entry_64.s

linux 内核源代码

	
	/* edi: workmask, edx: work */
retint_careful:
	CFI_RESTORE_STATE
	bt    $TIF_NEED_RESCHED,%edx
	jnc   retint_signal
	TRACE_IRQS_ON
	sti
	pushq %rdi
	CFI_ADJUST_CFA_OFFSET	8
	call  schedule
	popq %rdi		
	CFI_ADJUST_CFA_OFFSET	-8
	GET_THREAD_INFO(%rcx)
	cli
	TRACE_IRQS_OFF
	jmp retint_check
	
retint_signal:
	testl $(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
	jz    retint_swapgs
	TRACE_IRQS_ON
	sti
	SAVE_REST
	movq $-1,ORIG_RAX(%rsp) 			
	xorl %esi,%esi		# oldset
	movq %rsp,%rdi		# &pt_regs
	call do_notify_resume
	RESTORE_REST
	cli
	TRACE_IRQS_OFF
	movl $_TIF_NEED_RESCHED,%edi
	GET_THREAD_INFO(%rcx)
	jmp retint_check

#ifdef CONFIG_PREEMPT
	/* Returning to kernel space. Check if we need preemption */
	/* rcx:	 threadinfo. interrupts off. */
ENTRY(retint_kernel)
	cmpl $0,threadinfo_preempt_count(%rcx)
	jnz  retint_restore_args
	bt  $TIF_NEED_RESCHED,threadinfo_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)
	
/*
 * APIC interrupts.
 */		
	.macro apicinterrupt num,func
	INTR_FRAME
	pushq $~(\num)
	CFI_ADJUST_CFA_OFFSET 8
	interrupt \func
	jmp ret_from_intr
	CFI_ENDPROC
	.endm

ENTRY(thermal_interrupt)
	apicinterrupt THERMAL_APIC_VECTOR,smp_thermal_interrupt
END(thermal_interrupt)

ENTRY(threshold_interrupt)
	apicinterrupt THRESHOLD_APIC_VECTOR,mce_threshold_interrupt
END(threshold_interrupt)

#ifdef CONFIG_SMP	
ENTRY(reschedule_interrupt)
	apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt
END(reschedule_interrupt)

	.macro INVALIDATE_ENTRY num
ENTRY(invalidate_interrupt\num)
	apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt	
END(invalidate_interrupt\num)
	.endm

	INVALIDATE_ENTRY 0
	INVALIDATE_ENTRY 1
	INVALIDATE_ENTRY 2
	INVALIDATE_ENTRY 3
	INVALIDATE_ENTRY 4
	INVALIDATE_ENTRY 5
	INVALIDATE_ENTRY 6
	INVALIDATE_ENTRY 7

ENTRY(call_function_interrupt)
	apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt
END(call_function_interrupt)
ENTRY(irq_move_cleanup_interrupt)
	apicinterrupt IRQ_MOVE_CLEANUP_VECTOR,smp_irq_move_cleanup_interrupt
END(irq_move_cleanup_interrupt)
#endif

ENTRY(apic_timer_interrupt)
	apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt
END(apic_timer_interrupt)

ENTRY(error_interrupt)
	apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt
END(error_interrupt)

ENTRY(spurious_interrupt)
	apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt
END(spurious_interrupt)
				
/*
 * Exception entry points.
 */ 		
	.macro zeroentry sym
	INTR_FRAME
	pushq $0	/* push error code/oldrax */ 
	CFI_ADJUST_CFA_OFFSET 8
	pushq %rax	/* push real oldrax to the rdi slot */ 
	CFI_ADJUST_CFA_OFFSET 8
	CFI_REL_OFFSET rax,0
	leaq  \sym(%rip),%rax
	jmp error_entry
	CFI_ENDPROC
	.endm	

	.macro errorentry sym
	XCPT_FRAME
	pushq %rax
	CFI_ADJUST_CFA_OFFSET 8
	CFI_REL_OFFSET rax,0
	leaq  \sym(%rip),%rax
	jmp error_entry
	CFI_ENDPROC
	.endm

	/* error code is on the stack already */
	/* handle NMI like exceptions that can happen everywhere */
	.macro paranoidentry sym, ist=0, irqtrace=1
	SAVE_ALL
	cld
	movl $1,%ebx
	movl  $MSR_GS_BASE,%ecx
	rdmsr
	testl %edx,%edx
	js    1f
	swapgs
	xorl  %ebx,%ebx
1:
	.if \ist
	movq	%gs:pda_data_offset, %rbp
	.endif
	movq %rsp,%rdi
	movq ORIG_RAX(%rsp),%rsi
	movq $-1,ORIG_RAX(%rsp)
	.if \ist
	subq	$EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
	.endif
	call \sym
	.if \ist
	addq	$EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
	.endif
	cli
	.if \irqtrace
	TRACE_IRQS_OFF
	.endif
	.endm

	/*
 	 * "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)
	 */
	.macro paranoidexit trace=1
	/* ebx:	no swapgs flag */
paranoid_exit\trace:
	testl %ebx,%ebx				/* swapgs needed? */
	jnz paranoid_restore\trace
	testl $3,CS(%rsp)
	jnz   paranoid_userspace\trace
paranoid_swapgs\trace:
	.if \trace
	TRACE_IRQS_IRETQ 0
	.endif
	swapgs
paranoid_restore\trace:
	RESTORE_ALL 8
	iretq
paranoid_userspace\trace:
	GET_THREAD_INFO(%rcx)
	movl threadinfo_flags(%rcx),%ebx
	andl $_TIF_WORK_MASK,%ebx
	jz paranoid_swapgs\trace
	movq %rsp,%rdi			/* &pt_regs */
	call sync_regs
	movq %rax,%rsp			/* switch stack for scheduling */
	testl $_TIF_NEED_RESCHED,%ebx
	jnz paranoid_schedule\trace
	movl %ebx,%edx			/* arg3: thread flags */
	.if \trace
	TRACE_IRQS_ON
	.endif
	sti
	xorl %esi,%esi 			/* arg2: oldset */
	movq %rsp,%rdi 			/* arg1: &pt_regs */
	call do_notify_resume
	cli
	.if \trace
	TRACE_IRQS_OFF
	.endif
	jmp paranoid_userspace\trace
paranoid_schedule\trace:
	.if \trace
	TRACE_IRQS_ON
	.endif
	sti
	call schedule
	cli
	.if \trace
	TRACE_IRQS_OFF
	.endif
	jmp paranoid_userspace\trace
	CFI_ENDPROC
	.endm

/*
 * Exception entry point. This expects an error code/orig_rax on the stack
 * and the exception handler in %rax.	
 */ 		  				
KPROBE_ENTRY(error_entry)
	_frame RDI
	CFI_REL_OFFSET rax,0
	/* rdi slot contains rax, oldrax contains error code */
	cld	
	subq  $14*8,%rsp
	CFI_ADJUST_CFA_OFFSET	(14*8)
	movq %rsi,13*8(%rsp)
	CFI_REL_OFFSET	rsi,RSI
	movq 14*8(%rsp),%rsi	/* load rax from rdi slot */
	CFI_REGISTER	rax,rsi
	movq %rdx,12*8(%rsp)
	CFI_REL_OFFSET	rdx,RDX
	movq %rcx,11*8(%rsp)
	CFI_REL_OFFSET	rcx,RCX
	movq %rsi,10*8(%rsp)	/* store rax */ 
	CFI_REL_OFFSET	rax,RAX
	movq %r8, 9*8(%rsp)
	CFI_REL_OFFSET	r8,R8
	movq %r9, 8*8(%rsp)
	CFI_REL_OFFSET	r9,R9
	movq %r10,7*8(%rsp)
	CFI_REL_OFFSET	r10,R10
	movq %r11,6*8(%rsp)
	CFI_REL_OFFSET	r11,R11
	movq %rbx,5*8(%rsp) 
	CFI_REL_OFFSET	rbx,RBX
	movq %rbp,4*8(%rsp) 
	CFI_REL_OFFSET	rbp,RBP
	movq %r12,3*8(%rsp) 
	CFI_REL_OFFSET	r12,R12
	movq %r13,2*8(%rsp) 
	CFI_REL_OFFSET	r13,R13
	movq %r14,1*8(%rsp) 
	CFI_REL_OFFSET	r14,R14
	movq %r15,(%rsp) 
	CFI_REL_OFFSET	r15,R15
	xorl %ebx,%ebx	
	testl $3,CS(%rsp)
	je  error_kernelspace
error_swapgs:	
	swapgs
error_sti:	
	movq %rdi,RDI(%rsp) 	
	CFI_REL_OFFSET	rdi,RDI
	movq %rsp,%rdi
	movq ORIG_RAX(%rsp),%rsi	/* get error code */ 
	movq $-1,ORIG_RAX(%rsp)
	call *%rax
	/* ebx:	no swapgs flag (1: don't need swapgs, 0: need it) */
error_exit:
	movl %ebx,%eax
	RESTORE_REST
	cli
	TRACE_IRQS_OFF
	GET_THREAD_INFO(%rcx)	
	testl %eax,%eax
	jne  retint_kernel
	LOCKDEP_SYS_EXIT_IRQ
	movl  threadinfo_flags(%rcx),%edx
	movl  $_TIF_WORK_MASK,%edi
	andl  %edi,%edx
	jnz  retint_careful
	jmp retint_swapgs
	CFI_ENDPROC

