#include <asm/unistd.h>
#include <asm/thread_info.h>
#include <asm/hw_irq.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/irqflags.h>
#include <asm/paravirt.h>
#include <asm/ftrace.h>
+#include <asm/percpu.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
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)
+ MCOUNT_SAVE_FRAME
movq 0x38(%rsp), %rdi
movq 8(%rbp), %rsi
subq $MCOUNT_INSN_SIZE, %rdi
-.globl ftrace_call
-ftrace_call:
+GLOBAL(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
+ MCOUNT_RESTORE_FRAME
-.globl ftrace_stub
-ftrace_stub:
+#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
-.globl ftrace_stub
-ftrace_stub:
+
+#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:
- /* 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)
+ MCOUNT_SAVE_FRAME
movq 0x38(%rsp), %rdi
movq 8(%rbp), %rsi
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
+ 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 $80, %rsp
+
+ /* Save the return values */
+ movq %rax, (%rsp)
+ movq %rdx, 8(%rsp)
+ movq %rbp, %rdi
+
+ call ftrace_return_to_handler
+
+ movq %rax, 72(%rsp)
+ movq 8(%rsp), %rdx
+ movq (%rsp), %rax
+ addq $72, %rsp
+ retq
+#endif
+
+
#ifndef CONFIG_PREEMPT
#define retint_kernel retint_restore_args
#endif
ENTRY(native_usergs_sysret64)
swapgs
sysretq
+ENDPROC(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */
/* %rsp:at FRAMEEND */
.macro FIXUP_TOP_OF_STACK tmp offset=0
- movq %gs:pda_oldrsp,\tmp
+ movq PER_CPU_VAR(old_rsp),\tmp
movq \tmp,RSP+\offset(%rsp)
movq $__USER_DS,SS+\offset(%rsp)
movq $__USER_CS,CS+\offset(%rsp)
.macro RESTORE_TOP_OF_STACK tmp offset=0
movq RSP+\offset(%rsp),\tmp
- movq \tmp,%gs:pda_oldrsp
+ movq \tmp,PER_CPU_VAR(old_rsp)
movq EFLAGS+\offset(%rsp),\tmp
movq \tmp,R11+\offset(%rsp)
.endm
pushq %rax /* rsp */
CFI_ADJUST_CFA_OFFSET 8
CFI_REL_OFFSET rsp,0
- pushq $(1<<9) /* eflags - interrupts on */
+ pushq $X86_EFLAGS_IF /* eflags - interrupts on */
CFI_ADJUST_CFA_OFFSET 8
/*CFI_REL_OFFSET rflags,0*/
pushq $__KERNEL_CS /* cs */
je 1f
SWAPGS
/*
- * irqcount is used to check if a CPU is already on an 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)
*/
-1: incl %gs:pda_irqcount
+1: incl PER_CPU_VAR(irq_count)
jne 2f
popq_cfi %rax /* move return address... */
- mov %gs:pda_irqstackptr,%rsp
+ mov PER_CPU_VAR(irq_stack_ptr),%rsp
EMPTY_FRAME 0
+ pushq_cfi %rbp /* backlink for unwinder */
pushq_cfi %rax /* ... to the new stack */
/*
* We entered an interrupt context - irqs are off:
END(save_rest)
/* save complete stack frame */
+ .pushsection .kprobes.text, "ax"
ENTRY(save_paranoid)
XCPT_FRAME 1 RDI+8
cld
1: ret
CFI_ENDPROC
END(save_paranoid)
+ .popsection
/*
- * A newly forked process directly context switches into this.
+ * A newly forked process directly context switches into this address.
+ *
+ * rdi: prev task we switched from
*/
-/* rdi: prev */
ENTRY(ret_from_fork)
DEFAULT_FRAME
+
+ LOCK ; btr $TIF_FORK,TI_flags(%r8)
+
push kernel_eflags(%rip)
CFI_ADJUST_CFA_OFFSET 8
- popf # reset kernel eflags
+ popf # reset kernel eflags
CFI_ADJUST_CFA_OFFSET -8
- call schedule_tail
+
+ call schedule_tail # rdi: 'prev' task parameter
+
GET_THREAD_INFO(%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?
