![Steven Rostedt](/assets/img/avatar_default.png)
Avi Kivity reported that page faults in NMIs could cause havic if the NMI preempted another page fault handler: The recent changes to NMI allow exceptions to take place in NMI handlers, but I think that a #PF (say, due to access to vmalloc space) is still problematic. Consider the sequence #PF (cr2 set by processor) NMI ... #PF (cr2 clobbered) do_page_fault() IRET ... IRET do_page_fault() address = read_cr2() The last line reads the overwritten cr2 value. Originally I wrote a patch to solve this by saving the cr2 on the stack. Brian Gerst suggested to save it in the r12 register as both r12 and rbx are saved by the do_nmi handler as required by the C standard. But rbx is already used for saving if swapgs needs to be run on exit of the NMI handler. Link: http://lkml.kernel.org/r/4FBB8C40.6080304@redhat.com Link: http://lkml.kernel.org/r/1337763411.13348.140.camel@gandalf.stny.rr.com Reported-by: Avi Kivity <avi@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Thomas Gleixner <tglx@linutronix.de> Suggested-by: Brian Gerst <brgerst@gmail.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
1808 lines
45 KiB
ArmAsm
1808 lines
45 KiB
ArmAsm
/*
|
|
* 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.
|
|
*
|
|
* Normal syscalls and interrupts don't save a full stack frame, this is
|
|
* only done for syscall tracing, signals or fork/exec et.al.
|
|
*
|
|
* A note on terminology:
|
|
* - top of stack: Architecture defined interrupt frame from SS to RIP
|
|
* at the top of the kernel process stack.
|
|
* - partial stack frame: partially saved registers up to R11.
|
|
* - full stack frame: Like partial stack frame, but all register saved.
|
|
*
|
|
* Some macro usage:
|
|
* - CFI macros are used to generate dwarf2 unwind information for better
|
|
* backtraces. They don't change any code.
|
|
* - SAVE_ALL/RESTORE_ALL - Save/restore all registers
|
|
* - SAVE_ARGS/RESTORE_ARGS - Save/restore registers that C functions modify.
|
|
* There are unfortunately lots of special cases where some registers
|
|
* not touched. The macro is a big mess that should be cleaned up.
|
|
* - SAVE_REST/RESTORE_REST - Handle the registers not saved by SAVE_ARGS.
|
|
* Gives a full stack frame.
|
|
* - ENTRY/END Define functions in the symbol table.
|
|
* - FIXUP_TOP_OF_STACK/RESTORE_TOP_OF_STACK - Fix up the hardware stack
|
|
* frame that is otherwise undefined after a SYSCALL
|
|
* - TRACE_IRQ_* - Trace hard interrupt state for lock debugging.
|
|
* - errorentry/paranoidentry/zeroentry - Define exception entry points.
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
#include <asm/segment.h>
|
|
#include <asm/cache.h>
|
|
#include <asm/errno.h>
|
|
#include <asm/dwarf2.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/ftrace.h>
|
|
#include <asm/percpu.h>
|
|
#include <asm/asm.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_FUNCTION_TRACER
|
|
#ifdef CONFIG_DYNAMIC_FTRACE
|
|
ENTRY(mcount)
|
|
retq
|
|
END(mcount)
|
|
|
|
ENTRY(ftrace_caller)
|
|
cmpl $0, function_trace_stop
|
|
jne ftrace_stub
|
|
|
|
MCOUNT_SAVE_FRAME
|
|
|
|
movq 0x38(%rsp), %rdi
|
|
movq 8(%rbp), %rsi
|
|
subq $MCOUNT_INSN_SIZE, %rdi
|
|
|
|
GLOBAL(ftrace_call)
|
|
call ftrace_stub
|
|
|
|
MCOUNT_RESTORE_FRAME
|
|
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
GLOBAL(ftrace_graph_call)
|
|
jmp ftrace_stub
|
|
#endif
|
|
|
|
GLOBAL(ftrace_stub)
|
|
retq
|
|
END(ftrace_caller)
|
|
|
|
#else /* ! CONFIG_DYNAMIC_FTRACE */
|
|
ENTRY(mcount)
|
|
cmpl $0, function_trace_stop
|
|
jne ftrace_stub
|
|
|
|
cmpq $ftrace_stub, ftrace_trace_function
|
|
jnz trace
|
|
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
cmpq $ftrace_stub, ftrace_graph_return
|
|
jnz ftrace_graph_caller
|
|
|
|
cmpq $ftrace_graph_entry_stub, ftrace_graph_entry
|
|
jnz ftrace_graph_caller
|
|
#endif
|
|
|
|
GLOBAL(ftrace_stub)
|
|
retq
|
|
|
|
trace:
|
|
MCOUNT_SAVE_FRAME
|
|
|
|
movq 0x38(%rsp), %rdi
|
|
movq 8(%rbp), %rsi
|
|
subq $MCOUNT_INSN_SIZE, %rdi
|
|
|
|
call *ftrace_trace_function
|
|
|
|
MCOUNT_RESTORE_FRAME
|
|
|
|
jmp ftrace_stub
|
|
END(mcount)
|
|
#endif /* CONFIG_DYNAMIC_FTRACE */
|
|
#endif /* CONFIG_FUNCTION_TRACER */
|
|
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
|
ENTRY(ftrace_graph_caller)
|
|
cmpl $0, function_trace_stop
|
|
jne ftrace_stub
|
|
|
|
MCOUNT_SAVE_FRAME
|
|
|
|
leaq 8(%rbp), %rdi
|
|
movq 0x38(%rsp), %rsi
|
|
movq (%rbp), %rdx
|
|
subq $MCOUNT_INSN_SIZE, %rsi
|
|
|
|
call prepare_ftrace_return
|
|
|
|
MCOUNT_RESTORE_FRAME
|
|
|
|
retq
|
|
END(ftrace_graph_caller)
|
|
|
|
GLOBAL(return_to_handler)
|
|
subq $24, %rsp
|
|
|
|
/* Save the return values */
|
|
movq %rax, (%rsp)
|
|
movq %rdx, 8(%rsp)
|
|
movq %rbp, %rdi
|
|
|
|
call ftrace_return_to_handler
|
|
|
|
movq %rax, %rdi
|
|
movq 8(%rsp), %rdx
|
|
movq (%rsp), %rax
|
|
addq $24, %rsp
|
|
jmp *%rdi
|
|
#endif
|
|
|
|
|
|
#ifndef CONFIG_PREEMPT
|
|
#define retint_kernel retint_restore_args
|
|
#endif
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
ENTRY(native_usergs_sysret64)
|
|
swapgs
|
|
sysretq
|
|
ENDPROC(native_usergs_sysret64)
|
|
#endif /* CONFIG_PARAVIRT */
|
|
|
|
|
|
.macro TRACE_IRQS_IRETQ offset=ARGOFFSET
|
|
#ifdef CONFIG_TRACE_IRQFLAGS
|
|
bt $9,EFLAGS-\offset(%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 offset=ARGOFFSET
|
|
bt $9,EFLAGS-\offset(%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
|
|
|
|
/*
|
|
* C code is not supposed to know about undefined top of stack. Every time
|
|
* a C function with an pt_regs argument is called from the SYSCALL based
|
|
* fast path FIXUP_TOP_OF_STACK is needed.
|
|
* RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs
|
|
* manipulation.
