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
  ...

arch/ia64/include/asm/kvm.h

@@ -166,8 +166,6 @@ struct saved_vpd {
 };
 
 struct kvm_regs {
-	char *saved_guest;
-	char *saved_stack;
 	struct saved_vpd vpd;
 	/*Arch-regs*/
 	int mp_state;
@@ -200,6 +198,10 @@ struct kvm_regs {
 	unsigned long fp_psr;       /*used for lazy float register */
 	unsigned long saved_gp;
 	/*for phycial  emulation */
+
+	union context saved_guest;
+
+	unsigned long reserved[64];	/* for future use */
 };
 
 struct kvm_sregs {

arch/ia64/include/asm/kvm_host.h

@@ -23,17 +23,6 @@
 #ifndef __ASM_KVM_HOST_H
 #define __ASM_KVM_HOST_H
 
-
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/kvm.h>
-#include <linux/kvm_para.h>
-#include <linux/kvm_types.h>
-
-#include <asm/pal.h>
-#include <asm/sal.h>
-
-#define KVM_MAX_VCPUS 4
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
@@ -50,70 +39,132 @@
 #define EXIT_REASON_EXTERNAL_INTERRUPT	6
 #define EXIT_REASON_IPI			7
 #define EXIT_REASON_PTC_G		8
+#define EXIT_REASON_DEBUG		20
 
 /*Define vmm address space and vm data space.*/
-#define KVM_VMM_SIZE (16UL<<20)
+#define KVM_VMM_SIZE (__IA64_UL_CONST(16)<<20)
 #define KVM_VMM_SHIFT 24
-#define KVM_VMM_BASE 0xD000000000000000UL
-#define VMM_SIZE (8UL<<20)
+#define KVM_VMM_BASE 0xD000000000000000
+#define VMM_SIZE (__IA64_UL_CONST(8)<<20)
 
 /*
  * Define vm_buffer, used by PAL Services, base address.
- * Note: vmbuffer is in the VMM-BLOCK, the size must be < 8M
+ * Note: vm_buffer is in the VMM-BLOCK, the size must be < 8M
  */
 #define KVM_VM_BUFFER_BASE (KVM_VMM_BASE + VMM_SIZE)
-#define KVM_VM_BUFFER_SIZE (8UL<<20)
+#define KVM_VM_BUFFER_SIZE (__IA64_UL_CONST(8)<<20)
 
-/*Define Virtual machine data layout.*/
-#define KVM_VM_DATA_SHIFT  24
-#define KVM_VM_DATA_SIZE (1UL << KVM_VM_DATA_SHIFT)
-#define KVM_VM_DATA_BASE (KVM_VMM_BASE + KVM_VMM_SIZE)
+/*
+ * kvm guest's data area looks as follow:
+ *
+ *            +----------------------+	-------	KVM_VM_DATA_SIZE
+ *	      |	    vcpu[n]'s data   |	 |     ___________________KVM_STK_OFFSET
+ *     	      |			     |	 |    /			  |
+ *     	      |	       ..........    |	 |   /vcpu's struct&stack |
+ *     	      |	       ..........    |	 |  /---------------------|---- 0
+ *	      |	    vcpu[5]'s data   |	 | /	   vpd		  |
+ *	      |	    vcpu[4]'s data   |	 |/-----------------------|
+ *	      |	    vcpu[3]'s data   |	 /	   vtlb		  |
+ *	      |	    vcpu[2]'s data   |	/|------------------------|
+ *	      |	    vcpu[1]'s data   |/  |	   vhpt		  |
+ *	      |	    vcpu[0]'s data   |____________________________|
+ *            +----------------------+	 |
+ *	      |	   memory dirty log  |	 |
+ *            +----------------------+	 |
+ *	      |	   vm's data struct  |	 |
+ *            +----------------------+	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |			     |	 |
+ *	      |	  vm's p2m table  |	 |
+ *	      |			     |	 |
+ *            |			     |	 |
+ *	      |			     |	 |  |
+ * vm's data->|			     |   |  |
+ *	      +----------------------+ ------- 0
+ * To support large memory, needs to increase the size of p2m.
+ * To support more vcpus, needs to ensure it has enough space to
+ * hold vcpus' data.
+ */
 
+#define KVM_VM_DATA_SHIFT	26
+#define KVM_VM_DATA_SIZE	(__IA64_UL_CONST(1) << KVM_VM_DATA_SHIFT)
+#define KVM_VM_DATA_BASE	(KVM_VMM_BASE + KVM_VM_DATA_SIZE)
 
-#define KVM_P2M_BASE    KVM_VM_DATA_BASE
-#define KVM_P2M_OFS     0
-#define KVM_P2M_SIZE    (8UL << 20)
+#define KVM_P2M_BASE		KVM_VM_DATA_BASE
+#define KVM_P2M_SIZE		(__IA64_UL_CONST(24) << 20)
 
-#define KVM_VHPT_BASE   (KVM_P2M_BASE + KVM_P2M_SIZE)
-#define KVM_VHPT_OFS    KVM_P2M_SIZE
-#define KVM_VHPT_BLOCK_SIZE   (2UL << 20)
-#define VHPT_SHIFT      18
-#define VHPT_SIZE       (1UL << VHPT_SHIFT)
-#define VHPT_NUM_ENTRIES (1<<(VHPT_SHIFT-5))
+#define VHPT_SHIFT		16
+#define VHPT_SIZE		(__IA64_UL_CONST(1) << VHPT_SHIFT)
+#define VHPT_NUM_ENTRIES	(__IA64_UL_CONST(1) << (VHPT_SHIFT-5))
 
