Merge branch 'kvm-updates/2.6.29' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm

* 'kvm-updates/2.6.29' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (140 commits)
  KVM: MMU: handle large host sptes on invlpg/resync
  KVM: Add locking to virtual i8259 interrupt controller
  KVM: MMU: Don't treat a global pte as such if cr4.pge is cleared
  MAINTAINERS: Maintainership changes for kvm/ia64
  KVM: ia64: Fix kvm_arch_vcpu_ioctl_[gs]et_regs()
  KVM: x86: Rework user space NMI injection as KVM_CAP_USER_NMI
  KVM: VMX: Fix pending NMI-vs.-IRQ race for user space irqchip
  KVM: fix handling of ACK from shared guest IRQ
  KVM: MMU: check for present pdptr shadow page in walk_shadow
  KVM: Consolidate userspace memory capability reporting into common code
  KVM: Advertise the bug in memory region destruction as fixed
  KVM: use cpumask_var_t for cpus_hardware_enabled
  KVM: use modern cpumask primitives, no cpumask_t on stack
  KVM: Extract core of kvm_flush_remote_tlbs/kvm_reload_remote_mmus
  KVM: set owner of cpu and vm file operations
  anon_inodes: use fops->owner for module refcount
  x86: KVM guest: kvm_get_tsc_khz: return khz, not lpj
  KVM: MMU: prepopulate the shadow on invlpg
  KVM: MMU: skip global pgtables on sync due to cr3 switch
  KVM: MMU: collapse remote TLB flushes on root sync
  ...

6 files changed, 90 insertions, 34 deletions

diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 4e8d77f01eeb..b59ddcc88cd8 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -14,14 +14,6 @@
 #include <asm/pat.h>
 #include "mtrr.h"
 
-struct mtrr_state {
-        struct mtrr_var_range var_ranges[MAX_VAR_RANGES];
-        mtrr_type fixed_ranges[NUM_FIXED_RANGES];
-        unsigned char enabled;
-        unsigned char have_fixed;
-        mtrr_type def_type;
-};
-
 struct fixed_range_block {
         int base_msr; /* start address of an MTRR block */
         int ranges;   /* number of MTRRs in this block  */
@@ -35,10 +27,12 @@ static struct fixed_range_block fixed_range_blocks[] = {
 };
 
 static unsigned long smp_changes_mask;
-static struct mtrr_state mtrr_state = {};
 static int mtrr_state_set;
 u64 mtrr_tom2;
 
+struct mtrr_state_type mtrr_state = {};
+EXPORT_SYMBOL_GPL(mtrr_state);
+
 #undef MODULE_PARAM_PREFIX
 #define MODULE_PARAM_PREFIX "mtrr."
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 1159e269e596..d6ec7ec30274 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -49,7 +49,7 @@
 
 u32 num_var_ranges = 0;
 
-unsigned int mtrr_usage_table[MAX_VAR_RANGES];
+unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
 static DEFINE_MUTEX(mtrr_mutex);
 
 u64 size_or_mask, size_and_mask;
@@ -574,7 +574,7 @@ struct mtrr_value {
         unsigned long   lsize;
 };
 
-static struct mtrr_value mtrr_state[MAX_VAR_RANGES];
+static struct mtrr_value mtrr_state[MTRR_MAX_VAR_RANGES];
 
 static int mtrr_save(struct sys_device * sysdev, pm_message_t state)
 {
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 2dc4ec656b23..ffd60409cc6d 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -8,11 +8,6 @@
 #define MTRRcap_MSR     0x0fe
 #define MTRRdefType_MSR 0x2ff
 
-#define MTRRphysBase_MSR(reg) (0x200 + 2 * (reg))
-#define MTRRphysMask_MSR(reg) (0x200 + 2 * (reg) + 1)
-
-#define NUM_FIXED_RANGES 88
-#define MAX_VAR_RANGES 256
 #define MTRRfix64K_00000_MSR 0x250
 #define MTRRfix16K_80000_MSR 0x258
 #define MTRRfix16K_A0000_MSR 0x259
@@ -29,11 +24,7 @@
 #define MTRR_CHANGE_MASK_VARIABLE  0x02
 #define MTRR_CHANGE_MASK_DEFTYPE   0x04
 
-/* In the Intel processor's MTRR interface, the MTRR type is always held in
-   an 8 bit field: */
-typedef u8 mtrr_type;
-
-extern unsigned int mtrr_usage_table[MAX_VAR_RANGES];
+extern unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES];
 
 struct mtrr_ops {
         u32     vendor;
@@ -70,13 +61,6 @@ struct set_mtrr_context {
         u32 ccr3;
 };
 
-struct mtrr_var_range {
-        u32 base_lo;
-        u32 base_hi;
-        u32 mask_lo;
-        u32 mask_hi;
-};
-
 void set_mtrr_done(struct set_mtrr_context *ctxt);
 void set_mtrr_cache_disable(struct set_mtrr_context *ctxt);
 void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index d84a852e4cd7..c689d19e35ab 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -26,6 +26,7 @@
 #include <linux/kdebug.h>
 #include <asm/smp.h>
 #include <asm/reboot.h>
+#include <asm/virtext.h>
 
 #include <mach_ipi.h>
 
@@ -49,6 +50,15 @@ static void kdump_nmi_callback(int cpu, struct die_args *args)
 #endif
         crash_save_cpu(regs, cpu);
 
