diff options
author | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2019-07-10 23:24:10 -0700 |
---|---|---|
committer | Dmitry Torokhov <dmitry.torokhov@gmail.com> | 2019-07-10 23:24:10 -0700 |
commit | 597473720f4dc69749542bfcfed4a927a43d935e (patch) | |
tree | 711bf773910fb93d1dd9120c633adc807685e0d8 /arch/x86/include | |
parent | Input: atmel_mxt_ts - fix leak in mxt_update_cfg() (diff) | |
parent | Input: gpio_keys_polled - allow specifying name of input device (diff) | |
download | linux-dev-597473720f4dc69749542bfcfed4a927a43d935e.tar.xz linux-dev-597473720f4dc69749542bfcfed4a927a43d935e.zip |
Merge branch 'next' into for-linus
Prepare input updates for 5.3 merge window.
Diffstat (limited to 'arch/x86/include')
73 files changed, 878 insertions, 801 deletions
diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h deleted file mode 100644 index 7d3ece8bfb61..000000000000 --- a/arch/x86/include/asm/a.out-core.h +++ /dev/null @@ -1,67 +0,0 @@ -/* a.out coredump register dumper - * - * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ - -#ifndef _ASM_X86_A_OUT_CORE_H -#define _ASM_X86_A_OUT_CORE_H - -#ifdef __KERNEL__ -#ifdef CONFIG_X86_32 - -#include <linux/user.h> -#include <linux/elfcore.h> -#include <linux/mm_types.h> - -#include <asm/debugreg.h> - -/* - * fill in the user structure for an a.out core dump - */ -static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump) -{ -/* changed the size calculations - should hopefully work better. lbt */ - dump->magic = CMAGIC; - dump->start_code = 0; - dump->start_stack = regs->sp & ~(PAGE_SIZE - 1); - dump->u_tsize = ((unsigned long)current->mm->end_code) >> PAGE_SHIFT; - dump->u_dsize = ((unsigned long)(current->mm->brk + (PAGE_SIZE - 1))) - >> PAGE_SHIFT; - dump->u_dsize -= dump->u_tsize; - dump->u_ssize = 0; - aout_dump_debugregs(dump); - - if (dump->start_stack < TASK_SIZE) - dump->u_ssize = ((unsigned long)(TASK_SIZE - dump->start_stack)) - >> PAGE_SHIFT; - - dump->regs.bx = regs->bx; - dump->regs.cx = regs->cx; - dump->regs.dx = regs->dx; - dump->regs.si = regs->si; - dump->regs.di = regs->di; - dump->regs.bp = regs->bp; - dump->regs.ax = regs->ax; - dump->regs.ds = (u16)regs->ds; - dump->regs.es = (u16)regs->es; - dump->regs.fs = (u16)regs->fs; - dump->regs.gs = get_user_gs(regs); - dump->regs.orig_ax = regs->orig_ax; - dump->regs.ip = regs->ip; - dump->regs.cs = (u16)regs->cs; - dump->regs.flags = regs->flags; - dump->regs.sp = regs->sp; - dump->regs.ss = (u16)regs->ss; - - dump->u_fpvalid = dump_fpu(regs, &dump->i387); -} - -#endif /* CONFIG_X86_32 */ -#endif /* __KERNEL__ */ -#endif /* _ASM_X86_A_OUT_CORE_H */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 4cd6a3b71824..4c74073a19cc 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -94,13 +94,12 @@ static inline int alternatives_text_reserved(void *start, void *end) #define alt_total_slen alt_end_marker"b-661b" #define alt_rlen(num) e_replacement(num)"f-"b_replacement(num)"f" -#define __OLDINSTR(oldinstr, num) \ +#define OLDINSTR(oldinstr, num) \ + "# ALT: oldnstr\n" \ "661:\n\t" oldinstr "\n662:\n" \ + "# ALT: padding\n" \ ".skip -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * " \ - "((" alt_rlen(num) ")-(" alt_slen ")),0x90\n" - -#define OLDINSTR(oldinstr, num) \ - __OLDINSTR(oldinstr, num) \ + "((" alt_rlen(num) ")-(" alt_slen ")),0x90\n" \ alt_end_marker ":\n" /* @@ -116,11 +115,23 @@ static inline int alternatives_text_reserved(void *start, void *end) * additionally longer than the first replacement alternative. */ #define OLDINSTR_2(oldinstr, num1, num2) \ + "# ALT: oldinstr2\n" \ "661:\n\t" oldinstr "\n662:\n" \ + "# ALT: padding2\n" \ ".skip -((" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) > 0) * " \ "(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")), 0x90\n" \ alt_end_marker ":\n" +#define OLDINSTR_3(oldinsn, n1, n2, n3) \ + "# ALT: oldinstr3\n" \ + "661:\n\t" oldinsn "\n662:\n" \ + "# ALT: padding3\n" \ + ".skip -((" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3)) \ + " - (" alt_slen ")) > 0) * " \ + "(" alt_max_short(alt_max_short(alt_rlen(n1), alt_rlen(n2)), alt_rlen(n3)) \ + " - (" alt_slen ")), 0x90\n" \ + alt_end_marker ":\n" + #define ALTINSTR_ENTRY(feature, num) \ " .long 661b - .\n" /* label */ \ " .long " b_replacement(num)"f - .\n" /* new instruction */ \ @@ -129,8 +140,9 @@ static inline int alternatives_text_reserved(void *start, void *end) " .byte " alt_rlen(num) "\n" /* replacement len */ \ " .byte " alt_pad_len "\n" /* pad len */ -#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \ - b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n\t" +#define ALTINSTR_REPLACEMENT(newinstr, feature, num) /* replacement */ \ + "# ALT: replacement " #num "\n" \ + b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n" /* alternative assembly primitive: */ #define ALTERNATIVE(oldinstr, newinstr, feature) \ @@ -153,6 +165,19 @@ static inline int alternatives_text_reserved(void *start, void *end) ALTINSTR_REPLACEMENT(newinstr2, feature2, 2) \ ".popsection\n" +#define ALTERNATIVE_3(oldinsn, newinsn1, feat1, newinsn2, feat2, newinsn3, feat3) \ + OLDINSTR_3(oldinsn, 1, 2, 3) \ + ".pushsection .altinstructions,\"a\"\n" \ + ALTINSTR_ENTRY(feat1, 1) \ + ALTINSTR_ENTRY(feat2, 2) \ + ALTINSTR_ENTRY(feat3, 3) \ + ".popsection\n" \ + ".pushsection .altinstr_replacement, \"ax\"\n" \ + ALTINSTR_REPLACEMENT(newinsn1, feat1, 1) \ + ALTINSTR_REPLACEMENT(newinsn2, feat2, 2) \ + ALTINSTR_REPLACEMENT(newinsn3, feat3, 3) \ + ".popsection\n" + /* * Alternative instructions for different CPU types or capabilities. * @@ -174,7 +199,7 @@ static inline int alternatives_text_reserved(void *start, void *end) /* * Alternative inline assembly with input. * - * Pecularities: + * Peculiarities: * No memory clobber here. * Argument numbers start with 1. * Best is to use constraints that are fixed size (like (%1) ... "r") diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h index 34a10b2d5b73..fc0693569f7a 100644 --- a/arch/x86/include/asm/arch_hweight.h +++ b/arch/x86/include/asm/arch_hweight.h @@ -5,15 +5,9 @@ #include <asm/cpufeatures.h> #ifdef CONFIG_64BIT -/* popcnt %edi, %eax */ -#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc7" -/* popcnt %rdi, %rax */ -#define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7" #define REG_IN "D" #define REG_OUT "a" #else -/* popcnt %eax, %eax */ -#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc0" #define REG_IN "a" #define REG_OUT "a" #endif @@ -24,7 +18,7 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res; - asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT) + asm (ALTERNATIVE("call __sw_hweight32", "popcntl %1, %0", X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); @@ -52,7 +46,7 @@ static __always_inline unsigned long __arch_hweight64(__u64 w) { unsigned long res; - asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT) + asm (ALTERNATIVE("call __sw_hweight64", "popcntq %1, %0", X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 1908214b9125..ce92c4acc913 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -7,7 +7,6 @@ #include <asm-generic/asm-prototypes.h> -#include <asm/page.h> #include <asm/pgtable.h> #include <asm/special_insns.h> #include <asm/preempt.h> diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 124f9195eb3e..8e790ec219a5 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -36,22 +36,17 @@ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). */ -#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1) -/* Technically wrong, but this avoids compilation errors on some gcc - versions. */ -#define BITOP_ADDR(x) "=m" (*(volatile long *) (x)) -#else -#define BITOP_ADDR(x) "+m" (*(volatile long *) (x)) -#endif +#define RLONG_ADDR(x) "m" (*(volatile long *) (x)) +#define WBYTE_ADDR(x) "+m" (*(volatile char *) (x)) -#define ADDR BITOP_ADDR(addr) +#define ADDR RLONG_ADDR(addr) /* * We do the locked ops that don't return the old value as * a mask operation on a byte. */ #define IS_IMMEDIATE(nr) (__builtin_constant_p(nr)) -#define CONST_MASK_ADDR(nr, addr) BITOP_ADDR((void *)(addr) + ((nr)>>3)) +#define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) #define CONST_MASK(nr) (1 << ((nr) & 7)) /** @@ -79,7 +74,7 @@ set_bit(long nr, volatile unsigned long *addr) : "memory"); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" - : BITOP_ADDR(addr) : "Ir" (nr) : "memory"); + : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } @@ -94,7 +89,7 @@ set_bit(long nr, volatile unsigned long *addr) */ static __always_inline void __set_bit(long nr, volatile unsigned long *addr) { - asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory"); + asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } /** @@ -116,8 +111,7 @@ clear_bit(long nr, volatile unsigned long *addr) : "iq" ((u8)~CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" - : BITOP_ADDR(addr) - : "Ir" (nr)); + : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } @@ -137,7 +131,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) { - asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) @@ -145,7 +139,7 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile bool negative; asm volatile(LOCK_PREFIX "andb %2,%1" CC_SET(s) - : CC_OUT(s) (negative), ADDR + : CC_OUT(s) (negative), WBYTE_ADDR(addr) : "ir" ((char) ~(1 << nr)) : "memory"); return negative; } @@ -161,13 +155,9 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile * __clear_bit() is non-atomic and implies release semantics before the memory * operation. It can be used for an unlock if no other CPUs can concurrently * modify other bits in the word. - * - * No memory barrier is required here, because x86 cannot reorder stores past - * older loads. Same principle as spin_unlock. */ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) { - barrier(); __clear_bit(nr, addr); } @@ -182,7 +172,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long * */ static __always_inline void __change_bit(long nr, volatile unsigned long *addr) { - asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr)); + asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } /** @@ -202,8 +192,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr) : "iq" ((u8)CONST_MASK(nr))); } else { asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" - : BITOP_ADDR(addr) - : "Ir" (nr)); + : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); } } @@ -248,8 +237,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * asm(__ASM_SIZE(bts) " %2,%1" CC_SET(c) - : CC_OUT(c) (oldbit), ADDR - : "Ir" (nr)); + : CC_OUT(c) (oldbit) + : ADDR, "Ir" (nr) : "memory"); return oldbit; } @@ -288,8 +277,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long asm volatile(__ASM_SIZE(btr) " %2,%1" CC_SET(c) - : CC_OUT(c) (oldbit), ADDR - : "Ir" (nr)); + : CC_OUT(c) (oldbit) + : ADDR, "Ir" (nr) : "memory"); return oldbit; } @@ -300,8 +289,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon asm volatile(__ASM_SIZE(btc) " %2,%1" CC_SET(c) - : CC_OUT(c) (oldbit), ADDR - : "Ir" (nr) : "memory"); + : CC_OUT(c) (oldbit) + : ADDR, "Ir" (nr) : "memory"); return oldbit; } @@ -332,7 +321,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l asm volatile(__ASM_SIZE(bt) " %2,%1" CC_SET(c) : CC_OUT(c) (oldbit) - : "m" (*(unsigned long *)addr), "Ir" (nr)); + : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); return oldbit; } @@ -448,7 +437,7 @@ static __always_inline int ffs(int x) * set bit if value is nonzero. The last (most significant) bit is * at position 32. */ -static __always_inline int fls(int x) +static __always_inline int fls(unsigned int x) { int r; diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h index 7a659c74cd03..f57b94e02c57 100644 --- a/arch/x86/include/asm/checksum_32.h +++ b/arch/x86/include/asm/checksum_32.h @@ -182,7 +182,7 @@ static inline __wsum csum_and_copy_to_user(const void *src, __wsum ret; might_sleep(); - if (access_ok(VERIFY_WRITE, dst, len)) { + if (access_ok(dst, len)) { stac(); ret = csum_partial_copy_generic(src, (__force void *)dst, len, sum, NULL, err_ptr); diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index bfb85e5844ab..a8bfac131256 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -7,7 +7,7 @@ #include <asm/alternative.h> /* Provides LOCK_PREFIX */ /* - * Non-existant functions to indicate usage errors at link time + * Non-existent functions to indicate usage errors at link time * (or compile-time if the compiler implements __compiletime_error(). */ extern void __xchg_wrong_size(void) diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index baeba0567126..31c379c1da41 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _CPU_DEVICE_ID -#define _CPU_DEVICE_ID 1 +#ifndef _ASM_X86_CPU_DEVICE_ID +#define _ASM_X86_CPU_DEVICE_ID /* * Declare drivers belonging to specific x86 CPUs @@ -9,6 +9,33 @@ #include <linux/mod_devicetable.h> +/* + * Match specific microcode revisions. + * + * vendor/family/model/stepping must be all set. + * + * Only checks against the boot CPU. When mixed-stepping configs are + * valid for a CPU model, add a quirk for every valid stepping and + * do the fine-tuning in the quirk handler. + */ + +struct x86_cpu_desc { + u8 x86_family; + u8 x86_vendor; + u8 x86_model; + u8 x86_stepping; + u32 x86_microcode_rev; +}; + +#define INTEL_CPU_DESC(model, stepping, revision) { \ + .x86_family = 6, \ + .x86_vendor = X86_VENDOR_INTEL, \ + .x86_model = (model), \ + .x86_stepping = (stepping), \ + .x86_microcode_rev = (revision), \ +} + extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); +extern bool x86_cpu_has_min_microcode_rev(const struct x86_cpu_desc *table); -#endif +#endif /* _ASM_X86_CPU_DEVICE_ID */ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index aced6c9290d6..0e56ff7e4848 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -112,8 +112,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; test_cpu_cap(c, bit)) #define