Merge branch 'x86-traps' (trap handling from Andy Lutomirski)

Merge x86-64 iret fixes from Andy Lutomirski:
 "This addresses the following issues:

   - an unrecoverable double-fault triggerable with modify_ldt.
   - invalid stack usage in espfix64 failed IRET recovery from IST
     context.
   - invalid stack usage in non-espfix64 failed IRET recovery from IST
     context.

  It also makes a good but IMO scary change: non-espfix64 failed IRET
  will now report the correct error.  Hopefully nothing depended on the
  old incorrect behavior, but maybe Wine will get confused in some
  obscure corner case"

* emailed patches from Andy Lutomirski <luto@amacapital.net>:
  x86_64, traps: Rework bad_iret
  x86_64, traps: Stop using IST for #SS
  x86_64, traps: Fix the espfix64 #DF fixup and rewrite it in C

arch/x86/include/asm/page_32_types.h

@@ -20,7 +20,6 @@
 #define THREAD_SIZE_ORDER	1
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
-#define STACKFAULT_STACK 0
 #define DOUBLEFAULT_STACK 1
 #define NMI_STACK 0
 #define DEBUG_STACK 0

arch/x86/include/asm/page_64_types.h

@@ -14,12 +14,11 @@
 #define IRQ_STACK_ORDER 2
 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
 
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2
-#define NMI_STACK 3
-#define DEBUG_STACK 4
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
+#define DOUBLEFAULT_STACK 1
+#define NMI_STACK 2
+#define DEBUG_STACK 3
+#define MCE_STACK 4
+#define N_EXCEPTION_STACKS 4  /* hw limit: 7 */
 
 #define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
 #define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))

arch/x86/include/asm/traps.h

@@ -39,6 +39,7 @@ asmlinkage void simd_coprocessor_error(void);
 
 #ifdef CONFIG_TRACING
 asmlinkage void trace_page_fault(void);
+#define trace_stack_segment stack_segment
 #define trace_divide_error divide_error
 #define trace_bounds bounds
 #define trace_invalid_op invalid_op

arch/x86/kernel/dumpstack_64.c

@@ -24,7 +24,6 @@ static char x86_stack_ids[][8] = {
 		[ DEBUG_STACK-1			]	= "#DB",
 		[ NMI_STACK-1			]	= "NMI",
 		[ DOUBLEFAULT_STACK-1		]	= "#DF",
-		[ STACKFAULT_STACK-1		]	= "#SS",
 		[ MCE_STACK-1			]	= "#MC",
 #if DEBUG_STKSZ > EXCEPTION_STKSZ
 		[ N_EXCEPTION_STACKS ...

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)
 

arch/x86/kernel/traps.c

@@ -233,32 +233,40 @@ DO_ERROR(X86_TRAP_UD,     SIGILL,  "invalid opcode",		invalid_op)
 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(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check)
 
 #ifdef CONFIG_X86_64
 /* Runs on IST stack */
-dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code)
-{
-	enum ctx_state prev_state;
-
-	prev_state = exception_enter();
-	if (notify_die(DIE_TRAP, "stack segment", regs, error_code,
-		       X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) {
-		preempt_conditional_sti(regs);
-		do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL);
-		preempt_conditional_cli(regs);
-	}
-	exception_exit(prev_state);
-}
-
 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
+
 	exception_enter();
 	/* Return not checked because double check cannot be ignored */
 	notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV);
@@ -399,6 +407,35 @@ asmlinkage __visible struct pt_regs *sync_regs(struct pt_regs *eregs)
 	return regs;
 }
 NOKPROBE_SYMBOL(sync_regs);
+
+struct bad_iret_stack {
+	void *error_entry_ret;
+	struct pt_regs regs;
+};
+
+asmlinkage __visible
+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
 
 /*
@@ -778,7 +815,7 @@ 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);