#include <linux/io.h>
#include <linux/lockdep.h>
#include <linux/kthread.h>
+#include <linux/suspend.h>
#include <asm/processor.h>
#include <asm/ioctl.h>
struct dentry *kvm_debugfs_dir;
EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
-static int kvm_debugfs_num_entries;
static const struct file_operations stat_fops_per_vm;
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
{
return kvm_make_all_cpus_request_except(kvm, req, NULL);
}
+EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request);
#ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL
void kvm_flush_remote_tlbs(struct kvm *kvm)
*/
if (!kvm_arch_flush_remote_tlb(kvm)
|| kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
- ++kvm->stat.remote_tlb_flush;
+ ++kvm->stat.generic.remote_tlb_flush;
cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
}
EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs);
#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
+#ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
+static int kvm_pm_notifier_call(struct notifier_block *bl,
+ unsigned long state,
+ void *unused)
+{
+ struct kvm *kvm = container_of(bl, struct kvm, pm_notifier);
+
+ return kvm_arch_pm_notifier(kvm, state);
+}
+
+static void kvm_init_pm_notifier(struct kvm *kvm)
+{
+ kvm->pm_notifier.notifier_call = kvm_pm_notifier_call;
+ /* Suspend KVM before we suspend ftrace, RCU, etc. */
+ kvm->pm_notifier.priority = INT_MAX;
+ register_pm_notifier(&kvm->pm_notifier);
+}
+
+static void kvm_destroy_pm_notifier(struct kvm *kvm)
+{
+ unregister_pm_notifier(&kvm->pm_notifier);
+}
+#else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */
+static void kvm_init_pm_notifier(struct kvm *kvm)
+{
+}
+
+static void kvm_destroy_pm_notifier(struct kvm *kvm)
+{
+}
+#endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */
+
static struct kvm_memslots *kvm_alloc_memslots(void)
{
int i;
kvfree(slots);
}
+static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc)
+{
+ switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) {
+ case KVM_STATS_TYPE_INSTANT:
+ return 0444;
+ case KVM_STATS_TYPE_CUMULATIVE:
+ case KVM_STATS_TYPE_PEAK:
+ default:
+ return 0644;
+ }
+}
+
+
static void kvm_destroy_vm_debugfs(struct kvm *kvm)
{
int i;
+ int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
+ kvm_vcpu_stats_header.num_desc;
if (!kvm->debugfs_dentry)
return;
{
char dir_name[ITOA_MAX_LEN * 2];
struct kvm_stat_data *stat_data;
- struct kvm_stats_debugfs_item *p;
+ const struct _kvm_stats_desc *pdesc;
+ int i;
+ int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc +
+ kvm_vcpu_stats_header.num_desc;
if (!debugfs_initialized())
return 0;
if (!kvm->debugfs_stat_data)
return -ENOMEM;
- for (p = debugfs_entries; p->name; p++) {
+ for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vm_stats_desc[i];
stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
if (!stat_data)
return -ENOMEM;
stat_data->kvm = kvm;
- stat_data->dbgfs_item = p;
- kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
- debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p),
+ stat_data->desc = pdesc;
+ stat_data->kind = KVM_STAT_VM;
+ kvm->debugfs_stat_data[i] = stat_data;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm->debugfs_dentry, stat_data,
+ &stat_fops_per_vm);
+ }
+
+ for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vcpu_stats_desc[i];
+ stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
+ if (!stat_data)
+ return -ENOMEM;
+
+ stat_data->kvm = kvm;
+ stat_data->desc = pdesc;
+ stat_data->kind = KVM_STAT_VCPU;
+ kvm->debugfs_stat_data[i] = stat_data;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
kvm->debugfs_dentry, stat_data,
&stat_fops_per_vm);
}
mutex_init(&kvm->lock);
mutex_init(&kvm->irq_lock);
mutex_init(&kvm->slots_lock);
+ mutex_init(&kvm->slots_arch_lock);
INIT_LIST_HEAD(&kvm->devices);
BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
mutex_unlock(&kvm_lock);
preempt_notifier_inc();
+ kvm_init_pm_notifier(kvm);
return kvm;
int i;
struct mm_struct *mm = kvm->mm;
+ kvm_destroy_pm_notifier(kvm);
kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
kvm_destroy_vm_debugfs(kvm);
kvm_arch_sync_events(kvm);
slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
rcu_assign_pointer(kvm->memslots[as_id], slots);
+
+ /*
+ * Acquired in kvm_set_memslot. Must be released before synchronize
+ * SRCU below in order to avoid deadlock with another thread
+ * acquiring the slots_arch_lock in an srcu critical section.
