KVM: remove in_range from io devices

This changes bus accesses to use high-level kvm_io_bus_read/kvm_io_bus_write
functions. in_range now becomes unused so it is removed from device ops in
favor of read/write callbacks performing range checks internally.

This allows aliasing (mostly for in-kernel virtio), as well as better error
handling by making it possible to pass errors up to userspace.

Signed-off-by: Michael S. Tsirkin <[email protected]>
Signed-off-by: Avi Kivity <[email protected]>

Author: mstsirkin

arch/ia64/kvm/kvm-ia64.c

@@ -210,16 +210,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 
 }
 
-static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
-					gpa_t addr, int len, int is_write)
-{
-	struct kvm_io_device *dev;
-
-	dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr, len, is_write);
-
-	return dev;
-}
-
 static int handle_vm_error(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
@@ -231,6 +221,7 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct kvm_mmio_req *p;
 	struct kvm_io_device *mmio_dev;
+	int r;
 
 	p = kvm_get_vcpu_ioreq(vcpu);
 
@@ -247,16 +238,13 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->exit_reason = KVM_EXIT_MMIO;
 	return 0;
 mmio:
-	mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr, p->size, !p->dir);
-	if (mmio_dev) {
-		if (!p->dir)
-			kvm_iodevice_write(mmio_dev, p->addr, p->size,
-						&p->data);
-		else
-			kvm_iodevice_read(mmio_dev, p->addr, p->size,
-						&p->data);
-
-	} else
+	if (p->dir)
+		r = kvm_io_bus_read(&vcpu->kvm->mmio_bus, p->addr,
+				    p->size, &p->data);
+	else
+		r = kvm_io_bus_write(&vcpu->kvm->mmio_bus, p->addr,
+				     p->size, &p->data);
+	if (r)
 		printk(KERN_ERR"kvm: No iodevice found! addr:%lx\n", p->addr);
 	p->state = STATE_IORESP_READY;
 

arch/x86/kvm/i8254.c

@@ -358,15 +358,23 @@ static inline struct kvm_pit *speaker_to_pit(struct kvm_io_device *dev)
 	return container_of(dev, struct kvm_pit, speaker_dev);
 }
 
-static void pit_ioport_write(struct kvm_io_device *this,
-			     gpa_t addr, int len, const void *data)
+static inline int pit_in_range(gpa_t addr)
+{
+	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
+		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
+}
+
+static int pit_ioport_write(struct kvm_io_device *this,
+			    gpa_t addr, int len, const void *data)
 {
 	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	int channel, access;
 	struct kvm_kpit_channel_state *s;
 	u32 val = *(u32 *) data;
+	if (!pit_in_range(addr))
+		return -EOPNOTSUPP;
 
 	val  &= 0xff;
 	addr &= KVM_PIT_CHANNEL_MASK;
@@ -429,16 +437,19 @@ static void pit_ioport_write(struct kvm_io_device *this,
 	}
 
 	mutex_unlock(&pit_state->lock);
+	return 0;
 }
 
-static void pit_ioport_read(struct kvm_io_device *this,
-			    gpa_t addr, int len, void *data)
+static int pit_ioport_read(struct kvm_io_device *this,
+			   gpa_t addr, int len, void *data)
 {
 	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	int ret, count;
 	struct kvm_kpit_channel_state *s;
+	if (!pit_in_range(addr))
+		return -EOPNOTSUPP;
 
 	addr &= KVM_PIT_CHANNEL_MASK;
 	s = &pit_state->channels[addr];
@@ -493,37 +504,36 @@ static void pit_ioport_read(struct kvm_io_device *this,
 	memcpy(data, (char *)&ret, len);
 
 	mutex_unlock(&pit_state->lock);
+	return 0;
 }
 
-static int pit_in_range(struct kvm_io_device *this, gpa_t addr,
-			int len, int is_write)
-{
-	return ((addr >= KVM_PIT_BASE_ADDRESS) &&
-		(addr < KVM_PIT_BASE_ADDRESS + KVM_PIT_MEM_LENGTH));
-}
-
-static void speaker_ioport_write(struct kvm_io_device *this,
-				 gpa_t addr, int len, const void *data)
+static int speaker_ioport_write(struct kvm_io_device *this,
+				gpa_t addr, int len, const void *data)
 {
 	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	u32 val = *(u32 *) data;
+	if (addr != KVM_SPEAKER_BASE_ADDRESS)
+		return -EOPNOTSUPP;
 
 	mutex_lock(&pit_state->lock);
 	pit_state->speaker_data_on = (val >> 1) & 1;
 	pit_set_gate(kvm, 2, val & 1);
 	mutex_unlock(&pit_state->lock);
+	return 0;
 }
 
