Browse Source

Merge tag 'kvm-s390-20140304' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into kvm-next

Paolo Bonzini 11 years ago
parent
commit
a2fa301fdd

+ 12 - 2
arch/s390/include/asm/airq.h

@@ -44,11 +44,21 @@ struct airq_iv {
 
 struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
 void airq_iv_release(struct airq_iv *iv);
-unsigned long airq_iv_alloc_bit(struct airq_iv *iv);
-void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit);
+unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num);
+void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num);
 unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start,
 			   unsigned long end);
 
+static inline unsigned long airq_iv_alloc_bit(struct airq_iv *iv)
+{
+	return airq_iv_alloc(iv, 1);
+}
+
+static inline void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit)
+{
+	airq_iv_free(iv, bit, 1);
+}
+
 static inline unsigned long airq_iv_end(struct airq_iv *iv)
 {
 	return iv->end;

+ 1 - 0
arch/s390/include/asm/irq.h

@@ -53,6 +53,7 @@ enum interruption_class {
 	IRQIO_PCI,
 	IRQIO_MSI,
 	IRQIO_VIR,
+	IRQIO_VAI,
 	NMI_NMI,
 	CPU_RST,
 	NR_ARCH_IRQS

+ 3 - 2
arch/s390/include/asm/kvm_host.h

@@ -107,7 +107,9 @@ struct kvm_s390_sie_block {
 	__u64	gbea;			/* 0x0180 */
 	__u8	reserved188[24];	/* 0x0188 */
 	__u32	fac;			/* 0x01a0 */
-	__u8	reserved1a4[68];	/* 0x01a4 */
+	__u8	reserved1a4[58];	/* 0x01a4 */
+	__u64	pp;			/* 0x01de */
+	__u8	reserved1e6[2];		/* 0x01e6 */
 	__u64	itdba;			/* 0x01e8 */
 	__u8	reserved1f0[16];	/* 0x01f0 */
 } __attribute__((packed));
@@ -213,7 +215,6 @@ struct kvm_s390_float_interrupt {
 	int next_rr_cpu;
 	unsigned long idle_mask[(KVM_MAX_VCPUS + sizeof(long) - 1)
 				/ sizeof(long)];
-	struct kvm_s390_local_interrupt *local_int[KVM_MAX_VCPUS];
 	unsigned int irq_count;
 };
 

+ 2 - 0
arch/s390/include/uapi/asm/kvm.h

@@ -76,4 +76,6 @@ struct kvm_sync_regs {
 #define KVM_REG_S390_PFTOKEN	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x5)
 #define KVM_REG_S390_PFCOMPARE	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x6)
 #define KVM_REG_S390_PFSELECT	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x7)
+#define KVM_REG_S390_PP		(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x8)
+#define KVM_REG_S390_GBEA	(KVM_REG_S390 | KVM_REG_SIZE_U64 | 0x9)
 #endif

+ 1 - 0
arch/s390/kernel/irq.c

@@ -84,6 +84,7 @@ static const struct irq_class irqclass_sub_desc[NR_ARCH_IRQS] = {
 	[IRQIO_PCI]  = {.name = "PCI", .desc = "[I/O] PCI Interrupt" },
 	[IRQIO_MSI]  = {.name = "MSI", .desc = "[I/O] MSI Interrupt" },
 	[IRQIO_VIR]  = {.name = "VIR", .desc = "[I/O] Virtual I/O Devices"},
+	[IRQIO_VAI]  = {.name = "VAI", .desc = "[I/O] Virtual I/O Devices AI"},
 	[NMI_NMI]    = {.name = "NMI", .desc = "[NMI] Machine Check"},
 	[CPU_RST]    = {.name = "RST", .desc = "[CPU] CPU Restart"},
 };

+ 4 - 2
arch/s390/kvm/interrupt.c

@@ -692,6 +692,7 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 	struct kvm_s390_local_interrupt *li;
 	struct kvm_s390_float_interrupt *fi;
 	struct kvm_s390_interrupt_info *iter;
+	struct kvm_vcpu *dst_vcpu = NULL;
 	int sigcpu;
 	int rc = 0;
 
@@ -726,9 +727,10 @@ static int __inject_vm(struct kvm *kvm, struct kvm_s390_interrupt_info *inti)
 			sigcpu = fi->next_rr_cpu++;
 			if (sigcpu == KVM_MAX_VCPUS)
 				sigcpu = fi->next_rr_cpu = 0;
-		} while (fi->local_int[sigcpu] == NULL);
+		} while (kvm_get_vcpu(kvm, sigcpu) == NULL);
 	}
-	li = fi->local_int[sigcpu];
+	dst_vcpu = kvm_get_vcpu(kvm, sigcpu);
+	li = &dst_vcpu->arch.local_int;
 	spin_lock_bh(&li->lock);
 	atomic_set_mask(CPUSTAT_EXT_INT, li->cpuflags);
 	if (waitqueue_active(li->wq))