+
+ testl $3, CS-ARGOFFSET(%rsp) # from kernel_thread?
je int_ret_from_sys_call
- testl $_TIF_IA32,TI_flags(%rcx)
+
+ 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
-rff_trace:
- movq %rsp,%rdi
- call syscall_trace_leave
- GET_THREAD_INFO(%rcx)
- jmp rff_action
+ jmp ret_from_sys_call # go to the SYSRET fastpath
+
CFI_ENDPROC
END(ret_from_fork)
ENTRY(system_call)
CFI_STARTPROC simple
CFI_SIGNAL_FRAME
- CFI_DEF_CFA rsp,PDA_STACKOFFSET
+ CFI_DEF_CFA rsp,KERNEL_STACK_OFFSET
CFI_REGISTER rip,rcx
/*CFI_REGISTER rflags,r11*/
SWAPGS_UNSAFE_STACK
*/
ENTRY(system_call_after_swapgs)
- movq %rsp,%gs:pda_oldrsp
- movq %gs:pda_kernelstack,%rsp
+ 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:
CFI_REGISTER rip,rcx
RESTORE_ARGS 0,-ARG_SKIP,1
/*CFI_REGISTER rflags,r11*/
- movq %gs:pda_oldrsp, %rsp
+ movq PER_CPU_VAR(old_rsp), %rsp
USERGS_SYSRET64
CFI_RESTORE_STATE
* Syscall return path ending with IRET.
* Has correct top of stack, but partial stack frame.
*/
- .globl int_ret_from_sys_call
- .globl int_with_check
-int_ret_from_sys_call:
+GLOBAL(int_ret_from_sys_call)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl $3,CS-ARGOFFSET(%rsp)
je retint_restore_args
movl $_TIF_ALLWORK_MASK,%edi
/* edi: mask to check */
-int_with_check:
+GLOBAL(int_with_check)
LOCKDEP_SYS_EXIT_IRQ
GET_THREAD_INFO(%rcx)
movl TI_flags(%rcx),%edx
XCPT_FRAME
addq $-0x80,(%rsp) /* Adjust vector to [-256,-1] range */
interrupt do_IRQ
- /* 0(%rsp): oldrsp-ARGOFFSET */
+ /* 0(%rsp): old_rsp-ARGOFFSET */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
leaveq
CFI_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET -8
#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
-apicinterrupt 220 \
+#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 GENERIC_INTERRUPT_VECTOR \
+ generic_interrupt smp_generic_interrupt
#ifdef CONFIG_SMP
apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \
#endif
apicinterrupt THRESHOLD_APIC_VECTOR \
- threshold_interrupt mce_threshold_interrupt
+ threshold_interrupt smp_threshold_interrupt
apicinterrupt THERMAL_APIC_VECTOR \
thermal_interrupt smp_thermal_interrupt
+#ifdef CONFIG_X86_MCE
+apicinterrupt MCE_SELF_VECTOR \
+ mce_self_interrupt smp_mce_self_interrupt
+#endif
+
#ifdef CONFIG_SMP
apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \
call_function_single_interrupt smp_call_function_single_interrupt
apicinterrupt SPURIOUS_APIC_VECTOR \
spurious_interrupt smp_spurious_interrupt
+#ifdef CONFIG_PERF_COUNTERS
+apicinterrupt LOCAL_PENDING_VECTOR \
+ perf_pending_interrupt smp_perf_pending_interrupt
+#endif
+
/*
* Exception entry points.
*/
.endm
.macro paranoidzeroentry sym do_sym
-KPROBE_ENTRY(\sym)
+ENTRY(\sym)
INTR_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq $-1 /* ORIG_RAX: no syscall to restart */
call \do_sym
jmp paranoid_exit /* %ebx: no swapgs flag */
CFI_ENDPROC
-KPROBE_END(\sym)
+END(\sym)
.endm
.macro paranoidzeroentry_ist sym do_sym ist
-KPROBE_ENTRY(\sym)
- INTR_FRAME
+ENTRY(\sym)
+ INTR_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
pushq $-1 /* ORIG_RAX: no syscall to restart */
CFI_ADJUST_CFA_OFFSET 8
TRACE_IRQS_OFF
movq %rsp,%rdi /* pt_regs pointer */
xorl %esi,%esi /* no error code */
- movq %gs:pda_data_offset, %rbp
- subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ PER_CPU(init_tss, %rbp)
+ subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
call \do_sym
- addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+ addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
jmp paranoid_exit /* %ebx: no swapgs flag */
CFI_ENDPROC
-KPROBE_END(\sym)
+END(\sym)
.endm
-.macro errorentry sym do_sym entry=0
-.if \entry
-KPROBE_ENTRY(\sym)
-.else
+.macro errorentry sym do_sym
ENTRY(\sym)
-.endif
XCPT_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
subq $15*8,%rsp
call \do_sym
jmp error_exit /* %ebx: no swapgs flag */
