsigned int irq) n = n->rb_right; } spin_unlock_irqrestore(&uv_irq_lock, irqflags); - destroy_irq(irq); + irq_free_hwirq(irq); } EXPORT_SYMBOL_GPL(uv_teardown_irq); diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index be27da6..c89c933 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -85,7 +85,7 @@ static cpumask_var_t uv_nmi_cpu_mask; * Default is all stack dumps go to the console and buffer. * Lower level to send to log buffer only. */ -static int uv_nmi_loglevel = 7; +static int uv_nmi_loglevel = CONSOLE_LOGLEVEL_DEFAULT; module_param_named(dump_loglevel, uv_nmi_loglevel, int, 0644); /* diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 3497f14..7c0d7be 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -52,8 +52,9 @@ $(obj)/realmode.elf: $(obj)/realmode.lds $(REALMODE_OBJS) FORCE OBJCOPYFLAGS_realmode.bin := -O binary targets += realmode.bin -$(obj)/realmode.bin: $(obj)/realmode.elf $(obj)/realmode.relocs +$(obj)/realmode.bin: $(obj)/realmode.elf $(obj)/realmode.relocs FORCE $(call if_changed,objcopy) + @: quiet_cmd_relocs = RELOCS $@ cmd_relocs = arch/x86/tools/relocs --realmode $< > $@ diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 04376ac..ec255a1 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -212,10 +212,10 @@ 203 common sched_setaffinity sys_sched_setaffinity 204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 common io_setup sys_io_setup +206 64 io_setup sys_io_setup 207 common io_destroy sys_io_destroy 208 common io_getevents sys_io_getevents -209 common io_submit sys_io_submit +209 64 io_submit sys_io_submit 210 common io_cancel sys_io_cancel 211 64 get_thread_area 212 common lookup_dcookie sys_lookup_dcookie @@ -359,3 +359,5 @@ 540 x32 process_vm_writev compat_sys_process_vm_writev 541 x32 setsockopt compat_sys_setsockopt 542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit diff --git a/arch/x86/um/vdso/vma.c b/arch/x86/um/vdso/vma.c index af91901..916cda4 100644 --- a/arch/x86/um/vdso/vma.c +++ b/arch/x86/um/vdso/vma.c @@ -12,7 +12,7 @@ #include <asm/page.h> #include <linux/init.h> -unsigned int __read_mostly vdso_enabled = 1; +static unsigned int __read_mostly vdso_enabled = 1; unsigned long um_vdso_addr; extern unsigned long task_size; diff --git a/arch/x86/vdso/.gitignore b/arch/x86/vdso/.gitignore index 3282874..aae8ffd 100644 --- a/arch/x86/vdso/.gitignore +++ b/arch/x86/vdso/.gitignore @@ -1,8 +1,7 @@ vdso.lds -vdso-syms.lds vdsox32.lds -vdsox32-syms.lds -vdso32-syms.lds vdso32-syscall-syms.lds vdso32-sysenter-syms.lds vdso32-int80-syms.lds +vdso-image-*.c +vdso2c diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile index c580d12..3c0809a 100644 --- a/arch/x86/vdso/Makefile +++ b/arch/x86/vdso/Makefile @@ -9,30 +9,36 @@ VDSOX32-$(CONFIG_X86_X32_ABI) := y VDSO32-$(CONFIG_X86_32) := y VDSO32-$(CONFIG_COMPAT) := y -vdso-install-$(VDSO64-y) += vdso.so -vdso-install-$(VDSOX32-y) += vdsox32.so -vdso-install-$(VDSO32-y) += $(vdso32-images) - - # files to link into the vdso -vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o - -vobjs-$(VDSOX32-y) += $(vobjx32s-compat) - -# Filter out x32 objects. -vobj64s := $(filter-out $(vobjx32s-compat),$(vobjs-y)) +vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vdso-fakesections.o +vobjs-nox32 := vdso-fakesections.o # files to link into kernel obj-y += vma.o -obj-$(VDSO64-y) += vdso.o -obj-$(VDSOX32-y) += vdsox32.o -obj-$(VDSO32-y) += vdso32.o vdso32-setup.o -vobjs := $(foreach F,$(vobj64s),$(obj)/$F) +# vDSO images to build +vdso_img-$(VDSO64-y) += 64 +vdso_img-$(VDSOX32-y) += x32 +vdso_img-$(VDSO32-y) += 32-int80 +vdso_img-$(CONFIG_COMPAT) += 32-syscall +vdso_img-$(VDSO32-y) += 32-sysenter + +obj-$(VDSO32-y) += vdso32-setup.o + +vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) $(obj)/vdso.o: $(obj)/vdso.so -targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y) +targets += vdso.lds $(vobjs-y) + +# Build the vDSO image C files and link them in. +vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o) +vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c) +vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg) +obj-y += $(vdso_img_objs) +targets += $(vdso_img_cfiles) +targets += $(vdso_img_sodbg) +.SECONDARY: $(vdso_img-y:%=$(obj)/vdso-image-%.c) export CPPFLAGS_vdso.lds += -P -C @@ -41,14 +47,19 @@ VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \ -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \ $(DISABLE_LTO) -$(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so - -$(obj)/vdso.so.dbg: $(src)/vdso.lds $(vobjs) FORCE +$(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE $(call if_changed,vdso) -$(obj)/%.so: OBJCOPYFLAGS := -S -$(obj)/%.so: $(obj)/%.so.dbg FORCE - $(call if_changed,objcopy) +HOST_EXTRACFLAGS += -I$(srctree)/tools/include +hostprogs-y += vdso2c + +quiet_cmd_vdso2c = VDSO2C $@ +define cmd_vdso2c + $(obj)/vdso2c $< $@ +endef + +$(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso2c FORCE + $(call if_changed,vdso2c) # # Don't omit frame pointers for ease of userspace debugging, but do @@ -68,22 +79,6 @@ CFLAGS_REMOVE_vclock_gettime.o = -pg CFLAGS_REMOVE_vgetcpu.o = -pg CFLAGS_REMOVE_vvar.o = -pg -targets += vdso-syms.lds -obj-$(VDSO64-y) += vdso-syms.lds - -# -# Match symbols in the DSO that look like VDSO*; produce a file of constants. -# -sed-vdsosym := -e 's/^00*/0/' \ - -e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p' -quiet_cmd_vdsosym = VDSOSYM $@ -define cmd_vdsosym - $(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@ -endef - -$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE - $(call if_changed,vdsosym) - # # X32 processes use x32 vDSO to access 64bit kernel data. # @@ -94,16 +89,19 @@ $(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE # so that it can reach 64bit address space with 64bit pointers. # -targets += vdsox32-syms.lds -obj-$(VDSOX32-y) += vdsox32-syms.lds - CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds) VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \ -Wl,-soname=linux-vdso.so.1 \ -Wl,-z,max-page-size=4096 \ -Wl,-z,common-page-size=4096 -vobjx32s-y := $(vobj64s:.o=-x32.o) +# 64-bit objects to re-brand as x32 +vobjs64-for-x32 := $(filter-out $(vobjs-nox32),$(vobjs-y)) + +# x32-rebranded versions +vobjx32s-y := $(vobjs64-for-x32:.o=-x32.o) + +# same thing, but in the output directory vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F) # Convert 64bit object file to x32 for x32 vDSO. @@ -113,9 +111,7 @@ quiet_cmd_x32 = X32 $@ $(obj)/%-x32.o: $(obj)/%.o FORCE $(call if_changed,x32) -targets += vdsox32.so vdsox32.so.dbg vdsox32.lds $(vobjx32s-y) - -$(obj)/vdsox32.o: $(src)/vdsox32.S $(obj)/vdsox32.so +targets += vdsox32.lds $(vobjx32s-y) $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE $(call if_changed,vdso) @@ -123,7 +119,6 @@ $(obj)/vdsox32.so.dbg: $(src)/vdsox32.lds $(vobjx32s) FORCE # # Build multiple 32-bit vDSO images to choose from at boot time. # -obj-$(VDSO32-y) += vdso32-syms.lds vdso32.so-$(VDSO32-y) += int80 vdso32.so-$(CONFIG_COMPAT) += syscall vdso32.so-$(VDSO32-y) += sysenter @@ -138,10 +133,8 @@ VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1 override obj-dirs = $(dir $(obj)) $(obj)/vdso32/ targets += vdso32/vdso32.lds -targets += $(vdso32-images) $(vdso32-images:=.dbg) targets += vdso32/note.o vdso32/vclock_gettime.o $(vdso32.so-y:%=vdso32/%.o) - -extra-y += $(vdso32-images) +targets += vdso32/vclock_gettime.o $(obj)/vdso32.o: $(vdso32-images:%=$(obj)/%) @@ -166,27 +159,6 @@ $(vdso32-images:%=$(obj)/%.dbg): $(obj)/vdso32-%.so.dbg: FORCE \ $(obj)/vdso32/%.o $(call if_changed,vdso) -# Make vdso32-*-syms.lds from each image, and then make sure they match. -# The only difference should be that some do not define VDSO32_SYSENTER_RETURN. - -targets += vdso32-syms.lds $(vdso32.so-y:%=vdso32-%-syms.lds) - -quiet_cmd_vdso32sym = VDSOSYM $@ -define cmd_vdso32sym - if LC_ALL=C sort -u $(filter-out FORCE,$^) > $(@D)/.tmp_$(@F) && \ - $(foreach H,$(filter-out FORCE,$^),\ - if grep -q VDSO32_SYSENTER_RETURN $H; \ - then diff -u $(@D)/.tmp_$(@F) $H; \ - else sed /VDSO32_SYSENTER_RETURN/d $(@D)/.tmp_$(@F) | \ - diff -u - $H; fi &&) : ;\ - then mv -f $(@D)/.tmp_$(@F) $@; \ - else rm -f $(@D)/.tmp_$(@F); exit 1; \ - fi -endef - -$(obj)/vdso32-syms.lds: $(vdso32.so-y:%=$(obj)/vdso32-%-syms.lds) FORCE - $(call if_changed,vdso32sym) - # # The DSO images are built using a special linker script. # @@ -197,19 +169,24 @@ quiet_cmd_vdso = VDSO $@ sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@' VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \ - $(LTO_CFLAGS) + -Wl,-Bsymbolic $(LTO_CFLAGS) GCOV_PROFILE := n # -# Install the unstripped copy of vdso*.so listed in $(vdso-install-y). +# Install the unstripped copies of vdso*.so. # -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ -$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE +quiet_cmd_vdso_install = INSTALL $(@:install_%=%) + cmd_vdso_install = cp $< $(MODLIB)/vdso/$(@:install_%=%) + +vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%) + +$(MODLIB)/vdso: FORCE @mkdir -p $(MODLIB)/vdso + +$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE $(call cmd,vdso_install) -PHONY += vdso_install $(vdso-install-y) -vdso_install: $(vdso-install-y) +PHONY += vdso_install $(vdso_img_insttargets) +vdso_install: $(vdso_img_insttargets) FORCE clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 16d6861..b2e4f49 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -30,9 +30,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz); extern time_t __vdso_time(time_t *t); #ifdef CONFIG_HPET_TIMER -static inline u32 read_hpet_counter(const volatile void *addr) +extern u8 hpet_page + __attribute__((visibility("hidden"))); + +static notrace cycle_t vread_hpet(void) { - return *(const volatile u32 *) (addr + HPET_COUNTER); + return *(const volatile u32 *)(&hpet_page + HPET_COUNTER); } #endif @@ -43,11 +46,6 @@ static inline u32 read_hpet_counter(const volatile void *addr) #include <asm/fixmap.h> #include <asm/pvclock.h> -static notrace cycle_t vread_hpet(void) -{ - return read_hpet_counter((const void *)fix_to_virt(VSYSCALL_HPET)); -} - notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; @@ -137,16 +135,6 @@ static notrace cycle_t vread_pvclock(int *mode) #else -extern u8 hpet_page - __attribute__((visibility("hidden"))); - -#ifdef CONFIG_HPET_TIMER -static notrace cycle_t vread_hpet(void) -{ - return read_hpet_counter((const void *)(&hpet_page)); -} -#endif - notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) { long ret; @@ -154,7 +142,7 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts) asm( "mov %%ebx, %%edx \n" "mov %2, %%ebx \n" - "call VDSO32_vsyscall \n" + "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" : "=a" (ret) : "0" (__NR_clock_gettime), "g" (clock), "c" (ts) @@ -169,7 +157,7 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz) asm( "mov %%ebx, %%edx \n" "mov %2, %%ebx \n" - "call VDSO32_vsyscall \n" + "call __kernel_vsyscall \n" "mov %%edx, %%ebx \n" : "=a" (ret) : "0" (__NR_gettimeofday), "g" (tv), "c" (tz) diff --git a/arch/x86/vdso/vdso-fakesections.c b/arch/x86/vdso/vdso-fakesections.c new file mode 100644 index 0000000..cb8a8d7 --- /dev/null +++ b/arch/x86/vdso/vdso-fakesections.c @@ -0,0 +1,32 @@ +/* + * Copyright 2014 Andy Lutomirski + * Subject to the GNU Public License, v.2 + * + * Hack to keep broken Go programs working. + * + * The Go runtime had a couple of bugs: it would read the section table to try + * to figure out how many dynamic symbols there were (it shouldn't have looked + * at the section table at all) and, if there were no SHT_SYNDYM section table + * entry, it would use an uninitialized value for the number of symbols. As a + * workaround, we supply a minimal section table. vdso2c will adjust the + * in-memory image so that "vdso_fake_sections" becomes the section table. + * + * The bug was introduced by: + * https://code.google.com/p/go/source/detail?r=56ea40aac72b (2012-08-31) + * and is being addressed in the Go runtime in this issue: + * https://code.google.com/p/go/issues/detail?id=8197 + */ + +#ifndef __x86_64__ +#error This hack is specific to the 64-bit vDSO +#endif + +#include <linux/elf.h> + +extern const __visible struct elf64_shdr vdso_fake_sections[]; +const __visible struct elf64_shdr vdso_fake_sections[] = { + { + .sh_type = SHT_DYNSYM, + .sh_entsize = sizeof(Elf64_Sym), + } +}; diff --git a/arch/x86/vdso/vdso-layout.lds.S b/arch/x86/vdso/vdso-layout.lds.S index 9df017a..2ec72f6 100644 --- a/arch/x86/vdso/vdso-layout.lds.S +++ b/arch/x86/vdso/vdso-layout.lds.S @@ -1,3 +1,5 @@ +#include <asm/vdso.h> + /* * Linker script for vDSO. This is an ELF shared object prelinked to * its virtual address, and with only one read-only segment. @@ -6,20 +8,6 @@ SECTIONS { -#ifdef BUILD_VDSO32 -#include <asm/vdso32.h> - - hpet_page = . - VDSO_OFFSET(VDSO_HPET_PAGE); - - vvar = . - VDSO_OFFSET(VDSO_VVAR_PAGE); - - /* Place all vvars at the offsets in asm/vvar.h. */ -#define EMIT_VVAR(name, offset) vvar_ ## name = vvar + offset; -#define __VVAR_KERNEL_LDS -#include <asm/vvar.h> -#undef __VVAR_KERNEL_LDS -#undef EMIT_VVAR -#endif . = SIZEOF_HEADERS; .hash : { *(.hash) } :text @@ -60,10 +48,30 @@ SECTIONS .text : { *(.text*) } :text =0x90909090, /* - * The comma above works around a bug in gold: - * https://sourceware.org/bugzilla/show_bug.cgi?id=16804 + * The remainder of the vDSO consists of special pages that are + * shared between the kernel and userspace. It needs to be at the + * end so that it doesn't overlap the mapping of the actual + * vDSO image. */ + . = ALIGN(PAGE_SIZE); + vvar_page = .; + + /* Place all vvars at the offsets in asm/vvar.h. */ +#define EMIT_VVAR(name, offset) vvar_ ## name = vvar_page + offset; +#define __VVAR_KERNEL_LDS +#include <asm/vvar.h> +#undef __VVAR_KERNEL_LDS +#undef EMIT_VVAR + + . = vvar_page + PAGE_SIZE; + + hpet_page = .; + . = . + PAGE_SIZE; + + . = ALIGN(PAGE_SIZE); + end_mapping = .; + /DISCARD/ : { *(.discard) *(.discard.*) diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S deleted file mode 100644 index be3f23b..0000000 --- a/arch/x86/vdso/vdso.S +++ /dev/null @@ -1,3 +0,0 @@ -#include <asm/vdso.h> - -DEFINE_VDSO_IMAGE(vdso, "arch/x86/vdso/vdso.so") diff --git a/arch/x86/vdso/vdso.lds.S b/arch/x86/vdso/vdso.lds.S index b96b267..75e3404 100644 --- a/arch/x86/vdso/vdso.lds.S +++ b/arch/x86/vdso/vdso.lds.S @@ -1,14 +1,11 @@ /* * Linker script for 64-bit vDSO. * We #include the file to define the layout details. - * Here we only choose the prelinked virtual address. * * This file defines the version script giving the user-exported symbols in - * the DSO. We can define local symbols here called VDSO* to make their - * values visible using the asm-x86/vdso.h macros from the kernel proper. + * the DSO. */ -#define VDSO_PRELINK 0xffffffffff700000 #include "vdso-layout.lds.S" /* @@ -28,5 +25,3 @@ VERSION { local: *; }; } - -VDSO64_PRELINK = VDSO_PRELINK; diff --git a/arch/x86/vdso/vdso2c.c b/arch/x86/vdso/vdso2c.c new file mode 100644 index 0000000..7a6bf50 --- /dev/null +++ b/arch/x86/vdso/vdso2c.c @@ -0,0 +1,188 @@ +#include <inttypes.h> +#include <stdint.h> +#include <unistd.h> +#include <stdarg.h> +#include <stdlib.h> +#include <stdio.h> +#include <string.h> +#include <fcntl.h> +#include <err.h> + +#include <sys/mman.h> +#include <sys/types.h> + +#include <tools/le_byteshift.h> + +#include <linux/elf.h> +#include <linux/types.h> + +const char *outfilename; + +/* Symbols that we need in vdso2c. */ +enum { + sym_vvar_page, + sym_hpet_page, + sym_end_mapping, +}; + +const int special_pages[] = { + sym_vvar_page, + sym_hpet_page, +}; + +char const * const required_syms[] = { + [sym_vvar_page] = "vvar_page", + [sym_hpet_page] = "hpet_page", + [sym_end_mapping] = "end_mapping", + "VDSO32_NOTE_MASK", + "VDSO32_SYSENTER_RETURN", + "__kernel_vsyscall", + "__kernel_sigreturn", + "__kernel_rt_sigreturn", +}; + +__attribute__((format(printf, 1, 