diff options
Diffstat (limited to 'arch/x86/entry')
| -rw-r--r-- | arch/x86/entry/Makefile | 4 | ||||
| -rw-r--r-- | arch/x86/entry/entry_32.S | 1249 | ||||
| -rw-r--r-- | arch/x86/entry/entry_64.S | 1442 |
3 files changed, 2695 insertions, 0 deletions
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile new file mode 100644 index 000000000000..fa7e0cf6d3c4 --- /dev/null +++ b/arch/x86/entry/Makefile @@ -0,0 +1,4 @@ +# +# Makefile for the x86 low level entry code +# +obj-y := entry_$(BITS).o diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S new file mode 100644 index 000000000000..0ac73de925d1 --- /dev/null +++ b/arch/x86/entry/entry_32.S @@ -0,0 +1,1249 @@ +/* + * + * Copyright (C) 1991, 1992 Linus Torvalds + */ + +/* + * entry.S contains the system-call and fault low-level handling routines. + * This also contains the timer-interrupt handler, as well as all interrupts + * and faults that can result in a task-switch. + * + * NOTE: This code handles signal-recognition, which happens every time + * after a timer-interrupt and after each system call. + * + * I changed all the .align's to 4 (16 byte alignment), as that's faster + * on a 486. + * + * Stack layout in 'syscall_exit': + * ptrace needs to have all regs on the stack. + * if the order here is changed, it needs to be + * updated in fork.c:copy_process, signal.c:do_signal, + * ptrace.c and ptrace.h + * + * 0(%esp) - %ebx + * 4(%esp) - %ecx + * 8(%esp) - %edx + * C(%esp) - %esi + * 10(%esp) - %edi + * 14(%esp) - %ebp + * 18(%esp) - %eax + * 1C(%esp) - %ds + * 20(%esp) - %es + * 24(%esp) - %fs + * 28(%esp) - %gs saved iff !CONFIG_X86_32_LAZY_GS + * 2C(%esp) - orig_eax + * 30(%esp) - %eip + * 34(%esp) - %cs + * 38(%esp) - %eflags + * 3C(%esp) - %oldesp + * 40(%esp) - %oldss + * + * "current" is in register %ebx during any slow entries. + */ + +#include <linux/linkage.h> +#include <linux/err.h> +#include <asm/thread_info.h> +#include <asm/irqflags.h> +#include <asm/errno.h> +#include <asm/segment.h> +#include <asm/smp.h> +#include <asm/page_types.h> +#include <asm/percpu.h> +#include <asm/processor-flags.h> +#include <asm/ftrace.h> +#include <asm/irq_vectors.h> +#include <asm/cpufeature.h> +#include <asm/alternative-asm.h> +#include <asm/asm.h> +#include <asm/smap.h> + +/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ +#include <linux/elf-em.h> +#define AUDIT_ARCH_I386 (EM_386|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_LE 0x40000000 + +#ifndef CONFIG_AUDITSYSCALL +#define sysenter_audit syscall_trace_entry +#define sysexit_audit syscall_exit_work +#endif + + .section .entry.text, "ax" + +/* + * We use macros for low-level operations which need to be overridden + * for paravirtualization. The following will never clobber any registers: + * INTERRUPT_RETURN (aka. "iret") + * GET_CR0_INTO_EAX (aka. "movl %cr0, %eax") + * ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit"). + * + * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must + * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY). + * Allowing a register to be clobbered can shrink the paravirt replacement + * enough to patch inline, increasing performance. + */ + +#ifdef CONFIG_PREEMPT +#define preempt_stop(clobbers) DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF +#else +#define preempt_stop(clobbers) +#define resume_kernel restore_all +#endif + +.macro TRACE_IRQS_IRET +#ifdef CONFIG_TRACE_IRQFLAGS + testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off? + jz 1f + TRACE_IRQS_ON +1: +#endif +.endm + +/* + * User gs save/restore + * + * %gs is used for userland TLS and kernel only uses it for stack + * canary which is required to be at %gs:20 by gcc. Read the comment + * at the top of stackprotector.h for more info. + * + * Local labels 98 and 99 are used. + */ +#ifdef CONFIG_X86_32_LAZY_GS + + /* unfortunately push/pop can't be no-op */ +.macro PUSH_GS + pushl $0 +.endm +.macro POP_GS pop=0 + addl $(4 + \pop), %esp +.endm +.macro POP_GS_EX +.endm + + /* all the rest are no-op */ +.macro PTGS_TO_GS +.endm +.macro PTGS_TO_GS_EX +.endm +.macro GS_TO_REG reg +.endm +.macro REG_TO_PTGS reg +.endm +.macro SET_KERNEL_GS reg +.endm + +#else /* CONFIG_X86_32_LAZY_GS */ + +.macro PUSH_GS + pushl %gs +.endm + +.macro POP_GS pop=0 +98: popl %gs + .if \pop <> 0 + add $\pop, %esp + .endif +.endm +.macro POP_GS_EX +.pushsection .fixup, "ax" +99: movl $0, (%esp) + jmp 98b +.popsection + _ASM_EXTABLE(98b,99b) +.endm + +.macro PTGS_TO_GS +98: mov PT_GS(%esp), %gs +.endm +.macro PTGS_TO_GS_EX +.pushsection .fixup, "ax" +99: movl $0, PT_GS(%esp) + jmp 98b +.popsection + _ASM_EXTABLE(98b,99b) +.endm + +.macro GS_TO_REG reg + movl %gs, \reg +.endm +.macro REG_TO_PTGS reg + movl \reg, PT_GS(%esp) +.endm +.macro SET_KERNEL_GS reg + movl $(__KERNEL_STACK_CANARY), \reg + movl \reg, %gs +.endm + +#endif /* CONFIG_X86_32_LAZY_GS */ + +.macro SAVE_ALL + cld + PUSH_GS + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + movl $(__USER_DS), %edx + movl %edx, %ds + movl %edx, %es + movl $(__KERNEL_PERCPU), %edx + movl %edx, %fs + SET_KERNEL_GS %edx +.endm + +.macro RESTORE_INT_REGS + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax +.endm + +.macro RESTORE_REGS pop=0 + RESTORE_INT_REGS +1: popl %ds +2: popl %es +3: popl %fs + POP_GS \pop +.pushsection .fixup, "ax" +4: movl $0, (%esp) + jmp 1b +5: movl $0, (%esp) + jmp 2b +6: movl $0, (%esp) + jmp 3b +.popsection + _ASM_EXTABLE(1b,4b) + _ASM_EXTABLE(2b,5b) + _ASM_EXTABLE(3b,6b) + POP_GS_EX +.endm + +ENTRY(ret_from_fork) + pushl %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl %eax + pushl $0x0202 # Reset kernel eflags + popfl + jmp syscall_exit +END(ret_from_fork) + +ENTRY(ret_from_kernel_thread) + pushl %eax + call schedule_tail + GET_THREAD_INFO(%ebp) + popl %eax + pushl $0x0202 # Reset kernel eflags + popfl + movl PT_EBP(%esp),%eax + call *PT_EBX(%esp) + movl $0,PT_EAX(%esp) + jmp syscall_exit +ENDPROC(ret_from_kernel_thread) + +/* + * Return to user mode is not as complex as all this looks, + * but we want the default path for a system call return to + * go as quickly as possible which is why some of this is + * less clear than it otherwise should be. + */ + + # userspace resumption stub bypassing syscall exit tracing + ALIGN +ret_from_exception: + preempt_stop(CLBR_ANY) +ret_from_intr: + GET_THREAD_INFO(%ebp) +#ifdef CONFIG_VM86 + movl PT_EFLAGS(%esp), %eax # mix EFLAGS and CS + movb PT_CS(%esp), %al + andl $(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %eax +#else + /* + * We can be coming here from child spawned by kernel_thread(). + */ + movl PT_CS(%esp), %eax + andl $SEGMENT_RPL_MASK, %eax +#endif + cmpl $USER_RPL, %eax + jb resume_kernel # not returning to v8086 or userspace + +ENTRY(resume_userspace) + LOCKDEP_SYS_EXIT + DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + andl $_TIF_WORK_MASK, %ecx # is there any work to be done on + # int/exception return? + jne work_pending + jmp restore_all +END(ret_from_exception) + +#ifdef CONFIG_PREEMPT +ENTRY(resume_kernel) + DISABLE_INTERRUPTS(CLBR_ANY) +need_resched: + cmpl $0,PER_CPU_VAR(__preempt_count) + jnz restore_all + testl $X86_EFLAGS_IF,PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all + call preempt_schedule_irq + jmp need_resched +END(resume_kernel) +#endif + +/* SYSENTER_RETURN points to after the "sysenter" instruction in + the vsyscall page. See vsyscall-sysentry.S, which defines the symbol. */ + + # sysenter call handler stub +ENTRY(ia32_sysenter_target) + movl TSS_sysenter_sp0(%esp),%esp +sysenter_past_esp: + /* + * Interrupts are disabled here, but we can't trace it until + * enough kernel state to call TRACE_IRQS_OFF can be called - but + * we immediately enable interrupts at that point anyway. + */ + pushl $__USER_DS + pushl %ebp + pushfl + orl $X86_EFLAGS_IF, (%esp) + pushl $__USER_CS + /* + * Push current_thread_info()->sysenter_return to the stack. + * A tiny bit of offset fixup is necessary: TI_sysenter_return + * is relative to thread_info, which is at the bottom of the + * kernel stack page. 4*4 means the 4 words pushed above; + * TOP_OF_KERNEL_STACK_PADDING takes us to the top of the stack; + * and THREAD_SIZE takes us to the bottom. + */ + pushl ((TI_sysenter_return) - THREAD_SIZE + TOP_OF_KERNEL_STACK_PADDING + 4*4)(%esp) + + pushl %eax + SAVE_ALL + ENABLE_INTERRUPTS(CLBR_NONE) + +/* + * Load the potential sixth argument from user stack. + * Careful about security. + */ + cmpl $__PAGE_OFFSET-3,%ebp + jae syscall_fault + ASM_STAC +1: movl (%ebp),%ebp + ASM_CLAC + movl %ebp,PT_EBP(%esp) + _ASM_EXTABLE(1b,syscall_fault) + + GET_THREAD_INFO(%ebp) + + testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) + jnz sysenter_audit +sysenter_do_call: + cmpl $(NR_syscalls), %eax + jae sysenter_badsys + call *sys_call_table(,%eax,4) +sysenter_after_call: + movl %eax,PT_EAX(%esp) + LOCKDEP_SYS_EXIT + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + testl $_TIF_ALLWORK_MASK, %ecx + jnz sysexit_audit +sysenter_exit: +/* if something modifies registers it must also disable sysexit */ + movl PT_EIP(%esp), %edx + movl PT_OLDESP(%esp), %ecx + xorl %ebp,%ebp + TRACE_IRQS_ON +1: mov PT_FS(%esp), %fs + PTGS_TO_GS + ENABLE_INTERRUPTS_SYSEXIT + +#ifdef CONFIG_AUDITSYSCALL +sysenter_audit: + testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%ebp) + jnz syscall_trace_entry + /* movl PT_EAX(%esp), %eax already set, syscall number: 1st arg to audit */ + movl PT_EBX(%esp), %edx /* ebx/a0: 2nd arg to audit */ + /* movl PT_ECX(%esp), %ecx already set, a1: 3nd arg to audit */ + pushl PT_ESI(%esp) /* a3: 5th arg */ + pushl PT_EDX+4(%esp) /* a2: 4th arg */ + call __audit_syscall_entry + popl %ecx /* get that remapped edx off the stack */ + popl %ecx /* get that remapped esi off the stack */ + movl PT_EAX(%esp),%eax /* reload syscall number */ + jmp sysenter_do_call + +sysexit_audit: + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx + jnz syscall_exit_work + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_ANY) + movl %eax,%edx /* second arg, syscall return value */ + cmpl $-MAX_ERRNO,%eax /* is it an error ? */ + setbe %al /* 1 if so, 0 if not */ + movzbl %al,%eax /* zero-extend that */ + call __audit_syscall_exit + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + testl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %ecx + jnz syscall_exit_work + movl PT_EAX(%esp),%eax /* reload syscall return value */ + jmp sysenter_exit +#endif + +.pushsection .fixup,"ax" +2: movl $0,PT_FS(%esp) + jmp 1b +.popsection + _ASM_EXTABLE(1b,2b) + PTGS_TO_GS_EX +ENDPROC(ia32_sysenter_target) + + # system call handler stub +ENTRY(system_call) + ASM_CLAC + pushl %eax # save orig_eax + SAVE_ALL + GET_THREAD_INFO(%ebp) + # system call tracing in operation / emulation + testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%ebp) + jnz syscall_trace_entry + cmpl $(NR_syscalls), %eax + jae syscall_badsys +syscall_call: + call *sys_call_table(,%eax,4) +syscall_after_call: + movl %eax,PT_EAX(%esp) # store the return value +syscall_exit: + LOCKDEP_SYS_EXIT + DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + testl $_TIF_ALLWORK_MASK, %ecx # current->work + jnz syscall_exit_work + +restore_all: + TRACE_IRQS_IRET +restore_all_notrace: +#ifdef CONFIG_X86_ESPFIX32 + movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS + # Warning: PT_OLDSS(%esp) contains the wrong/random values if we + # are returning to the kernel. + # See comments in process.c:copy_thread() for details. + movb PT_OLDSS(%esp), %ah + movb PT_CS(%esp), %al + andl $(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax + cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax + je ldt_ss # returning to user-space with LDT SS +#endif +restore_nocheck: + RESTORE_REGS 4 # skip orig_eax/error_code +irq_return: + INTERRUPT_RETURN +.section .fixup,"ax" +ENTRY(iret_exc) + pushl $0 # no error code + pushl $do_iret_error + jmp error_code +.previous + _ASM_EXTABLE(irq_return,iret_exc) + +#ifdef CONFIG_X86_ESPFIX32 +ldt_ss: +#ifdef CONFIG_PARAVIRT + /* + * The kernel can't run on a non-flat stack if paravirt mode + * is active. Rather than try to fixup the high bits of + * ESP, bypass this code entirely. This may break DOSemu + * and/or Wine support in a paravirt VM, although the option + * is still available to implement the setting of the high + * 16-bits in the INTERRUPT_RETURN paravirt-op. + */ + cmpl $0, pv_info+PARAVIRT_enabled + jne restore_nocheck +#endif + +/* + * Setup and switch to ESPFIX stack + * + * We're returning to userspace with a 16 bit stack. The CPU will not + * restore the high word of ESP for us on executing iret... This is an + * "official" bug of all the x86-compatible CPUs, which we can work + * around to make dosemu and wine happy. We do this by preloading the + * high word of ESP with the high word of the userspace ESP while + * compensating for the offset by changing to the ESPFIX segment with + * a base address that matches for the difference. + */ +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8) + mov %esp, %edx /* load kernel esp */ + mov PT_OLDESP(%esp), %eax /* load userspace esp */ + mov %dx, %ax /* eax: new kernel esp */ + sub %eax, %edx /* offset (low word is 0) */ + shr $16, %edx + mov %dl, GDT_ESPFIX_SS + 4 /* bits 16..23 */ + mov %dh, GDT_ESPFIX_SS + 7 /* bits 24..31 */ + pushl $__ESPFIX_SS + pushl %eax /* new kernel esp */ + /* Disable interrupts, but do not irqtrace this section: we + * will soon execute iret and the tracer was already set to + * the irqstate after the iret */ + DISABLE_INTERRUPTS(CLBR_EAX) + lss (%esp), %esp /* switch to espfix segment */ + jmp restore_nocheck +#endif +ENDPROC(system_call) + + # perform work that needs to be done immediately before resumption + ALIGN +work_pending: + testb $_TIF_NEED_RESCHED, %cl + jz work_notifysig +work_resched: + call schedule + LOCKDEP_SYS_EXIT + DISABLE_INTERRUPTS(CLBR_ANY) # make sure we don't miss an interrupt + # setting need_resched or sigpending + # between sampling and the iret + TRACE_IRQS_OFF + movl TI_flags(%ebp), %ecx + andl $_TIF_WORK_MASK, %ecx # is there any work to be done other + # than syscall tracing? + jz restore_all + testb $_TIF_NEED_RESCHED, %cl + jnz work_resched + +work_notifysig: # deal with pending signals and + # notify-resume requests +#ifdef CONFIG_VM86 + testl $X86_EFLAGS_VM, PT_EFLAGS(%esp) + movl %esp, %eax + jnz work_notifysig_v86 # returning to kernel-space or + # vm86-space +1: +#else + movl %esp, %eax +#endif + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + movb PT_CS(%esp), %bl + andb $SEGMENT_RPL_MASK, %bl + cmpb $USER_RPL, %bl + jb resume_kernel + xorl %edx, %edx + call do_notify_resume + jmp resume_userspace + +#ifdef CONFIG_VM86 + ALIGN +work_notifysig_v86: + pushl %ecx # save ti_flags for do_notify_resume + call save_v86_state # %eax contains pt_regs pointer + popl %ecx + movl %eax, %esp + jmp 1b +#endif +END(work_pending) + + # perform syscall exit tracing + ALIGN +syscall_trace_entry: + movl $-ENOSYS,PT_EAX(%esp) + movl %esp, %eax + call syscall_trace_enter + /* What it returned is what we'll actually use. */ + cmpl $(NR_syscalls), %eax + jnae syscall_call + jmp syscall_exit +END(syscall_trace_entry) + + # perform syscall exit tracing + ALIGN +syscall_exit_work: + testl $_TIF_WORK_SYSCALL_EXIT, %ecx + jz work_pending + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_ANY) # could let syscall_trace_leave() call + # schedule() instead + movl %esp, %eax + call syscall_trace_leave + jmp resume_userspace +END(syscall_exit_work) + +syscall_fault: + ASM_CLAC + GET_THREAD_INFO(%ebp) + movl $-EFAULT,PT_EAX(%esp) + jmp resume_userspace +END(syscall_fault) + +syscall_badsys: + movl $-ENOSYS,%eax + jmp syscall_after_call +END(syscall_badsys) + +sysenter_badsys: + movl $-ENOSYS,%eax + jmp sysenter_after_call +END(sysenter_badsys) + +.macro FIXUP_ESPFIX_STACK +/* + * Switch back for ESPFIX stack to the normal zerobased stack + * + * We can't call C functions using the ESPFIX stack. This code reads + * the high word of the segment base from the GDT and swiches to the + * normal stack and adjusts ESP with the matching offset. + */ +#ifdef CONFIG_X86_ESPFIX32 + /* fixup the stack */ + mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ + mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ + shl $16, %eax + addl %esp, %eax /* the adjusted stack pointer */ + pushl $__KERNEL_DS + pushl %eax + lss (%esp), %esp /* switch to the normal stack segment */ +#endif +.endm +.macro UNWIND_ESPFIX_STACK +#ifdef CONFIG_X86_ESPFIX32 + movl %ss, %eax + /* see if on espfix stack */ + cmpw $__ESPFIX_SS, %ax + jne 27f + movl $__KERNEL_DS, %eax + movl %eax, %ds + movl %eax, %es + /* switch to normal stack */ + FIXUP_ESPFIX_STACK +27: +#endif +.endm + +/* + * Build the entry stubs with some assembler magic. + * We pack 1 stub into every 8-byte block. + */ + .align 8 +ENTRY(irq_entries_start) + vector=FIRST_EXTERNAL_VECTOR + .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) + pushl $(~vector+0x80) /* Note: always in signed byte range */ + vector=vector+1 + jmp common_interrupt + .align 8 + .endr +END(irq_entries_start) + +/* + * the CPU automatically disables interrupts when executing an IRQ vector, + * so IRQ-flags tracing has to follow that: + */ + .p2align CONFIG_X86_L1_CACHE_SHIFT +common_interrupt: + ASM_CLAC + addl $-0x80,(%esp) /* Adjust vector into the [-256,-1] range */ + SAVE_ALL + TRACE_IRQS_OFF + movl %esp,%eax + call do_IRQ + jmp ret_from_intr +ENDPROC(common_interrupt) + +#define BUILD_INTERRUPT3(name, nr, fn) \ +ENTRY(name) \ + ASM_CLAC; \ + pushl $~(nr); \ + SAVE_ALL; \ + TRACE_IRQS_OFF \ + movl %esp,%eax; \ + call fn; \ + jmp ret_from_intr; \ +ENDPROC(name) + + +#ifdef CONFIG_TRACING +#define TRACE_BUILD_INTERRUPT(name, nr) \ + BUILD_INTERRUPT3(trace_##name, nr, smp_trace_##name) +#else +#define TRACE_BUILD_INTERRUPT(name, nr) +#endif + +#define BUILD_INTERRUPT(name, nr) \ + BUILD_INTERRUPT3(name, nr, smp_##name); \ + TRACE_BUILD_INTERRUPT(name, nr) + +/* The include is where all of the SMP etc. interrupts come from */ +#include <asm/entry_arch.h> + +ENTRY(coprocessor_error) + ASM_CLAC + pushl $0 + pushl $do_coprocessor_error + jmp error_code +END(coprocessor_error) + +ENTRY(simd_coprocessor_error) + ASM_CLAC + pushl $0 +#ifdef CONFIG_X86_INVD_BUG + /* AMD 486 bug: invd from userspace calls exception 19 instead of #GP */ + ALTERNATIVE "pushl $do_general_protection", \ + "pushl $do_simd_coprocessor_error", \ + X86_FEATURE_XMM +#else + pushl $do_simd_coprocessor_error +#endif + jmp error_code +END(simd_coprocessor_error) + +ENTRY(device_not_available) + ASM_CLAC + pushl $-1 # mark this as an int + pushl $do_device_not_available + jmp error_code +END(device_not_available) + +#ifdef CONFIG_PARAVIRT +ENTRY(native_iret) + iret + _ASM_EXTABLE(native_iret, iret_exc) +END(native_iret) + +ENTRY(native_irq_enable_sysexit) + sti + sysexit +END(native_irq_enable_sysexit) +#endif + +ENTRY(overflow) + ASM_CLAC + pushl $0 + pushl $do_overflow + jmp error_code +END(overflow) + +ENTRY(bounds) + ASM_CLAC + pushl $0 + pushl $do_bounds + jmp error_code +END(bounds) + +ENTRY(invalid_op) + ASM_CLAC + pushl $0 + pushl $do_invalid_op + jmp error_code +END(invalid_op) + +ENTRY(coprocessor_segment_overrun) + ASM_CLAC + pushl $0 + pushl $do_coprocessor_segment_overrun + jmp error_code +END(coprocessor_segment_overrun) + +ENTRY(invalid_TSS) + ASM_CLAC + pushl $do_invalid_TSS + jmp error_code +END(invalid_TSS) + +ENTRY(segment_not_present) + ASM_CLAC + pushl $do_segment_not_present + jmp error_code +END(segment_not_present) + +ENTRY(stack_segment) + ASM_CLAC + pushl $do_stack_segment + jmp error_code +END(stack_segment) + +ENTRY(alignment_check) + ASM_CLAC + pushl $do_alignment_check + jmp error_code +END(alignment_check) + +ENTRY(divide_error) + ASM_CLAC + pushl $0 # no error code + pushl $do_divide_error + jmp error_code +END(divide_error) + +#ifdef CONFIG_X86_MCE +ENTRY(machine_check) + ASM_CLAC + pushl $0 + pushl machine_check_vector + jmp error_code +END(machine_check) +#endif + +ENTRY(spurious_interrupt_bug) + ASM_CLAC + pushl $0 + pushl $do_spurious_interrupt_bug + jmp error_code +END(spurious_interrupt_bug) + +#ifdef CONFIG_XEN +/* Xen doesn't set %esp to be precisely what the normal sysenter + entrypoint expects, so fix it up before using the normal path. */ +ENTRY(xen_sysenter_target) + addl $5*4, %esp /* remove xen-provided frame */ + jmp sysenter_past_esp + +ENTRY(xen_hypervisor_callback) + pushl $-1 /* orig_ax = -1 => not a system call */ + SAVE_ALL + TRACE_IRQS_OFF + + /* Check to see if we got the event in the critical + region in xen_iret_direct, after we've reenabled + events and checked for pending events. This simulates + iret instruction's behaviour where it delivers a + pending interrupt when enabling interrupts. */ + movl PT_EIP(%esp),%eax + cmpl $xen_iret_start_crit,%eax + jb 1f + cmpl $xen_iret_end_crit,%eax + jae 1f + + jmp xen_iret_crit_fixup + +ENTRY(xen_do_upcall) +1: mov %esp, %eax + call xen_evtchn_do_upcall +#ifndef CONFIG_PREEMPT + call xen_maybe_preempt_hcall +#endif + jmp ret_from_intr +ENDPROC(xen_hypervisor_callback) + +# Hypervisor uses this for application faults while it executes. +# We get here for two reasons: +# 1. Fault while reloading DS, ES, FS or GS +# 2. Fault while executing IRET +# Category 1 we fix up by reattempting the load, and zeroing the segment +# register if the load fails. +# Category 2 we fix up by jumping to do_iret_error. We cannot use the +# normal Linux return path in this case because if we use the IRET hypercall +# to pop the stack frame we end up in an infinite loop of failsafe callbacks. +# We distinguish between categories by maintaining a status value in EAX. +ENTRY(xen_failsafe_callback) + pushl %eax + movl $1,%eax +1: mov 4(%esp),%ds +2: mov 8(%esp),%es +3: mov 12(%esp),%fs +4: mov 16(%esp),%gs + /* EAX == 0 => Category 1 (Bad segment) + EAX != 0 => Category 2 (Bad IRET) */ + testl %eax,%eax + popl %eax + lea 16(%esp),%esp + jz 5f + jmp iret_exc +5: pushl $-1 /* orig_ax = -1 => not a system call */ + SAVE_ALL + jmp ret_from_exception + +.section .fixup,"ax" +6: xorl %eax,%eax + movl %eax,4(%esp) + jmp 1b +7: xorl %eax,%eax + movl %eax,8(%esp) + jmp 2b +8: xorl %eax,%eax + movl %eax,12(%esp) + jmp 3b +9: xorl %eax,%eax + movl %eax,16(%esp) + jmp 4b +.previous + _ASM_EXTABLE(1b,6b) + _ASM_EXTABLE(2b,7b) + _ASM_EXTABLE(3b,8b) + _ASM_EXTABLE(4b,9b) +ENDPROC(xen_failsafe_callback) + +BUILD_INTERRUPT3(xen_hvm_callback_vector, HYPERVISOR_CALLBACK_VECTOR, + xen_evtchn_do_upcall) + +#endif /* CONFIG_XEN */ + +#if IS_ENABLED(CONFIG_HYPERV) + +BUILD_INTERRUPT3(hyperv_callback_vector, HYPERVISOR_CALLBACK_VECTOR, + hyperv_vector_handler) + +#endif /* CONFIG_HYPERV */ + +#ifdef CONFIG_FUNCTION_TRACER +#ifdef CONFIG_DYNAMIC_FTRACE + +ENTRY(mcount) + ret +END(mcount) + +ENTRY(ftrace_caller) + pushl %eax + pushl %ecx + pushl %edx + pushl $0 /* Pass NULL as regs pointer */ + movl 4*4(%esp), %eax + movl 0x4(%ebp), %edx + movl function_trace_op, %ecx + subl $MCOUNT_INSN_SIZE, %eax + +.globl ftrace_call +ftrace_call: + call ftrace_stub + + addl $4,%esp /* skip NULL pointer */ + popl %edx + popl %ecx + popl %eax +ftrace_ret: +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +.globl ftrace_graph_call +ftrace_graph_call: + jmp ftrace_stub +#endif + +.globl ftrace_stub +ftrace_stub: + ret +END(ftrace_caller) + +ENTRY(ftrace_regs_caller) + pushf /* push flags before compare (in cs location) */ + + /* + * i386 does not save SS and ESP when coming from kernel. + * Instead, to get sp, ®s->sp is used (see ptrace.h). + * Unfortunately, that means eflags must be at the same location + * as the current return ip is. We move the return ip into the + * ip location, and move flags into the return ip location. + */ + pushl 4(%esp) /* save return ip into ip slot */ + + pushl $0 /* Load 0 into orig_ax */ + pushl %gs + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + + movl 13*4(%esp), %eax /* Get the saved flags */ + movl %eax, 14*4(%esp) /* Move saved flags into regs->flags location */ + /* clobbering return ip */ + movl $__KERNEL_CS,13*4(%esp) + + movl 12*4(%esp), %eax /* Load ip (1st parameter) */ + subl $MCOUNT_INSN_SIZE, %eax /* Adjust ip */ + movl 0x4(%ebp), %edx /* Load parent ip (2nd parameter) */ + movl function_trace_op, %ecx /* Save ftrace_pos in 3rd parameter */ + pushl %esp /* Save pt_regs as 4th parameter */ + +GLOBAL(ftrace_regs_call) + call ftrace_stub + + addl $4, %esp /* Skip pt_regs */ + movl 14*4(%esp), %eax /* Move flags back into cs */ + movl %eax, 13*4(%esp) /* Needed to keep addl from modifying flags */ + movl 12*4(%esp), %eax /* Get return ip from regs->ip */ + movl %eax, 14*4(%esp) /* Put return ip back for ret */ + + popl %ebx + popl %ecx + popl %edx + popl %esi + popl %edi + popl %ebp + popl %eax + popl %ds + popl %es + popl %fs + popl %gs + addl $8, %esp /* Skip orig_ax and ip */ + popf /* Pop flags at end (no addl to corrupt flags) */ + jmp ftrace_ret + + popf + jmp ftrace_stub +#else /* ! CONFIG_DYNAMIC_FTRACE */ + +ENTRY(mcount) + cmpl $__PAGE_OFFSET, %esp + jb ftrace_stub /* Paging not enabled yet? */ + + cmpl $ftrace_stub, ftrace_trace_function + jnz trace +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + cmpl $ftrace_stub, ftrace_graph_return + jnz ftrace_graph_caller + + cmpl $ftrace_graph_entry_stub, ftrace_graph_entry + jnz ftrace_graph_caller +#endif +.globl ftrace_stub +ftrace_stub: + ret + + /* taken from glibc */ +trace: + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + movl 0x4(%ebp), %edx + subl $MCOUNT_INSN_SIZE, %eax + + call *ftrace_trace_function + + popl %edx + popl %ecx + popl %eax + jmp ftrace_stub +END(mcount) +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FUNCTION_TRACER */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) + pushl %eax + pushl %ecx + pushl %edx + movl 0xc(%esp), %eax + lea 0x4(%ebp), %edx + movl (%ebp), %ecx + subl $MCOUNT_INSN_SIZE, %eax + call prepare_ftrace_return + popl %edx + popl %ecx + popl %eax + ret +END(ftrace_graph_caller) + +.globl return_to_handler +return_to_handler: + pushl %eax + pushl %edx + movl %ebp, %eax + call ftrace_return_to_handler + movl %eax, %ecx + popl %edx + popl %eax + jmp *%ecx +#endif + +#ifdef CONFIG_TRACING +ENTRY(trace_page_fault) + ASM_CLAC + pushl $trace_do_page_fault + jmp error_code +END(trace_page_fault) +#endif + +ENTRY(page_fault) + ASM_CLAC + pushl $do_page_fault + ALIGN +error_code: + /* the function address is in %gs's slot on the stack */ + pushl %fs + pushl %es + pushl %ds + pushl %eax + pushl %ebp + pushl %edi + pushl %esi + pushl %edx + pushl %ecx + pushl %ebx + cld + movl $(__KERNEL_PERCPU), %ecx + movl %ecx, %fs + UNWIND_ESPFIX_STACK + GS_TO_REG %ecx + movl PT_GS(%esp), %edi # get the function address + movl PT_ORIG_EAX(%esp), %edx # get the error code + movl $-1, PT_ORIG_EAX(%esp) # no syscall to restart + REG_TO_PTGS %ecx + SET_KERNEL_GS %ecx + movl $(__USER_DS), %ecx + movl %ecx, %ds + movl %ecx, %es + TRACE_IRQS_OFF + movl %esp,%eax # pt_regs pointer + call *%edi + jmp ret_from_exception +END(page_fault) + +/* + * Debug traps and NMI can happen at the one SYSENTER instruction + * that sets up the real kernel stack. Check here, since we can't + * allow the wrong stack to be used. + * + * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have + * already pushed 3 words if it hits on the sysenter instruction: + * eflags, cs and eip. + * + * We just load the right stack, and push the three (known) values + * by hand onto the new stack - while updating the return eip past + * the instruction that would have done it for sysenter. + */ +.macro FIX_STACK offset ok label + cmpw $__KERNEL_CS, 4(%esp) + jne \ok +\label: + movl TSS_sysenter_sp0 + \offset(%esp), %esp + pushfl + pushl $__KERNEL_CS + pushl $sysenter_past_esp +.endm + +ENTRY(debug) + ASM_CLAC + cmpl $ia32_sysenter_target,(%esp) + jne debug_stack_correct + FIX_STACK 12, debug_stack_correct, debug_esp_fix_insn +debug_stack_correct: + pushl $-1 # mark this as an int + SAVE_ALL + TRACE_IRQS_OFF + xorl %edx,%edx # error code 0 + movl %esp,%eax # pt_regs pointer + call do_debug + jmp ret_from_exception +END(debug) + +/* + * NMI is doubly nasty. It can happen _while_ we're handling + * a debug fault, and the debug fault hasn't yet been able to + * clear up the stack. So we first check whether we got an + * NMI on the sysenter entry path, but after that we need to + * check whether we got an NMI on the debug path where the debug + * fault happened on the sysenter path. + */ +ENTRY(nmi) + ASM_CLAC +#ifdef CONFIG_X86_ESPFIX32 + pushl %eax + movl %ss, %eax + cmpw $__ESPFIX_SS, %ax + popl %eax + je nmi_espfix_stack +#endif + cmpl $ia32_sysenter_target,(%esp) + je nmi_stack_fixup + pushl %eax + movl %esp,%eax + /* Do not access memory above the end of our stack page, + * it might not exist. + */ + andl $(THREAD_SIZE-1),%eax + cmpl $(THREAD_SIZE-20),%eax + popl %eax + jae nmi_stack_correct + cmpl $ia32_sysenter_target,12(%esp) + je nmi_debug_stack_check +nmi_stack_correct: + pushl %eax + SAVE_ALL + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_nmi + jmp restore_all_notrace + +nmi_stack_fixup: + FIX_STACK 12, nmi_stack_correct, 1 + jmp nmi_stack_correct + +nmi_debug_stack_check: + cmpw $__KERNEL_CS,16(%esp) + jne nmi_stack_correct + cmpl $debug,(%esp) + jb nmi_stack_correct + cmpl $debug_esp_fix_insn,(%esp) + ja nmi_stack_correct + FIX_STACK 24, nmi_stack_correct, 1 + jmp nmi_stack_correct + +#ifdef CONFIG_X86_ESPFIX32 +nmi_espfix_stack: + /* + * create the pointer to lss back + */ + pushl %ss + pushl %esp + addl $4, (%esp) + /* copy the iret frame of 12 bytes */ + .rept 3 + pushl 16(%esp) + .endr + pushl %eax + SAVE_ALL + FIXUP_ESPFIX_STACK # %eax == %esp + xorl %edx,%edx # zero error code + call do_nmi + RESTORE_REGS + lss 12+4(%esp), %esp # back to espfix stack + jmp irq_return +#endif +END(nmi) + +ENTRY(int3) + ASM_CLAC + pushl $-1 # mark this as an int + SAVE_ALL + TRACE_IRQS_OFF + xorl %edx,%edx # zero error code + movl %esp,%eax # pt_regs pointer + call do_int3 + jmp ret_from_exception +END(int3) + +ENTRY(general_protection) + pushl $do_general_protection + jmp error_code +END(general_protection) + +#ifdef CONFIG_KVM_GUEST +ENTRY(async_page_fault) + ASM_CLAC + pushl $do_async_page_fault + jmp error_code +END(async_page_fault) +#endif + diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S new file mode 100644 index 000000000000..4ad79e946f5a --- /dev/null +++ b/arch/x86/entry/entry_64.S @@ -0,0 +1,1442 @@ +/* + * linux/arch/x86_64/entry.S + * + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs + * Copyright (C) 2000 Pavel Machek <pavel@suse.cz> + */ + +/* + * entry.S contains the system-call and fault low-level handling routines. + * + * Some of this is documented in Documentation/x86/entry_64.txt + * + * NOTE: This code handles signal-recognition, which happens every time + * after an interrupt and after each system call. + * + * A note on terminology: + * - iret frame: Architecture defined interrupt frame from SS to RIP + * at the top of the kernel process stack. + * + * Some macro usage: + * - ENTRY/END Define functions in the symbol table. + * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging. + * - idtentry - Define exception entry points. + */ + +#include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/cache.h> +#include <asm/errno.h> +#include <asm/calling.h> +#include <asm/asm-offsets.h> +#include <asm/msr.h> +#include <asm/unistd.h> +#include <asm/thread_info.h> +#include <asm/hw_irq.h> +#include <asm/page_types.h> +#include <asm/irqflags.h> +#include <asm/paravirt.h> +#include <asm/percpu.h> +#include <asm/asm.h> +#include <asm/context_tracking.h> +#include <asm/smap.h> +#include <asm/pgtable_types.h> +#include <linux/err.h> + +/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ +#include <linux/elf-em.h> +#define AUDIT_ARCH_X86_64 (EM_X86_64|__AUDIT_ARCH_64BIT|__AUDIT_ARCH_LE) +#define __AUDIT_ARCH_64BIT 0x80000000 +#define __AUDIT_ARCH_LE 0x40000000 + + .code64 + .section .entry.text, "ax" + + +#ifdef CONFIG_PARAVIRT +ENTRY(native_usergs_sysret64) + swapgs + sysretq +ENDPROC(native_usergs_sysret64) +#endif /* CONFIG_PARAVIRT */ + + +.macro TRACE_IRQS_IRETQ +#ifdef CONFIG_TRACE_IRQFLAGS + bt $9,EFLAGS(%rsp) /* interrupts off? */ + jnc 1f + TRACE_IRQS_ON +1: +#endif +.endm + +/* + * When dynamic function tracer is enabled it will add a breakpoint + * to all locations that it is about to modify, sync CPUs, update + * all the code, sync CPUs, then remove the breakpoints. In this time + * if lockdep is enabled, it might jump back into the debug handler + * outside the updating of the IST protection. (TRACE_IRQS_ON/OFF). + * + * We need to change the IDT table before calling TRACE_IRQS_ON/OFF to + * make sure the stack pointer does not get reset back to the top + * of the debug stack, and instead just reuses the current stack. + */ +#if defined(CONFIG_DYNAMIC_FTRACE) && defined(CONFIG_TRACE_IRQFLAGS) + +.macro TRACE_IRQS_OFF_DEBUG + call debug_stack_set_zero + TRACE_IRQS_OFF + call debug_stack_reset +.endm + +.macro TRACE_IRQS_ON_DEBUG + call debug_stack_set_zero + TRACE_IRQS_ON + call debug_stack_reset +.endm + +.macro TRACE_IRQS_IRETQ_DEBUG + bt $9,EFLAGS(%rsp) /* interrupts off? */ + jnc 1f + TRACE_IRQS_ON_DEBUG +1: +.endm + +#else +# define TRACE_IRQS_OFF_DEBUG TRACE_IRQS_OFF +# define TRACE_IRQS_ON_DEBUG TRACE_IRQS_ON +# define TRACE_IRQS_IRETQ_DEBUG TRACE_IRQS_IRETQ +#endif + +/* + * 64bit SYSCALL instruction entry. Up to 6 arguments in registers. + * + * 64bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11, + * then loads new ss, cs, and rip from previously programmed MSRs. + * rflags gets masked by a value from another MSR (so CLD and CLAC + * are not needed). SYSCALL does not save anything on the stack + * and does not change rsp. + * + * Registers on entry: + * rax system call number + * rcx return address + * r11 saved rflags (note: r11 is callee-clobbered register in C ABI) + * rdi arg0 + * rsi arg1 + * rdx arg2 + * r10 arg3 (needs to be moved to rcx to conform to C ABI) + * r8 arg4 + * r9 arg5 + * (note: r12-r15,rbp,rbx are callee-preserved in C ABI) + * + * Only called from user space. + * + * When user can change pt_regs->foo always force IRET. That is because + * it deals with uncanonical addresses better. SYSRET has trouble + * with them due to bugs in both AMD and Intel CPUs. + */ + +ENTRY(system_call) + /* + * Interrupts are off on entry. + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. + */ + SWAPGS_UNSAFE_STACK + /* + * A hypervisor implementation might want to use a label + * after the swapgs, so that it can do the swapgs + * for the guest and jump here on syscall. + */ +GLOBAL(system_call_after_swapgs) + + movq %rsp,PER_CPU_VAR(rsp_scratch) + movq PER_CPU_VAR(cpu_current_top_of_stack),%rsp + + /* Construct struct pt_regs on stack */ + pushq $__USER_DS /* pt_regs->ss */ + pushq PER_CPU_VAR(rsp_scratch) /* pt_regs->sp */ + /* + * Re-enable interrupts. + * We use 'rsp_scratch' as a scratch space, hence irq-off block above + * must execute atomically in the face of possible interrupt-driven + * task preemption. We must enable interrupts only after we're done + * with using rsp_scratch: + */ + ENABLE_INTERRUPTS(CLBR_NONE) + pushq %r11 /* pt_regs->flags */ + pushq $__USER_CS /* pt_regs->cs */ + pushq %rcx /* pt_regs->ip */ + pushq %rax /* pt_regs->orig_ax */ + pushq %rdi /* pt_regs->di */ + pushq %rsi /* pt_regs->si */ + pushq %rdx /* pt_regs->dx */ + pushq %rcx /* pt_regs->cx */ + pushq $-ENOSYS /* pt_regs->ax */ + pushq %r8 /* pt_regs->r8 */ + pushq %r9 /* pt_regs->r9 */ + pushq %r10 /* pt_regs->r10 */ + pushq %r11 /* pt_regs->r11 */ + sub $(6*8),%rsp /* pt_regs->bp,bx,r12-15 not saved */ + + testl $_TIF_WORK_SYSCALL_ENTRY, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz tracesys +system_call_fastpath: +#if __SYSCALL_MASK == ~0 + cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif + ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + movq %r10,%rcx + call *sys_call_table(,%rax,8) + movq %rax,RAX(%rsp) +1: +/* + * Syscall return path ending with SYSRET (fast path). + * Has incompletely filled pt_regs. + */ + LOCKDEP_SYS_EXIT + /* + * We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON, + * it is too small to ever cause noticeable irq latency. + */ + DISABLE_INTERRUPTS(CLBR_NONE) + + /* + * We must check ti flags with interrupts (or at least preemption) + * off because we must *never* return to userspace without + * processing exit work that is enqueued if we're preempted here. + * In particular, returning to userspace with any of the one-shot + * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is + * very bad. + */ + testl $_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS) + jnz int_ret_from_sys_call_irqs_off /* Go to the slow path */ + + RESTORE_C_REGS_EXCEPT_RCX_R11 + movq RIP(%rsp),%rcx + movq EFLAGS(%rsp),%r11 + movq RSP(%rsp),%rsp + /* + * 64bit SYSRET restores rip from rcx, + * rflags from r11 (but RF and VM bits are forced to 0), + * cs and ss are loaded from MSRs. + * Restoration of rflags re-enables interrupts. + * + * NB: On AMD CPUs with the X86_BUG_SYSRET_SS_ATTRS bug, the ss + * descriptor is not reinitialized. This means that we should + * avoid SYSRET with SS == NULL, which could happen if we schedule, + * exit the kernel, and re-enter using an interrupt vector. (All + * interrupt entries on x86_64 set SS to NULL.) We prevent that + * from happening by reloading SS in __switch_to. (Actually + * detecting the failure in 64-bit userspace is tricky but can be + * done.) + */ + USERGS_SYSRET64 + + /* Do syscall entry tracing */ +tracesys: + movq %rsp, %rdi + movl $AUDIT_ARCH_X86_64, %esi + call syscall_trace_enter_phase1 + test %rax, %rax + jnz tracesys_phase2 /* if needed, run the slow path */ + RESTORE_C_REGS_EXCEPT_RAX /* else restore clobbered regs */ + movq ORIG_RAX(%rsp), %rax + jmp system_call_fastpath /* and return to the fast path */ + +tracesys_phase2: + SAVE_EXTRA_REGS + movq %rsp, %rdi + movl $AUDIT_ARCH_X86_64, %esi + movq %rax,%rdx + call syscall_trace_enter_phase2 + + /* + * Reload registers from stack in case ptrace changed them. + * We don't reload %rax because syscall_trace_entry_phase2() returned + * the value it wants us to use in the table lookup. + */ + RESTORE_C_REGS_EXCEPT_RAX + RESTORE_EXTRA_REGS +#if __SYSCALL_MASK == ~0 + cmpq $__NR_syscall_max,%rax +#else + andl $__SYSCALL_MASK,%eax + cmpl $__NR_syscall_max,%eax +#endif + ja 1f /* return -ENOSYS (already in pt_regs->ax) */ + movq %r10,%rcx /* fixup for C */ + call *sys_call_table(,%rax,8) + movq %rax,RAX(%rsp) +1: + /* Use IRET because user could have changed pt_regs->foo */ + +/* + * Syscall return path ending with IRET. + * Has correct iret frame. + */ +GLOBAL(int_ret_from_sys_call) + DISABLE_INTERRUPTS(CLBR_NONE) +int_ret_from_sys_call_irqs_off: /* jumps come here from the irqs-off SYSRET path */ + TRACE_IRQS_OFF + movl $_TIF_ALLWORK_MASK,%edi + /* edi: mask to check */ +GLOBAL(int_with_check) + LOCKDEP_SYS_EXIT_IRQ + GET_THREAD_INFO(%rcx) + movl TI_flags(%rcx),%edx + andl %edi,%edx + jnz int_careful + andl $~TS_COMPAT,TI_status(%rcx) + jmp syscall_return + + /* Either reschedule or signal or syscall exit tracking needed. */ + /* First do a reschedule test. */ + /* edx: work, edi: workmask */ +int_careful: + bt $TIF_NEED_RESCHED,%edx + jnc int_very_careful + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + pushq %rdi + SCHEDULE_USER + popq %rdi + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + jmp int_with_check + + /* handle signals and tracing -- both require a full pt_regs */ +int_very_careful: + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + SAVE_EXTRA_REGS + /* Check for syscall exit trace */ + testl $_TIF_WORK_SYSCALL_EXIT,%edx + jz int_signal + pushq %rdi + leaq 8(%rsp),%rdi # &ptregs -> arg1 + call syscall_trace_leave + popq %rdi + andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi + jmp int_restore_rest + +int_signal: + testl $_TIF_DO_NOTIFY_MASK,%edx + jz 1f + movq %rsp,%rdi # &ptregs -> arg1 + xorl %esi,%esi # oldset -> arg2 + call do_notify_resume +1: movl $_TIF_WORK_MASK,%edi +int_restore_rest: + RESTORE_EXTRA_REGS + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + jmp int_with_check + +syscall_return: + /* The IRETQ could re-enable interrupts: */ + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_IRETQ + + /* + * Try to use SYSRET instead of IRET if we're returning to + * a completely clean 64-bit userspace context. + */ + movq RCX(%rsp),%rcx + movq RIP(%rsp),%r11 + cmpq %rcx,%r11 /* RCX == RIP */ + jne opportunistic_sysret_failed + + /* + * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP + * in kernel space. This essentially lets the user take over + * the kernel, since userspace controls RSP. + * + * If width of "canonical tail" ever becomes variable, this will need + * to be updated to remain correct on both old and new CPUs. + */ + .ifne __VIRTUAL_MASK_SHIFT - 47 + .error "virtual address width changed -- SYSRET checks need update" + .endif + /* Change top 16 bits to be the sign-extension of 47th bit */ + shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx + sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx + /* If this changed %rcx, it was not canonical */ + cmpq %rcx, %r11 + jne opportunistic_sysret_failed + + cmpq $__USER_CS,CS(%rsp) /* CS must match SYSRET */ + jne opportunistic_sysret_failed + + movq R11(%rsp),%r11 + cmpq %r11,EFLAGS(%rsp) /* R11 == RFLAGS */ + jne opportunistic_sysret_failed + + /* + * SYSRET can't restore RF. SYSRET can restore TF, but unlike IRET, + * restoring TF results in a trap from userspace immediately after + * SYSRET. This would cause an infinite loop whenever #DB happens + * with register state that satisfies the opportunistic SYSRET + * conditions. For example, single-stepping this user code: + * + * movq $stuck_here,%rcx + * pushfq + * popq %r11 + * stuck_here: + * + * would never get past 'stuck_here'. + */ + testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 + jnz opportunistic_sysret_failed + + /* nothing to check for RSP */ + + cmpq $__USER_DS,SS(%rsp) /* SS must match SYSRET */ + jne opportunistic_sysret_failed + + /* + * We win! This label is here just for ease of understanding + * perf profiles. Nothing jumps here. + */ +syscall_return_via_sysret: + /* rcx and r11 are already restored (see code above) */ + RESTORE_C_REGS_EXCEPT_RCX_R11 + movq RSP(%rsp),%rsp + USERGS_SYSRET64 + +opportunistic_sysret_failed: + SWAPGS + jmp restore_c_regs_and_iret +END(system_call) + + + .macro FORK_LIKE func +ENTRY(stub_\func) + SAVE_EXTRA_REGS 8 + jmp sys_\func +END(stub_\func) + .endm + + FORK_LIKE clone + FORK_LIKE fork + FORK_LIKE vfork + +ENTRY(stub_execve) + call sys_execve +return_from_execve: + testl %eax, %eax + jz 1f + /* exec failed, can use fast SYSRET code path in this case */ + ret +1: + /* must use IRET code path (pt_regs->cs may have changed) */ + addq $8, %rsp + ZERO_EXTRA_REGS + movq %rax,RAX(%rsp) + jmp int_ret_from_sys_call +END(stub_execve) +/* + * Remaining execve stubs are only 7 bytes long. + * ENTRY() often aligns to 16 bytes, which in this case has no benefits. + */ + .align 8 +GLOBAL(stub_execveat) + call sys_execveat + jmp return_from_execve +END(stub_execveat) + +#if defined(CONFIG_X86_X32_ABI) || defined(CONFIG_IA32_EMULATION) + .align 8 +GLOBAL(stub_x32_execve) +GLOBAL(stub32_execve) + call compat_sys_execve + jmp return_from_execve +END(stub32_execve) +END(stub_x32_execve) + .align 8 +GLOBAL(stub_x32_execveat) +GLOBAL(stub32_execveat) + call compat_sys_execveat + jmp return_from_execve +END(stub32_execveat) +END(stub_x32_execveat) +#endif + +/* + * sigreturn is