+        /* Disable VMX or SVM if needed.
+         *
+         * We need to disable virtualization on all CPUs.
+         * Having VMX or SVM enabled on any CPU may break rebooting
+         * after the kdump kernel has finished its task.
+         */
+        cpu_emergency_vmxoff();
+        cpu_emergency_svm_disable();
+
         disable_local_APIC();
 }
 
@@ -80,6 +90,14 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
         local_irq_disable();
 
         kdump_nmi_shootdown_cpus();
+
+        /* Booting kdump kernel with VMX or SVM enabled won't work,
+         * because (among other limitations) we can't disable paging
+         * with the virt flags.
+         */
+        cpu_emergency_vmxoff();
+        cpu_emergency_svm_disable();
+
         lapic_shutdown();
 #if defined(CONFIG_X86_IO_APIC)
         disable_IO_APIC();
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index e169ae9b6a62..652fce6d2cce 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -89,17 +89,17 @@ static cycle_t kvm_clock_read(void)
  */
 static unsigned long kvm_get_tsc_khz(void)
 {
-        return preset_lpj;
+        struct pvclock_vcpu_time_info *src;
+        src = &per_cpu(hv_clock, 0);
+        return pvclock_tsc_khz(src);
 }
 
 static void kvm_get_preset_lpj(void)
 {
-        struct pvclock_vcpu_time_info *src;
         unsigned long khz;
         u64 lpj;
 
-        src = &per_cpu(hv_clock, 0);
-        khz = pvclock_tsc_khz(src);
+        khz = kvm_get_tsc_khz();
 
         lpj = ((u64)khz * 1000);
         do_div(lpj, HZ);
@@ -194,5 +194,7 @@ void __init kvmclock_init(void)
 #endif
                 kvm_get_preset_lpj();
                 clocksource_register(&kvm_clock);
+                pv_info.paravirt_enabled = 1;
+                pv_info.name = "KVM";
         }
 }
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 61f718df6eec..72e0e4e712d6 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -12,6 +12,7 @@
 #include <asm/proto.h>
 #include <asm/reboot_fixups.h>
 #include <asm/reboot.h>
+#include <asm/virtext.h>
 
 #ifdef CONFIG_X86_32
 # include <linux/dmi.h>
@@ -39,6 +40,12 @@ int reboot_force;
 static int reboot_cpu = -1;
 #endif
 
+/* This is set if we need to go through the 'emergency' path.
+ * When machine_emergency_restart() is called, we may be on
+ * an inconsistent state and won't be able to do a clean cleanup
+ */
+static int reboot_emergency;
+
 /* This is set by the PCI code if either type 1 or type 2 PCI is detected */
 bool port_cf9_safe = false;
 
@@ -368,6 +375,48 @@ static inline void kb_wait(void)
         }
 }
 
+static void vmxoff_nmi(int cpu, struct die_args *args)
+{
+        cpu_emergency_vmxoff();
+}
+
+/* Use NMIs as IPIs to tell all CPUs to disable virtualization
+ */
+static void emergency_vmx_disable_all(void)
+{
+        /* Just make sure we won't change CPUs while doing this */
+        local_irq_disable();
+
+        /* We need to disable VMX on all CPUs before rebooting, otherwise
+         * we risk hanging up the machine, because the CPU ignore INIT
+         * signals when VMX is enabled.
+         *
+         * We can't take any locks and we may be on an inconsistent
+         * state, so we use NMIs as IPIs to tell the other CPUs to disable
+         * VMX and halt.
+         *
+         * For safety, we will avoid running the nmi_shootdown_cpus()
+         * stuff unnecessarily, but we don't have a way to check
+         * if other CPUs have VMX enabled. So we will call it only if the
+         * CPU we are running on has VMX enabled.
+         *
+         * We will miss cases where VMX is not enabled on all CPUs. This
+         * shouldn't do much harm because KVM always enable VMX on all
+         * CPUs anyway. But we can miss it on the small window where KVM
+         * is still enabling VMX.
+         */
+        if (cpu_has_vmx() && cpu_vmx_enabled()) {
+                /* Disable VMX on this CPU.
+                 */
+                cpu_vmxoff();
+
+                /* Halt and disable VMX on the other CPUs */
+                nmi_shootdown_cpus(vmxoff_nmi);
+
+        }
+}
+
+
 void __attribute__((weak)) mach_reboot_fixups(void)
 {
 }
@@ -376,6 +425,9 @@ static void native_machine_emergency_restart(void)
 {
         int i;
 
+        if (reboot_emergency)
+                emergency_vmx_disable_all();
+
         /* Tell the BIOS if we want cold or warm reboot */
         *((unsigned short *)__va(0x472)) = reboot_mode;
 
@@ -482,13 +534,19 @@ void native_machine_shutdown(void)
 #endif
 }
 
+static void __machine_emergency_restart(int emergency)
+{
+        reboot_emergency = emergency;
+        machine_ops.emergency_restart();
+}
+
 static void native_machine_restart(char *__unused)
 {
         printk("machine restart\n");
 
         if (!reboot_force)
                 machine_shutdown();
-        machine_emergency_restart();
+        __machine_emergency_restart(0);
 }
 
 static void native_machine_halt(void)
@@ -532,7 +590,7 @@ void machine_shutdown(void)
 
 void machine_emergency_restart(void)
 {
-        machine_ops.emergency_restart();
+        __machine_emergency_restart(1);
 }
 
 void machine_restart(char *cmd)