2))) __attribute__((noreturn)) +static void fail(const char *format, ...) +{ + va_list ap; + va_start(ap, format); + fprintf(stderr, "Error: "); + vfprintf(stderr, format, ap); + unlink(outfilename); + exit(1); + va_end(ap); +} + +/* + * Evil macros for little-endian reads and writes + */ +#define GLE(x, bits, ifnot) \ + __builtin_choose_expr( \ + (sizeof(*(x)) == bits/8), \ + (__typeof__(*(x)))get_unaligned_le##bits(x), ifnot) + +extern void bad_get_le(void); +#define LAST_GLE(x) \ + __builtin_choose_expr(sizeof(*(x)) == 1, *(x), bad_get_le()) + +#define GET_LE(x) \ + GLE(x, 64, GLE(x, 32, GLE(x, 16, LAST_GLE(x)))) + +#define PLE(x, val, bits, ifnot) \ + __builtin_choose_expr( \ + (sizeof(*(x)) == bits/8), \ + put_unaligned_le##bits((val), (x)), ifnot) + +extern void bad_put_le(void); +#define LAST_PLE(x, val) \ + __builtin_choose_expr(sizeof(*(x)) == 1, *(x) = (val), bad_put_le()) + +#define PUT_LE(x, val) \ + PLE(x, val, 64, PLE(x, val, 32, PLE(x, val, 16, LAST_PLE(x, val)))) + + +#define NSYMS (sizeof(required_syms) / sizeof(required_syms[0])) + +#define BITS 64 +#define GOFUNC go64 +#define Elf_Ehdr Elf64_Ehdr +#define Elf_Shdr Elf64_Shdr +#define Elf_Phdr Elf64_Phdr +#define Elf_Sym Elf64_Sym +#define Elf_Dyn Elf64_Dyn +#include "vdso2c.h" +#undef BITS +#undef GOFUNC +#undef Elf_Ehdr +#undef Elf_Shdr +#undef Elf_Phdr +#undef Elf_Sym +#undef Elf_Dyn + +#define BITS 32 +#define GOFUNC go32 +#define Elf_Ehdr Elf32_Ehdr +#define Elf_Shdr Elf32_Shdr +#define Elf_Phdr Elf32_Phdr +#define Elf_Sym Elf32_Sym +#define Elf_Dyn Elf32_Dyn +#include "vdso2c.h" +#undef BITS +#undef GOFUNC +#undef Elf_Ehdr +#undef Elf_Shdr +#undef Elf_Phdr +#undef Elf_Sym +#undef Elf_Dyn + +static void go(void *addr, size_t len, FILE *outfile, const char *name) +{ + Elf64_Ehdr *hdr = (Elf64_Ehdr *)addr; + + if (hdr->e_ident[EI_CLASS] == ELFCLASS64) { + go64(addr, len, outfile, name); + } else if (hdr->e_ident[EI_CLASS] == ELFCLASS32) { + go32(addr, len, outfile, name); + } else { + fail("unknown ELF class\n"); + } +} + +int main(int argc, char **argv) +{ + int fd; + off_t len; + void *addr; + FILE *outfile; + char *name, *tmp; + int namelen; + + if (argc != 3) { + printf("Usage: vdso2c INPUT OUTPUT\n"); + return 1; + } + + /* + * Figure out the struct name. If we're writing to a .so file, + * generate raw output insted. + */ + name = strdup(argv[2]); + namelen = strlen(name); + if (namelen >= 3 && !strcmp(name + namelen - 3, ".so")) { + name = NULL; + } else { + tmp = strrchr(name, '/'); + if (tmp) + name = tmp + 1; + tmp = strchr(name, '.'); + if (tmp) + *tmp = '\0'; + for (tmp = name; *tmp; tmp++) + if (*tmp == '-') + *tmp = '_'; + } + + fd = open(argv[1], O_RDONLY); + if (fd == -1) + err(1, "%s", argv[1]); + + len = lseek(fd, 0, SEEK_END); + if (len == (off_t)-1) + err(1, "lseek"); + + addr = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); + if (addr == MAP_FAILED) + err(1, "mmap"); + + outfilename = argv[2]; + outfile = fopen(outfilename, "w"); + if (!outfile) + err(1, "%s", argv[2]); + + go(addr, (size_t)len, outfile, name); + + munmap(addr, len); + fclose(outfile); + + return 0; +} diff --git a/arch/x86/vdso/vdso2c.h b/arch/x86/vdso/vdso2c.h new file mode 100644 index 0000000..c6eefaf --- /dev/null +++ b/arch/x86/vdso/vdso2c.h @@ -0,0 +1,176 @@ +/* + * This file is included twice from vdso2c.c. It generates code for 32-bit + * and 64-bit vDSOs. We need both for 64-bit builds, since 32-bit vDSOs + * are built for 32-bit userspace. + */ + +static void GOFUNC(void *addr, size_t len, FILE *outfile, const char *name) +{ + int found_load = 0; + unsigned long load_size = -1; /* Work around bogus warning */ + unsigned long data_size; + Elf_Ehdr *hdr = (Elf_Ehdr *)addr; + int i; + unsigned long j; + Elf_Shdr *symtab_hdr = NULL, *strtab_hdr, *secstrings_hdr, + *alt_sec = NULL; + Elf_Dyn *dyn = 0, *dyn_end = 0; + const char *secstrings; + uint64_t syms[NSYMS] = {}; + + uint64_t fake_sections_value = 0, fake_sections_size = 0; + + Elf_Phdr *pt = (Elf_Phdr *)(addr + GET_LE(&hdr->e_phoff)); + + /* Walk the segment table. */ + for (i = 0; i < GET_LE(&hdr->e_phnum); i++) { + if (GET_LE(&pt[i].p_type) == PT_LOAD) { + if (found_load) + fail("multiple PT_LOAD segs\n"); + + if (GET_LE(&pt[i].p_offset) != 0 || + GET_LE(&pt[i].p_vaddr) != 0) + fail("PT_LOAD in wrong place\n"); + + if (GET_LE(&pt[i].p_memsz) != GET_LE(&pt[i].p_filesz)) + fail("cannot handle memsz != filesz\n"); + + load_size = GET_LE(&pt[i].p_memsz); + found_load = 1; + } else if (GET_LE(&pt[i].p_type) == PT_DYNAMIC) { + dyn = addr + GET_LE(&pt[i].p_offset); + dyn_end = addr + GET_LE(&pt[i].p_offset) + + GET_LE(&pt[i].p_memsz); + } + } + if (!found_load) + fail("no PT_LOAD seg\n"); + data_size = (load_size + 4095) / 4096 * 4096; + + /* Walk the dynamic table */ + for (i = 0; dyn + i < dyn_end && + GET_LE(&dyn[i].d_tag) != DT_NULL; i++) { + typeof(dyn[i].d_tag) tag = GET_LE(&dyn[i].d_tag); + if (tag == DT_REL || tag == DT_RELSZ || + tag == DT_RELENT || tag == DT_TEXTREL) + fail("vdso image contains dynamic relocations\n"); + } + + /* Walk the section table */ + secstrings_hdr = addr + GET_LE(&hdr->e_shoff) + + GET_LE(&hdr->e_shentsize)*GET_LE(&hdr->e_shstrndx); + secstrings = addr + GET_LE(&secstrings_hdr->sh_offset); + for (i = 0; i < GET_LE(&hdr->e_shnum); i++) { + Elf_Shdr *sh = addr + GET_LE(&hdr->e_shoff) + + GET_LE(&hdr->e_shentsize) * i; + if (GET_LE(&sh->sh_type) == SHT_SYMTAB) + symtab_hdr = sh; + + if (!strcmp(secstrings + GET_LE(&sh->sh_name), + ".altinstructions")) + alt_sec = sh; + } + + if (!symtab_hdr) + fail("no symbol table\n"); + + strtab_hdr = addr + GET_LE(&hdr->e_shoff) + + GET_LE(&hdr->e_shentsize) * GET_LE(&symtab_hdr->sh_link); + + /* Walk the symbol table */ + for (i = 0; + i < GET_LE(&symtab_hdr->sh_size) / GET_LE(&symtab_hdr->sh_entsize); + i++) { + int k; + Elf_Sym *sym = addr + GET_LE(&symtab_hdr->sh_offset) + + GET_LE(&symtab_hdr->sh_entsize) * i; + const char *name = addr + GET_LE(&strtab_hdr->sh_offset) + + GET_LE(&sym->st_name); + + for (k = 0; k < NSYMS; k++) { + if (!strcmp(name, required_syms[k])) { + if (syms[k]) { + fail("duplicate symbol %s\n", + required_syms[k]); + } + syms[k] = GET_LE(&sym->st_value); + } + } + + if (!strcmp(name, "vdso_fake_sections")) { + if (fake_sections_value) + fail("duplicate vdso_fake_sections\n"); + fake_sections_value = GET_LE(&sym->st_value); + fake_sections_size = GET_LE(&sym->st_size); + } + } + + /* Validate mapping addresses. */ + for (i = 0; i < sizeof(special_pages) / sizeof(special_pages[0]); i++) { + if (!syms[i]) + continue; /* The mapping isn't used; ignore it. */ + + if (syms[i] % 4096) + fail("%s must be a multiple of 4096\n", + required_syms[i]); + if (syms[i] < data_size) + fail("%s must be after the text mapping\n", + required_syms[i]); + if (syms[sym_end_mapping] < syms[i] + 4096) + fail("%s overruns end_mapping\n", required_syms[i]); + } + if (syms[sym_end_mapping] % 4096) + fail("end_mapping must be a multiple of 4096\n"); + + /* Remove sections or use fakes */ + if (fake_sections_size % sizeof(Elf_Shdr)) + fail("vdso_fake_sections size is not a multiple of %ld\n", + (long)sizeof(Elf_Shdr)); + PUT_LE(&hdr->e_shoff, fake_sections_value); + PUT_LE(&hdr->e_shentsize, fake_sections_value ? sizeof(Elf_Shdr) : 0); + PUT_LE(&hdr->e_shnum, fake_sections_size / sizeof(Elf_Shdr)); + PUT_LE(&hdr->e_shstrndx, SHN_UNDEF); + + if (!name) { + fwrite(addr, load_size, 1, outfile); + return; + } + + fprintf(outfile, "/* AUTOMATICALLY GENERATED -- DO NOT EDIT */\n\n"); + fprintf(outfile, "#include <linux/linkage.h>\n"); + fprintf(outfile, "#include <asm/page_types.h>\n"); + fprintf(outfile, "#include <asm/vdso.h>\n"); + fprintf(outfile, "\n"); + fprintf(outfile, + "static unsigned char raw_data[%lu] __page_aligned_data = {", + data_size); + for (j = 0; j < load_size; j++) { + if (j % 10 == 0) + fprintf(outfile, "\n\t"); + fprintf(outfile, "0x%02X, ", (int)((unsigned char *)addr)[j]); + } + fprintf(outfile, "\n};\n\n"); + + fprintf(outfile, "static