+ */
+ mutex_unlock(&kvm->slots_arch_lock);
+
synchronize_srcu_expedited(&kvm->srcu);
/*
return old_memslots;
}
+static size_t kvm_memslots_size(int slots)
+{
+ return sizeof(struct kvm_memslots) +
+ (sizeof(struct kvm_memory_slot) * slots);
+}
+
+static void kvm_copy_memslots(struct kvm_memslots *to,
+ struct kvm_memslots *from)
+{
+ memcpy(to, from, kvm_memslots_size(from->used_slots));
+}
+
/*
* Note, at a minimum, the current number of used slots must be allocated, even
* when deleting a memslot, as we need a complete duplicate of the memslots for
enum kvm_mr_change change)
{
struct kvm_memslots *slots;
- size_t old_size, new_size;
-
- old_size = sizeof(struct kvm_memslots) +
- (sizeof(struct kvm_memory_slot) * old->used_slots);
+ size_t new_size;
if (change == KVM_MR_CREATE)
- new_size = old_size + sizeof(struct kvm_memory_slot);
+ new_size = kvm_memslots_size(old->used_slots + 1);
else
- new_size = old_size;
+ new_size = kvm_memslots_size(old->used_slots);
slots = kvzalloc(new_size, GFP_KERNEL_ACCOUNT);
if (likely(slots))
- memcpy(slots, old, old_size);
+ kvm_copy_memslots(slots, old);
return slots;
}
struct kvm_memslots *slots;
int r;
+ /*
+ * Released in install_new_memslots.
+ *
+ * Must be held from before the current memslots are copied until
+ * after the new memslots are installed with rcu_assign_pointer,
+ * then released before the synchronize srcu in install_new_memslots.
+ *
+ * When modifying memslots outside of the slots_lock, must be held
+ * before reading the pointer to the current memslots until after all
+ * changes to those memslots are complete.
+ *
+ * These rules ensure that installing new memslots does not lose
+ * changes made to the previous memslots.
+ */
+ mutex_lock(&kvm->slots_arch_lock);
+
slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change);
- if (!slots)
+ if (!slots) {
+ mutex_unlock(&kvm->slots_arch_lock);
return -ENOMEM;
+ }
if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
/*
slot->flags |= KVM_MEMSLOT_INVALID;
/*
- * We can re-use the old memslots, the only difference from the
- * newly installed memslots is the invalid flag, which will get
- * dropped by update_memslots anyway. We'll also revert to the
- * old memslots if preparing the new memory region fails.
+ * We can re-use the memory from the old memslots.
+ * It will be overwritten with a copy of the new memslots
+ * after reacquiring the slots_arch_lock below.
*/
slots = install_new_memslots(kvm, as_id, slots);
* - kvm_is_visible_gfn (mmu_check_root)
*/
kvm_arch_flush_shadow_memslot(kvm, slot);
+
+ /* Released in install_new_memslots. */
+ mutex_lock(&kvm->slots_arch_lock);
+
+ /*
+ * The arch-specific fields of the memslots could have changed
+ * between releasing the slots_arch_lock in
+ * install_new_memslots and here, so get a fresh copy of the
+ * slots.
+ */
+ kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id));
}
r = kvm_arch_prepare_memory_region(kvm, new, mem, change);
return 0;
out_slots:
- if (change == KVM_MR_DELETE || change == KVM_MR_MOVE)
+ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
+ slot = id_to_memslot(slots, old->id);
+ slot->flags &= ~KVM_MEMSLOT_INVALID;
slots = install_new_memslots(kvm, as_id, slots);
+ } else {
+ mutex_unlock(&kvm->slots_arch_lock);
+ }
kvfree(slots);
return r;
}
return true;
}
+static int kvm_try_get_pfn(kvm_pfn_t pfn)
+{
+ if (kvm_is_reserved_pfn(pfn))
+ return 1;
+ return get_page_unless_zero(pfn_to_page(pfn));
+}
+
static int hva_to_pfn_remapped(struct vm_area_struct *vma,
unsigned long addr, bool *async,
bool write_fault, bool *writable,
* Whoever called remap_pfn_range is also going to call e.g.
* unmap_mapping_range before the underlying pages are freed,
* causing a call to our MMU notifier.
+ *
+ * Certain IO or PFNMAP mappings can be backed with valid
+ * struct pages, but be allocated without refcounting e.g.,
+ * tail pages of non-compound higher order allocations, which
+ * would then underflow the refcount when the caller does the
+ * required put_page. Don't allow those pages here.
*/
- kvm_get_pfn(pfn);
+ if (!kvm_try_get_pfn(pfn))
+ r = -EFAULT;
out:
pte_unmap_unlock(ptep, ptl);
*p_pfn = pfn;
- return 0;
+
+ return r;
}
/*
goto out;
if (signal_pending(current))
goto out;
+ if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu))
+ goto out;
ret = 0;
out:
update_halt_poll_stats(struct kvm_vcpu *vcpu, u64 poll_ns, bool waited)
{
if (waited)
- vcpu->stat.halt_poll_fail_ns += poll_ns;
+ vcpu->stat.generic.halt_poll_fail_ns += poll_ns;
else
- vcpu->stat.halt_poll_success_ns += poll_ns;
+ vcpu->stat.generic.halt_poll_success_ns += poll_ns;
}
/*
if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) {
ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
- ++vcpu->stat.halt_attempted_poll;
+ ++vcpu->stat.generic.halt_attempted_poll;
do {
/*
* This sets KVM_REQ_UNHALT if an interrupt
* arrives.
*/
if (kvm_vcpu_check_block(vcpu) < 0) {
- ++vcpu->stat.halt_successful_poll;
+ ++vcpu->stat.generic.halt_successful_poll;
if (!vcpu_valid_wakeup(vcpu))
- ++vcpu->stat.halt_poll_invalid;
+ ++vcpu->stat.generic.halt_poll_invalid;
goto out;
}
poll_end = cur = ktime_get();
- } while (single_task_running() && !need_resched() &&
- ktime_before(cur, stop));
+ } while (kvm_vcpu_can_poll(cur, stop));
}
prepare_to_rcuwait(&vcpu->wait);
waitp = kvm_arch_vcpu_get_wait(vcpu);
if (rcuwait_wake_up(waitp)) {
WRITE_ONCE(vcpu->ready, true);
- ++vcpu->stat.halt_wakeup;
+ ++vcpu->stat.generic.halt_wakeup;
return true;
}
vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus);
BUG_ON(kvm->vcpus[vcpu->vcpu_idx]);
+ /* Fill the stats id string for the vcpu */
+ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d",
+ task_pid_nr(current), id);
+
/* Now it's all set up, let userspace reach it */
kvm_get_kvm(kvm);
r = create_vcpu_fd(vcpu);
return 0;
}
+static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer,
+ size_t size, loff_t *offset)
+{
+ struct kvm_vcpu *vcpu = file->private_data;
+
+ return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header,
+ &kvm_vcpu_stats_desc[0], &vcpu->stat,
+ sizeof(vcpu->stat), user_buffer, size, offset);
+}
+
+static const struct file_operations kvm_vcpu_stats_fops = {
+ .read = kvm_vcpu_stats_read,
+ .llseek = noop_llseek,
+};
+
+static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu)
+{
+ int fd;
+ struct file *file;
+ char name[15 + ITOA_MAX_LEN + 1];
+
+ snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id);
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ file = anon_inode_getfile(name, &kvm_vcpu_stats_fops, vcpu, O_RDONLY);
+ if (IS_ERR(file)) {
+ put_unused_fd(fd);
+ return PTR_ERR(file);
+ }
+ file->f_mode |= FMODE_PREAD;
+ fd_install(fd, file);
+
+ return fd;
+}
+
static long kvm_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu);
break;
}
+ case KVM_GET_STATS_FD: {
+ r = kvm_vcpu_ioctl_get_stats_fd(vcpu);
+ break;
+ }
default:
r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
}
#else
return 0;
#endif
+ case KVM_CAP_BINARY_STATS_FD:
+ return 1;
default:
break;
}
}
}
+static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer,
+ size_t size, loff_t *offset)
+{
+ struct kvm *kvm = file->private_data;
+
+ return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header,
+ &kvm_vm_stats_desc[0], &kvm->stat,
+ sizeof(kvm->stat), user_buffer, size, offset);
+}
+
+static const struct file_operations kvm_vm_stats_fops = {
+ .read = kvm_vm_stats_read,
+ .llseek = noop_llseek,
+};
+
+static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm)
+{
+ int fd;
+ struct file *file;
+
+ fd = get_unused_fd_flags(O_CLOEXEC);
+ if (fd < 0)
+ return fd;
+
+ file = anon_inode_getfile("kvm-vm-stats",
+ &kvm_vm_stats_fops, kvm, O_RDONLY);
+ if (IS_ERR(file)) {
+ put_unused_fd(fd);
+ return PTR_ERR(file);
+ }
+ file->f_mode |= FMODE_PREAD;
+ fd_install(fd, file);
+
+ return fd;
+}
+
static long kvm_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
case KVM_RESET_DIRTY_RINGS:
r = kvm_vm_ioctl_reset_dirty_pages(kvm);
break;
+ case KVM_GET_STATS_FD:
+ r = kvm_vm_ioctl_get_stats_fd(kvm);
+ break;
default:
r = kvm_arch_vm_ioctl(filp, ioctl, arg);
}
if (r < 0)
goto put_kvm;
+ snprintf(kvm->stats_id, sizeof(kvm->stats_id),
+ "kvm-%d", task_pid_nr(current));
+
file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR);
if (IS_ERR(file)) {
put_unused_fd(r);
return -ENOENT;
if (simple_attr_open(inode, file, get,
- KVM_DBGFS_GET_MODE(stat_data->dbgfs_item) & 0222
+ kvm_stats_debugfs_mode(stat_data->desc) & 0222
? set : NULL,
fmt)) {
kvm_put_kvm(stat_data->kvm);
static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val)
{
- *val = *(ulong *)((void *)kvm + offset);
+ *val = *(u64 *)((void *)(&kvm->stat) + offset);
return 0;
}
static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset)
{
- *(ulong *)((void *)kvm + offset) = 0;
+ *(u64 *)((void *)(&kvm->stat) + offset) = 0;
return 0;
}
*val = 0;
kvm_for_each_vcpu(i, vcpu, kvm)
- *val += *(u64 *)((void *)vcpu + offset);
+ *val += *(u64 *)((void *)(&vcpu->stat) + offset);
return 0;
}
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm)
- *(u64 *)((void *)vcpu + offset) = 0;
+ *(u64 *)((void *)(&vcpu->stat) + offset) = 0;
return 0;
}
int r = -EFAULT;
struct kvm_stat_data *stat_data = (struct kvm_stat_data *)data;
- switch (stat_data->dbgfs_item->kind) {
+ switch (stat_data->kind) {
case KVM_STAT_VM:
r = kvm_get_stat_per_vm(stat_data->kvm,
- stat_data->dbgfs_item->offset, val);
+ stat_data->desc->desc.offset, val);
break;
case KVM_STAT_VCPU:
r = kvm_get_stat_per_vcpu(stat_data->kvm,
- stat_data->dbgfs_item->offset, val);
+ stat_data->desc->desc.offset, val);
break;
}
if (val)
return -EINVAL;
- switch (stat_data->dbgfs_item->kind) {
+ switch (stat_data->kind) {
case KVM_STAT_VM:
r = kvm_clear_stat_per_vm(stat_data->kvm,
- stat_data->dbgfs_item->offset);
+ stat_data->desc->desc.offset);
break;
case KVM_STAT_VCPU:
r = kvm_clear_stat_per_vcpu(stat_data->kvm,
- stat_data->dbgfs_item->offset);
+ stat_data->desc->desc.offset);
break;
}
}
DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n");
+DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%llu\n");
static int vcpu_stat_get(void *_offset, u64 *val)
{
DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear,
"%llu\n");
-
-static const struct file_operations *stat_fops[] = {
- [KVM_STAT_VCPU] = &vcpu_stat_fops,
- [KVM_STAT_VM] = &vm_stat_fops,
-};
+DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n");
static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm)
{
static void kvm_init_debug(void)
{
- struct kvm_stats_debugfs_item *p;
+ const struct file_operations *fops;
+ const struct _kvm_stats_desc *pdesc;
+ int i;
kvm_debugfs_dir = debugfs_create_dir("kvm", NULL);
- kvm_debugfs_num_entries = 0;
- for (p = debugfs_entries; p->name; ++p, kvm_debugfs_num_entries++) {
- debugfs_create_file(p->name, KVM_DBGFS_GET_MODE(p),
- kvm_debugfs_dir, (void *)(long)p->offset,
- stat_fops[p->kind]);
+ for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vm_stats_desc[i];
+ if (kvm_stats_debugfs_mode(pdesc) & 0222)
+ fops = &vm_stat_fops;
+ else
+ fops = &vm_stat_readonly_fops;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm_debugfs_dir,
+ (void *)(long)pdesc->desc.offset, fops);
+ }
+
+ for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) {
+ pdesc = &kvm_vcpu_stats_desc[i];
+ if (kvm_stats_debugfs_mode(pdesc) & 0222)
+ fops = &vcpu_stat_fops;
+ else
+ fops = &vcpu_stat_readonly_fops;
+ debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
+ kvm_debugfs_dir,
+ (void *)(long)pdesc->desc.offset, fops);
}
}
kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align,
SLAB_ACCOUNT,
offsetof(struct kvm_vcpu, arch),
- sizeof_field(struct kvm_vcpu, arch),
+ offsetofend(struct kvm_vcpu, stats_id)
+ - offsetof(struct kvm_vcpu, arch),
NULL);
if (!kvm_vcpu_cache) {
r = -ENOMEM;
projects / linux-2.6-microblaze.git / blobdiff