Merge branch 'kvm-updates-2.6.26' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm

* 'kvm-updates-2.6.26' of git://git.kernel.org/pub/scm/linux/kernel/git/avi/kvm: (147 commits)
  KVM: kill file->f_count abuse in kvm
  KVM: MMU: kvm_pv_mmu_op should not take mmap_sem
  KVM: SVM: remove selective CR0 comment
  KVM: SVM: remove now obsolete FIXME comment
  KVM: SVM: disable CR8 intercept when tpr is not masking interrupts
  KVM: SVM: sync V_TPR with LAPIC.TPR if CR8 write intercept is disabled
  KVM: export kvm_lapic_set_tpr() to modules
  KVM: SVM: sync TPR value to V_TPR field in the VMCB
  KVM: ppc: PowerPC 440 KVM implementation
  KVM: Add MAINTAINERS entry for PowerPC KVM
  KVM: ppc: Add DCR access information to struct kvm_run
  ppc: Export tlb_44x_hwater for KVM
  KVM: Rename debugfs_dir to kvm_debugfs_dir
  KVM: x86 emulator: fix lea to really get the effective address
  KVM: x86 emulator: fix smsw and lmsw with a memory operand
  KVM: x86 emulator: initialize src.val and dst.val for register operands
  KVM: SVM: force a new asid when initializing the vmcb
  KVM: fix kvm_vcpu_kick vs __vcpu_run race
  KVM: add ioctls to save/store mpstate
  KVM: Rename VCPU_MP_STATE_* to KVM_MP_STATE_*
  ...

5 files changed, 188 insertions, 16 deletions

diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index c1ec04fd000..a281afeddfb 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -8,11 +8,18 @@
  */
 
 #include <asm/types.h>
+#include <linux/compiler.h>
 #include <linux/ioctl.h>
 #include <asm/kvm.h>
 
 #define KVM_API_VERSION 12
 
+/* for KVM_TRACE_ENABLE */
+struct kvm_user_trace_setup {
+	__u32 buf_size; /* sub_buffer size of each per-cpu */
+	__u32 buf_nr; /* the number of sub_buffers of each per-cpu */
+};
+
 /* for KVM_CREATE_MEMORY_REGION */
 struct kvm_memory_region {
 	__u32 slot;
@@ -73,6 +80,9 @@ struct kvm_irqchip {
 #define KVM_EXIT_INTR             10
 #define KVM_EXIT_SET_TPR          11
 #define KVM_EXIT_TPR_ACCESS       12
+#define KVM_EXIT_S390_SIEIC       13
+#define KVM_EXIT_S390_RESET       14
+#define KVM_EXIT_DCR              15
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {
@@ -137,6 +147,27 @@ struct kvm_run {
 			__u32 is_write;
 			__u32 pad;
 		} tpr_access;
+		/* KVM_EXIT_S390_SIEIC */
+		struct {
+			__u8 icptcode;
+			__u64 mask; /* psw upper half */
+			__u64 addr; /* psw lower half */
+			__u16 ipa;
+			__u32 ipb;
+		} s390_sieic;
+		/* KVM_EXIT_S390_RESET */
+#define KVM_S390_RESET_POR       1
+#define KVM_S390_RESET_CLEAR     2
+#define KVM_S390_RESET_SUBSYSTEM 4
+#define KVM_S390_RESET_CPU_INIT  8
+#define KVM_S390_RESET_IPL       16
+		__u64 s390_reset_flags;
+		/* KVM_EXIT_DCR */
+		struct {
+			__u32 dcrn;
+			__u32 data;
+			__u8  is_write;
+		} dcr;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -204,6 +235,74 @@ struct kvm_vapic_addr {
 	__u64 vapic_addr;
 };
 
+/* for KVM_SET_MPSTATE */
+
+#define KVM_MP_STATE_RUNNABLE          0
+#define KVM_MP_STATE_UNINITIALIZED     1
+#define KVM_MP_STATE_INIT_RECEIVED     2
+#define KVM_MP_STATE_HALTED            3
+#define KVM_MP_STATE_SIPI_RECEIVED     4
+
+struct kvm_mp_state {
+	__u32 mp_state;
+};
+
+struct kvm_s390_psw {
+	__u64 mask;
+	__u64 addr;
+};
+
+/* valid values for type in kvm_s390_interrupt */
+#define KVM_S390_SIGP_STOP		0xfffe0000u
+#define KVM_S390_PROGRAM_INT		0xfffe0001u
+#define KVM_S390_SIGP_SET_PREFIX	0xfffe0002u
+#define KVM_S390_RESTART		0xfffe0003u
+#define KVM_S390_INT_VIRTIO		0xffff2603u
+#define KVM_S390_INT_SERVICE		0xffff2401u
+#define KVM_S390_INT_EMERGENCY		0xffff1201u
+
+struct kvm_s390_interrupt {
+	__u32 type;
+	__u32 parm;
+	__u64 parm64;
+};
+
+#define KVM_TRC_SHIFT           16
+/*
+ * kvm trace categories
+ */
+#define KVM_TRC_ENTRYEXIT       (1 << KVM_TRC_SHIFT)
+#define KVM_TRC_HANDLER         (1 << (KVM_TRC_SHIFT + 1)) /* only 12 bits */
+
+/*
+ * kvm trace action
+ */
+#define KVM_TRC_VMENTRY         (KVM_TRC_ENTRYEXIT + 0x01)
+#define KVM_TRC_VMEXIT          (KVM_TRC_ENTRYEXIT + 0x02)
+#define KVM_TRC_PAGE_FAULT      (KVM_TRC_HANDLER + 0x01)
+
+#define KVM_TRC_HEAD_SIZE       12
+#define KVM_TRC_CYCLE_SIZE      8
+#define KVM_TRC_EXTRA_MAX       7
+
+/* This structure represents a single trace buffer record. */
+struct kvm_trace_rec {
+	__u32 event:28;
+	__u32 extra_u32:3;
+	__u32 cycle_in:1;
+	__u32 pid;
+	__u32 vcpu_id;
+	union {
+		struct {
+			__u32 cycle_lo, cycle_hi;
+			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
+		} cycle;
+		struct {
+			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
+		} nocycle;
+	} u;
+};
+
 #define KVMIO 0xAE
 
 /*
@@ -212,6 +311,8 @@ struct kvm_vapic_addr {
 #define KVM_GET_API_VERSION       _IO(KVMIO,   0x00)
 #define KVM_CREATE_VM             _IO(KVMIO,   0x01) /* returns a VM fd */
 #define KVM_GET_MSR_INDEX_LIST    _IOWR(KVMIO, 0x02, struct kvm_msr_list)
+
+#define KVM_S390_ENABLE_SIE       _IO(KVMIO,   0x06)
 /*
  * Check if a kvm extension is available.  Argument is extension number,
  * return is 1 (yes) or 0 (no, sorry).
@@ -222,7 +323,12 @@ struct kvm_vapic_addr {
  */
 #define KVM_GET_VCPU_MMAP_SIZE    _IO(KVMIO,   0x04) /* in bytes */
 #define KVM_GET_SUPPORTED_CPUID   _IOWR(KVMIO, 0x05, struct kvm_cpuid2)
-
+/*
+ * ioctls for kvm trace
+ */
+#define KVM_TRACE_ENABLE          _IOW(KVMIO, 0x06, struct kvm_user_trace_setup)
+#define KVM_TRACE_PAUSE           _IO(KVMIO,  0x07)
+#define KVM_TRACE_DISABLE         _IO(KVMIO,  0x08)
 /*
  * Extension capability list.
  */
@@ -233,6 +339,13 @@ struct kvm_vapic_addr {
 #define KVM_CAP_SET_TSS_ADDR 4
 #define KVM_CAP_VAPIC 6
 #define KVM_CAP_EXT_CPUID 7
+#define KVM_CAP_CLOCKSOURCE 8
+#define KVM_CAP_NR_VCPUS 9       /* returns max vcpus per vm */
+#define KVM_CAP_NR_MEMSLOTS 10   /* returns max memory slots per vm */
+#define KVM_CAP_PIT 11
+#define KVM_CAP_NOP_IO_DELAY 12
+#define KVM_CAP_PV_MMU 13
+#define KVM_CAP_MP_STATE 14
 