-#define KVM_VTLB_BASE   (KVM_VHPT_BASE+KVM_VHPT_BLOCK_SIZE)
-#define KVM_VTLB_OFS    (KVM_VHPT_OFS+KVM_VHPT_BLOCK_SIZE)
-#define KVM_VTLB_BLOCK_SIZE   (1UL<<20)
-#define VTLB_SHIFT      17
-#define VTLB_SIZE       (1UL<<VTLB_SHIFT)
-#define VTLB_NUM_ENTRIES (1<<(VTLB_SHIFT-5))
+#define VTLB_SHIFT		16
+#define VTLB_SIZE		(__IA64_UL_CONST(1) << VTLB_SHIFT)
+#define VTLB_NUM_ENTRIES	(1UL << (VHPT_SHIFT-5))
 
-#define KVM_VPD_BASE   (KVM_VTLB_BASE+KVM_VTLB_BLOCK_SIZE)
-#define KVM_VPD_OFS    (KVM_VTLB_OFS+KVM_VTLB_BLOCK_SIZE)
-#define KVM_VPD_BLOCK_SIZE   (2UL<<20)
-#define VPD_SHIFT       16
-#define VPD_SIZE        (1UL<<VPD_SHIFT)
+#define VPD_SHIFT		16
+#define VPD_SIZE		(__IA64_UL_CONST(1) << VPD_SHIFT)
 
-#define KVM_VCPU_BASE   (KVM_VPD_BASE+KVM_VPD_BLOCK_SIZE)
-#define KVM_VCPU_OFS    (KVM_VPD_OFS+KVM_VPD_BLOCK_SIZE)
-#define KVM_VCPU_BLOCK_SIZE   (2UL<<20)
-#define VCPU_SHIFT 18
-#define VCPU_SIZE (1UL<<VCPU_SHIFT)
-#define MAX_VCPU_NUM KVM_VCPU_BLOCK_SIZE/VCPU_SIZE
+#define VCPU_STRUCT_SHIFT	16
+#define VCPU_STRUCT_SIZE	(__IA64_UL_CONST(1) << VCPU_STRUCT_SHIFT)
 
-#define KVM_VM_BASE     (KVM_VCPU_BASE+KVM_VCPU_BLOCK_SIZE)
-#define KVM_VM_OFS      (KVM_VCPU_OFS+KVM_VCPU_BLOCK_SIZE)
-#define KVM_VM_BLOCK_SIZE     (1UL<<19)
+#define KVM_STK_OFFSET		VCPU_STRUCT_SIZE
 
-#define KVM_MEM_DIRTY_LOG_BASE (KVM_VM_BASE+KVM_VM_BLOCK_SIZE)
-#define KVM_MEM_DIRTY_LOG_OFS  (KVM_VM_OFS+KVM_VM_BLOCK_SIZE)
-#define KVM_MEM_DIRTY_LOG_SIZE (1UL<<19)
+#define KVM_VM_STRUCT_SHIFT	19
+#define KVM_VM_STRUCT_SIZE	(__IA64_UL_CONST(1) << KVM_VM_STRUCT_SHIFT)
 
-/* Get vpd, vhpt, tlb, vcpu, base*/
-#define VPD_ADDR(n) (KVM_VPD_BASE+n*VPD_SIZE)
-#define VHPT_ADDR(n) (KVM_VHPT_BASE+n*VHPT_SIZE)
-#define VTLB_ADDR(n) (KVM_VTLB_BASE+n*VTLB_SIZE)
-#define VCPU_ADDR(n) (KVM_VCPU_BASE+n*VCPU_SIZE)
+#define KVM_MEM_DIRY_LOG_SHIFT	19
+#define KVM_MEM_DIRTY_LOG_SIZE (__IA64_UL_CONST(1) << KVM_MEM_DIRY_LOG_SHIFT)
+
+#ifndef __ASSEMBLY__
+
+/*Define the max vcpus and memory for Guests.*/
+#define KVM_MAX_VCPUS	(KVM_VM_DATA_SIZE - KVM_P2M_SIZE - KVM_VM_STRUCT_SIZE -\
+			KVM_MEM_DIRTY_LOG_SIZE) / sizeof(struct kvm_vcpu_data)
+#define KVM_MAX_MEM_SIZE (KVM_P2M_SIZE >> 3 << PAGE_SHIFT)
+
+#define VMM_LOG_LEN 256
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/kvm.h>
+#include <linux/kvm_para.h>
+#include <linux/kvm_types.h>
+
+#include <asm/pal.h>
+#include <asm/sal.h>
+#include <asm/page.h>
+
+struct kvm_vcpu_data {
+	char vcpu_vhpt[VHPT_SIZE];
+	char vcpu_vtlb[VTLB_SIZE];
+	char vcpu_vpd[VPD_SIZE];
+	char vcpu_struct[VCPU_STRUCT_SIZE];
+};
+
+struct kvm_vm_data {
+	char kvm_p2m[KVM_P2M_SIZE];
+	char kvm_vm_struct[KVM_VM_STRUCT_SIZE];
+	char kvm_mem_dirty_log[KVM_MEM_DIRTY_LOG_SIZE];
+	struct kvm_vcpu_data vcpu_data[KVM_MAX_VCPUS];
+};
+
+#define VCPU_BASE(n)	KVM_VM_DATA_BASE + \
+				offsetof(struct kvm_vm_data, vcpu_data[n])
+#define VM_BASE		KVM_VM_DATA_BASE + \
+				offsetof(struct kvm_vm_data, kvm_vm_struct)
+#define KVM_MEM_DIRTY_LOG_BASE	KVM_VM_DATA_BASE + \
+				offsetof(struct kvm_vm_data, kvm_mem_dirty_log)
+
+#define VHPT_BASE(n) (VCPU_BASE(n) + offsetof(struct kvm_vcpu_data, vcpu_vhpt))
+#define VTLB_BASE(n) (VCPU_BASE(n) + offsetof(struct kvm_vcpu_data, vcpu_vtlb))
+#define VPD_BASE(n)  (VCPU_BASE(n) + offsetof(struct kvm_vcpu_data, vcpu_vpd))
+#define VCPU_STRUCT_BASE(n)	(VCPU_BASE(n) + \
+				offsetof(struct kvm_vcpu_data, vcpu_struct))
 