+ 18 - 4
arch/s390/kvm/kvm-s390.c

@@ -386,6 +386,7 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.guest_fpregs.fpc = 0;
 	asm volatile("lfpc %0" : : "Q" (vcpu->arch.guest_fpregs.fpc));
 	vcpu->arch.sie_block->gbea = 1;
+	vcpu->arch.sie_block->pp = 0;
 	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
 	kvm_clear_async_pf_completion_queue(vcpu);
 	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
@@ -459,11 +460,8 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	spin_lock_init(&vcpu->arch.local_int.lock);
 	INIT_LIST_HEAD(&vcpu->arch.local_int.list);
 	vcpu->arch.local_int.float_int = &kvm->arch.float_int;
-	spin_lock(&kvm->arch.float_int.lock);
-	kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
 	vcpu->arch.local_int.wq = &vcpu->wq;
 	vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
-	spin_unlock(&kvm->arch.float_int.lock);
 
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
@@ -571,6 +569,14 @@ static int kvm_arch_vcpu_ioctl_get_one_reg(struct kvm_vcpu *vcpu,
 		r = put_user(vcpu->arch.pfault_select,
 			     (u64 __user *)reg->addr);
 		break;
+	case KVM_REG_S390_PP:
+		r = put_user(vcpu->arch.sie_block->pp,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_GBEA:
+		r = put_user(vcpu->arch.sie_block->gbea,
+			     (u64 __user *)reg->addr);
+		break;
 	default:
 		break;
 	}
@@ -612,6 +618,14 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
 		r = get_user(vcpu->arch.pfault_select,
 			     (u64 __user *)reg->addr);
 		break;
+	case KVM_REG_S390_PP:
+		r = get_user(vcpu->arch.sie_block->pp,
+			     (u64 __user *)reg->addr);
+		break;
+	case KVM_REG_S390_GBEA:
+		r = get_user(vcpu->arch.sie_block->gbea,
+			     (u64 __user *)reg->addr);
+		break;
 	default:
 		break;
 	}
@@ -935,7 +949,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 
-	BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);
+	BUG_ON(kvm_get_vcpu(vcpu->kvm, vcpu->vcpu_id) == NULL);
 
 	switch (kvm_run->exit_reason) {
 	case KVM_EXIT_S390_SIEIC:

+ 1 - 6
arch/s390/kvm/priv.c

@@ -396,15 +396,10 @@ static int handle_stidp(struct kvm_vcpu *vcpu)
 
 static void handle_stsi_3_2_2(struct kvm_vcpu *vcpu, struct sysinfo_3_2_2 *mem)
 {
-	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	int cpus = 0;
 	int n;
 
-	spin_lock(&fi->lock);
-	for (n = 0; n < KVM_MAX_VCPUS; n++)
-		if (fi->local_int[n])
-			cpus++;
-	spin_unlock(&fi->lock);
+	cpus = atomic_read(&vcpu->kvm->online_vcpus);
 
 	/* deal with other level 3 hypervisors */
 	if (stsi(mem, 3, 2, 2))

+ 59 - 89
arch/s390/kvm/sigp.c

@@ -23,29 +23,30 @@
 static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
 			u64 *reg)
 {
-	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_vcpu *dst_vcpu = NULL;
+	int cpuflags;
 	int rc;
 
 	if (cpu_addr >= KVM_MAX_VCPUS)
 		return SIGP_CC_NOT_OPERATIONAL;
 
-	spin_lock(&fi->lock);
-	if (fi->local_int[cpu_addr] == NULL)
-		rc = SIGP_CC_NOT_OPERATIONAL;
-	else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags)
-		   & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED)))
+	dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+	if (!dst_vcpu)
+		return SIGP_CC_NOT_OPERATIONAL;
+	li = &dst_vcpu->arch.local_int;
+
+	cpuflags = atomic_read(li->cpuflags);
+	if (!(cpuflags & (CPUSTAT_ECALL_PEND | CPUSTAT_STOPPED)))
 		rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 	else {
 		*reg &= 0xffffffff00000000UL;
-		if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
-		    & CPUSTAT_ECALL_PEND)
+		if (cpuflags & CPUSTAT_ECALL_PEND)
 			*reg |= SIGP_STATUS_EXT_CALL_PENDING;
-		if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
-		    & CPUSTAT_STOPPED)
+		if (cpuflags & CPUSTAT_STOPPED)
 			*reg |= SIGP_STATUS_STOPPED;
 		rc = SIGP_CC_STATUS_STORED;
 	}
-	spin_unlock(&fi->lock);
 
 	VCPU_EVENT(vcpu, 4, "sensed status of cpu %x rc %x", cpu_addr, rc);
 	return rc;
@@ -53,10 +54,9 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
 
 static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
 {
-	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	struct kvm_s390_local_interrupt *li;
 	struct kvm_s390_interrupt_info *inti;
-	int rc;
+	struct kvm_vcpu *dst_vcpu = NULL;
 
 	if (cpu_addr >= KVM_MAX_VCPUS)
 		return SIGP_CC_NOT_OPERATIONAL;
@@ -68,13 +68,10 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
 	inti->type = KVM_S390_INT_EMERGENCY;
 	inti->emerg.code = vcpu->vcpu_id;
 
-	spin_lock(&fi->lock);
-	li = fi->local_int[cpu_addr];
-	if (li == NULL) {
-		rc = SIGP_CC_NOT_OPERATIONAL;
-		kfree(inti);
-		goto unlock;
-	}
+	dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+	if (!dst_vcpu)
+		return SIGP_CC_NOT_OPERATIONAL;
+	li = &dst_vcpu->arch.local_int;
 	spin_lock_bh(&li->lock);
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
@@ -82,11 +79,9 @@ static int __sigp_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr)
 	if (waitqueue_active(li->wq))
 		wake_up_interruptible(li->wq);
 	spin_unlock_bh(&li->lock);
-	rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 	VCPU_EVENT(vcpu, 4, "sent sigp emerg to cpu %x", cpu_addr);
-unlock:
-	spin_unlock(&fi->lock);
-	return rc;
+
+	return SIGP_CC_ORDER_CODE_ACCEPTED;
 }
 
 static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr,
@@ -122,10 +117,9 @@ static int __sigp_conditional_emergency(struct kvm_vcpu *vcpu, u16 cpu_addr,
 
 static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
 {
-	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	struct kvm_s390_local_interrupt *li;
 	struct kvm_s390_interrupt_info *inti;
-	int rc;
+	struct kvm_vcpu *dst_vcpu = NULL;
 
 	if (cpu_addr >= KVM_MAX_VCPUS)
 		return SIGP_CC_NOT_OPERATIONAL;
@@ -137,13 +131,10 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
 	inti->type = KVM_S390_INT_EXTERNAL_CALL;
 	inti->extcall.code = vcpu->vcpu_id;
 
-	spin_lock(&fi->lock);
-	li = fi->local_int[cpu_addr];
-	if (li == NULL) {
-		rc = SIGP_CC_NOT_OPERATIONAL;
-		kfree(inti);
-		goto unlock;
-	}
+	dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+	if (!dst_vcpu)
+		return SIGP_CC_NOT_OPERATIONAL;
+	li = &dst_vcpu->arch.local_int;
 	spin_lock_bh(&li->lock);
 	list_add_tail(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
@@ -151,11 +142,9 @@ static int __sigp_external_call(struct kvm_vcpu *vcpu, u16 cpu_addr)
 	if (waitqueue_active(li->wq))
 		wake_up_interruptible(li->wq);
 	spin_unlock_bh(&li->lock);
-	rc = SIGP_CC_ORDER_CODE_ACCEPTED;
 	VCPU_EVENT(vcpu, 4, "sent sigp ext call to cpu %x", cpu_addr);
-unlock:
-	spin_unlock(&fi->lock);
-	return rc;
+
+	return SIGP_CC_ORDER_CODE_ACCEPTED;
 }
 
 static int __inject_sigp_stop(struct kvm_s390_local_interrupt *li, int action)
@@ -189,31 +178,26 @@ out:
 
 static int __sigp_stop(struct kvm_vcpu *vcpu, u16 cpu_addr, int action)
 {
-	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	struct kvm_s390_local_interrupt *li;
+	struct kvm_vcpu *dst_vcpu = NULL;
 	int rc;
 
 	if (cpu_addr >= KVM_MAX_VCPUS)
 		return SIGP_CC_NOT_OPERATIONAL;
 
-	spin_lock(&fi->lock);
-	li = fi->local_int[cpu_addr];
-	if (li == NULL) {
-		rc = SIGP_CC_NOT_OPERATIONAL;
-		goto unlock;
-	}
+	dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+	if (!dst_vcpu)
+		return SIGP_CC_NOT_OPERATIONAL;
+	li = &dst_vcpu->arch.local_int;
 
 	rc = __inject_sigp_stop(li, action);
 
-unlock:
-	spin_unlock(&fi->lock);
 	VCPU_EVENT(vcpu, 4, "sent sigp stop to cpu %x", cpu_addr);
 
 	if ((action & ACTION_STORE_ON_STOP) != 0 && rc == -ESHUTDOWN) {
 		/* If the CPU has already been stopped, we still have
 		 * to save the status when doing stop-and-store. This
 		 * has to be done after unlocking all spinlocks. */
-		struct kvm_vcpu *dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
 		rc = kvm_s390_store_status_unloaded(dst_vcpu,
 						KVM_S390_STORE_STATUS_NOADDR);
 	}
@@ -249,12 +233,18 @@ static int __sigp_set_arch(struct kvm_vcpu *vcpu, u32 parameter)
 static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 			     u64 *reg)
 {
-	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
-	struct kvm_s390_local_interrupt *li = NULL;
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_vcpu *dst_vcpu = NULL;
 	struct kvm_s390_interrupt_info *inti;
 	int rc;
 	u8 tmp;
 
+	if (cpu_addr < KVM_MAX_VCPUS)
+		dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+	if (!dst_vcpu)
+		return SIGP_CC_NOT_OPERATIONAL;
+	li = &dst_vcpu->arch.local_int;
+
 	/* make sure that the new value is valid memory */
 	address = address & 0x7fffe000u;
 	if (copy_from_guest_absolute(vcpu, &tmp, address, 1) ||
@@ -268,18 +258,6 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 	if (!inti)
 		return SIGP_CC_BUSY;
 
-	spin_lock(&fi->lock);
-	if (cpu_addr < KVM_MAX_VCPUS)
-		li = fi->local_int[cpu_addr];
-
-	if (li == NULL) {
-		*reg &= 0xffffffff00000000UL;
-		*reg |= SIGP_STATUS_INCORRECT_STATE;
-		rc = SIGP_CC_STATUS_STORED;
-		kfree(inti);
-		goto out_fi;
-	}
-
 	spin_lock_bh(&li->lock);
 	/* cpu must be in stopped state */
 	if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
@@ -302,8 +280,6 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 	VCPU_EVENT(vcpu, 4, "set prefix of cpu %02x to %x", cpu_addr, address);
 out_li:
 	spin_unlock_bh(&li->lock);
-out_fi:
-	spin_unlock(&fi->lock);
 	return rc;
 }
 
@@ -341,28 +317,26 @@ static int __sigp_store_status_at_addr(struct kvm_vcpu *vcpu, u16 cpu_id,
 static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
 				u64 *reg)
 {
+	struct kvm_s390_local_interrupt *li;
+	struct kvm_vcpu *dst_vcpu = NULL;
 	int rc;
-	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 
 	if (cpu_addr >= KVM_MAX_VCPUS)
 		return SIGP_CC_NOT_OPERATIONAL;
 
-	spin_lock(&fi->lock);
-	if (fi->local_int[cpu_addr] == NULL)
-		rc = SIGP_CC_NOT_OPERATIONAL;
-	else {
-		if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
-		    & CPUSTAT_RUNNING) {
-			/* running */
-			rc = SIGP_CC_ORDER_CODE_ACCEPTED;
-		} else {
-			/* not running */
-			*reg &= 0xffffffff00000000UL;
-			*reg |= SIGP_STATUS_NOT_RUNNING;
-			rc = SIGP_CC_STATUS_STORED;
-		}
+	dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+	if (!dst_vcpu)
+		return SIGP_CC_NOT_OPERATIONAL;
+	li = &dst_vcpu->arch.local_int;
+	if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+		/* running */
+		rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+	} else {
+		/* not running */
+		*reg &= 0xffffffff00000000UL;
+		*reg |= SIGP_STATUS_NOT_RUNNING;
+		rc = SIGP_CC_STATUS_STORED;
 	}
-	spin_unlock(&fi->lock);
 
 	VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr,
 		   rc);
@@ -373,26 +347,22 @@ static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
 /* Test whether the destination CPU is available and not busy */
 static int sigp_check_callable(struct kvm_vcpu *vcpu, u16 cpu_addr)
 {
-	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
 	struct kvm_s390_local_interrupt *li;
 	int rc = SIGP_CC_ORDER_CODE_ACCEPTED;
+	struct kvm_vcpu *dst_vcpu = NULL;
 
 	if (cpu_addr >= KVM_MAX_VCPUS)
 		return SIGP_CC_NOT_OPERATIONAL;
 
-	spin_lock(&fi->lock);
-	li = fi->local_int[cpu_addr];
-	if (li == NULL) {
-		rc = SIGP_CC_NOT_OPERATIONAL;
-		goto out;
-	}
-
+	dst_vcpu = kvm_get_vcpu(vcpu->kvm, cpu_addr);
+	if (!dst_vcpu)
+		return SIGP_CC_NOT_OPERATIONAL;
+	li = &dst_vcpu->arch.local_int;
 	spin_lock_bh(&li->lock);
 	if (li->action_bits & ACTION_STOP_ON_STOP)
 		rc = SIGP_CC_BUSY;
 	spin_unlock_bh(&li->lock);
-out:
-	spin_unlock(&fi->lock);
+
 	return rc;
 }
 

+ 41 - 25
drivers/s390/cio/airq.c

@@ -186,55 +186,71 @@ void airq_iv_release(struct airq_iv *iv)
 EXPORT_SYMBOL(airq_iv_release);
 
 /**
- * airq_iv_alloc_bit - allocate an irq bit from an interrupt vector
+ * airq_iv_alloc - allocate irq bits from an interrupt vector
  * @iv: pointer to an interrupt vector structure
+ * @num: number of consecutive irq bits to allocate
  *
- * Returns the bit number of the allocated irq, or -1UL if no bit
- * is available or the AIRQ_IV_ALLOC flag has not been specified
+ * Returns the bit number of the first irq in the allocated block of irqs,
+ * or -1UL if no bit is available or the AIRQ_IV_ALLOC flag has not been
+ * specified
  */
-unsigned long airq_iv_alloc_bit(struct airq_iv *iv)
+unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num)
 {
-	unsigned long bit;
+	unsigned long bit, i;
 