struct page *pages[%lu];\n\n", + data_size / 4096); + + fprintf(outfile, "const struct vdso_image %s = {\n", name); + fprintf(outfile, "\t.data = raw_data,\n"); + fprintf(outfile, "\t.size = %lu,\n", data_size); + fprintf(outfile, "\t.text_mapping = {\n"); + fprintf(outfile, "\t\t.name = \"[vdso]\",\n"); + fprintf(outfile, "\t\t.pages = pages,\n"); + fprintf(outfile, "\t},\n"); + if (alt_sec) { + fprintf(outfile, "\t.alt = %lu,\n", + (unsigned long)GET_LE(&alt_sec->sh_offset)); + fprintf(outfile, "\t.alt_len = %lu,\n", + (unsigned long)GET_LE(&alt_sec->sh_size)); + } + for (i = 0; i < NSYMS; i++) { + if (syms[i]) + fprintf(outfile, "\t.sym_%s = 0x%" PRIx64 ",\n", + required_syms[i], syms[i]); + } + fprintf(outfile, "};\n"); +} diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c index e1f220e..e4f7781 100644 --- a/arch/x86/vdso/vdso32-setup.c +++ b/arch/x86/vdso/vdso32-setup.c @@ -8,27 +8,12 @@ #include <linux/init.h> #include <linux/smp.h> -#include <linux/thread_info.h> -#include <linux/sched.h> -#include <linux/gfp.h> -#include <linux/string.h> -#include <linux/elf.h> -#include <linux/mm.h> -#include <linux/err.h> -#include <linux/module.h> -#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/mm_types.h> #include <asm/cpufeature.h> -#include <asm/msr.h> -#include <asm/pgtable.h> -#include <asm/unistd.h> -#include <asm/elf.h> -#include <asm/tlbflush.h> +#include <asm/processor.h> #include <asm/vdso.h> -#include <asm/proto.h> -#include <asm/fixmap.h> -#include <asm/hpet.h> -#include <asm/vvar.h> #ifdef CONFIG_COMPAT_VDSO #define VDSO_DEFAULT 0 @@ -36,23 +21,17 @@ #define VDSO_DEFAULT 1 #endif -#ifdef CONFIG_X86_64 -#define vdso_enabled sysctl_vsyscall32 -#define arch_setup_additional_pages syscall32_setup_pages -extern int sysctl_ldt16; -#endif - /* * Should the kernel map a VDSO page into processes and pass its * address down to glibc upon exec()? */ -unsigned int __read_mostly vdso_enabled = VDSO_DEFAULT; +unsigned int __read_mostly vdso32_enabled = VDSO_DEFAULT; -static int __init vdso_setup(char *s) +static int __init vdso32_setup(char *s) { - vdso_enabled = simple_strtoul(s, NULL, 0); + vdso32_enabled = simple_strtoul(s, NULL, 0); - if (vdso_enabled > 1) + if (vdso32_enabled > 1) pr_warn("vdso32 values other than 0 and 1 are no longer allowed; vdso disabled\n"); return 1; @@ -63,177 +42,45 @@ static int __init vdso_setup(char *s) * behavior on both 64-bit and 32-bit kernels. * On 32-bit kernels, vdso=[012] means the same thing. */ -__setup("vdso32=", vdso_setup); +__setup("vdso32=", vdso32_setup); #ifdef CONFIG_X86_32 -__setup_param("vdso=", vdso32_setup, vdso_setup, 0); - -EXPORT_SYMBOL_GPL(vdso_enabled); +__setup_param("vdso=", vdso_setup, vdso32_setup, 0); #endif -static struct page **vdso32_pages; -static unsigned vdso32_size; - #ifdef CONFIG_X86_64 #define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SYSENTER32)) #define vdso32_syscall() (boot_cpu_has(X86_FEATURE_SYSCALL32)) -/* May not be __init: called during resume */ -void syscall32_cpu_init(void) -{ - /* Load these always in case some future AMD CPU supports - SYSENTER from compat mode too. */ - wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); - wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)ia32_sysenter_target); - - wrmsrl(MSR_CSTAR, ia32_cstar_target); -} - #else /* CONFIG_X86_32 */ #define vdso32_sysenter() (boot_cpu_has(X86_FEATURE_SEP)) #define vdso32_syscall() (0) -void enable_sep_cpu(void) -{ - int cpu = get_cpu(); - struct tss_struct *tss = &per_cpu(init_tss, cpu); - - if (!boot_cpu_has(X86_FEATURE_SEP)) { - put_cpu(); - return; - } - - tss->x86_tss.ss1 = __KERNEL_CS; - tss->x86_tss.sp1 = sizeof(struct tss_struct) + (unsigned long) tss; - wrmsr(MSR_IA32_SYSENTER_CS, __KERNEL_CS, 0); - wrmsr(MSR_IA32_SYSENTER_ESP, tss->x86_tss.sp1, 0); - wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long) ia32_sysenter_target, 0); - put_cpu(); -} - #endif /* CONFIG_X86_64 */ +#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +const struct vdso_image *selected_vdso32; +#endif + int __init sysenter_setup(void) { - char *vdso32_start, *vdso32_end; - int npages, i; - #ifdef CONFIG_COMPAT - if (vdso32_syscall()) { - vdso32_start = vdso32_syscall_start; - vdso32_end = vdso32_syscall_end; - vdso32_pages = vdso32_syscall_pages; - } else + if (vdso32_syscall()) + selected_vdso32 = &vdso_image_32_syscall; + else #endif - if (vdso32_sysenter()) { - vdso32_start = vdso32_sysenter_start; - vdso32_end = vdso32_sysenter_end; - vdso32_pages = vdso32_sysenter_pages; - } else { - vdso32_start = vdso32_int80_start; - vdso32_end = vdso32_int80_end; - vdso32_pages = vdso32_int80_pages; - } - - npages = ((vdso32_end - vdso32_start) + PAGE_SIZE - 1) / PAGE_SIZE; - vdso32_size = npages << PAGE_SHIFT; - for (i = 0; i < npages; i++) - vdso32_pages[i] = virt_to_page(vdso32_start + i*PAGE_SIZE); + if (vdso32_sysenter()) + selected_vdso32 = &vdso_image_32_sysenter; + else + selected_vdso32 = &vdso_image_32_int80; - patch_vdso32(vdso32_start, vdso32_size); + init_vdso_image(selected_vdso32); return 0; } -/* Setup a VMA at program startup for the vsyscall page */ -int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) -{ - struct mm_struct *mm = current->mm; - unsigned long addr; - int ret = 0; - struct vm_area_struct *vma; - -#ifdef CONFIG_X86_X32_ABI - if (test_thread_flag(TIF_X32)) - return x32_setup_additional_pages(bprm, uses_interp); -#endif - - if (vdso_enabled != 1) /* Other values all mean "disabled" */ - return 0; - - down_write(&mm->mmap_sem); - - addr = get_unmapped_area(NULL, 0, vdso32_size + VDSO_OFFSET(VDSO_PREV_PAGES), 0, 0); - if (IS_ERR_VALUE(addr)) { - ret = addr; - goto up_fail; - } - - addr += VDSO_OFFSET(VDSO_PREV_PAGES); - - current->mm->context.vdso = (void *)addr; - - /* - * MAYWRITE to allow gdb to COW and set breakpoints - */ - ret = install_special_mapping(mm, - addr, - vdso32_size, - VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - vdso32_pages); - - if (ret) - goto up_fail; - - vma = _install_special_mapping(mm, - addr - VDSO_OFFSET(VDSO_PREV_PAGES), - VDSO_OFFSET(VDSO_PREV_PAGES), - VM_READ, - NULL); - - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto up_fail; - } - - ret = remap_pfn_range(vma, - addr - VDSO_OFFSET(VDSO_VVAR_PAGE), - __pa_symbol(&__vvar_page) >> PAGE_SHIFT, - PAGE_SIZE, - PAGE_READONLY); - - if (ret) - goto up_fail; - -#ifdef CONFIG_HPET_TIMER - if (hpet_address) { - ret = io_remap_pfn_range(vma, - addr - VDSO_OFFSET(VDSO_HPET_PAGE), - hpet_address >> PAGE_SHIFT, - PAGE_SIZE, - pgprot_noncached(PAGE_READONLY)); - - if (ret) - goto up_fail; - } -#endif - - current_thread_info()->sysenter_return = - VDSO32_SYMBOL(addr, SYSENTER_RETURN); - - up_fail: - if (ret) - current->mm->context.vdso = NULL; - - up_write(&mm->mmap_sem); - - return ret; -} - #ifdef CONFIG_X86_64 subsys_initcall(sysenter_setup); @@ -245,14 +92,7 @@ subsys_initcall(sysenter_setup); static struct ctl_table abi_table2[] = { { .procname = "vsyscall32", - .data = &sysctl_vsyscall32, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, - { - .procname = "ldt16", - .data = &sysctl_ldt16, + .data = &vdso32_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec @@ -279,13 +119,6 @@ __initcall(ia32_binfmt_init); #else /* CONFIG_X86_32 */ -const char *arch_vma_name(struct vm_area_struct *vma) -{ - if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso) - return "[vdso]"; - return NULL; -} - struct vm_area_struct *get_gate_vma(struct mm_struct *mm) { return NULL; diff --git a/arch/x86/vdso/vdso32.S b/arch/x86/vdso/vdso32.S deleted file mode 100644 index 018bcd9..0000000 --- a/arch/x86/vdso/vdso32.S +++ /dev/null @@ -1,9 +0,0 @@ -#include <asm/vdso.h> - -DEFINE_VDSO_IMAGE(vdso32_int80, "arch/x86/vdso/vdso32-int80.so") - -#ifdef CONFIG_COMPAT -DEFINE_VDSO_IMAGE(vdso32_syscall, "arch/x86/vdso/vdso32-syscall.so") -#endif - -DEFINE_VDSO_IMAGE(vdso32_sysenter, "arch/x86/vdso/vdso32-sysenter.so") diff --git a/arch/x86/vdso/vdso32/vdso32.lds.S b/arch/x86/vdso/vdso32/vdso32.lds.S index aadb8b9..31056cf 100644 --- a/arch/x86/vdso/vdso32/vdso32.lds.S +++ b/arch/x86/vdso/vdso32/vdso32.lds.S @@ -1,17 +1,14 @@ /* * Linker script for 32-bit vDSO. * We #include the file to define the layout details. - * Here we only choose the prelinked virtual address. * * This file defines the version script giving the user-exported symbols in - * the DSO. We can define local symbols here called VDSO* to make their - * values visible using the asm-x86/vdso.h macros from the kernel proper. + * the DSO. */ #include <asm/page.h> #define BUILD_VDSO32 -#define VDSO_PRELINK 0 #include "../vdso-layout.lds.S" @@ -38,13 +35,3 @@ VERSION local: *; }; } - -/* - * Symbols we define here called VDSO* get their values into vdso32-syms.h. - */ -VDSO32_vsyscall = __kernel_vsyscall; -VDSO32_sigreturn = __kernel_sigreturn; -VDSO32_rt_sigreturn = __kernel_rt_sigreturn; -VDSO32_clock_gettime = clock_gettime; -VDSO32_gettimeofday = gettimeofday; -VDSO32_time = time; diff --git a/arch/x86/vdso/vdsox32.S b/arch/x86/vdso/vdsox32.S deleted file mode 100644 index f4aa34e..0000000 --- a/arch/x86/vdso/vdsox32.S +++ /dev/null @@ -1,3 +0,0 @@ -#include <asm/vdso.h> - -DEFINE_VDSO_IMAGE(vdsox32, "arch/x86/vdso/vdsox32.so") diff --git a/arch/x86/vdso/vdsox32.lds.S b/arch/x86/vdso/vdsox32.lds.S index 62272aa..46b991b 100644 --- a/arch/x86/vdso/vdsox32.lds.S +++ b/arch/x86/vdso/vdsox32.lds.S @@ -1,14 +1,11 @@ /* * Linker script for x32 vDSO. * We #include the file to define the layout details. - * Here we only choose the prelinked virtual address. * * This file defines the version script giving the user-exported symbols in - * the DSO. We can define local symbols here called VDSO* to make their - * values visible using the asm-x86/vdso.h macros from the kernel proper. + * the DSO. */ -#define VDSO_PRELINK 0 #include "vdso-layout.lds.S" /* @@ -24,5 +21,3 @@ VERSION { local: *; }; } - -VDSOX32_PRELINK = VDSO_PRELINK; diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c index 1ad1026..e1513c4 100644 --- a/arch/x86/vdso/vma.c +++ b/arch/x86/vdso/vma.c @@ -15,115 +15,51 @@ #include <asm/proto.h> #include <asm/vdso.h> #include <asm/page.h> +#include <asm/hpet.h> #if defined(CONFIG_X86_64) -unsigned int __read_mostly vdso_enabled = 1; +unsigned int __read_mostly vdso64_enabled = 1; -DECLARE_VDSO_IMAGE(vdso); extern unsigned short vdso_sync_cpuid; -static unsigned vdso_size; - -#ifdef CONFIG_X86_X32_ABI -DECLARE_VDSO_IMAGE(vdsox32); -static unsigned vdsox32_size; -#endif #endif -#if defined(CONFIG_X86_32) || defined(CONFIG_X86_X32_ABI) || \ - defined(CONFIG_COMPAT) -void __init patch_vdso32(void *vdso, size_t len) +void __init init_vdso_image(const struct vdso_image *image) { - Elf32_Ehdr *hdr = vdso; - Elf32_Shdr *sechdrs, *alt_sec = 0; - char *secstrings; - void *alt_data; int i; + int npages = (image->size) / PAGE_SIZE; - BUG_ON(len < sizeof(Elf32_Ehdr)); - BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0); - - sechdrs = (void *)hdr + hdr->e_shoff; - secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - - for (i = 1; i < hdr->e_shnum; i++) { - Elf32_Shdr *shdr = &sechdrs[i]; - if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) { - alt_sec = shdr; - goto found; - } - } - - /* If we get here, it's probably a bug. */ - pr_warning("patch_vdso32: .altinstructions not found\n"); - return; /* nothing to patch */ + BUG_ON(image->size % PAGE_SIZE != 0); + for (i = 0; i < npages; i++) + image->text_mapping.pages[i] = + virt_to_page(image->data + i*PAGE_SIZE); -found: - alt_data = (void *)hdr + alt_sec->sh_offset; - apply_alternatives(alt_data, alt_data + alt_sec->sh_size); + apply_alternatives((struct alt_instr *)(image->data + image->alt), + (struct alt_instr *)(image->data + image->alt + + image->alt_len)); } -#endif #if defined(CONFIG_X86_64) -static void __init patch_vdso64(void *vdso, size_t len) -{ - Elf64_Ehdr *hdr = vdso; - Elf64_Shdr *sechdrs, *alt_sec = 0; - char *secstrings; - void *alt_data; - int i; - - BUG_ON(len < sizeof(Elf64_Ehdr)); - BUG_ON(memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0); - - sechdrs = (void *)hdr + hdr->e_shoff; - secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - - for (i = 1; i < hdr->e_shnum; i++) { - Elf64_Shdr *shdr = &sechdrs[i]; - if (!strcmp(secstrings + shdr->sh_name, ".altinstructions")) { - alt_sec = shdr; - goto found; - } - } - - /* If we get here, it's probably a bug. */ - pr_warning("patch_vdso64: .altinstructions not found\n"); - return; /* nothing to patch */ - -found: - alt_data = (void *)hdr + alt_sec->sh_offset; - apply_alternatives(alt_data, alt_data + alt_sec->sh_size); -} - static int __init init_vdso(void) { - int npages = (vdso_end - vdso_start + PAGE_SIZE - 1) / PAGE_SIZE; - int i; - - patch_vdso64(vdso_start, vdso_end - vdso_start); - - vdso_size = npages << PAGE_SHIFT; - for (i = 0; i < npages; i++) - vdso_pages[i] = virt_to_page(vdso_start + i*PAGE_SIZE); + init_vdso_image(&vdso_image_64); #ifdef CONFIG_X86_X32_ABI - patch_vdso32(vdsox32_start, vdsox32_end - vdsox32_start); - npages = (vdsox32_end - vdsox32_start + PAGE_SIZE - 1) / PAGE_SIZE; - vdsox32_size = npages << PAGE_SHIFT; - for (i = 0; i < npages; i++) - vdsox32_pages[i] = virt_to_page(vdsox32_start + i*PAGE_SIZE); + init_vdso_image(&vdso_image_x32); #endif return 0; } subsys_initcall(init_vdso); +#endif struct linux_binprm; /* Put the vdso above the (randomized) stack with another randomized offset. This way there is no hole in the middle of address space. To save memory make sure it is still in the same PTE as the stack top. - This doesn't give that many random bits */ + This doesn't give that many random bits. + + Only used for the 64-bit and x32 vdsos. */ static unsigned long vdso_addr(unsigned long start, unsigned len) { unsigned long addr, end; @@ -149,61 +85,149 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) return addr; } -/* Setup a VMA at program startup for the vsyscall page. - Not called for compat tasks */ -static int setup_additional_pages(struct linux_binprm *bprm, - int uses_interp, - struct page **pages, - unsigned size) +static int map_vdso(const struct vdso_image *image, bool calculate_addr) { struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; unsigned long addr; - int ret; - - if (!vdso_enabled) - return 0; + int ret = 0; + static struct page *no_pages[] = {NULL}; + static struct vm_special_mapping vvar_mapping = { + .name = "[vvar]", + .pages = no_pages, + }; + + if (calculate_addr) { + addr = vdso_addr(current->mm->start_stack, + image->sym_end_mapping); + } else { + addr = 0; + } down_write(&mm->mmap_sem); - addr = vdso_addr(mm->start_stack, size); - addr = get_unmapped_area(NULL, addr, size, 0, 0); + + addr = get_unmapped_area(NULL, addr, image->sym_end_mapping, 0, 0); if (IS_ERR_VALUE(addr)) { ret = addr; goto up_fail; } - current->mm->context.vdso = (void *)addr; + current->mm->context.vdso = (void __user *)addr; - ret = install_special_mapping(mm, addr, size, - VM_READ|VM_EXEC| - VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, - pages); - if (ret) { - current->mm->context.vdso = NULL; + /* + * MAYWRITE to allow gdb to COW and set breakpoints + */ + vma = _install_special_mapping(mm, + addr, + image->size, + VM_READ|VM_EXEC| + VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, + &image->text_mapping); + + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); goto up_fail; } + vma = _install_special_mapping(mm, + addr + image->size, + image->sym_end_mapping - image->size, + VM_READ, + &vvar_mapping); + + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto up_fail; + } + + if (image->sym_vvar_page) + ret = remap_pfn_range(vma, + addr + image->sym_vvar_page, + __pa_symbol(&__vvar_page) >> PAGE_SHIFT, + PAGE_SIZE, + PAGE_READONLY); + + if (ret) + goto up_fail; + +#ifdef CONFIG_HPET_TIMER + if (hpet_address && image->sym_hpet_page) { + ret = io_remap_pfn_range(vma, + addr + image->sym_hpet_page, + hpet_address >> PAGE_SHIFT, + PAGE_SIZE, + pgprot_noncached(PAGE_READONLY)); + + if (ret) + goto up_fail; + } +#endif + up_fail: + if (ret) + current->mm->context.vdso = NULL; + up_write(&mm->mmap_sem); return ret; } +#if defined(CONFIG_X86_32) || defined(CONFIG_COMPAT) +static int load_vdso32(void) +{ + int ret; + + if (vdso32_enabled != 1) /* Other values all mean "disabled" */ + return 0; + + ret = map_vdso(selected_vdso32, false); + if (ret) + return ret; + + if (selected_vdso32->sym_VDSO32_SYSENTER_RETURN) + current_thread_info()->sysenter_return = + current->mm->context.vdso + + selected_vdso32->sym_VDSO32_SYSENTER_RETURN; + + return 0; +} +#endif + +#ifdef CONFIG_X86_64 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - return setup_additional_pages(bprm, uses_interp, vdso_pages, - vdso_size); + if (!vdso64_enabled) + return 0; + + return map_vdso(&vdso_image_64, true); } +#ifdef CONFIG_COMPAT +int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp) +{ #ifdef CONFIG_X86_X32_ABI -int x32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) + if (test_thread_flag(TIF_X32)) { + if (!vdso64_enabled) + return 0; + + return map_vdso(&vdso_image_x32, true); + } +#endif + + return load_vdso32(); +} +#endif +#else +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { - return setup_additional_pages(bprm, uses_interp, vdsox32_pages, - vdsox32_size); + return load_vdso32(); } #endif +#ifdef CONFIG_X86_64 static __init int vdso_setup(char *s) { - vdso_enabled = simple_strtoul(s, NULL, 0); + vdso64_enabled = simple_strtoul(s, NULL, 0); return 0; } __setup("vdso=", vdso_setup); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c34bfc4..f17b292 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1339,6 +1339,7 @@ xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) static struct notifier_block xen_panic_block = { .notifier_call= xen_panic_event, + .priority = INT_MIN }; int xen_panic_handler_init(void) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 86e02ea..e8a1201 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1494,7 +1494,7 @@ static int xen_pgd_alloc(struct mm_struct *mm) page->private = (unsigned long)user_pgd; if (user_pgd != NULL) { - user_pgd[pgd_index(VSYSCALL_START)] = + user_pgd[pgd_index(VSYSCALL_ADDR)] = __pgd(__pa(level3_user_vsyscall) | _PAGE_TABLE); ret = 0; } @@ -2062,8 +2062,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) case FIX_KMAP_BEGIN ... FIX_KMAP_END: # endif #else - case VSYSCALL_LAST_PAGE ... VSYSCALL_FIRST_PAGE: - case VVAR_PAGE: + case VSYSCALL_PAGE: #endif case FIX_TEXT_POKE0: case FIX_TEXT_POKE1: @@ -2104,8 +2103,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot) #ifdef CONFIG_X86_64 /* Replicate changes to map the vsyscall page into the user pagetable vsyscall mapping. */ - if ((idx >= VSYSCALL_LAST_PAGE && idx <= VSYSCALL_FIRST_PAGE) || - idx == VVAR_PAGE) { + if (idx == VSYSCALL_PAGE) { unsigned long vaddr = __fix_to_virt(idx); set_pte_vaddr_pud(level3_user_vsyscall, vaddr, pte); } @@ -2510,6 +2508,95 @@ void __init xen_hvm_init_mmu_ops(void) } #endif +#ifdef CONFIG_XEN_PVH +/* + * Map foreign gfn (fgfn), to local pfn (lpfn). This for the user + * space creating new guest on pvh dom0 and needing to map domU pages. + */ +static int xlate_add_to_p2m(unsigned long lpfn, unsigned long fgfn, + unsigned int domid) +{ + int rc, err = 0; + xen_pfn_t gpfn = lpfn; + xen_ulong_t idx = fgfn; + + struct xen_add_to_physmap_range xatp = { + .domid = DOMID_SELF, + .foreign_domid = domid, + .size = 1, + .space = XENMAPSPACE_gmfn_foreign, + }; + set_xen_guest_handle(xatp.idxs, &idx); + set_xen_guest_handle(xatp.gpfns, &gpfn); + set_xen_guest_handle(xatp.errs, &err); + + rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp); + if (rc < 0) + return rc; + return err; +} + +static int xlate_remove_from_p2m(unsigned long spfn, int count) +{ + struct xen_remove_from_physmap xrp; + int i, rc; + + for (i = 0; i < count; i++) { + xrp.domid = DOMID_SELF; + xrp.gpfn = spfn+i; + rc = HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp); + if (rc) + break; + } + return rc; +} + +struct xlate_remap_data { + unsigned long fgfn; /* foreign domain's gfn */ + pgprot_t prot; + domid_t domid; + int index; + struct page **pages; +}; + +static int xlate_map_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, + void *data) +{ + int rc; + struct xlate_remap_data *remap = data; + unsigned long pfn = page_to_pfn(remap->pages[remap->index++]); + pte_t pteval = pte_mkspecial(pfn_pte(pfn, remap->prot)); + + rc = xlate_add_to_p2m(pfn, remap->fgfn, remap->domid); + if (rc) + return rc; + native_set_pte(ptep, pteval); + + return 0; +} + +static int xlate_remap_gfn_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long mfn, + int nr, pgprot_t prot, unsigned domid, + struct page **pages) +{ + int err; + struct xlate_remap_data pvhdata; + + BUG_ON(!pages); + + pvhdata.fgfn = mfn; + pvhdata.prot = prot; + pvhdata.domid = domid; + pvhdata.index = 0; + pvhdata.pages = pages; + err = apply_to_page_range(vma->vm_mm, addr, nr << PAGE_SHIFT, + xlate_map_pte_fn, &pvhdata); + flush_tlb_all(); + return err; +} +#endif + #define REMAP_BATCH_SIZE 16 struct remap_data { @@ -2522,7 +2609,7 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { struct remap_data *rmd = data; - pte_t pte = pte_mkspecial(pfn_pte(rmd->mfn++, rmd->prot)); + pte_t pte = pte_mkspecial(mfn_pte(rmd->mfn++, rmd->prot)); rmd->mmu_update->ptr = virt_to_machine(ptep).maddr; rmd->mmu_update->val = pte_val_ma(pte); @@ -2544,13 +2631,18 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, unsigned long range; int err = 0; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return -EINVAL; - - prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP); - BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO))); + if (xen_feature(XENFEAT_auto_translated_physmap)) { +#ifdef CONFIG_XEN_PVH + /* We need to update the local page tables and the xen HAP */ + return xlate_remap_gfn_range(vma, addr, mfn, nr, prot, + domid, pages); +#else + return -EINVAL; +#endif + } + rmd.mfn = mfn; rmd.prot = prot; @@ -2588,6 +2680,25 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, if (!pages || !xen_feature(XENFEAT_auto_translated_physmap)) return 0; +#ifdef CONFIG_XEN_PVH + while (numpgs--) { + /* + * The mmu has already cleaned up the process mmu + * resources at this point (lookup_address will return + * NULL). + */ + unsigned long pfn = page_to_pfn(pages[numpgs]); + + xlate_remove_from_p2m(pfn, 1); + } + /* + * We don't need to flush tlbs because as part of + * xlate_remove_from_p2m, the hypervisor will do tlb flushes + * after removing the p2m entries from the EPT/NPT + */ + return 0; +#else return -EINVAL; +#endif } EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 85e5d78..9bb3d82 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -36,7 +36,7 @@ * pfn_to_mfn(0xc0000)=0xc0000 * * The benefit of this is, that we can assume for non-RAM regions (think - * PCI BARs, or ACPI spaces), we can create mappings easily b/c we + * PCI BARs, or ACPI spaces), we can create mappings easily because we * get the PFN value to match the MFN. * * For this to work efficiently we have one new page p2m_identity and @@ -60,7 +60,7 @@ * There is also a digram of the P2M at the end that can help. * Imagine your E820 looking as so: * - * 1GB 2GB + * 1GB 2GB 4GB * /-------------------+---------\/----\ /----------\ /---+-----\ * | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM | * \-------------------+---------/\----/ \----------/ \---+-----/ @@ -77,9 +77,8 @@ * of the PFN and the end PFN (263424 and 512256 respectively). The first step * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page * covers 512^2 of page estate (1GB) and in case the start or end PFN is not - * aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn - * to end pfn. We reserve_brk top leaf pages if they are missing (means they - * point to p2m_mid_missing). + * aligned on 512^2*PAGE_SIZE (1GB) we reserve_brk new middle and leaf pages as + * required to split any existing p2m_mid_missing middle pages. * * With the E820 example above, 263424 is not 1GB aligned so we allocate a * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000. @@ -88,7 +87,7 @@ * Next stage is to determine if we need to do a more granular boundary check * on the 4MB (or 2MB depending on architecture) off the start and end pfn's. * We check if the start pfn and end pfn violate that boundary check, and if - * so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer + * so reserve_brk a (p2m[x][y]) leaf page. This way we have a much finer * granularity of setting which PFNs are missing and which ones are identity. * In our example 263424 and 512256 both fail the check so we reserve_brk two * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing" @@ -102,9 +101,10 @@ * * The next step is to walk from the start pfn to the end pfn setting * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity. - * If we find that the middle leaf is pointing to p2m_missing we can swap it - * over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this - * point we do not need to worry about boundary aligment (so no need to + * If we find that the middle entry is pointing to p2m_missing we can swap it + * over to p2m_identity - this way covering 4MB (or 2MB) PFN space (and + * similarly swapping p2m_mid_missing for p2m_mid_identity for larger regions). + * At this point we do not need to worry about boundary aligment (so no need to * reserve_brk a middle page, figure out which PFNs are "missing" and which * ones are identity), as that has been done earlier. If we find that the * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference @@ -118,6 +118,9 @@ * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511] * contain the INVALID_P2M_ENTRY value and are considered "missing." * + * Finally, the region beyond the end of of the E820 (4 GB in this example) + * is set to be identity (in case there are MMIO regions placed here). + * * This is what the p2m ends up looking (for the E820 above) with this * fabulous drawing: * @@ -129,21 +132,27 @@ * |-----| \ | [p2m_identity]+\\ | .... | * | 2 |--\ \-------------------->| ... | \\ \----------------/ * |-----| \ \---------------/ \\ - * | 3 |\ \ \\ p2m_identity - * |-----| \ \-------------------->/---------------\ /-----------------\ - * | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... | - * \-----/ / | [p2m_identity]+-->| ..., ~0 | - * / /---------------\ | .... | \-----------------/ - * / | IDENTITY[@0] | /-+-[x], ~0, ~0.. | - * / | IDENTITY[@256]|<----/ \---------------/ - * / | ~0, ~0, .... | - * | \---------------/ - * | - * p2m_mid_missing p2m_missing - * /-----------------\ /------------\ - * | [p2m_missing] +---->| ~0, ~0, ~0 | - * | [p2m_missing] +---->| ..., ~0 | - * \-----------------/ \------------/ + * | 3 |-\ \ \\ p2m_identity [1] + * |-----| \ \-------------------->/---------------\ /-----------------\ + * | .. |\ | | [p2m_identity]+-->| ~0, ~0, ~0, ... | + * \-----/ | | | [p2m_identity]+-->| ..., ~0 | + * | | | .... | \-----------------/ + * | | +-[x], ~0, ~0.. +\ + * | | \---------------/ \ + * | | \-> /---------------\ + * | V p2m_mid_missing p2m_missing | IDENTITY[@0] | + * | /-----------------\ /------------\ | IDENTITY[@256]| + * | | [p2m_missing] +---->| ~0, ~0, ...| | ~0, ~0, .... | + * | | [p2m_missing] +---->| ..., ~0 | \---------------/ + * | | ... | \------------/ + * | \-----------------/ + * | + * | p2m_mid_identity + * | /-----------------\ + * \-->| [p2m_identity] +---->[1] + * | [p2m_identity] +---->[1] + * | ... | + * \-----------------/ * * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) */ @@ -187,13 +196,15 @@ static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE); static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE); static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_identity, P2M_MID_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_identity_mfn, P2M_MID_PER_PAGE); RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); /* We might hit two boundary violations at the start and end, at max each * boundary violation will require three middle nodes. */ -RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3); +RESERVE_BRK(p2m_mid_extra, PAGE_SIZE * 2 * 3); /* When we populate back during bootup, the amount of pages can vary. The * max we have is seen is 395979, but that does not mean it can't be more. @@ -242,20 +253,20 @@ static void p2m_top_mfn_p_init(unsigned long **top) top[i] = p2m_mid_missing_mfn; } -static void p2m_mid_init(unsigned long **mid) +static void p2m_mid_init(unsigned long **mid, unsigned long *leaf) { unsigned i; for (i = 0; i < P2M_MID_PER_PAGE; i++) - mid[i] = p2m_missing; + mid[i] = leaf; } -static void p2m_mid_mfn_init(unsigned long *mid) +static void p2m_mid_mfn_init(unsigned long *mid, unsigned long *leaf) { unsigned i; for (i = 0; i < P2M_MID_PER_PAGE; i++) - mid[i] = virt_to_mfn(p2m_missing); + mid[i] = virt_to_mfn(leaf); } static void p2m_init(unsigned long *p2m) @@ -286,7 +297,9 @@ void __ref xen_build_mfn_list_list(void) /* Pre-initialize p2m_top_mfn to be completely missing */ if (p2m_top_mfn == NULL) { p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_mfn_init(p2m_mid_missing_mfn); + p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing); + p2m_mid_identity_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity); p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); p2m_top_mfn_p_init(p2m_top_mfn_p); @@ -295,7 +308,8 @@ void __ref xen_build_mfn_list_list(void) p2m_top_mfn_init(p2m_top_mfn); } else { /* Reinitialise, mfn's all change after migration */ - p2m_mid_mfn_init(p2m_mid_missing_mfn); + p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing); + p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity); } for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) { @@ -327,7 +341,7 @@ void __ref xen_build_mfn_list_list(void) * it too late. */ mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_mfn_init(mid_mfn_p); + p2m_mid_mfn_init(mid_mfn_p, p2m_missing); p2m_top_mfn_p[topidx] = mid_mfn_p; } @@ -365,16 +379,17 @@ void __init xen_build_dynamic_phys_to_machine(void) p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE); p2m_init(p2m_missing); + p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_init(p2m_identity); p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_init(p2m_mid_missing); + p2m_mid_init(p2m_mid_missing, p2m_missing); + p2m_mid_identity = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_mid_init(p2m_mid_identity, p2m_identity); p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE); p2m_top_init(p2m_top); - p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_init(p2m_identity); - /* * The domain builder gives us a pre-constructed p2m array in * mfn_list for all the pages initially given to us, so we just @@ -386,7 +401,7 @@ void __init xen_build_dynamic_phys_to_machine(void) if (p2m_top[topidx] == p2m_mid_missing) { unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_init(mid); + p2m_mid_init(mid, p2m_missing); p2m_top[topidx] = mid; } @@ -492,7 +507,7 @@ unsigned long get_phys_to_machine(unsigned long pfn) unsigned topidx, mididx, idx; if (unlikely(pfn >= MAX_P2M_PFN)) - return INVALID_P2M_ENTRY; + return IDENTITY_FRAME(pfn); topidx = p2m_top_index(pfn); mididx = p2m_mid_index(pfn); @@ -545,7 +560,7 @@ static bool alloc_p2m(unsigned long pfn) if (!mid) return false; - p2m_mid_init(mid); + p2m_mid_init(mid, p2m_missing); if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing) free_p2m_page(mid); @@ -565,7 +580,7 @@ static bool alloc_p2m(unsigned long pfn) if (!mid_mfn) return false; - p2m_mid_mfn_init(mid_mfn); + p2m_mid_mfn_init(mid_mfn, p2m_missing); missing_mfn = virt_to_mfn(p2m_mid_missing_mfn); mid_mfn_mfn = virt_to_mfn(mid_mfn); @@ -596,7 +611,7 @@ static bool alloc_p2m(unsigned long pfn) return true; } -static bool __init early_alloc_p2m_middle(unsigned long pfn, bool