|
|
*/
|
|
|
|
/* %rsp:at FRAMEEND */
|
|
.macro FIXUP_TOP_OF_STACK tmp offset=0
|
|
movq PER_CPU_VAR(old_rsp),\tmp
|
|
movq \tmp,RSP+\offset(%rsp)
|
|
movq $__USER_DS,SS+\offset(%rsp)
|
|
movq $__USER_CS,CS+\offset(%rsp)
|
|
movq $-1,RCX+\offset(%rsp)
|
|
movq R11+\offset(%rsp),\tmp /* get eflags */
|
|
movq \tmp,EFLAGS+\offset(%rsp)
|
|
.endm
|
|
|
|
.macro RESTORE_TOP_OF_STACK tmp offset=0
|
|
movq RSP+\offset(%rsp),\tmp
|
|
movq \tmp,PER_CPU_VAR(old_rsp)
|
|
movq EFLAGS+\offset(%rsp),\tmp
|
|
movq \tmp,R11+\offset(%rsp)
|
|
.endm
|
|
|
|
.macro FAKE_STACK_FRAME child_rip
|
|
/* push in order ss, rsp, eflags, cs, rip */
|
|
xorl %eax, %eax
|
|
pushq_cfi $__KERNEL_DS /* ss */
|
|
/*CFI_REL_OFFSET ss,0*/
|
|
pushq_cfi %rax /* rsp */
|
|
CFI_REL_OFFSET rsp,0
|
|
pushq_cfi $(X86_EFLAGS_IF|X86_EFLAGS_BIT1) /* eflags - interrupts on */
|
|
/*CFI_REL_OFFSET rflags,0*/
|
|
pushq_cfi $__KERNEL_CS /* cs */
|
|
/*CFI_REL_OFFSET cs,0*/
|
|
pushq_cfi \child_rip /* rip */
|
|
CFI_REL_OFFSET rip,0
|
|
pushq_cfi %rax /* orig rax */
|
|
.endm
|
|
|
|
.macro UNFAKE_STACK_FRAME
|
|
addq $8*6, %rsp
|
|
CFI_ADJUST_CFA_OFFSET -(6*8)
|
|
.endm
|
|
|
|
/*
|
|
* initial frame state for interrupts (and exceptions without error code)
|
|
*/
|
|
.macro EMPTY_FRAME start=1 offset=0
|
|
.if \start
|
|
CFI_STARTPROC simple
|
|
CFI_SIGNAL_FRAME
|
|
CFI_DEF_CFA rsp,8+\offset
|
|
.else
|
|
CFI_DEF_CFA_OFFSET 8+\offset
|
|
.endif
|
|
.endm
|
|
|
|
/*
|
|
* initial frame state for interrupts (and exceptions without error code)
|
|
*/
|
|
.macro INTR_FRAME start=1 offset=0
|
|
EMPTY_FRAME \start, SS+8+\offset-RIP
|
|
/*CFI_REL_OFFSET ss, SS+\offset-RIP*/
|
|
CFI_REL_OFFSET rsp, RSP+\offset-RIP
|
|
/*CFI_REL_OFFSET rflags, EFLAGS+\offset-RIP*/
|
|
/*CFI_REL_OFFSET cs, CS+\offset-RIP*/
|
|
CFI_REL_OFFSET rip, RIP+\offset-RIP
|
|
.endm
|
|
|
|
/*
|
|
* initial frame state for exceptions with error code (and interrupts
|
|
* with vector already pushed)
|
|
*/
|
|
.macro XCPT_FRAME start=1 offset=0
|
|
INTR_FRAME \start, RIP+\offset-ORIG_RAX
|
|
/*CFI_REL_OFFSET orig_rax, ORIG_RAX-ORIG_RAX*/
|
|
.endm
|
|
|
|
/*
|
|
* frame that enables calling into C.
|
|
*/
|
|
.macro PARTIAL_FRAME start=1 offset=0
|
|
XCPT_FRAME \start, ORIG_RAX+\offset-ARGOFFSET
|
|
CFI_REL_OFFSET rdi, RDI+\offset-ARGOFFSET
|
|
CFI_REL_OFFSET rsi, RSI+\offset-ARGOFFSET
|
|
CFI_REL_OFFSET rdx, RDX+\offset-ARGOFFSET
|
|
CFI_REL_OFFSET rcx, RCX+\offset-ARGOFFSET
|
|
CFI_REL_OFFSET rax, RAX+\offset-ARGOFFSET
|
|
CFI_REL_OFFSET r8, R8+\offset-ARGOFFSET
|
|
CFI_REL_OFFSET r9, R9+\offset-ARGOFFSET
|
|
CFI_REL_OFFSET r10, R10+\offset-ARGOFFSET
|
|
CFI_REL_OFFSET r11, R11+\offset-ARGOFFSET
|
|
.endm
|
|
|
|
/*
|
|
* frame that enables passing a complete pt_regs to a C function.
|
|
*/
|
|
.macro DEFAULT_FRAME start=1 offset=0
|
|
PARTIAL_FRAME \start, R11+\offset-R15
|
|
CFI_REL_OFFSET rbx, RBX+\offset
|
|
CFI_REL_OFFSET rbp, RBP+\offset
|
|
CFI_REL_OFFSET r12, R12+\offset
|
|
CFI_REL_OFFSET r13, R13+\offset
|
|
CFI_REL_OFFSET r14, R14+\offset
|
|
CFI_REL_OFFSET r15, R15+\offset
|
|
.endm
|
|
|
|
/* save partial stack frame */
|
|
.macro SAVE_ARGS_IRQ
|
|
cld
|
|
/* start from rbp in pt_regs and jump over */
|
|
movq_cfi rdi, RDI-RBP
|
|
movq_cfi rsi, RSI-RBP
|
|
movq_cfi rdx, RDX-RBP
|
|
movq_cfi rcx, RCX-RBP
|
|
movq_cfi rax, RAX-RBP
|
|
movq_cfi r8, R8-RBP
|
|
movq_cfi r9, R9-RBP
|
|
movq_cfi r10, R10-RBP
|
|
movq_cfi r11, R11-RBP
|
|
|
|
/* Save rbp so that we can unwind from get_irq_regs() */
|
|
movq_cfi rbp, 0
|
|
|
|
/* Save previous stack value */
|
|
movq %rsp, %rsi
|
|
|
|
leaq -RBP(%rsp),%rdi /* arg1 for handler */
|
|
testl $3, CS-RBP(%rsi)
|
|
je 1f
|
|
SWAPGS
|
|
/*
|
|
* 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)
|
|
*/
|
|
1: incl PER_CPU_VAR(irq_count)
|
|
cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
|
|
CFI_DEF_CFA_REGISTER rsi
|
|
|
|
/* Store previous stack value */
|
|
pushq %rsi
|
|
CFI_ESCAPE 0x0f /* DW_CFA_def_cfa_expression */, 6, \
|
|
0x77 /* DW_OP_breg7 */, 0, \
|
|
0x06 /* DW_OP_deref */, \
|
|
0x08 /* DW_OP_const1u */, SS+8-RBP, \
|
|
0x22 /* DW_OP_plus */
|
|
/* We entered an interrupt context - irqs are off: */
|
|
TRACE_IRQS_OFF
|
|
.endm
|
|
|
|
ENTRY(save_rest)
|
|
PARTIAL_FRAME 1 REST_SKIP+8
|
|
movq 5*8+16(%rsp), %r11 /* save return address */
|
|
movq_cfi rbx, RBX+16
|
|
movq_cfi rbp, RBP+16
|
|
movq_cfi r12, R12+16
|
|
movq_cfi r13, R13+16
|
|
movq_cfi r14, R14+16
|
|
movq_cfi r15, R15+16
|
|
movq %r11, 8(%rsp) /* return address */
|
|
FIXUP_TOP_OF_STACK %r11, 16
|
|
ret
|
|
CFI_ENDPROC
|
|
END(save_rest)
|
|
|
|
/* save complete stack frame */
|
|
.pushsection .kprobes.text, "ax"
|
|
ENTRY(save_paranoid)
|
|
XCPT_FRAME 1 RDI+8
|
|
cld
|
|
movq_cfi rdi, RDI+8
|
|
movq_cfi rsi, RSI+8
|
|
movq_cfi rdx, RDX+8
|
|
movq_cfi rcx, RCX+8
|
|
movq_cfi rax, RAX+8
|
|
movq_cfi r8, R8+8
|
|
movq_cfi r9, R9+8
|
|
movq_cfi r10, R10+8
|
|
movq_cfi r11, R11+8
|
|
movq_cfi rbx, RBX+8
|
|
movq_cfi rbp, RBP+8
|
|
movq_cfi r12, R12+8
|
|
movq_cfi r13, R13+8
|
|
movq_cfi r14, R14+8
|
|
movq_cfi r15, R15+8
|
|
movl $1,%ebx
|
|
movl $MSR_GS_BASE,%ecx
|
|
rdmsr
|
|
testl %edx,%edx
|
|
js 1f /* negative -> in kernel */
|
|
SWAPGS
|
|
xorl %ebx,%ebx
|
|
1: ret
|
|
CFI_ENDPROC
|
|
END(save_paranoid)
|
|
.popsection
|
|
|
|
/*
|
|
* A newly forked process directly context switches into this address.
