KVM: PPC: Book3S HV: XIVE: Allow userspace to set the # of VPs

Add a new attribute to both XIVE and XICS-on-XIVE KVM devices so that
userspace can tell how many interrupt servers it needs. If a VM needs
less than the current default of KVM_MAX_VCPUS (2048), we can allocate
less VPs in OPAL. Combined with a core stride (VSMT) that matches the
number of guest threads per core, this may substantially increases the
number of VMs that can run concurrently with an in-kernel XIVE device.

Since the legacy XIVE KVM device is exposed to userspace through the
XICS KVM API, a new attribute group is added to it for this purpose.
While here, fix the syntax of the existing KVM_DEV_XICS_GRP_SOURCES
in the XICS documentation.
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>

Documentation/virt/kvm/devices/xics.txt

@@ -3,9 +3,19 @@ XICS interrupt controller
 Device type supported: KVM_DEV_TYPE_XICS
 
 Groups:
-  KVM_DEV_XICS_SOURCES
+  1. KVM_DEV_XICS_GRP_SOURCES
   Attributes: One per interrupt source, indexed by the source number.
 
+  2. KVM_DEV_XICS_GRP_CTRL
+  Attributes:
+    2.1 KVM_DEV_XICS_NR_SERVERS (write only)
+  The kvm_device_attr.addr points to a __u32 value which is the number of
+  interrupt server numbers (ie, highest possible vcpu id plus one).
+  Errors:
+    -EINVAL: Value greater than KVM_MAX_VCPU_ID.
+    -EFAULT: Invalid user pointer for attr->addr.
+    -EBUSY:  A vcpu is already connected to the device.
+
 This device emulates the XICS (eXternal Interrupt Controller
 Specification) defined in PAPR.  The XICS has a set of interrupt
 sources, each identified by a 20-bit source number, and a set of
@@ -38,7 +48,7 @@ least-significant end of the word:
 
 Each source has 64 bits of state that can be read and written using
 the KVM_GET_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls, specifying the
-KVM_DEV_XICS_SOURCES attribute group, with the attribute number being
+KVM_DEV_XICS_GRP_SOURCES attribute group, with the attribute number being
 the interrupt source number.  The 64 bit state word has the following
 bitfields, starting from the least-significant end of the word:
 

Documentation/virt/kvm/devices/xive.txt

@@ -78,6 +78,14 @@ the legacy interrupt mode, referred as XICS (POWER7/8).
     migrating the VM.
     Errors: none
 
+    1.3 KVM_DEV_XIVE_NR_SERVERS (write only)
+    The kvm_device_attr.addr points to a __u32 value which is the number of
+    interrupt server numbers (ie, highest possible vcpu id plus one).
+    Errors:
+      -EINVAL: Value greater than KVM_MAX_VCPU_ID.
+      -EFAULT: Invalid user pointer for attr->addr.
+      -EBUSY:  A vCPU is already connected to the device.
+
   2. KVM_DEV_XIVE_GRP_SOURCE (write only)
   Initializes a new source in the XIVE device and mask it.
   Attributes:

arch/powerpc/include/uapi/asm/kvm.h

@@ -667,6 +667,8 @@ struct kvm_ppc_cpu_char {
 
 /* PPC64 eXternal Interrupt Controller Specification */
 #define KVM_DEV_XICS_GRP_SOURCES	1	/* 64-bit source attributes */
+#define KVM_DEV_XICS_GRP_CTRL		2
+#define   KVM_DEV_XICS_NR_SERVERS	1
 
 /* Layout of 64-bit source attribute values */
 #define  KVM_XICS_DESTINATION_SHIFT	0
@@ -683,6 +685,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_DEV_XIVE_GRP_CTRL		1
 #define   KVM_DEV_XIVE_RESET		1
 #define   KVM_DEV_XIVE_EQ_SYNC		2
+#define   KVM_DEV_XIVE_NR_SERVERS	3
 #define KVM_DEV_XIVE_GRP_SOURCE		2	/* 64-bit source identifier */
 #define KVM_DEV_XIVE_GRP_SOURCE_CONFIG	3	/* 64-bit source identifier */
 #define KVM_DEV_XIVE_GRP_EQ_CONFIG	4	/* 64-bit EQ identifier */

arch/powerpc/kvm/book3s_xive.c

@@ -1911,6 +1911,11 @@ static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 	switch (attr->group) {
 	case KVM_DEV_XICS_GRP_SOURCES:
 		return xive_set_source(xive, attr->attr, attr->addr);
+	case KVM_DEV_XICS_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XICS_NR_SERVERS:
+			return kvmppc_xive_set_nr_servers(xive, attr->addr);
+		}
 	}
 	return -ENXIO;
 }
@@ -1936,6 +1941,11 @@ static int xive_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
 		    attr->attr < KVMPPC_XICS_NR_IRQS)
 			return 0;
 		break;
+	case KVM_DEV_XICS_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XICS_NR_SERVERS:
+			return 0;
+		}
 	}
 	return -ENXIO;
 }

arch/powerpc/kvm/book3s_xive_native.c

@@ -921,6 +921,8 @@ static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
 			return kvmppc_xive_reset(xive);
 		case KVM_DEV_XIVE_EQ_SYNC:
 			return kvmppc_xive_native_eq_sync(xive);
+		case KVM_DEV_XIVE_NR_SERVERS:
+			return kvmppc_xive_set_nr_servers(xive, attr->addr);
 		}
 		break;
 	case KVM_DEV_XIVE_GRP_SOURCE:
@@ -960,6 +962,7 @@ static int kvmppc_xive_native_has_attr(struct kvm_device *dev,
 		switch (attr->attr) {
 		case KVM_DEV_XIVE_RESET:
 		case KVM_DEV_XIVE_EQ_SYNC:
+		case KVM_DEV_XIVE_NR_SERVERS:
 			return 0;
 		}
 		break;