#include <asm/paravirt.h>
#include <asm/ftrace.h>
#include <asm/percpu.h>
+#include <asm/pgtable_types.h>
/* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */
#include <linux/elf-em.h>
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 native_iret, bad_iret
- .previous
+ /*
+ * Are we returning to a stack segment from the LDT? Note: in
+ * 64-bit mode SS:RSP on the exception stack is always valid.
+ */
+#ifdef CONFIG_X86_ESPFIX64
+ testb $4,(SS-RIP)(%rsp)
+ jnz native_irq_return_ldt
#endif
- .section .fixup,"ax"
-bad_iret:
+.global native_irq_return_iret
+native_irq_return_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.
+ * This may fault. Non-paranoid faults on return to userspace are
+ * handled by fixup_bad_iret. These include #SS, #GP, and #NP.
+ * Double-faults due to espfix64 are handled in do_double_fault.
+ * Other faults here are fatal.
*/
- pushq $0
+ iretq
+#ifdef CONFIG_X86_ESPFIX64
+native_irq_return_ldt:
+ pushq_cfi %rax
+ pushq_cfi %rdi
SWAPGS
- jmp general_protection
-
- .previous
+ movq PER_CPU_VAR(espfix_waddr),%rdi
+ movq %rax,(0*8)(%rdi) /* RAX */
+ movq (2*8)(%rsp),%rax /* RIP */
+ movq %rax,(1*8)(%rdi)
+ movq (3*8)(%rsp),%rax /* CS */
+ movq %rax,(2*8)(%rdi)
+ movq (4*8)(%rsp),%rax /* RFLAGS */
+ movq %rax,(3*8)(%rdi)
+ movq (6*8)(%rsp),%rax /* SS */
+ movq %rax,(5*8)(%rdi)
+ movq (5*8)(%rsp),%rax /* RSP */
+ movq %rax,(4*8)(%rdi)
+ andl $0xffff0000,%eax
+ popq_cfi %rdi
+ orq PER_CPU_VAR(espfix_stack),%rax
+ SWAPGS
+ movq %rax,%rsp
+ popq_cfi %rax
+ jmp native_irq_return_iret
+#endif
/* edi: workmask, edx: work */
retint_careful:
call preempt_schedule_irq
jmp exit_intr
#endif
-
CFI_ENDPROC
END(common_interrupt)
+
/*
* End of kprobes section
*/
CFI_RESTORE r11
addq $0x30,%rsp
CFI_ADJUST_CFA_OFFSET -0x30
- pushq_cfi $0
+ pushq_cfi $-1 /* orig_ax = -1 => not a system call */
SAVE_ALL
jmp error_exit
CFI_ENDPROC
paranoidzeroentry_ist debug do_debug DEBUG_STACK
paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
-paranoiderrorentry stack_segment do_stack_segment
+errorentry stack_segment do_stack_segment
#ifdef CONFIG_XEN
zeroentry xen_debug do_debug
zeroentry xen_int3 do_int3
/*
* 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.
+ * usergs. Handle them here. B stepping K8s sometimes report a
+ * truncated RIP for IRET exceptions returning to compat mode. Check
+ * for these here too.
*/
error_kernelspace:
incl %ebx
- leaq irq_return(%rip),%rcx
+ leaq native_irq_return_iret(%rip),%rcx
cmpq %rcx,RIP+8(%rsp)
- je error_swapgs
+ je error_bad_iret
movl %ecx,%eax /* zero extend */
cmpq %rax,RIP+8(%rsp)
je bstep_iret
bstep_iret:
/* Fix truncated RIP */
movq %rcx,RIP+8(%rsp)
- jmp error_swapgs
+ /* fall through */
+
+error_bad_iret:
+ SWAPGS
+ mov %rsp,%rdi
+ call fixup_bad_iret
+ mov %rax,%rsp
+ decl %ebx /* Return to usergs */
+ jmp error_sti
CFI_ENDPROC
END(error_entry)