error_kernelspace:
	incl %ebx
       /* 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. */
	leaq iret_label(%rip),%rbp
	cmpq %rbp,RIP(%rsp) 
	je   error_swapgs
	movl %ebp,%ebp	/* zero extend */
	cmpq %rbp,RIP(%rsp) 
	je   error_swapgs
	cmpq $gs_change,RIP(%rsp)
        je   error_swapgs
	jmp  error_sti
KPROBE_END(error_entry)
	
       /* Reload gs selector with exception handling */
       /* edi:  new selector */ 
ENTRY(load_gs_index)
	CFI_STARTPROC
	pushf
	CFI_ADJUST_CFA_OFFSET 8
	cli
        swapgs
gs_change:     
        movl %edi,%gs   
2:	mfence		/* workaround */
	swapgs
        popf
	CFI_ADJUST_CFA_OFFSET -8
        ret
	CFI_ENDPROC
ENDPROC(load_gs_index)
       
        .section __ex_table,"a"
        .align 8
        .quad gs_change,bad_gs
        .previous
        .section .fixup,"ax"
	/* running with kernelgs */
bad_gs: 
	swapgs			/* switch back to user gs */
	xorl %eax,%eax
        movl %eax,%gs
        jmp  2b
        .previous       
	
/*
 * Create a kernel thread.
 *
 * C extern interface:
 *	extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 *
 * asm input arguments:
 *	rdi: fn, rsi: arg, rdx: flags
 */
ENTRY(kernel_thread)
	CFI_STARTPROC
	FAKE_STACK_FRAME $child_rip
	SAVE_ALL

	# rdi: flags, rsi: usp, rdx: will be &pt_regs
	movq %rdx,%rdi
	orq  kernel_thread_flags(%rip),%rdi
	movq $-1, %rsi
	movq %rsp, %rdx

	xorl %r8d,%r8d
	xorl %r9d,%r9d
	
	# clone now
	call do_fork
	movq %rax,RAX(%rsp)
	xorl %edi,%edi

	/*
	 * It isn't worth to check for reschedule here,
	 * so internally to the x86_64 port you can rely on kernel_thread()
	 * not to reschedule the child before returning, this avoids the need
	 * of hacks for example to fork off the per-CPU idle tasks.
         * [Hopefully no generic code relies on the reschedule -AK]	
	 */
	RESTORE_ALL
	UNFAKE_STACK_FRAME
	ret
	CFI_ENDPROC
ENDPROC(kernel_thread)
	
child_rip:
	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.
	 */
	movq %rdi, %rax
	movq %rsi, %rdi
	call *%rax
	# exit
	mov %eax, %edi
	call do_exit
	CFI_ENDPROC
ENDPROC(child_rip)

/*
 * execve(). This function needs to use IRET, not SYSRET, to set up all state properly.
 *
 * C extern interface:
 *	 extern long execve(char *name, char **argv, char **envp)
 *
 * asm input arguments:
 *	rdi: name, rsi: argv, rdx: envp
 *
 * We want to fallback into:
 *	extern long sys_execve(char *name, char **argv,char **envp, struct pt_regs regs)
 *
 * do_sys_execve asm fallback arguments:
 *	rdi: name, rsi: argv, rdx: envp, fake frame on the stack
 */
ENTRY(kernel_execve)
	CFI_STARTPROC
	FAKE_STACK_FRAME $0
	SAVE_ALL	
	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
ENDPROC(kernel_execve)