-static void speaker_ioport_read(struct kvm_io_device *this,
-				gpa_t addr, int len, void *data)
+static int speaker_ioport_read(struct kvm_io_device *this,
+			       gpa_t addr, int len, void *data)
 {
 	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	unsigned int refresh_clock;
 	int ret;
+	if (addr != KVM_SPEAKER_BASE_ADDRESS)
+		return -EOPNOTSUPP;
 
 	/* Refresh clock toggles at about 15us. We approximate as 2^14ns. */
 	refresh_clock = ((unsigned int)ktime_to_ns(ktime_get()) >> 14) & 1;
@@ -535,12 +545,7 @@ static void speaker_ioport_read(struct kvm_io_device *this,
 		len = sizeof(ret);
 	memcpy(data, (char *)&ret, len);
 	mutex_unlock(&pit_state->lock);
-}
-
-static int speaker_in_range(struct kvm_io_device *this, gpa_t addr,
-			    int len, int is_write)
-{
-	return (addr == KVM_SPEAKER_BASE_ADDRESS);
+	return 0;
 }
 
 void kvm_pit_reset(struct kvm_pit *pit)
@@ -574,13 +579,11 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
 static const struct kvm_io_device_ops pit_dev_ops = {
 	.read     = pit_ioport_read,
 	.write    = pit_ioport_write,
-	.in_range = pit_in_range,
 };
 
 static const struct kvm_io_device_ops speaker_dev_ops = {
 	.read     = speaker_ioport_read,
 	.write    = speaker_ioport_write,
-	.in_range = speaker_in_range,
 };
 
 /* Caller must have writers lock on slots_lock */

arch/x86/kvm/i8259.c

@@ -430,8 +430,7 @@ static u32 elcr_ioport_read(void *opaque, u32 addr1)
 	return s->elcr;
 }
 
-static int picdev_in_range(struct kvm_io_device *this, gpa_t addr,
-			   int len, int is_write)
+static int picdev_in_range(gpa_t addr)
 {
 	switch (addr) {
 	case 0x20:
@@ -451,16 +450,18 @@ static inline struct kvm_pic *to_pic(struct kvm_io_device *dev)
 	return container_of(dev, struct kvm_pic, dev);
 }
 
-static void picdev_write(struct kvm_io_device *this,
+static int picdev_write(struct kvm_io_device *this,
 			 gpa_t addr, int len, const void *val)
 {
 	struct kvm_pic *s = to_pic(this);
 	unsigned char data = *(unsigned char *)val;
+	if (!picdev_in_range(addr))
+		return -EOPNOTSUPP;
 
 	if (len != 1) {
 		if (printk_ratelimit())
 			printk(KERN_ERR "PIC: non byte write\n");
-		return;
+		return 0;
 	}
 	pic_lock(s);
 	switch (addr) {
@@ -476,18 +477,21 @@ static void picdev_write(struct kvm_io_device *this,
 		break;
 	}
 	pic_unlock(s);
+	return 0;
 }
 
-static void picdev_read(struct kvm_io_device *this,
-			gpa_t addr, int len, void *val)
+static int picdev_read(struct kvm_io_device *this,
+		       gpa_t addr, int len, void *val)
 {
 	struct kvm_pic *s = to_pic(this);
 	unsigned char data = 0;
+	if (!picdev_in_range(addr))
+		return -EOPNOTSUPP;
 
 	if (len != 1) {
 		if (printk_ratelimit())
 			printk(KERN_ERR "PIC: non byte read\n");
-		return;
+		return 0;
 	}
 	pic_lock(s);
 	switch (addr) {
@@ -504,6 +508,7 @@ static void picdev_read(struct kvm_io_device *this,
 	}
 	*(unsigned char *)val = data;
 	pic_unlock(s);
+	return 0;
 }
 
 /*
@@ -526,7 +531,6 @@ static void pic_irq_request(void *opaque, int level)
 static const struct kvm_io_device_ops picdev_ops = {
 	.read     = picdev_read,
 	.write    = picdev_write,
-	.in_range = picdev_in_range,
 };
 
 struct kvm_pic *kvm_create_pic(struct kvm *kvm)

arch/x86/kvm/lapic.c

@@ -546,18 +546,27 @@ static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev)
 	return container_of(dev, struct kvm_lapic, dev);
 }
 
-static void apic_mmio_read(struct kvm_io_device *this,
-			   gpa_t address, int len, void *data)
+static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
+{
+	return apic_hw_enabled(apic) &&
+	    addr >= apic->base_address &&
+	    addr < apic->base_address + LAPIC_MMIO_LENGTH;
+}
+
+static int apic_mmio_read(struct kvm_io_device *this,
+			  gpa_t address, int len, void *data)
 {
 	struct kvm_lapic *apic = to_lapic(this);
 	unsigned int offset = address - apic->base_address;
 	unsigned char alignment = offset & 0xf;
 	u32 result;
+	if (!apic_mmio_in_range(apic, address))
+		return -EOPNOTSUPP;
 
 	if ((alignment + len) > 4) {
 		printk(KERN_ERR "KVM_APIC_READ: alignment error %lx %d",
 		       (unsigned long)address, len);
-		return;
+		return 0;
 	}
 	result = __apic_read(apic, offset & ~0xf);
 
@@ -574,6 +583,7 @@ static void apic_mmio_read(struct kvm_io_device *this,
 		       "should be 1,2, or 4 instead\n", len);
 		break;
 	}
+	return 0;
 }
 
 static void update_divide_count(struct kvm_lapic *apic)
@@ -629,13 +639,15 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 		apic->vcpu->kvm->arch.vapics_in_nmi_mode--;
 }
 
-static void apic_mmio_write(struct kvm_io_device *this,
-			    gpa_t address, int len, const void *data)
+static int apic_mmio_write(struct kvm_io_device *this,
+			   gpa_t address, int len, const void *data)
 {
 	struct kvm_lapic *apic = to_lapic(this);
 	unsigned int offset = address - apic->base_address;
 	unsigned char alignment = offset & 0xf;
 	u32 val;
+	if (!apic_mmio_in_range(apic, address))
+		return -EOPNOTSUPP;
 
 	/*
 	 * APIC register must be aligned on 128-bits boundary.
@@ -646,7 +658,7 @@ static void apic_mmio_write(struct kvm_io_device *this,
 		/* Don't shout loud, $infamous_os would cause only noise. */
 		apic_debug("apic write: bad size=%d %lx\n",
 			   len, (long)address);
-		return;
+		return 0;
 	}
 
 	val = *(u32 *) data;
@@ -729,7 +741,7 @@ static void apic_mmio_write(struct kvm_io_device *this,
 		hrtimer_cancel(&apic->lapic_timer.timer);
 		apic_set_reg(apic, APIC_TMICT, val);
 		start_apic_timer(apic);
-		return;
+		return 0;
 
 	case APIC_TDCR:
 		if (val & 4)
@@ -743,22 +755,7 @@ static void apic_mmio_write(struct kvm_io_device *this,
 			   offset);
 		break;
 	}
-
-}
-
-static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr,
-			   int len, int size)
-{
-	struct kvm_lapic *apic = to_lapic(this);
-	int ret = 0;
-
-
-	if (apic_hw_enabled(apic) &&
-	    (addr >= apic->base_address) &&
-	    (addr < (apic->base_address + LAPIC_MMIO_LENGTH)))
-		ret = 1;
-
-	return ret;
+	return 0;
 }
 
 void kvm_free_lapic(struct kvm_vcpu *vcpu)
@@ -938,7 +935,6 @@ static struct kvm_timer_ops lapic_timer_ops = {
 static const struct kvm_io_device_ops apic_mmio_ops = {
 	.read     = apic_mmio_read,
 	.write    = apic_mmio_write,
-	.in_range = apic_mmio_range,
 };
 
 int kvm_create_lapic(struct kvm_vcpu *vcpu)