#include <asm/smap.h>
#include <asm/pgtable_types.h>
#include <asm/export.h>
+#include <asm/frame.h>
#include <linux/err.h>
.code64
#ifdef CONFIG_PARAVIRT
ENTRY(native_usergs_sysret64)
+ UNWIND_HINT_EMPTY
swapgs
sysretq
-ENDPROC(native_usergs_sysret64)
+END(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */
.macro TRACE_IRQS_IRETQ
* with them due to bugs in both AMD and Intel CPUs.
*/
+ .pushsection .entry_trampoline, "ax"
+
+/*
+ * The code in here gets remapped into cpu_entry_area's trampoline. This means
+ * that the assembler and linker have the wrong idea as to where this code
+ * lives (and, in fact, it's mapped more than once, so it's not even at a
+ * fixed address). So we can't reference any symbols outside the entry
+ * trampoline and expect it to work.
+ *
+ * Instead, we carefully abuse %rip-relative addressing.
+ * _entry_trampoline(%rip) refers to the start of the remapped) entry
+ * trampoline. We can thus find cpu_entry_area with this macro:
+ */
+
+#define CPU_ENTRY_AREA \
+ _entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
+
+/* The top word of the SYSENTER stack is hot and is usable as scratch space. */
+#define RSP_SCRATCH CPU_ENTRY_AREA_SYSENTER_stack + \
+ SIZEOF_SYSENTER_stack - 8 + CPU_ENTRY_AREA
+
+ENTRY(entry_SYSCALL_64_trampoline)
+ UNWIND_HINT_EMPTY
+ swapgs
+
+ /* Stash the user RSP. */
+ movq %rsp, RSP_SCRATCH
+
+ /* Load the top of the task stack into RSP */
+ movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
+
+ /* Start building the simulated IRET frame. */
+ pushq $__USER_DS /* pt_regs->ss */
+ pushq RSP_SCRATCH /* pt_regs->sp */
+ pushq %r11 /* pt_regs->flags */
+ pushq $__USER_CS /* pt_regs->cs */
+ pushq %rcx /* pt_regs->ip */
+
+ /*
+ * x86 lacks a near absolute jump, and we can't jump to the real
+ * entry text with a relative jump. We could push the target
+ * address and then use retq, but this destroys the pipeline on
+ * many CPUs (wasting over 20 cycles on Sandy Bridge). Instead,
+ * spill RDI and restore it in a second-stage trampoline.
+ */
+ pushq %rdi
+ movq $entry_SYSCALL_64_stage2, %rdi
+ jmp *%rdi
+END(entry_SYSCALL_64_trampoline)
+
+ .popsection
+
+ENTRY(entry_SYSCALL_64_stage2)
+ UNWIND_HINT_EMPTY
+ popq %rdi
+ jmp entry_SYSCALL_64_after_hwframe
+END(entry_SYSCALL_64_stage2)
+
ENTRY(entry_SYSCALL_64)
+ UNWIND_HINT_EMPTY
/*
* Interrupts are off on entry.
* We do not frame this tiny irq-off block with TRACE_IRQS_OFF/ON,
* it is too small to ever cause noticeable irq latency.
*/
- SWAPGS_UNSAFE_STACK
- /*
- * A hypervisor implementation might want to use a label
- * after the swapgs, so that it can do the swapgs
- * for the guest and jump here on syscall.
- */
-GLOBAL(entry_SYSCALL_64_after_swapgs)
+ swapgs
movq %rsp, PER_CPU_VAR(rsp_scratch)
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
pushq %r11 /* pt_regs->flags */
pushq $__USER_CS /* pt_regs->cs */
pushq %rcx /* pt_regs->ip */
+GLOBAL(entry_SYSCALL_64_after_hwframe)
pushq %rax /* pt_regs->orig_ax */
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
pushq %r10 /* pt_regs->r10 */
pushq %r11 /* pt_regs->r11 */
sub $(6*8), %rsp /* pt_regs->bp, bx, r12-15 not saved */
+ UNWIND_HINT_REGS extra=0
/*
* If we need to do entry work or if we guess we'll need to do
TRACE_IRQS_ON /* user mode is traced as IRQs on */
movq RIP(%rsp), %rcx
movq EFLAGS(%rsp), %r11
- RESTORE_C_REGS_EXCEPT_RCX_R11
- movq RSP(%rsp), %rsp
- USERGS_SYSRET64
+ addq $6*8, %rsp /* skip extra regs -- they were preserved */
+ UNWIND_HINT_EMPTY
+ jmp .Lpop_c_regs_except_rcx_r11_and_sysret
1:
/*
call do_syscall_64 /* returns with IRQs disabled */
return_from_SYSCALL_64:
- RESTORE_EXTRA_REGS
TRACE_IRQS_IRETQ /* we're about to change IF */
/*
* Try to use SYSRET instead of IRET if we're returning to
- * a completely clean 64-bit userspace context.
+ * a completely clean 64-bit userspace context. If we're not,
+ * go to the slow exit path.
*/
movq RCX(%rsp), %rcx
movq RIP(%rsp), %r11
- cmpq %rcx, %r11 /* RCX == RIP */
- jne opportunistic_sysret_failed
+
+ cmpq %rcx, %r11 /* SYSRET requires RCX == RIP */
+ jne swapgs_restore_regs_and_return_to_usermode
/*
* On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
/* If this changed %rcx, it was not canonical */
cmpq %rcx, %r11
- jne opportunistic_sysret_failed
+ jne swapgs_restore_regs_and_return_to_usermode
cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */
- jne opportunistic_sysret_failed
+ jne swapgs_restore_regs_and_return_to_usermode
movq R11(%rsp), %r11
cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */
- jne opportunistic_sysret_failed
+ jne swapgs_restore_regs_and_return_to_usermode
/*
* SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
* would never get past 'stuck_here'.
*/
testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
- jnz opportunistic_sysret_failed
+ jnz swapgs_restore_regs_and_return_to_usermode
/* nothing to check for RSP */
cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */
- jne opportunistic_sysret_failed
+ jne swapgs_restore_regs_and_return_to_usermode
/*
* We win! This label is here just for ease of understanding
*/
syscall_return_via_sysret:
/* rcx and r11 are already restored (see code above) */
- RESTORE_C_REGS_EXCEPT_RCX_R11
- movq RSP(%rsp), %rsp
- USERGS_SYSRET64
+ UNWIND_HINT_EMPTY
+ POP_EXTRA_REGS
+.Lpop_c_regs_except_rcx_r11_and_sysret:
+ popq %rsi /* skip r11 */
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rsi /* skip rcx */
+ popq %rdx
+ popq %rsi
-opportunistic_sysret_failed:
- SWAPGS
- jmp restore_c_regs_and_iret
+ /*
+ * Now all regs are restored except RSP and RDI.
+ * Save old stack pointer and switch to trampoline stack.
+ */
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+ pushq RSP-RDI(%rdi) /* RSP */
+ pushq (%rdi) /* RDI */
+
+ /*
+ * We are on the trampoline stack. All regs except RDI are live.
+ * We can do future final exit work right here.
