KVM: stats: Add fd-based API to read binary stats data

This commit defines the API for userspace and prepare the common
functionalities to support per VM/VCPU binary stats data readings.

The KVM stats now is only accessible by debugfs, which has some
shortcomings this change series are supposed to fix:
1. The current debugfs stats solution in KVM could be disabled
   when kernel Lockdown mode is enabled, which is a potential
   rick for production.
2. The current debugfs stats solution in KVM is organized as "one
   stats per file", it is good for debugging, but not efficient
   for production.
3. The stats read/clear in current debugfs solution in KVM are
   protected by the global kvm_lock.

Besides that, there are some other benefits with this change:
1. All KVM VM/VCPU stats can be read out in a bulk by one copy
   to userspace.
2. A schema is used to describe KVM statistics. From userspace's
   perspective, the KVM statistics are self-describing.
3. With the fd-based solution, a separate telemetry would be able
   to read KVM stats in a less privileged environment.
4. After the initial setup by reading in stats descriptors, a
   telemetry only needs to read the stats data itself, no more
   parsing or setup is needed.

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: <20210618222709.1858088-3-jingzhangos@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 80 insertions, 2 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 37cbb56ccd09..9ee7f350473b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1272,16 +1272,94 @@ struct kvm_stats_debugfs_item {
 	int mode;
 };
 
+struct _kvm_stats_desc {
+	struct kvm_stats_desc desc;
+	char name[KVM_STATS_NAME_SIZE];
+};
+
 #define KVM_DBGFS_GET_MODE(dbgfs_item)                                         \
 	((dbgfs_item)->mode ? (dbgfs_item)->mode : 0644)
 
-#define VM_STAT(n, x, ...) 							\
+#define VM_STAT(n, x, ...)						       \
 	{ n, offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__ }
-#define VCPU_STAT(n, x, ...)							\
+#define VCPU_STAT(n, x, ...)						       \
 	{ n, offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__ }
 
+#define STATS_DESC_COMMON(type, unit, base, exp)			       \
+	.flags = type | unit | base |					       \
+		 BUILD_BUG_ON_ZERO(type & ~KVM_STATS_TYPE_MASK) |	       \
+		 BUILD_BUG_ON_ZERO(unit & ~KVM_STATS_UNIT_MASK) |	       \
+		 BUILD_BUG_ON_ZERO(base & ~KVM_STATS_BASE_MASK),	       \
+	.exponent = exp,						       \
+	.size = 1
+
+#define VM_GENERIC_STATS_DESC(stat, type, unit, base, exp)		       \
+	{								       \
+		{							       \
+			STATS_DESC_COMMON(type, unit, base, exp),	       \
+			.offset = offsetof(struct kvm_vm_stat, generic.stat)   \
+		},							       \
+		.name = #stat,						       \
+	}
+#define VCPU_GENERIC_STATS_DESC(stat, type, unit, base, exp)		       \
+	{								       \
+		{							       \
+			STATS_DESC_COMMON(type, unit, base, exp),	       \
+			.offset = offsetof(struct kvm_vcpu_stat, generic.stat) \
+		},							       \
+		.name = #stat,						       \
+	}
+#define VM_STATS_DESC(stat, type, unit, base, exp)			       \
+	{								       \
+		{							       \
+			STATS_DESC_COMMON(type, unit, base, exp),	       \
+			.offset = offsetof(struct kvm_vm_stat, stat)	       \
+		},							       \
+		.name = #stat,						       \
+	}
+#define VCPU_STATS_DESC(stat, type, unit, base, exp)			       \
+	{								       \
+		{							       \
+			STATS_DESC_COMMON(type, unit, base, exp),	       \
+			.offset = offsetof(struct kvm_vcpu_stat, stat)	       \
+		},							       \
+		.name = #stat,						       \
+	}
+/* SCOPE: VM, VM_GENERIC, VCPU, VCPU_GENERIC */
+#define STATS_DESC(SCOPE, stat, type, unit, base, exp)			       \
+	SCOPE##_STATS_DESC(stat, type, unit, base, exp)
+
+#define STATS_DESC_CUMULATIVE(SCOPE, name, unit, base, exponent)	       \
+	STATS_DESC(SCOPE, name, KVM_STATS_TYPE_CUMULATIVE, unit, base, exponent)
+#define STATS_DESC_INSTANT(SCOPE, name, unit, base, exponent)		       \
+	STATS_DESC(SCOPE, name, KVM_STATS_TYPE_INSTANT, unit, base, exponent)
+#define STATS_DESC_PEAK(SCOPE, name, unit, base, exponent)		       \
+	STATS_DESC(SCOPE, name, KVM_STATS_TYPE_PEAK, unit, base, exponent)
+
+/* Cumulative counter, read/write */
+#define STATS_DESC_COUNTER(SCOPE, name)					       \
+	STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_NONE,		       \
+		KVM_STATS_BASE_POW10, 0)
+/* Instantaneous counter, read only */
+#define STATS_DESC_ICOUNTER(SCOPE, name)				       \
+	STATS_DESC_INSTANT(SCOPE, name, KVM_STATS_UNIT_NONE,		       \
+		KVM_STATS_BASE_POW10, 0)
+/* Peak counter, read/write */
+#define STATS_DESC_PCOUNTER(SCOPE, name)				       \
+	STATS_DESC_PEAK(SCOPE, name, KVM_STATS_UNIT_NONE,		       \
+		KVM_STATS_BASE_POW10, 0)
+
+/* Cumulative time in nanosecond */
+#define STATS_DESC_TIME_NSEC(SCOPE, name)				       \
+	STATS_DESC_CUMULATIVE(SCOPE, name, KVM_STATS_UNIT_SECONDS,	       \
+		KVM_STATS_BASE_POW10, -9)
+
 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);
 
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq)