KVM: ia64: Re-organize data sturure of guests' data area

1. Increase the size of data area to 64M
2. Support more vcpus and memory, 128 vcpus and 256G memory are supported
   for guests.
3. Add the boundary check for memory and vcpu allocation.

With this patch, 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.
  */

Signed-off-by: Xiantao Zhang <xiantao.zhang@intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

5 files changed, 41 insertions, 35 deletions

diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index af1464f..43e45f6 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -698,27 +698,24 @@ 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 +757,12 @@ 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
 	 */
@@ -864,7 +852,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 		goto out;
 	r = copy_from_user(vcpu + 1, regs->saved_stack +
 			sizeof(struct kvm_vcpu),
-			IA64_STK_OFFSET - sizeof(struct kvm_vcpu));
+			KVM_STK_OFFSET - sizeof(struct kvm_vcpu));
 	if (r)
 		goto out;
 	vcpu->arch.exit_data =
@@ -1166,10 +1154,11 @@ 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 +1172,7 @@ 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 +1207,12 @@ 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 +1262,22 @@ 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();
@@ -1396,7 +1395,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 					sizeof(union context));
 	if (r)
 		goto out;
-	r = copy_to_user(regs->saved_stack, (void *)vcpu, IA64_STK_OFFSET);
+	r = copy_to_user(regs->saved_stack, (void *)vcpu, KVM_STK_OFFSET);
 	if (r)
 		goto out;
 	SAVE_REGS(mp_state);
@@ -1457,6 +1456,9 @@ 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 +1633,8 @@ 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)
diff --git a/arch/ia64/kvm/kvm_minstate.h b/arch/ia64/kvm/kvm_minstate.h
index 2cc41d1..b2bcaa2 100644
--- a/arch/ia64/kvm/kvm_minstate.h
+++ b/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 */\
diff --git a/arch/ia64/kvm/misc.h b/arch/ia64/kvm/misc.h
index e585c46..dd979e0 100644
--- a/arch/ia64/kvm/misc.h
+++ b/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,
diff --git a/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c
index e44027c..a528d70 100644
--- a/arch/ia64/kvm/vcpu.c
+++ b/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;
 		}
diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
index e22b933..6b6307a 100644
--- a/arch/ia64/kvm/vtlb.c
+++ b/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);