#include <asm/hw_irq.h>
#include <asm/page.h>
#include <asm/irqflags.h>
+#include <asm/paravirt.h>
+#include <asm/ftrace.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
+#ifdef CONFIG_FUNCTION_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE
+ENTRY(mcount)
+ retq
+END(mcount)
+
+ENTRY(ftrace_caller)
+ cmpl $0, function_trace_stop
+ jne ftrace_stub
+
+ /* taken from glibc */
+ subq $0x38, %rsp
+ movq %rax, (%rsp)
+ movq %rcx, 8(%rsp)
+ movq %rdx, 16(%rsp)
+ movq %rsi, 24(%rsp)
+ movq %rdi, 32(%rsp)
+ movq %r8, 40(%rsp)
+ movq %r9, 48(%rsp)
+
+ movq 0x38(%rsp), %rdi
+ movq 8(%rbp), %rsi
+ subq $MCOUNT_INSN_SIZE, %rdi
+
+.globl ftrace_call
+ftrace_call:
+ call ftrace_stub
+
+ movq 48(%rsp), %r9
+ movq 40(%rsp), %r8
+ movq 32(%rsp), %rdi
+ movq 24(%rsp), %rsi
+ movq 16(%rsp), %rdx
+ movq 8(%rsp), %rcx
+ movq (%rsp), %rax
+ addq $0x38, %rsp
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+.globl ftrace_graph_call
+ftrace_graph_call:
+ jmp ftrace_stub
+#endif
+
+.globl ftrace_stub
+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
+
+.globl ftrace_stub
+ftrace_stub:
+ retq
+
+trace:
+ /* taken from glibc */
+ subq $0x38, %rsp
+ movq %rax, (%rsp)
+ movq %rcx, 8(%rsp)
+ movq %rdx, 16(%rsp)
+ movq %rsi, 24(%rsp)
+ movq %rdi, 32(%rsp)
+ movq %r8, 40(%rsp)
+ movq %r9, 48(%rsp)
+
+ movq 0x38(%rsp), %rdi
+ movq 8(%rbp), %rsi
+ subq $MCOUNT_INSN_SIZE, %rdi
+
+ call *ftrace_trace_function
+
+ movq 48(%rsp), %r9
+ movq 40(%rsp), %r8
+ movq 32(%rsp), %rdi
+ movq 24(%rsp), %rsi
+ movq 16(%rsp), %rdx
+ movq 8(%rsp), %rcx
+ movq (%rsp), %rax
+ addq $0x38, %rsp
+
+ 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
+
+ subq $0x38, %rsp
+ movq %rax, (%rsp)
+ movq %rcx, 8(%rsp)
+ movq %rdx, 16(%rsp)
+ movq %rsi, 24(%rsp)
+ movq %rdi, 32(%rsp)
+ movq %r8, 40(%rsp)
+ movq %r9, 48(%rsp)
+
+ leaq 8(%rbp), %rdi
+ movq 0x38(%rsp), %rsi
+ subq $MCOUNT_INSN_SIZE, %rsi
+
+ call prepare_ftrace_return
+
+ movq 48(%rsp), %r9
+ movq 40(%rsp), %r8
+ movq 32(%rsp), %rdi
+ movq 24(%rsp), %rsi
+ movq 16(%rsp), %rdx
+ movq 8(%rsp), %rcx
+ movq (%rsp), %rax
+ addq $0x38, %rsp
+ retq
+END(ftrace_graph_caller)
+
+
+.globl return_to_handler
+return_to_handler:
+ subq $80, %rsp
+
+ movq %rax, (%rsp)
+ movq %rcx, 8(%rsp)
+ movq %rdx, 16(%rsp)
+ movq %rsi, 24(%rsp)
+ movq %rdi, 32(%rsp)
+ movq %r8, 40(%rsp)
+ movq %r9, 48(%rsp)
+ movq %r10, 56(%rsp)
+ movq %r11, 64(%rsp)
+
+ call ftrace_return_to_handler
+
+ movq %rax, 72(%rsp)
+ movq 64(%rsp), %r11
+ movq 56(%rsp), %r10
+ movq 48(%rsp), %r9
+ movq 40(%rsp), %r8
+ movq 32(%rsp), %rdi
+ movq 24(%rsp), %rsi
+ movq 16(%rsp), %rdx
+ movq 8(%rsp), %rcx
+ movq (%rsp), %rax
+ addq $72, %rsp
+ retq
+#endif
+
+
#ifndef CONFIG_PREEMPT
#define retint_kernel retint_restore_args
#endif
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_usergs_sysret64)
+ swapgs
+ sysretq
+#endif /* CONFIG_PARAVIRT */
+
.macro TRACE_IRQS_IRETQ offset=ARGOFFSET
#ifdef CONFIG_TRACE_IRQFLAGS
.macro FAKE_STACK_FRAME child_rip
/* push in order ss, rsp, eflags, cs, rip */
xorl %eax, %eax