special because it needs to restore all registers on return. + * This cannot be done with SYSRET, so use the IRET return path instead. + */ +ENTRY(stub_rt_sigreturn) + /* + * SAVE_EXTRA_REGS result is not normally needed: + * sigreturn overwrites all pt_regs->GPREGS. + * But sigreturn can fail (!), and there is no easy way to detect that. + * To make sure RESTORE_EXTRA_REGS doesn't restore garbage on error, + * we SAVE_EXTRA_REGS here. + */ + SAVE_EXTRA_REGS 8 + call sys_rt_sigreturn +return_from_stub: + addq $8, %rsp + RESTORE_EXTRA_REGS + movq %rax,RAX(%rsp) + jmp int_ret_from_sys_call +END(stub_rt_sigreturn) + +#ifdef CONFIG_X86_X32_ABI +ENTRY(stub_x32_rt_sigreturn) + SAVE_EXTRA_REGS 8 + call sys32_x32_rt_sigreturn + jmp return_from_stub +END(stub_x32_rt_sigreturn) +#endif + +/* + * A newly forked process directly context switches into this address. + * + * rdi: prev task we switched from + */ +ENTRY(ret_from_fork) + + LOCK ; btr $TIF_FORK,TI_flags(%r8) + + pushq $0x0002 + popfq # reset kernel eflags + + call schedule_tail # rdi: 'prev' task parameter + + RESTORE_EXTRA_REGS + + testb $3, CS(%rsp) # from kernel_thread? + + /* + * By the time we get here, we have no idea whether our pt_regs, + * ti flags, and ti status came from the 64-bit SYSCALL fast path, + * the slow path, or one of the ia32entry paths. + * Use IRET code path to return, since it can safely handle + * all of the above. + */ + jnz int_ret_from_sys_call + + /* We came from kernel_thread */ + /* nb: we depend on RESTORE_EXTRA_REGS above */ + movq %rbp, %rdi + call *%rbx + movl $0, RAX(%rsp) + RESTORE_EXTRA_REGS + jmp int_ret_from_sys_call +END(ret_from_fork) + +/* + * Build the entry stubs with some assembler magic. + * We pack 1 stub into every 8-byte block. + */ + .align 8 +ENTRY(irq_entries_start) + vector=FIRST_EXTERNAL_VECTOR + .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) + pushq $(~vector+0x80) /* Note: always in signed byte range */ + vector=vector+1 + jmp common_interrupt + .align 8 + .endr +END(irq_entries_start) + +/* + * Interrupt entry/exit. + * + * Interrupt entry points save only callee clobbered registers in fast path. + * + * Entry runs with interrupts off. + */ + +/* 0(%rsp): ~(interrupt number) */ + .macro interrupt func + cld + /* + * Since nothing in interrupt handling code touches r12...r15 members + * of "struct pt_regs", and since interrupts can nest, we can save + * four stack slots and simultaneously provide + * an unwind-friendly stack layout by saving "truncated" pt_regs + * exactly up to rbp slot, without these members. + */ + ALLOC_PT_GPREGS_ON_STACK -RBP + SAVE_C_REGS -RBP + /* this goes to 0(%rsp) for unwinder, not for saving the value: */ + SAVE_EXTRA_REGS_RBP -RBP + + leaq -RBP(%rsp),%rdi /* arg1 for \func (pointer to pt_regs) */ + + testb $3, CS-RBP(%rsp) + jz 1f + SWAPGS +1: + /* + * Save previous stack pointer, optionally switch to interrupt stack. + * irq_count is used to check if a CPU is already on an interrupt stack + * or not. While this is essentially redundant with preempt_count it is + * a little cheaper to use a separate counter in the PDA (short of + * moving irq_enter into assembly, which would be too much work) + */ + movq %rsp, %rsi + incl PER_CPU_VAR(irq_count) + cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp + pushq %rsi + /* We entered an interrupt context - irqs are off: */ + TRACE_IRQS_OFF + + call \func + .endm + + /* + * The interrupt stubs push (~vector+0x80) onto the stack and + * then jump to common_interrupt. + */ + .p2align CONFIG_X86_L1_CACHE_SHIFT +common_interrupt: + ASM_CLAC + addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */ + interrupt do_IRQ + /* 0(%rsp): old RSP */ +ret_from_intr: + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + decl PER_CPU_VAR(irq_count) + + /* Restore saved previous stack */ + popq %rsi + /* return code expects complete pt_regs - adjust rsp accordingly: */ + leaq -RBP(%rsi),%rsp + + testb $3, CS(%rsp) + jz retint_kernel + /* Interrupt came from user space */ +retint_user: + GET_THREAD_INFO(%rcx) + /* + * %rcx: thread info. Interrupts off. + */ +retint_with_reschedule: + movl $_TIF_WORK_MASK,%edi +retint_check: + LOCKDEP_SYS_EXIT_IRQ + movl TI_flags(%rcx),%edx + andl %edi,%edx + jnz retint_careful + +retint_swapgs: /* return to user-space */ + /* + * The iretq could re-enable interrupts: + */ + DISABLE_INTERRUPTS(CLBR_ANY) + TRACE_IRQS_IRETQ + + SWAPGS + jmp restore_c_regs_and_iret + +/* Returning to kernel space */ +retint_kernel: +#ifdef CONFIG_PREEMPT + /* Interrupts are off */ + /* Check if we need preemption */ + bt $9,EFLAGS(%rsp) /* interrupts were off? */ + jnc 1f +0: cmpl $0,PER_CPU_VAR(__preempt_count) + jnz 1f + call preempt_schedule_irq + jmp 0b +1: +#endif + /* + * The iretq could re-enable interrupts: + */ + TRACE_IRQS_IRETQ + +/* + * At this label, code paths which return to kernel and to user, + * which come from interrupts/exception and from syscalls, merge. + */ +restore_c_regs_and_iret: + RESTORE_C_REGS + REMOVE_PT_GPREGS_FROM_STACK 8 + +irq_return: + INTERRUPT_RETURN + +ENTRY(native_iret) + /* + * Are we returning to a stack segment from the LDT? Note: in + * 64-bit mode SS:RSP on the exception stack is always valid. + */ +#ifdef CONFIG_X86_ESPFIX64 + testb $4,(SS-RIP)(%rsp) + jnz native_irq_return_ldt +#endif + +.global native_irq_return_iret +native_irq_return_iret: + /* + * This may fault. Non-paranoid faults on return to userspace are + * handled by fixup_bad_iret. These include #SS, #GP, and #NP. + * Double-faults due to espfix64 are handled in do_double_fault. + * Other faults here are fatal. + */ + iretq + +#ifdef CONFIG_X86_ESPFIX64 +native_irq_return_ldt: + pushq %rax + pushq %rdi + SWAPGS + movq PER_CPU_VAR(espfix_waddr),%rdi + movq %rax,(0*8)(%rdi) /* RAX */ + movq (2*8)(%rsp),%rax /* RIP */ + movq %rax,(1*8)(%rdi) + movq (3*8)(%rsp),%rax /* CS */ + movq %rax,(2*8)(%rdi) + movq (4*8)(%rsp),%rax /* RFLAGS */ + movq %rax,(3*8)(%rdi) + movq (6*8)(%rsp),%rax /* SS */ + movq %rax,(5*8)(%rdi) + movq (5*8)(%rsp),%rax /* RSP */ + movq %rax,(4*8)(%rdi) + andl $0xffff0000,%eax + popq %rdi + orq PER_CPU_VAR(espfix_stack),%rax + SWAPGS + movq %rax,%rsp + popq %rax + jmp native_irq_return_iret +#endif + + /* edi: workmask, edx: work */ +retint_careful: + bt $TIF_NEED_RESCHED,%edx + jnc retint_signal + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + pushq %rdi + SCHEDULE_USER + popq %rdi + GET_THREAD_INFO(%rcx) + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + jmp retint_check + +retint_signal: + testl $_TIF_DO_NOTIFY_MASK,%edx + jz retint_swapgs + TRACE_IRQS_ON + ENABLE_INTERRUPTS(CLBR_NONE) + SAVE_EXTRA_REGS + movq $-1,ORIG_RAX(%rsp) + xorl %esi,%esi # oldset + movq %rsp,%rdi # &pt_regs + call do_notify_resume + RESTORE_EXTRA_REGS + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + GET_THREAD_INFO(%rcx) + jmp retint_with_reschedule + +END(common_interrupt) + +/* + * APIC interrupts. + */ +.macro apicinterrupt3 num sym do_sym +ENTRY(\sym) + ASM_CLAC + pushq $~(\num) +.Lcommon_\sym: + interrupt \do_sym + jmp ret_from_intr +END(\sym) +.endm + +#ifdef CONFIG_TRACING +#define trace(sym) trace_##sym +#define smp_trace(sym) smp_trace_##sym + +.macro trace_apicinterrupt num sym +apicinterrupt3 \num trace(\sym) smp_trace(\sym) +.endm +#else +.macro trace_apicinterrupt num sym do_sym +.endm +#endif + +.macro apicinterrupt num sym do_sym +apicinterrupt3 \num \sym \do_sym +trace_apicinterrupt \num \sym +.endm + +#ifdef CONFIG_SMP +apicinterrupt3 IRQ_MOVE_CLEANUP_VECTOR \ + irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt +apicinterrupt3 REBOOT_VECTOR \ + reboot_interrupt smp_reboot_interrupt +#endif + +#ifdef CONFIG_X86_UV +apicinterrupt3 UV_BAU_MESSAGE \ + uv_bau_message_intr1 uv_bau_message_interrupt +#endif +apicinterrupt LOCAL_TIMER_VECTOR \ + apic_timer_interrupt smp_apic_timer_interrupt +apicinterrupt X86_PLATFORM_IPI_VECTOR \ + x86_platform_ipi smp_x86_platform_ipi + +#ifdef CONFIG_HAVE_KVM +apicinterrupt3 POSTED_INTR_VECTOR \ + kvm_posted_intr_ipi smp_kvm_posted_intr_ipi +#endif + +#ifdef CONFIG_X86_MCE_THRESHOLD +apicinterrupt THRESHOLD_APIC_VECTOR \ + threshold_interrupt smp_threshold_interrupt +#endif + +#ifdef CONFIG_X86_THERMAL_VECTOR +apicinterrupt THERMAL_APIC_VECTOR \ + thermal_interrupt smp_thermal_interrupt +#endif + +#ifdef CONFIG_SMP +apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \ + call_function_single_interrupt smp_call_function_single_interrupt +apicinterrupt CALL_FUNCTION_VECTOR \ + call_function_interrupt smp_call_function_interrupt +apicinterrupt RESCHEDULE_VECTOR \ + reschedule_interrupt smp_reschedule_interrupt +#endif + +apicinterrupt ERROR_APIC_VECTOR \ + error_interrupt smp_error_interrupt +apicinterrupt SPURIOUS_APIC_VECTOR \ + spurious_interrupt smp_spurious_interrupt + +#ifdef CONFIG_IRQ_WORK +apicinterrupt IRQ_WORK_VECTOR \ + irq_work_interrupt smp_irq_work_interrupt +#endif + +/* + * Exception entry points. + */ +#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8) + +.