x86/entry/32: Pull the MSR_IA32_SYSENTER_CS update code out of native_load_sp0()

This causes the MSR_IA32_SYSENTER_CS write to move out of the
paravirt callback.  This shouldn't affect Xen PV: Xen already ignores
MSR_IA32_SYSENTER_ESP writes.  In any event, Xen doesn't support
vm86() in a useful way.

Note to any potential backporters: This patch won't break lguest, as
lguest didn't have any SYSENTER support at all.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/75cf09fe03ae778532d0ca6c65aa58e66bc2f90c.1509609304.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/processor.h

@@ -520,13 +520,6 @@ static inline void
 native_load_sp0(struct tss_struct *tss, struct thread_struct *thread)
 {
 	tss->x86_tss.sp0 = thread->sp0;
-#ifdef CONFIG_X86_32
-	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
-	if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
-		tss->x86_tss.ss1 = thread->sysenter_cs;
-		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
-	}
-#endif
 }
 
 static inline void native_swapgs(void)

arch/x86/include/asm/switch_to.h

@@ -72,4 +72,16 @@ do {									\
 	((last) = __switch_to_asm((prev), (next)));			\
 } while (0)
 
+#ifdef CONFIG_X86_32
+static inline void refresh_sysenter_cs(struct thread_struct *thread)
+{
+	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
+	if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs))
+		return;
+
+	this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs);
+	wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
+}
+#endif
+
 #endif /* _ASM_X86_SWITCH_TO_H */

arch/x86/kernel/process_32.c

@@ -284,9 +284,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	/*
 	 * Reload esp0 and cpu_current_top_of_stack.  This changes
-	 * current_thread_info().
+	 * current_thread_info().  Refresh the SYSENTER configuration in
+	 * case prev or next is vm86.
 	 */
 	load_sp0(tss, next);
+	refresh_sysenter_cs(next);
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
 		       THREAD_SIZE);

arch/x86/kernel/process_64.c

@@ -464,7 +464,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 */
 	this_cpu_write(current_task, next_p);
 
-	/* Reload esp0 and ss1.  This changes current_thread_info(). */
+	/* Reload sp0. */
 	load_sp0(tss, next);
 
 	/*

arch/x86/kernel/vm86_32.c

@@ -54,6 +54,7 @@
 #include <asm/irq.h>
 #include <asm/traps.h>
 #include <asm/vm86.h>
+#include <asm/switch_to.h>
 
 /*
  * Known problems:
@@ -149,6 +150,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 	tsk->thread.sp0 = vm86->saved_sp0;
 	tsk->thread.sysenter_cs = __KERNEL_CS;
 	load_sp0(tss, &tsk->thread);
+	refresh_sysenter_cs(&tsk->thread);
 	vm86->saved_sp0 = 0;
 	put_cpu();
 
@@ -368,8 +370,10 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	/* make room for real-mode segments */
 	tsk->thread.sp0 += 16;
 
-	if (static_cpu_has(X86_FEATURE_SEP))
+	if (static_cpu_has(X86_FEATURE_SEP)) {
 		tsk->thread.sysenter_cs = 0;
+		refresh_sysenter_cs(&tsk->thread);
+	}
 
 	load_sp0(tss, &tsk->thread);
 	put_cpu();