KVM: PPC: Book3S HV: XIVE: Add controls for the EQ configuration

These controls will be used by the H_INT_SET_QUEUE_CONFIG and
H_INT_GET_QUEUE_CONFIG hcalls from QEMU to configure the underlying
Event Queue in the XIVE IC. They will also be used to restore the
configuration of the XIVE EQs and to capture the internal run-time
state of the EQs. Both 'get' and 'set' rely on an OPAL call to access
the EQ toggle bit and EQ index which are updated by the XIVE IC when
event notifications are enqueued in the EQ.

The value of the guest physical address of the event queue is saved in
the XIVE internal xive_q structure for later use. That is when
migration needs to mark the EQ pages dirty to capture a consistent
memory state of the VM.

To be noted that H_INT_SET_QUEUE_CONFIG does not require the extra
OPAL call setting the EQ toggle bit and EQ index to configure the EQ,
but restoring the EQ state will.

Signed-off-by: Cédric Le Goater <[email protected]>
Reviewed-by: David Gibson <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>

Author: legoater

Documentation/virtual/kvm/devices/xive.txt

@@ -53,3 +53,37 @@ the legacy interrupt mode, referred as XICS (POWER7/8).
     -ENXIO:  CPU event queues not configured or configuration of the
              underlying HW interrupt failed
     -EBUSY:  No CPU available to serve interrupt
+
+  4. KVM_DEV_XIVE_GRP_EQ_CONFIG (read-write)
+  Configures an event queue of a CPU
+  Attributes:
+    EQ descriptor identifier (64-bit)
+  The EQ descriptor identifier is a tuple (server, priority) :
+  bits:     | 63   ....  32 | 31 .. 3 |  2 .. 0
+  values:   |    unused     |  server | priority
+  The kvm_device_attr.addr points to :
+    struct kvm_ppc_xive_eq {
+	__u32 flags;
+	__u32 qshift;
+	__u64 qaddr;
+	__u32 qtoggle;
+	__u32 qindex;
+	__u8  pad[40];
+    };
+  - flags: queue flags
+    KVM_XIVE_EQ_ALWAYS_NOTIFY (required)
+	forces notification without using the coalescing mechanism
+	provided by the XIVE END ESBs.
+  - qshift: queue size (power of 2)
+  - qaddr: real address of queue
+  - qtoggle: current queue toggle bit
+  - qindex: current queue index
+  - pad: reserved for future use
+  Errors:
+    -ENOENT: Invalid CPU number
+    -EINVAL: Invalid priority
+    -EINVAL: Invalid flags
+    -EINVAL: Invalid queue size
+    -EINVAL: Invalid queue address
+    -EFAULT: Invalid user pointer for attr->addr.
+    -EIO:    Configuration of the underlying HW failed

arch/powerpc/include/asm/xive.h

@@ -73,6 +73,8 @@ struct xive_q {
 	u32			esc_irq;
 	atomic_t		count;
 	atomic_t		pending_count;
+	u64			guest_qaddr;
+	u32			guest_qshift;
 };
 
 /* Global enable flags for the XIVE support */

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

@@ -681,6 +681,7 @@ struct kvm_ppc_cpu_char {
 #define KVM_DEV_XIVE_GRP_CTRL		1
 #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 */
 
 /* Layout of 64-bit XIVE source attribute values */
 #define KVM_XIVE_LEVEL_SENSITIVE	(1ULL << 0)
@@ -696,4 +697,22 @@ struct kvm_ppc_cpu_char {
 #define KVM_XIVE_SOURCE_EISN_SHIFT	33
 #define KVM_XIVE_SOURCE_EISN_MASK	0xfffffffe00000000ULL
 
+/* Layout of 64-bit EQ identifier */
+#define KVM_XIVE_EQ_PRIORITY_SHIFT	0
+#define KVM_XIVE_EQ_PRIORITY_MASK	0x7
+#define KVM_XIVE_EQ_SERVER_SHIFT	3
+#define KVM_XIVE_EQ_SERVER_MASK		0xfffffff8ULL
+
+/* Layout of EQ configuration values (64 bytes) */
+struct kvm_ppc_xive_eq {
+	__u32 flags;
+	__u32 qshift;
+	__u64 qaddr;
+	__u32 qtoggle;
+	__u32 qindex;
+	__u8  pad[40];
+};
+
+#define KVM_XIVE_EQ_ALWAYS_NOTIFY	0x00000001
+
 #endif /* __LINUX_KVM_POWERPC_H */

arch/powerpc/kvm/book3s_xive.c

@@ -166,7 +166,8 @@ static irqreturn_t xive_esc_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
+int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
+				  bool single_escalation)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
 	struct xive_q *q = &xc->queues[prio];
@@ -185,7 +186,7 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
 		return -EIO;
 	}
 
-	if (xc->xive->single_escalation)
+	if (single_escalation)
 		name = kasprintf(GFP_KERNEL, "kvm-%d-%d",
 				 vcpu->kvm->arch.lpid, xc->server_num);
 	else
@@ -217,7 +218,7 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
 	 * interrupt, thus leaving it effectively masked after
 	 * it fires once.
 	 */
-	if (xc->xive->single_escalation) {
+	if (single_escalation) {
 		struct irq_data *d = irq_get_irq_data(xc->esc_virq[prio]);
 		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
 
@@ -291,7 +292,8 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio)
 			continue;
 		rc = xive_provision_queue(vcpu, prio);
 		if (rc == 0 && !xive->single_escalation)
-			xive_attach_escalation(vcpu, prio);
+			kvmppc_xive_attach_escalation(vcpu, prio,
+						      xive->single_escalation);
 		if (rc)
 			return rc;
 	}
@@ -1214,7 +1216,8 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		if (xive->qmap & (1 << i)) {
 			r = xive_provision_queue(vcpu, i);
 			if (r == 0 && !xive->single_escalation)
-				xive_attach_escalation(vcpu, i);
+				kvmppc_xive_attach_escalation(
+					vcpu, i, xive->single_escalation);
 			if (r)
 				goto bail;
 		} else {
@@ -1229,7 +1232,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	}
 
 	/* If not done above, attach priority 0 escalation */
-	r = xive_attach_escalation(vcpu, 0);
+	r = kvmppc_xive_attach_escalation(vcpu, 0, xive->single_escalation);
 	if (r)
 		goto bail;
 

arch/powerpc/kvm/book3s_xive.h

@@ -272,6 +272,8 @@ struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
 	struct kvmppc_xive *xive, int irq);
 void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb);
 int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio);
+int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
+				  bool single_escalation);
 
 #endif /* CONFIG_KVM_XICS */
 #endif /* _KVM_PPC_BOOK3S_XICS_H */