KVM: stats: Support binary stats retrieval for a VM

Add a VM ioctl to get a statistics file descriptor by which a read
functionality is provided for userspace to read out VM stats header,
descriptors and data.
Define VM statistics descriptors and header for all architectures.
Reviewed-by: David Matlack <dmatlack@google.com>
Reviewed-by: Ricardo Koller <ricarkol@google.com>
Reviewed-by: Krish Sadhukhan <krish.sadhukhan@oracle.com>
Reviewed-by: Fuad Tabba <tabba@google.com>
Tested-by: Fuad Tabba <tabba@google.com> #arm64
Signed-off-by: Jing Zhang <jingzhangos@google.com>
Message-Id: <20210618222709.1858088-4-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/arm64/kvm/guest.c

@@ -28,6 +28,21 @@
 
 #include "trace.h"
 
+const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+	KVM_GENERIC_VM_STATS()
+};
+static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
+		sizeof(struct kvm_vm_stat) / sizeof(u64));
+
+const struct kvm_stats_header kvm_vm_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
+	.id_offset =  sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vm_stats_desc),
+};
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("halt_successful_poll", generic.halt_successful_poll),
 	VCPU_STAT("halt_attempted_poll", generic.halt_attempted_poll),

arch/mips/kvm/mips.c

@@ -38,6 +38,21 @@
 #define VECTORSPACING 0x100	/* for EI/VI mode */
 #endif
 
+const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+	KVM_GENERIC_VM_STATS()
+};
+static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
+		sizeof(struct kvm_vm_stat) / sizeof(u64));
+
+const struct kvm_stats_header kvm_vm_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
+	.id_offset = sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vm_stats_desc),
+};
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("wait", wait_exits),
 	VCPU_STAT("cache", cache_exits),

arch/powerpc/kvm/book3s.c

@@ -38,6 +38,23 @@
 
 /* #define EXIT_DEBUG */
 
+const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+	KVM_GENERIC_VM_STATS(),
+	STATS_DESC_ICOUNTER(VM, num_2M_pages),
+	STATS_DESC_ICOUNTER(VM, num_1G_pages)
+};
+static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
+		sizeof(struct kvm_vm_stat) / sizeof(u64));
+
+const struct kvm_stats_header kvm_vm_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
+	.id_offset = sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vm_stats_desc),
+};
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("exits", sum_exits),
 	VCPU_STAT("mmio", mmio_exits),

arch/powerpc/kvm/booke.c

@@ -36,6 +36,23 @@
 
 unsigned long kvmppc_booke_handlers;
 
+const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+	KVM_GENERIC_VM_STATS(),
+	STATS_DESC_ICOUNTER(VM, num_2M_pages),
+	STATS_DESC_ICOUNTER(VM, num_1G_pages)
+};
+static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
+		sizeof(struct kvm_vm_stat) / sizeof(u64));
+
+const struct kvm_stats_header kvm_vm_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
+	.id_offset = sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vm_stats_desc),
+};
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("mmio", mmio_exits),
 	VCPU_STAT("sig", signal_exits),

arch/s390/kvm/kvm-s390.c

@@ -58,6 +58,26 @@
 #define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
 			   (KVM_MAX_VCPUS + LOCAL_IRQS))
 
+const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+	KVM_GENERIC_VM_STATS(),
+	STATS_DESC_COUNTER(VM, inject_io),
+	STATS_DESC_COUNTER(VM, inject_float_mchk),
+	STATS_DESC_COUNTER(VM, inject_pfault_done),
+	STATS_DESC_COUNTER(VM, inject_service_signal),
+	STATS_DESC_COUNTER(VM, inject_virtio)
+};
+static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
+		sizeof(struct kvm_vm_stat) / sizeof(u64));
+
+const struct kvm_stats_header kvm_vm_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
+	.id_offset = sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vm_stats_desc),
+};
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("userspace_handled", exit_userspace),
 	VCPU_STAT("exit_null", exit_null),

arch/x86/kvm/x86.c

@@ -223,6 +223,31 @@ EXPORT_SYMBOL_GPL(host_xss);
 u64 __read_mostly supported_xss;
 EXPORT_SYMBOL_GPL(supported_xss);
 
+const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
+	KVM_GENERIC_VM_STATS(),
+	STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
+	STATS_DESC_COUNTER(VM, mmu_pte_write),
+	STATS_DESC_COUNTER(VM, mmu_pde_zapped),
+	STATS_DESC_COUNTER(VM, mmu_flooded),
+	STATS_DESC_COUNTER(VM, mmu_recycled),
+	STATS_DESC_COUNTER(VM, mmu_cache_miss),
+	STATS_DESC_ICOUNTER(VM, mmu_unsync),
+	STATS_DESC_ICOUNTER(VM, lpages),
+	STATS_DESC_ICOUNTER(VM, nx_lpage_splits),
+	STATS_DESC_ICOUNTER(VM, max_mmu_page_hash_collisions)
+};
+static_assert(ARRAY_SIZE(kvm_vm_stats_desc) ==
+		sizeof(struct kvm_vm_stat) / sizeof(u64));
+
+const struct kvm_stats_header kvm_vm_stats_header = {
+	.name_size = KVM_STATS_NAME_SIZE,
+	.num_desc = ARRAY_SIZE(kvm_vm_stats_desc),
+	.id_offset = sizeof(struct kvm_stats_header),
+	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
+	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
+		       sizeof(kvm_vm_stats_desc),
+};
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	VCPU_STAT("pf_fixed", pf_fixed),
 	VCPU_STAT("pf_guest", pf_guest),

include/linux/kvm_host.h

@@ -599,6 +599,7 @@ struct kvm {
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 	struct notifier_block pm_notifier;
 #endif
+	char stats_id[KVM_STATS_NAME_SIZE];
 };
 
 #define kvm_err(fmt, ...) \
@@ -1354,12 +1355,17 @@ struct _kvm_stats_desc {
 	STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS,	       \
 		KVM_STATS_BASE_POW10, -9)
 
+#define KVM_GENERIC_VM_STATS()						       \
+	STATS_DESC_COUNTER(VM_GENERIC, remote_tlb_flush)
+
 extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
 		       const struct _kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
 		       char __user *user_buffer, size_t size, loff_t *offset);
+extern const struct kvm_stats_header kvm_vm_stats_header;
+extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)

virt/kvm/kvm_main.c

@@ -4055,6 +4055,42 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 	}
 }
 
+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)
 {
@@ -4237,6 +4273,9 @@ static long kvm_vm_ioctl(struct file *filp,
 	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);
 	}
@@ -4316,6 +4355,9 @@ static int kvm_dev_ioctl_create_vm(unsigned long type)
 	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);