Merge tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Marcelo Tosatti:
 "Considerable KVM/PPC work, x86 kvmclock vsyscall support,
  IA32_TSC_ADJUST MSR emulation, amongst others."

Fix up trivial conflict in kernel/sched/core.c due to cross-cpu
migration notifier added next to rq migration call-back.

* tag 'kvm-3.8-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (156 commits)
  KVM: emulator: fix real mode segment checks in address linearization
  VMX: remove unneeded enable_unrestricted_guest check
  KVM: VMX: fix DPL during entry to protected mode
  x86/kexec: crash_vmclear_local_vmcss needs __rcu
  kvm: Fix irqfd resampler list walk
  KVM: VMX: provide the vmclear function and a bitmap to support VMCLEAR in kdump
  x86/kexec: VMCLEAR VMCSs loaded on all cpus if necessary
  KVM: MMU: optimize for set_spte
  KVM: PPC: booke: Get/set guest EPCR register using ONE_REG interface
  KVM: PPC: bookehv: Add EPCR support in mtspr/mfspr emulation
  KVM: PPC: bookehv: Add guest computation mode for irq delivery
  KVM: PPC: Make EPCR a valid field for booke64 and bookehv
  KVM: PPC: booke: Extend MAS2 EPN mask for 64-bit
  KVM: PPC: e500: Mask MAS2 EPN high 32-bits in 32/64 tlbwe emulation
  KVM: PPC: Mask ea's high 32-bits in 32/64 instr emulation
  KVM: PPC: e500: Add emulation helper for getting instruction ea
  KVM: PPC: bookehv64: Add support for interrupt handling
  KVM: PPC: bookehv: Remove GET_VCPU macro from exception handler
  KVM: PPC: booke: Fix get_tb() compile error on 64-bit
  KVM: PPC: e500: Silence bogus GCC warning in tlb code
  ...

10 files changed, 105 insertions, 6 deletions

diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h
index 0bdbbb3b9ce7..16a57f4ed64d 100644
--- a/arch/x86/include/asm/clocksource.h
+++ b/arch/x86/include/asm/clocksource.h
@@ -8,6 +8,7 @@
 #define VCLOCK_NONE 0  /* No vDSO clock available.      */
 #define VCLOCK_TSC  1  /* vDSO should use vread_tsc.    */
 #define VCLOCK_HPET 2  /* vDSO should use vread_hpet.   */
+#define VCLOCK_PVCLOCK 3 /* vDSO should use vread_pvclock. */
 
 struct arch_clocksource_data {
         int vclock_mode;
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index da40b1e2228e..2d9075e863a0 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -202,6 +202,7 @@
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE    (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
+#define X86_FEATURE_TSC_ADJUST  (9*32+ 1) /* TSC adjustment MSR 0x3b */
 #define X86_FEATURE_BMI1        (9*32+ 3) /* 1st group bit manipulation extensions */
 #define X86_FEATURE_HLE         (9*32+ 4) /* Hardware Lock Elision */
 #define X86_FEATURE_AVX2        (9*32+ 5) /* AVX2 instructions */
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 4da3c0c4c974..a09c28571064 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -19,6 +19,7 @@
 #include <asm/acpi.h>
 #include <asm/apicdef.h>
 #include <asm/page.h>
+#include <asm/pvclock.h>
 #ifdef CONFIG_X86_32
 #include <linux/threads.h>
 #include <asm/kmap_types.h>
@@ -81,6 +82,10 @@ enum fixed_addresses {
         VVAR_PAGE,
         VSYSCALL_HPET,
 #endif
+#ifdef CONFIG_PARAVIRT_CLOCK
+        PVCLOCK_FIXMAP_BEGIN,
+        PVCLOCK_FIXMAP_END = PVCLOCK_FIXMAP_BEGIN+PVCLOCK_VSYSCALL_NR_PAGES-1,
+#endif
         FIX_DBGP_BASE,
         FIX_EARLYCON_MEM_BASE,
 #ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 317ff1703d0b..6080d2694bad 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -163,6 +163,9 @@ struct kimage_arch {
 };
 #endif
 
+typedef void crash_vmclear_fn(void);
+extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_KEXEC_H */
diff --git a/arch/x86/include/asm/kvm_guest.h b/arch/x86/include/asm/kvm_guest.h
new file mode 100644
index 000000000000..a92b1763c419
--- /dev/null
+++ b/arch/x86/include/asm/kvm_guest.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_X86_KVM_GUEST_H
+#define _ASM_X86_KVM_GUEST_H
+
+int kvm_setup_vsyscall_timeinfo(void);
+
+#endif /* _ASM_X86_KVM_GUEST_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b2e11f452435..dc87b65e9c3a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -22,6 +22,8 @@
 #include <linux/kvm_para.h>
 #include <linux/kvm_types.h>
 #include <linux/perf_event.h>
+#include <linux/pvclock_gtod.h>
+#include <linux/clocksource.h>
 
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
@@ -442,6 +444,7 @@ struct kvm_vcpu_arch {
         s8 virtual_tsc_shift;
         u32 virtual_tsc_mult;
         u32 virtual_tsc_khz;
+        s64 ia32_tsc_adjust_msr;
 
         atomic_t nmi_queued;  /* unprocessed asynchronous NMIs */
         unsigned nmi_pending; /* NMI queued after currently running handler */
@@ -559,6 +562,12 @@ struct kvm_arch {
         u64 cur_tsc_write;
         u64 cur_tsc_offset;
         u8  cur_tsc_generation;
+        int nr_vcpus_matched_tsc;
+
+        spinlock_t pvclock_gtod_sync_lock;
+        bool use_master_clock;
+        u64 master_kernel_ns;
+        cycle_t master_cycle_now;
 
         struct kvm_xen_hvm_config xen_hvm_config;
 