- pushq %rax /* ss */
+ pushq $__KERNEL_DS /* ss */
CFI_ADJUST_CFA_OFFSET 8
/*CFI_REL_OFFSET ss,0*/
pushq %rax /* rsp */
ENTRY(ret_from_fork)
CFI_DEFAULT_STACK
push kernel_eflags(%rip)
- CFI_ADJUST_CFA_OFFSET 4
+ CFI_ADJUST_CFA_OFFSET 8
popf # reset kernel eflags
- CFI_ADJUST_CFA_OFFSET -4
+ CFI_ADJUST_CFA_OFFSET -8
call schedule_tail
GET_THREAD_INFO(%rcx)
- testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),threadinfo_flags(%rcx)
+ testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
jnz rff_trace
rff_action:
RESTORE_REST
testl $3,CS-ARGOFFSET(%rsp) # from kernel_thread?
je int_ret_from_sys_call
- testl $_TIF_IA32,threadinfo_flags(%rcx)
+ testl $_TIF_IA32,TI_flags(%rcx)
jnz int_ret_from_sys_call
RESTORE_TOP_OF_STACK %rdi,ARGOFFSET
jmp ret_from_sys_call
CFI_DEF_CFA rsp,PDA_STACKOFFSET
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
- swapgs
+ 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.
+ */
+ENTRY(system_call_after_swapgs)
+
movq %rsp,%gs:pda_oldrsp
movq %gs:pda_kernelstack,%rsp
/*
* No need to follow this irqs off/on section - it's straight
* and short:
*/
- sti
+ ENABLE_INTERRUPTS(CLBR_NONE)
SAVE_ARGS 8,1
movq %rax,ORIG_RAX-ARGOFFSET(%rsp)
movq %rcx,RIP-ARGOFFSET(%rsp)
CFI_REL_OFFSET rip,RIP-ARGOFFSET
GET_THREAD_INFO(%rcx)
- testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SECCOMP),threadinfo_flags(%rcx)
+ testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%rcx)
jnz tracesys
+system_call_fastpath:
cmpq $__NR_syscall_max,%rax
ja badsys
movq %r10,%rcx
sysret_check:
LOCKDEP_SYS_EXIT
GET_THREAD_INFO(%rcx)
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- movl threadinfo_flags(%rcx),%edx
+ movl TI_flags(%rcx),%edx
andl %edi,%edx
jnz sysret_careful
CFI_REMEMBER_STATE
CFI_REGISTER rip,rcx
RESTORE_ARGS 0,-ARG_SKIP,1
/*CFI_REGISTER rflags,r11*/
- movq %gs:pda_oldrsp,%rsp
- swapgs
- sysretq
+ movq %gs:pda_oldrsp, %rsp
+ USERGS_SYSRET64
CFI_RESTORE_STATE
/* Handle reschedules */
bt $TIF_NEED_RESCHED,%edx
jnc sysret_signal
TRACE_IRQS_ON
- sti
+ ENABLE_INTERRUPTS(CLBR_NONE)
pushq %rdi
CFI_ADJUST_CFA_OFFSET 8
call schedule
/* Handle a signal */
sysret_signal:
TRACE_IRQS_ON
- sti
- testl $(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
- jz 1f
-
- /* Really a signal */
+ ENABLE_INTERRUPTS(CLBR_NONE)
+#ifdef CONFIG_AUDITSYSCALL
+ bt $TIF_SYSCALL_AUDIT,%edx
+ jc sysret_audit
+#endif
/* edx: work flags (arg3) */
leaq do_notify_resume(%rip),%rax
leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1
xorl %esi,%esi # oldset -> arg2
call ptregscall_common
-1: movl $_TIF_NEED_RESCHED,%edi
+ movl $_TIF_WORK_MASK,%edi
/* Use IRET because user could have changed frame. This
works because ptregscall_common has called FIXUP_TOP_OF_STACK. */
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
jmp int_with_check
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,%rsi /* second arg, syscall return value */
+ cmpq $0,%rax /* is it < 0? */
+ setl %al /* 1 if so, 0 if not */
+ movzbl %al,%edi /* zero-extend that into %edi */
+ inc %edi /* first arg, 0->1(AUDITSC_SUCCESS), 1->2(AUDITSC_FAILURE) */