 /*IO section definitions*/
 #define IOREQ_READ      1
@@ -389,6 +440,7 @@ struct kvm_vcpu_arch {
 
 	unsigned long opcode;
 	unsigned long cause;
+	char log_buf[VMM_LOG_LEN];
 	union context host;
 	union context guest;
 };
@@ -403,14 +455,13 @@ struct kvm_sal_data {
 };
 
 struct kvm_arch {
+	spinlock_t dirty_log_lock;
+
 	unsigned long	vm_base;
 	unsigned long	metaphysical_rr0;
 	unsigned long	metaphysical_rr4;
 	unsigned long	vmm_init_rr;
-	unsigned long	vhpt_base;
-	unsigned long	vtlb_base;
-	unsigned long 	vpd_base;
-	spinlock_t dirty_log_lock;
+
 	struct kvm_ioapic *vioapic;
 	struct kvm_vm_stat stat;
 	struct kvm_sal_data rdv_sal_data;
@@ -512,7 +563,7 @@ struct kvm_pt_regs {
 
 static inline struct kvm_pt_regs *vcpu_regs(struct kvm_vcpu *v)
 {
-	return (struct kvm_pt_regs *) ((unsigned long) v + IA64_STK_OFFSET) - 1;
+	return (struct kvm_pt_regs *) ((unsigned long) v + KVM_STK_OFFSET) - 1;
 }
 
 typedef int kvm_vmm_entry(void);
@@ -531,5 +582,6 @@ int kvm_pal_emul(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run);
 void kvm_sal_emul(struct kvm_vcpu *vcpu);
 
 static inline void kvm_inject_nmi(struct kvm_vcpu *vcpu) {}
+#endif /* __ASSEMBLY__*/
 
 #endif

arch/ia64/kvm/Makefile

@@ -60,7 +60,7 @@ obj-$(CONFIG_KVM) += kvm.o
 
 CFLAGS_vcpu.o += -mfixed-range=f2-f5,f12-f127
 kvm-intel-objs = vmm.o vmm_ivt.o trampoline.o vcpu.o optvfault.o mmio.o \
-	vtlb.o process.o
+	vtlb.o process.o kvm_lib.o
 #Add link memcpy and memset to avoid possible structure assignment error
 kvm-intel-objs += memcpy.o memset.o
 obj-$(CONFIG_KVM_INTEL) += kvm-intel.o

arch/ia64/kvm/asm-offsets.c

@@ -24,19 +24,10 @@
 
 #include <linux/autoconf.h>
 #include <linux/kvm_host.h>
+#include <linux/kbuild.h>
 
 #include "vcpu.h"
 
-#define task_struct kvm_vcpu
-
-#define DEFINE(sym, val) \
-	asm volatile("\n->" #sym " (%0) " #val : : "i" (val))
-
-#define BLANK() asm volatile("\n->" : :)
-
-#define OFFSET(_sym, _str, _mem) \
-    DEFINE(_sym, offsetof(_str, _mem));
-
 void foo(void)
 {
 	DEFINE(VMM_TASK_SIZE, sizeof(struct kvm_vcpu));

arch/ia64/kvm/kvm-ia64.c

@@ -180,7 +180,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 
 	switch (ext) {
 	case KVM_CAP_IRQCHIP:
-	case KVM_CAP_USER_MEMORY:
 	case KVM_CAP_MP_STATE:
 
 		r = 1;
@@ -439,7 +438,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 		expires = div64_u64(itc_diff, cyc_per_usec);
 		kt = ktime_set(0, 1000 * expires);
 
-		down_read(&vcpu->kvm->slots_lock);
 		vcpu->arch.ht_active = 1;
 		hrtimer_start(p_ht, kt, HRTIMER_MODE_ABS);
 
@@ -452,7 +450,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 			if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
 				vcpu->arch.mp_state =
 					KVM_MP_STATE_RUNNABLE;
-		up_read(&vcpu->kvm->slots_lock);
 
 		if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
 			return -EINTR;
@@ -476,6 +473,13 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu,
 	return 1;
 }
 
+static int handle_vcpu_debug(struct kvm_vcpu *vcpu,
+				struct kvm_run *kvm_run)
+{
+	printk("VMM: %s", vcpu->arch.log_buf);
+	return 1;
+}
+
 static int (*kvm_vti_exit_handlers[])(struct kvm_vcpu *vcpu,
 		struct kvm_run *kvm_run) = {
 	[EXIT_REASON_VM_PANIC]              = handle_vm_error,
@@ -487,6 +491,7 @@ static int (*kvm_vti_exit_handlers[])(struct kvm_vcpu *vcpu,
 	[EXIT_REASON_EXTERNAL_INTERRUPT]    = handle_external_interrupt,
 	[EXIT_REASON_IPI]		    = handle_ipi,
 	[EXIT_REASON_PTC_G]		    = handle_global_purge,
+	[EXIT_REASON_DEBUG]		    = handle_vcpu_debug,
 
