Replace tsc_native config option with tsc_mode config option

(NOTE: pvrdtscp mode not finished yet, but all other
modes have been tested so sooner seemed better than
later to submit this fairly major patch so we can get
more mileage on it before next release.)

New tsc_mode config option supercedes tsc_native and
offers a more intelligent default and an additional
option for intelligent apps running on PV domains
("pvrdtscp").

For PV domains, default mode will determine if the initial
host has a "safe"** TSC (meaning it is always synchronized
across all physical CPUs).  If so, all domains will
execute all rdtsc instructions natively; if not,
all domains will emulate all rdtsc instructions but
providing the TSC hertz rate of the initial machine.
After being restored or live-migrated, all PV domains will
emulate all rdtsc instructions.  Hence, this default mode
guarantees correctness while providing native performance
in most conditions.

For PV domains, tsc_mode==1 will always emulate rdtsc
and tsc_mode==2 will never emulate rdtsc.  For tsc_mode==3,
rdtsc will never be emulated, but information is provided
through pvcpuid instructions and rdtscp instructions
so that an app can obtain "safe" pvclock-like TSC information
across save/restore and live migration. (Will be completed in
a follow-on patch.)

For HVM domains, the default mode and "always emulate"
mode do the same as tsc_native==0; the other two modes
do the same as tsc_native==1.  (HVM domains since 3.4
have implemented a tsc_mode=default-like functionality,
but also can preserve native TSC across save/restore
and live-migration IFF the initial and target machines
have a common TSC cycle rate.)

** All newer AMD machines, and Nehalem and future Intel
machines have "Invariant TSC"; many newer Intel machines
have "Constant TSC" and do not support deep-C sleep states;
these and all single-processor machines are "safe".

Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>

1 files changed, 17 insertions, 6 deletions

diff --git a/xen/include/public/domctl.h b/xen/include/public/domctl.h
index cac3477671..88b19a4ffe 100644
--- a/xen/include/public/domctl.h
+++ b/xen/include/public/domctl.h
@@ -401,11 +401,6 @@ struct xen_domctl_settimeoffset {
 typedef struct xen_domctl_settimeoffset xen_domctl_settimeoffset_t;
 DEFINE_XEN_GUEST_HANDLE(xen_domctl_settimeoffset_t);
 
-#define XEN_DOMCTL_set_tsc_native    57
-typedef struct xen_domctl_set_tsc_native {
-    uint32_t is_native; /* IN: 0: TSC is emulated; 1: TSC is host TSC */
-} xen_domctl_set_tsc_native_t;
-
 #define XEN_DOMCTL_gethvmcontext     33
 #define XEN_DOMCTL_sethvmcontext     34
 typedef struct xen_domctl_hvmcontext {
@@ -656,6 +651,22 @@ typedef struct xen_domctl_disable_migrate {
 } xen_domctl_disable_migrate_t;
 
 
+#define XEN_DOMCTL_gettscinfo    59
+#define XEN_DOMCTL_settscinfo    60
+struct xen_guest_tsc_info {
+    uint32_t tsc_mode;
+    uint32_t gtsc_khz;
+    uint32_t incarnation;
+    uint32_t pad;
+    uint64_t elapsed_nsec;
+};
+typedef struct xen_guest_tsc_info xen_guest_tsc_info_t;
+DEFINE_XEN_GUEST_HANDLE(xen_guest_tsc_info_t);
+typedef struct xen_domctl_tsc_info {
+    XEN_GUEST_HANDLE_64(xen_guest_tsc_info_t) out_info; /* OUT */
+    xen_guest_tsc_info_t info; /* IN */
+} xen_domctl_tsc_info_t;
+
 #define XEN_DOMCTL_gdbsx_guestmemio     1000 /* guest mem io */
 struct xen_domctl_gdbsx_memio {
     uint64_aligned_t pgd3val;/* optional: init_mm.pgd[3] value */
@@ -705,8 +716,8 @@ struct xen_domctl {
         struct xen_domctl_hypercall_init    hypercall_init;
         struct xen_domctl_arch_setup        arch_setup;
         struct xen_domctl_settimeoffset     settimeoffset;
-        struct xen_domctl_set_tsc_native    set_tsc_native;
         struct xen_domctl_disable_migrate   disable_migrate;
+        struct xen_domctl_tsc_info          tsc_info;
         struct xen_domctl_real_mode_area    real_mode_area;
         struct xen_domctl_hvmcontext        hvmcontext;
         struct xen_domctl_hvmcontext_partial hvmcontext_partial;