+ */
+
+ popq %rdi
+ popq %rsp
+ USERGS_SYSRET64
END(entry_SYSCALL_64)
ENTRY(stub_ptregs_64)
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
popq %rax
+ UNWIND_HINT_REGS extra=0
jmp entry_SYSCALL64_slow_path
1:
.macro ptregs_stub func
ENTRY(ptregs_\func)
+ UNWIND_HINT_FUNC
leaq \func(%rip), %rax
jmp stub_ptregs_64
END(ptregs_\func)
* %rsi: next task
*/
ENTRY(__switch_to_asm)
+ UNWIND_HINT_FUNC
/*
* Save callee-saved registers
* This must match the order in inactive_task_frame
* r12: kernel thread arg
*/
ENTRY(ret_from_fork)
+ UNWIND_HINT_EMPTY
movq %rax, %rdi
call schedule_tail /* rdi: 'prev' task parameter */
jnz 1f /* kernel threads are uncommon */
2:
+ UNWIND_HINT_REGS
movq %rsp, %rdi
call syscall_return_slowpath /* returns with IRQs disabled */
TRACE_IRQS_ON /* user mode is traced as IRQS on */
- SWAPGS
- jmp restore_regs_and_iret
+ jmp swapgs_restore_regs_and_return_to_usermode
1:
/* kernel thread */
ENTRY(irq_entries_start)
vector=FIRST_EXTERNAL_VECTOR
.rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
+ UNWIND_HINT_IRET_REGS
pushq $(~vector+0x80) /* Note: always in signed byte range */
- vector=vector+1
jmp common_interrupt
.align 8
+ vector=vector+1
.endr
END(irq_entries_start)
+.macro DEBUG_ENTRY_ASSERT_IRQS_OFF
+#ifdef CONFIG_DEBUG_ENTRY
+ pushq %rax
+ SAVE_FLAGS(CLBR_RAX)
+ testl $X86_EFLAGS_IF, %eax
+ jz .Lokay_\@
+ ud2
+.Lokay_\@:
+ popq %rax
+#endif
+.endm
+
+/*
+ * Enters the IRQ stack if we're not already using it. NMI-safe. Clobbers
+ * flags and puts old RSP into old_rsp, and leaves all other GPRs alone.
+ * Requires kernel GSBASE.
+ *
+ * The invariant is that, if irq_count != -1, then the IRQ stack is in use.
+ */
+.macro ENTER_IRQ_STACK regs=1 old_rsp
+ DEBUG_ENTRY_ASSERT_IRQS_OFF
+ movq %rsp, \old_rsp
+
+ .if \regs
+ UNWIND_HINT_REGS base=\old_rsp
+ .endif
+
+ incl PER_CPU_VAR(irq_count)
+ jnz .Lirq_stack_push_old_rsp_\@
+
+ /*
+ * Right now, if we just incremented irq_count to zero, we've
+ * claimed the IRQ stack but we haven't switched to it yet.
+ *
+ * If anything is added that can interrupt us here without using IST,
+ * it must be *extremely* careful to limit its stack usage. This
+ * could include kprobes and a hypothetical future IST-less #DB
+ * handler.
+ *
+ * The OOPS unwinder relies on the word at the top of the IRQ
+ * stack linking back to the previous RSP for the entire time we're
+ * on the IRQ stack. For this to work reliably, we need to write
+ * it before we actually move ourselves to the IRQ stack.
+ */
+
+ movq \old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8)
+ movq PER_CPU_VAR(irq_stack_ptr), %rsp
+
+#ifdef CONFIG_DEBUG_ENTRY
+ /*
+ * If the first movq above becomes wrong due to IRQ stack layout
+ * changes, the only way we'll notice is if we try to unwind right
+ * here. Assert that we set up the stack right to catch this type
+ * of bug quickly.
+ */
+ cmpq -8(%rsp), \old_rsp
+ je .Lirq_stack_okay\@
+ ud2
+ .Lirq_stack_okay\@:
+#endif
+
+.Lirq_stack_push_old_rsp_\@:
+ pushq \old_rsp
+
+ .if \regs
+ UNWIND_HINT_REGS indirect=1
+ .endif
+.endm
+
+/*
+ * Undoes ENTER_IRQ_STACK.
+ */
+.macro LEAVE_IRQ_STACK regs=1
+ DEBUG_ENTRY_ASSERT_IRQS_OFF
+ /* We need to be off the IRQ stack before decrementing irq_count. */
+ popq %rsp
+
+ .if \regs
+ UNWIND_HINT_REGS
+ .endif
+
+ /*
+ * As in ENTER_IRQ_STACK, irq_count == 0, we are still claiming
+ * the irq stack but we're not on it.