 /*
  * ioctls for VM fds
@@ -255,6 +368,9 @@ struct kvm_vapic_addr {
 #define KVM_IRQ_LINE		  _IOW(KVMIO, 0x61, struct kvm_irq_level)
 #define KVM_GET_IRQCHIP		  _IOWR(KVMIO, 0x62, struct kvm_irqchip)
 #define KVM_SET_IRQCHIP		  _IOR(KVMIO,  0x63, struct kvm_irqchip)
+#define KVM_CREATE_PIT		  _IO(KVMIO,  0x64)
+#define KVM_GET_PIT		  _IOWR(KVMIO, 0x65, struct kvm_pit_state)
+#define KVM_SET_PIT		  _IOR(KVMIO,  0x66, struct kvm_pit_state)
 
 /*
  * ioctls for vcpu fds
@@ -281,5 +397,17 @@ struct kvm_vapic_addr {
 #define KVM_TPR_ACCESS_REPORTING  _IOWR(KVMIO,  0x92, struct kvm_tpr_access_ctl)
 /* Available with KVM_CAP_VAPIC */
 #define KVM_SET_VAPIC_ADDR        _IOW(KVMIO,  0x93, struct kvm_vapic_addr)
+/* valid for virtual machine (for floating interrupt)_and_ vcpu */
+#define KVM_S390_INTERRUPT        _IOW(KVMIO,  0x94, struct kvm_s390_interrupt)
+/* store status for s390 */
+#define KVM_S390_STORE_STATUS_NOADDR    (-1ul)
+#define KVM_S390_STORE_STATUS_PREFIXED  (-2ul)
+#define KVM_S390_STORE_STATUS	  _IOW(KVMIO,  0x95, unsigned long)
+/* initial ipl psw for s390 */
+#define KVM_S390_SET_INITIAL_PSW  _IOW(KVMIO,  0x96, struct kvm_s390_psw)
+/* initial reset for s390 */
+#define KVM_S390_INITIAL_RESET    _IO(KVMIO,  0x97)
+#define KVM_GET_MP_STATE          _IOR(KVMIO,  0x98, struct kvm_mp_state)
+#define KVM_SET_MP_STATE          _IOW(KVMIO,  0x99, struct kvm_mp_state)
 
 #endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 928b0d59e9b..398978972b7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -15,6 +15,7 @@
 #include <linux/sched.h>
 #include <linux/mm.h>
 #include <linux/preempt.h>
+#include <linux/marker.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -24,29 +25,18 @@
 
 #include <asm/kvm_host.h>
 
-#define KVM_MAX_VCPUS 4
-#define KVM_MEMORY_SLOTS 8
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
-
-#define KVM_PIO_PAGE_OFFSET 1
-
 /*
  * vcpu->requests bit members
  */
 #define KVM_REQ_TLB_FLUSH          0
 #define KVM_REQ_MIGRATE_TIMER      1
 #define KVM_REQ_REPORT_TPR_ACCESS  2
+#define KVM_REQ_MMU_RELOAD         3
+#define KVM_REQ_TRIPLE_FAULT       4
 
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
-struct kvm_guest_debug {
-	int enabled;
-	unsigned long bp[4];
-	int singlestep;
-};
-
 /*
  * It would be nice to use something smarter than a linear search, TBD...
  * Thankfully we dont expect many devices to register (famous last words :),
@@ -67,7 +57,9 @@ void kvm_io_bus_register_dev(struct kvm_io_bus *bus,
 
 struct kvm_vcpu {
 	struct kvm *kvm;
+#ifdef CONFIG_PREEMPT_NOTIFIERS
 	struct preempt_notifier preempt_notifier;
+#endif
 	int vcpu_id;
 	struct mutex mutex;
 	int   cpu;
@@ -100,6 +92,10 @@ struct kvm_memory_slot {
 	unsigned long flags;
 	unsigned long *rmap;
 	unsigned long *dirty_bitmap;
+	struct {
+		unsigned long rmap_pde;
+		int write_count;
+	} *lpage_info;
 	unsigned long userspace_addr;
 	int user_alloc;
 };
@@ -114,11 +110,11 @@ struct kvm {
 					KVM_PRIVATE_MEM_SLOTS];
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 	struct list_head vm_list;
-	struct file *filp;
 	struct kvm_io_bus mmio_bus;
 	struct kvm_io_bus pio_bus;
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
+	atomic_t users_count;
 };
 