check_boundary) +static bool __init early_alloc_p2m(unsigned long pfn, bool check_boundary) { unsigned topidx, mididx, idx; unsigned long *p2m; @@ -638,7 +653,7 @@ static bool __init early_alloc_p2m_middle(unsigned long pfn, bool check_boundary return true; } -static bool __init early_alloc_p2m(unsigned long pfn) +static bool __init early_alloc_p2m_middle(unsigned long pfn) { unsigned topidx = p2m_top_index(pfn); unsigned long *mid_mfn_p; @@ -649,7 +664,7 @@ static bool __init early_alloc_p2m(unsigned long pfn) if (mid == p2m_mid_missing) { mid = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_init(mid); + p2m_mid_init(mid, p2m_missing); p2m_top[topidx] = mid; @@ -658,12 +673,12 @@ static bool __init early_alloc_p2m(unsigned long pfn) /* And the save/restore P2M tables.. */ if (mid_mfn_p == p2m_mid_missing_mfn) { mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_mfn_init(mid_mfn_p); + p2m_mid_mfn_init(mid_mfn_p, p2m_missing); p2m_top_mfn_p[topidx] = mid_mfn_p; p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p); /* Note: we don't set mid_mfn_p[midix] here, - * look in early_alloc_p2m_middle */ + * look in early_alloc_p2m() */ } return true; } @@ -739,7 +754,7 @@ found: /* This shouldn't happen */ if (WARN_ON(p2m_top[topidx] == p2m_mid_missing)) - early_alloc_p2m(set_pfn); + early_alloc_p2m_middle(set_pfn); if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing)) return false; @@ -754,13 +769,13 @@ found: bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn) { if (unlikely(!__set_phys_to_machine(pfn, mfn))) { - if (!early_alloc_p2m(pfn)) + if (!early_alloc_p2m_middle(pfn)) return false; if (early_can_reuse_p2m_middle(pfn, mfn)) return __set_phys_to_machine(pfn, mfn); - if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/)) + if (!early_alloc_p2m(pfn, false /* boundary crossover OK!*/)) return false; if (!__set_phys_to_machine(pfn, mfn)) @@ -769,12 +784,30 @@ bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn) return true; } + +static void __init early_split_p2m(unsigned long pfn) +{ + unsigned long mididx, idx; + + mididx = p2m_mid_index(pfn); + idx = p2m_index(pfn); + + /* + * Allocate new middle and leaf pages if this pfn lies in the + * middle of one. + */ + if (mididx || idx) + early_alloc_p2m_middle(pfn); + if (idx) + early_alloc_p2m(pfn, false); +} + unsigned long __init set_phys_range_identity(unsigned long pfn_s, unsigned long pfn_e) { unsigned long pfn; - if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN)) + if (unlikely(pfn_s >= MAX_P2M_PFN)) return 0; if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) @@ -783,19 +816,30 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s, if (pfn_s > pfn_e) return 0; - for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1)); - pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE)); - pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE) - { - WARN_ON(!early_alloc_p2m(pfn)); - } + if (pfn_e > MAX_P2M_PFN) + pfn_e = MAX_P2M_PFN; - early_alloc_p2m_middle(pfn_s, true); - early_alloc_p2m_middle(pfn_e, true); + early_split_p2m(pfn_s); + early_split_p2m(pfn_e); + + for (pfn = pfn_s; pfn < pfn_e;) { + unsigned topidx = p2m_top_index(pfn); + unsigned mididx = p2m_mid_index(pfn); - for (pfn = pfn_s; pfn < pfn_e; pfn++) if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn))) break; + pfn++; + + /* + * If the PFN was set to a middle or leaf identity + * page the remainder must also be identity, so skip + * ahead to the next middle or leaf entry. + */ + if (p2m_top[topidx] == p2m_mid_identity) + pfn = ALIGN(pfn, P2M_MID_PER_PAGE * P2M_PER_PAGE); + else if (p2m_top[topidx][mididx] == p2m_identity) + pfn = ALIGN(pfn, P2M_PER_PAGE); + } if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s), "Identity mapping failed. We are %ld short of 1-1 mappings!\n", @@ -825,8 +869,22 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) /* For sparse holes were the p2m leaf has real PFN along with * PCI holes, stick in the PFN as the MFN value. + * + * set_phys_range_identity() will have allocated new middle + * and leaf pages as required so an existing p2m_mid_missing + * or p2m_missing mean that whole range will be identity so + * these can be switched to p2m_mid_identity or p2m_identity. */ if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) { + if (p2m_top[topidx] == p2m_mid_identity) + return true; + + if (p2m_top[topidx] == p2m_mid_missing) { + WARN_ON(cmpxchg(&p2m_top[topidx], p2m_mid_missing, + p2m_mid_identity) != p2m_mid_missing); + return true; + } + if (p2m_top[topidx][mididx] == p2m_identity) return true; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 0982233..821a11a 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -89,10 +89,10 @@ static void __init xen_add_extra_mem(u64 start, u64 size) for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) { unsigned long mfn = pfn_to_mfn(pfn); - if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn)) + if (WARN_ONCE(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn)) continue; - WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n", - pfn, mfn); + WARN_ONCE(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n", + pfn, mfn); __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } @@ -469,6 +469,15 @@ char * __init xen_memory_setup(void) } /* + * Set the rest as identity mapped, in case PCI BARs are + * located here. + * + * PFNs above MAX_P2M_PFN are considered identity mapped as + * well. + */ + set_phys_range_identity(map[i-1].addr / PAGE_SIZE, ~0ul); + + /* * In domU, the ISA region is normal, usable memory, but we * reserve ISA memory anyway because too many things poke * about in there. @@ -516,10 +525,17 @@ char * __init xen_memory_setup(void) static void __init fiddle_vdso(void) { #ifdef CONFIG_X86_32 + /* + * This could be called before selected_vdso32 is initialized, so + * just fiddle with both possible images. vdso_image_32_syscall + * can't be selected, since it only exists on 64-bit systems. + */ u32 *mask; - mask = VDSO32_SYMBOL(&vdso32_int80_start, NOTE_MASK); + mask = vdso_image_32_int80.data + + vdso_image_32_int80.sym_VDSO32_NOTE_MASK; *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; - mask = VDSO32_SYMBOL(&vdso32_sysenter_start, NOTE_MASK); + mask = vdso_image_32_sysenter.data + + vdso_image_32_sysenter.sym_VDSO32_NOTE_MASK; *mask |= 1 << VDSO_NOTE_NONEGSEG_BIT; #endif } diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 45329c8..c4df9db 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -12,8 +12,10 @@ #include "xen-ops.h" #include "mmu.h" -void xen_arch_pre_suspend(void) +static void xen_pv_pre_suspend(void) { + xen_mm_pin_all(); + xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn); xen_start_info->console.domU.mfn = mfn_to_pfn(xen_start_info->console.domU.mfn); @@ -26,7 +28,7 @@ void xen_arch_pre_suspend(void) BUG(); } -void xen_arch_hvm_post_suspend(int suspend_cancelled) +static void xen_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; @@ -41,7 +43,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled) #endif } -void xen_arch_post_suspend(int suspend_cancelled) +static void xen_pv_post_suspend(int suspend_cancelled) { xen_build_mfn_list_list(); @@ -60,6 +62,21 @@ void xen_arch_post_suspend(int suspend_cancelled) xen_vcpu_restore(); } + xen_mm_unpin_all(); +} + +void xen_arch_pre_suspend(void) +{ + if (xen_pv_domain()) + xen_pv_pre_suspend(); +} + +void xen_arch_post_suspend(int cancelled) +{ + if (xen_pv_domain()) + xen_pv_post_suspend(cancelled); + else + xen_hvm_post_suspend(cancelled); } static void xen_vcpu_notify_restore(void *data) diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1cb6f4c..c834d4b 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -31,6 +31,8 @@ void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); void xen_reserve_top(void); extern unsigned long xen_max_p2m_pfn; +void xen_mm_pin_all(void); +void xen_mm_unpin_all(void); void xen_set_pat(u64); char * __init xen_memory_setup(void); |