+ */
+
+ decl PER_CPU_VAR(irq_count)
+.endm
+
/*
* Interrupt entry/exit.
*
/* 0(%rsp): ~(interrupt number) */
.macro interrupt func
cld
+
+ testb $3, CS-ORIG_RAX(%rsp)
+ jz 1f
+ SWAPGS
+ call switch_to_thread_stack
+1:
+
ALLOC_PT_GPREGS_ON_STACK
SAVE_C_REGS
SAVE_EXTRA_REGS
jz 1f
/*
- * IRQ from user mode. Switch to kernel gsbase and inform context
- * tracking that we're in kernel mode.
- */
- SWAPGS
-
- /*
+ * IRQ from user mode.
+ *
* We need to tell lockdep that IRQs are off. We can't do this until
* we fix gsbase, and we should do it before enter_from_user_mode
* (which can take locks). Since TRACE_IRQS_OFF idempotent,
CALL_enter_from_user_mode
1:
- /*
- * Save previous stack pointer, optionally switch to interrupt stack.
- * irq_count is used to check if a CPU is already on an interrupt stack
- * or not. While this is essentially redundant with preempt_count it is
- * a little cheaper to use a separate counter in the PDA (short of
- * moving irq_enter into assembly, which would be too much work)
- */
- movq %rsp, %rdi
- incl PER_CPU_VAR(irq_count)
- cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp
- pushq %rdi
+ ENTER_IRQ_STACK old_rsp=%rdi
/* We entered an interrupt context - irqs are off: */
TRACE_IRQS_OFF
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
- decl PER_CPU_VAR(irq_count)
- /* Restore saved previous stack */
- popq %rsp
+ LEAVE_IRQ_STACK
testb $3, CS(%rsp)
jz retint_kernel
mov %rsp,%rdi
call prepare_exit_to_usermode
TRACE_IRQS_IRETQ
+
+GLOBAL(swapgs_restore_regs_and_return_to_usermode)
+#ifdef CONFIG_DEBUG_ENTRY
+ /* Assert that pt_regs indicates user mode. */
+ testb $3, CS(%rsp)
+ jnz 1f
+ ud2
+1:
+#endif
+ POP_EXTRA_REGS
+ popq %r11
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rcx
+ popq %rdx
+ popq %rsi
+
+ /*
+ * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
+ * Save old stack pointer and switch to trampoline stack.
+ */
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+ /* Copy the IRET frame to the trampoline stack. */
+ pushq 6*8(%rdi) /* SS */
+ pushq 5*8(%rdi) /* RSP */
+ pushq 4*8(%rdi) /* EFLAGS */
+ pushq 3*8(%rdi) /* CS */
+ pushq 2*8(%rdi) /* RIP */
+
+ /* Push user RDI on the trampoline stack. */
+ pushq (%rdi)
+
+ /*
+ * We are on the trampoline stack. All regs except RDI are live.
+ * We can do future final exit work right here.
+ */
+
+ /* Restore RDI. */
+ popq %rdi
SWAPGS
- jmp restore_regs_and_iret
+ INTERRUPT_RETURN
+
/* Returning to kernel space */
retint_kernel:
*/
TRACE_IRQS_IRETQ
-/*
- * At this label, code paths which return to kernel and to user,
- * which come from interrupts/exception and from syscalls, merge.