this_cpu_has(bit) \ - (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ - x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability)) + (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ + x86_this_cpu_test_bit(bit, \ + (unsigned long __percpu *)&cpu_info.x86_capability)) /* * This macro is for detection of features which need kernel @@ -140,7 +141,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); #define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) -#if defined(__clang__) && !defined(CC_HAVE_ASM_GOTO) +#if defined(__clang__) && !defined(CONFIG_CC_HAS_ASM_GOTO) /* * Workaround for the sake of BPF compilation which utilizes kernel diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 28c4a502b419..981ff9479648 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -281,9 +281,11 @@ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_IRPERF (13*32+ 1) /* Instructions Retired Count */ #define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* Always save/restore FP error pointers */ +#define X86_FEATURE_WBNOINVD (13*32+ 9) /* WBNOINVD instruction */ #define X86_FEATURE_AMD_IBPB (13*32+12) /* "" Indirect Branch Prediction Barrier */ #define X86_FEATURE_AMD_IBRS (13*32+14) /* "" Indirect Branch Restricted Speculation */ #define X86_FEATURE_AMD_STIBP (13*32+15) /* "" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* "" Single Thread Indirect Branch Predictors always-on preferred */ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ @@ -342,6 +344,7 @@ /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ #define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* AVX-512 Neural Network Instructions */ #define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */ #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h index a7adb2bfbf0b..0acf5ee45a21 100644 --- a/arch/x86/include/asm/crash.h +++ b/arch/x86/include/asm/crash.h @@ -6,5 +6,6 @@ int crash_load_segments(struct kimage *image); int crash_copy_backup_region(struct kimage *image); int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params); +void crash_smp_send_stop(void); #endif /* _ASM_X86_CRASH_H */ diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 33833d1909af..a5ea841cc6d2 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -16,6 +16,12 @@ # define DISABLE_MPX (1<<(X86_FEATURE_MPX & 31)) #endif +#ifdef CONFIG_X86_SMAP +# define DISABLE_SMAP 0 +#else +# define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31)) +#endif + #ifdef CONFIG_X86_INTEL_UMIP # define DISABLE_UMIP 0 #else @@ -68,7 +74,7 @@ #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) #define DISABLED_MASK8 0 -#define DISABLED_MASK9 (DISABLE_MPX) +#define DISABLED_MASK9 (DISABLE_MPX|DISABLE_SMAP) #define DISABLED_MASK10 0 #define DISABLED_MASK11 0 #define DISABLED_MASK12 0 diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index eea40d52ca78..606a4b6a9812 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -19,7 +19,7 @@ * This is the main reason why we're doing stable VA mappings for RT * services. * - * This flag is used in conjuction with a chicken bit called + * This flag is used in conjunction with a chicken bit called * "efi=old_map" which can be used as a fallback to the old runtime * services mapping method in case there's some b0rkage with a * particular EFI implementation (haha, it is hard to hold up the @@ -82,8 +82,7 @@ struct efi_scratch { #define arch_efi_call_virt_setup() \ ({ \ efi_sync_low_kernel_mappings(); \ - preempt_disable(); \ - __kernel_fpu_begin(); \ + kernel_fpu_begin(); \ firmware_restrict_branch_speculation_start(); \ \ if (!efi_enabled(EFI_OLD_MEMMAP)) \ @@ -99,8 +98,7 @@ struct efi_scratch { efi_switch_mm(efi_scratch.prev_mm); \ \ firmware_restrict_branch_speculation_end(); \ - __kernel_fpu_end(); \ - preempt_enable(); \ + kernel_fpu_end(); \ }) extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size, @@ -141,6 +139,8 @@ extern int __init efi_reuse_config(u64 tables, int nr_tables); extern void efi_delete_dummy_variable(void); extern void efi_switch_mm(struct mm_struct *mm); extern void efi_recover_from_page_fault(unsigned long phys_addr); +extern void efi_free_boot_services(void); +extern void efi_reserve_boot_services(void); struct efi_setup_data { u64 fw_vendor; @@ -170,7 +170,6 @@ static inline bool efi_runtime_supported(void) return false; } -extern struct console early_efi_console; extern void parse_efi_setup(u64 phys_addr, u32 data_len); extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index a9caac9d4a72..b56d504af654 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -12,17 +12,12 @@ #define _ASM_X86_FPU_API_H /* - * Careful: __kernel_fpu_begin/end() must be called with preempt disabled - * and they don't touch the preempt state on their own. - * If you enable preemption after __kernel_fpu_begin(), preempt notifier - * should call the __kernel_fpu_end() to prevent the kernel/user FPU - * state from getting corrupted. KVM for example uses this model. - * - * All other cases use kernel_fpu_begin/end() which disable preemption - * during kernel FPU usage. + * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It + * disables preemption so be careful if you intend to use it for long periods + * of time. + * If you intend to use the FPU in softirq you need to check first with + * irq_fpu_usable() if it is possible. */ -extern void __kernel_fpu_begin(void); -extern void __kernel_fpu_end(void); extern void kernel_fpu_begin(void); extern void kernel_fpu_end(void); extern bool irq_fpu_usable(void); diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 69dcdf195b61..fb04a3ded7dd 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -106,6 +106,9 @@ extern void fpstate_sanitize_xstate(struct fpu *fpu); #define user_insn(insn, output, input...) \ ({ \ int err; \ + \ + might_fault(); \ + \ asm volatile(ASM_STAC "\n" \ "1:" #insn "\n\t" \ "2: " ASM_CLAC "\n" \ @@ -134,37 +137,25 @@ static inline int copy_fxregs_to_user(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxsave %[fx], [fx] "=m" (*fx), "m" (*fx)); - else if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) + else return user_insn(fxsaveq %[fx], [fx] "=m" (*fx), "m" (*fx)); - /* See comment in copy_fxregs_to_kernel() below. */ - return user_insn(rex64/fxsave (%[fx]), "=m" (*fx), [fx] "R" (fx)); } static inline void copy_kernel_to_fxregs(struct fxregs_state *fx) { - if (IS_ENABLED(CONFIG_X86_32)) { + if (IS_ENABLED(CONFIG_X86_32)) kernel_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - } else { - if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) { - kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - } else { - /* See comment in copy_fxregs_to_kernel() below. */ - kernel_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), "m" (*fx)); - } - } + else + kernel_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); } static inline int copy_user_to_fxregs(struct fxregs_state __user *fx) { if (IS_ENABLED(CONFIG_X86_32)) return user_insn(fxrstor %[fx], "=m" (*fx), [fx] "m" (*fx)); - else if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) + else return user_insn(fxrstorq %[fx], "=m" (*fx), [fx] "m" (*fx)); - - /* See comment in copy_fxregs_to_kernel() below. */ - return user_insn(rex64/fxrstor (%[fx]), "=m" (*fx), [fx] "R" (fx), - "m" (*fx)); } static inline void copy_kernel_to_fregs(struct fregs_state *fx) @@ -181,34 +172,8 @@ static inline void copy_fxregs_to_kernel(struct fpu *fpu) { if (IS_ENABLED(CONFIG_X86_32)) asm volatile( "fxsave %[fx]" : [fx] "=m" (fpu->state.fxsave)); - else if (IS_ENABLED(CONFIG_AS_FXSAVEQ)) + else asm volatile("fxsaveq %[fx]" : [fx] "=m" (fpu->state.fxsave)); - else { - /* Using "rex64; fxsave %0" is broken because, if the memory - * operand uses any extended registers for addressing, a second - * REX prefix will be generated (to the assembler, rex64 - * followed by semicolon is a separate instruction), and hence - * the 64-bitness is lost. - * - * Using "fxsaveq %0" would be the ideal choice, but is only - * supported starting with gas 2.16. - * - * Using, as a workaround, the properly prefixed form below - * isn't accepted by any binutils version so far released, - * complaining that the same type of prefix is used twice if - * an extended register is needed for addressing (fix submitted - * to mainline 2005-11-21). - * - * asm volatile("rex64/fxsave %0" : "=m" (fpu->state.fxsave)); - * - * This, however, we can work around by forcing the compiler to - * select an addressing mode that doesn't require extended - * registers. - */ - asm volatile( "rex64/fxsave (%[fx])" - : "=m" (fpu->state.fxsave) - : [fx] "R" (&fpu->state.fxsave)); - } } /* These macros all use (%edi)/(%rdi) as the single memory argument. */ @@ -411,6 +376,13 @@ static inline int copy_fpregs_to_fpstate(struct fpu *fpu) { if (likely(use_xsave())) { copy_xregs_to_kernel(&fpu->state.xsave); + + /* + * AVX512 state is tracked here because its use is + * known to slow the max clock speed of the core. + */ + if (fpu->state.xsave.header.xfeatures & XFEATURE_MASK_AVX512) + fpu->avx512_timestamp = jiffies; return 1; } diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index 202c53918ecf..2e32e178e064 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -303,6 +303,13 @@ struct fpu { unsigned char initialized; /* + * @avx512_timestamp: + * + * Records the timestamp of AVX512 use during last context switch. + */ + unsigned long avx512_timestamp; + + /* * @state: * * In-memory copy of all FPU registers that we save/restore diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 4139f7650fe5..2bdbbbcfa393 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -10,6 +10,7 @@ #define _ASM_X86_HYPERV_TLFS_H #include <linux/types.h> +#include <asm/page.h> /* * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent @@ -30,158 +31,150 @@ /* * Feature identification. EAX indicates which features are available * to the partition based upon the current partition privileges. + * These are HYPERV_CPUID_FEATURES.EAX bits. */ /* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */ -#define HV_X64_MSR_VP_RUNTIME_AVAILABLE (1 << 0) +#define HV_X64_MSR_VP_RUNTIME_AVAILABLE BIT(0) /* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/ -#define HV_MSR_TIME_REF_COUNT_AVAILABLE (1 << 1) -/* Partition reference TSC MSR is available */ -#define HV_MSR_REFERENCE_TSC_AVAILABLE (1 << 9) -/* Partition Guest IDLE MSR is available */ -#define HV_X64_MSR_GUEST_IDLE_AVAILABLE (1 << 10) - -/* A partition's reference time stamp counter (TSC) page */ -#define HV_X64_MSR_REFERENCE_TSC 0x40000021 - -/* - * There is a single feature flag that signifies if the partition has access - * to MSRs with local APIC and TSC frequencies. - */ -#define HV_X64_ACCESS_FREQUENCY_MSRS (1 << 11) - -/* AccessReenlightenmentControls privilege */ -#define HV_X64_ACCESS_REENLIGHTENMENT BIT(13) - +#define HV_MSR_TIME_REF_COUNT_AVAILABLE BIT(1) /* * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available */ -#define HV_X64_MSR_SYNIC_AVAILABLE (1 << 2) +#define HV_X64_MSR_SYNIC_AVAILABLE BIT(2) /* * Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through * HV_X64_MSR_STIMER3_COUNT) available */ -#define HV_MSR_SYNTIMER_AVAILABLE (1 << 3) +#define HV_MSR_SYNTIMER_AVAILABLE BIT(3) /* * APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR) * are available */ -#define HV_X64_MSR_APIC_ACCESS_AVAILABLE (1 << 4) +#define HV_X64_MSR_APIC_ACCESS_AVAILABLE BIT(4) /* Hypercall MSRs (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL) available*/ -#define HV_X64_MSR_HYPERCALL_AVAILABLE (1 << 5) +#define HV_X64_MSR_HYPERCALL_AVAILABLE BIT(5) /* Access virtual processor index MSR (HV_X64_MSR_VP_INDEX) available*/ -#define HV_X64_MSR_VP_INDEX_AVAILABLE (1 << 6) +#define HV_X64_MSR_VP_INDEX_AVAILABLE BIT(6) /* Virtual system reset MSR (HV_X64_MSR_RESET) is available*/ -#define HV_X64_MSR_RESET_AVAILABLE (1 << 7) - /* - * Access statistics pages MSRs (HV_X64_MSR_STATS_PARTITION_RETAIL_PAGE, - * HV_X64_MSR_STATS_PARTITION_INTERNAL_PAGE, HV_X64_MSR_STATS_VP_RETAIL_PAGE, - * HV_X64_MSR_STATS_VP_INTERNAL_PAGE) available - */ -#define HV_X64_MSR_STAT_PAGES_AVAILABLE (1 << 8) - -/* Frequency MSRs available */ -#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE (1 << 8) - -/* Crash MSR available */ -#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10) - -/* stimer Direct Mode is available */ -#define HV_STIMER_DIRECT_MODE_AVAILABLE (1 << 19) +#define HV_X64_MSR_RESET_AVAILABLE BIT(7) +/* + * Access statistics pages MSRs (HV_X64_MSR_STATS_PARTITION_RETAIL_PAGE, + * HV_X64_MSR_STATS_PARTITION_INTERNAL_PAGE, HV_X64_MSR_STATS_VP_RETAIL_PAGE, + * HV_X64_MSR_STATS_VP_INTERNAL_PAGE) available + */ +#define HV_X64_MSR_STAT_PAGES_AVAILABLE BIT(8) +/* Partition reference TSC MSR is available */ +#define HV_MSR_REFERENCE_TSC_AVAILABLE BIT(9) +/* Partition Guest IDLE MSR is available */ +#define HV_X64_MSR_GUEST_IDLE_AVAILABLE BIT(10) +/* + * There is a single feature flag that signifies if the partition has access + * to MSRs with local APIC and TSC frequencies. + */ +#define HV_X64_ACCESS_FREQUENCY_MSRS BIT(11) +/* AccessReenlightenmentControls privilege */ +#define HV_X64_ACCESS_REENLIGHTENMENT BIT(13) /* - * Feature identification: EBX indicates which flags were specified at - * partition creation. The format is the same as the partition creation - * flag structure defined in section Partition Creation Flags. + * Feature identification: indicates which flags were specified at partition + * creation. The format is the same as the partition creation flag structure + * defined in section Partition Creation Flags. + * These are HYPERV_CPUID_FEATURES.EBX bits. */ -#define HV_X64_CREATE_PARTITIONS (1 << 0) -#define HV_X64_ACCESS_PARTITION_ID (1 << 1) -#define HV_X64_ACCESS_MEMORY_POOL (1 << 2) -#define HV_X64_ADJUST_MESSAGE_BUFFERS (1 << 3) -#define HV_X64_POST_MESSAGES (1 << 4) -#define HV_X64_SIGNAL_EVENTS (1 << 