diff options
Diffstat (limited to 'arch/x86')
39 files changed, 328 insertions, 147 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 6a0cc524882d..883da0abf779 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -67,7 +67,7 @@ config X86 select ARCH_HAS_FILTER_PGPROT select ARCH_HAS_FORTIFY_SOURCE select ARCH_HAS_GCOV_PROFILE_ALL - select ARCH_HAS_KCOV if X86_64 + select ARCH_HAS_KCOV if X86_64 && STACK_VALIDATION select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index e821a7d7d5c4..97d37f0a34f5 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -213,7 +213,6 @@ SYM_FUNC_START(startup_32) * We place all of the values on our mini stack so lret can * used to perform that far jump. */ - pushl $__KERNEL_CS leal startup_64(%ebp), %eax #ifdef CONFIG_EFI_MIXED movl efi32_boot_args(%ebp), %edi @@ -224,11 +223,20 @@ SYM_FUNC_START(startup_32) movl efi32_boot_args+8(%ebp), %edx // saved bootparams pointer cmpl $0, %edx jnz 1f + /* + * efi_pe_entry uses MS calling convention, which requires 32 bytes of + * shadow space on the stack even if all arguments are passed in + * registers. We also need an additional 8 bytes for the space that + * would be occupied by the return address, and this also results in + * the correct stack alignment for entry. + */ + subl $40, %esp leal efi_pe_entry(%ebp), %eax movl %edi, %ecx // MS calling convention movl %esi, %edx 1: #endif + pushl $__KERNEL_CS pushl %eax /* Enter paged protected Mode, activating Long Mode */ @@ -784,6 +792,7 @@ SYM_DATA_LOCAL(boot_heap, .fill BOOT_HEAP_SIZE, 1, 0) SYM_DATA_START_LOCAL(boot_stack) .fill BOOT_STACK_SIZE, 1, 0 + .balign 16 SYM_DATA_END_LABEL(boot_stack, SYM_L_LOCAL, boot_stack_end) /* diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index bd3f14175193..e83b3f14897c 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -45,6 +45,32 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> +/* Check that the stack and regs on entry from user mode are sane. */ +static void check_user_regs(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) { + /* + * Make sure that the entry code gave us a sensible EFLAGS + * register. Native because we want to check the actual CPU + * state, not the interrupt state as imagined by Xen. + */ + unsigned long flags = native_save_fl(); + WARN_ON_ONCE(flags & (X86_EFLAGS_AC | X86_EFLAGS_DF | + X86_EFLAGS_NT)); + + /* We think we came from user mode. Make sure pt_regs agrees. */ + WARN_ON_ONCE(!user_mode(regs)); + + /* + * All entries from user mode (except #DF) should be on the + * normal thread stack and should have user pt_regs in the + * correct location. + */ + WARN_ON_ONCE(!on_thread_stack()); + WARN_ON_ONCE(regs != task_pt_regs(current)); + } +} + #ifdef CONFIG_CONTEXT_TRACKING /** * enter_from_user_mode - Establish state when coming from user mode @@ -127,9 +153,6 @@ static long syscall_trace_enter(struct pt_regs *regs) unsigned long ret = 0; u32 work; - if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) - BUG_ON(regs != task_pt_regs(current)); - work = READ_ONCE(ti->flags); if (work & (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU)) { @@ -346,6 +369,8 @@ __visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs) { struct thread_info *ti; + check_user_regs(regs); + enter_from_user_mode(); instrumentation_begin(); @@ -409,6 +434,8 @@ static void do_syscall_32_irqs_on(struct pt_regs *regs) /* Handles int $0x80 */ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { + check_user_regs(regs); + enter_from_user_mode(); instrumentation_begin(); @@ -460,6 +487,8 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs) vdso_image_32.sym_int80_landing_pad; bool success; + check_user_regs(regs); + /* * SYSENTER loses EIP, and even SYSCALL32 needs us to skip forward * so that 'regs->ip -= 2' lands back on an int $0x80 instruction. @@ -510,6 +539,18 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs) (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0; #endif } + +/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ +__visible noinstr long do_SYSENTER_32(struct pt_regs *regs) +{ + /* SYSENTER loses RSP, but the vDSO saved it in RBP. */ + regs->sp = regs->bp; + + /* SYSENTER clobbers EFLAGS.IF. Assume it was set in usermode. */ + regs->flags |= X86_EFLAGS_IF; + + return do_fast_syscall_32(regs); +} #endif SYSCALL_DEFINE0(ni_syscall) @@ -553,6 +594,7 @@ SYSCALL_DEFINE0(ni_syscall) bool noinstr idtentry_enter_cond_rcu(struct pt_regs *regs) { if (user_mode(regs)) { + check_user_regs(regs); enter_from_user_mode(); return false; } @@ -686,6 +728,7 @@ void noinstr idtentry_exit_cond_rcu(struct pt_regs *regs, bool