 };
 
@@ -698,27 +703,24 @@ out:
 	return r;
 }
 
-/*
- * Allocate 16M memory for every vm to hold its specific data.
- * Its memory map is defined in kvm_host.h.
- */
 static struct kvm *kvm_alloc_kvm(void)
 {
 
 	struct kvm *kvm;
 	uint64_t  vm_base;
 
+	BUG_ON(sizeof(struct kvm) > KVM_VM_STRUCT_SIZE);
+
 	vm_base = __get_free_pages(GFP_KERNEL, get_order(KVM_VM_DATA_SIZE));
 
 	if (!vm_base)
 		return ERR_PTR(-ENOMEM);
-	printk(KERN_DEBUG"kvm: VM data's base Address:0x%lx\n", vm_base);
 
-	/* Zero all pages before use! */
 	memset((void *)vm_base, 0, KVM_VM_DATA_SIZE);
-
-	kvm = (struct kvm *)(vm_base + KVM_VM_OFS);
+	kvm = (struct kvm *)(vm_base +
+			offsetof(struct kvm_vm_data, kvm_vm_struct));
 	kvm->arch.vm_base = vm_base;
+	printk(KERN_DEBUG"kvm: vm's data area:0x%lx\n", vm_base);
 
 	return kvm;
 }
@@ -760,21 +762,12 @@ static void kvm_build_io_pmt(struct kvm *kvm)
 
 static void kvm_init_vm(struct kvm *kvm)
 {
-	long vm_base;
-
 	BUG_ON(!kvm);
 
 	kvm->arch.metaphysical_rr0 = GUEST_PHYSICAL_RR0;
 	kvm->arch.metaphysical_rr4 = GUEST_PHYSICAL_RR4;
 	kvm->arch.vmm_init_rr = VMM_INIT_RR;
 
-	vm_base = kvm->arch.vm_base;
-	if (vm_base) {
-		kvm->arch.vhpt_base = vm_base + KVM_VHPT_OFS;
-		kvm->arch.vtlb_base = vm_base + KVM_VTLB_OFS;
-		kvm->arch.vpd_base  = vm_base + KVM_VPD_OFS;
-	}
-
 	/*
 	 *Fill P2M entries for MMIO/IO ranges
 	 */
@@ -838,9 +831,8 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 
 int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
-	int i;
 	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
-	int r;
+	int i;
 
 	vcpu_load(vcpu);
 
@@ -857,18 +849,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 
 	vpd->vpr = regs->vpd.vpr;
 
-	r = -EFAULT;
-	r = copy_from_user(&vcpu->arch.guest, regs->saved_guest,
-						sizeof(union context));
-	if (r)
-		goto out;
-	r = copy_from_user(vcpu + 1, regs->saved_stack +
-			sizeof(struct kvm_vcpu),
-			IA64_STK_OFFSET - sizeof(struct kvm_vcpu));
-	if (r)
-		goto out;
-	vcpu->arch.exit_data =
-		((struct kvm_vcpu *)(regs->saved_stack))->arch.exit_data;
+	memcpy(&vcpu->arch.guest, &regs->saved_guest, sizeof(union context));
 
 	RESTORE_REGS(mp_state);
 	RESTORE_REGS(vmm_rr);
@@ -902,9 +883,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	set_bit(KVM_REQ_RESUME, &vcpu->requests);
 
 	vcpu_put(vcpu);
-	r = 0;
-out:
-	return r;
+
+	return 0;
 }
 
 long kvm_arch_vm_ioctl(struct file *filp,
@@ -1166,10 +1146,11 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		/*Set entry address for first run.*/
 		regs->cr_iip = PALE_RESET_ENTRY;
 
-		/*Initilize itc offset for vcpus*/
+		/*Initialize itc offset for vcpus*/
 		itc_offset = 0UL - ia64_getreg(_IA64_REG_AR_ITC);
-		for (i = 0; i < MAX_VCPU_NUM; i++) {
-			v = (struct kvm_vcpu *)((char *)vcpu + VCPU_SIZE * i);
+		for (i = 0; i < KVM_MAX_VCPUS; i++) {
+			v = (struct kvm_vcpu *)((char *)vcpu +
+					sizeof(struct kvm_vcpu_data) * i);
 			v->arch.itc_offset = itc_offset;
 			v->arch.last_itc = 0;
 		}
@@ -1183,7 +1164,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.apic->vcpu = vcpu;
 
 	p_ctx->gr[1] = 0;
-	p_ctx->gr[12] = (unsigned long)((char *)vmm_vcpu + IA64_STK_OFFSET);
+	p_ctx->gr[12] = (unsigned long)((char *)vmm_vcpu + KVM_STK_OFFSET);
 	p_ctx->gr[13] = (unsigned long)vmm_vcpu;
 	p_ctx->psr = 0x1008522000UL;
 	p_ctx->ar[40] = FPSR_DEFAULT; /*fpsr*/
@@ -1218,12 +1199,12 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.hlt_timer.function = hlt_timer_fn;
 
 	vcpu->arch.last_run_cpu = -1;
-	vcpu->arch.vpd = (struct vpd *)VPD_ADDR(vcpu->vcpu_id);
+	vcpu->arch.vpd = (struct vpd *)VPD_BASE(vcpu->vcpu_id);
 	vcpu->arch.vsa_base = kvm_vsa_base;
 	vcpu->arch.__gp = kvm_vmm_gp;
 	vcpu->arch.dirty_log_lock_pa = __pa(&kvm->arch.dirty_log_lock);
-	vcpu->arch.vhpt.hash = (struct thash_data *)VHPT_ADDR(vcpu->vcpu_id);
-	vcpu->arch.vtlb.hash = (struct thash_data *)VTLB_ADDR(vcpu->vcpu_id);
+	vcpu->arch.vhpt.hash = (struct thash_data *)VHPT_BASE(vcpu->vcpu_id);
+	vcpu->arch.vtlb.hash = (struct thash_data *)VTLB_BASE(vcpu->vcpu_id);
 	init_ptce_info(vcpu);
 
 	r = 0;
@@ -1273,12 +1254,22 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	int r;
 	int cpu;
 