5) -#define HV_X64_CREATE_PORT (1 << 6) -#define HV_X64_CONNECT_PORT (1 << 7) -#define HV_X64_ACCESS_STATS (1 << 8) -#define HV_X64_DEBUGGING (1 << 11) -#define HV_X64_CPU_POWER_MANAGEMENT (1 << 12) -#define HV_X64_CONFIGURE_PROFILER (1 << 13) +#define HV_X64_CREATE_PARTITIONS BIT(0) +#define HV_X64_ACCESS_PARTITION_ID BIT(1) +#define HV_X64_ACCESS_MEMORY_POOL BIT(2) +#define HV_X64_ADJUST_MESSAGE_BUFFERS BIT(3) +#define HV_X64_POST_MESSAGES BIT(4) +#define HV_X64_SIGNAL_EVENTS BIT(5) +#define HV_X64_CREATE_PORT BIT(6) +#define HV_X64_CONNECT_PORT BIT(7) +#define HV_X64_ACCESS_STATS BIT(8) +#define HV_X64_DEBUGGING BIT(11) +#define HV_X64_CPU_POWER_MANAGEMENT BIT(12) /* * Feature identification. EDX indicates which miscellaneous features * are available to the partition. + * These are HYPERV_CPUID_FEATURES.EDX bits. */ /* The MWAIT instruction is available (per section MONITOR / MWAIT) */ -#define HV_X64_MWAIT_AVAILABLE (1 << 0) +#define HV_X64_MWAIT_AVAILABLE BIT(0) /* Guest debugging support is available */ -#define HV_X64_GUEST_DEBUGGING_AVAILABLE (1 << 1) +#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1) /* Performance Monitor support is available*/ -#define HV_X64_PERF_MONITOR_AVAILABLE (1 << 2) +#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2) /* Support for physical CPU dynamic partitioning events is available*/ -#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE (1 << 3) +#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3) /* * Support for passing hypercall input parameter block via XMM * registers is available */ -#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE (1 << 4) +#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4) /* Support for a virtual guest idle state is available */ -#define HV_X64_GUEST_IDLE_STATE_AVAILABLE (1 << 5) -/* Guest crash data handler available */ -#define HV_X64_GUEST_CRASH_MSR_AVAILABLE (1 << 10) +#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5) +/* Frequency MSRs available */ +#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8) +/* Crash MSR available */ +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) +/* stimer Direct Mode is available */ +#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19) /* * Implementation recommendations. Indicates which behaviors the hypervisor * recommends the OS implement for optimal performance. + * These are HYPERV_CPUID_ENLIGHTMENT_INFO.EAX bits. + */ +/* + * Recommend using hypercall for address space switches rather + * than MOV to CR3 instruction */ - /* - * Recommend using hypercall for address space switches rather - * than MOV to CR3 instruction - */ -#define HV_X64_AS_SWITCH_RECOMMENDED (1 << 0) +#define HV_X64_AS_SWITCH_RECOMMENDED BIT(0) /* Recommend using hypercall for local TLB flushes rather * than INVLPG or MOV to CR3 instructions */ -#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED (1 << 1) +#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED BIT(1) /* * Recommend using hypercall for remote TLB flushes rather * than inter-processor interrupts */ -#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED (1 << 2) +#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED BIT(2) /* * Recommend using MSRs for accessing APIC registers * EOI, ICR and TPR rather than their memory-mapped counterparts */ -#define HV_X64_APIC_ACCESS_RECOMMENDED (1 << 3) +#define HV_X64_APIC_ACCESS_RECOMMENDED BIT(3) /* Recommend using the hypervisor-provided MSR to initiate a system RESET */ -#define HV_X64_SYSTEM_RESET_RECOMMENDED (1 << 4) +#define HV_X64_SYSTEM_RESET_RECOMMENDED BIT(4) /* * Recommend using relaxed timing for this partition. If used, * the VM should disable any watchdog timeouts that rely on the * timely delivery of external interrupts */ -#define HV_X64_RELAXED_TIMING_RECOMMENDED (1 << 5) +#define HV_X64_RELAXED_TIMING_RECOMMENDED BIT(5) /* * Recommend not using Auto End-Of-Interrupt feature */ -#define HV_DEPRECATING_AEOI_RECOMMENDED (1 << 9) +#define HV_DEPRECATING_AEOI_RECOMMENDED BIT(9) /* * Recommend using cluster IPI hypercalls. */ -#define HV_X64_CLUSTER_IPI_RECOMMENDED (1 << 10) +#define HV_X64_CLUSTER_IPI_RECOMMENDED BIT(10) /* Recommend using the newer ExProcessorMasks interface */ -#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED (1 << 11) +#define HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED BIT(11) /* Recommend using enlightened VMCS */ -#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED (1 << 14) +#define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED BIT(14) -/* - * Crash notification flags. - */ -#define HV_CRASH_CTL_CRASH_NOTIFY_MSG BIT_ULL(62) -#define HV_CRASH_CTL_CRASH_NOTIFY BIT_ULL(63) +/* Nested features. These are HYPERV_CPUID_NESTED_FEATURES.EAX bits. */ +#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) +#define HV_X64_NESTED_MSR_BITMAP BIT(19) + +/* Hyper-V specific model specific registers (MSRs) */ /* MSR used to identify the guest OS. */ #define HV_X64_MSR_GUEST_OS_ID 0x40000000 @@ -201,6 +194,9 @@ /* MSR used to read the per-partition time reference counter */ #define HV_X64_MSR_TIME_REF_COUNT 0x40000020 +/* A partition's reference time stamp counter (TSC) page */ +#define HV_X64_MSR_REFERENCE_TSC 0x40000021 + /* MSR used to retrieve the TSC frequency */ #define HV_X64_MSR_TSC_FREQUENCY 0x40000022 @@ -258,9 +254,11 @@ #define HV_X64_MSR_CRASH_P3 0x40000103 #define HV_X64_MSR_CRASH_P4 0x40000104 #define HV_X64_MSR_CRASH_CTL 0x40000105 -#define HV_X64_MSR_CRASH_CTL_NOTIFY (1ULL << 63) -#define HV_X64_MSR_CRASH_PARAMS \ - (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) + +/* TSC emulation after migration */ +#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 +#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 +#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 /* * Declare the MSR used to setup pages used to communicate with the hypervisor. @@ -271,7 +269,7 @@ union hv_x64_msr_hypercall_contents { u64 enable:1; u64 reserved:11; u64 guest_physical_address:52; - }; + } __packed; }; /* @@ -283,7 +281,7 @@ struct ms_hyperv_tsc_page { volatile u64 tsc_scale; volatile s64 tsc_offset; u64 reserved2[509]; -}; +} __packed; /* * The guest OS needs to register the guest ID with the hypervisor. @@ -311,39 +309,37 @@ struct ms_hyperv_tsc_page { #define HV_LINUX_VENDOR_ID 0x8100 -/* TSC emulation after migration */ -#define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 - -/* Nested features (CPUID 0x4000000A) EAX */ -#define HV_X64_NESTED_GUEST_MAPPING_FLUSH BIT(18) -#define HV_X64_NESTED_MSR_BITMAP BIT(19) - struct hv_reenlightenment_control { __u64 vector:8; __u64 reserved1:8; __u64 enabled:1; __u64 reserved2:15; __u64 target_vp:32; -}; - -#define HV_X64_MSR_TSC_EMULATION_CONTROL 0x40000107 -#define HV_X64_MSR_TSC_EMULATION_STATUS 0x40000108 +} __packed; struct hv_tsc_emulation_control { __u64 enabled:1; __u64 reserved:63; -}; +} __packed; struct hv_tsc_emulation_status { __u64 inprogress:1; __u64 reserved:63; -}; +} __packed; #define HV_X64_MSR_HYPERCALL_ENABLE 0x00000001 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT 12 #define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK \ (~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1)) +/* + * Crash notification (HV_X64_MSR_CRASH_CTL) flags. + */ +#define HV_CRASH_CTL_CRASH_NOTIFY_MSG BIT_ULL(62) +#define HV_CRASH_CTL_CRASH_NOTIFY BIT_ULL(63) +#define HV_X64_MSR_CRASH_PARAMS \ + (1 + (HV_X64_MSR_CRASH_P4 - HV_X64_MSR_CRASH_P0)) + #define HV_IPI_LOW_VECTOR 0x10 #define HV_IPI_HIGH_VECTOR 0xff @@ -358,6 +354,7 @@ struct hv_tsc_emulation_status { #define HVCALL_POST_MESSAGE 0x005c #define HVCALL_SIGNAL_EVENT 0x005d #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af +#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0 #define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001 #define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12 @@ -409,7 +406,7 @@ typedef struct _HV_REFERENCE_TSC_PAGE { __u32 res1; __u64 tsc_scale; __s64 tsc_offset; -} HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE; +} __packed HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE; /* Define the number of synthetic interrupt sources. */ #define HV_SYNIC_SINT_COUNT (16) @@ -466,7 +463,7 @@ union hv_message_flags { struct { __u8 msg_pending:1; __u8 reserved:7; - }; + } __packed; }; /* Define port identifier type. */ @@ -475,7 +472,7 @@ union hv_port_id { struct { __u32 id:24; __u32 reserved:8; - } u; + } __packed u; }; /* Define synthetic interrupt controller message header. */ @@ -488,7 +485,7 @@ struct hv_message_header { __u64 sender; union hv_port_id port; }; -}; +} __packed; /* Define synthetic interrupt controller message format. */ struct hv_message { @@ -496,12 +493,12 @@ struct hv_message { union { __u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; } u; -}; +} __packed; /* Define the synthetic interrupt message page layout. */ struct hv_message_page { struct hv_message sint_message[HV_SYNIC_SINT_COUNT]; -}; +} __packed; /* Define timer message payload structure. */ struct hv_timer_message_payload { @@ -509,7 +506,7 @@ struct hv_timer_message_payload { __u32 reserved; __u64 expiration_time; /* When the timer expired */ __u64 delivery_time; /* When the message was delivered */ -}; +} __packed; /* Define virtual processor assist page structure. */ struct hv_vp_assist_page { @@ -518,8 +515,9 @@ struct hv_vp_assist_page { __u64 vtl_control[2]; __u64 nested_enlightenments_control[2]; __u32 enlighten_vmentry; + __u32 padding; __u64 current_nested_vmcs; -}; +} __packed; struct hv_enlightened_vmcs { u32 revision_id; @@ -533,6 +531,8 @@ struct hv_enlightened_vmcs { u16 host_gs_selector; u16 host_tr_selector; + u16 padding16_1; + u64 host_ia32_pat; u64 host_ia32_efer; @@ -651,7 +651,7 @@ struct hv_enlightened_vmcs { u64 ept_pointer; u16 virtual_processor_id; - u16 padding16[3]; + u16 padding16_2[3]; u64 padding64_2[5]; u64 guest_physical_address; @@ -693,7 +693,7 @@ struct hv_enlightened_vmcs { u32 nested_flush_hypercall:1; u32 msr_bitmap:1; u32 reserved:30; - } hv_enlightenments_control; + } __packed hv_enlightenments_control; u32 hv_vp_id; u64 hv_vm_id; @@ -703,7 +703,7 @@ struct hv_enlightened_vmcs { u64 padding64_5[7]; u64 xss_exit_bitmap; u64 padding64_6[7]; -}; +} __packed; #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0 #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0) @@ -725,36 +725,129 @@ struct hv_enlightened_vmcs { #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF -#define HV_STIMER_ENABLE (1ULL << 0) -#define HV_STIMER_PERIODIC (1ULL << 1) -#define HV_STIMER_LAZY (1ULL << 2) -#define HV_STIMER_AUTOENABLE (1ULL << 3) -#define HV_STIMER_SINT(config) (__u8)(((config) >> 16) & 0x0F) +/* Define synthetic interrupt controller flag constants. */ +#define HV_EVENT_FLAGS_COUNT (256 * 8) +#define HV_EVENT_FLAGS_LONG_COUNT (256 / sizeof(unsigned long)) + +/* + * Synthetic timer configuration. + */ +union hv_stimer_config { + u64 as_uint64; + struct { + u64 enable:1; + u64 periodic:1; + u64 lazy:1; + u64 auto_enable:1; + u64 apic_vector:8; + u64 direct_mode:1; + u64 reserved_z0:3; + u64 sintx:4; + u64 reserved_z1:44; + } __packed; +}; + + +/* Define the synthetic interrupt controller event flags format. */ +union hv_synic_event_flags { + unsigned long flags[HV_EVENT_FLAGS_LONG_COUNT]; +}; + +/* Define SynIC control register. */ +union hv_synic_scontrol { + u64 as_uint64; + struct { + u64 enable:1; + u64 reserved:63; + } __packed; +}; + +/* Define synthetic interrupt source. */ +union hv_synic_sint { + u64 as_uint64; + struct { + u64 vector:8; + u64 reserved1:8; + u64 masked:1; + u64 auto_eoi:1; + u64 reserved2:46; + } __packed; +}; + +/* Define the format of the SIMP register */ +union hv_synic_simp { + u64 as_uint64; + struct { + u64 simp_enabled:1; + u64 preserved:11; + u64 base_simp_gpa:52; + } __packed; +}; + +/* Define the format of the SIEFP register */ +union hv_synic_siefp { + u64 as_uint64; + struct { + u64 siefp_enabled:1; + u64 preserved:11; + u64 base_siefp_gpa:52; + } __packed; +}; struct hv_vpset { u64 format; u64 valid_bank_mask; u64 bank_contents[]; -}; +} __packed; /* HvCallSendSyntheticClusterIpi hypercall */ struct hv_send_ipi { u32 vector; u32 reserved; u64 cpu_mask; -}; +} __packed; /* HvCallSendSyntheticClusterIpiEx hypercall */ struct hv_send_ipi_ex { u32 vector; u32 reserved; struct hv_vpset vp_set; -}; +} __packed; /* HvFlushGuestPhysicalAddressSpace hypercalls */ struct hv_guest_mapping_flush { u64 address_space; u64 flags; +} __packed; + +/* + * HV_MAX_FLUSH_PAGES = "additional_pages" + 1. It's limited + * by the bitwidth of "additional_pages" in union hv_gpa_page_range. + */ +#define HV_MAX_FLUSH_PAGES (2048) + +/* HvFlushGuestPhysicalAddressList hypercall */ +union hv_gpa_page_range { + u64 address_space; + struct { + u64 additional_pages:11; + u64 largepage:1; + u64 basepfn:52; + } page; +}; + +/* + * All input flush parameters should be in single page. The max flush + * count is equal with how many entries of union hv_gpa_page_range can + * be populated into the input parameter page. + */ +#define HV_MAX_FLUSH_REP_COUNT ((PAGE_SIZE - 2 * sizeof(u64)) / \ + sizeof(union hv_gpa_page_range)) + +struct hv_guest_mapping_flush_list { + u64 address_space; + u64 flags; + union hv_gpa_page_range gpa_list[HV_MAX_FLUSH_REP_COUNT]; }; /* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */ @@ -763,7 +856,7 @@ struct hv_tlb_flush { u64 flags; u64 processor_mask; u64 gva_list[]; -}; +} __packed; /* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */ struct hv_tlb_flush_ex { @@ -771,6 +864,6 @@ struct hv_tlb_flush_ex { u64 flags; struct hv_vpset hv_vp_set; u64 gva_list[]; -}; +} __packed; #endif diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 0dd6b0f4000e..9f15384c504a 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -6,7 +6,7 @@ * "Big Core" Processors (Branded as Core, Xeon, etc...) * * The "_X" parts are generally the EP and EX Xeons, or the - * "Extreme" ones, like Broadwell-E. + * "Extreme" ones, like Broadwell-E, or Atom microserver. * * While adding a new CPUID for a new microarchitecture, add a new * group to keep logically sorted out in chronological order. Within @@ -52,6 +52,8 @@ #define INTEL_FAM6_CANNONLAKE_MOBILE 0x66 +#define INTEL_FAM6_ICELAKE_MOBILE 0x7E + /* "Small Core" Processors (Atom) */ #define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */ @@ -71,6 +73,7 @@ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */ #define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */ #define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */ +#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */ /* Xeon Phi */ diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h index b523f51c5400..634f99b1dc22 100644 --- a/arch/x86/include/asm/intel_pt.h +++ b/arch/x86/include/asm/intel_pt.h @@ -2,10 +2,36 @@ #ifndef _ASM_X86_INTEL_PT_H #define _ASM_X86_INTEL_PT_H +#define PT_CPUID_LEAVES 2 +#define PT_CPUID_REGS_NUM 4 /* number of regsters (eax, ebx, ecx, edx) */ + +enum pt_capabilities { + PT_CAP_max_subleaf = 0, + PT_CAP_cr3_filtering, + PT_CAP_psb_cyc, + PT_CAP_ip_filtering, + PT_CAP_mtc, + PT_CAP_ptwrite, + PT_CAP_power_event_trace, + PT_CAP_topa_output, + PT_CAP_topa_multiple_entries, + PT_CAP_single_range_output, + PT_CAP_output_subsys, + PT_CAP_payloads_lip, + PT_CAP_num_address_ranges, + PT_CAP_mtc_periods, + PT_CAP_cycle_thresholds, + PT_CAP_psb_periods, +}; + #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) void cpu_emergency_stop_pt(void); +extern u32 intel_pt_validate_hw_cap(enum pt_capabilities cap); +extern u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities cap); #else static inline void cpu_emergency_stop_pt(void) {} +static inline u32 intel_pt_validate_hw_cap(enum pt_capabilities cap) { return 0; } +static inline u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities capability) { return 0; } #endif #endif /* _ASM_X86_INTEL_PT_H */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 832da8229cc7..686247db3106 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -221,6 +221,14 @@ extern void set_iounmap_nonlazy(void); #ifdef __KERNEL__ +void memcpy_fromio(void *, const volatile void __iomem *, size_t); +void memcpy_toio(volatile void __iomem *, const void *, size_t); +void memset_io(volatile void __iomem *, int, size_t); + +#define memcpy_fromio memcpy_fromio +#define memcpy_toio memcpy_toio +#define memset_io memset_io + #include <asm-generic/iomap.h> /* diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 2395bb794c7b..fbb16e6b6c18 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -30,6 +30,9 @@ extern void fixup_irqs(void); #ifdef CONFIG_HAVE_KVM extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); +extern __visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs); +extern __visible void smp_kvm_posted_intr_wakeup_ipi(struct pt_regs *regs); +extern __visible void smp_kvm_posted_intr_nested_ipi(struct pt_regs *regs); #endif extern void (*x86_platform_ipi_callback)(void); @@ -41,9 +44,13 @@ extern __visible unsigned int do_IRQ(struct pt_regs *regs); extern void init_ISA_irqs(void); +extern void __init init_IRQ(void); + #ifdef CONFIG_X86_LOCAL_APIC void arch_trigger_cpumask_backtrace(const struct cpumask *mask, bool exclude_self); + +extern __visible void smp_x86_platform_ipi(struct pt_regs *regs); #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace #endif diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index 800ffce0db29..80b35e3adf03 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -10,6 +10,7 @@ static inline bool arch_irq_work_has_interrupt(void) return boot_cpu_has(X86_FEATURE_APIC); } extern void arch_irq_work_raise(void); +extern __visible void smp_irq_work_interrupt(struct pt_regs *regs); #else static inline bool arch_irq_work_has_interrupt(void) { diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h index 21efc9d07ed9..65191ce8e1cf 100644 --- a/arch/x86/include/asm/jump_label.h +++ b/arch/x86/include/asm/jump_label.h @@ -2,19 +2,6 @@ #ifndef _ASM_X86_JUMP_LABEL_H #define _ASM_X86_JUMP_LABEL_H -#ifndef HAVE_JUMP_LABEL -/* - * For better or for worse, if jump labels (the gcc extension) are missing, - * then the entire static branch patching infrastructure is compiled out. - * If that happens, the code in here will malfunction. Raise a compiler - * error instead. - * - * In theory, jump labels and the static branch patching infrastructure - * could be decoupled to fix this. - */ -#error asm/jump_label.h included on a non-jump-label kernel -#endif - #define JUMP_LABEL_NOP_SIZE 5 #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 93c4bf598fb0..feab24cac610 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -226,7 +226,9 @@ struct x86_emulate_ops { unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags); - int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase); + int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, + const char *smstate); + void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt); }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index fbda5a917c5b..c79abe7ca093 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -35,6 +35,7 @@ #include <asm/msr-index.h> #include <asm/asm.h> #include <asm/kvm_page_track.h> +#include <asm/kvm_vcpu_regs.h> #include <asm/hyperv-tlfs.h> #define KVM_MAX_VCPUS 288 @@ -125,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) } #define KVM_PERMILLE_MMU_PAGES 20 -#define KVM_MIN_ALLOC_MMU_PAGES 64 +#define KVM_MIN_ALLOC_MMU_PAGES 64UL #define KVM_MMU_HASH_SHIFT 12 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT) #define KVM_MIN_FREE_MMU_PAGES 5 @@ -137,23 +138,23 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level) #define ASYNC_PF_PER_VCPU 64 enum kvm_reg { - VCPU_REGS_RAX = 0, - VCPU_REGS_RCX = 1, - VCPU_REGS_RDX = 2, - VCPU_REGS_RBX = 3, - VCPU_REGS_RSP = 4, - VCPU_REGS_RBP = 5, - VCPU_REGS_RSI = 6, - VCPU_REGS_RDI = 7, + VCPU_REGS_RAX = __VCPU_REGS_RAX, + VCPU_REGS_RCX = __VCPU_REGS_RCX, + VCPU_REGS_RDX = __VCPU_REGS_RDX, + VCPU_REGS_RBX = __VCPU_REGS_RBX, + VCPU_REGS_RSP = __VCPU_REGS_RSP, + VCPU_REGS_RBP = __VCPU_REGS_RBP, + VCPU_REGS_RSI = __VCPU_REGS_RSI, + VCPU_REGS_RDI = __VCPU_REGS_RDI, #ifdef CONFIG_X86_64 - VCPU_REGS_R8 = 8, - VCPU_REGS_R9 = 9, - VCPU_REGS_R10 = 10, - VCPU_REGS_R11 = 11, - VCPU_REGS_R12 = 12, - VCPU_REGS_R13 = 13, - VCPU_REGS_R14 = 14, - VCPU_REGS_R15 = 15, + VCPU_REGS_R8 = __VCPU_REGS_R8, + VCPU_REGS_R9 = __VCPU_REGS_R9, + VCPU_REGS_R10 = __VCPU_REGS_R10, + VCPU_REGS_R11 = __VCPU_REGS_R11, + VCPU_REGS_R12 = __VCPU_REGS_R12, + VCPU_REGS_R13 = __VCPU_REGS_R13, + VCPU_REGS_R14 = __VCPU_REGS_R14, + VCPU_REGS_R15 = __VCPU_REGS_R15, #endif VCPU_REGS_RIP, NR_VCPU_REGS @@ -252,14 +253,14 @@ struct kvm_mmu_memory_cache { * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used * by indirect shadow page can not be more than 15 bits. * - * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access, + * Currently, we used 14 bits that are @level, @gpte_is_8_bytes, @quadrant, @access, * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp. */ union kvm_mmu_page_role { u32 word; struct { unsigned level:4; - unsigned cr4_pae:1; + unsigned gpte_is_8_bytes:1; unsigned quadrant:2; unsigned direct:1; unsigned access:3; @@ -294,11 +295,13 @@ union kvm_mmu_extended_role { unsigned int valid:1; unsigned int execonly:1; unsigned int cr0_pg:1; + unsigned int cr4_pae:1; unsigned int cr4_pse:1; unsigned int cr4_pke:1; unsigned int cr4_smap:1; unsigned int cr4_smep:1; unsigned int cr4_la57:1; + unsigned int maxphyaddr:6; }; }; @@ -318,6 +321,7 @@ struct kvm_mmu_page { struct list_head link; struct hlist_node hash_link; bool unsync; + bool mmio_cached; /* * The following two entries are used to key the shadow page in the @@ -332,10 +336,6 @@ struct kvm_mmu_page { int root_count; /* Currently serving as active root */ unsigned int unsync_children; struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ - - /* The page is obsolete if mmu_valid_gen != kvm->arch.mmu_valid_gen. */ - unsigned long mmu_valid_gen; - DECLARE_BITMAP(unsync_child_bitmap, 512); #ifdef CONFIG_X86_32 @@ -351,6 +351,7 @@ struct kvm_mmu_page { }; struct kvm_pio_request { + unsigned long linear_rip; unsigned long count; int in; int port; @@ -397,6 +398,7 @@ struct kvm_mmu { void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, u64 *spte, const void *pte); hpa_t root_hpa; + gpa_t root_cr3; union kvm_mmu_role mmu_role; u8 root_level; u8 shadow_root_level; @@ -439,6 +441,11 @@ struct kvm_mmu { u64 pdptrs[4]; /* pae */ }; +struct kvm_tlb_range { + u64 start_gfn; + u64 pages; +}; + enum pmc_type { KVM_PMC_GP = 0, KVM_PMC_FIXED, @@ -497,7 +504,7 @@ struct kvm_mtrr { struct kvm_vcpu_hv_stimer { struct hrtimer timer; int index; - u64 config; + union hv_stimer_config config; u64 count; u64 exp_time; struct hv_message msg; @@ -563,6 +570,7 @@ struct kvm_vcpu_arch { bool tpr_access_reporting; u64 ia32_xss; u64 microcode_version; + u64 arch_capabilities; /* * Paging state of the vcpu @@ -601,17 +609,16 @@ struct kvm_vcpu_arch { /* * QEMU userspace and the guest each have their own FPU state. - * In vcpu_run, we switch between the user and guest FPU contexts. - * While running a VCPU, the VCPU thread will have the guest FPU - * context. + * In vcpu_run, we switch between the user, maintained in the + * task_struct struct, and guest FPU contexts. While running a VCPU, + * the VCPU thread will have the guest FPU context. * * Note that while the PKRU state lives inside the fpu registers, * it is switched out separately at VMENTER and VMEXIT time. The * "guest_fpu" state here contains the guest FPU context, with the * host PRKU bits. */ - struct fpu user_fpu; - struct fpu guest_fpu; + struct fpu *guest_fpu; u64 xcr0; u64 guest_supported_xcr0; @@ -838,17 +845,15 @@ enum kvm_irqchip_mode { }; struct kvm_arch { - unsigned int n_used_mmu_pages; - unsigned int n_requested_mmu_pages; - unsigned int n_max_mmu_pages; + unsigned long n_used_mmu_pages; + unsigned long n_requested_mmu_pages; + unsigned long n_max_mmu_pages; unsigned int indirect_shadow_pages; - unsigned long mmu_valid_gen; struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; /* * Hash table of struct kvm_mmu_page. */ struct list_head active_mmu_pages; - struct list_head zapped_obsolete_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; @@ -1042,6 +1047,8 @@ struct kvm_x86_ops { void (*tlb_flush)(struct kvm_vcpu *vcpu, bool invalidate_gpa); int (*tlb_remote_flush)(struct kvm *kvm); + int (*tlb_remote_flush_with_range)(struct kvm *kvm, + struct kvm_tlb_range *range); /* * Flush any TLB entries associated with the given GVA. @@ -1106,6 +1113,7 @@ struct kvm_x86_ops { bool (*mpx_supported)(void); bool (*xsaves_supported)(void); bool (*umip_emulated)(void); + bool (*pt_supported)(void); int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr); void (*request_immediate_exit)(struct kvm_vcpu *vcpu); @@ -1175,7 +1183,7 @@ struct kvm_x86_ops { int (*smi_allowed)(struct kvm_vcpu *vcpu); int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate); - int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase); + int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); int (*enable_smi_window)(struct kvm_vcpu *vcpu); int (*mem_enc_op)(struct kvm *kvm, void __user *argp); @@ -1186,6 +1194,9 @@ struct kvm_x86_ops { int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); + uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu); + + bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu); }; struct kvm_arch_async_pf { @@ -1196,6 +1207,7 @@ struct kvm_arch_async_pf { }; extern struct kvm_x86_ops *kvm_x86_ops; +extern struct kmem_cache *x86_fpu_cache; #define __KVM_HAVE_ARCH_VM_ALLOC static inline struct kvm *kvm_arch_alloc_vm(void) @@ -1244,9 +1256,9 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask); void kvm_mmu_zap_all(struct kvm *kvm); -void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, struct kvm_memslots *slots); -unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm); -void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages); +void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen); +unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm); +void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages); int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3); bool pdptrs_changed(struct kvm_vcpu *vcpu); @@ -1492,7 +1504,7 @@ asmlinkage void kvm_spurious_fault(void); "cmpb $0, kvm_rebooting \n\t" \ "jne 668b \n\t" \ __ASM_SIZE(push) " $666b \n\t" \ - "call kvm_spurious_fault \n\t" \ + "jmp kvm_spurious_fault \n\t" \ ".popsection \n\t" \ _ASM_EXTABLE(666b, 667b) @@ -1503,7 +1515,7 @@ asmlinkage void kvm_spurious_fault(void); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); -void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); +int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu); @@ -1581,4 +1593,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #define put_smstate(type, buf, offset, val) \ *(type *)((buf) + (offset) - 0x7e00) = val +#define GET_SMSTATE(type, buf, offset) \ + (*(type *)((buf) + (offset) - 0x7e00)) + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h index 4c723632c036..5ed3cf1c3934 100644 --- a/arch/x86/include/asm/kvm_para.h +++ b/arch/x86/include/asm/kvm_para.h @@ -92,6 +92,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel); void kvm_async_pf_task_wake(u32 token); u32 kvm_read_and_reset_pf_reason(void); extern void kvm_disable_steal_time(void); +void do_async_page_fault(struct pt_regs *regs, unsigned long error_code); #ifdef CONFIG_PARAVIRT_SPINLOCKS void __init kvm_spinlock_init(void); diff --git a/arch/x86/include/asm/kvm_vcpu_regs.h b/arch/x86/include/asm/kvm_vcpu_regs.h new file mode 100644 index 000000000000..1af2cb59233b --- /dev/null +++ b/arch/x86/include/asm/kvm_vcpu_regs.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KVM_VCPU_REGS_H +#define _ASM_X86_KVM_VCPU_REGS_H + +#define __VCPU_REGS_RAX 0 +#define __VCPU_REGS_RCX 1 +#define __VCPU_REGS_RDX 2 +#define __VCPU_REGS_RBX 3 +#define __VCPU_REGS_RSP 4 +#define __VCPU_REGS_RBP 5 +#define __VCPU_REGS_RSI 6 +#define __VCPU_REGS_RDI 7 + +#ifdef CONFIG_X86_64 +#define __VCPU_REGS_R8 8 +#define __VCPU_REGS_R9 9 +#define __VCPU_REGS_R10 10 +#define __VCPU_REGS_R11 11 +#define __VCPU_REGS_R12 12 +#define __VCPU_REGS_R13 13 +#define __VCPU_REGS_R14 14 +#define __VCPU_REGS_R15 15 +#endif + +#endif /* _ASM_X86_KVM_VCPU_REGS_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index c1a812bd5a27..22d05e3835f0 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -48,6 +48,7 @@ #define MCI_STATUS_SYNDV BIT_ULL(53) /* synd reg. valid */ #define MCI_STATUS_DEFERRED BIT_ULL(44) /* uncorrected error, deferred exception */ #define MCI_STATUS_POISON BIT_ULL(43) /* access poisonous data */ +#define MCI_STATUS_SCRUB BIT_ULL(40) /* Error detected during scrub operation */ /* * McaX field if set indicates a given bank supports MCA extensions: @@ -307,11 +308,17 @@ enum smca_bank_types { SMCA_FP, /* Floating Point */ SMCA_L3_CACHE, /* L3 Cache */ SMCA_CS, /* Coherent Slave */ + SMCA_CS_V2, /* Coherent Slave */ SMCA_PIE, /* Power, Interrupts, etc. */ SMCA_UMC, /* Unified Memory Controller */ SMCA_PB, /* Parameter Block */ SMCA_PSP, /* Platform Security Processor */ + SMCA_PSP_V2, /* Platform Security Processor */ SMCA_SMU, /* System Management Unit */ + SMCA_SMU_V2, /* System Management Unit */ + SMCA_MP5, /* Microprocessor 5 Unit */ + SMCA_NBIO, /* Northbridge IO Unit */ + SMCA_PCIE, /* PCI Express Unit */ N_SMCA_BANK_TYPES }; diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 0ca50611e8ce..19d18fae6ec6 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -178,6 +178,10 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); +/* + * Init a new mm. Used on mm copies, like at fork() + * and on mm's that are brand-new, like at execve(). + */ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { @@ -228,8 +232,22 @@ do { \ } while (0) #endif +static inline void arch_dup_pkeys(struct mm_struct *oldmm, + struct mm_struct *mm) +{ +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + + /* Duplicate the oldmm pkey state in mm: */ + mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; + mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; +#endif +} + static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { + arch_dup_pkeys(oldmm, mm); paravirt_arch_dup_mmap(oldmm, mm); return ldt_dup_context(oldmm, mm); } diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 1d0a7778e163..cc60e617931c 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -22,6 +22,11 @@ struct ms_hyperv_info { extern struct ms_hyperv_info ms_hyperv; + +typedef int (*hyperv_fill_flush_list_func)( + struct hv_guest_mapping_flush_list *flush, + void *data); + /* * Generate the guest ID. */ @@ -348,6 +353,11 @@ void set_hv_tscchange_cb(void (*cb)(void)); void clear_hv_tscchange_cb(void); void hyperv_stop_tsc_emulation(void); int hyperv_flush_guest_mapping(u64 as); +int hyperv_flush_guest_mapping_range(u64 as, + hyperv_fill_flush_list_func fill_func, void *data); +int hyperv_fill_flush_guest_mapping_list( + struct hv_guest_mapping_flush_list *flush, + u64 start_gfn, u64 end_gfn); #ifdef CONFIG_X86_64 void hv_apic_init(void); @@ -370,6 +380,11 @@ static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) return NULL; } static inline int hyperv_flush_guest_mapping(u64 as) { return -1; } +static inline int hyperv_flush_guest_mapping_range(u64 as, + hyperv_fill_flush_list_func fill_func, void *data) +{ + return -1; +} #endif /* CONFIG_HYPERV */ #ifdef CONFIG_HYPERV_TSCPAGE diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 9e39cc8bd989..ca5bc0eacb95 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -121,7 +121,43 @@ #define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 #define MSR_IA32_RTIT_CTL 0x00000570 +#define RTIT_CTL_TRACEEN BIT(0) +#define RTIT_CTL_CYCLEACC BIT(1) +#define RTIT_CTL_OS BIT(2) +#define RTIT_CTL_USR BIT(3) +#define RTIT_CTL_PWR_EVT_EN BIT(4) +#define RTIT_CTL_FUP_ON_PTW BIT(5) +#define RTIT_CTL_FABRIC_EN BIT(6) +#define RTIT_CTL_CR3EN BIT(7) +#define RTIT_CTL_TOPA BIT(8) +#define RTIT_CTL_MTC_EN BIT(9) +#define RTIT_CTL_TSC_EN BIT(10) +#define RTIT_CTL_DISRETC BIT(11) +#define RTIT_CTL_PTW_EN BIT(12) +#define RTIT_CTL_BRANCH_EN BIT(13) +#define RTIT_CTL_MTC_RANGE_OFFSET 14 +#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) +#define RTIT_CTL_CYC_THRESH_OFFSET 19 +#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET) +#define RTIT_CTL_PSB_FREQ_OFFSET 24 +#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET) +#define RTIT_CTL_ADDR0_OFFSET 32 +#define RTIT_CTL_ADDR0 (0x0full << RTIT_CTL_ADDR0_OFFSET) +#define RTIT_CTL_ADDR1_OFFSET 36 +#define RTIT_CTL_ADDR1 (0x0full << RTIT_CTL_ADDR1_OFFSET) +#define RTIT_CTL_ADDR2_OFFSET 40 +#define RTIT_CTL_ADDR2 (0x0full << RTIT_CTL_ADDR2_OFFSET) +#define RTIT_CTL_ADDR3_OFFSET 44 +#define RTIT_CTL_ADDR3 (0x0full << RTIT_CTL_ADDR3_OFFSET) #define MSR_IA32_RTIT_STATUS 0x00000571 +#define RTIT_STATUS_FILTEREN BIT(0) +#define RTIT_STATUS_CONTEXTEN BIT(1) +#define RTIT_STATUS_TRIGGEREN BIT(2) +#define RTIT_STATUS_BUFFOVF BIT(3) +#define RTIT_STATUS_ERROR BIT(4) +#define RTIT_STATUS_STOPPED BIT(5) +#define RTIT_STATUS_BYTECNT_OFFSET 32 +#define RTIT_STATUS_BYTECNT (0x1ffffull << RTIT_STATUS_BYTECNT_OFFSET) #define MSR_IA32_RTIT_ADDR0_A 0x00000580 #define MSR_IA32_RTIT_ADDR0_B 0x00000581 #define MSR_IA32_RTIT_ADDR1_A 0x00000582 @@ -630,6 +666,12 @@ #define MSR_IA32_TSC_DEADLINE 0x000006E0 + +#define MSR_TSX_FORCE_ABORT 0x0000010F + +#define MSR_TFA_RTM_FORCE_ABORT_BIT 0 +#define MSR_TFA_RTM_FORCE_ABORT BIT_ULL(MSR_TFA_RTM_FORCE_ABORT_BIT) + /* P4/Xeon+ specific */ #define MSR_IA32_MCG_EAX 0x00000180 #define MSR_IA32_MCG_EBX 0x00000181 @@ -772,6 +814,7 @@ #define VMX_BASIC_INOUT 0x0040000000000000LLU /* MSR_IA32_VMX_MISC bits */ +#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F /* AMD-V MSRs */ diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 91e4cf189914..5cc3930cb465 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -217,6 +217,8 @@ static __always_inline unsigned long long rdtsc(void) */ static __always_inline unsigned long long rdtsc_ordered(void) { + DECLARE_ARGS(val, low, high); + /* * The RDTSC instruction is not ordered relative to memory * access. The Intel SDM and the AMD APM are both vague on this @@ -227,9 +229,19 @@ static __always_inline unsigned long long rdtsc_ordered(void) * ordering guarantees as reading from a global memory location * that some other imaginary CPU is updating continuously with a * time stamp. + * + * Thus, use the preferred barrier on the respective CPU, aiming for + * RDTSCP as the default. */ - barrier_nospec(); - return rdtsc(); + asm volatile(ALTERNATIVE_3("rdtsc", + "mfence; rdtsc", X86_FEATURE_MFENCE_RDTSC, + "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC, + "rdtscp", X86_FEATURE_RDTSCP) + : EAX_EDX_RET(val, low, high) + /* RDTSCP clobbers ECX with MSR_TSC_AUX. */ + :: "ecx"); + + return EAX_EDX_VAL(val, low, high); } static inline unsigned long long native_read_pmc(int counter) diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 032b6009baab..dad12b767ba0 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -232,6 +232,7 @@ enum spectre_v2_mitigation { enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, + SPECTRE_V2_USER_STRICT_PREFERRED, SPECTRE_V2_USER_PRCTL, SPECTRE_V2_USER_SECCOMP, }; diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 4bf42f9e4eea..c25c38a05c1c 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -26,6 +26,11 @@ struct static_key; extern struct static_key paravirt_steal_enabled; extern struct static_key paravirt_steal_rq_enabled; +__visible void __native_queued_spin_unlock(struct qspinlock *lock); +bool pv_is_native_spin_unlock(void); +__visible bool __native_vcpu_is_preempted(long cpu); +bool pv_is_native_vcpu_is_preempted(void); + static inline u64 paravirt_steal_clock(int cpu) { return PVOP_CALL1(u64, time.steal_clock, cpu); @@ -417,25 +422,26 @@ static inline pgdval_t pgd_val(pgd_t pgd) } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION -static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr, +static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pteval_t ret; - ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, mm, addr, ptep); + ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, vma, addr, ptep); return (pte_t) { .pte = ret }; } -static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr, - pte_t *ptep, pte_t pte) +static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte) { + if (sizeof(pteval_t) > sizeof(long)) /* 5 arg words */ - pv_ops.mmu.ptep_modify_prot_commit(mm, addr, ptep, pte); + pv_ops.mmu.ptep_modify_prot_commit(vma, addr, ptep, pte); else PVOP_VCALL4(mmu.ptep_modify_prot_commit, - mm, addr, ptep, pte.pte); + vma, addr, ptep, pte.pte); } static inline void set_pte(pte_t *ptep, pte_t pte) diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 488c59686a73..2474e434a6f7 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -55,6 +55,7 @@ struct task_struct; struct cpumask; struct flush_tlb_info; struct mmu_gather; +struct vm_area_struct; /* * Wrapper type for pointers to code which uses the non-standard @@ -254,9 +255,9 @@ struct pv_mmu_ops { pte_t *ptep, pte_t pteval); void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval); - pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr, + pte_t (*ptep_modify_prot_start)(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); - void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr, + void (*ptep_modify_prot_commit)(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte); struct paravirt_callee_save pte_val; diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 662963681ea6..e662f987dfa2 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -7,6 +7,7 @@ #include <linux/slab.h> #include <linux/string.h> #include <linux/scatterlist.h> +#include <linux/numa.h> #include <asm/io.h> #include <asm/pat.h> #include <asm/x86_init.h> @@ -141,7 +142,7 @@ cpumask_of_pcibus(const struct pci_bus *bus) int node; node = __pcibus_to_node(bus); - return (node == -1) ? cpu_online_mask : + return (node == NUMA_NO_NODE) ? cpu_online_mask : cpumask_of_node(node); } #endif diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 959d618dbb17..73bb404f4d2a 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -121,7 +121,14 @@ extern void __init dmi_check_pciprobe(void); extern void __init dmi_check_skip_isa_align(void); /* some common used subsys_initcalls */ +#ifdef CONFIG_PCI extern int __init pci_acpi_init(void); +#else +static inline int __init pci_acpi_init(void) +{ + return -EINVAL; +} +#endif extern void __init pcibios_irq_init(void); extern int __init pcibios_init(void); extern int pci_legacy_init(void); diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index ec7f43327033..a281e61ec60c 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -47,8 +47,8 @@ extern gfp_t __userpte_alloc_gfp; extern pgd_t *pgd_alloc(struct mm_struct *); extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); -extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long); -extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long); +extern pte_t *pte_alloc_one_kernel(struct mm_struct *); +extern pgtable_t pte_alloc_one(struct mm_struct *); /* Should really implement gc for free page table pages. This could be done with a reference count in struct page. */ @@ -80,6 +80,13 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); } +static inline void pmd_populate_kernel_safe(struct mm_struct *mm, + pmd_t *pmd, pte_t *pte) +{ + paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); + set_pmd_safe(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); +} + static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte) { @@ -132,6 +139,12 @@ static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); } + +static inline void pud_populate_safe(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +{ + paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); + set_pud_safe(pud, __pud(_PAGE_TABLE | __pa(pmd))); +} #endif /* CONFIG_X86_PAE */ #if CONFIG_PGTABLE_LEVELS > 3 @@ -141,6 +154,12 @@ static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); } +static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) +{ + paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); + set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); +} + static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_KERNEL_ACCOUNT; @@ -173,6 +192,14 @@ static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); } +static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) +{ + if (!pgtable_l5_enabled()) + return; + paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); + set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); +} + static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) { gfp_t gfp = GFP_KERNEL_ACCOUNT; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 40616e805292..50b3e2d963c9 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -46,7 +46,7 @@ void ptdump_walk_user_pgd_level_checkwx(void); */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __visible; -#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page)) +#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page)) extern spinlock_t pgd_lock; extern struct list_head pgd_list; @@ -1065,7 +1065,7 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - native_set_pmd(pmdp, pmd); + set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index b3ec519e3982..4fe9e7fc74d3 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -37,7 +37,7 @@ void