rcu_exit) */ void noinstr idtentry_enter_user(struct pt_regs *regs) { + check_user_regs(regs); enter_from_user_mode(); } diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 024d7d276cd4..2d0bd5d5f032 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -933,9 +933,8 @@ SYM_FUNC_START(entry_SYSENTER_32) .Lsysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ - pushl %ebp /* pt_regs->sp (stashed in bp) */ + pushl $0 /* pt_regs->sp (placeholder) */ pushfl /* pt_regs->flags (except IF = 0) */ - orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ pushl $0 /* pt_regs->ip = 0 (placeholder) */ pushl %eax /* pt_regs->orig_ax */ @@ -965,7 +964,7 @@ SYM_FUNC_START(entry_SYSENTER_32) .Lsysenter_flags_fixed: movl %esp, %eax - call do_fast_syscall_32 + call do_SYSENTER_32 /* XEN PV guests always use IRET path */ ALTERNATIVE "testl %eax, %eax; jz .Lsyscall_32_done", \ "jmp .Lsyscall_32_done", X86_FEATURE_XENPV diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 0f974ae01e62..541fdaf64045 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -57,29 +57,30 @@ SYM_CODE_START(entry_SYSENTER_compat) movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp - /* - * User tracing code (ptrace or signal handlers) might assume that - * the saved RAX contains a 32-bit number when we're invoking a 32-bit - * syscall. Just in case the high bits are nonzero, zero-extend - * the syscall number. (This could almost certainly be deleted - * with no ill effects.) - */ - movl %eax, %eax - /* Construct struct pt_regs on stack */ pushq $__USER32_DS /* pt_regs->ss */ - pushq %rbp /* pt_regs->sp (stashed in bp) */ + pushq $0 /* pt_regs->sp = 0 (placeholder) */ /* * Push flags. This is nasty. First, interrupts are currently - * off, but we need pt_regs->flags to have IF set. Second, even - * if TF was set when SYSENTER started, it's clear by now. We fix - * that later using TIF_SINGLESTEP. + * off, but we need pt_regs->flags to have IF set. Second, if TS + * was set in usermode, it's still set, and we're singlestepping + * through this code. do_SYSENTER_32() will fix up IF. */ pushfq /* pt_regs->flags (except IF = 0) */ - orl $X86_EFLAGS_IF, (%rsp) /* Fix saved flags */ pushq $__USER32_CS /* pt_regs->cs */ pushq $0 /* pt_regs->ip = 0 (placeholder) */ +SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) + + /* + * User tracing code (ptrace or signal handlers) might assume that + * the saved RAX contains a 32-bit number when we're invoking a 32-bit + * syscall. Just in case the high bits are nonzero, zero-extend + * the syscall number. (This could almost certainly be deleted + * with no ill effects.) + */ + movl %eax, %eax + pushq %rax /* pt_regs->orig_ax */ pushq %rdi /* pt_regs->di */ pushq %rsi /* pt_regs->si */ @@ -135,7 +136,7 @@ SYM_CODE_START(entry_SYSENTER_compat) .Lsysenter_flags_fixed: movq %rsp, %rdi - call do_fast_syscall_32 + call do_SYSENTER_32 /* XEN PV guests always use IRET path */ ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \ "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile index 12c42eba77ec..9933c0e8e97a 100644 --- a/arch/x86/events/Makefile +++ b/arch/x86/events/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only obj-y += core.o probe.o -obj-$(PERF_EVENTS_INTEL_RAPL) += rapl.o +obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL) += rapl.o obj-y += amd/ obj-$(CONFIG_X86_LOCAL_APIC) += msr.o obj-$(CONFIG_CPU_SUP_INTEL) += intel/ diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index a54c6a401581..6035df1b49e1 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -375,7 +375,10 @@ void __init hyperv_init(void) guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0); wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id); - hv_hypercall_pg = vmalloc_exec(PAGE_SIZE); + hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START, + VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX, + VM_FLUSH_RESET_PERMS, NUMA_NO_NODE, + __builtin_return_address(0)); if (hv_hypercall_pg == NULL) { wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); goto remove_cpuhp_state; diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 35460fef39b8..0367efdc5b7a 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -201,12 +201,8 @@ arch_test_and_change_bit(long nr, volatile unsigned long *addr) return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); } -static __no_kcsan_or_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) +static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) { - /* - * Because this is a plain access, we need to disable KCSAN here to - * avoid double instrumentation via instrumented bitops. - */ return ((1UL << (nr & (BITS_PER_LONG-1))) & (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; } diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index fb34ff641e0a..028189575560 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -75,6 +75,12 @@ do { \ unreachable(); \ } while (0) +/* + * This instrumentation_begin() is strictly speaking incorrect; but it + * suppresses the complaints from WARN()s in noinstr code. If such a WARN() + * were to trigger, we'd rather wreck the machine in an attempt to get the + * message out than not know about it. + */ #define __WARN_FLAGS(flags) \ do { \ instrumentation_begin(); \ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index dd17c2da1af5..da78ccbd493b 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -58,4 +58,9 @@ static inline bool handle_guest_split_lock(unsigned long ip) return false; } #endif +#ifdef CONFIG_IA32_FEAT_CTL +void init_ia32_feat_ctl(struct cpuinfo_x86 *c); +#else +static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {} +#endif #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h index 6722ffcef2e6..3afa990d756b 100644 --- a/arch/x86/include/asm/cpumask.h +++ b/arch/x86/include/asm/cpumask.h @@ -11,5 +11,23 @@ extern cpumask_var_t cpu_sibling_setup_mask; extern void setup_cpu_local_masks(void); +/* + * NMI and MCE exceptions need cpu_is_offline() _really_ early, + * provide an arch_ special for them to avoid instrumentation. + */ +#if NR_CPUS > 1 +static __always_inline bool arch_cpu_online(int cpu) +{ + return arch_test_bit(cpu, cpumask_bits(cpu_online_mask)); +} +#else +static __always_inline bool arch_cpu_online(int cpu) +{ + return cpu == 0; +} +#endif + +#define arch_cpu_is_offline(cpu) unlikely(!arch_cpu_online(cpu)) + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_CPUMASK_H */ diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 42159f45bf9c..845e7481ab77 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -623,6 +623,11 @@ static inline void switch_fpu_finish(struct fpu *new_fpu) * MXCSR and XCR definitions: */ +static inline void ldmxcsr(u32 mxcsr) +{ + asm volatile("ldmxcsr %0" :: "m" (mxcsr)); +} + extern unsigned int mxcsr_feature_mask; #define XCR_XFEATURE_ENABLED_MASK 0x00000000 diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index cf51c50eb356..eeac6dc2adaa 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -353,10 +353,6 @@ static __always_inline void __##func(struct pt_regs *regs) #else /* CONFIG_X86_64 */ -/* Maps to a regular IDTENTRY on 32bit for now */ -# define DECLARE_IDTENTRY_IST DECLARE_IDTENTRY -# define DEFINE_IDTENTRY_IST DEFINE_IDTENTRY - /** * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant * @vector: Vector number (ignored for C) @@ -387,28 +383,18 @@ __visible noinstr void func(struct pt_regs *regs, \ #endif /* !CONFIG_X86_64 */ /* C-Code mapping */ +#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW +#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW + +#ifdef CONFIG_X86_64 #define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST -#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW -#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW - #define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST - -/** - * DECLARE_IDTENTRY_XEN - Declare functions for XEN redirect IDT entry points - * @vector: Vector number (ignored for C) - * @func: Function name of the entry point - * - * Used for xennmi and xendebug redirections. No DEFINE as this is all ASM - * indirection magic. - */ -#define DECLARE_IDTENTRY_XEN(vector, func) \ - asmlinkage void xen_asm_exc_xen##func(void); \ - asmlinkage void asm_exc_xen##func(void) +#endif #else /* !__ASSEMBLY__ */ @@ -455,9 +441,6 @@ __visible noinstr void func(struct pt_regs *regs, \ # define DECLARE_IDTENTRY_MCE(vector, func) \ DECLARE_IDTENTRY(vector, func) -# define DECLARE_IDTENTRY_DEBUG(vector, func) \ - DECLARE_IDTENTRY(vector, func) - /* No ASM emitted for DF as this goes through a C shim */ # define DECLARE_IDTENTRY_DF(vector, func) @@ -469,10 +452,6 @@ __visible noinstr void func(struct pt_regs *regs, \ /* No ASM code emitted for NMI */ #define DECLARE_IDTENTRY_NMI(vector, func) -/* XEN NMI and DB wrapper */ -#define DECLARE_IDTENTRY_XEN(vector, func) \ - idtentry vector asm_exc_xen##func exc_##func has_error_code=0 - /* * ASM code to emit the common vector entry stubs where each stub is * packed into 8 bytes. @@ -565,16 +544,28 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_BP, exc_int3); DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF, exc_page_fault); #ifdef CONFIG_X86_MCE +#ifdef CONFIG_X86_64 DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check); +#else +DECLARE_IDTENTRY_RAW(X86_TRAP_MC, exc_machine_check); +#endif #endif /* NMI */ DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi); -DECLARE_IDTENTRY_XEN(X86_TRAP_NMI, nmi); +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW(X86_TRAP_NMI, xenpv_exc_nmi); +#endif /* #DB */ +#ifdef CONFIG_X86_64 DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB, exc_debug); -DECLARE_IDTENTRY_XEN(X86_TRAP_DB, debug); +#else +DECLARE_IDTENTRY_RAW(X86_TRAP_DB, exc_debug); +#endif +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW(X86_TRAP_DB, xenpv_exc_debug); +#endif /* #DF */ DECLARE_IDTENTRY_DF(X86_TRAP_DF, exc_double_fault); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 2da1f95b88d7..816b31c68550 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -194,6 +194,7 @@ enum page_cache_mode { #define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) #define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) #define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_ROX (__PP| 0| 0|___A| 0|___D| 0|___G) #define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) #define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX|___D| 0|___G) #define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) @@ -219,6 +220,7 @@ enum page_cache_mode { #define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC) #define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC) #define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) +#define PAGE_KERNEL_ROX __pgprot_mask(__PAGE_KERNEL_ROX | _ENC) #define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC) #define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC) #define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 42cd333616c4..03b7c4ca425a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -370,7 +370,7 @@ struct x86_hw_tss { #define IO_BITMAP_OFFSET_INVALID (__KERNEL_TSS_LIMIT + 1) struct entry_stack { - unsigned long words[64]; + char stack[PAGE_SIZE]; }; struct entry_stack_page { diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 17c5a038f42d..0780f97c1850 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -408,14 +408,15 @@ struct kvm_vmx_nested_state_data { }; struct kvm_vmx_nested_state_hdr { - __u32 flags; __u64 vmxon_pa; __u64 vmcs12_pa; - __u64 preemption_timer_deadline; struct { __u16 flags; } smm; + + __u32 flags; + __u64 preemption_timer_deadline; }; struct kvm_svm_nested_state_data { diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 426792565d86..c5cf336e5077 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -3,6 +3,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include <asm/e820/api.h> #include <asm/mtrr.h> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 043d93cdcaad..95c090a45b4b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -347,6 +347,9 @@ out: cr4_clear_bits(X86_CR4_UMIP); } +/* These bits should not change their value after CPU init is finished. */ +static const unsigned long cr4_pinned_mask = + X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | X86_CR4_FSGSBASE; static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); static unsigned long cr4_pinned_bits __ro_after_init; @@ -371,20 +374,20 @@ EXPORT_SYMBOL(native_write_cr0); void native_write_cr4(unsigned long val) { - unsigned long bits_missing = 0; + unsigned long bits_changed = 0; set_register: asm volatile("mov %0,%%cr4": "+r" (val), "+m" (cr4_pinned_bits)); if (static_branch_likely(&cr_pinning)) { - if (unlikely((val & cr4_pinned_bits) != cr4_pinned_bits)) { - bits_missing = ~val & cr4_pinned_bits; - val |= bits_missing; + if (unlikely((val & cr4_pinned_mask) != cr4_pinned_bits)) { + bits_changed = (val & cr4_pinned_mask) ^ cr4_pinned_bits; + val = (val & ~cr4_pinned_mask) | cr4_pinned_bits; goto set_register; } - /* Warn after we've set the missing bits. */ - WARN_ONCE(bits_missing, "CR4 bits went missing: %lx!?\n", - bits_missing); + /* Warn after we've corrected the changed bits. */ + WARN_ONCE(bits_changed, "pinned CR4 bits changed: 0x%lx!?