@@ -612,6 +621,12 @@ struct kvm_vcpu_stat {
 
 struct x86_instruction_info;
 
+struct msr_data {
+        bool host_initiated;
+        u32 index;
+        u64 data;
+};
+
 struct kvm_x86_ops {
         int (*cpu_has_kvm_support)(void);          /* __init */
         int (*disabled_by_bios)(void);             /* __init */
@@ -634,7 +649,7 @@ struct kvm_x86_ops {
 
         void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu);
         int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
-        int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
+        int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
         u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
         void (*get_segment)(struct kvm_vcpu *vcpu,
                             struct kvm_segment *var, int seg);
@@ -697,10 +712,11 @@ struct kvm_x86_ops {
         bool (*has_wbinvd_exit)(void);
 
         void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale);
+        u64 (*read_tsc_offset)(struct kvm_vcpu *vcpu);
         void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
         u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc);
-        u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu);
+        u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc);
 
         void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
 
@@ -785,7 +801,7 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu,
 
 void kvm_enable_efer_bits(u64);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
-int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
+int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
 struct x86_emulate_ctxt;
 
@@ -812,7 +828,7 @@ void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
 int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr);
 
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
-int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr);
 
 unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu);
 void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e400cdb2dd65..6e930b218724 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -236,6 +236,7 @@
 #define MSR_IA32_EBL_CR_POWERON         0x0000002a
 #define MSR_EBC_FREQUENCY_ID            0x0000002c
 #define MSR_IA32_FEATURE_CONTROL        0x0000003a
+#define MSR_IA32_TSC_ADJUST             0x0000003b
 
 #define FEATURE_CONTROL_LOCKED                          (1<<0)
 #define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX        (1<<1)
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index c59cc97fe6c1..109a9dd5d454 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -6,6 +6,7 @@
 
 /* some helper functions for xen and kvm pv clock sources */
 cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
+u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src);
 void pvclock_set_flags(u8 flags);
 unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
 void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
@@ -56,4 +57,50 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
         return product;
 }
 
+static __always_inline
+u64 pvclock_get_nsec_offset(const struct pvclock_vcpu_time_info *src)
+{
+        u64 delta = __native_read_tsc() - src->tsc_timestamp;
+        return pvclock_scale_delta(delta, src->tsc_to_system_mul,
+                                   src->tsc_shift);
+}
+
+static __always_inline
+unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src,
+                               cycle_t *cycles, u8 *flags)
+{
+        unsigned version;
+        cycle_t ret, offset;
+        u8 ret_flags;
+
+        version = src->version;
+        /* Note: emulated platforms which do not advertise SSE2 support
+         * result in kvmclock not using the necessary RDTSC barriers.
+         * Without barriers, it is possible that RDTSC instruction reads from
+         * the time stamp counter outside rdtsc_barrier protected section
+         * below, resulting in violation of monotonicity.
+         */
+        rdtsc_barrier();
+        offset = pvclock_get_nsec_offset(src);
+        ret = src->system_time + offset;
+        ret_flags = src->flags;
+        rdtsc_barrier();
+
+        *cycles = ret;
+        *flags = ret_flags;
+        return version;
+}
+
+struct pvclock_vsyscall_time_info {
+        struct pvclock_vcpu_time_info pvti;
+        u32 migrate_count;
+} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+
+#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
+#define PVCLOCK_VSYSCALL_NR_PAGES (((NR_CPUS-1)/(PAGE_SIZE/PVTI_SIZE))+1)
+
+int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i,
+                                 int size);
+struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu);
+
 #endif /* _ASM_X86_PVCLOCK_H */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 36ec21c36d68..c2d56b34830d 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -445,8 +445,7 @@ enum vmcs_field {
 #define VMX_EPTP_WB_BIT                         (1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT                    (1ull << 16)
 #define VMX_EPT_1GB_PAGE_BIT                    (1ull << 17)
-#define VMX_EPT_AD_BIT                                  (1ull << 21)
-#define VMX_EPT_EXTENT_INDIVIDUAL_BIT           (1ull << 24)
+#define VMX_EPT_AD_BIT                              (1ull << 21)
 #define VMX_EPT_EXTENT_CONTEXT_BIT              (1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT               (1ull << 26)
 
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index eaea1d31f753..80f80955cfd8 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -33,6 +33,26 @@ extern void map_vsyscall(void);
  */
 extern bool emulate_vsyscall(struct pt_regs *regs, unsigned long address);
 
+#ifdef CONFIG_X86_64
+
+#define VGETCPU_CPU_MASK 0xfff
+
+static inline unsigned int __getcpu(void)
+{
+        unsigned int p;
+
+        if (VVAR(vgetcpu_mode) == VGETCPU_RDTSCP) {
+                /* Load per CPU data from RDTSCP */
+                native_read_tscp(&p);
+        } else {
+                /* Load per CPU data from GDT */
+                asm("lsl %1,%0" : "=r" (p) : "r" (__PER_CPU_SEG));
+        }
+
+        return p;
+}
+#endif /* CONFIG_X86_64 */
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_VSYSCALL_H */