1 files changed, 22 insertions, 59 deletions

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index df088bb03fb3..c0226ab54106 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -828,9 +828,15 @@ ENTRY(native_iret)
         jnz native_irq_return_ldt
 #endif
 
+.global native_irq_return_iret
 native_irq_return_iret:
+        /*
+         * 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.
+         */
         iretq
-        _ASM_EXTABLE(native_irq_return_iret, bad_iret)
 
 #ifdef CONFIG_X86_ESPFIX64
 native_irq_return_ldt:
@@ -858,25 +864,6 @@ native_irq_return_ldt:
         jmp native_irq_return_iret
 #endif
 
-        .section .fixup,"ax"
-bad_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.
-         */
-        pushq $0
-
-        SWAPGS
-        jmp general_protection
-
-        .previous
-
         /* edi: workmask, edx: work */
 retint_careful:
         CFI_RESTORE_STATE
@@ -922,37 +909,6 @@ ENTRY(retint_kernel)
         CFI_ENDPROC
 END(common_interrupt)
 
-        /*
-         * If IRET takes a fault on the espfix stack, then we
-         * end up promoting it to a doublefault.  In that case,
-         * modify the stack to make it look like we just entered
-         * the #GP handler from user space, similar to bad_iret.
-         */
-#ifdef CONFIG_X86_ESPFIX64
-        ALIGN
-__do_double_fault:
-        XCPT_FRAME 1 RDI+8
-        movq RSP(%rdi),%rax             /* Trap on the espfix stack? */
-        sarq $PGDIR_SHIFT,%rax
-        cmpl $ESPFIX_PGD_ENTRY,%eax
-        jne do_double_fault             /* No, just deliver the fault */
-        cmpl $__KERNEL_CS,CS(%rdi)
-        jne do_double_fault
-        movq RIP(%rdi),%rax
-        cmpq $native_irq_return_iret,%rax
-        jne do_double_fault             /* This shouldn't happen... */
-        movq PER_CPU_VAR(kernel_stack),%rax
-        subq $(6*8-KERNEL_STACK_OFFSET),%rax    /* Reset to original stack */
-        movq %rax,RSP(%rdi)
-        movq $0,(%rax)                  /* Missing (lost) #GP error code */
-        movq $general_protection,RIP(%rdi)
-        retq
-        CFI_ENDPROC
-END(__do_double_fault)
-#else
-# define __do_double_fault do_double_fault
-#endif
-
 /*
  * APIC interrupts.
  */
@@ -1124,7 +1080,7 @@ idtentry overflow do_overflow has_error_code=0
 idtentry bounds do_bounds has_error_code=0
 idtentry invalid_op do_invalid_op has_error_code=0
 idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault __do_double_fault has_error_code=1 paranoid=1
+idtentry double_fault do_double_fault has_error_code=1 paranoid=1
 idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
 idtentry invalid_TSS do_invalid_TSS has_error_code=1
 idtentry segment_not_present do_segment_not_present has_error_code=1
@@ -1289,7 +1245,7 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \
 
 idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
 idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK
-idtentry stack_segment do_stack_segment has_error_code=1 paranoid=1
+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
@@ -1399,17 +1355,16 @@ error_sti:
 
 /*
  * 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:
         CFI_REL_OFFSET rcx, RCX+8
         incl %ebx
         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
@@ -1420,7 +1375,15 @@ error_kernelspace:
 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)