|
|
*
|
|
* rdi: prev task we switched from
|
|
*/
|
|
ENTRY(ret_from_fork)
|
|
DEFAULT_FRAME
|
|
|
|
LOCK ; btr $TIF_FORK,TI_flags(%r8)
|
|
|
|
pushq_cfi kernel_eflags(%rip)
|
|
popfq_cfi # reset kernel eflags
|
|
|
|
call schedule_tail # rdi: 'prev' task parameter
|
|
|
|
GET_THREAD_INFO(%rcx)
|
|
|
|
RESTORE_REST
|
|
|
|
testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
|
|
jz retint_restore_args
|
|
|
|
testl $_TIF_IA32, TI_flags(%rcx) # 32-bit compat task needs IRET
|
|
jnz int_ret_from_sys_call
|
|
|
|
RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
|
|
jmp ret_from_sys_call # go to the SYSRET fastpath
|
|
|
|
CFI_ENDPROC
|
|
END(ret_from_fork)
|
|
|
|
/*
|
|
* System call entry. Up to 6 arguments in registers are supported.
|
|
*
|
|
* SYSCALL does not save anything on the stack and does not change the
|
|
* stack pointer.
|
|
*/
|
|
|
|
/*
|
|
* Register setup:
|
|
* rax system call number
|
|
* rdi arg0
|
|
* rcx return address for syscall/sysret, C arg3
|
|
* rsi arg1
|
|
* rdx arg2
|
|
* r10 arg3 (--> moved to rcx for C)
|
|
* r8 arg4
|
|
* r9 arg5
|
|
* r11 eflags for syscall/sysret, temporary for C
|
|
* r12-r15,rbp,rbx saved by C code, not touched.
|
|
*
|
|
* Interrupts are off on entry.
|
|
* Only called from user space.
|
|
*
|
|
* XXX if we had a free scratch register we could save the RSP into the stack frame
|
|
* and report it properly in ps. Unfortunately we haven't.
|
|
*
|
|
* When user can change the frames 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)
|
|
CFI_STARTPROC simple
|
|
CFI_SIGNAL_FRAME
|
|
CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
|
|
CFI_REGISTER rip,rcx
|
|
/*CFI_REGISTER rflags,r11*/
|
|
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(old_rsp)
|
|
movq PER_CPU_VAR(kernel_stack),%rsp
|
|
/*
|
|
* No need to follow this irqs off/on section - it's straight
|
|
* and short:
|
|
*/
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
SAVE_ARGS 8,0
|
|
movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
|
|
movq %rcx,RIP-ARGOFFSET(%rsp)
|
|
CFI_REL_OFFSET rip,RIP-ARGOFFSET
|
|
testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
|
|
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 badsys
|
|
movq %r10,%rcx
|
|
call *sys_call_table(,%rax,8) # XXX: rip relative
|
|
movq %rax,RAX-ARGOFFSET(%rsp)
|
|
/*
|
|
* Syscall return path ending with SYSRET (fast path)
|
|
* Has incomplete stack frame and undefined top of stack.
|
|
*/
|
|
ret_from_sys_call:
|
|
movl $_TIF_ALLWORK_MASK,%edi
|
|
/* edi: flagmask */
|
|
sysret_check:
|
|
LOCKDEP_SYS_EXIT
|
|
DISABLE_INTERRUPTS(CLBR_NONE)
|
|
TRACE_IRQS_OFF
|
|
movl TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET),%edx
|
|
andl %edi,%edx
|
|
jnz sysret_careful
|
|
CFI_REMEMBER_STATE
|
|
/*
|
|
* sysretq will re-enable interrupts:
|
|
*/
|
|
TRACE_IRQS_ON
|
|
movq RIP-ARGOFFSET(%rsp),%rcx
|
|
CFI_REGISTER rip,rcx
|
|
RESTORE_ARGS 1,-ARG_SKIP,0
|
|
/*CFI_REGISTER rflags,r11*/
|
|
movq PER_CPU_VAR(old_rsp), %rsp
|
|
USERGS_SYSRET64
|
|
|
|
CFI_RESTORE_STATE
|
|
/* Handle reschedules */
|
|
/* edx: work, edi: workmask */
|
|
sysret_careful:
|
|
bt $TIF_NEED_RESCHED,%edx
|
|
jnc sysret_signal
|
|
TRACE_IRQS_ON
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
pushq_cfi %rdi
|
|
call schedule
|
|
popq_cfi %rdi
|
|
jmp sysret_check
|
|
|
|
/* Handle a signal */
|
|
sysret_signal:
|
|
TRACE_IRQS_ON
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
#ifdef CONFIG_AUDITSYSCALL
|
|
bt $TIF_SYSCALL_AUDIT,%edx
|
|
jc sysret_audit
|
|
#endif
|
|
/*
|
|
* We have a signal, or exit tracing or single-step.
|
|
* These all wind up with the iret return path anyway,
|
|
* so just join that path right now.
|
|
*/
|
|
FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
|
|
jmp int_check_syscall_exit_work
|
|
|
|
badsys:
|
|
movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
|
|
jmp ret_from_sys_call
|
|
|
|
#ifdef CONFIG_AUDITSYSCALL
|
|
/*
|
|
* Fast path for syscall audit without full syscall trace.
|
|
* We just call __audit_syscall_entry() directly, and then
|
|
* jump back to the normal fast path.
|
|
*/
|
|
auditsys:
|
|
movq %r10,%r9 /* 6th arg: 4th syscall arg */
|
|
movq %rdx,%r8 /* 5th arg: 3rd syscall arg */
|
|
movq %rsi,%rcx /* 4th arg: 2nd syscall arg */
|
|
movq %rdi,%rdx /* 3rd arg: 1st syscall arg */
|
|
movq %rax,%rsi /* 2nd arg: syscall number */
|
|
movl $AUDIT_ARCH_X86_64,%edi /* 1st arg: audit arch */
|
|
call __audit_syscall_entry
|
|
LOAD_ARGS 0 /* reload call-clobbered registers */
|
|
jmp system_call_fastpath
|
|
|
|
/*
|
|
* Return fast path for syscall audit. Call __audit_syscall_exit()
|
|
* directly and then jump back to the fast path with TIF_SYSCALL_AUDIT
|
|
* masked off.
|
|
*/
|
|
sysret_audit:
|
|
movq RAX-ARGOFFSET(%rsp),%rsi /* second arg, syscall return value */
|
|
cmpq $-MAX_ERRNO,%rsi /* is it < -MAX_ERRNO? */
|
|
setbe %al /* 1 if so, 0 if not */
|
|
movzbl %al,%edi /* zero-extend that into %edi */
|
|
call __audit_syscall_exit
|
|
movl $(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT),%edi
|
|
jmp sysret_check
|
|
#endif /* CONFIG_AUDITSYSCALL */
|
|
|
|
/* Do syscall tracing */
|
|
tracesys:
|
|
#ifdef CONFIG_AUDITSYSCALL
|
|
testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
|
|
jz auditsys
|
|
#endif
|
|
SAVE_REST
|
|
movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
|
|
FIXUP_TOP_OF_STACK %rdi
|
|
movq %rsp,%rdi
|
|
call syscall_trace_enter
|
|
/*
|
|
* Reload arg registers from stack in case ptrace changed them.
|
|
* We don't reload %rax because syscall_trace_enter() returned
|
|
* the value it wants us to use in the table lookup.
|
|
*/
|
|
LOAD_ARGS ARGOFFSET, 1
|
|
RESTORE_REST
|
|
#if __SYSCALL_MASK == ~0
|
|
cmpq $__NR_syscall_max,%rax
|
|
#else
|
|
andl $__SYSCALL_MASK,%eax
|
|
cmpl $__NR_syscall_max,%eax
|
|
#endif
|
|
ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */
|
|
movq %r10,%rcx /* fixup for C */
|
|
call *sys_call_table(,%rax,8)
|
|
movq %rax,RAX-ARGOFFSET(%rsp)
|
|
/* Use IRET because user could have changed frame */
|
|
|
|
/*
|
|
* Syscall return path ending with IRET.
|
|
* Has correct top of stack, but partial stack frame.
|
|
*/
|
|
GLOBAL(int_ret_from_sys_call)
|
|
DISABLE_INTERRUPTS(CLBR_NONE)
|
|
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 retint_swapgs
|
|
|
|
/* 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_cfi %rdi
|
|
call schedule
|
|
popq_cfi %rdi
|
|
DISABLE_INTERRUPTS(CLBR_NONE)
|
|
TRACE_IRQS_OFF
|
|
jmp int_with_check
|
|
|
|
/* handle signals and tracing -- both require a full stack frame */
|
|
int_very_careful:
|
|
TRACE_IRQS_ON
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
int_check_syscall_exit_work:
|
|
SAVE_REST
|
|
/* Check for syscall exit trace */
|
|
testl $_TIF_WORK_SYSCALL_EXIT,%edx
|
|
jz int_signal
|
|
pushq_cfi %rdi
|
|
leaq 8(%rsp),%rdi # &ptregs -> arg1
|
|
call syscall_trace_leave
|
|
popq_cfi %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_REST
|
|
DISABLE_INTERRUPTS(CLBR_NONE)
|
|
TRACE_IRQS_OFF
|
|
jmp int_with_check
|
|
CFI_ENDPROC
|
|
END(system_call)
|
|
|
|
/*
|
|
* Certain special system calls that need to save a complete full stack frame.
|
|
*/
|
|
.macro PTREGSCALL label,func,arg
|
|
ENTRY(\label)
|
|
PARTIAL_FRAME 1 8 /* offset 8: return address */
|
|
subq $REST_SKIP, %rsp
|
|
CFI_ADJUST_CFA_OFFSET REST_SKIP
|
|
call save_rest
|
|
DEFAULT_FRAME 0 8 /* offset 8: return address */
|
|
leaq 8(%rsp), \arg /* pt_regs pointer */
|
|
call \func
|
|
jmp ptregscall_common
|
|
CFI_ENDPROC
|
|
END(\label)
|
|
.endm
|
|
|
|
PTREGSCALL stub_clone, sys_clone, %r8
|
|
PTREGSCALL stub_fork, sys_fork, %rdi
|
|
PTREGSCALL stub_vfork, sys_vfork, %rdi
|
|
PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
|
|
PTREGSCALL stub_iopl, sys_iopl, %rsi
|
|
|
|
ENTRY(ptregscall_common)
|
|
DEFAULT_FRAME 1 8 /* offset 8: return address */
|
|
RESTORE_TOP_OF_STACK %r11, 8
|
|
movq_cfi_restore R15+8, r15
|
|
movq_cfi_restore R14+8, r14
|
|
movq_cfi_restore R13+8, r13
|
|
movq_cfi_restore R12+8, r12
|
|
movq_cfi_restore RBP+8, rbp
|
|
movq_cfi_restore RBX+8, rbx
|
|
ret $REST_SKIP /* pop extended registers */
|
|
CFI_ENDPROC
|
|
END(ptregscall_common)
|
|
|
|
ENTRY(stub_execve)
|
|
CFI_STARTPROC
|
|
addq $8, %rsp
|
|
PARTIAL_FRAME 0
|
|
SAVE_REST
|
|
FIXUP_TOP_OF_STACK %r11
|
|
movq %rsp, %rcx
|
|
call sys_execve
|
|
RESTORE_TOP_OF_STACK %r11
|
|
movq %rax,RAX(%rsp)
|
|
RESTORE_REST
|
|
jmp int_ret_from_sys_call
|
|
CFI_ENDPROC
|
|
END(stub_execve)
|
|
|
|
/*
|
|
* 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)
|
|
CFI_STARTPROC
|
|
addq $8, %rsp
|
|
PARTIAL_FRAME 0
|
|
SAVE_REST
|
|
movq %rsp,%rdi
|
|
FIXUP_TOP_OF_STACK %r11
|
|
call sys_rt_sigreturn
|
|
movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
|
|
RESTORE_REST
|
|
jmp int_ret_from_sys_call
|
|
CFI_ENDPROC
|
|
END(stub_rt_sigreturn)
|
|
|
|
#ifdef CONFIG_X86_X32_ABI
|
|
PTREGSCALL stub_x32_sigaltstack, sys32_sigaltstack, %rdx
|
|
|
|
ENTRY(stub_x32_rt_sigreturn)
|
|
CFI_STARTPROC
|
|
addq $8, %rsp
|
|
PARTIAL_FRAME 0
|
|
SAVE_REST
|
|
movq %rsp,%rdi
|
|
FIXUP_TOP_OF_STACK %r11
|
|
call sys32_x32_rt_sigreturn
|
|
movq %rax,RAX(%rsp) # fixme, this could be done at the higher layer
|
|
RESTORE_REST
|
|
jmp int_ret_from_sys_call
|
|
CFI_ENDPROC
|
|
END(stub_x32_rt_sigreturn)
|
|
|
|
ENTRY(stub_x32_execve)
|
|
CFI_STARTPROC
|
|
addq $8, %rsp
|
|
PARTIAL_FRAME 0
|
|
SAVE_REST
|
|
FIXUP_TOP_OF_STACK %r11
|
|
movq %rsp, %rcx
|
|
call sys32_execve
|
|
RESTORE_TOP_OF_STACK %r11
|
|
movq %rax,RAX(%rsp)
|
|
RESTORE_REST
|
|
jmp int_ret_from_sys_call
|
|
CFI_ENDPROC
|
|
END(stub_x32_execve)
|
|
|
|
#endif
|
|
|
|
/*
|
|
* Build the entry stubs and pointer table with some assembler magic.
|
|
* We pack 7 stubs into a single 32-byte chunk, which will fit in a
|
|
* single cache line on all modern x86 implementations.
|
|
*/
|
|
.section .init.rodata,"a"
|
|
ENTRY(interrupt)
|
|
.section .entry.text
|
|
.p2align 5
|
|
.p2align CONFIG_X86_L1_CACHE_SHIFT
|
|
ENTRY(irq_entries_start)
|
|
INTR_FRAME
|
|
vector=FIRST_EXTERNAL_VECTOR
|
|
.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
|
|
.balign 32
|
|
.rept 7
|
|
.if vector < NR_VECTORS
|
|
.if vector <> FIRST_EXTERNAL_VECTOR
|
|
CFI_ADJUST_CFA_OFFSET -8
|
|
.endif
|
|
1: pushq_cfi $(~vector+0x80) /* Note: always in signed byte range */
|
|
.if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
|
|
jmp 2f
|
|
.endif
|
|
.previous
|
|
.quad 1b
|
|
.section .entry.text
|
|
vector=vector+1
|
|
.endif
|
|
.endr
|
|
2: jmp common_interrupt
|
|
.endr
|
|
CFI_ENDPROC
|
|
END(irq_entries_start)
|
|
|
|
.previous
|
|
END(interrupt)
|
|
.previous
|
|
|
|
/*
|
|
* 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
|
|
/* reserve pt_regs for scratch regs and rbp */
|
|
subq $ORIG_RAX-RBP, %rsp
|
|
CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
|
|
SAVE_ARGS_IRQ
|
|
call \func
|
|
.endm
|
|
|
|
/*
|
|
* Interrupt entry/exit should be protected against kprobes
|
|
*/
|
|
.pushsection .kprobes.text, "ax"
|
|
/*
|
|
* The interrupt stubs push (~vector+0x80) onto the stack and
|
|
* then jump to common_interrupt.
|
|
*/
|
|
.p2align CONFIG_X86_L1_CACHE_SHIFT
|
|
common_interrupt:
|
|
XCPT_FRAME
|
|
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
|
|
interrupt do_IRQ
|
|
/* 0(%rsp): old_rsp-ARGOFFSET */
|
|
ret_from_intr:
|
|
DISABLE_INTERRUPTS(CLBR_NONE)
|
|
TRACE_IRQS_OFF
|
|
decl PER_CPU_VAR(irq_count)
|
|
|
|
/* Restore saved previous stack */
|
|
popq %rsi
|
|
CFI_DEF_CFA rsi,SS+8-RBP /* reg/off reset after def_cfa_expr */
|
|
leaq ARGOFFSET-RBP(%rsi), %rsp
|
|
CFI_DEF_CFA_REGISTER rsp
|
|
CFI_ADJUST_CFA_OFFSET RBP-ARGOFFSET
|
|
|
|
exit_intr:
|
|
GET_THREAD_INFO(%rcx)
|
|
testl $3,CS-ARGOFFSET(%rsp)
|
|
je retint_kernel
|
|
|
|
/* Interrupt came from user space */
|
|
/*
|
|
* Has a correct top of stack, but a partial stack frame
|
|
* %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
|
|
CFI_REMEMBER_STATE
|
|
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_args
|
|
|
|
retint_restore_args: /* return to kernel space */
|
|
DISABLE_INTERRUPTS(CLBR_ANY)
|
|
/*
|
|
* The iretq could re-enable interrupts:
|
|
*/
|
|
TRACE_IRQS_IRETQ
|
|
restore_args:
|
|
RESTORE_ARGS 1,8,1
|
|
|
|
irq_return:
|
|
INTERRUPT_RETURN
|
|
_ASM_EXTABLE(irq_return, bad_iret)
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
ENTRY(native_iret)
|
|
iretq
|
|
_ASM_EXTABLE(native_iret, bad_iret)
|
|
#endif
|
|
|
|
.section .fixup,"ax"
|
|
bad_iret:
|
|
/*
|
|
* The iret traps when the %cs or %ss being restored is bogus.
|
|
* We've lost the original trap vector and error code.
|
|
* #GPF is the most likely one to get for an invalid selector.
|
|
* So pretend we completed the iret and took the #GPF in user mode.
|
|
*
|
|
* We are now running with the kernel GS after exception recovery.
|
|
* But error_entry expects us to have user GS to match the user %cs,
|
|
* so swap back.
|
|
*/
|
|
pushq $0
|
|
|
|
SWAPGS
|
|
jmp general_protection
|
|
|
|
.previous
|
|
|
|
/* edi: workmask, edx: work */
|
|
retint_careful:
|
|
CFI_RESTORE_STATE
|
|
bt $TIF_NEED_RESCHED,%edx
|
|
jnc retint_signal
|
|
TRACE_IRQS_ON
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
pushq_cfi %rdi
|
|
call schedule
|
|
popq_cfi %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_REST
|
|
movq $-1,ORIG_RAX(%rsp)
|
|
xorl %esi,%esi # oldset
|
|
movq %rsp,%rdi # &pt_regs
|
|
call do_notify_resume
|
|
RESTORE_REST
|
|
DISABLE_INTERRUPTS(CLBR_NONE)
|
|
TRACE_IRQS_OFF
|
|
GET_THREAD_INFO(%rcx)
|
|
jmp retint_with_reschedule
|
|
|
|
#ifdef CONFIG_PREEMPT
|
|
/* Returning to kernel space. Check if we need preemption */
|
|
/* rcx: threadinfo. interrupts off. */
|
|
ENTRY(retint_kernel)
|
|
cmpl $0,TI_preempt_count(%rcx)
|
|
jnz retint_restore_args
|
|
bt $TIF_NEED_RESCHED,TI_flags(%rcx)
|
|
jnc retint_restore_args
|
|
bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */
|
|
jnc retint_restore_args
|
|
call preempt_schedule_irq
|
|
jmp exit_intr
|
|
#endif
|
|
|
|
CFI_ENDPROC
|
|
END(common_interrupt)
|
|
/*
|
|
* End of kprobes section
|
|
*/
|
|
.popsection
|
|
|
|
/*
|
|
* APIC interrupts.
|
|
*/
|
|
.macro apicinterrupt num sym do_sym
|
|
ENTRY(\sym)
|
|
INTR_FRAME
|
|
pushq_cfi $~(\num)
|
|
.Lcommon_\sym:
|
|
interrupt \do_sym
|
|
jmp ret_from_intr
|
|
CFI_ENDPROC
|
|
END(\sym)
|
|
.endm
|
|
|
|
#ifdef CONFIG_SMP
|
|
apicinterrupt IRQ_MOVE_CLEANUP_VECTOR \
|
|
irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
|
|
apicinterrupt REBOOT_VECTOR \
|
|
reboot_interrupt smp_reboot_interrupt
|
|
#endif
|
|
|
|
#ifdef CONFIG_X86_UV
|
|
apicinterrupt 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_SMP
|
|
ALIGN
|
|
INTR_FRAME
|
|
.irp idx,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
|
|
16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
|
|
.if NUM_INVALIDATE_TLB_VECTORS > \idx
|
|
ENTRY(invalidate_interrupt\idx)
|
|
pushq_cfi $~(INVALIDATE_TLB_VECTOR_START+\idx)
|
|
jmp .Lcommon_invalidate_interrupt0
|
|
CFI_ADJUST_CFA_OFFSET -8
|
|
END(invalidate_interrupt\idx)
|
|
.endif
|
|
.endr
|
|
CFI_ENDPROC
|
|
apicinterrupt INVALIDATE_TLB_VECTOR_START, \
|
|
invalidate_interrupt0, smp_invalidate_interrupt
|
|
#endif
|
|
|
|
apicinterrupt THRESHOLD_APIC_VECTOR \
|
|
threshold_interrupt smp_threshold_interrupt
|
|
apicinterrupt THERMAL_APIC_VECTOR \
|
|
thermal_interrupt smp_thermal_interrupt
|
|
|
|
#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.
|
|
*/
|
|
.macro zeroentry sym do_sym
|
|
ENTRY(\sym)
|
|
INTR_FRAME
|
|
PARAVIRT_ADJUST_EXCEPTION_FRAME
|
|
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
|
|
subq $ORIG_RAX-R15, %rsp
|
|
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
|
|
call error_entry
|
|
DEFAULT_FRAME 0
|
|
movq %rsp,%rdi /* pt_regs pointer */
|
|
xorl %esi,%esi /* no error code */
|
|
call \do_sym
|
|
jmp error_exit /* %ebx: no swapgs flag */
|
|
CFI_ENDPROC
|
|
END(\sym)
|
|
.endm
|
|
|
|
.macro paranoidzeroentry sym do_sym
|
|
ENTRY(\sym)
|
|
INTR_FRAME
|
|
PARAVIRT_ADJUST_EXCEPTION_FRAME
|
|
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
|
|
subq $ORIG_RAX-R15, %rsp
|
|
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
|
|
call save_paranoid
|
|
TRACE_IRQS_OFF
|
|
movq %rsp,%rdi /* pt_regs pointer */
|
|
xorl %esi,%esi /* no error code */
|
|
call \do_sym
|
|
jmp paranoid_exit /* %ebx: no swapgs flag */
|
|
CFI_ENDPROC
|
|
END(\sym)
|
|
.endm
|
|
|
|
#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8)
|
|
.macro paranoidzeroentry_ist sym do_sym ist
|
|
ENTRY(\sym)
|
|
INTR_FRAME
|
|
PARAVIRT_ADJUST_EXCEPTION_FRAME
|
|
pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */
|
|
subq $ORIG_RAX-R15, %rsp
|
|
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
|
|
call save_paranoid
|
|
TRACE_IRQS_OFF_DEBUG
|
|
movq %rsp,%rdi /* pt_regs pointer */
|
|
xorl %esi,%esi /* no error code */
|
|
subq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist)
|
|
call \do_sym
|
|
addq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist)
|
|
jmp paranoid_exit /* %ebx: no swapgs flag */
|
|
CFI_ENDPROC
|
|
END(\sym)
|
|
.endm
|
|
|
|
.macro errorentry sym do_sym
|
|
ENTRY(\sym)
|
|
XCPT_FRAME
|
|
PARAVIRT_ADJUST_EXCEPTION_FRAME
|
|
subq $ORIG_RAX-R15, %rsp
|
|
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
|
|
call error_entry
|
|
DEFAULT_FRAME 0
|
|
movq %rsp,%rdi /* pt_regs pointer */
|
|
movq ORIG_RAX(%rsp),%rsi /* get error code */
|
|
movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */
|
|
call \do_sym
|
|
jmp error_exit /* %ebx: no swapgs flag */
|
|
CFI_ENDPROC
|
|
END(\sym)
|
|
.endm
|
|
|
|
/* error code is on the stack already */
|
|
.macro paranoiderrorentry sym do_sym
|
|
ENTRY(\sym)
|
|
XCPT_FRAME
|
|
PARAVIRT_ADJUST_EXCEPTION_FRAME
|
|
subq $ORIG_RAX-R15, %rsp
|
|
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
|
|
call save_paranoid
|
|
DEFAULT_FRAME 0
|
|
TRACE_IRQS_OFF
|
|
movq %rsp,%rdi /* pt_regs pointer */
|
|
movq ORIG_RAX(%rsp),%rsi /* get error code */
|
|
movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */
|
|
call \do_sym
|
|
jmp paranoid_exit /* %ebx: no swapgs flag */
|
|
CFI_ENDPROC
|
|
END(\sym)
|
|
.endm
|
|
|
|
zeroentry divide_error do_divide_error
|
|
zeroentry overflow do_overflow
|
|
zeroentry bounds do_bounds
|
|
zeroentry invalid_op do_invalid_op
|
|
zeroentry device_not_available do_device_not_available
|
|
paranoiderrorentry double_fault do_double_fault
|
|
zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun
|
|
errorentry invalid_TSS do_invalid_TSS
|
|
errorentry segment_not_present do_segment_not_present
|
|
zeroentry spurious_interrupt_bug do_spurious_interrupt_bug
|
|
zeroentry coprocessor_error do_coprocessor_error
|
|
errorentry alignment_check do_alignment_check
|
|
zeroentry simd_coprocessor_error do_simd_coprocessor_error
|
|
|
|
|
|
/* Reload gs selector with exception handling */
|
|
/* edi: new selector */
|
|
ENTRY(native_load_gs_index)
|
|
CFI_STARTPROC
|
|
pushfq_cfi
|
|
DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
|
|
SWAPGS
|
|
gs_change:
|
|
movl %edi,%gs
|
|
2: mfence /* workaround */
|
|
SWAPGS
|
|
popfq_cfi
|
|
ret
|
|
CFI_ENDPROC
|
|
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
|
|
|
|
ENTRY(kernel_thread_helper)
|
|
pushq $0 # fake return address
|
|
CFI_STARTPROC
|
|
/*
|
|
* Here we are in the child and the registers are set as they were
|
|
* at kernel_thread() invocation in the parent.
|
|
*/
|
|
call *%rsi
|
|
# exit
|
|
mov %eax, %edi
|
|
call do_exit
|
|
ud2 # padding for call trace
|
|
CFI_ENDPROC
|
|
END(kernel_thread_helper)
|
|
|
|
/*
|
|
* execve(). This function needs to use IRET, not SYSRET, to set up all state properly.
|
|
*
|
|
* C extern interface:
|
|
* extern long execve(const char *name, char **argv, char **envp)
|
|
*
|
|
* asm input arguments:
|
|
* rdi: name, rsi: argv, rdx: envp
|
|
*
|
|
* We want to fallback into:
|
|
* extern long sys_execve(const char *name, char **argv,char **envp, struct pt_regs *regs)
|
|
*
|
|
* do_sys_execve asm fallback arguments:
|
|
* rdi: name, rsi: argv, rdx: envp, rcx: fake frame on the stack
|
|
*/
|
|
ENTRY(kernel_execve)
|
|
CFI_STARTPROC
|
|
FAKE_STACK_FRAME $0
|
|
SAVE_ALL
|
|
movq %rsp,%rcx
|
|
call sys_execve
|
|
movq %rax, RAX(%rsp)
|
|
RESTORE_REST
|
|
testq %rax,%rax
|
|
je int_ret_from_sys_call
|
|
RESTORE_ARGS
|
|
UNFAKE_STACK_FRAME
|
|
ret
|
|
CFI_ENDPROC
|
|
END(kernel_execve)
|
|
|
|
/* Call softirq on interrupt stack. Interrupts are off. */
|
|
ENTRY(call_softirq)
|
|
CFI_STARTPROC
|
|
pushq_cfi %rbp
|
|
CFI_REL_OFFSET rbp,0
|
|
mov %rsp,%rbp
|
|
CFI_DEF_CFA_REGISTER 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
|
|
CFI_RESTORE rbp
|
|
CFI_DEF_CFA_REGISTER rsp
|
|
CFI_ADJUST_CFA_OFFSET -8
|
|
decl PER_CPU_VAR(irq_count)
|
|
ret
|
|
CFI_ENDPROC
|
|
END(call_softirq)
|
|
|
|
#ifdef CONFIG_XEN
|
|
zeroentry xen_hypervisor_callback xen_do_hypervisor_callback
|
|
|
|
/*
|
|
* 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)
|
|
CFI_STARTPROC
|
|
/*
|
|
* 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
|
|
CFI_ENDPROC
|
|
DEFAULT_FRAME
|
|
11: incl PER_CPU_VAR(irq_count)
|
|
movq %rsp,%rbp
|
|
CFI_DEF_CFA_REGISTER rbp
|
|
cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
|
|
pushq %rbp # backlink for old unwinder
|
|
call xen_evtchn_do_upcall
|
|
popq %rsp
|
|
CFI_DEF_CFA_REGISTER rsp
|
|
decl PER_CPU_VAR(irq_count)
|
|
jmp error_exit
|
|
CFI_ENDPROC
|
|
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)
|
|
INTR_FRAME 1 (6*8)
|
|
/*CFI_REL_OFFSET gs,GS*/
|
|
/*CFI_REL_OFFSET fs,FS*/
|
|
/*CFI_REL_OFFSET es,ES*/
|
|
/*CFI_REL_OFFSET ds,DS*/
|
|
CFI_REL_OFFSET r11,8
|
|
CFI_REL_OFFSET rcx,0
|
|
movw %ds,%cx
|
|
cmpw %cx,0x10(%rsp)
|
|
CFI_REMEMBER_STATE
|
|
jne 1f
|
|
movw %es,%cx
|
|
cmpw %cx,0x18(%rsp)
|
|
jne 1f
|
|
movw %fs,%cx
|
|
cmpw %cx,0x20(%rsp)
|
|
jne 1f
|
|
movw %gs,%cx
|
|
cmpw %cx,0x28(%rsp)
|
|
jne 1f
|
|
/* All segments match their saved values => Category 2 (Bad IRET). */
|
|
movq (%rsp),%rcx
|
|
CFI_RESTORE rcx
|
|
movq 8(%rsp),%r11
|
|
CFI_RESTORE r11
|
|
addq $0x30,%rsp
|
|
CFI_ADJUST_CFA_OFFSET -0x30
|
|
pushq_cfi $0 /* RIP */
|
|
pushq_cfi %r11
|
|
pushq_cfi %rcx
|
|
jmp general_protection
|
|
CFI_RESTORE_STATE
|
|
1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
|
|
movq (%rsp),%rcx
|
|
CFI_RESTORE rcx
|
|
movq 8(%rsp),%r11
|
|
CFI_RESTORE r11
|
|
addq $0x30,%rsp
|
|
CFI_ADJUST_CFA_OFFSET -0x30
|
|
pushq_cfi $0
|
|
SAVE_ALL
|
|
jmp error_exit
|
|
CFI_ENDPROC
|
|
END(xen_failsafe_callback)
|
|
|
|
apicinterrupt XEN_HVM_EVTCHN_CALLBACK \
|
|
xen_hvm_callback_vector xen_evtchn_do_upcall
|
|
|
|
#endif /* CONFIG_XEN */
|
|
|
|
/*
|
|
* Some functions should be protected against kprobes
|
|
*/
|
|
.pushsection .kprobes.text, "ax"
|
|
|
|
paranoidzeroentry_ist debug do_debug DEBUG_STACK
|
|
paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
|
|
paranoiderrorentry stack_segment do_stack_segment
|
|
#ifdef CONFIG_XEN
|
|
zeroentry xen_debug do_debug
|
|
zeroentry xen_int3 do_int3
|
|
errorentry xen_stack_segment do_stack_segment
|
|
#endif
|
|
errorentry general_protection do_general_protection
|
|
errorentry page_fault do_page_fault
|
|
#ifdef CONFIG_KVM_GUEST
|
|
errorentry async_page_fault do_async_page_fault
|
|
#endif
|
|
#ifdef CONFIG_X86_MCE
|
|
paranoidzeroentry machine_check *machine_check_vector(%rip)
|
|
#endif
|
|
|
|
/*
|
|
* "Paranoid" exit path from exception stack.
|
|
* Paranoid because this is used by NMIs and cannot take
|
|
* any kernel state for granted.
|
|
* We don't do kernel preemption checks here, because only
|
|
* NMI should be common and it does not enable IRQs and
|
|
* cannot get reschedule ticks.
|
|
*
|
|
* "trace" is 0 for the NMI handler only, because irq-tracing
|
|
* is fundamentally NMI-unsafe. (we cannot change the soft and
|
|
* hard flags at once, atomically)
|
|
*/
|
|
|
|
/* ebx: no swapgs flag */
|
|
ENTRY(paranoid_exit)
|
|
DEFAULT_FRAME
|
|
DISABLE_INTERRUPTS(CLBR_NONE)
|
|
TRACE_IRQS_OFF_DEBUG
|
|
testl %ebx,%ebx /* swapgs needed? */
|
|
jnz paranoid_restore
|
|
testl $3,CS(%rsp)
|
|
jnz paranoid_userspace
|
|
paranoid_swapgs:
|
|
TRACE_IRQS_IRETQ 0
|
|
SWAPGS_UNSAFE_STACK
|
|
RESTORE_ALL 8
|
|
jmp irq_return
|
|
paranoid_restore:
|
|
TRACE_IRQS_IRETQ_DEBUG 0
|
|
RESTORE_ALL 8
|
|
jmp irq_return
|
|
paranoid_userspace:
|
|
GET_THREAD_INFO(%rcx)
|
|
movl TI_flags(%rcx),%ebx
|
|
andl $_TIF_WORK_MASK,%ebx
|
|
jz paranoid_swapgs
|
|
movq %rsp,%rdi /* &pt_regs */
|
|
call sync_regs
|
|
movq %rax,%rsp /* switch stack for scheduling */
|
|
testl $_TIF_NEED_RESCHED,%ebx
|
|
jnz paranoid_schedule
|
|
movl %ebx,%edx /* arg3: thread flags */
|
|
TRACE_IRQS_ON
|
|
ENABLE_INTERRUPTS(CLBR_NONE)
|
|
xorl %esi,%esi /* arg2: oldset */
|
|
movq %rsp,%rdi /* arg1: &pt_regs */
|
|
call do_notify_resume
|
|
DISABLE_INTERRUPTS(CLBR_NONE)
|
|
TRACE_IRQS_OFF
|
|
jmp paranoid_userspace
|
|
paranoid_schedule:
|
|
TRACE_IRQS_ON
|
|
ENABLE_INTERRUPTS(CLBR_ANY)
|
|
call schedule
|
|
DISABLE_INTERRUPTS(CLBR_ANY)
|
|
TRACE_IRQS_OFF
|
|
jmp paranoid_userspace
|
|
CFI_ENDPROC
|
|
END(paranoid_exit)
|
|
|
|
/*
|
|
* Exception entry point. This expects an error code/orig_rax on the stack.
|
|
* returns in "no swapgs flag" in %ebx.
|
|
*/
|
|
ENTRY(error_entry)
|
|
XCPT_FRAME
|
|
CFI_ADJUST_CFA_OFFSET 15*8
|
|
/* oldrax contains error code */
|
|
cld
|
|
movq_cfi rdi, RDI+8
|
|
movq_cfi rsi, RSI+8
|
|
movq_cfi rdx, RDX+8
|
|
movq_cfi rcx, RCX+8
|
|
movq_cfi rax, RAX+8
|
|
movq_cfi r8, R8+8
|
|
movq_cfi r9, R9+8
|
|
movq_cfi r10, R10+8
|
|
movq_cfi r11, R11+8
|
|
movq_cfi rbx, RBX+8
|
|
movq_cfi rbp, RBP+8
|
|
movq_cfi r12, R12+8
|
|
movq_cfi r13, R13+8
|
|
movq_cfi r14, R14+8
|
|
movq_cfi r15, R15+8
|
|
xorl %ebx,%ebx
|
|
testl $3,CS+8(%rsp)
|
|
je 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. The exception handlers after iret run with
|
|
* kernel gs again, so don't set the user space flag. B stepping K8s
|
|
* sometimes report an truncated RIP for IRET exceptions returning to
|
|
* compat mode. Check for these here too.
|
|
*/
|
|
error_kernelspace:
|
|
incl %ebx
|
|
leaq irq_return(%rip),%rcx
|
|
cmpq %rcx,RIP+8(%rsp)
|
|
je error_swapgs
|
|
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)
|
|
jmp error_swapgs
|
|
CFI_ENDPROC
|
|
END(error_entry)
|
|
|
|
|
|
/* ebx: no swapgs flag (1: don't need swapgs, 0: need it) */
|
|
ENTRY(error_exit)
|
|
DEFAULT_FRAME
|
|
movl %ebx,%eax
|
|
RESTORE_REST
|
|
DISABLE_INTERRUPTS(CLBR_NONE)
|
|
TRACE_IRQS_OFF
|
|
GET_THREAD_INFO(%rcx)
|
|
testl %eax,%eax
|
|
jne retint_kernel
|
|
LOCKDEP_SYS_EXIT_IRQ
|
|
movl TI_flags(%rcx),%edx
|
|
movl $_TIF_WORK_MASK,%edi
|
|
andl %edi,%edx
|
|
jnz retint_careful
|
|
jmp retint_swapgs
|
|
CFI_ENDPROC
|
|
END(error_exit)
|
|
|
|
/*
|
|
* Test if a given stack is an NMI stack or not.
|
|
*/
|
|
.macro test_in_nmi reg stack nmi_ret normal_ret
|
|
cmpq %\reg, \stack
|
|
ja \normal_ret
|
|
subq $EXCEPTION_STKSZ, %\reg
|
|
cmpq %\reg, \stack
|
|
jb \normal_ret
|
|
jmp \nmi_ret
|
|
.endm
|
|
|
|
/* runs on exception stack */
|
|
ENTRY(nmi)
|
|
INTR_FRAME
|
|
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 out temp variable throughout */
|
|
pushq_cfi %rdx
|
|
CFI_REL_OFFSET rdx, 0
|
|
|
|
/*
|
|
* 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
|
|
test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi
|
|
CFI_REMEMBER_STATE
|
|
|
|
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 -6*8(%rsp), %rdx
|
|
movq %rdx, %rsp
|
|
CFI_ADJUST_CFA_OFFSET 6*8
|
|
pushq_cfi $__KERNEL_DS
|
|
pushq_cfi %rdx
|
|
pushfq_cfi
|
|
pushq_cfi $__KERNEL_CS
|
|
pushq_cfi $repeat_nmi
|
|
|
|
/* Put stack back */
|
|
addq $(11*8), %rsp
|
|
CFI_ADJUST_CFA_OFFSET -11*8
|
|
|
|
nested_nmi_out:
|
|
popq_cfi %rdx
|
|
CFI_RESTORE rdx
|
|
|
|
/* No need to check faults here */
|
|
INTERRUPT_RETURN
|
|
|
|
CFI_RESTORE_STATE
|
|
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 |
|
|
* +-------------------------+
|
|
* | Saved SS |
|
|
* | Saved Return RSP |
|
|
* | Saved RFLAGS |
|
|
* | Saved CS |
|
|
* | Saved RIP |
|
|
* +-------------------------+
|
|
* | copied SS |
|
|
* | copied Return RSP |
|
|
* | copied RFLAGS |
|
|
* | copied CS |
|
|
* | copied 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
|
|
CFI_RESTORE rdx
|
|
|
|
/* Set the NMI executing variable on the stack. */
|
|
pushq_cfi $1
|
|
|
|
/* Copy the stack frame to the Saved frame */
|
|
.rept 5
|
|
pushq_cfi 6*8(%rsp)
|
|
.endr
|
|
CFI_DEF_CFA_OFFSET SS+8-RIP
|
|
|
|
/* 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, 5*8(%rsp)
|
|
|
|
/* Make another copy, this one may be modified by nested NMIs */
|
|
.rept 5
|
|
pushq_cfi 4*8(%rsp)
|
|
.endr
|
|
CFI_DEF_CFA_OFFSET SS+8-RIP
|
|
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_cfi $-1 /* ORIG_RAX: no syscall to restart */
|
|
subq $ORIG_RAX-R15, %rsp
|
|
CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
|
|
/*
|
|
* Use save_paranoid 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 save_paranoid
|
|
DEFAULT_FRAME 0
|
|
|
|
/*
|
|
* 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_ALL 8
|
|
/* Clear the NMI executing stack variable */
|
|
movq $0, 10*8(%rsp)
|
|
jmp irq_return
|
|
CFI_ENDPROC
|
|
END(nmi)
|
|
|
|
ENTRY(ignore_sysret)
|
|
CFI_STARTPROC
|
|
mov $-ENOSYS,%eax
|
|
sysret
|
|
CFI_ENDPROC
|
|
END(ignore_sysret)
|
|
|
|
/*
|
|
* End of kprobes section
|
|
*/
|
|
.popsection
|