From: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
stts() is implemented in terms of read_cr0/write_cr0 to update the
state of the TS bit. This happens during context switch, and so
is fairly performance critical. Rather than falling back to
a trap-and-emulate native read_cr0, implement our own by caching
the last-written value from write_cr0 (the TS bit is the only one
we really care about).
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
---
arch/x86/xen/enlighten.c | 18 +++++++++++++++++-
1 files changed, 17 insertions(+), 1 deletions(-)
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index cbb31eb..9c6de48 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -656,10 +656,26 @@ static void xen_clts(void)
xen_mc_issue(PARAVIRT_LAZY_CPU);
}
+static DEFINE_PER_CPU(unsigned long, xen_cr0_value);
+
+static unsigned long xen_read_cr0(void)
+{
+ unsigned long cr0 = percpu_read(xen_cr0_value);
+
+ if (unlikely(cr0 == 0)) {
+ cr0 = native_read_cr0();
+ percpu_write(xen_cr0_value, cr0);
+ }
+
+ return cr0;
+}
+
static void xen_write_cr0(unsigned long cr0)
{
struct multicall_space mcs;
+ percpu_write(xen_cr0_value, cr0);
+
/* Only pay attention to cr0.TS; everything else is
ignored. */
mcs = xen_mc_entry(0);
@@ -845,7 +861,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
.clts = xen_clts,
- .read_cr0 = native_read_cr0,
+ .read_cr0 = xen_read_cr0,
.write_cr0 = xen_write_cr0,
.read_cr4 = native_read_cr4,
--
1.6.0.6
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
Home