x86_64, traps: Rework bad_iret

[pandora-kernel.git] / arch / x86 / kernel / traps.c

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index e6fbb94..56d013f 100644 (file)
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -213,29 +213,41 @@ DO_ERROR(X86_TRAP_OLD_MF, SIGFPE, "coprocessor segment overrun",
                coprocessor_segment_overrun)
 DO_ERROR(X86_TRAP_TS, SIGSEGV, "invalid TSS", invalid_TSS)
 DO_ERROR(X86_TRAP_NP, SIGBUS, "segment not present", segment_not_present)
-#ifdef CONFIG_X86_32
 DO_ERROR(X86_TRAP_SS, SIGBUS, "stack segment", stack_segment)
-#endif
 DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check,
                BUS_ADRALN, 0)
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
-dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
-{
-       if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-                       X86_TRAP_SS, SIGBUS) == NOTIFY_STOP)
-               return;
-       preempt_conditional_sti(regs);
-       do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
-       preempt_conditional_cli(regs);
-}
-
 dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 {
        static const char str[] = "double fault";
        struct task_struct *tsk = current;
 
+#ifdef CONFIG_X86_ESPFIX64
+       extern unsigned char native_irq_return_iret[];
+
+       /*
+        * If IRET takes a non-IST fault on the espfix64 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.
+        */
+       if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+               regs->cs == __KERNEL_CS &&
+               regs->ip == (unsigned long)native_irq_return_iret)
+       {
+               struct pt_regs *normal_regs = task_pt_regs(current);
+
+               /* Fake a #GP(0) from userspace. */
+               memmove(&normal_regs->ip, (void *)regs->sp, 5*8);
+               normal_regs->orig_ax = 0;  /* Missing (lost) #GP error code */
+               regs->ip = (unsigned long)general_protection;
+               regs->sp = (unsigned long)&normal_regs->orig_ax;
+               return;
+       }
+#endif
+
        /* Return not checked because double check cannot be ignored */
        notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
 
@@ -351,6 +363,35 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
                *regs = *eregs;
        return regs;
 }
+
+struct bad_iret_stack {
+       void *error_entry_ret;
+       struct pt_regs regs;
+};
+
+asmlinkage
+struct bad_iret_stack *fixup_bad_iret(struct bad_iret_stack *s)
+{
+       /*
+        * This is called from entry_64.S early in handling a fault
+        * caused by a bad iret to user mode.  To handle the fault
+        * correctly, we want move our stack frame to task_pt_regs
+        * and we want to pretend that the exception came from the
+        * iret target.
+        */
+       struct bad_iret_stack *new_stack =
+               container_of(task_pt_regs(current),
+                            struct bad_iret_stack, regs);
+
+       /* Copy the IRET target to the new stack. */
+       memmove(&new_stack->regs.ip, (void *)s->regs.sp, 5*8);
+
+       /* Copy the remainder of the stack from the current stack. */
+       memmove(new_stack, s, offsetof(struct bad_iret_stack, regs.ip));
+
+       BUG_ON(!user_mode_vm(&new_stack->regs));
+       return new_stack;
+}
 #endif
 
 /*
@@ -582,12 +623,13 @@ void __math_state_restore(struct task_struct *tsk)
        /* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
           is pending.  Clear the x87 state here by setting it to fixed
           values. safe_address is a random variable that should be in L1 */
-       alternative_input(
-               ASM_NOP8 ASM_NOP2,
-               "emms\n\t"              /* clear stack tags */
-               "fildl %P[addr]",       /* set F?P to defined value */
-               X86_FEATURE_FXSAVE_LEAK,
-               [addr] "m" (safe_address));
+       if (unlikely(static_cpu_has(X86_FEATURE_FXSAVE_LEAK))) {
+               asm volatile(
+                       "fnclex\n\t"
+                       "emms\n\t"
+                       "fildl %P[addr]"        /* set F?P to defined value */
+                       : : [addr] "m" (safe_address));
+       }
 
        /*
         * Paranoid restore. send a SIGSEGV if we fail to restore the state.
@@ -710,7 +752,7 @@ void __init trap_init(void)
        set_intr_gate(X86_TRAP_OLD_MF, &coprocessor_segment_overrun);
        set_intr_gate(X86_TRAP_TS, &invalid_TSS);
        set_intr_gate(X86_TRAP_NP, &segment_not_present);
-       set_intr_gate_ist(X86_TRAP_SS, &stack_segment, STACKFAULT_STACK);
+       set_intr_gate(X86_TRAP_SS, stack_segment);
        set_intr_gate(X86_TRAP_GP, &general_protection);
        set_intr_gate(X86_TRAP_SPURIOUS, &spurious_interrupt_bug);
        set_intr_gate(X86_TRAP_MF, &coprocessor_error);