sync_initial_page_table(void); /* * Define this if things work differently on an i386 and an i486: * it will (on an i486) warn about kernel memory accesses that are - * done without a 'access_ok(VERIFY_WRITE,..)' + * done without a 'access_ok( ..)' */ #undef TEST_ACCESS_OK diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 9c85b54bf03c..0bb566315621 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -259,8 +259,7 @@ extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted -static inline bool gup_fast_permitted(unsigned long start, int nr_pages, - int write) +static inline bool gup_fast_permitted(unsigned long start, int nr_pages) { unsigned long len, end; diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 106b7d0e2dae..d6ff0bbdb394 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -564,8 +564,12 @@ extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, unsigned int *level); extern pmd_t *lookup_pmd_address(unsigned long address); extern phys_addr_t slow_virt_to_phys(void *__address); -extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, - unsigned numpages, unsigned long page_flags); +extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, + unsigned long address, + unsigned numpages, + unsigned long page_flags); +extern int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, + unsigned long numpages); #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_DEFS_H */ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 90cb2f36c042..99a7fa9ab0a3 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -8,6 +8,9 @@ DECLARE_PER_CPU(int, __preempt_count); +/* We use the MSB mostly because its available */ +#define PREEMPT_NEED_RESCHED 0x80000000 + /* * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such * that a decrement hitting 0 means we can and should reschedule. diff --git a/arch/x86/include/asm/processor-cyrix.h b/arch/x86/include/asm/processor-cyrix.h index aaedd73ea2c6..df700a6cc869 100644 --- a/arch/x86/include/asm/processor-cyrix.h +++ b/arch/x86/include/asm/processor-cyrix.h @@ -3,19 +3,6 @@ * NSC/Cyrix CPU indexed register access. Must be inlined instead of * macros to ensure correct access ordering * Access order is always 0x22 (=offset), 0x23 (=value) - * - * When using the old macros a line like - * setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88); - * gets expanded to: - * do { - * outb((CX86_CCR2), 0x22); - * outb((({ - * outb((CX86_CCR2), 0x22); - * inb(0x23); - * }) | 0x88), 0x23); - * } while (0); - * - * which in fact violates the access order (= 0x22, 0x22, 0x23, 0x23). */ static inline u8 getCx86(u8 reg) @@ -29,11 +16,3 @@ static inline void setCx86(u8 reg, u8 data) outb(reg, 0x22); outb(data, 0x23); } - -#define getCx86_old(reg) ({ outb((reg), 0x22); inb(0x23); }) - -#define setCx86_old(reg, data) do { \ - outb((reg), 0x22); \ - outb((data), 0x23); \ -} while (0) - diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 071b2a6fff85..2bb3a648fc12 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -742,7 +742,6 @@ enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, extern void enable_sep_cpu(void); extern int sysenter_setup(void); -void early_trap_pf_init(void); /* Defined in head.S */ extern struct desc_ptr early_gdt_descr; @@ -967,7 +966,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) } extern unsigned long arch_align_stack(unsigned long sp); -extern void free_init_pages(char *what, unsigned long begin, unsigned long end); +void free_init_pages(const char *what, unsigned long begin, unsigned long end); extern void free_kernel_image_pages(void *begin, void *end); void default_idle(void); diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index 63b3393bd98e..c53682303c9c 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -77,7 +77,11 @@ static inline size_t real_mode_size_needed(void) return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE); } -void set_real_mode_mem(phys_addr_t mem, size_t size); +static inline void set_real_mode_mem(phys_addr_t mem) +{ + real_mode_header = (struct real_mode_header *) __va(mem); +} + void reserve_real_mode(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h index a671a1145906..04c17be9b5fd 100644 --- a/arch/x86/include/asm/reboot.h +++ b/arch/x86/include/asm/reboot.h @@ -26,6 +26,7 @@ void __noreturn machine_real_restart(unsigned int type); #define MRR_APM 1 typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); +void nmi_panic_self_stop(struct pt_regs *regs); void nmi_shootdown_cpus(nmi_shootdown_cb callback); void run_crash_ipi_callback(struct pt_regs *regs); diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h index dbaed55c1c24..232f856e0db0 100644 --- a/arch/x86/include/asm/refcount.h +++ b/arch/x86/include/asm/refcount.h @@ -67,16 +67,30 @@ static __always_inline void refcount_dec(refcount_t *r) static __always_inline __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r) { - return GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", + bool ret = GEN_BINARY_SUFFIXED_RMWcc(LOCK_PREFIX "subl", REFCOUNT_CHECK_LT_ZERO, r->refs.counter, e, "er", i, "cx"); + + if (ret) { + smp_acquire__after_ctrl_dep(); + return true; + } + + return false; } static __always_inline __must_check bool refcount_dec_and_test(refcount_t *r) { - return GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", - REFCOUNT_CHECK_LT_ZERO, - r->refs.counter, e, "cx"); + bool ret = GEN_UNARY_SUFFIXED_RMWcc(LOCK_PREFIX "decl", + REFCOUNT_CHECK_LT_ZERO, + r->refs.counter, e, "cx"); + + if (ret) { + smp_acquire__after_ctrl_dep(); + return true; + } + + return false; } static __always_inline __must_check diff --git a/arch/x86/include/asm/intel_rdt_sched.h b/arch/x86/include/asm/resctrl_sched.h index 9acb06b6f81e..f6b7fe2833cc 100644 --- a/arch/x86/include/asm/intel_rdt_sched.h +++ b/arch/x86/include/asm/resctrl_sched.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_INTEL_RDT_SCHED_H -#define _ASM_X86_INTEL_RDT_SCHED_H +#ifndef _ASM_X86_RESCTRL_SCHED_H +#define _ASM_X86_RESCTRL_SCHED_H -#ifdef CONFIG_INTEL_RDT +#ifdef CONFIG_X86_CPU_RESCTRL #include <linux/sched.h> #include <linux/jump_label.h> @@ -10,7 +10,7 @@ #define IA32_PQR_ASSOC 0x0c8f /** - * struct intel_pqr_state - State cache for the PQR MSR + * struct resctrl_pqr_state - State cache for the PQR MSR * @cur_rmid: The cached Resource Monitoring ID * @cur_closid: The cached Class Of Service ID * @default_rmid: The user assigned Resource Monitoring ID @@ -24,21 +24,21 @@ * The cache also helps to avoid pointless updates if the value does * not change. */ -struct intel_pqr_state { +struct resctrl_pqr_state { u32 cur_rmid; u32 cur_closid; u32 default_rmid; u32 default_closid; }; -DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); +DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state); DECLARE_STATIC_KEY_FALSE(rdt_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); /* - * __intel_rdt_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR + * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR * * Following considerations are made so that this has minimal impact * on scheduler hot path: @@ -51,9 +51,9 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); * simple as possible. * Must be called with preemption disabled. */ -static void __intel_rdt_sched_in(void) +static void __resctrl_sched_in(void) { - struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); u32 closid = state->default_closid; u32 rmid = state->default_rmid; @@ -78,16 +78,16 @@ static void __intel_rdt_sched_in(void) } } -static inline void intel_rdt_sched_in(void) +static inline void resctrl_sched_in(void) { if (static_branch_likely(&rdt_enable_key)) - __intel_rdt_sched_in(); + __resctrl_sched_in(); } #else -static inline void intel_rdt_sched_in(void) {} +static inline void resctrl_sched_in(void) {} -#endif /* CONFIG_INTEL_RDT */ +#endif /* CONFIG_X86_CPU_RESCTRL */ -#endif /* _ASM_X86_INTEL_RDT_SCHED_H */ +#endif /* _ASM_X86_RESCTRL_SCHED_H */ diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h index 46ac84b506f5..8a9eba191516 100644 --- a/arch/x86/include/asm/rmwcc.h +++ b/arch/x86/include/asm/rmwcc.h @@ -11,7 +11,7 @@ #define __CLOBBERS_MEM(clb...) "memory", ## clb -#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO) +#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CONFIG_CC_HAS_ASM_GOTO) /* Use asm goto */ @@ -27,7 +27,7 @@ cc_label: c = true; \ c; \ }) -#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ +#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */ /* Use flags output or a set instruction */ @@ -40,7 +40,7 @@ cc_label: c = true; \ c; \ }) -#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */ +#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CONFIG_CC_HAS_ASM_GOTO) */ #define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \ __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index ae13bc974416..ed8ec011a9fd 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -46,6 +46,9 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); +extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); +extern unsigned long __startup_secondary_64(void); +extern int early_make_pgtable(unsigned long address); #ifdef CONFIG_X86_INTEL_MID extern void x86_intel_mid_early_setup(void); diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index bd26834724e5..2fcbd6f33ef7 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -17,4 +17,9 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where); int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, struct pt_regs *regs, unsigned long mask); + +#ifdef CONFIG_X86_X32_ABI +asmlinkage long sys32_x32_rt_sigreturn(void); +#endif + #endif /* _ASM_X86_SIGHANDLING_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 547c4fe50711..2e95b6c1bca3 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -148,6 +148,12 @@ void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle); void smp_store_boot_cpu_info(void); void smp_store_cpu_info(int id); + +asmlinkage __visible void smp_reboot_interrupt(void); +__visible void smp_reschedule_interrupt(struct pt_regs *regs); +__visible void smp_call_function_interrupt(struct pt_regs *regs); +__visible void smp_call_function_single_interrupt(struct pt_regs *r); + #define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) #define cpu_acpi_id(cpu) per_cpu(x86_cpu_to_acpiid, cpu) diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h index 55d392c6bd29..f74362b05619 100644 --- a/arch/x86/include/asm/string_32.h +++ b/arch/x86/include/asm/string_32.h @@ -179,14 +179,7 @@ static inline void *__memcpy3d(void *to, const void *from, size_t len) * No 3D Now! */ -#if (__GNUC__ >= 4) #define memcpy(t, f, n) __builtin_memcpy(t, f, n) -#else -#define memcpy(t, f, n) \ - (__builtin_constant_p((n)) \ - ? __constant_memcpy((t), (f), (n)) \ - : __memcpy((t), (f), (n))) -#endif #endif #endif /* !CONFIG_FORTIFY_SOURCE */ @@ -216,29 +209,6 @@ static inline void *__memset_generic(void *s, char c, size_t count) /* we might want to write optimized versions of these later */ #define __constant_count_memset(s, c, count) __memset_generic((s), (c), (count)) -/* - * memset(x, 0, y) is a reasonably common thing to do, so we want to fill - * things 32 bits at a time even when we don't know the size of the - * area at compile-time.. - */ -static __always_inline -void *__constant_c_memset(void *s, unsigned long c, size_t count) -{ - int d0, d1; - asm volatile("rep ; stosl\n\t" - "testb $2,%b3\n\t" - "je 1f\n\t" - "stosw\n" - "1:\ttestb $1,%b3\n\t" - "je 2f\n\t" - "stosb\n" - "2:" - : "=&c" (d0), "=&D" (d1) - : "a" (c), "q" (count), "0" (count/4), "1" ((long)s) - : "memory"); - return s; -} - /* Added by Gertjan van Wingerde to make minix and sysv module work */ #define __HAVE_ARCH_STRNLEN extern size_t strnlen(const char *s, size_t count); @@ -247,72 +217,6 @@ extern size_t strnlen(const char *s, size_t count); #define __HAVE_ARCH_STRSTR extern char *strstr(const char *cs, const char *ct); -/* - * This looks horribly ugly, but the compiler can optimize it totally, - * as we by now know that both pattern and count is constant.. - */ -static __always_inline -void *__constant_c_and_count_memset(void *s, unsigned long pattern, - size_t count) -{ - switch (count) { - case 0: - return s; - case 1: - *(unsigned char *)s = pattern & 0xff; - return s; - case 2: - *(unsigned short *)s = pattern & 0xffff; - return s; - case 3: - *(unsigned short *)s = pattern & 0xffff; - *((unsigned char *)s + 2) = pattern & 0xff; - return s; - case 4: - *(unsigned long *)s = pattern; - return s; - } - -#define COMMON(x) \ - asm volatile("rep ; stosl" \ - x \ - : "=&c" (d0), "=&D" (d1) \ - : "a" (eax), "0" (count/4), "1" ((long)s) \ - : "memory") - - { - int d0, d1; -#if __GNUC__ == 4 && __GNUC_MINOR__ == 0 - /* Workaround for broken gcc 4.0 */ - register unsigned long eax asm("%eax") = pattern; -#else - unsigned long eax = pattern; -#endif - - switch (count % 4) { - case 0: - COMMON(""); - return s; - case 1: - COMMON("\n\tstosb"); - return s; - case 2: - COMMON("\n\tstosw"); - return s; - default: - COMMON("\n\tstosw\n\tstosb"); - return s; - } - } - -#undef COMMON -} - -#define __constant_c_x_memset(s, c, count) \ - (__builtin_constant_p(count) \ - ? __constant_c_and_count_memset((s), (c), (count)) \ - : __constant_c_memset((s), (c), (count))) - #define __memset(s, c, count) \ (__builtin_constant_p(count) \ ? __constant_count_memset((s), (c), (count)) \ @@ -321,15 +225,7 @@ void *__constant_c_and_count_memset(void *s, unsigned long pattern, #define __HAVE_ARCH_MEMSET extern void *memset(void *, int, size_t); #ifndef CONFIG_FORTIFY_SOURCE -#if (__GNUC__ >= 4) #define memset(s, c, count) __builtin_memset(s, c, count) -#else -#define memset(s, c, count) \ - (__builtin_constant_p(c) \ - ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \ - (count)) \ - : __memset((s), (c), (count))) -#endif #endif /* !CONFIG_FORTIFY_SOURCE */ #define __HAVE_ARCH_MEMSET16 diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h index 7ad41bfcc16c..75314c3dbe47 100644 --- a/arch/x86/include/asm/string_64.h +++ b/arch/x86/include/asm/string_64.h @@ -7,24 +7,6 @@ /* Written 2002 by Andi Kleen */ -/* Only used for special circumstances. Stolen from i386/string.h */ -static __always_inline void *__inline_memcpy(void *to, const void *from, size_t n) -{ - unsigned long d0, d1, d2; - asm volatile("rep ; movsl\n\t" - "testb $2,%b4\n\t" - "je 1f\n\t" - "movsw\n" - "1:\ttestb $1,%b4\n\t" - "je 2f\n\t" - "movsb\n" - "2:" - : "=&c" (d0), "=&D" (d1), "=&S" (d2) - : "0" (n / 4), "q" (n), "1" ((long)to), "2" ((long)from) - : "memory"); - return to; -} - /* Even with __builtin_ the compiler may decide to use the out of line function. */ @@ -32,21 +14,6 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t extern void *memcpy(void *to, const void *from, size_t len); extern void *__memcpy(void *to, const void *from, size_t len); -#ifndef CONFIG_FORTIFY_SOURCE -#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4 -#define memcpy(dst, src, len) \ -({ \ - size_t __len = (len); \ - void *__ret; \ - if (__builtin_constant_p(len) && __len >= 64) \ - __ret = __memcpy((dst), (src), __len); \ - else \ - __ret = __builtin_memcpy((dst), (src), __len); \ - __ret; \ -}) -#endif -#endif /* !CONFIG_FORTIFY_SOURCE */ - #define __HAVE_ARCH_MEMSET void *memset(void *s, int c, size_t n); void *__memset(void *s, int c, size_t n); diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 93b462e48067..dec9c1e84c78 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -290,11 +290,4 @@ struct __attribute__ ((__packed__)) vmcb { #define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) -#define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda" -#define SVM_VMRUN ".byte 0x0f, 0x01, 0xd8" -#define SVM_VMSAVE ".byte 0x0f, 0x01, 0xdb" -#define SVM_CLGI ".byte 0x0f, 0x01, 0xdd" -#define SVM_STGI ".byte 0x0f, 0x01, 0xdc" -#define SVM_INVLPGA ".byte 0x0f, 0x01, 0xdf" - #endif diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index d653139857af..4c305471ec33 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -91,11 +91,9 @@ static inline void syscall_set_return_value(struct task_struct *task, static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { - BUG_ON(i + n > 6); - memcpy(args, ®s->bx + i, n * sizeof(args[0])); + memcpy(args, ®s->bx, 6 * sizeof(args[0])); } static inline void syscall_set_arguments(struct task_struct *task, @@ -116,124 +114,50 @@ static inline int syscall_get_arch(void) static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread_info.status & TS_COMPAT) - switch (i) { - case 0: - if (!n--) break; - *args++ = regs->bx; - case 1: - if (!n--) break; - *args++ = regs->cx; - case 2: - if (!n--) break; - *args++ = regs->dx; - case 3: - if (!n--) break; - *args++ = regs->si; - case 4: - if (!n--) break; - *args++ = regs->di; - case 5: - if (!n--) break; - *args++ = regs->bp; - case 6: - if (!n--) break; - default: - BUG(); - break; - } - else + if (task->thread_info.status & TS_COMPAT) { + *args++ = regs->bx; + *args++ = regs->cx; + *args++ = regs->dx; + *args++ = regs->si; + *args++ = regs->di; + *args = regs->bp; + } else # endif - switch (i) { - case 0: - if (!n--) break; - *args++ = regs->di; - case 1: - if (!n--) break; - *args++ = regs->si; - case 2: - if (!n--) break; - *args++ = regs->dx; - case 3: - if (!n--) break; - *args++ = regs->r10; - case 4: - if (!n--) break; - *args++ = regs->r8; - case 5: - if (!n--) break; - *args++ = regs->r9; - case 6: - if (!n--) break; - default: - BUG(); - break; - } + { + *args++ = regs->di; + *args++ = regs->si; + *args++ = regs->dx; + *args++ = regs->r10; + *args++ = regs->r8; + *args = regs->r9; + } } static inline void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs, - unsigned int i, unsigned int n, const unsigned long *args) { # ifdef CONFIG_IA32_EMULATION - if (task->thread_info.status & TS_COMPAT) - switch (i) { - case 0: - if (!n--) break; - regs->bx = *args++; - case 1: - if (!n--) break; - regs->cx = *args++; - case 2: - if (!n--) break; - regs->dx = *args++; - case 3: - if (!n--) break; - regs->si = *args++; - case 4: - if (!n--) break; - regs->di = *args++; - case 5: - if (!n--) break; - regs->bp = *args++; - case 6: - if (!n--) break; - default: - BUG(); - break; - } - else + if (task->thread_info.status & TS_COMPAT) { + regs->bx = *args++; + regs->cx = *args++; + regs->dx = *args++; + regs->si = *args++; + regs->di = *args++; + regs->bp = *args; + } else # endif - switch (i) { - case 0: - if (!n--) break; - regs->di = *args++; - case 1: - if (!n--) break; - regs->si = *args++; - case 2: - if (!n--) break; - regs->dx = *args++; - case 3: - if (!n--) break; - regs->r10 = *args++; - case 4: - if (!n--) break; - regs->r8 = *args++; - case 5: - if (!n--) break; - regs->r9 = *args++; - case 6: - if (!n--) break; - default: - BUG(); - break; - } + { + regs->di = *args++; + regs->si = *args++; + regs->dx = *args++; + regs->r10 = *args++; + regs->r8 = *args++; + regs->r9 = *args; + } } static inline int syscall_get_arch(void) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 82b73b75d67c..e0eccbcb8447 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -140,14 +140,6 @@ struct thread_info { _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \ _TIF_NOHZ) -/* work to do on any return to user space */ -#define _TIF_ALLWORK_MASK \ - (_TIF_SYSCALL_TRACE | _TIF_NOTIFY_RESUME | _TIF_SIGPENDING | \ - _TIF_NEED_RESCHED | _TIF_SINGLESTEP | _TIF_SYSCALL_EMU | \ - _TIF_SYSCALL_AUDIT | _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE | \ - _TIF_PATCH_PENDING | _TIF_NOHZ | _TIF_SYSCALL_TRACEPOINT | \ - _TIF_FSCHECK) - /* flags to check in __switch_to() */ #define _TIF_WORK_CTXSW_BASE \ (_TIF_IO_BITMAP|_TIF_NOCPUID|_TIF_NOTSC|_TIF_BLOCKSTEP| \ diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h index 69615e387973..e0e6d7f21399 100644 --- a/arch/x86/include/asm/trace/exceptions.h +++ b/arch/x86/include/asm/trace/exceptions.h @@ -45,6 +45,7 @@ DEFINE_PAGE_FAULT_EVENT(page_fault_user); DEFINE_PAGE_FAULT_EVENT(page_fault_kernel); #undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE exceptions #endif /* _TRACE_PAGE_FAULT_H */ diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h index 2e6245a023ef..ace464f09681 100644 --- a/arch/x86/include/asm/trace/hyperv.h +++ b/arch/x86/include/asm/trace/hyperv.h @@ -42,6 +42,20 @@ TRACE_EVENT(hyperv_nested_flush_guest_mapping, TP_printk("address space %llx ret %d", __entry->as, __entry->ret) ); +TRACE_EVENT(hyperv_nested_flush_guest_mapping_range, + TP_PROTO(u64 as, int ret), + TP_ARGS(as, ret), + + TP_STRUCT__entry( + __field(u64, as) + __field(int, ret) + ), + TP_fast_assign(__entry->as = as; + __entry->ret = ret; + ), + TP_printk("address space %llx ret %d", __entry->as, __entry->ret) + ); + TRACE_EVENT(hyperv_send_ipi_mask, TP_PROTO(const struct cpumask *cpus, int vector), diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h index 0af81b590a0c..33b9d0f0aafe 100644 --- a/arch/x86/include/asm/trace/irq_vectors.h +++ b/arch/x86/include/asm/trace/irq_vectors.h @@ -389,6 +389,7 @@ TRACE_EVENT(vector_free_moved, #endif /* CONFIG_X86_LOCAL_APIC */ #undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE irq_vectors #endif /* _TRACE_IRQ_VECTORS_H */ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 3de69330e6c5..7d6f3f3fad78 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -61,34 +61,38 @@ asmlinkage void xen_machine_check(void); asmlinkage void xen_simd_coprocessor_error(void); #endif -dotraplinkage void do_divide_error(struct pt_regs *, long); -dotraplinkage void do_debug(struct pt_regs *, long); -dotraplinkage void do_nmi(struct pt_regs *, long); -dotraplinkage void do_int3(struct pt_regs *, long); -dotraplinkage void do_overflow(struct pt_regs *, long); -dotraplinkage void do_bounds(struct pt_regs *, long); -dotraplinkage void do_invalid_op(struct pt_regs *, long); -dotraplinkage void do_device_not_available(struct pt_regs *, long); -dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long); -dotraplinkage void do_invalid_TSS(struct pt_regs *, long); -dotraplinkage void do_segment_not_present(struct pt_regs *, long); -dotraplinkage void do_stack_segment(struct pt_regs *, long); +dotraplinkage void do_divide_error(struct pt_regs *regs, long error_code); +dotraplinkage void do_debug(struct pt_regs *regs, long error_code); +dotraplinkage void do_nmi(struct pt_regs *regs, long error_code); +dotraplinkage void do_int3(struct pt_regs *regs, long error_code); +dotraplinkage void do_overflow(struct pt_regs *regs, long error_code); +dotraplinkage void do_bounds(struct pt_regs *regs, long error_code); +dotraplinkage void do_invalid_op(struct pt_regs *regs, long error_code); +dotraplinkage void do_device_not_available(struct pt_regs *regs, long error_code); +dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *regs, long error_code); +dotraplinkage void do_invalid_TSS(struct pt_regs *regs, long error_code); +dotraplinkage void do_segment_not_present(struct pt_regs *regs, long error_code); +dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code); #ifdef CONFIG_X86_64 -dotraplinkage void do_double_fault(struct pt_regs *, long); +dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code); +asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); +asmlinkage __visible notrace +struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s); +void __init trap_init(void); #endif -dotraplinkage void do_general_protection(struct pt_regs *, long); -dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); -dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long); -dotraplinkage void do_coprocessor_error(struct pt_regs *, long); -dotraplinkage void do_alignment_check(struct pt_regs *, long); +dotraplinkage void do_general_protection(struct pt_regs *regs, long error_code); +dotraplinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code); +dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *regs, long error_code); +dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code); +dotraplinkage void do_alignment_check(struct pt_regs *regs, long error_code); #ifdef CONFIG_X86_MCE -dotraplinkage void do_machine_check(struct pt_regs *, long); +dotraplinkage void do_machine_check(struct pt_regs *regs, long error_code); #endif -dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long); +dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code); #ifdef CONFIG_X86_32 -dotraplinkage void do_iret_error(struct pt_regs *, long); +dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code); #endif -dotraplinkage void do_mce(struct pt_regs *, long); +dotraplinkage void do_mce(struct pt_regs *regs, long error_code); static inline int get_si_code(unsigned long condition) { @@ -104,11 +108,16 @@ extern int panic_on_unrecovered_nmi; void math_emulate(struct math_emu_info *); #ifndef CONFIG_X86_32 -asmlinkage void smp_thermal_interrupt(void); -asmlinkage void smp_threshold_interrupt(void); -asmlinkage void smp_deferred_error_interrupt(void); +asmlinkage void smp_thermal_interrupt(struct pt_regs *regs); +asmlinkage void smp_threshold_interrupt(struct pt_regs *regs); +asmlinkage void smp_deferred_error_interrupt(struct pt_regs *regs); #endif +void smp_apic_timer_interrupt(struct pt_regs *regs); +void smp_spurious_interrupt(struct pt_regs *regs); +void smp_error_interrupt(struct pt_regs *regs); +asmlinkage void smp_irq_move_cleanup_interrupt(void); + extern void ist_enter(struct pt_regs *regs); extern void ist_exit(struct pt_regs *regs); extern void ist_begin_non_atomic(struct pt_regs *regs); diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index eb5bbfeccb66..8a0c25c6bf09 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -35,6 +35,7 @@ extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns); extern void tsc_early_init(void); extern void tsc_init(void); +extern unsigned long calibrate_delay_is_known(void); extern void mark_tsc_unstable(char *reason); extern int unsynchronized_tsc(void); extern int check_tsc_unstable(void); diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index b5e58cc0c5e7..1954dd5552a2 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -25,7 +25,6 @@ #define KERNEL_DS MAKE_MM_SEG(-1UL) #define USER_DS MAKE_MM_SEG(TASK_SIZE_MAX) -#define get_ds() (KERNEL_DS) #define get_fs() (current->thread.addr_limit) static inline void set_fs(mm_segment_t fs) { @@ -35,10 +34,7 @@ static inline void set_fs(mm_segment_t fs) } #define segment_eq(a, b) ((a).seg == (b).seg) - #define user_addr_max() (current->thread.addr_limit.seg) -#define __addr_ok(addr) \ - ((unsigned long __force)(addr) < user_addr_max()) /* * Test whether a block of memory is a valid user space address. @@ -76,10 +72,7 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un #endif /** - * access_ok: - Checks if a user space pointer is valid - * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE. Note that - * %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe - * to write to a block, it is always safe to read from it. + * access_ok - Checks if a user space pointer is valid * @addr: User space pointer to start of block to check * @size: Size of block to check * @@ -88,14 +81,14 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un * * Checks if a pointer to a block of memory in user space is valid. * - * Returns true (nonzero) if the memory block may be valid, false (zero) - * if it is definitely invalid. - * * Note that, depending on architecture, this function probably just * checks that the pointer is in the user space range - after calling * this function, memory access functions may still return -EFAULT. + * + * Return: true (nonzero) if the memory block may be valid, false (zero) + * if it is definitely invalid. */ -#define access_ok(type, addr, size) \ +#define access_ok(addr, size) \ ({ \ WARN_ON_IN_IRQ(); \ likely(!