+	BUG_ON(sizeof(struct kvm_vcpu) > VCPU_STRUCT_SIZE/2);
+
+	r = -EINVAL;
+	if (id >= KVM_MAX_VCPUS) {
+		printk(KERN_ERR"kvm: Can't configure vcpus > %ld",
+				KVM_MAX_VCPUS);
+		goto fail;
+	}
+
 	r = -ENOMEM;
 	if (!vm_base) {
 		printk(KERN_ERR"kvm: Create vcpu[%d] error!\n", id);
 		goto fail;
 	}
-	vcpu = (struct kvm_vcpu *)(vm_base + KVM_VCPU_OFS + VCPU_SIZE * id);
+	vcpu = (struct kvm_vcpu *)(vm_base + offsetof(struct kvm_vm_data,
+					vcpu_data[id].vcpu_struct));
 	vcpu->kvm = kvm;
 
 	cpu = get_cpu();
@@ -1374,9 +1365,9 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
-	int i;
-	int r;
 	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
+	int i;
+
 	vcpu_load(vcpu);
 
 	for (i = 0; i < 16; i++) {
@@ -1391,14 +1382,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->vpd.vpsr = vpd->vpsr;
 	regs->vpd.vpr = vpd->vpr;
 
-	r = -EFAULT;
-	r = copy_to_user(regs->saved_guest, &vcpu->arch.guest,
-					sizeof(union context));
-	if (r)
-		goto out;
-	r = copy_to_user(regs->saved_stack, (void *)vcpu, IA64_STK_OFFSET);
-	if (r)
-		goto out;
+	memcpy(&regs->saved_guest, &vcpu->arch.guest, sizeof(union context));
+
 	SAVE_REGS(mp_state);
 	SAVE_REGS(vmm_rr);
 	memcpy(regs->itrs, vcpu->arch.itrs, sizeof(struct thash_data) * NITRS);
@@ -1426,10 +1411,9 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	SAVE_REGS(metaphysical_saved_rr4);
 	SAVE_REGS(fp_psr);
 	SAVE_REGS(saved_gp);
+
 	vcpu_put(vcpu);
-	r = 0;
-out:
-	return r;
+	return 0;
 }
 
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
@@ -1457,6 +1441,9 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 	struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot];
 	unsigned long base_gfn = memslot->base_gfn;
 
+	if (base_gfn + npages > (KVM_MAX_MEM_SIZE >> PAGE_SHIFT))
+		return -ENOMEM;
+
 	for (i = 0; i < npages; i++) {
 		pfn = gfn_to_pfn(kvm, base_gfn + i);
 		if (!kvm_is_mmio_pfn(pfn)) {
@@ -1631,8 +1618,8 @@ static int kvm_ia64_sync_dirty_log(struct kvm *kvm,
 	struct kvm_memory_slot *memslot;
 	int r, i;
 	long n, base;
-	unsigned long *dirty_bitmap = (unsigned long *)((void *)kvm - KVM_VM_OFS
-					+ KVM_MEM_DIRTY_LOG_OFS);
+	unsigned long *dirty_bitmap = (unsigned long *)(kvm->arch.vm_base +
+			offsetof(struct kvm_vm_data, kvm_mem_dirty_log));
 
 	r = -EINVAL;
 	if (log->slot >= KVM_MEMORY_SLOTS)

arch/ia64/kvm/kvm_lib.c

@@ -0,0 +1,15 @@
+/*
+ * kvm_lib.c: Compile some libraries for kvm-intel module.
+ *
+ *	Just include kernel's library, and disable symbols export.
+ * 	Copyright (C) 2008, Intel Corporation.
+ *  	Xiantao Zhang  (xiantao.zhang@intel.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+#undef CONFIG_MODULES
+#include "../../../lib/vsprintf.c"
+#include "../../../lib/ctype.c"

arch/ia64/kvm/kvm_minstate.h

@@ -24,6 +24,8 @@
 #include <asm/asmmacro.h>
 #include <asm/types.h>
 #include <asm/kregs.h>
+#include <asm/kvm_host.h>
+
 #include "asm-offsets.h"
 