\n", + bits_changed); } } #if IS_MODULE(CONFIG_LKDTM) @@ -419,7 +422,7 @@ void cr4_init(void) if (boot_cpu_has(X86_FEATURE_PCID)) cr4 |= X86_CR4_PCIDE; if (static_branch_likely(&cr_pinning)) - cr4 |= cr4_pinned_bits; + cr4 = (cr4 & ~cr4_pinned_mask) | cr4_pinned_bits; __write_cr4(cr4); @@ -434,10 +437,7 @@ void cr4_init(void) */ static void __init setup_cr_pinning(void) { - unsigned long mask; - - mask = (X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP); - cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & mask; + cr4_pinned_bits = this_cpu_read(cpu_tlbstate.cr4) & cr4_pinned_mask; static_key_enable(&cr_pinning.key); } diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index fb538fccd24c..9d033693519a 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -81,8 +81,4 @@ extern void update_srbds_msr(void); extern u64 x86_read_arch_cap_msr(void); -#ifdef CONFIG_IA32_FEAT_CTL -void init_ia32_feat_ctl(struct cpuinfo_x86 *c); -#endif - #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index c25a67a34bd3..0ab48f1cdf84 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -50,6 +50,13 @@ static enum split_lock_detect_state sld_state __ro_after_init = sld_off; static u64 msr_test_ctrl_cache __ro_after_init; /* + * With a name like MSR_TEST_CTL it should go without saying, but don't touch + * MSR_TEST_CTL unless the CPU is one of the whitelisted models. Writing it + * on CPUs that do not support SLD can cause fireworks, even when writing '0'. + */ +static bool cpu_model_supports_sld __ro_after_init; + +/* * Processors which have self-snooping capability can handle conflicting * memory type across CPUs by snooping its own cache. However, there exists * CPU models in which having conflicting memory types still leads to @@ -1071,7 +1078,8 @@ static void sld_update_msr(bool on) static void split_lock_init(void) { - split_lock_verify_msr(sld_state != sld_off); + if (cpu_model_supports_sld) + split_lock_verify_msr(sld_state != sld_off); } static void split_lock_warn(unsigned long ip) @@ -1177,5 +1185,6 @@ void __init cpu_set_core_cap_bits(struct cpuinfo_x86 *c) return; } + cpu_model_supports_sld = true; split_lock_setup(); } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index ce9120c4f740..14e4b4d17ee5 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1083,7 +1083,7 @@ static noinstr bool mce_check_crashing_cpu(void) { unsigned int cpu = smp_processor_id(); - if (cpu_is_offline(cpu) || + if (arch_cpu_is_offline(cpu) || (crashing_cpu != -1 && crashing_cpu != cpu)) { u64 mcgstatus; @@ -1901,6 +1901,8 @@ void (*machine_check_vector)(struct pt_regs *) = unexpected_machine_check; static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) { + WARN_ON_ONCE(user_mode(regs)); + /* * Only required when from kernel mode. See * mce_check_crashing_cpu() for details. @@ -1954,7 +1956,7 @@ DEFINE_IDTENTRY_MCE_USER(exc_machine_check) } #else /* 32bit unified entry point */ -DEFINE_IDTENTRY_MCE(exc_machine_check) +DEFINE_IDTENTRY_RAW(exc_machine_check) { unsigned long dr7; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 12f967c6b603..6a9df71c1b9e 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -981,10 +981,10 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c) c->x86_cache_max_rmid = ecx; c->x86_cache_occ_scale = ebx; - if (c->x86_vendor == X86_VENDOR_INTEL) - c->x86_cache_mbm_width_offset = eax & 0xff; - else - c->x86_cache_mbm_width_offset = -1; + c->x86_cache_mbm_width_offset = eax & 0xff; + + if (c->x86_vendor == X86_VENDOR_AMD && !c->x86_cache_mbm_width_offset) + c->x86_cache_mbm_width_offset = MBM_CNTR_WIDTH_OFFSET_AMD; } } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index f20a47d120b1..5ffa32256b3b 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -37,6 +37,7 @@ #define MBA_IS_LINEAR 0x4 #define MBA_MAX_MBPS U32_MAX #define MAX_MBA_BW_AMD 0x800 +#define MBM_CNTR_WIDTH_OFFSET_AMD 20 #define RMID_VAL_ERROR BIT_ULL(63) #define RMID_VAL_UNAVAIL BIT_ULL(62) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 23b4b61319d3..3f844f14fc0a 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1117,6 +1117,7 @@ static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); if (WARN_ON(IS_ERR_OR_NULL(_d_cdp))) { _r_cdp = NULL; + _d_cdp = NULL; ret = -EINVAL; } diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index df1358ba622b..05fa4ef63490 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -2,6 +2,7 @@ #include <linux/sched.h> #include <linux/sched/clock.h> +#include <asm/cpu.h> #include <asm/cpufeature.h> #include "cpu.h" diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index 06c818967bb6..15247b96c6ea 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -101,6 +101,12 @@ void kernel_fpu_begin(void) copy_fpregs_to_fpstate(¤t->thread.fpu); } __cpu_invalidate_fpregs_state(); + + if (boot_cpu_has(X86_FEATURE_XMM)) + ldmxcsr(MXCSR_DEFAULT); + + if (boot_cpu_has(X86_FEATURE_FPU)) + asm volatile ("fninit"); } EXPORT_SYMBOL_GPL(kernel_fpu_begin); diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 8748321c4486..b8aee71840ae 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -29,6 +29,8 @@ #include <asm/mmu_context.h> #include <asm/pgtable_areas.h> +#include <xen/xen.h> + /* This is a multiple of PAGE_SIZE. */ #define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE) @@ -543,6 +545,28 @@ static int read_default_ldt(void __user *ptr, unsigned long bytecount) return bytecount; } +static bool allow_16bit_segments(void) +{ + if (!IS_ENABLED(CONFIG_X86_16BIT)) + return false; + +#ifdef CONFIG_XEN_PV + /* + * Xen PV does not implement ESPFIX64, which means that 16-bit + * segments will not work correctly. Until either Xen PV implements + * ESPFIX64 and can signal this fact to the guest or unless someone + * provides compelling evidence that allowing broken 16-bit segments + * is worthwhile, disallow 16-bit segments under Xen PV. + */ + if (xen_pv_domain()) { + pr_info_once("Warning: 16-bit segments do not work correctly in a Xen PV guest\n"); + return false; + } +#endif + + return true; +} + static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) { struct mm_struct *mm = current->mm; @@ -574,7 +598,7 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) /* The user wants to clear the entry. */ memset(&ldt, 0, sizeof(ldt)); } else { - if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + if (!ldt_info.seg_32bit && !allow_16bit_segments()) { error = -EINVAL; goto out; } diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 2de365f15684..d7c5e44b26f7 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -478,7 +478,7 @@ static DEFINE_PER_CPU(unsigned long, nmi_dr7); DEFINE_IDTENTRY_RAW(exc_nmi) { - if (IS_ENABLED(CONFIG_SMP) && cpu_is_offline(smp_processor_id())) + if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) return; if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f9727b96961f..b038695f36c5 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -84,17 +84,16 @@ static inline void cond_local_irq_disable(struct pt_regs *regs) local_irq_disable(); } -int is_valid_bugaddr(unsigned long addr) +__always_inline int is_valid_bugaddr(unsigned long addr) { - unsigned short ud; - if (addr < TASK_SIZE_MAX) return 0; - if (get_kernel_nofault(ud, (unsigned short *)addr)) - return 0; - - return ud == INSN_UD0 || ud == INSN_UD2; + /* + * We got #UD, if the text isn't readable we'd have gotten + * a different exception. + */ + return *(unsigned short *)addr == INSN_UD2; } static nokprobe_inline int @@ -216,40 +215,45 @@ static inline void handle_invalid_op(struct pt_regs *regs) ILL_ILLOPN, error_get_trap_addr(regs)); } -DEFINE_IDTENTRY_RAW(exc_invalid_op) +static noinstr bool handle_bug(struct pt_regs *regs) { - bool rcu_exit; + bool handled = false; + + if (!is_valid_bugaddr(regs->ip)) + return handled; /* - * Handle BUG/WARN like NMIs instead of like normal idtentries: - * if we bugged/warned in a bad RCU context, for example, the last - * thing we want is to BUG/WARN again in the idtentry code, ad - * infinitum. + * All lies, just get the WARN/BUG out. + */ + instrumentation_begin(); + /* + * Since we're emulating a CALL with exceptions, restore the interrupt + * state to what it was at the exception site. */ - if (!user_mode(regs) && is_valid_bugaddr(regs->ip)) { - enum bug_trap_type type; + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_enable(); + if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { + regs->ip += LEN_UD2; + handled = true; + } + if (regs->flags & X86_EFLAGS_IF) + raw_local_irq_disable(); + instrumentation_end(); - nmi_enter(); - instrumentation_begin(); - trace_hardirqs_off_finish(); - type = report_bug(regs->ip, regs); - if (regs->flags & X86_EFLAGS_IF) - trace_hardirqs_on_prepare(); - instrumentation_end(); - nmi_exit(); + return handled; +} - if (type == BUG_TRAP_TYPE_WARN) { - /* Skip the ud2. */ - regs->ip += LEN_UD2; - return; - } +DEFINE_IDTENTRY_RAW(exc_invalid_op) +{ + bool rcu_exit; - /* - * Else, if this was a BUG and report_bug returns or if this - * was just a normal #UD, we want to continue onward and - * crash. - */ - } + /* + * We use UD2 as a short encoding for 'CALL __WARN', as such + * handle it before exception entry to avoid recursive WARN + * in case exception entry is the one triggering WARNs. + */ + if (!user_mode(regs) && handle_bug(regs)) + return; rcu_exit = idtentry_enter_cond_rcu(regs); instrumentation_begin(); @@ -691,13 +695,13 @@ struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s) (struct bad_iret_stack *)__this_cpu_read(cpu_tss_rw.x86_tss.sp0) - 1; /* Copy the IRET target to the temporary storage. */ - memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); + __memcpy(&tmp.regs.ip, (void *)s->regs.sp, 5*8); /* Copy the remainder of the stack from the current stack. */ - memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); + __memcpy(&tmp, s, offsetof(struct bad_iret_stack, regs.ip)); /* Update the entry stack */ - memcpy(new_stack, &tmp, sizeof(tmp)); + __memcpy(new_stack, &tmp, sizeof(tmp)); BUG_ON(!user_mode(&new_stack->regs)); return new_stack; @@ -866,6 +870,12 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, trace_hardirqs_off_finish(); /* + * If something gets miswired and we end up here for a user mode + * #DB, we will malfunction. + */ + WARN_ON_ONCE(user_mode(regs)); + + /* * Catch SYSENTER with TF set and clear DR_STEP. If this hit a * watchpoint at the same time then that will still be handled. */ @@ -883,6 +893,12 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, static __always_inline void exc_debug_user(struct pt_regs *regs, unsigned long dr6) { + /* + * If something gets miswired and we end up here for a kernel mode + * #DB, we will malfunction. + */ + WARN_ON_ONCE(!user_mode(regs)); + idtentry_enter_user(regs); instrumentation_begin(); @@ -913,7 +929,7 @@ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) } #else /* 32 bit does not have separate entry points. */ -DEFINE_IDTENTRY_DEBUG(exc_debug) +DEFINE_IDTENTRY_RAW(exc_debug) { unsigned long dr6, dr7; diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index ff2d0e9ca3bc..cfe83d4ae625 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -7,7 +7,7 @@ #define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE) + | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_PGE | X86_CR4_TSD) #define BUILD_KVM_GPR_ACCESSORS(lname, uname) \ static __always_inline unsigned long kvm_##lname##_read(struct kvm_vcpu *vcpu)\ diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 76817d13c86e..6d6a0ae7800c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4449,7 +4449,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, nonleaf_bit8_rsvd | rsvd_bits(7, 7) | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | - nonleaf_bit8_rsvd | gbpages_bit_rsvd | + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index d1af20b050a8..d4a4cec034d0 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4109,7 +4109,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * CR0_GUEST_HOST_MASK is already set in the original vmcs01 * (KVM doesn't change it); */ - vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; + vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; vmx_set_cr0(vcpu, vmcs12->host_cr0); /* Same as above - no reason to call set_cr4_guest_host_mask(). */ @@ -4259,7 +4259,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) */ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); - vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS; + vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); @@ -6176,6 +6176,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, goto error_guest_mode; } + vmx->nested.has_preemption_timer_deadline = false; if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) { vmx->nested.has_preemption_timer_deadline = true; vmx->nested.preemption_timer_deadline = diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index cb22f33bf1d8..13745f2a5ecd 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -133,9 +133,6 @@ module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO); #define KVM_VM_CR0_ALWAYS_ON \ (KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | \ X86_CR0_WP | X86_CR0_PG | X86_CR0_PE) -#define KVM_CR4_GUEST_OWNED_BITS \ - (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ - | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_TSD) #define KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST X86_CR4_VMXE #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE) @@ -4034,9 +4031,9 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx) void set_cr4_guest_host_mask(struct vcpu_vmx *vmx) { - vmx->vcpu.arch.cr4_guest_owned_bits = KVM_CR4_GUEST_OWNED_BITS; - if (enable_ept) - vmx->vcpu.arch.cr4_guest_owned_bits |= X86_CR4_PGE; + vmx->vcpu.arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS; + if (!enable_ept) + vmx->vcpu.arch.cr4_guest_owned_bits &= ~X86_CR4_PGE; if (is_guest_mode(&vmx->vcpu)) vmx->vcpu.arch.cr4_guest_owned_bits &= ~get_vmcs12(&vmx->vcpu)->cr4_guest_host_mask; @@ -4333,8 +4330,8 @@ static void init_vmcs(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); - vmx->vcpu.arch.cr0_guest_owned_bits = X86_CR0_TS; - vmcs_writel(CR0_GUEST_HOST_MASK, ~X86_CR0_TS); + vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits); set_cr4_guest_host_mask(vmx); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3b92db412335..88c593f83b28 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -975,6 +975,8 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) return 1; + if ((cr4 ^ old_cr4) & X86_CR4_LA57) + return 1; } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, @@ -2693,6 +2695,9 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data) if (data & 0x30) return 1; + if (!lapic_in_kernel(vcpu)) + return 1; + vcpu->arch.apf.msr_en_val = data; if (!kvm_pv_async_pf_enabled(vcpu)) { diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 56b243b14c3a..bbcc05bcefad 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -8,6 +8,8 @@ #include <asm/alternative-asm.h> #include <asm/export.h> +.pushsection .noinstr.text, "ax" + /* * We build a jump to memcpy_orig by default which gets NOPped out on * the majority of x86 CPUs which set REP_GOOD. In addition, CPUs which @@ -184,6 +186,8 @@ SYM_FUNC_START_LOCAL(memcpy_orig) retq SYM_FUNC_END(memcpy_orig) +.popsection + #ifndef CONFIG_UML MCSAFE_TEST_CTL diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index fff28c6f73a2..b0dfac3d3df7 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -24,6 +24,7 @@ unsigned long __clear_user(void __user *addr, unsigned long size) asm volatile( " testq %[size8],%[size8]\n" " jz 4f\n" + " .align 16\n" "0: movq $0,(%[dst])\n" " addq $8,%[dst]\n" " decl %%ecx ; jnz 0b\n" diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 7c65102debaf..db1378c6ff26 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -193,6 +193,8 @@ static void fix_processor_context(void) */ static void notrace __restore_processor_state(struct saved_context *ctxt) { + struct cpuinfo_x86 *c; + if (ctxt->misc_enable_saved) wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable); /* @@ -263,6 +265,10 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) mtrr_bp_restore(); perf_restore_debug_store(); msr_restore_context(ctxt); + + c = &cpu_data(smp_processor_id()); + if (cpu_has(c, X86_FEATURE_MSR_IA32_FEAT_CTL)) + init_ia32_feat_ctl(c); } /* Needed by apm.c */ diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index acc49fa6a097..0d68948c82ad 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -598,6 +598,26 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum, } #ifdef CONFIG_X86_64 +void noist_exc_debug(struct pt_regs *regs); + +DEFINE_IDTENTRY_RAW(xenpv_exc_nmi) +{ + /* On Xen PV, NMI doesn't use IST. The C part is the sane as native. */ + exc_nmi(regs); +} + +DEFINE_IDTENTRY_RAW(xenpv_exc_debug) +{ + /* + * There's no IST on Xen PV, but we still need to dispatch + * to the correct handler. + */ + if (user_mode(regs)) + noist_exc_debug(regs); + else + exc_debug(regs); +} + struct trap_array_entry { void (*orig)(void); void (*xen)(void); @@ -609,18 +629,18 @@ struct trap_array_entry { .xen = xen_asm_##func, \ .ist_okay = ist_ok } -#define TRAP_ENTRY_REDIR(func, xenfunc, ist_ok) { \ +#define TRAP_ENTRY_REDIR(func, ist_ok) { \ .orig = asm_##func, \ - .xen = xen_asm_##xenfunc, \ + .xen = xen_asm_xenpv_##func, \ .ist_okay = ist_ok } static struct trap_array_entry trap_array[] = { - TRAP_ENTRY_REDIR(exc_debug, exc_xendebug, true ), + TRAP_ENTRY_REDIR(exc_debug, true ), TRAP_ENTRY(exc_double_fault, true ), #ifdef CONFIG_X86_MCE TRAP_ENTRY(exc_machine_check, true ), #endif - TRAP_ENTRY_REDIR(exc_nmi, exc_xennmi, true ), + TRAP_ENTRY_REDIR(exc_nmi, true ), TRAP_ENTRY(exc_int3, false ), TRAP_ENTRY(exc_overflow, false ), #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S index 5d252aaeade8..aab1d99b2b48 100644 --- a/arch/x86/xen/xen-asm_64.S +++ b/arch/x86/xen/xen-asm_64.S @@ -29,10 +29,9 @@ _ASM_NOKPROBE(xen_\name) .endm xen_pv_trap asm_exc_divide_error -xen_pv_trap asm_exc_debug -xen_pv_trap asm_exc_xendebug +xen_pv_trap asm_xenpv_exc_debug xen_pv_trap asm_exc_int3 -xen_pv_trap asm_exc_xennmi +xen_pv_trap asm_xenpv_exc_nmi xen_pv_trap asm_exc_overflow xen_pv_trap asm_exc_bounds xen_pv_trap asm_exc_invalid_op @@ -161,10 +160,22 @@ SYM_FUNC_END(xen_syscall32_target) /* 32-bit compat sysenter target */ SYM_FUNC_START(xen_sysenter_target) - mov 0*8(%rsp), %rcx - mov 1*8(%rsp), %r11 - mov 5*8(%rsp), %rsp - jmp entry_SYSENTER_compat + /* + * NB: Xen is polite and clears TF from EFLAGS for us. This means + * that we don't need to guard against single step exceptions here. + */ + popq %rcx + popq %r11 + + /* + * Neither Xen nor the kernel really knows what the old SS and + * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * report those values even though Xen will guess its own values. + */ + movq $__USER32_DS, 4*8(%rsp) + movq $__USER32_CS, 1*8(%rsp) + + jmp entry_SYSENTER_compat_after_hwframe SYM_FUNC_END(xen_sysenter_target) #else /* !CONFIG_IA32_EMULATION */ |