+ 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(%rcx)
+ jz auditsys
+#endif
SAVE_REST
- movq $-ENOSYS,RAX(%rsp)
+ movq $-ENOSYS,RAX(%rsp) /* ptrace can change this for a bad syscall */
FIXUP_TOP_OF_STACK %rdi
movq %rsp,%rdi
call syscall_trace_enter
- LOAD_ARGS ARGOFFSET /* reload args from stack in case ptrace changed it */
+ /*
+ * 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
cmpq $__NR_syscall_max,%rax
- movq $-ENOSYS,%rcx
- cmova %rcx,%rax
- ja 1f
+ ja int_ret_from_sys_call /* RAX(%rsp) set to -ENOSYS above */
movq %r10,%rcx /* fixup for C */
call *sys_call_table(,%rax,8)
-1: movq %rax,RAX-ARGOFFSET(%rsp)
+ movq %rax,RAX-ARGOFFSET(%rsp)
/* Use IRET because user could have changed frame */
/*
* Has correct top of stack, but partial stack frame.
*/
.globl int_ret_from_sys_call
+ .globl int_with_check
int_ret_from_sys_call:
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl $3,CS-ARGOFFSET(%rsp)
je retint_restore_args
int_with_check:
LOCKDEP_SYS_EXIT_IRQ
GET_THREAD_INFO(%rcx)
- movl threadinfo_flags(%rcx),%edx
+ movl TI_flags(%rcx),%edx
andl %edi,%edx
jnz int_careful
- andl $~TS_COMPAT,threadinfo_status(%rcx)
+ andl $~TS_COMPAT,TI_status(%rcx)
jmp retint_swapgs
/* Either reschedule or signal or syscall exit tracking needed. */
bt $TIF_NEED_RESCHED,%edx
jnc int_very_careful
TRACE_IRQS_ON
- sti
+ ENABLE_INTERRUPTS(CLBR_NONE)
pushq %rdi
CFI_ADJUST_CFA_OFFSET 8
call schedule
popq %rdi
CFI_ADJUST_CFA_OFFSET -8
- cli
+ 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
- sti
+ ENABLE_INTERRUPTS(CLBR_NONE)
SAVE_REST
/* Check for syscall exit trace */
- testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP),%edx
+ testl $_TIF_WORK_SYSCALL_EXIT,%edx
jz int_signal
pushq %rdi
CFI_ADJUST_CFA_OFFSET 8
call syscall_trace_leave
popq %rdi
CFI_ADJUST_CFA_OFFSET -8
- andl $~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP),%edi
+ andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
jmp int_restore_rest
int_signal:
- testl $(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
+ 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_NEED_RESCHED,%edi
+1: movl $_TIF_WORK_MASK,%edi
int_restore_rest:
RESTORE_REST
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
jmp int_with_check
CFI_ENDPROC
PTREGSCALL stub_clone, sys_clone, %r8
PTREGSCALL stub_fork, sys_fork, %rdi
PTREGSCALL stub_vfork, sys_vfork, %rdi
- PTREGSCALL stub_rt_sigsuspend, sys_rt_sigsuspend, %rdx
PTREGSCALL stub_sigaltstack, sys_sigaltstack, %rdx
PTREGSCALL stub_iopl, sys_iopl, %rsi
CFI_REGISTER rip, r11
SAVE_REST
FIXUP_TOP_OF_STACK %r11
+ movq %rsp, %rcx
call sys_execve
RESTORE_TOP_OF_STACK %r11
movq %rax,RAX(%rsp)
SAVE_ARGS
leaq -ARGOFFSET(%rsp),%rdi # arg1 for handler
pushq %rbp
+ /*
+ * Save rbp twice: One is for marking the stack frame, as usual, and the
+ * other, to fill pt_regs properly. This is because bx comes right
+ * before the last saved register in that structure, and not bp. If the
+ * base pointer were in the place bx is today, this would not be needed.
