[Xen-devel] [PATCH] Allow guest to register a secondary vcpu_time_info structure

[Jeremy Fitzhardinge <jeremy@xxxxxxxx>]

Allow a guest to register a second location for the VCPU time info
structure for each vcpu.  This is intended to allow the guest kernel to
map this information into a usermode accessible page, so that usermode
can efficiently calculate system time from the TSC without having to
make a syscall.

The second vcpu_time_info structure is updated by copy, rather than
being a shared page between the guest and Xen.  It is not directly
updated by copy; instead, Xen preserves and increments the existing
version number in place.  This allows the guest to also update the
version number (useful to indicate vcpu context switches to usermode). 
This assumes that the guest will only ever update the structure for a
given vcpu on that vcpu (as Xen does, so there are never any cross-cpu
accesses).

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>

diff -r 6472342c8ab0 -r 1dc86d83b352 xen/arch/x86/domain.c
--- a/xen/arch/x86/domain.c     Wed Sep 30 08:51:21 2009 +0100
+++ b/xen/arch/x86/domain.c     Fri Oct 02 17:01:26 2009 -0700
@@ -964,6 +964,24 @@
         break;
     }
 
+    case VCPUOP_register_vcpu_time_memory_area:
+    {
+        struct vcpu_register_time_memory_area area;
+        rc = -EFAULT;
+        if ( copy_from_guest(&area, arg, 1) )
+            break;
+
+        if ( !guest_handle_okay(area.addr.h, 1) )
+            break;
+
+        rc = 0;
+        v->time_info_guest = area.addr.h;
+
+        __update_vcpu_system_time(v, 1);
+
+        break;
+    }
+
     case VCPUOP_get_physid:
     {
         struct vcpu_get_physid cpu_id;
diff -r 6472342c8ab0 -r 1dc86d83b352 xen/arch/x86/time.c
--- a/xen/arch/x86/time.c       Wed Sep 30 08:51:21 2009 +0100
+++ b/xen/arch/x86/time.c       Fri Oct 02 17:01:26 2009 -0700
@@ -22,6 +22,7 @@
 #include <xen/irq.h>
 #include <xen/softirq.h>
 #include <xen/keyhandler.h>
+#include <xen/guest_access.h>
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/mpspec.h>
@@ -826,7 +827,31 @@
     (*version)++;
 }
 
-void update_vcpu_system_time(struct vcpu *v)
+static void update_guest_time_info(struct vcpu *v, struct vcpu_time_info *u)
+{
+    struct vcpu_time_info info;
+    u32 version;
+
+    if ( guest_handle_is_null(v->time_info_guest) )
+        return;
+
+    if ( __copy_from_guest(&info, v->time_info_guest, 1) )
+        return;
+
+    /*
+     * Update the guest copy of the time info.  We need to make sure
+     * we update the guest's version of the version number rather than
+     * use a verbtim copy of the master one, because the guest may
+     * update the version for its own purposes.
+     */
+    version = info.version;
+    info = *u;
+    info.version = (version + 2) & ~1;
+
+    __copy_to_guest(v->time_info_guest, &info, 1);
+}
+
+void __update_vcpu_system_time(struct vcpu *v, int force)
 {
     struct cpu_time       *t;
     struct vcpu_time_info *u;
@@ -837,7 +862,7 @@
     t = &this_cpu(cpu_time);
     u = &vcpu_info(v, time);
 
-    if ( u->tsc_timestamp == t->local_tsc_stamp )
+    if ( !force && u->tsc_timestamp == t->local_tsc_stamp )
         return;
 
     version_update_begin(&u->version);
@@ -848,6 +873,13 @@
     u->tsc_shift         = (s8)t->tsc_scale.shift;
 
     version_update_end(&u->version);
+
+    update_guest_time_info(v, u);
+}
+
+void update_vcpu_system_time(struct vcpu *v)
+{
+    __update_vcpu_system_time(v, 0);
 }
 
 void update_domain_wallclock_time(struct domain *d)
diff -r 6472342c8ab0 -r 1dc86d83b352 xen/include/public/vcpu.h
--- a/xen/include/public/vcpu.h Wed Sep 30 08:51:21 2009 +0100
+++ b/xen/include/public/vcpu.h Fri Oct 02 17:01:26 2009 -0700
@@ -202,6 +202,49 @@
 #define xen_vcpu_physid_to_x86_acpiid(physid) \
     ((((uint32_t)((physid)>>32)) >= 0xff) ? 0xff : ((uint8_t)((physid)>>32)))
 
+/* 
+ * Register a memory location to get a secondary copy of the vcpu time
+ * parameters.  The master copy still exists as part of the vcpu
+ * shared memory area, and this secondary copy is updated whenever the
+ * master copy is updated.
+ *
+ * The intent is that this copy may be mapped (RO) into userspace so
+ * that usermode can compute system time using the time info and the
+ * tsc.  Usermode will see an array of vcpu_time_info structures, one
+ * for each vcpu, and choose the right one by an existing mechanism
+ * which allows it to get the current vcpu number (such as via a
+ * segment limit).  It can then apply the normal algorithm to compute
+ * system time from the tsc.
+ *
+ * However, because usermode threads are subject to two levels of
+ * scheduling (kernel scheduling of threads to vcpus, and Xen
+ * scheduling of vcpus to pcpus), we must make sure that the thread
+ * knows it has had a race with either (or both) of these two events.
+ * To allow this, the guest kernel updates the time_info version
+ * number when the vcpu does a context switch, so that usermode will
+ * always see a version number change when the parameters need to be
+ * revalidated.  Xen makes sure that it always updates the guest's
+ * version rather than overwriting it.  (It assumes that a vcpu will
+ * always update its own version number, so there are no cross-cpu
+ * synchronization issues; the only concern is that if the guest
+ * kernel gets preempted by Xen it doesn't revert the version number
+ * to an older value.)
+ *
+ * @extra_arg == pointer to vcpu_register_time_info_memory_area structure.
+ */
+#define VCPUOP_register_vcpu_time_memory_area   13
+
+DEFINE_XEN_GUEST_HANDLE(vcpu_time_info_t);
+struct vcpu_register_time_memory_area {
+    union {
+        XEN_GUEST_HANDLE(vcpu_time_info_t) h;
+        struct vcpu_time_info *v;
+        uint64_t p;
+    } addr;
+};
+typedef struct vcpu_register_time_memory_area vcpu_register_time_memory_area_t;
+DEFINE_XEN_GUEST_HANDLE(vcpu_register_time_memory_area_t);
+
 #endif /* __XEN_PUBLIC_VCPU_H__ */
 
 /*
diff -r 6472342c8ab0 -r 1dc86d83b352 xen/include/xen/sched.h
--- a/xen/include/xen/sched.h   Wed Sep 30 08:51:21 2009 +0100
+++ b/xen/include/xen/sched.h   Fri Oct 02 17:01:26 2009 -0700
@@ -102,6 +102,9 @@
     } runstate_guest; /* guest address */
 #endif
 
+    /* A secondary copy of the vcpu time info */
+    XEN_GUEST_HANDLE(vcpu_time_info_t) time_info_guest;
+
     /* last time when vCPU is scheduled out */
     uint64_t last_run_time;
 
diff -r 6472342c8ab0 -r 1dc86d83b352 xen/include/xen/time.h
--- a/xen/include/xen/time.h    Wed Sep 30 08:51:21 2009 +0100
+++ b/xen/include/xen/time.h    Fri Oct 02 17:01:26 2009 -0700
@@ -54,6 +54,7 @@
 #define STIME_MAX ((s_time_t)((uint64_t)~0ull>>1))
 
 extern void update_vcpu_system_time(struct vcpu *v);
+extern void __update_vcpu_system_time(struct vcpu *v, int force);
 extern void update_domain_wallclock_time(struct domain *d);
 
 extern void do_settime(



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel