x86/entry/xen: Route #DB correctly on Xen PV

On Xen PV, #DB doesn't use IST. It still needs to be correctly routed
depending on whether it came from user or kernel mode.

Get rid of DECLARE/DEFINE_IDTENTRY_XEN -- it was too hard to follow the
logic.  Instead, route #DB and NMI through DECLARE/DEFINE_IDTENTRY_RAW on
Xen, and do the right thing for #DB.  Also add more warnings to the
exc_debug* handlers to make this type of failure more obvious.

This fixes various forms of corruption that happen when usermode
triggers #DB on Xen PV.

Fixes: 4c0dcd8 ("x86/entry: Implement user mode C entry points for #DB and #MCE")
Signed-off-by: Andy Lutomirski <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lkml.kernel.org/r/4163e733cce0b41658e252c6c6b3464f33fdff17.1593795633.git.luto@kernel.org

Author: amluto

arch/x86/include/asm/idtentry.h

@@ -398,18 +398,6 @@ __visible noinstr void func(struct pt_regs *regs,			\
 #define DEFINE_IDTENTRY_DEBUG		DEFINE_IDTENTRY_IST
 #define DEFINE_IDTENTRY_DEBUG_USER	DEFINE_IDTENTRY_NOIST
 
-/**
- * DECLARE_IDTENTRY_XEN - Declare functions for XEN redirect IDT entry points
- * @vector:	Vector number (ignored for C)
- * @func:	Function name of the entry point
- *
- * Used for xennmi and xendebug redirections. No DEFINE as this is all ASM
- * indirection magic.
- */
-#define DECLARE_IDTENTRY_XEN(vector, func)				\
-	asmlinkage void xen_asm_exc_xen##func(void);			\
-	asmlinkage void asm_exc_xen##func(void)
-
 #else /* !__ASSEMBLY__ */
 
 /*
@@ -469,10 +457,6 @@ __visible noinstr void func(struct pt_regs *regs,			\
 /* No ASM code emitted for NMI */
 #define DECLARE_IDTENTRY_NMI(vector, func)
 
-/* XEN NMI and DB wrapper */
-#define DECLARE_IDTENTRY_XEN(vector, func)				\
-	idtentry vector asm_exc_xen##func exc_##func has_error_code=0
-
 /*
  * ASM code to emit the common vector entry stubs where each stub is
  * packed into 8 bytes.
@@ -570,11 +554,15 @@ DECLARE_IDTENTRY_MCE(X86_TRAP_MC,	exc_machine_check);
 
 /* NMI */
 DECLARE_IDTENTRY_NMI(X86_TRAP_NMI,	exc_nmi);
-DECLARE_IDTENTRY_XEN(X86_TRAP_NMI,	nmi);
+#ifdef CONFIG_XEN_PV
+DECLARE_IDTENTRY_RAW(X86_TRAP_NMI,	xenpv_exc_nmi);
+#endif
 
 /* #DB */
 DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB,	exc_debug);
-DECLARE_IDTENTRY_XEN(X86_TRAP_DB,	debug);
+#ifdef CONFIG_XEN_PV
+DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	xenpv_exc_debug);
+#endif
 
 /* #DF */
 DECLARE_IDTENTRY_DF(X86_TRAP_DF,	exc_double_fault);

arch/x86/kernel/traps.c

@@ -865,6 +865,12 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 	instrumentation_begin();
 	trace_hardirqs_off_finish();
 
+	/*
+	 * If something gets miswired and we end up here for a user mode
+	 * #DB, we will malfunction.
+	 */
+	WARN_ON_ONCE(user_mode(regs));
+
 	/*
 	 * Catch SYSENTER with TF set and clear DR_STEP. If this hit a
 	 * watchpoint at the same time then that will still be handled.
@@ -883,6 +889,12 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs,
 static __always_inline void exc_debug_user(struct pt_regs *regs,
 					   unsigned long dr6)
 {
+	/*
+	 * If something gets miswired and we end up here for a kernel mode
+	 * #DB, we will malfunction.
+	 */
+	WARN_ON_ONCE(!user_mode(regs));
+
 	idtentry_enter_user(regs);
 	instrumentation_begin();
 

arch/x86/xen/enlighten_pv.c

@@ -598,6 +598,26 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 }
 
 #ifdef CONFIG_X86_64
+void noist_exc_debug(struct pt_regs *regs);
+
+DEFINE_IDTENTRY_RAW(xenpv_exc_nmi)
+{
+	/* On Xen PV, NMI doesn't use IST.  The C part is the sane as native. */
+	exc_nmi(regs);
+}
+
+DEFINE_IDTENTRY_RAW(xenpv_exc_debug)
+{
+	/*
+	 * There's no IST on Xen PV, but we still need to dispatch
+	 * to the correct handler.
+	 */
+	if (user_mode(regs))
+		noist_exc_debug(regs);
+	else
+		exc_debug(regs);
+}
+
 struct trap_array_entry {
 	void (*orig)(void);
 	void (*xen)(void);
@@ -609,18 +629,18 @@ struct trap_array_entry {
 	.xen		= xen_asm_##func,		\
 	.ist_okay	= ist_ok }
 
-#define TRAP_ENTRY_REDIR(func, xenfunc, ist_ok) {	\
+#define TRAP_ENTRY_REDIR(func, ist_ok) {		\
 	.orig		= asm_##func,			\
-	.xen		= xen_asm_##xenfunc,		\
+	.xen		= xen_asm_xenpv_##func,		\
 	.ist_okay	= ist_ok }
 
 static struct trap_array_entry trap_array[] = {
-	TRAP_ENTRY_REDIR(exc_debug, exc_xendebug,	true  ),
+	TRAP_ENTRY_REDIR(exc_debug,			true  ),
 	TRAP_ENTRY(exc_double_fault,			true  ),
 #ifdef CONFIG_X86_MCE
 	TRAP_ENTRY(exc_machine_check,			true  ),
 #endif
-	TRAP_ENTRY_REDIR(exc_nmi, exc_xennmi,		true  ),
+	TRAP_ENTRY_REDIR(exc_nmi,			true  ),
 	TRAP_ENTRY(exc_int3,				false ),
 	TRAP_ENTRY(exc_overflow,			false ),
 #ifdef CONFIG_IA32_EMULATION

arch/x86/xen/xen-asm_64.S

@@ -29,10 +29,9 @@ _ASM_NOKPROBE(xen_\name)
 .endm
 
 xen_pv_trap asm_exc_divide_error
-xen_pv_trap asm_exc_debug
-xen_pv_trap asm_exc_xendebug
+xen_pv_trap asm_xenpv_exc_debug
 xen_pv_trap asm_exc_int3
-xen_pv_trap asm_exc_xennmi
+xen_pv_trap asm_xenpv_exc_nmi
 xen_pv_trap asm_exc_overflow
 xen_pv_trap asm_exc_bounds
 xen_pv_trap asm_exc_invalid_op