 /* The guest did something we don't support. */
@@ -145,14 +141,19 @@ int kvm_init(void *opaque, unsigned int vcpu_size,
 		  struct module *module);
 void kvm_exit(void);
 
+void kvm_get_kvm(struct kvm *kvm);
+void kvm_put_kvm(struct kvm *kvm);
+
 #define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
 #define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB)
 static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; }
 struct page *gva_to_page(struct kvm_vcpu *vcpu, gva_t gva);
 
 extern struct page *bad_page;
+extern pfn_t bad_pfn;
 
 int is_error_page(struct page *page);
+int is_error_pfn(pfn_t pfn);
 int kvm_is_error_hva(unsigned long addr);
 int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem,
@@ -166,8 +167,19 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				int user_alloc);
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
+unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
+void kvm_set_page_dirty(struct page *page);
+void kvm_set_page_accessed(struct page *page);
+
+pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
+void kvm_release_pfn_dirty(pfn_t);
+void kvm_release_pfn_clean(pfn_t pfn);
+void kvm_set_pfn_dirty(pfn_t pfn);
+void kvm_set_pfn_accessed(pfn_t pfn);
+void kvm_get_pfn(pfn_t pfn);
+
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 			int len);
 int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
@@ -188,6 +200,7 @@ void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_flush_remote_tlbs(struct kvm *kvm);
+void kvm_reload_remote_mmus(struct kvm *kvm);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -223,6 +236,10 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs);
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 				  struct kvm_sregs *sregs);
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state);
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+				    struct kvm_mp_state *mp_state);
 int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
 				    struct kvm_debug_guest *dbg);
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
@@ -255,6 +272,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm);
 
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v);
+int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 
 static inline void kvm_guest_enter(void)
@@ -296,5 +314,18 @@ struct kvm_stats_debugfs_item {
 	struct dentry *dentry;
 };
 extern struct kvm_stats_debugfs_item debugfs_entries[];
+extern struct dentry *kvm_debugfs_dir;
+
+#ifdef CONFIG_KVM_TRACE
+int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg);
+void kvm_trace_cleanup(void);
+#else
+static inline
+int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg)
+{
+	return -EINVAL;
+}
+#define kvm_trace_cleanup() ((void)0)
+#endif
 
 #endif
diff --git a/include/linux/kvm_para.h b/include/linux/kvm_para.h
index 5497aac0d2f..3ddce03766c 100644
--- a/include/linux/kvm_para.h
+++ b/include/linux/kvm_para.h
@@ -11,8 +11,11 @@
 
 /* Return values for hypercalls */
 #define KVM_ENOSYS		1000
+#define KVM_EFAULT		EFAULT
+#define KVM_E2BIG		E2BIG
 
-#define KVM_HC_VAPIC_POLL_IRQ            1
+#define KVM_HC_VAPIC_POLL_IRQ		1
+#define KVM_HC_MMU_OP			2
 
 /*
  * hypercalls use architecture specific
@@ -20,6 +23,12 @@
 #include <asm/kvm_para.h>
 
 #ifdef __KERNEL__
+#ifdef CONFIG_KVM_GUEST
+void __init kvm_guest_init(void);
+#else
+#define kvm_guest_init() do { } while (0)
+#endif
+
 static inline int kvm_para_has_feature(unsigned int feature)
 {
 	if (kvm_arch_para_features() & (1UL << feature))
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 1c4e46decb2..9b6f395c962 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -38,6 +38,8 @@ typedef unsigned long  hva_t;
 typedef u64            hpa_t;
 typedef unsigned long  hfn_t;
 
+typedef hfn_t pfn_t;
+
 struct kvm_pio_request {
 	unsigned long count;
 	int cur_count;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d0bd97044ab..9a4f3e63e3b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1798,6 +1798,8 @@ extern void mmput(struct mm_struct *);
 extern struct mm_struct *get_task_mm(struct task_struct *task);
 /* Remove the current tasks stale references to the old mm_struct */
 extern void mm_release(struct task_struct *, struct mm_struct *);
+/* Allocate a new mm structure and copy contents from tsk->mm */
+extern struct mm_struct *dup_mm(struct task_struct *tsk);
 
 extern int  copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
 extern void flush_thread(void);