KPROBE_ENTRY(page_fault)
	errorentry do_page_fault
KPROBE_END(page_fault)

ENTRY(coprocessor_error)
	zeroentry do_coprocessor_error
END(coprocessor_error)

ENTRY(simd_coprocessor_error)
	zeroentry do_simd_coprocessor_error	
END(simd_coprocessor_error)

ENTRY(device_not_available)
	zeroentry math_state_restore
END(device_not_available)

	/* runs on exception stack */
KPROBE_ENTRY(debug)
 	INTR_FRAME
	pushq $0
	CFI_ADJUST_CFA_OFFSET 8		
	paranoidentry do_debug, DEBUG_STACK
	paranoidexit
KPROBE_END(debug)

	/* runs on exception stack */	
KPROBE_ENTRY(nmi)
	INTR_FRAME
	pushq $-1
	CFI_ADJUST_CFA_OFFSET 8
	paranoidentry do_nmi, 0, 0
#ifdef CONFIG_TRACE_IRQFLAGS
	paranoidexit 0
#else
	jmp paranoid_exit1
 	CFI_ENDPROC
#endif
KPROBE_END(nmi)

KPROBE_ENTRY(int3)
 	INTR_FRAME
 	pushq $0
 	CFI_ADJUST_CFA_OFFSET 8
 	paranoidentry do_int3, DEBUG_STACK
 	jmp paranoid_exit1
 	CFI_ENDPROC
KPROBE_END(int3)

ENTRY(overflow)
	zeroentry do_overflow
END(overflow)

ENTRY(bounds)
	zeroentry do_bounds
END(bounds)

ENTRY(invalid_op)
	zeroentry do_invalid_op	
END(invalid_op)

ENTRY(coprocessor_segment_overrun)
	zeroentry do_coprocessor_segment_overrun
END(coprocessor_segment_overrun)

ENTRY(reserved)
	zeroentry do_reserved
END(reserved)

	/* runs on exception stack */
ENTRY(double_fault)
	XCPT_FRAME
	paranoidentry do_double_fault
	jmp paranoid_exit1
	CFI_ENDPROC
END(double_fault)

ENTRY(invalid_TSS)
	errorentry do_invalid_TSS
END(invalid_TSS)

ENTRY(segment_not_present)
	errorentry do_segment_not_present
END(segment_not_present)

	/* runs on exception stack */
ENTRY(stack_segment)
	XCPT_FRAME
	paranoidentry do_stack_segment
	jmp paranoid_exit1
	CFI_ENDPROC
END(stack_segment)

KPROBE_ENTRY(general_protection)
	errorentry do_general_protection
KPROBE_END(general_protection)

ENTRY(alignment_check)
	errorentry do_alignment_check
END(alignment_check)

ENTRY(divide_error)
	zeroentry do_divide_error
END(divide_error)

ENTRY(spurious_interrupt_bug)
	zeroentry do_spurious_interrupt_bug
END(spurious_interrupt_bug)

#ifdef CONFIG_X86_MCE
	/* runs on exception stack */
ENTRY(machine_check)
	INTR_FRAME
	pushq $0
	CFI_ADJUST_CFA_OFFSET 8	
	paranoidentry do_machine_check
	jmp paranoid_exit1
	CFI_ENDPROC
END(machine_check)
#endif

/* Call softirq on interrupt stack. Interrupts are off. */
ENTRY(call_softirq)
	CFI_STARTPROC
	push %rbp
	CFI_ADJUST_CFA_OFFSET	8
	CFI_REL_OFFSET rbp,0
	mov  %rsp,%rbp
	CFI_DEF_CFA_REGISTER rbp
	incl %gs:pda_irqcount
	cmove %gs:pda_irqstackptr,%rsp
	push  %rbp			# backlink for old unwinder
	call __do_softirq
	leaveq
	CFI_DEF_CFA_REGISTER	rsp
	CFI_ADJUST_CFA_OFFSET   -8
	decl %gs:pda_irqcount
	ret
	CFI_ENDPROC
ENDPROC(call_softirq)

KPROBE_ENTRY(ignore_sysret)
	CFI_STARTPROC
	mov $-ENOSYS,%eax
	sysret
	CFI_ENDPROC
ENDPROC(ignore_sysret)