__range_not_ok(addr, size, user_addr_max())); \ @@ -138,7 +131,7 @@ extern int __get_user_bad(void); __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) /** - * get_user: - Get a simple variable from user space. + * get_user - Get a simple variable from user space. * @x: Variable to store result. * @ptr: Source address, in user space. * @@ -152,7 +145,7 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * - * Returns zero on success, or -EFAULT on error. + * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ /* @@ -189,19 +182,14 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) #ifdef CONFIG_X86_32 -#define __put_user_asm_u64(x, addr, err, errret) \ - asm volatile("\n" \ - "1: movl %%eax,0(%2)\n" \ - "2: movl %%edx,4(%2)\n" \ - "3:" \ - ".section .fixup,\"ax\"\n" \ - "4: movl %3,%0\n" \ - " jmp 3b\n" \ - ".previous\n" \ - _ASM_EXTABLE_UA(1b, 4b) \ - _ASM_EXTABLE_UA(2b, 4b) \ - : "=r" (err) \ - : "A" (x), "r" (addr), "i" (errret), "0" (err)) +#define __put_user_goto_u64(x, addr, label) \ + asm_volatile_goto("\n" \ + "1: movl %%eax,0(%1)\n" \ + "2: movl %%edx,4(%1)\n" \ + _ASM_EXTABLE_UA(1b, %l2) \ + _ASM_EXTABLE_UA(2b, %l2) \ + : : "A" (x), "r" (addr) \ + : : label) #define __put_user_asm_ex_u64(x, addr) \ asm volatile("\n" \ @@ -216,8 +204,8 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) asm volatile("call __put_user_8" : "=a" (__ret_pu) \ : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") #else -#define __put_user_asm_u64(x, ptr, retval, errret) \ - __put_user_asm(x, ptr, retval, "q", "", "er", errret) +#define __put_user_goto_u64(x, ptr, label) \ + __put_user_goto(x, ptr, "q", "", "er", label) #define __put_user_asm_ex_u64(x, addr) \ __put_user_asm_ex(x, addr, "q", "", "er") #define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu) @@ -235,7 +223,7 @@ extern void __put_user_4(void); extern void __put_user_8(void); /** - * put_user: - Write a simple value into user space. + * put_user - Write a simple value into user space. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * @@ -249,7 +237,7 @@ extern void __put_user_8(void); * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * - * Returns zero on success, or -EFAULT on error. + * Return: zero on success, or -EFAULT on error. */ #define put_user(x, ptr) \ ({ \ @@ -278,23 +266,21 @@ extern void __put_user_8(void); __builtin_expect(__ret_pu, 0); \ }) -#define __put_user_size(x, ptr, size, retval, errret) \ +#define __put_user_size(x, ptr, size, label) \ do { \ - retval = 0; \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ - __put_user_asm(x, ptr, retval, "b", "b", "iq", errret); \ + __put_user_goto(x, ptr, "b", "b", "iq", label); \ break; \ case 2: \ - __put_user_asm(x, ptr, retval, "w", "w", "ir", errret); \ + __put_user_goto(x, ptr, "w", "w", "ir", label); \ break; \ case 4: \ - __put_user_asm(x, ptr, retval, "l", "k", "ir", errret); \ + __put_user_goto(x, ptr, "l", "k", "ir", label); \ break; \ case 8: \ - __put_user_asm_u64((__typeof__(*ptr))(x), ptr, retval, \ - errret); \ + __put_user_goto_u64(x, ptr, label); \ break; \ default: \ __put_user_bad(); \ @@ -439,9 +425,14 @@ do { \ #define __put_user_nocheck(x, ptr, size) \ ({ \ - int __pu_err; \ + __label__ __pu_label; \ + int __pu_err = -EFAULT; \ + __typeof__(*(ptr)) __pu_val; \ + __pu_val = x; \ __uaccess_begin(); \ - __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \ + __put_user_size(__pu_val, (ptr), (size), __pu_label); \ + __pu_err = 0; \ +__pu_label: \ __uaccess_end(); \ __builtin_expect(__pu_err, 0); \ }) @@ -466,17 +457,23 @@ struct __large_struct { unsigned long buf[100]; }; * we do not write to any memory gcc knows about, so there are no * aliasing issues. */ -#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret) \ - asm volatile("\n" \ - "1: mov"itype" %"rtype"1,%2\n" \ - "2:\n" \ - ".section .fixup,\"ax\"\n" \ - "3: mov %3,%0\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE_UA(1b, 3b) \ - : "=r"(err) \ - : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err)) +#define __put_user_goto(x, addr, itype, rtype, ltype, label) \ + asm_volatile_goto("\n" \ + "1: mov"itype" %"rtype"0,%1\n" \ + _ASM_EXTABLE_UA(1b, %l2) \ + : : ltype(x), "m" (__m(addr)) \ + : : label) + +#define __put_user_failed(x, addr, itype, rtype, ltype, errret) \ + ({ __label__ __puflab; \ + int __pufret = errret; \ + __put_user_goto(x,addr,itype,rtype,ltype,__puflab); \ + __pufret = 0; \ + __puflab: __pufret; }) + +#define __put_user_asm(x, addr, retval, itype, rtype, ltype, errret) do { \ + retval = __put_user_failed(x, addr, itype, rtype, ltype, errret); \ +} while (0) #define __put_user_asm_ex(x, addr, itype, rtype, ltype) \ asm volatile("1: mov"itype" %"rtype"0,%1\n" \ @@ -502,7 +499,7 @@ struct __large_struct { unsigned long buf[100]; }; } while (0) /** - * __get_user: - Get a simple variable from user space, with less checking. + * __get_user - Get a simple variable from user space, with less checking. * @x: Variable to store result. * @ptr: Source address, in user space. * @@ -519,7 +516,7 @@ struct __large_struct { unsigned long buf[100]; }; * Caller must check the pointer with access_ok() before calling this * function. * - * Returns zero on success, or -EFAULT on error. + * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ @@ -527,7 +524,7 @@ struct __large_struct { unsigned long buf[100]; }; __get_user_nocheck((x), (ptr), sizeof(*(ptr))) /** - * __put_user: - Write a simple value into user space, with less checking. + * __put_user - Write a simple value into user space, with less checking. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * @@ -544,7 +541,7 @@ struct __large_struct { unsigned long buf[100]; }; * Caller must check the pointer with access_ok() before calling this * function. * - * Returns zero on success, or -EFAULT on error. + * Return: zero on success, or -EFAULT on error. */ #define __put_user(x, ptr) \ @@ -670,7 +667,7 @@ extern void __cmpxchg_wrong_size(void) #define user_atomic_cmpxchg_inatomic(uval, ptr, old, new) \ ({ \ - access_ok(VERIFY_WRITE, (ptr), sizeof(*(ptr))) ? \ + access_ok((ptr), sizeof(*(ptr))) ? \ __user_atomic_cmpxchg_inatomic((uval), (ptr), \ (old), (new), sizeof(*(ptr))) : \ -EFAULT; \ @@ -708,16 +705,18 @@ extern struct movsl_mask { * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ -#define user_access_begin() __uaccess_begin() +static __must_check inline bool user_access_begin(const void __user *ptr, size_t len) +{ + if (unlikely(!access_ok(ptr,len))) + return 0; + __uaccess_begin_nospec(); + return 1; +} +#define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() -#define unsafe_put_user(x, ptr, err_label) \ -do { \ - int __pu_err; \ - __typeof__(*(ptr)) __pu_val = (x); \ - __put_user_size(__pu_val, (ptr), sizeof(*(ptr)), __pu_err, -EFAULT); \ - if (unlikely(__pu_err)) goto err_label; \ -} while (0) +#define unsafe_put_user(x, ptr, label) \ + __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) #define unsafe_get_user(x, ptr, err_label) \ do { \ diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index dc4ed8bc2382..146859efd83c 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -23,8 +23,8 @@ # include <asm/unistd_64.h> # include <asm/unistd_64_x32.h> -# define __ARCH_WANT_COMPAT_SYS_TIME -# define __ARCH_WANT_SYS_UTIME32 +# define __ARCH_WANT_SYS_TIME +# define __ARCH_WANT_SYS_UTIME # define __ARCH_WANT_COMPAT_SYS_PREADV64 # define __ARCH_WANT_COMPAT_SYS_PWRITEV64 # define __ARCH_WANT_COMPAT_SYS_PREADV64V2 @@ -48,8 +48,8 @@ # define __ARCH_WANT_SYS_SIGPENDING # define __ARCH_WANT_SYS_SIGPROCMASK # define __ARCH_WANT_SYS_SOCKETCALL -# define __ARCH_WANT_SYS_TIME -# define __ARCH_WANT_SYS_UTIME +# define __ARCH_WANT_SYS_TIME32 +# define __ARCH_WANT_SYS_UTIME32 # define __ARCH_WANT_SYS_WAITPID # define __ARCH_WANT_SYS_FORK # define __ARCH_WANT_SYS_VFORK diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h index 1f86e1b0a5cd..499578f7e6d7 100644 --- a/arch/x86/include/asm/unwind.h +++ b/arch/x86/include/asm/unwind.h @@ -23,6 +23,12 @@ struct unwind_state { #elif defined(CONFIG_UNWINDER_FRAME_POINTER) bool got_irq; unsigned long *bp, *orig_sp, ip; + /* + * If non-NULL: The current frame is incomplete and doesn't contain a + * valid BP. When looking for the next frame, use this instead of the + * non-existent saved BP. + */ + unsigned long *next_bp; struct pt_regs *regs; #else unsigned long *sp; diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h index e652a7cc6186..8cfccc3cbbf4 100644 --- a/arch/x86/include/asm/uv/bios.h +++ b/arch/x86/include/asm/uv/bios.h @@ -48,7 +48,8 @@ enum { BIOS_STATUS_SUCCESS = 0, BIOS_STATUS_UNIMPLEMENTED = -ENOSYS, BIOS_STATUS_EINVAL = -EINVAL, - BIOS_STATUS_UNAVAIL = -EBUSY + BIOS_STATUS_UNAVAIL = -EBUSY, + BIOS_STATUS_ABORT = -EINTR, }; /* Address map parameters */ @@ -140,7 +141,6 @@ enum uv_memprotect { */ extern s64 uv_bios_call(enum uv_bios_cmd, u64, u64, u64, u64, u64); extern s64 uv_bios_call_irqsave(enum uv_bios_cmd, u64, u64, u64, u64, u64); -extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64); extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *, long *); extern s64 uv_bios_freq_base(u64, u64 *); @@ -151,11 +151,7 @@ extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect); extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *); extern int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus); -#ifdef CONFIG_EFI extern void uv_bios_init(void); -#else -void uv_bios_init(void) { } -#endif extern unsigned long sn_rtc_cycles_per_second; extern int uv_type; @@ -167,4 +163,9 @@ extern long system_serial_number; extern struct kobject *sgi_uv_kobj; /* /sys/firmware/sgi_uv */ +/* + * EFI runtime lock; cf. firmware/efi/runtime-wrappers.c for details + */ +extern struct semaphore __efi_uv_runtime_lock; + #endif /* _ASM_X86_UV_BIOS_H */ diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index ade0f153947d..4e4133e86484 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -77,7 +77,10 @@ #define SECONDARY_EXEC_ENCLS_EXITING 0x00008000 #define SECONDARY_EXEC_RDSEED_EXITING 0x00010000 #define SECONDARY_EXEC_ENABLE_PML 0x00020000 +#define SECONDARY_EXEC_PT_CONCEAL_VMX 0x00080000 #define SECONDARY_EXEC_XSAVES 0x00100000 +#define SECONDARY_EXEC_PT_USE_GPA 0x01000000 +#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC 0x00400000 #define SECONDARY_EXEC_TSC_SCALING 0x02000000 #define PIN_BASED_EXT_INTR_MASK 0x00000001 @@ -98,6 +101,8 @@ #define VM_EXIT_LOAD_IA32_EFER 0x00200000 #define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER 0x00400000 #define VM_EXIT_CLEAR_BNDCFGS 0x00800000 +#define VM_EXIT_PT_CONCEAL_PIP 0x01000000 +#define VM_EXIT_CLEAR_IA32_RTIT_CTL 0x02000000 #define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff @@ -109,6 +114,8 @@ #define VM_ENTRY_LOAD_IA32_PAT 0x00004000 #define VM_ENTRY_LOAD_IA32_EFER 0x00008000 #define VM_ENTRY_LOAD_BNDCFGS 0x00010000 +#define VM_ENTRY_PT_CONCEAL_PIP 0x00020000 +#define VM_ENTRY_LOAD_IA32_RTIT_CTL 0x00040000 #define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff @@ -240,6 +247,8 @@ enum vmcs_field { GUEST_PDPTR3_HIGH = 0x00002811, GUEST_BNDCFGS = 0x00002812, GUEST_BNDCFGS_HIGH = 0x00002813, + GUEST_IA32_RTIT_CTL = 0x00002814, + GUEST_IA32_RTIT_CTL_HIGH = 0x00002815, HOST_IA32_PAT = 0x00002c00, HOST_IA32_PAT_HIGH = 0x00002c01, HOST_IA32_EFER = 0x00002c02, diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index ef05bea7010d..2863c2026655 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -206,6 +206,9 @@ xen_single_call(unsigned int call, __HYPERCALL_DECLS; __HYPERCALL_5ARG(a1, a2, a3, a4, a5); + if (call >= PAGE_SIZE / sizeof(hypercall_page[0])) + return -EINVAL; + asm volatile(CALL_NOSPEC : __HYPERCALL_5PARAM : [thunk_target] "a" (&hypercall_page[call]) @@ -332,15 +335,11 @@ HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val, return _hypercall4(int, update_va_mapping, va, new_val.pte, new_val.pte >> 32, flags); } -extern int __must_check xen_event_channel_op_compat(int, void *); static inline int HYPERVISOR_event_channel_op(int cmd, void *arg) { - int rc = _hypercall2(int, event_channel_op, cmd, arg); - if (unlikely(rc == -ENOSYS)) - rc = xen_event_channel_op_compat(cmd, arg); - return rc; + return _hypercall2(int, event_channel_op, cmd, arg); } static inline int @@ -355,15 +354,10 @@ HYPERVISOR_console_io(int cmd, int count, char *str) return _hypercall3(int, console_io, cmd, count, str); } -extern int __must_check xen_physdev_op_compat(int, void *); - static inline int HYPERVISOR_physdev_op(int cmd, void *arg) { - int rc = _hypercall2(int, physdev_op, cmd, arg); - if (unlikely(rc == -ENOSYS)) - rc = xen_physdev_op_compat(cmd, arg); - return rc; + return _hypercall2(int, physdev_op, cmd, arg); } static inline int diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild index 322681622d1e..59b5ad310f78 100644 --- a/arch/x86/include/uapi/asm/Kbuild +++ b/arch/x86/include/uapi/asm/Kbuild @@ -1,8 +1,3 @@ -# UAPI Header export list -include include/uapi/asm-generic/Kbuild.asm - -generic-y += bpf_perf_event.h generated-y += unistd_32.h generated-y += unistd_64.h generated-y += unistd_x32.h -generic-y += poll.h diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index dabfcf7c3941..7a0e64ccd6ff 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -381,6 +381,7 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 diff --git a/arch/x86/include/uapi/asm/socket.h b/arch/x86/include/uapi/asm/socket.h deleted file mode 100644 index 6b71384b9d8b..000000000000 --- a/arch/x86/include/uapi/asm/socket.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/socket.h> diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h index f0b0c90dd398..d213ec5c3766 100644 --- a/arch/x86/include/uapi/asm/vmx.h +++ b/arch/x86/include/uapi/asm/vmx.h @@ -146,6 +146,7 @@ #define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2 +#define VMX_ABORT_VMCS_CORRUPTED 3 #define VMX_ABORT_LOAD_HOST_MSR_FAIL 4 #endif /* _UAPIVMX_H */ |