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 +ENTRY(\sym) + /* Sanity check */ + .if \shift_ist != -1 && \paranoid == 0 + .error "using shift_ist requires paranoid=1" + .endif + + ASM_CLAC + PARAVIRT_ADJUST_EXCEPTION_FRAME + + .ifeq \has_error_code + pushq $-1 /* ORIG_RAX: no syscall to restart */ + .endif + + ALLOC_PT_GPREGS_ON_STACK + + .if \paranoid + .if \paranoid == 1 + testb $3, CS(%rsp) /* If coming from userspace, switch */ + jnz 1f /* stacks. */ + .endif + call paranoid_entry + .else + call error_entry + .endif + /* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */ + + .if \paranoid + .if \shift_ist != -1 + TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ + .else + TRACE_IRQS_OFF + .endif + .endif + + movq %rsp,%rdi /* pt_regs pointer */ + + .if \has_error_code + movq ORIG_RAX(%rsp),%rsi /* get error code */ + movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + .else + xorl %esi,%esi /* no error code */ + .endif + + .if \shift_ist != -1 + subq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + .endif + + call \do_sym + + .if \shift_ist != -1 + addq $EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist) + .endif + + /* these procedures expect "no swapgs" flag in ebx */ + .if \paranoid + jmp paranoid_exit + .else + jmp error_exit + .endif + + .if \paranoid == 1 + /* + * Paranoid entry from userspace. Switch stacks and treat it + * as a normal entry. This means that paranoid handlers + * run in real process context if user_mode(regs). + */ +1: + call error_entry + + + movq %rsp,%rdi /* pt_regs pointer */ + call sync_regs + movq %rax,%rsp /* switch stack */ + + movq %rsp,%rdi /* pt_regs pointer */ + + .if \has_error_code + movq ORIG_RAX(%rsp),%rsi /* get error code */ + movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + .else + xorl %esi,%esi /* no error code */ + .endif + + call \do_sym + + jmp error_exit /* %ebx: no swapgs flag */ + .endif +END(\sym) +.endm + +#ifdef CONFIG_TRACING +.macro trace_idtentry sym do_sym has_error_code:req +idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code +idtentry \sym \do_sym has_error_code=\has_error_code +.endm +#else +.macro trace_idtentry sym do_sym has_error_code:req +idtentry \sym \do_sym has_error_code=\has_error_code +.endm +#endif + +idtentry divide_error do_divide_error has_error_code=0 +idtentry overflow do_overflow has_error_code=0 +idtentry bounds do_bounds has_error_code=0 +idtentry invalid_op do_invalid_op has_error_code=0 +idtentry device_not_available do_device_not_available has_error_code=0 +idtentry double_fault do_double_fault has_error_code=1 paranoid=2 +idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 +idtentry invalid_TSS do_invalid_TSS has_error_code=1 +idtentry segment_not_present do_segment_not_present has_error_code=1 +idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0 +idtentry coprocessor_error do_coprocessor_error has_error_code=0 +idtentry alignment_check do_alignment_check has_error_code=1 +idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 + + + /* Reload gs selector with exception handling */ + /* edi: new selector */ +ENTRY(native_load_gs_index) + pushfq + DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI) + SWAPGS +gs_change: + movl %edi,%gs +2: mfence /* workaround */ + SWAPGS + popfq + ret +END(native_load_gs_index) + + _ASM_EXTABLE(gs_change,bad_gs) + .section .fixup,"ax" + /* running with kernelgs */ +bad_gs: + SWAPGS /* switch back to user gs */ + xorl %eax,%eax + movl %eax,%gs + jmp 2b + .previous + +/* Call softirq on interrupt stack. Interrupts are off. */ +ENTRY(do_softirq_own_stack) + pushq %rbp + mov %rsp,%rbp + incl PER_CPU_VAR(irq_count) + cmove PER_CPU_VAR(irq_stack_ptr),%rsp + push %rbp # backlink for old unwinder + call __do_softirq + leaveq + decl PER_CPU_VAR(irq_count) + ret +END(do_softirq_own_stack) + +#ifdef CONFIG_XEN +idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 + +/* + * A note on the "critical region" in our callback handler. + * We want to avoid stacking callback handlers due to events occurring + * during handling of the last event. To do this, we keep events disabled + * until we've done all processing. HOWEVER, we must enable events before + * popping the stack frame (can't be done atomically) and so it would still + * be possible to get enough handler activations to overflow the stack. + * Although unlikely, bugs of that kind are hard to track down, so we'd + * like to avoid the possibility. + * So, on entry to the handler we detect whether we interrupted an + * existing activation in its critical region -- if so, we pop the current + * activation and restart the handler using the previous one. + */ +ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs) +/* + * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will + * see the correct pointer to the pt_regs + */ + movq %rdi, %rsp # we don't return, adjust the stack frame +11: incl PER_CPU_VAR(irq_count) + movq %rsp,%rbp + cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp + pushq %rbp # backlink for old unwinder + call xen_evtchn_do_upcall + popq %rsp + decl PER_CPU_VAR(irq_count) +#ifndef CONFIG_PREEMPT + call xen_maybe_preempt_hcall +#endif + jmp error_exit +END(xen_do_hypervisor_callback) + +/* + * Hypervisor uses this for application faults while it executes. + * We get here for two reasons: + * 1. Fault while reloading DS, ES, FS or GS + * 2. Fault while executing IRET + * Category 1 we do not need to fix up as Xen has already reloaded all segment + * registers that could be reloaded and zeroed the others. + * Category 2 we fix up by killing the current process. We cannot use the + * normal Linux return path in this case because if we use the IRET hypercall + * to pop the stack frame we end up in an infinite loop of failsafe callbacks. + * We distinguish between categories by comparing each saved segment register + * with its current contents: any discrepancy means we in category 1. + */ +ENTRY(xen_failsafe_callback) + movl %ds,%ecx + cmpw %cx,0x10(%rsp) + jne 1f + movl %es,%ecx + cmpw %cx,0x18(%rsp) + jne 1f + movl %fs,%ecx + cmpw %cx,0x20(%rsp) + jne 1f + movl %gs,%ecx + cmpw %cx,0x28(%rsp) + jne 1f + /* All segments match their saved values => Category 2 (Bad IRET). */ + movq (%rsp),%rcx + movq 8(%rsp),%r11 + addq $0x30,%rsp + pushq $0 /* RIP */ + pushq %r11 + pushq %rcx + jmp general_protection +1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */ + movq (%rsp),%rcx + movq 8(%rsp),%r11 + addq $0x30,%rsp + pushq $-1 /* orig_ax = -1 => not a system call */ + ALLOC_PT_GPREGS_ON_STACK + SAVE_C_REGS + SAVE_EXTRA_REGS + jmp error_exit +END(xen_failsafe_callback) + +apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ + xen_hvm_callback_vector xen_evtchn_do_upcall + +#endif /* CONFIG_XEN */ + +#if IS_ENABLED(CONFIG_HYPERV) +apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ + hyperv_callback_vector hyperv_vector_handler +#endif /* CONFIG_HYPERV */ + +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry stack_segment do_stack_segment has_error_code=1 +#ifdef CONFIG_XEN +idtentry xen_debug do_debug has_error_code=0 +idtentry xen_int3 do_int3 has_error_code=0 +idtentry xen_stack_segment do_stack_segment has_error_code=1 +#endif +idtentry general_protection do_general_protection has_error_code=1 +trace_idtentry page_fault do_page_fault has_error_code=1 +#ifdef CONFIG_KVM_GUEST +idtentry async_page_fault do_async_page_fault has_error_code=1 +#endif +#ifdef CONFIG_X86_MCE +idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) +#endif + +/* + * Save all registers in pt_regs, and switch gs if needed. + * Use slow, but surefire "are we in kernel?" check. + * Return: ebx=0: need swapgs on exit, ebx=1: otherwise + */ +ENTRY(paranoid_entry) + cld + SAVE_C_REGS 8 + SAVE_EXTRA_REGS 8 + movl $1,%ebx + movl $MSR_GS_BASE,%ecx + rdmsr + testl %edx,%edx + js 1f /* negative -> in kernel */ + SWAPGS + xorl %ebx,%ebx +1: ret +END(paranoid_entry) + +/* + * "Paranoid" exit path from exception stack. This is invoked + * only on return from non-NMI IST interrupts that came + * from kernel space. + * + * We may be returning to very strange contexts (e.g. very early + * in syscall entry), so checking for preemption here would + * be complicated. Fortunately, we there's no good reason + * to try to handle preemption here. + */ +/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ +ENTRY(paranoid_exit) + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF_DEBUG + testl %ebx,%ebx /* swapgs needed? */ + jnz paranoid_exit_no_swapgs + TRACE_IRQS_IRETQ + SWAPGS_UNSAFE_STACK + jmp paranoid_exit_restore +paranoid_exit_no_swapgs: + TRACE_IRQS_IRETQ_DEBUG +paranoid_exit_restore: + RESTORE_EXTRA_REGS + RESTORE_C_REGS + REMOVE_PT_GPREGS_FROM_STACK 8 + INTERRUPT_RETURN +END(paranoid_exit) + +/* + * Save all registers in pt_regs, and switch gs if needed. + * Return: ebx=0: need swapgs on exit, ebx=1: otherwise + */ +ENTRY(error_entry) + cld + SAVE_C_REGS 8 + SAVE_EXTRA_REGS 8 + xorl %ebx,%ebx + testb $3, CS+8(%rsp) + jz error_kernelspace +error_swapgs: + SWAPGS +error_sti: + TRACE_IRQS_OFF + ret + + /* + * There are two places in the kernel that can potentially fault with + * usergs. Handle them here. B stepping K8s sometimes report a + * truncated RIP for IRET exceptions returning to compat mode. Check + * for these here too. + */ +error_kernelspace: + incl %ebx + leaq native_irq_return_iret(%rip),%rcx + cmpq %rcx,RIP+8(%rsp) + je error_bad_iret + movl %ecx,%eax /* zero extend */ + cmpq %rax,RIP+8(%rsp) + je bstep_iret + cmpq $gs_change,RIP+8(%rsp) + je error_swapgs + jmp error_sti + +bstep_iret: + /* Fix truncated RIP */ + movq %rcx,RIP+8(%rsp) + /* fall through */ + +error_bad_iret: + SWAPGS + mov %rsp,%rdi + call fixup_bad_iret + mov %rax,%rsp + decl %ebx /* Return to usergs */ + jmp error_sti +END(error_entry) + + +/* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it) */ +ENTRY(error_exit) + movl %ebx,%eax + RESTORE_EXTRA_REGS + DISABLE_INTERRUPTS(CLBR_NONE) + TRACE_IRQS_OFF + testl %eax,%eax + jnz retint_kernel + jmp retint_user +END(error_exit) + +/* Runs on exception stack */ +ENTRY(nmi) + PARAVIRT_ADJUST_EXCEPTION_FRAME + /* + * We allow breakpoints in NMIs. If a breakpoint occurs, then + * the iretq it performs will take us out of NMI context. + * This means that we can have nested NMIs where the next + * NMI is using the top of the stack of the previous NMI. We + * can't let it execute because the nested NMI will corrupt the + * stack of the previous NMI. NMI handlers are not re-entrant + * anyway. + * + * To handle this case we do the following: + * Check the a special location on the stack that contains + * a variable that is set when NMIs are executing. + * The interrupted task's stack is also checked to see if it + * is an NMI stack. + * If the variable is not set and the stack is not the NMI + * stack then: + * o Set the special variable on the stack + * o Copy the interrupt frame into a "saved" location on the stack + * o Copy the interrupt frame into a "copy" location on the stack + * o Continue processing the NMI + * If the variable is set or the previous stack is the NMI stack: + * o Modify the "copy" location to jump to the repeate_nmi + * o return back to the first NMI + * + * Now on exit of the first NMI, we first clear the stack variable + * The NMI stack will tell any nested NMIs at that point that it is + * nested. Then we pop the stack normally with iret, and if there was + * a nested NMI that updated the copy interrupt stack frame, a + * jump will be made to the repeat_nmi code that will handle the second + * NMI. + */ + + /* Use %rdx as our temp variable throughout */ + pushq %rdx + + /* + * If %cs was not the kernel segment, then the NMI triggered in user + * space, which means it is definitely not nested. + */ + cmpl $__KERNEL_CS, 16(%rsp) + jne first_nmi + + /* + * Check the special variable on the stack to see if NMIs are + * executing. + */ + cmpl $1, -8(%rsp) + je nested_nmi + + /* + * Now test if the previous stack was an NMI stack. + * We need the double check. We check the NMI stack to satisfy the + * race when the first NMI clears the variable before returning. + * We check the variable because the first NMI could be in a + * breakpoint routine using a breakpoint stack. + */ + lea 6*8(%rsp), %rdx + /* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */ + cmpq %rdx, 4*8(%rsp) + /* If the stack pointer is above the NMI stack, this is a normal NMI */ + ja first_nmi + subq $EXCEPTION_STKSZ, %rdx + cmpq %rdx, 4*8(%rsp) + /* If it is below the NMI stack, it is a normal NMI */ + jb first_nmi + /* Ah, it is within the NMI stack, treat it as nested */ + +nested_nmi: + /* + * Do nothing if we interrupted the fixup in repeat_nmi. + * It's about to repeat the NMI handler, so we are fine + * with ignoring this one. + */ + movq $repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja 1f + movq $end_repeat_nmi, %rdx + cmpq 8(%rsp), %rdx + ja nested_nmi_out + +1: + /* Set up the interrupted NMIs stack to jump to repeat_nmi */ + leaq -1*8(%rsp), %rdx + movq %rdx, %rsp + leaq -10*8(%rsp), %rdx + pushq $__KERNEL_DS + pushq %rdx + pushfq + pushq $__KERNEL_CS + pushq $repeat_nmi + + /* Put stack back */ + addq $(6*8), %rsp + +nested_nmi_out: + popq %rdx + + /* No need to check faults here */ + INTERRUPT_RETURN + +first_nmi: + /* + * Because nested NMIs will use the pushed location that we + * stored in rdx, we must keep that space available. + * Here's what our stack frame will look like: + * +-------------------------+ + * | original SS | + * | original Return RSP | + * | original RFLAGS | + * | original CS | + * | original RIP | + * +-------------------------+ + * | temp storage for rdx | + * +-------------------------+ + * | NMI executing variable | + * +-------------------------+ + * | copied SS | + * | copied Return RSP | + * | copied RFLAGS | + * | copied CS | + * | copied RIP | + * +-------------------------+ + * | Saved SS | + * | Saved Return RSP | + * | Saved RFLAGS | + * | Saved CS | + * | Saved RIP | + * +-------------------------+ + * | pt_regs | + * +-------------------------+ + * + * The saved stack frame is used to fix up the copied stack frame + * that a nested NMI may change to make the interrupted NMI iret jump + * to the repeat_nmi. The original stack frame and the temp storage + * is also used by nested NMIs and can not be trusted on exit. + */ + /* Do not pop rdx, nested NMIs will corrupt that part of the stack */ + movq (%rsp), %rdx + + /* Set the NMI executing variable on the stack. */ + pushq $1 + + /* + * Leave room for the "copied" frame + */ + subq $(5*8), %rsp + + /* Copy the stack frame to the Saved frame */ + .rept 5 + pushq 11*8(%rsp) + .endr + + /* Everything up to here is safe from nested NMIs */ + + /* + * If there was a nested NMI, the first NMI's iret will return + * here. But NMIs are still enabled and we can take another + * nested NMI. The nested NMI checks the interrupted RIP to see + * if it is between repeat_nmi and end_repeat_nmi, and if so + * it will just return, as we are about to repeat an NMI anyway. + * This makes it safe to copy to the stack frame that a nested + * NMI will update. + */ +repeat_nmi: + /* + * Update the stack variable to say we are still in NMI (the update + * is benign for the non-repeat case, where 1 was pushed just above + * to this very stack slot). + */ + movq $1, 10*8(%rsp) + + /* Make another copy, this one may be modified by nested NMIs */ + addq $(10*8), %rsp + .rept 5 + pushq -6*8(%rsp) + .endr + subq $(5*8), %rsp +end_repeat_nmi: + + /* + * Everything below this point can be preempted by a nested + * NMI if the first NMI took an exception and reset our iret stack + * so that we repeat another NMI. + */ + pushq $-1 /* ORIG_RAX: no syscall to restart */ + ALLOC_PT_GPREGS_ON_STACK + + /* + * Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit + * as we should not be calling schedule in NMI context. + * Even with normal interrupts enabled. An NMI should not be + * setting NEED_RESCHED or anything that normal interrupts and + * exceptions might do. + */ + call paranoid_entry + + /* + * Save off the CR2 register. If we take a page fault in the NMI then + * it could corrupt the CR2 value. If the NMI preempts a page fault + * handler before it was able to read the CR2 register, and then the + * NMI itself takes a page fault, the page fault that was preempted + * will read the information from the NMI page fault and not the + * origin fault. Save it off and restore it if it changes. + * Use the r12 callee-saved register. + */ + movq %cr2, %r12 + + /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */ + movq %rsp,%rdi + movq $-1,%rsi + call do_nmi + + /* Did the NMI take a page fault? Restore cr2 if it did */ + movq %cr2, %rcx + cmpq %rcx, %r12 + je 1f + movq %r12, %cr2 +1: + testl %ebx,%ebx /* swapgs needed? */ + jnz nmi_restore +nmi_swapgs: + SWAPGS_UNSAFE_STACK +nmi_restore: + RESTORE_EXTRA_REGS + RESTORE_C_REGS + /* Pop the extra iret frame at once */ + REMOVE_PT_GPREGS_FROM_STACK 6*8 + + /* Clear the NMI executing stack variable */ + movq $0, 5*8(%rsp) + jmp irq_return +END(nmi) + +ENTRY(ignore_sysret) + mov $-ENOSYS,%eax + sysret +END(ignore_sysret) + |