 #define KVM_MINSTATE_START_SAVE_MIN	     					\
@@ -33,7 +35,7 @@
 	addl r22 = VMM_RBS_OFFSET,r1;            /* compute base of RBS */	\
 	;;									\
 	lfetch.fault.excl.nt1 [r22];						\
-	addl r1 = IA64_STK_OFFSET-VMM_PT_REGS_SIZE,r1;  /* compute base of memory stack */  \
+	addl r1 = KVM_STK_OFFSET-VMM_PT_REGS_SIZE, r1;  \
 	mov r23 = ar.bspstore;			/* save ar.bspstore */          \
 	;;									\
 	mov ar.bspstore = r22;				/* switch to kernel RBS */\

arch/ia64/kvm/misc.h

@@ -27,7 +27,8 @@
  */
 static inline uint64_t *kvm_host_get_pmt(struct kvm *kvm)
 {
-	return (uint64_t *)(kvm->arch.vm_base + KVM_P2M_OFS);
+	return (uint64_t *)(kvm->arch.vm_base +
+				offsetof(struct kvm_vm_data, kvm_p2m));
 }
 
 static inline void kvm_set_pmt_entry(struct kvm *kvm, gfn_t gfn,

arch/ia64/kvm/mmio.c

@@ -66,31 +66,25 @@ void lsapic_write(struct kvm_vcpu *v, unsigned long addr,
 
 	switch (addr) {
 	case PIB_OFST_INTA:
-		/*panic_domain(NULL, "Undefined write on PIB INTA\n");*/
-		panic_vm(v);
+		panic_vm(v, "Undefined write on PIB INTA\n");
 		break;
 	case PIB_OFST_XTP:
 		if (length == 1) {
 			vlsapic_write_xtp(v, val);
 		} else {
-			/*panic_domain(NULL,
-			"Undefined write on PIB XTP\n");*/
-			panic_vm(v);
+			panic_vm(v, "Undefined write on PIB XTP\n");
 		}
 		break;
 	default:
 		if (PIB_LOW_HALF(addr)) {
-			/*lower half */
+			/*Lower half */
 			if (length != 8)
-				/*panic_domain(NULL,
-				"Can't LHF write with size %ld!\n",
-				length);*/
-				panic_vm(v);
+				panic_vm(v, "Can't LHF write with size %ld!\n",
+						length);
 			else
 				vlsapic_write_ipi(v, addr, val);
-		} else {   /*	upper half
-				printk("IPI-UHF write %lx\n",addr);*/
-			panic_vm(v);
+		} else {   /*Upper half */
+			panic_vm(v, "IPI-UHF write %lx\n", addr);
 		}
 		break;
 	}
@@ -108,22 +102,18 @@ unsigned long lsapic_read(struct kvm_vcpu *v, unsigned long addr,
 		if (length == 1) /* 1 byte load */
 			; /* There is no i8259, there is no INTA access*/
 		else
-			/*panic_domain(NULL,"Undefined read on PIB INTA\n"); */
-			panic_vm(v);
+			panic_vm(v, "Undefined read on PIB INTA\n");
 
 		break;
 	case PIB_OFST_XTP:
 		if (length == 1) {
 			result = VLSAPIC_XTP(v);
-			/* printk("read xtp %lx\n", result); */
 		} else {
-			/*panic_domain(NULL,
-			"Undefined read on PIB XTP\n");*/
-			panic_vm(v);
+			panic_vm(v, "Undefined read on PIB XTP\n");
 		}
 		break;
 	default:
-		panic_vm(v);
+		panic_vm(v, "Undefined addr access for lsapic!\n");
 		break;
 	}
 	return result;
@@ -162,7 +152,7 @@ static void mmio_access(struct kvm_vcpu *vcpu, u64 src_pa, u64 *dest,
 			/* it's necessary to ensure zero extending */
 			*dest = p->u.ioreq.data & (~0UL >> (64-(s*8)));
 	} else
-		panic_vm(vcpu);
+		panic_vm(vcpu, "Unhandled mmio access returned!\n");
 out:
 	local_irq_restore(psr);
 	return ;
@@ -324,7 +314,9 @@ void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma)
 		return;
 	} else {
 		inst_type = -1;
-		panic_vm(vcpu);
+		panic_vm(vcpu, "Unsupported MMIO access instruction! \
+				Bunld[0]=0x%lx, Bundle[1]=0x%lx\n",
+				bundle.i64[0], bundle.i64[1]);
 	}
 
 	size = 1 << size;
@@ -335,7 +327,7 @@ void emulate_io_inst(struct kvm_vcpu *vcpu, u64 padr, u64 ma)
 		if (inst_type == SL_INTEGER)
 			vcpu_set_gr(vcpu, inst.M1.r1, data, 0);
 		else
-			panic_vm(vcpu);
+			panic_vm(vcpu, "Unsupported instruction type!\n");
 
 	}
 	vcpu_increment_iip(vcpu);

arch/ia64/kvm/process.c

@@ -527,7 +527,8 @@ void reflect_interruption(u64 ifa, u64 isr, u64 iim,
 	vector = vec2off[vec];
 
 	if (!(vpsr & IA64_PSR_IC) && (vector != IA64_DATA_NESTED_TLB_VECTOR)) {
-		panic_vm(vcpu);
+		panic_vm(vcpu, "Interruption with vector :0x%lx occurs "
+						"with psr.ic = 0\n", vector);
 		return;
 	}
 
@@ -586,7 +587,7 @@ static void set_pal_call_result(struct kvm_vcpu *vcpu)
 		vcpu_set_gr(vcpu, 10, p->u.pal_data.ret.v1, 0);
 		vcpu_set_gr(vcpu, 11, p->u.pal_data.ret.v2, 0);
 	} else
-		panic_vm(vcpu);
+		panic_vm(vcpu, "Mis-set for exit reason!\n");
 }
 
 static void set_sal_call_data(struct kvm_vcpu *vcpu)
@@ -614,7 +615,7 @@ static void set_sal_call_result(struct kvm_vcpu *vcpu)
 		vcpu_set_gr(vcpu, 10, p->u.sal_data.ret.r10, 0);
 		vcpu_set_gr(vcpu, 11, p->u.sal_data.ret.r11, 0);
 	} else
-		panic_vm(vcpu);
+		panic_vm(vcpu, "Mis-set for exit reason!\n");
 }
 
 void  kvm_ia64_handle_break(unsigned long ifa, struct kvm_pt_regs *regs,
@@ -680,7 +681,7 @@ static void generate_exirq(struct kvm_vcpu *vcpu)
 	vpsr = VCPU(vcpu, vpsr);
 	isr = vpsr & IA64_PSR_RI;
 	if (!(vpsr & IA64_PSR_IC))
-		panic_vm(vcpu);
+		panic_vm(vcpu, "Trying to inject one IRQ with psr.ic=0\n");
 	reflect_interruption(0, isr, 0, 12, regs); /* EXT IRQ */
 }
 
