KVM: s390: deliver floating interrupts in order of priority

This patch makes interrupt handling compliant to the z/Architecture
Principles of Operation with regard to interrupt priorities.

Add a bitmap for pending floating interrupts. Each bit relates to a
interrupt type and its list. A turned on bit indicates that a list
contains items (interrupts) which need to be delivered.  When delivering
interrupts on a cpu we can merge the existing bitmap for cpu-local
interrupts and floating interrupts and have a single mechanism for
delivery.
Currently we have one list for all kinds of floating interrupts and a
corresponding spin lock. This patch adds a separate list per
interrupt type. An exception to this are service signal and machine check
interrupts, as there can be only one pending interrupt at a time.
Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>

arch/s390/include/asm/kvm_host.h

@@ -344,6 +344,11 @@ enum irq_types {
 	IRQ_PEND_COUNT
 };
 
+/* We have 2M for virtio device descriptor pages. Smallest amount of
+ * memory per page is 24 bytes (1 queue), so (2048*1024) / 24 = 87381
+ */
+#define KVM_S390_MAX_VIRTIO_IRQS 87381
+
 /*
  * Repressible (non-floating) machine check interrupts
  * subclass bits in MCIC
@@ -421,13 +426,32 @@ struct kvm_s390_local_interrupt {
 	unsigned long pending_irqs;
 };
 
+#define FIRQ_LIST_IO_ISC_0 0
+#define FIRQ_LIST_IO_ISC_1 1
+#define FIRQ_LIST_IO_ISC_2 2
+#define FIRQ_LIST_IO_ISC_3 3
+#define FIRQ_LIST_IO_ISC_4 4
+#define FIRQ_LIST_IO_ISC_5 5
+#define FIRQ_LIST_IO_ISC_6 6
+#define FIRQ_LIST_IO_ISC_7 7
+#define FIRQ_LIST_PFAULT   8
+#define FIRQ_LIST_VIRTIO   9
+#define FIRQ_LIST_COUNT   10
+#define FIRQ_CNTR_IO       0
+#define FIRQ_CNTR_SERVICE  1
+#define FIRQ_CNTR_VIRTIO   2
+#define FIRQ_CNTR_PFAULT   3
+#define FIRQ_MAX_COUNT     4
+
 struct kvm_s390_float_interrupt {
+	unsigned long pending_irqs;
 	spinlock_t lock;
-	struct list_head list;
-	atomic_t active;
+	struct list_head lists[FIRQ_LIST_COUNT];
+	int counters[FIRQ_MAX_COUNT];
+	struct kvm_s390_mchk_info mchk;
+	struct kvm_s390_ext_info srv_signal;
 	int next_rr_cpu;
 	unsigned long idle_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
-	unsigned int irq_count;
 };
 
 struct kvm_hw_wp_info_arch {

arch/s390/kvm/kvm-s390.c

@@ -31,6 +31,7 @@
 #include <asm/pgtable.h>
 #include <asm/nmi.h>
 #include <asm/switch_to.h>
+#include <asm/isc.h>
 #include <asm/sclp.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
@@ -1069,7 +1070,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		goto out_err;
 
 	spin_lock_init(&kvm->arch.float_int.lock);
-	INIT_LIST_HEAD(&kvm->arch.float_int.list);
+	for (i = 0; i < FIRQ_LIST_COUNT; i++)
+		INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
 	init_waitqueue_head(&kvm->arch.ipte_wq);
 	mutex_init(&kvm->arch.ipte_mutex);
 

arch/s390/kvm/kvm-s390.h

@@ -178,7 +178,7 @@ int __must_check kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 				      struct kvm_s390_irq *irq);
 int __must_check kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
-						    u64 cr6, u64 schid);
+						    u64 isc_mask, u32 schid);
 int kvm_s390_reinject_io_int(struct kvm *kvm,
 			     struct kvm_s390_interrupt_info *inti);
 int kvm_s390_mask_adapter(struct kvm *kvm, unsigned int id, bool masked);

arch/s390/kvm/priv.c

@@ -294,10 +294,13 @@ static int handle_tpi(struct kvm_vcpu *vcpu)
 
 static int handle_tsch(struct kvm_vcpu *vcpu)
 {
-	struct kvm_s390_interrupt_info *inti;
+	struct kvm_s390_interrupt_info *inti = NULL;
+	const u64 isc_mask = 0xffUL << 24; /* all iscs set */
 
-	inti = kvm_s390_get_io_int(vcpu->kvm, 0,
-				   vcpu->run->s.regs.gprs[1]);
+	/* a valid schid has at least one bit set */
+	if (vcpu->run->s.regs.gprs[1])
+		inti = kvm_s390_get_io_int(vcpu->kvm, isc_mask,
+					   vcpu->run->s.regs.gprs[1]);
 
 	/*
 	 * Prepare exit to userspace.