CFI_ENDPROC
-.if \entry
-KPROBE_END(\sym)
-.else
END(\sym)
-.endif
.endm
/* error code is on the stack already */
-.macro paranoiderrorentry sym do_sym entry=1
-.if \entry
-KPROBE_ENTRY(\sym)
-.else
+.macro paranoiderrorentry sym do_sym
ENTRY(\sym)
-.endif
XCPT_FRAME
PARAVIRT_ADJUST_EXCEPTION_FRAME
subq $15*8,%rsp
call \do_sym
jmp paranoid_exit /* %ebx: no swapgs flag */
CFI_ENDPROC
-.if \entry
-KPROBE_END(\sym)
-.else
END(\sym)
-.endif
.endm
zeroentry divide_error do_divide_error
-paranoidzeroentry_ist debug do_debug DEBUG_STACK
-paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
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 0
+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
-paranoiderrorentry stack_segment do_stack_segment
-errorentry general_protection do_general_protection 1
-errorentry page_fault do_page_fault 1
zeroentry spurious_interrupt_bug do_spurious_interrupt_bug
zeroentry coprocessor_error do_coprocessor_error
errorentry alignment_check do_alignment_check
-#ifdef CONFIG_X86_MCE
-paranoidzeroentry machine_check do_machine_check
-#endif
zeroentry simd_coprocessor_error do_simd_coprocessor_error
- /*
- * "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 */
-KPROBE_ENTRY(paranoid_exit)
- INTR_FRAME
- DISABLE_INTERRUPTS(CLBR_NONE)
- TRACE_IRQS_OFF
- testl %ebx,%ebx /* swapgs needed? */
- jnz paranoid_restore
- testl $3,CS(%rsp)
- jnz paranoid_userspace
-paranoid_swapgs:
- TRACE_IRQS_IRETQ 0
- SWAPGS_UNSAFE_STACK
-paranoid_restore:
- 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
-KPROBE_END(paranoid_exit)
-
-/*
- * Exception entry point. This expects an error code/orig_rax on the stack.
- * returns in "no swapgs flag" in %ebx.
- */
-KPROBE_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
- CFI_ENDPROC
-
-/*
- * 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,%ecx /* zero extend */
- cmpq %rcx,RIP+8(%rsp)
- je error_swapgs
- cmpq $gs_change,RIP+8(%rsp)
- je error_swapgs
- jmp error_sti
-KPROBE_END(error_entry)
-
-
-/* ebx: no swapgs flag (1: don't need swapgs, 0: need it) */
-KPROBE_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
-KPROBE_END(error_exit)
-
- /* Reload gs selector with exception handling */
- /* edi: new selector */
+ /* Reload gs selector with exception handling */
+ /* edi: new selector */
ENTRY(native_load_gs_index)
CFI_STARTPROC
pushf
CFI_ADJUST_CFA_OFFSET 8
- DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI))
- SWAPGS
+ DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
+ SWAPGS
gs_change:
- movl %edi,%gs
+ movl %edi,%gs
2: mfence /* workaround */
SWAPGS
- popf
+ popf
CFI_ADJUST_CFA_OFFSET -8
- ret
+ ret
CFI_ENDPROC
END(native_load_gs_index)
- .section __ex_table,"a"
- .align 8
- .quad gs_change,bad_gs
- .previous
- .section .fixup,"ax"
+ .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
+ movl %eax,%gs
+ jmp 2b
+ .previous
/*
* Create a kernel thread.
* 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]
+ * [Hopefully no generic code relies on the reschedule -AK]
*/
RESTORE_ALL
UNFAKE_STACK_FRAME
CFI_ENDPROC
END(kernel_thread)
-child_rip:
+ENTRY(child_rip)
pushq $0 # fake return address
CFI_STARTPROC
/*
# exit
mov %eax, %edi
call do_exit
+ ud2 # padding for call trace
CFI_ENDPROC
END(child_rip)
CFI_ENDPROC
END(kernel_execve)
- /* runs on exception stack */
-KPROBE_ENTRY(nmi)
- INTR_FRAME
- PARAVIRT_ADJUST_EXCEPTION_FRAME
- pushq_cfi $-1
- subq $15*8, %rsp
- CFI_ADJUST_CFA_OFFSET 15*8
- call save_paranoid
- DEFAULT_FRAME 0
- /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
- movq %rsp,%rdi
- movq $-1,%rsi
- call do_nmi
-#ifdef CONFIG_TRACE_IRQFLAGS
- /* paranoidexit; without TRACE_IRQS_OFF */
- /* ebx: no swapgs flag */
- DISABLE_INTERRUPTS(CLBR_NONE)
- testl %ebx,%ebx /* swapgs needed? */
- jnz nmi_restore
- testl $3,CS(%rsp)
- jnz nmi_userspace
-nmi_swapgs:
- SWAPGS_UNSAFE_STACK
-nmi_restore:
- RESTORE_ALL 8
- jmp irq_return
-nmi_userspace:
- GET_THREAD_INFO(%rcx)
- movl TI_flags(%rcx),%ebx
- andl $_TIF_WORK_MASK,%ebx
- jz nmi_swapgs
- movq %rsp,%rdi /* &pt_regs */
- call sync_regs
- movq %rax,%rsp /* switch stack for scheduling */
- testl $_TIF_NEED_RESCHED,%ebx
- jnz nmi_schedule
- movl %ebx,%edx /* arg3: thread flags */
- ENABLE_INTERRUPTS(CLBR_NONE)
- xorl %esi,%esi /* arg2: oldset */
- movq %rsp,%rdi /* arg1: &pt_regs */
- call do_notify_resume
- DISABLE_INTERRUPTS(CLBR_NONE)
- jmp nmi_userspace
-nmi_schedule:
- ENABLE_INTERRUPTS(CLBR_ANY)
- call schedule
- DISABLE_INTERRUPTS(CLBR_ANY)
- jmp nmi_userspace
- CFI_ENDPROC
-#else
- jmp paranoid_exit
- CFI_ENDPROC
-#endif
-KPROBE_END(nmi)
-
/* Call softirq on interrupt stack. Interrupts are off. */
ENTRY(call_softirq)
CFI_STARTPROC
CFI_REL_OFFSET rbp,0
mov %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
- incl %gs:pda_irqcount
- cmove %gs:pda_irqstackptr,%rsp
+ 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_DEF_CFA_REGISTER rsp
CFI_ADJUST_CFA_OFFSET -8
- decl %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
ret
CFI_ENDPROC
END(call_softirq)
-KPROBE_ENTRY(ignore_sysret)
- CFI_STARTPROC
- mov $-ENOSYS,%eax
- sysret
- CFI_ENDPROC
-KPROBE_END(ignore_sysret)
-
#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.
-*/
+ * 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 */
+/*
+ * 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 %gs:pda_irqcount
+11: incl PER_CPU_VAR(irq_count)
movq %rsp,%rbp
CFI_DEF_CFA_REGISTER rbp
- cmovzq %gs:pda_irqstackptr,%rsp
+ 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 %gs:pda_irqcount
+ decl PER_CPU_VAR(irq_count)
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.
-*/
+ * 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*/
END(xen_failsafe_callback)
#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_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)
+ INTR_FRAME
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ TRACE_IRQS_OFF
+ 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 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
+ CFI_ENDPROC
+
+/*
+ * 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,%ecx /* zero extend */
+ cmpq %rcx,RIP+8(%rsp)
+ je error_swapgs
+ cmpq $gs_change,RIP+8(%rsp)
+ je error_swapgs
+ jmp error_sti
+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)
+
+
+ /* runs on exception stack */
+ENTRY(nmi)
+ INTR_FRAME
+ PARAVIRT_ADJUST_EXCEPTION_FRAME
+ pushq_cfi $-1
+ subq $15*8, %rsp
+ CFI_ADJUST_CFA_OFFSET 15*8
+ call save_paranoid
+ DEFAULT_FRAME 0
+ /* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
+ movq %rsp,%rdi
+ movq $-1,%rsi
+ call do_nmi
+#ifdef CONFIG_TRACE_IRQFLAGS
+ /* paranoidexit; without TRACE_IRQS_OFF */
+ /* ebx: no swapgs flag */
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ testl %ebx,%ebx /* swapgs needed? */
+ jnz nmi_restore
+ testl $3,CS(%rsp)
+ jnz nmi_userspace
+nmi_swapgs:
+ SWAPGS_UNSAFE_STACK
+nmi_restore:
+ RESTORE_ALL 8
+ jmp irq_return
+nmi_userspace:
+ GET_THREAD_INFO(%rcx)
+ movl TI_flags(%rcx),%ebx
+ andl $_TIF_WORK_MASK,%ebx
+ jz nmi_swapgs
+ movq %rsp,%rdi /* &pt_regs */
+ call sync_regs
+ movq %rax,%rsp /* switch stack for scheduling */
+ testl $_TIF_NEED_RESCHED,%ebx
+ jnz nmi_schedule
+ movl %ebx,%edx /* arg3: thread flags */
+ ENABLE_INTERRUPTS(CLBR_NONE)
+ xorl %esi,%esi /* arg2: oldset */
+ movq %rsp,%rdi /* arg1: &pt_regs */
+ call do_notify_resume
+ DISABLE_INTERRUPTS(CLBR_NONE)
+ jmp nmi_userspace
+nmi_schedule:
+ ENABLE_INTERRUPTS(CLBR_ANY)
+ call schedule
+ DISABLE_INTERRUPTS(CLBR_ANY)
+ jmp nmi_userspace
+ CFI_ENDPROC
+#else
+ jmp paranoid_exit
+ CFI_ENDPROC
+#endif
+END(nmi)
+
+ENTRY(ignore_sysret)
+ CFI_STARTPROC
+ mov $-ENOSYS,%eax
+ sysret
+ CFI_ENDPROC
+END(ignore_sysret)
+
+/*
+ * End of kprobes section
+ */
+ .popsection