@@ -941,8 +942,20 @@ static void vcpu_do_resume(struct kvm_vcpu *vcpu)
 	ia64_set_pta(vcpu->arch.vhpt.pta.val);
 }
 
+static void vmm_sanity_check(struct kvm_vcpu *vcpu)
+{
+	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+
+	if (!vmm_sanity && p->exit_reason != EXIT_REASON_DEBUG) {
+		panic_vm(vcpu, "Failed to do vmm sanity check,"
+			"it maybe caused by crashed vmm!!\n\n");
+	}
+}
+
 static void kvm_do_resume_op(struct kvm_vcpu *vcpu)
 {
+	vmm_sanity_check(vcpu); /*Guarantee vcpu runing on healthy vmm!*/
+
 	if (test_and_clear_bit(KVM_REQ_RESUME, &vcpu->requests)) {
 		vcpu_do_resume(vcpu);
 		return;
@@ -968,3 +981,11 @@ void vmm_transition(struct kvm_vcpu *vcpu)
 						1, 0, 0, 0, 0, 0);
 	kvm_do_resume_op(vcpu);
 }
+
+void vmm_panic_handler(u64 vec)
+{
+	struct kvm_vcpu *vcpu = current_vcpu;
+	vmm_sanity = 0;
+	panic_vm(vcpu, "Unexpected interruption occurs in VMM, vector:0x%lx\n",
+			vec2off[vec]);
+}

arch/ia64/kvm/vcpu.c

@@ -816,8 +816,9 @@ static void vcpu_set_itc(struct kvm_vcpu *vcpu, u64 val)
 	unsigned long vitv = VCPU(vcpu, itv);
 
 	if (vcpu->vcpu_id == 0) {
-		for (i = 0; i < MAX_VCPU_NUM; i++) {
-			v = (struct kvm_vcpu *)((char *)vcpu + VCPU_SIZE * i);
+		for (i = 0; i < KVM_MAX_VCPUS; i++) {
+			v = (struct kvm_vcpu *)((char *)vcpu +
+					sizeof(struct kvm_vcpu_data) * i);
 			VMX(v, itc_offset) = itc_offset;
 			VMX(v, last_itc) = 0;
 		}
@@ -1650,7 +1651,8 @@ void vcpu_set_psr(struct kvm_vcpu *vcpu, unsigned long val)
 	 * Otherwise panic
 	 */
 	if (val & (IA64_PSR_PK | IA64_PSR_IS | IA64_PSR_VM))
-		panic_vm(vcpu);
+		panic_vm(vcpu, "Only support guests with vpsr.pk =0 \
+				& vpsr.is=0\n");
 
 	/*
 	 * For those IA64_PSR bits: id/da/dd/ss/ed/ia
@@ -2103,7 +2105,7 @@ void kvm_init_all_rr(struct kvm_vcpu *vcpu)
 
 	if (is_physical_mode(vcpu)) {
 		if (vcpu->arch.mode_flags & GUEST_PHY_EMUL)
-			panic_vm(vcpu);
+			panic_vm(vcpu, "Machine Status conflicts!\n");
 
 		ia64_set_rr((VRN0 << VRN_SHIFT), vcpu->arch.metaphysical_rr0);
 		ia64_dv_serialize_data();
@@ -2152,10 +2154,70 @@ int vmm_entry(void)
 	return 0;
 }
 
-void panic_vm(struct kvm_vcpu *v)
+static void kvm_show_registers(struct kvm_pt_regs *regs)
 {
-	struct exit_ctl_data *p = &v->arch.exit_data;
+	unsigned long ip = regs->cr_iip + ia64_psr(regs)->ri;
 
+	struct kvm_vcpu *vcpu = current_vcpu;
+	if (vcpu != NULL)
+		printk("vcpu 0x%p vcpu %d\n",
+		       vcpu, vcpu->vcpu_id);
+
+	printk("psr : %016lx ifs : %016lx ip  : [<%016lx>]\n",
+	       regs->cr_ipsr, regs->cr_ifs, ip);
+
+	printk("unat: %016lx pfs : %016lx rsc : %016lx\n",
+	       regs->ar_unat, regs->ar_pfs, regs->ar_rsc);
+	printk("rnat: %016lx bspstore: %016lx pr  : %016lx\n",
+	       regs->ar_rnat, regs->ar_bspstore, regs->pr);
+	printk("ldrs: %016lx ccv : %016lx fpsr: %016lx\n",
+	       regs->loadrs, regs->ar_ccv, regs->ar_fpsr);
+	printk("csd : %016lx ssd : %016lx\n", regs->ar_csd, regs->ar_ssd);
+	printk("b0  : %016lx b6  : %016lx b7  : %016lx\n", regs->b0,
+							regs->b6, regs->b7);
+	printk("f6  : %05lx%016lx f7  : %05lx%016lx\n",
+	       regs->f6.u.bits[1], regs->f6.u.bits[0],
+	       regs->f7.u.bits[1], regs->f7.u.bits[0]);
+	printk("f8  : %05lx%016lx f9  : %05lx%016lx\n",
+	       regs->f8.u.bits[1], regs->f8.u.bits[0],
+	       regs->f9.u.bits[1], regs->f9.u.bits[0]);
+	printk("f10 : %05lx%016lx f11 : %05lx%016lx\n",
+	       regs->f10.u.bits[1], regs->f10.u.bits[0],
+	       regs->f11.u.bits[1], regs->f11.u.bits[0]);
+
+	printk("r1  : %016lx r2  : %016lx r3  : %016lx\n", regs->r1,
+							regs->r2, regs->r3);
+	printk("r8  : %016lx r9  : %016lx r10 : %016lx\n", regs->r8,
+							regs->r9, regs->r10);
+	printk("r11 : %016lx r12 : %016lx r13 : %016lx\n", regs->r11,
+							regs->r12, regs->r13);
+	printk("r14 : %016lx r15 : %016lx r16 : %016lx\n", regs->r14,
+							regs->r15, regs->r16);
+	printk("r17 : %016lx r18 : %016lx r19 : %016lx\n", regs->r17,
+							regs->r18, regs->r19);
+	printk("r20 : %016lx r21 : %016lx r22 : %016lx\n", regs->r20,
+							regs->r21, regs->r22);
+	printk("r23 : %016lx r24 : %016lx r25 : %016lx\n", regs->r23,
+							regs->r24, regs->r25);
+	printk("r26 : %016lx r27 : %016lx r28 : %016lx\n", regs->r26,
+							regs->r27, regs->r28);
+	printk("r29 : %016lx r30 : %016lx r31 : %016lx\n", regs->r29,
+							regs->r30, regs->r31);
+
+}
+
+void panic_vm(struct kvm_vcpu *v, const char *fmt, ...)
+{
+	va_list args;
+	char buf[256];
+
+	struct kvm_pt_regs *regs = vcpu_regs(v);
+	struct exit_ctl_data *p = &v->arch.exit_data;
+	va_start(args, fmt);
+	vsnprintf(buf, sizeof(buf), fmt, args);
+	va_end(args);
+	printk(buf);
+	kvm_show_registers(regs);
 	p->exit_reason = EXIT_REASON_VM_PANIC;
 	vmm_transition(v);
 	/*Never to return*/

arch/ia64/kvm/vcpu.h

@@ -737,9 +737,12 @@ void kvm_init_vtlb(struct kvm_vcpu *v);
 void kvm_init_vhpt(struct kvm_vcpu *v);
 void thash_init(struct thash_cb *hcb, u64 sz);
 
-void panic_vm(struct kvm_vcpu *v);
+void panic_vm(struct kvm_vcpu *v, const char *fmt, ...);
 
 extern u64 ia64_call_vsa(u64 proc, u64 arg1, u64 arg2, u64 arg3,
 		u64 arg4, u64 arg5, u64 arg6, u64 arg7);
+
+extern long vmm_sanity;
+
 #endif
 #endif	/* __VCPU_H__ */

arch/ia64/kvm/vmm.c

@@ -20,6 +20,7 @@
  */
 
 
+#include<linux/kernel.h>
 #include<linux/module.h>
 #include<asm/fpswa.h>
 
@@ -31,6 +32,8 @@ MODULE_LICENSE("GPL");
 extern char kvm_ia64_ivt;
 extern fpswa_interface_t *vmm_fpswa_interface;
 
+long vmm_sanity = 1;
+
 struct kvm_vmm_info vmm_info = {
 	.module	     = THIS_MODULE,
 	.vmm_entry   = vmm_entry,
@@ -62,5 +65,31 @@ void vmm_spin_unlock(spinlock_t *lock)
 {
 	_vmm_raw_spin_unlock(lock);
 }
+
+static void vcpu_debug_exit(struct kvm_vcpu *vcpu)
+{
+	struct exit_ctl_data *p = &vcpu->arch.exit_data;
+	long psr;
+
+	local_irq_save(psr);
+	p->exit_reason = EXIT_REASON_DEBUG;
+	vmm_transition(vcpu);
+	local_irq_restore(psr);
+}
+
+asmlinkage int printk(const char *fmt, ...)
+{
+	struct kvm_vcpu *vcpu = current_vcpu;
+	va_list args;
+	int r;
+
+	memset(vcpu->arch.log_buf, 0, VMM_LOG_LEN);
+	va_start(args, fmt);
+	r = vsnprintf(vcpu->arch.log_buf, VMM_LOG_LEN, fmt, args);
+	va_end(args);
+	vcpu_debug_exit(vcpu);
+	return r;
+}
+
 module_init(kvm_vmm_init)
 module_exit(kvm_vmm_exit)

arch/ia64/kvm/vtlb.c

@@ -183,8 +183,8 @@ void mark_pages_dirty(struct kvm_vcpu *v, u64 pte, u64 ps)
 	u64 i, dirty_pages = 1;
 	u64 base_gfn = (pte&_PAGE_PPN_MASK) >> PAGE_SHIFT;
 	spinlock_t *lock = __kvm_va(v->arch.dirty_log_lock_pa);
-	void *dirty_bitmap = (void *)v - (KVM_VCPU_OFS + v->vcpu_id * VCPU_SIZE)
-						+ KVM_MEM_DIRTY_LOG_OFS;
+	void *dirty_bitmap = (void *)KVM_MEM_DIRTY_LOG_BASE;
+
 	dirty_pages <<= ps <= PAGE_SHIFT ? 0 : ps - PAGE_SHIFT;
 
 	vmm_spin_lock(lock);