-	if (!iv->avail)
+	if (!iv->avail || num == 0)
 		return -1UL;
 	spin_lock(&iv->lock);
 	bit = find_first_bit_inv(iv->avail, iv->bits);
-	if (bit < iv->bits) {
-		clear_bit_inv(bit, iv->avail);
-		if (bit >= iv->end)
-			iv->end = bit + 1;
-	} else
+	while (bit + num <= iv->bits) {
+		for (i = 1; i < num; i++)
+			if (!test_bit_inv(bit + i, iv->avail))
+				break;
+		if (i >= num) {
+			/* Found a suitable block of irqs */
+			for (i = 0; i < num; i++)
+				clear_bit_inv(bit + i, iv->avail);
+			if (bit + num >= iv->end)
+				iv->end = bit + num + 1;
+			break;
+		}
+		bit = find_next_bit_inv(iv->avail, iv->bits, bit + i + 1);
+	}
+	if (bit + num > iv->bits)
 		bit = -1UL;
 	spin_unlock(&iv->lock);
 	return bit;
 
 }
-EXPORT_SYMBOL(airq_iv_alloc_bit);
+EXPORT_SYMBOL(airq_iv_alloc);
 
 /**
- * airq_iv_free_bit - free an irq bit of an interrupt vector
+ * airq_iv_free - free irq bits of an interrupt vector
  * @iv: pointer to interrupt vector structure
- * @bit: number of the irq bit to free
+ * @bit: number of the first irq bit to free
+ * @num: number of consecutive irq bits to free
  */
-void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit)
+void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num)
 {
-	if (!iv->avail)
+	unsigned long i;
+
+	if (!iv->avail || num == 0)
 		return;
 	spin_lock(&iv->lock);
-	/* Clear (possibly left over) interrupt bit */
-	clear_bit_inv(bit, iv->vector);
-	/* Make the bit position available again */
-	set_bit_inv(bit, iv->avail);
-	if (bit == iv->end - 1) {
+	for (i = 0; i < num; i++) {
+		/* Clear (possibly left over) interrupt bit */
+		clear_bit_inv(bit + i, iv->vector);
+		/* Make the bit positions available again */
+		set_bit_inv(bit + i, iv->avail);
+	}
+	if (bit + num >= iv->end) {
 		/* Find new end of bit-field */
-		while (--iv->end > 0)
-			if (!test_bit_inv(iv->end - 1, iv->avail))
-				break;
+		while (iv->end > 0 && !test_bit_inv(iv->end - 1, iv->avail))
+			iv->end--;
 	}
 	spin_unlock(&iv->lock);
 }
-EXPORT_SYMBOL(airq_iv_free_bit);
+EXPORT_SYMBOL(airq_iv_free);
 
 /**
  * airq_iv_scan - scan interrupt vector for non-zero bits

+ 296 - 17
drivers/s390/kvm/virtio_ccw.c

@@ -1,7 +1,7 @@
 /*
  * ccw based virtio transport
  *
- * Copyright IBM Corp. 2012
+ * Copyright IBM Corp. 2012, 2014
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -32,6 +32,8 @@
 #include <asm/cio.h>
 #include <asm/ccwdev.h>
 #include <asm/virtio-ccw.h>
+#include <asm/isc.h>
+#include <asm/airq.h>
 
 /*
  * virtio related functions
@@ -58,6 +60,8 @@ struct virtio_ccw_device {
 	unsigned long indicators;
 	unsigned long indicators2;
 	struct vq_config_block *config_block;
+	bool is_thinint;
+	void *airq_info;
 };
 
 struct vq_info_block {
@@ -72,15 +76,38 @@ struct virtio_feature_desc {
 	__u8 index;
 } __packed;
 
+struct virtio_thinint_area {
+	unsigned long summary_indicator;
+	unsigned long indicator;
+	u64 bit_nr;
+	u8 isc;
+} __packed;
+
 struct virtio_ccw_vq_info {
 	struct virtqueue *vq;
 	int num;
 	void *queue;
 	struct vq_info_block *info_block;
+	int bit_nr;
 	struct list_head node;
 	long cookie;
 };
 
+#define VIRTIO_AIRQ_ISC IO_SCH_ISC /* inherit from subchannel */
+
+#define VIRTIO_IV_BITS (L1_CACHE_BYTES * 8)
+#define MAX_AIRQ_AREAS 20
+
+static int virtio_ccw_use_airq = 1;
+
+struct airq_info {
+	rwlock_t lock;
+	u8 summary_indicator;
+	struct airq_struct airq;
+	struct airq_iv *aiv;
+};
+static struct airq_info *airq_areas[MAX_AIRQ_AREAS];
+
 #define CCW_CMD_SET_VQ 0x13
 #define CCW_CMD_VDEV_RESET 0x33
 #define CCW_CMD_SET_IND 0x43
@@ -91,6 +118,7 @@ struct virtio_ccw_vq_info {
 #define CCW_CMD_WRITE_CONF 0x21
 #define CCW_CMD_WRITE_STATUS 0x31
 #define CCW_CMD_READ_VQ_CONF 0x32
+#define CCW_CMD_SET_IND_ADAPTER 0x73
 
 #define VIRTIO_CCW_DOING_SET_VQ 0x00010000
 #define VIRTIO_CCW_DOING_RESET 0x00040000
@@ -102,6 +130,7 @@ struct virtio_ccw_vq_info {
 #define VIRTIO_CCW_DOING_SET_IND 0x01000000
 #define VIRTIO_CCW_DOING_READ_VQ_CONF 0x02000000
 #define VIRTIO_CCW_DOING_SET_CONF_IND 0x04000000
+#define VIRTIO_CCW_DOING_SET_IND_ADAPTER 0x08000000
 #define VIRTIO_CCW_INTPARM_MASK 0xffff0000
 
 static struct virtio_ccw_device *to_vc_device(struct virtio_device *vdev)
@@ -109,6 +138,125 @@ static struct virtio_ccw_device *to_vc_device(struct virtio_device *vdev)
 	return container_of(vdev, struct virtio_ccw_device, vdev);
 }
 
+static void drop_airq_indicator(struct virtqueue *vq, struct airq_info *info)
+{
+	unsigned long i, flags;
+
+	write_lock_irqsave(&info->lock, flags);
+	for (i = 0; i < airq_iv_end(info->aiv); i++) {
+		if (vq == (void *)airq_iv_get_ptr(info->aiv, i)) {
+			airq_iv_free_bit(info->aiv, i);
+			airq_iv_set_ptr(info->aiv, i, 0);
+			break;
+		}
+	}
+	write_unlock_irqrestore(&info->lock, flags);
+}
+
+static void virtio_airq_handler(struct airq_struct *airq)
+{
+	struct airq_info *info = container_of(airq, struct airq_info, airq);
+	unsigned long ai;
+
+	inc_irq_stat(IRQIO_VAI);
+	read_lock(&info->lock);
+	/* Walk through indicators field, summary indicator active. */
+	for (ai = 0;;) {
+		ai = airq_iv_scan(info->aiv, ai, airq_iv_end(info->aiv));
+		if (ai == -1UL)
+			break;
+		vring_interrupt(0, (void *)airq_iv_get_ptr(info->aiv, ai));
+	}
+	info->summary_indicator = 0;
+	smp_wmb();
+	/* Walk through indicators field, summary indicator not active. */
+	for (ai = 0;;) {
+		ai = airq_iv_scan(info->aiv, ai, airq_iv_end(info->aiv));
+		if (ai == -1UL)
+			break;
+		vring_interrupt(0, (void *)airq_iv_get_ptr(info->aiv, ai));
+	}
+	read_unlock(&info->lock);
+}
+
+static struct airq_info *new_airq_info(void)
+{
+	struct airq_info *info;
+	int rc;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return NULL;
+	rwlock_init(&info->lock);
+	info->aiv = airq_iv_create(VIRTIO_IV_BITS, AIRQ_IV_ALLOC | AIRQ_IV_PTR);
+	if (!info->aiv) {
+		kfree(info);
+		return NULL;
+	}
+	info->airq.handler = virtio_airq_handler;
+	info->airq.lsi_ptr = &info->summary_indicator;
+	info->airq.lsi_mask = 0xff;
+	info->airq.isc = VIRTIO_AIRQ_ISC;
+	rc = register_adapter_interrupt(&info->airq);
+	if (rc) {
+		airq_iv_release(info->aiv);
+		kfree(info);
+		return NULL;
+	}
+	return info;
+}
+
+static void destroy_airq_info(struct airq_info *info)
+{
+	if (!info)
+		return;
+
+	unregister_adapter_interrupt(&info->airq);
+	airq_iv_release(info->aiv);
+	kfree(info);
+}
+
+static unsigned long get_airq_indicator(struct virtqueue *vqs[], int nvqs,
+					u64 *first, void **airq_info)
+{
+	int i, j;
+	struct airq_info *info;
+	unsigned long indicator_addr = 0;
+	unsigned long bit, flags;
+
+	for (i = 0; i < MAX_AIRQ_AREAS && !indicator_addr; i++) {
+		if (!airq_areas[i])
+			airq_areas[i] = new_airq_info();
+		info = airq_areas[i];
+		if (!info)
+			return 0;
+		write_lock_irqsave(&info->lock, flags);
+		bit = airq_iv_alloc(info->aiv, nvqs);
+		if (bit == -1UL) {
+			/* Not enough vacancies. */
+			write_unlock_irqrestore(&info->lock, flags);
+			continue;
+		}
+		*first = bit;
+		*airq_info = info;
+		indicator_addr = (unsigned long)info->aiv->vector;
+		for (j = 0; j < nvqs; j++) {
+			airq_iv_set_ptr(info->aiv, bit + j,
+					(unsigned long)vqs[j]);
+		}
+		write_unlock_irqrestore(&info->lock, flags);
+	}
+	return indicator_addr;
+}
+
+static void virtio_ccw_drop_indicators(struct virtio_ccw_device *vcdev)
+{
+	struct virtio_ccw_vq_info *info;
+
+	list_for_each_entry(info, &vcdev->virtqueues, node)
+		drop_airq_indicator(info->vq, vcdev->airq_info);
+}
+
 static int doing_io(struct virtio_ccw_device *vcdev, __u32 flag)
 {
 	unsigned long flags;
@@ -145,6 +293,51 @@ static int ccw_io_helper(struct virtio_ccw_device *vcdev,
 	return ret ? ret : vcdev->err;
 }
 
+static void virtio_ccw_drop_indicator(struct virtio_ccw_device *vcdev,
+				      struct ccw1 *ccw)
+{
+	int ret;
+	unsigned long *indicatorp = NULL;
+	struct virtio_thinint_area *thinint_area = NULL;
+	struct airq_info *airq_info = vcdev->airq_info;
+
+	if (vcdev->is_thinint) {
+		thinint_area = kzalloc(sizeof(*thinint_area),
+				       GFP_DMA | GFP_KERNEL);
+		if (!thinint_area)
+			return;
+		thinint_area->summary_indicator =
+			(unsigned long) &airq_info->summary_indicator;
+		thinint_area->isc = VIRTIO_AIRQ_ISC;
+		ccw->cmd_code = CCW_CMD_SET_IND_ADAPTER;
+		ccw->count = sizeof(*thinint_area);
+		ccw->cda = (__u32)(unsigned long) thinint_area;
+	} else {
+		indicatorp = kmalloc(sizeof(&vcdev->indicators),
+				     GFP_DMA | GFP_KERNEL);
+		if (!indicatorp)
+			return;
+		*indicatorp = 0;
+		ccw->cmd_code = CCW_CMD_SET_IND;
+		ccw->count = sizeof(vcdev->indicators);
+		ccw->cda = (__u32)(unsigned long) indicatorp;
+	}
+	/* Deregister indicators from host. */
+	vcdev->indicators = 0;
+	ccw->flags = 0;
+	ret = ccw_io_helper(vcdev, ccw,
+			    vcdev->is_thinint ?
+			    VIRTIO_CCW_DOING_SET_IND_ADAPTER :
+			    VIRTIO_CCW_DOING_SET_IND);
+	if (ret && (ret != -ENODEV))
+		dev_info(&vcdev->cdev->dev,
+			 "Failed to deregister indicators (%d)\n", ret);
+	else if (vcdev->is_thinint)
+		virtio_ccw_drop_indicators(vcdev);
+	kfree(indicatorp);
+	kfree(thinint_area);
+}
+
 static inline long do_kvm_notify(struct subchannel_id schid,
 				 unsigned long queue_index,
 				 long cookie)
@@ -232,11 +425,13 @@ static void virtio_ccw_del_vqs(struct virtio_device *vdev)
 {
 	struct virtqueue *vq, *n;
 	struct ccw1 *ccw;
+	struct virtio_ccw_device *vcdev = to_vc_device(vdev);
 
 	ccw = kzalloc(sizeof(*ccw), GFP_DMA | GFP_KERNEL);
 	if (!ccw)
 		return;
 
+	virtio_ccw_drop_indicator(vcdev, ccw);
 
 	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
 		virtio_ccw_del_vq(vq, ccw);
@@ -326,6 +521,54 @@ out_err:
 	return ERR_PTR(err);
 }
 
+static int virtio_ccw_register_adapter_ind(struct virtio_ccw_device *vcdev,
+					   struct virtqueue *vqs[], int nvqs,
+					   struct ccw1 *ccw)
+{
+	int ret;
+	struct virtio_thinint_area *thinint_area = NULL;
+	struct airq_info *info;
+
+	thinint_area = kzalloc(sizeof(*thinint_area), GFP_DMA | GFP_KERNEL);
+	if (!thinint_area) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	/* Try to get an indicator. */
+	thinint_area->indicator = get_airq_indicator(vqs, nvqs,
+						     &thinint_area->bit_nr,
+						     &vcdev->airq_info);
+	if (!thinint_area->indicator) {
+		ret = -ENOSPC;
+		goto out;
+	}
+	info = vcdev->airq_info;
+	thinint_area->summary_indicator =
+		(unsigned long) &info->summary_indicator;
+	thinint_area->isc = VIRTIO_AIRQ_ISC;
+	ccw->cmd_code = CCW_CMD_SET_IND_ADAPTER;
+	ccw->flags = CCW_FLAG_SLI;
+	ccw->count = sizeof(*thinint_area);
+	ccw->cda = (__u32)(unsigned long)thinint_area;
+	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND_ADAPTER);
+	if (ret) {
+		if (ret == -EOPNOTSUPP) {
+			/*
+			 * The host does not support adapter interrupts
+			 * for virtio-ccw, stop trying.
+			 */
+			virtio_ccw_use_airq = 0;
+			pr_info("Adapter interrupts unsupported on host\n");
+		} else
+			dev_warn(&vcdev->cdev->dev,
+				 "enabling adapter interrupts = %d\n", ret);
+		virtio_ccw_drop_indicators(vcdev);
+	}
+out:
+	kfree(thinint_area);
+	return ret;
+}
+
 static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 			       struct virtqueue *vqs[],
 			       vq_callback_t *callbacks[],
@@ -355,15 +598,23 @@ static int virtio_ccw_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	if (!indicatorp)
 		goto out;
 	*indicatorp = (unsigned long) &vcdev->indicators;
-	/* Register queue indicators with host. */
-	vcdev->indicators = 0;
-	ccw->cmd_code = CCW_CMD_SET_IND;
-	ccw->flags = 0;
-	ccw->count = sizeof(vcdev->indicators);
-	ccw->cda = (__u32)(unsigned long) indicatorp;
-	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND);
-	if (ret)
-		goto out;
+	if (vcdev->is_thinint) {
+		ret = virtio_ccw_register_adapter_ind(vcdev, vqs, nvqs, ccw);
+		if (ret)
+			/* no error, just fall back to legacy interrupts */
+			vcdev->is_thinint = 0;
+	}
+	if (!vcdev->is_thinint) {
+		/* Register queue indicators with host. */
+		vcdev->indicators = 0;
+		ccw->cmd_code = CCW_CMD_SET_IND;
+		ccw->flags = 0;
+		ccw->count = sizeof(vcdev->indicators);
+		ccw->cda = (__u32)(unsigned long) indicatorp;
+		ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_SET_IND);
+		if (ret)
+			goto out;
+	}
 	/* Register indicators2 with host for config changes */
 	*indicatorp = (unsigned long) &vcdev->indicators2;
 	vcdev->indicators2 = 0;
@@ -636,6 +887,8 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev,
 	struct virtqueue *vq;
 	struct virtio_driver *drv;
 
+	if (!vcdev)
+		return;
 	/* Check if it's a notification from the host. */
 	if ((intparm == 0) &&
 	    (scsw_stctl(&irb->scsw) ==
@@ -663,6 +916,7 @@ static void virtio_ccw_int_handler(struct ccw_device *cdev,
 		case VIRTIO_CCW_DOING_SET_CONF_IND:
 		case VIRTIO_CCW_DOING_RESET:
 		case VIRTIO_CCW_DOING_READ_VQ_CONF:
+		case VIRTIO_CCW_DOING_SET_IND_ADAPTER:
 			vcdev->curr_io &= ~activity;
 			wake_up(&vcdev->wait_q);
 			break;
@@ -734,23 +988,37 @@ static int virtio_ccw_probe(struct ccw_device *cdev)
 	return 0;
 }
 
+static struct virtio_ccw_device *virtio_grab_drvdata(struct ccw_device *cdev)
+{
+	unsigned long flags;
+	struct virtio_ccw_device *vcdev;
+
+	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
+	vcdev = dev_get_drvdata(&cdev->dev);
+	if (!vcdev) {
+		spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
+		return NULL;
+	}
+	dev_set_drvdata(&cdev->dev, NULL);
+	spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
+	return vcdev;
+}
+
 static void virtio_ccw_remove(struct ccw_device *cdev)
 {
-	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
+	struct virtio_ccw_device *vcdev = virtio_grab_drvdata(cdev);
 
-	if (cdev->online) {
+	if (vcdev && cdev->online)
 		unregister_virtio_device(&vcdev->vdev);
-		dev_set_drvdata(&cdev->dev, NULL);
-	}
 	cdev->handler = NULL;
 }
 
 static int virtio_ccw_offline(struct ccw_device *cdev)
 {
-	struct virtio_ccw_device *vcdev = dev_get_drvdata(&cdev->dev);
+	struct virtio_ccw_device *vcdev = virtio_grab_drvdata(cdev);
 
-	unregister_virtio_device(&vcdev->vdev);
-	dev_set_drvdata(&cdev->dev, NULL);
+	if (vcdev)
+		unregister_virtio_device(&vcdev->vdev);
 	return 0;
 }
 
@@ -759,6 +1027,7 @@ static int virtio_ccw_online(struct ccw_device *cdev)
 {
 	int ret;
 	struct virtio_ccw_device *vcdev;
+	unsigned long flags;
 
 	vcdev = kzalloc(sizeof(*vcdev), GFP_KERNEL);
 	if (!vcdev) {
@@ -778,6 +1047,8 @@ static int virtio_ccw_online(struct ccw_device *cdev)
 		goto out_free;
 	}
 
+	vcdev->is_thinint = virtio_ccw_use_airq; /* at least try */
+
 	vcdev->vdev.dev.parent = &cdev->dev;
 	vcdev->vdev.dev.release = virtio_ccw_release_dev;
 	vcdev->vdev.config = &virtio_ccw_config_ops;
@@ -786,7 +1057,9 @@ static int virtio_ccw_online(struct ccw_device *cdev)
 	INIT_LIST_HEAD(&vcdev->virtqueues);
 	spin_lock_init(&vcdev->lock);
 
+	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
 	dev_set_drvdata(&cdev->dev, vcdev);
+	spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
 	vcdev->vdev.id.vendor = cdev->id.cu_type;
 	vcdev->vdev.id.device = cdev->id.cu_model;
 	ret = register_virtio_device(&vcdev->vdev);
@@ -797,7 +1070,9 @@ static int virtio_ccw_online(struct ccw_device *cdev)
 	}
 	return 0;
 out_put:
+	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
 	dev_set_drvdata(&cdev->dev, NULL);
+	spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
 	put_device(&vcdev->vdev.dev);
 	return ret;
 out_free:
@@ -935,6 +1210,10 @@ module_init(virtio_ccw_init);
 
 static void __exit virtio_ccw_exit(void)
 {
+	int i;
+
 	ccw_driver_unregister(&virtio_ccw_driver);
+	for (i = 0; i < MAX_AIRQ_AREAS; i++)
+		destroy_airq_info(airq_areas[i]);
 }
 module_exit(virtio_ccw_exit);