[PATCH v2 5/6] x86/xen: Add a Xen-specific sync_core() implementation

[Andy Lutomirski <luto@kernel.org>]

On Xen PV, CPUID is likely to trap, and Xen hypercalls aren't
guaranteed to serialize.  (Even CPUID isn't *really* guaranteed to
serialize on Xen PV, but, in practice, any trap it generates will
serialize.)

On my laptop, CPUID(eax=1, ecx=0) is ~83ns and IRET-to-self is
~110ns.  But Xen PV will trap CPUID if possible, so IRET-to-self
should end up being a nice speedup.

Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Andy Lutomirski <luto@kernel.org>
---
 arch/x86/xen/enlighten.c | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bdd855685403..1f765b41eee7 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -311,6 +311,39 @@ static __read_mostly unsigned int cpuid_leaf1_ecx_set_mask;
 static __read_mostly unsigned int cpuid_leaf5_ecx_val;
 static __read_mostly unsigned int cpuid_leaf5_edx_val;
 
+static void xen_sync_core(void)
+{
+	register void *__sp asm(_ASM_SP);
+
+#ifdef CONFIG_X86_32
+	asm volatile (
+		"pushl %%ss\n\t"
+		"pushl %%esp\n\t"
+		"addl $4, (%%esp)\n\t"
+		"pushfl\n\t"
+		"pushl %%cs\n\t"
+		"pushl $1f\n\t"
+		"iret\n\t"
+		"1:"
+		: "+r" (__sp) : : "cc");
+#else
+	unsigned long tmp;
+
+	asm volatile (
+		"movq %%ss, %0\n\t"
+		"pushq %0\n\t"
+		"pushq %%rsp\n\t"
+		"addq $8, (%%rsp)\n\t"
+		"pushfq\n\t"
+		"movq %%cs, %0\n\t"
+		"pushq %0\n\t"
+		"pushq $1f\n\t"
+		"iretq\n\t"
+		"1:"
+		: "=r" (tmp), "+r" (__sp) : : "cc");
+#endif
+}
+
 static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 		      unsigned int *cx, unsigned int *dx)
 {
@@ -1289,6 +1322,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 
 	.start_context_switch = paravirt_start_context_switch,
 	.end_context_switch = xen_end_context_switch,
+
+	.sync_core = xen_sync_core,
 };
 
 static void xen_reboot(int reason)
-- 
2.9.3