4 files changed, 96 insertions, 2 deletions

diff --git a/arch/ia64/include/asm/xen/interface.h b/arch/ia64/include/asm/xen/interface.h
index fbb519828aa1..09d5f7fd9db1 100644
--- a/arch/ia64/include/asm/xen/interface.h
+++ b/arch/ia64/include/asm/xen/interface.h
@@ -77,6 +77,7 @@ DEFINE_GUEST_HANDLE(int);
 DEFINE_GUEST_HANDLE(long);
 DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
+DEFINE_GUEST_HANDLE(uint32_t);
 
 typedef unsigned long xen_pfn_t;
 DEFINE_GUEST_HANDLE(xen_pfn_t);
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index a1f2db5f1170..cbf0c9d50b92 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -56,6 +56,7 @@ DEFINE_GUEST_HANDLE(int);
 DEFINE_GUEST_HANDLE(long);
 DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
+DEFINE_GUEST_HANDLE(uint32_t);
 #endif
 
 #ifndef HYPERVISOR_VIRT_START
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 312c9e3cb635..fe06bf4ef0e3 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -62,6 +62,15 @@
 #include <asm/reboot.h>
 #include <asm/stackprotector.h>
 #include <asm/hypervisor.h>
+#include <asm/mwait.h>
+
+#ifdef CONFIG_ACPI
+#include <linux/acpi.h>
+#include <asm/acpi.h>
+#include <acpi/pdc_intel.h>
+#include <acpi/processor.h>
+#include <xen/interface/platform.h>
+#endif
 
 #include "xen-ops.h"
 #include "mmu.h"
@@ -200,13 +209,17 @@ static void __init xen_banner(void)
 static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
 static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
 
+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_cpuid(unsigned int *ax, unsigned int *bx,
                       unsigned int *cx, unsigned int *dx)
 {
         unsigned maskebx = ~0;
         unsigned maskecx = ~0;
         unsigned maskedx = ~0;
-
+        unsigned setecx = 0;
         /*
          * Mask out inconvenient features, to try and disable as many
          * unsupported kernel subsystems as possible.
@@ -214,9 +227,18 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
         switch (*ax) {
         case 1:
                 maskecx = cpuid_leaf1_ecx_mask;
+                setecx = cpuid_leaf1_ecx_set_mask;
                 maskedx = cpuid_leaf1_edx_mask;
                 break;
 
+        case CPUID_MWAIT_LEAF:
+                /* Synthesize the values.. */
+                *ax = 0;
+                *bx = 0;
+                *cx = cpuid_leaf5_ecx_val;
+                *dx = cpuid_leaf5_edx_val;
+                return;
+
         case 0xb:
                 /* Suppress extended topology stuff */
                 maskebx = 0;
@@ -232,9 +254,75 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 
         *bx &= maskebx;
         *cx &= maskecx;
+        *cx |= setecx;
         *dx &= maskedx;
+
 }
 
+static bool __init xen_check_mwait(void)
+{
+#ifdef CONFIG_ACPI
+        struct xen_platform_op op = {
+                .cmd                    = XENPF_set_processor_pminfo,
+                .u.set_pminfo.id        = -1,
+                .u.set_pminfo.type      = XEN_PM_PDC,
+        };
+        uint32_t buf[3];
+        unsigned int ax, bx, cx, dx;
+        unsigned int mwait_mask;
+
+        /* We need to determine whether it is OK to expose the MWAIT
+         * capability to the kernel to harvest deeper than C3 states from ACPI
+         * _CST using the processor_harvest_xen.c module. For this to work, we
+         * need to gather the MWAIT_LEAF values (which the cstate.c code
+         * checks against). The hypervisor won't expose the MWAIT flag because
+         * it would break backwards compatibility; so we will find out directly
+         * from the hardware and hypercall.
+         */
+        if (!xen_initial_domain())
+                return false;
+
+        ax = 1;
+        cx = 0;
+
+        native_cpuid(&ax, &bx, &cx, &dx);
+
+        mwait_mask = (1 << (X86_FEATURE_EST % 32)) |
+                     (1 << (X86_FEATURE_MWAIT % 32));
+
+        if ((cx & mwait_mask) != mwait_mask)
+                return false;
+
+        /* We need to emulate the MWAIT_LEAF and for that we need both
+         * ecx and edx. The hypercall provides only partial information.
+         */
+
+        ax = CPUID_MWAIT_LEAF;
+        bx = 0;
+        cx = 0;
+        dx = 0;
+
+        native_cpuid(&ax, &bx, &cx, &dx);
+
+        /* Ask the Hypervisor whether to clear ACPI_PDC_C_C2C3_FFH. If so,
+         * don't expose MWAIT_LEAF and let ACPI pick the IOPORT version of C3.
+         */
+        buf[0] = ACPI_PDC_REVISION_ID;
+        buf[1] = 1;
+        buf[2] = (ACPI_PDC_C_CAPABILITY_SMP | ACPI_PDC_EST_CAPABILITY_SWSMP);
+
+        set_xen_guest_handle(op.u.set_pminfo.pdc, buf);
+
+        if ((HYPERVISOR_dom0_op(&op) == 0) &&
+            (buf[2] & (ACPI_PDC_C_C1_FFH | ACPI_PDC_C_C2C3_FFH))) {
+                cpuid_leaf5_ecx_val = cx;
+                cpuid_leaf5_edx_val = dx;
+        }
+        return true;
+#else
+        return false;
+#endif
+}
 static void __init xen_init_cpuid_mask(void)
 {
         unsigned int ax, bx, cx, dx;
@@ -261,6 +349,9 @@ static void __init xen_init_cpuid_mask(void)
         /* Xen will set CR4.OSXSAVE if supported and not disabled by force */
         if ((cx & xsave_mask) != xsave_mask)
                 cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
+
+        if (xen_check_mwait())
+                cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
 }
 
 static void xen_set_debugreg(int reg, unsigned long val)
diff --git a/include/xen/interface/platform.h b/include/xen/interface/platform.h
index c1684680431b..861b359b44aa 100644
--- a/include/xen/interface/platform.h
+++ b/include/xen/interface/platform.h
@@ -200,7 +200,7 @@ DEFINE_GUEST_HANDLE_STRUCT(xenpf_getidletime_t);
 #define XEN_PM_CX   0
 #define XEN_PM_PX   1
 #define XEN_PM_TX   2
-
+#define XEN_PM_PDC  3
 /* Px sub info type */
 #define XEN_PX_PCT   1
 #define XEN_PX_PSS   2
@@ -293,6 +293,7 @@ struct xenpf_set_processor_pminfo {
         union {
                 struct xen_processor_power          power;/* Cx: _CST/_CSD */
                 struct xen_processor_performance    perf; /* Px: _PPC/_PCT/_PSS/_PSD */
+                GUEST_HANDLE(uint32_t)              pdc;
         };
 };
 DEFINE_GUEST_HANDLE_STRUCT(xenpf_set_processor_pminfo);