- */
-GLOBAL(restore_regs_and_iret)
- RESTORE_EXTRA_REGS
-restore_c_regs_and_iret:
- RESTORE_C_REGS
- REMOVE_PT_GPREGS_FROM_STACK 8
+GLOBAL(restore_regs_and_return_to_kernel)
+#ifdef CONFIG_DEBUG_ENTRY
+ /* Assert that pt_regs indicates kernel mode. */
+ testb $3, CS(%rsp)
+ jz 1f
+ ud2
+1:
+#endif
+ POP_EXTRA_REGS
+ POP_C_REGS
+ addq $8, %rsp /* skip regs->orig_ax */
INTERRUPT_RETURN
ENTRY(native_iret)
+ UNWIND_HINT_IRET_REGS
/*
* Are we returning to a stack segment from the LDT? Note: in
* 64-bit mode SS:RSP on the exception stack is always valid.
orq PER_CPU_VAR(espfix_stack), %rax
SWAPGS
movq %rax, %rsp
+ UNWIND_HINT_IRET_REGS offset=8
/*
* At this point, we cannot write to the stack any more, but we can
*/
.macro apicinterrupt3 num sym do_sym
ENTRY(\sym)
+ UNWIND_HINT_IRET_REGS
ASM_CLAC
pushq $~(\num)
.Lcommon_\sym:
#endif
/* Make sure APIC interrupt handlers end up in the irqentry section: */
-#if defined(CONFIG_FUNCTION_GRAPH_TRACER) || defined(CONFIG_KASAN)
-# define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
-# define POP_SECTION_IRQENTRY .popsection
-#else
-# define PUSH_SECTION_IRQENTRY
-# define POP_SECTION_IRQENTRY
-#endif
+#define PUSH_SECTION_IRQENTRY .pushsection .irqentry.text, "ax"
+#define POP_SECTION_IRQENTRY .popsection
.macro apicinterrupt num sym do_sym
PUSH_SECTION_IRQENTRY
/*
* Exception entry points.
*/
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+
+/*
+ * Switch to the thread stack. This is called with the IRET frame and
+ * orig_ax on the stack. (That is, RDI..R12 are not on the stack and
+ * space has not been allocated for them.)
+ */
+ENTRY(switch_to_thread_stack)
+ UNWIND_HINT_FUNC
+
+ pushq %rdi
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
+
+ pushq 7*8(%rdi) /* regs->ss */
+ pushq 6*8(%rdi) /* regs->rsp */
+ pushq 5*8(%rdi) /* regs->eflags */
+ pushq 4*8(%rdi) /* regs->cs */
+ pushq 3*8(%rdi) /* regs->ip */
+ pushq 2*8(%rdi) /* regs->orig_ax */
+ pushq 8(%rdi) /* return address */
+ UNWIND_HINT_FUNC
+
+ movq (%rdi), %rdi
+ ret
+END(switch_to_thread_stack)
.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
ENTRY(\sym)
+ UNWIND_HINT_IRET_REGS offset=\has_error_code*8
+
/* Sanity check */
.if \shift_ist != -1 && \paranoid == 0
.error "using shift_ist requires paranoid=1"
.endif
ASM_CLAC
- PARAVIRT_ADJUST_EXCEPTION_FRAME
- .ifeq \has_error_code
+ .if \has_error_code == 0
pushq $-1 /* ORIG_RAX: no syscall to restart */
.endif
ALLOC_PT_GPREGS_ON_STACK
- .if \paranoid
- .if \paranoid == 1
+ .if \paranoid < 2
testb $3, CS(%rsp) /* If coming from userspace, switch stacks */
- jnz 1f
+ jnz .Lfrom_usermode_switch_stack_\@
.endif
+
+ .if \paranoid
call paranoid_entry
.else
call error_entry
.endif
+ UNWIND_HINT_REGS
/* returned flag: ebx=0: need swapgs on exit, ebx=1: don't need it */
.if \paranoid
jmp error_exit
.endif
- .if \paranoid == 1
+ .if \paranoid < 2
/*
- * Paranoid entry from userspace. Switch stacks and treat it
+ * Entry from userspace. Switch stacks and treat it
* as a normal entry. This means that paranoid handlers
* run in real process context if user_mode(regs).
*/
-1:
+.Lfrom_usermode_switch_stack_\@:
call error_entry
-
- movq %rsp, %rdi /* pt_regs pointer */
- call sync_regs
- movq %rax, %rsp /* switch stack */
-
movq %rsp, %rdi /* pt_regs pointer */
.if \has_error_code
END(\sym)
.endm
-#ifdef CONFIG_TRACING
-.macro trace_idtentry sym do_sym has_error_code:req
-idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code
-idtentry \sym \do_sym has_error_code=\has_error_code
-.endm
-#else
-.macro trace_idtentry sym do_sym has_error_code:req
-idtentry \sym \do_sym has_error_code=\has_error_code
-.endm
-#endif
-
idtentry divide_error do_divide_error has_error_code=0
idtentry overflow do_overflow has_error_code=0
idtentry bounds do_bounds has_error_code=0
* edi: new selector
*/
ENTRY(native_load_gs_index)
+ FRAME_BEGIN
pushfq
DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
SWAPGS
2: ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
SWAPGS
popfq
+ FRAME_END
ret
-END(native_load_gs_index)
+ENDPROC(native_load_gs_index)
EXPORT_SYMBOL(native_load_gs_index)
_ASM_EXTABLE(.Lgs_change, bad_gs)
ENTRY(do_softirq_own_stack)
pushq %rbp
mov %rsp, %rbp
- incl PER_CPU_VAR(irq_count)
- cmove PER_CPU_VAR(irq_stack_ptr), %rsp
- push %rbp /* frame pointer backlink */
+ ENTER_IRQ_STACK regs=0 old_rsp=%r11
call __do_softirq
+ LEAVE_IRQ_STACK regs=0
leaveq
- decl PER_CPU_VAR(irq_count)
ret
-END(do_softirq_own_stack)
+ENDPROC(do_softirq_own_stack)
#ifdef CONFIG_XEN
-idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
+idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0
/*
* A note on the "critical region" in our callback handler.
* Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
* see the correct pointer to the pt_regs
*/
+ UNWIND_HINT_FUNC
movq %rdi, %rsp /* we don't return, adjust the stack frame */
-11: incl PER_CPU_VAR(irq_count)
- movq %rsp, %rbp
- cmovzq PER_CPU_VAR(irq_stack_ptr), %rsp
- pushq %rbp /* frame pointer backlink */
+ UNWIND_HINT_REGS
+
+ ENTER_IRQ_STACK old_rsp=%r10
call xen_evtchn_do_upcall
- popq %rsp
- decl PER_CPU_VAR(irq_count)
+ LEAVE_IRQ_STACK
+
#ifndef CONFIG_PREEMPT
call xen_maybe_preempt_hcall
#endif
* with its current contents: any discrepancy means we in category 1.
*/
ENTRY(xen_failsafe_callback)
+ UNWIND_HINT_EMPTY
movl %ds, %ecx
cmpw %cx, 0x10(%rsp)
jne 1f
movq 8(%rsp), %r11
addq $0x30, %rsp
pushq $0 /* RIP */
- pushq %r11
- pushq %rcx
+ UNWIND_HINT_IRET_REGS offset=8
jmp general_protection
1: /* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
movq (%rsp), %rcx
movq 8(%rsp), %r11
addq $0x30, %rsp
+ UNWIND_HINT_IRET_REGS
pushq $-1 /* orig_ax = -1 => not a system call */
ALLOC_PT_GPREGS_ON_STACK
SAVE_C_REGS
idtentry stack_segment do_stack_segment has_error_code=1
#ifdef CONFIG_XEN
-idtentry xen_debug do_debug has_error_code=0
-idtentry xen_int3 do_int3 has_error_code=0
-idtentry xen_stack_segment do_stack_segment has_error_code=1
+idtentry xennmi do_nmi has_error_code=0
+idtentry xendebug do_debug has_error_code=0
+idtentry xenint3 do_int3 has_error_code=0
#endif
idtentry general_protection do_general_protection has_error_code=1
-trace_idtentry page_fault do_page_fault has_error_code=1
+idtentry page_fault do_page_fault has_error_code=1
#ifdef CONFIG_KVM_GUEST
idtentry async_page_fault do_async_page_fault has_error_code=1
* Return: ebx=0: need swapgs on exit, ebx=1: otherwise
*/
ENTRY(paranoid_entry)
+ UNWIND_HINT_FUNC
cld
SAVE_C_REGS 8
SAVE_EXTRA_REGS 8
* On entry, ebx is "no swapgs" flag (1: don't need swapgs, 0: need it)
*/
ENTRY(paranoid_exit)
+ UNWIND_HINT_REGS
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF_DEBUG
testl %ebx, %ebx /* swapgs needed? */
- jnz paranoid_exit_no_swapgs
+ jnz .Lparanoid_exit_no_swapgs
TRACE_IRQS_IRETQ
SWAPGS_UNSAFE_STACK
- jmp paranoid_exit_restore
-paranoid_exit_no_swapgs:
+ jmp .Lparanoid_exit_restore
+.Lparanoid_exit_no_swapgs:
TRACE_IRQS_IRETQ_DEBUG
-paranoid_exit_restore:
- RESTORE_EXTRA_REGS
- RESTORE_C_REGS
- REMOVE_PT_GPREGS_FROM_STACK 8
- INTERRUPT_RETURN
+.Lparanoid_exit_restore:
+ jmp restore_regs_and_return_to_kernel
END(paranoid_exit)
/*
* Return: EBX=0: came from user mode; EBX=1: otherwise
*/
ENTRY(error_entry)
+ UNWIND_HINT_FUNC
cld
SAVE_C_REGS 8
SAVE_EXTRA_REGS 8
SWAPGS
.Lerror_entry_from_usermode_after_swapgs:
+ /* Put us onto the real thread stack. */
+ popq %r12 /* save return addr in %12 */
+ movq %rsp, %rdi /* arg0 = pt_regs pointer */
+ call sync_regs
+ movq %rax, %rsp /* switch stack */
+ ENCODE_FRAME_POINTER
+ pushq %r12
+
/*
* We need to tell lockdep that IRQs are off. We can't do this until
* we fix gsbase, and we should do it before enter_from_user_mode
* 0: user gsbase is loaded, we need SWAPGS and standard preparation for return to usermode
*/
ENTRY(error_exit)
+ UNWIND_HINT_REGS
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
testl %ebx, %ebx
jmp retint_user
END(error_exit)
-/* Runs on exception stack */
+/*
+ * Runs on exception stack. Xen PV does not go through this path at all,
+ * so we can use real assembly here.
+ */
ENTRY(nmi)
- /*
- * Fix up the exception frame if we're on Xen.
- * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most
- * one value to the stack on native, so it may clobber the rdx
- * scratch slot, but it won't clobber any of the important
- * slots past it.
- *
- * Xen is a different story, because the Xen frame itself overlaps
- * the "NMI executing" variable.
- */
- PARAVIRT_ADJUST_EXCEPTION_FRAME
+ UNWIND_HINT_IRET_REGS
/*
* We allow breakpoints in NMIs. If a breakpoint occurs, then
* other IST entries.
*/
+ ASM_CLAC
+
/* Use %rdx as our temp variable throughout */
pushq %rdx
* stacks lest we corrupt the "NMI executing" variable.
*/
- SWAPGS_UNSAFE_STACK
+ swapgs
cld
movq %rsp, %rdx
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+ UNWIND_HINT_IRET_REGS base=%rdx offset=8
pushq 5*8(%rdx) /* pt_regs->ss */
pushq 4*8(%rdx) /* pt_regs->rsp */
pushq 3*8(%rdx) /* pt_regs->flags */
pushq 2*8(%rdx) /* pt_regs->cs */
pushq 1*8(%rdx) /* pt_regs->rip */
+ UNWIND_HINT_IRET_REGS
pushq $-1 /* pt_regs->orig_ax */
pushq %rdi /* pt_regs->di */
pushq %rsi /* pt_regs->si */
pushq %r13 /* pt_regs->r13 */
pushq %r14 /* pt_regs->r14 */
pushq %r15 /* pt_regs->r15 */
+ UNWIND_HINT_REGS
ENCODE_FRAME_POINTER
/*
* Return back to user mode. We must *not* do the normal exit
* work, because we don't want to enable interrupts.
*/
- SWAPGS
- jmp restore_regs_and_iret
+ jmp swapgs_restore_regs_and_return_to_usermode
.Lnmi_from_kernel:
/*
popq %rdx
/* We are returning to kernel mode, so this cannot result in a fault. */
- INTERRUPT_RETURN
+ iretq
first_nmi:
/* Restore rdx. */
.rept 5
pushq 11*8(%rsp)
.endr
+ UNWIND_HINT_IRET_REGS
/* Everything up to here is safe from nested NMIs */
pushfq /* RFLAGS */
pushq $__KERNEL_CS /* CS */
pushq $1f /* RIP */
- INTERRUPT_RETURN /* continues at repeat_nmi below */
+ iretq /* continues at repeat_nmi below */
+ UNWIND_HINT_IRET_REGS
1:
#endif
* exceptions might do.
*/
call paranoid_entry
+ UNWIND_HINT_REGS
/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
movq %rsp, %rdi
nmi_swapgs:
SWAPGS_UNSAFE_STACK
nmi_restore:
- RESTORE_EXTRA_REGS
- RESTORE_C_REGS
+ POP_EXTRA_REGS
+ POP_C_REGS
- /* Point RSP at the "iret" frame. */
- REMOVE_PT_GPREGS_FROM_STACK 6*8
+ /*
+ * Skip orig_ax and the "outermost" frame to point RSP at the "iret"
+ * at the "iret" frame.
+ */
+ addq $6*8, %rsp
/*
* Clear "NMI executing". Set DF first so that we can easily
* distinguish the remaining code between here and IRET from
- * the SYSCALL entry and exit paths. On a native kernel, we
- * could just inspect RIP, but, on paravirt kernels,
- * INTERRUPT_RETURN can translate into a jump into a
- * hypercall page.
+ * the SYSCALL entry and exit paths.
+ *
+ * We arguably should just inspect RIP instead, but I (Andy) wrote
+ * this code when I had the misapprehension that Xen PV supported
+ * NMIs, and Xen PV would break that approach.
*/
std
movq $0, 5*8(%rsp) /* clear "NMI executing" */
/*
- * INTERRUPT_RETURN reads the "iret" frame and exits the NMI
- * stack in a single instruction. We are returning to kernel
- * mode, so this cannot result in a fault.
+ * iretq reads the "iret" frame and exits the NMI stack in a
+ * single instruction. We are returning to kernel mode, so this
+ * cannot result in a fault. Similarly, we don't need to worry
+ * about espfix64 on the way back to kernel mode.
*/
- INTERRUPT_RETURN
+ iretq
END(nmi)
ENTRY(ignore_sysret)
+ UNWIND_HINT_EMPTY
mov $-ENOSYS, %eax
sysret
END(ignore_sysret)
ENTRY(rewind_stack_do_exit)
+ UNWIND_HINT_FUNC
/* Prevent any naive code from trying to unwind to our caller. */
xorl %ebp, %ebp
movq PER_CPU_VAR(cpu_current_top_of_stack), %rax
- leaq -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%rax), %rsp
+ leaq -PTREGS_SIZE(%rax), %rsp
+ UNWIND_HINT_FUNC sp_offset=PTREGS_SIZE
call do_exit
-1: jmp 1b
END(rewind_stack_do_exit)