+ */
+ movq %rbp, -8(%rsp)
CFI_ADJUST_CFA_OFFSET 8
CFI_REL_OFFSET rbp, 0
movq %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
testl $3,CS(%rdi)
je 1f
- swapgs
+ SWAPGS
/* irqcount 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
interrupt do_IRQ
/* 0(%rsp): oldrsp-ARGOFFSET */
ret_from_intr:
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
decl %gs:pda_irqcount
leaveq
movl $_TIF_WORK_MASK,%edi
retint_check:
LOCKDEP_SYS_EXIT_IRQ
- movl threadinfo_flags(%rcx),%edx
+ movl TI_flags(%rcx),%edx
andl %edi,%edx
CFI_REMEMBER_STATE
jnz retint_careful
/*
* The iretq could re-enable interrupts:
*/
- cli
+ DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_IRETQ
- swapgs
+ SWAPGS
jmp restore_args
retint_restore_args: /* return to kernel space */
- cli
+ DISABLE_INTERRUPTS(CLBR_ANY)
/*
* The iretq could re-enable interrupts:
*/
TRACE_IRQS_IRETQ
restore_args:
- RESTORE_ARGS 0,8,0
-iret_label:
+ RESTORE_ARGS 0,8,0
+
+irq_return:
+ INTERRUPT_RETURN
+
+ .section __ex_table, "a"
+ .quad irq_return, bad_iret
+ .previous
+
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_iret)
iretq
.section __ex_table,"a"
- .quad iret_label,bad_iret
+ .quad native_iret, bad_iret
.previous
+#endif
+
.section .fixup,"ax"
- /* force a signal here? this matches i386 behaviour */
- /* running with kernel gs */
bad_iret:
- movq $11,%rdi /* SIGSEGV */
- TRACE_IRQS_ON
- sti
- jmp do_exit
- .previous
-
+ /*
+ * 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
- sti
+ ENABLE_INTERRUPTS(CLBR_NONE)
pushq %rdi
CFI_ADJUST_CFA_OFFSET 8
call schedule
popq %rdi
CFI_ADJUST_CFA_OFFSET -8
GET_THREAD_INFO(%rcx)
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
jmp retint_check
retint_signal:
- testl $(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY),%edx
+ testl $_TIF_DO_NOTIFY_MASK,%edx
jz retint_swapgs
TRACE_IRQS_ON
- sti
+ 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
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- movl $_TIF_NEED_RESCHED,%edi
GET_THREAD_INFO(%rcx)
- jmp retint_check
+ 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,threadinfo_preempt_count(%rcx)
+ cmpl $0,TI_preempt_count(%rcx)
jnz retint_restore_args
- bt $TIF_NEED_RESCHED,threadinfo_flags(%rcx)
+ bt $TIF_NEED_RESCHED,TI_flags(%rcx)
jnc retint_restore_args
bt $9,EFLAGS-ARGOFFSET(%rsp) /* interrupts off? */
jnc retint_restore_args
ENTRY(call_function_interrupt)
apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt
END(call_function_interrupt)
+ENTRY(call_function_single_interrupt)
+ apicinterrupt CALL_FUNCTION_SINGLE_VECTOR,smp_call_function_single_interrupt
+END(call_function_single_interrupt)
ENTRY(irq_move_cleanup_interrupt)
apicinterrupt IRQ_MOVE_CLEANUP_VECTOR,smp_irq_move_cleanup_interrupt
END(irq_move_cleanup_interrupt)
apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt
END(apic_timer_interrupt)
+ENTRY(uv_bau_message_intr1)
+ apicinterrupt 220,uv_bau_message_interrupt
+END(uv_bau_message_intr1)
+
ENTRY(error_interrupt)
apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt
END(error_interrupt)
*/
.macro zeroentry sym
INTR_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq $0 /* push error code/oldrax */
CFI_ADJUST_CFA_OFFSET 8
pushq %rax /* push real oldrax to the rdi slot */
.macro errorentry sym
XCPT_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq %rax
CFI_ADJUST_CFA_OFFSET 8
CFI_REL_OFFSET rax,0
rdmsr
testl %edx,%edx
js 1f
- swapgs
+ SWAPGS
xorl %ebx,%ebx
1:
.if \ist
movq %gs:pda_data_offset, %rbp
.endif
+ .if \irqtrace
+ TRACE_IRQS_OFF
+ .endif
movq %rsp,%rdi
movq ORIG_RAX(%rsp),%rsi
movq $-1,ORIG_RAX(%rsp)
.if \ist
addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
.endif
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
.if \irqtrace
TRACE_IRQS_OFF
.endif
.if \trace
TRACE_IRQS_IRETQ 0
.endif
- swapgs
+ SWAPGS_UNSAFE_STACK
paranoid_restore\trace:
RESTORE_ALL 8
- iretq
+ jmp irq_return
paranoid_userspace\trace:
GET_THREAD_INFO(%rcx)
- movl threadinfo_flags(%rcx),%ebx
+ movl TI_flags(%rcx),%ebx
andl $_TIF_WORK_MASK,%ebx
jz paranoid_swapgs\trace
movq %rsp,%rdi /* &pt_regs */
.if \trace
TRACE_IRQS_ON
.endif
- sti
+ ENABLE_INTERRUPTS(CLBR_NONE)
xorl %esi,%esi /* arg2: oldset */
movq %rsp,%rdi /* arg1: &pt_regs */
call do_notify_resume
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
.if \trace
TRACE_IRQS_OFF
.endif
.if \trace
TRACE_IRQS_ON
.endif
- sti
+ ENABLE_INTERRUPTS(CLBR_ANY)
call schedule
- cli
+ DISABLE_INTERRUPTS(CLBR_ANY)
.if \trace
TRACE_IRQS_OFF
.endif
testl $3,CS(%rsp)
je error_kernelspace
error_swapgs:
- swapgs
-error_sti:
+ SWAPGS
+error_sti:
+ TRACE_IRQS_OFF
movq %rdi,RDI(%rsp)
CFI_REL_OFFSET rdi,RDI
movq %rsp,%rdi
error_exit:
movl %ebx,%eax
RESTORE_REST
- cli
+ DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
GET_THREAD_INFO(%rcx)
testl %eax,%eax
jne retint_kernel
LOCKDEP_SYS_EXIT_IRQ
- movl threadinfo_flags(%rcx),%edx
+ movl TI_flags(%rcx),%edx
movl $_TIF_WORK_MASK,%edi
andl %edi,%edx
jnz retint_careful
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)
+ leaq irq_return(%rip),%rcx
+ cmpq %rcx,RIP(%rsp)
je error_swapgs
- movl %ebp,%ebp /* zero extend */
- cmpq %rbp,RIP(%rsp)
+ movl %ecx,%ecx /* zero extend */
+ cmpq %rcx,RIP(%rsp)
je error_swapgs
cmpq $gs_change,RIP(%rsp)
je error_swapgs
/* Reload gs selector with exception handling */
/* edi: new selector */
-ENTRY(load_gs_index)
+ENTRY(native_load_gs_index)
CFI_STARTPROC
pushf
CFI_ADJUST_CFA_OFFSET 8
- cli
- swapgs
+ DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI))
+ SWAPGS
gs_change:
movl %edi,%gs
2: mfence /* workaround */
- swapgs
+ SWAPGS
popf
CFI_ADJUST_CFA_OFFSET -8
ret
CFI_ENDPROC
-ENDPROC(load_gs_index)
+ENDPROC(native_load_gs_index)
.section __ex_table,"a"
.align 8
.section .fixup,"ax"
/* running with kernelgs */
bad_gs:
- swapgs /* switch back to user gs */
+ SWAPGS /* switch back to user gs */
xorl %eax,%eax
movl %eax,%gs
jmp 2b
movq %rsi, %rdi
call *%rax
# exit
- xorl %edi, %edi
+ mov %eax, %edi
call do_exit
CFI_ENDPROC
ENDPROC(child_rip)
* 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)
+ * 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
+ * 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
END(simd_coprocessor_error)
ENTRY(device_not_available)
- zeroentry math_state_restore
+ zeroentry do_device_not_available
END(device_not_available)
/* runs on exception stack */
KPROBE_ENTRY(debug)
INTR_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq $0
CFI_ADJUST_CFA_OFFSET 8
paranoidentry do_debug, DEBUG_STACK
/* runs on exception stack */
KPROBE_ENTRY(nmi)
INTR_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq $-1
CFI_ADJUST_CFA_OFFSET 8
paranoidentry do_nmi, 0, 0
KPROBE_ENTRY(int3)
INTR_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq $0
CFI_ADJUST_CFA_OFFSET 8
paranoidentry do_int3, DEBUG_STACK
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
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
paranoidentry do_double_fault
jmp paranoid_exit1
CFI_ENDPROC
/* runs on exception stack */
ENTRY(stack_segment)
XCPT_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
paranoidentry do_stack_segment
jmp paranoid_exit1
CFI_ENDPROC
/* runs on exception stack */
ENTRY(machine_check)
INTR_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq $0
CFI_ADJUST_CFA_OFFSET 8
paranoidentry do_machine_check
sysret
CFI_ENDPROC
ENDPROC(ignore_sysret)
+
+#ifdef CONFIG_XEN
+ENTRY(xen_hypervisor_callback)
+ zeroentry xen_do_hypervisor_callback
+END(xen_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
+ CFI_DEFAULT_STACK
+11: incl %gs:pda_irqcount
+ movq %rsp,%rbp
+ CFI_DEF_CFA_REGISTER rbp
+ cmovzq %gs:pda_irqstackptr,%rsp
+ pushq %rbp # backlink for old unwinder
+ call xen_evtchn_do_upcall
+ popq %rsp
+ CFI_DEF_CFA_REGISTER rsp
+ decl %gs:pda_irqcount
+ jmp error_exit
+ CFI_ENDPROC
+END(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)
+ framesz = (RIP-0x30) /* workaround buggy gas */
+ _frame framesz
+ CFI_REL_OFFSET rcx, 0
+ CFI_REL_OFFSET r11, 8
+ 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 $0
+ CFI_ADJUST_CFA_OFFSET 8
+ pushq %r11
+ CFI_ADJUST_CFA_OFFSET 8
+ pushq %rcx
+ CFI_ADJUST_CFA_OFFSET 8
+ 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 $0
+ CFI_ADJUST_CFA_OFFSET 8
+ SAVE_ALL
+ jmp error_exit
+ CFI_ENDPROC
+END(xen_failsafe_callback)
+
+#endif /* CONFIG_XEN */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff