Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio/vhost cross endian support from Michael Tsirkin:
 "I have just queued some more bugfix patches today but none fix
  regressions and none are related to these ones, so it looks like a
  good time for a merge for -rc1.

  The motivation for this is support for legacy BE guests on the new LE
  hosts.  There are two redeeming properties that made me merge this:

   - It's a trivial amount of code: since we wrap host/guest accesses
     anyway, almost all of it is well hidden from drivers.

   - Sane platforms would never set flags like VHOST_CROSS_ENDIAN_LEGACY,
     and when it's clear, there's zero overhead (as some point it was
     tested by compiling with and without the patches, got the same
     stripped binary).

  Maybe we could create a Kconfig symbol to enforce the second point:
  prevent people from enabling it eg on x86.  I will look into this"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio-pci: alloc only resources actually used.
  macvtap/tun: cross-endian support for little-endian hosts
  vhost: cross-endian support for legacy devices
  virtio: add explicit big-endian support to memory accessors
  vhost: introduce vhost_is_little_endian() helper
  vringh: introduce vringh_is_little_endian() helper
  macvtap: introduce macvtap_is_little_endian() helper
  tun: add tun_is_little_endian() helper
  virtio: introduce virtio_is_little_endian() helper

10 files changed, 292 insertions, 25 deletions

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 019fceffc9e5..b7f31150753d 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -258,6 +258,20 @@ config TUN
 
 	  If you don't know what to use this for, you don't need it.
 
+config TUN_VNET_CROSS_LE
+	bool "Support for cross-endian vnet headers on little-endian kernels"
+	default n
+	---help---
+	  This option allows TUN/TAP and MACVTAP device drivers in a
+	  little-endian kernel to parse vnet headers that come from a
+	  big-endian legacy virtio device.
+
+	  Userspace programs can control the feature using the TUNSETVNETBE
+	  and TUNGETVNETBE ioctls.
+
+	  Unless you have a little-endian system hosting a big-endian virtual
+	  machine with a legacy virtio NIC, you should say N.
+
 config VETH
 	tristate "Virtual ethernet pair device"
 	---help---
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 6a64197f5bce..f8370808a018 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -48,15 +48,70 @@ struct macvtap_queue {
 #define MACVTAP_FEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE)
 
 #define MACVTAP_VNET_LE 0x80000000
+#define MACVTAP_VNET_BE 0x40000000
+
+#ifdef CONFIG_TUN_VNET_CROSS_LE
+static inline bool macvtap_legacy_is_little_endian(struct macvtap_queue *q)
+{
+	return q->flags & MACVTAP_VNET_BE ? false :
+		virtio_legacy_is_little_endian();
+}
+
+static long macvtap_get_vnet_be(struct macvtap_queue *q, int __user *sp)
+{
+	int s = !!(q->flags & MACVTAP_VNET_BE);
+
+	if (put_user(s, sp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long macvtap_set_vnet_be(struct macvtap_queue *q, int __user *sp)
+{
+	int s;
+
+	if (get_user(s, sp))
+		return -EFAULT;
+
+	if (s)
+		q->flags |= MACVTAP_VNET_BE;
+	else
+		q->flags &= ~MACVTAP_VNET_BE;
+
+	return 0;
+}
+#else
+static inline bool macvtap_legacy_is_little_endian(struct macvtap_queue *q)
+{
+	return virtio_legacy_is_little_endian();
+}
+
+static long macvtap_get_vnet_be(struct macvtap_queue *q, int __user *argp)
+{
+	return -EINVAL;
+}
+
+static long macvtap_set_vnet_be(struct macvtap_queue *q, int __user *argp)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_TUN_VNET_CROSS_LE */
+
+static inline bool macvtap_is_little_endian(struct macvtap_queue *q)
+{
+	return q->flags & MACVTAP_VNET_LE ||
+		macvtap_legacy_is_little_endian(q);
+}
 
 static inline u16 macvtap16_to_cpu(struct macvtap_queue *q, __virtio16 val)
 {
-	return __virtio16_to_cpu(q->flags & MACVTAP_VNET_LE, val);
+	return __virtio16_to_cpu(macvtap_is_little_endian(q), val);
 }
 
 static inline __virtio16 cpu_to_macvtap16(struct macvtap_queue *q, u16 val)
 {
-	return __cpu_to_virtio16(q->flags & MACVTAP_VNET_LE, val);
+	return __cpu_to_virtio16(macvtap_is_little_endian(q), val);
 }
 
 static struct proto macvtap_proto = {
@@ -1085,6 +1140,12 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd,
 			q->flags &= ~MACVTAP_VNET_LE;
 		return 0;
 
+	case TUNGETVNETBE:
+		return macvtap_get_vnet_be(q, sp);
+
+	case TUNSETVNETBE:
+		return macvtap_set_vnet_be(q, sp);
+
 	case TUNSETOFFLOAD:
 		/* let the user check for future flags */
 		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 1a1c4f7b3ec5..06a039414628 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -111,6 +111,7 @@ do {								\
 #define TUN_FASYNC	IFF_ATTACH_QUEUE
 /* High bits in flags field are unused. */
 #define TUN_VNET_LE     0x80000000
+#define TUN_VNET_BE     0x40000000
 
 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
 		      IFF_MULTI_QUEUE)
@@ -205,14 +206,68 @@ struct tun_struct {
 	u32 flow_count;
 };
 
+#ifdef CONFIG_TUN_VNET_CROSS_LE
+static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
+{
+	return tun->flags & TUN_VNET_BE ? false :
+		virtio_legacy_is_little_endian();
+}
+
+static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	int be = !!(tun->flags & TUN_VNET_BE);
+
+	if (put_user(be, argp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	int be;
+
+	if (get_user(be, argp))
+		return -EFAULT;
+
+	if (be)
+		tun->flags |= TUN_VNET_BE;
+	else
+		tun->flags &= ~TUN_VNET_BE;
+
+	return 0;
+}
+#else
+static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
+{
+	return virtio_legacy_is_little_endian();
+}
+
+static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	return -EINVAL;
+}
+
+static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_TUN_VNET_CROSS_LE */
+
+static inline bool tun_is_little_endian(struct tun_struct *tun)
+{
+	return tun->flags & TUN_VNET_LE ||
+		tun_legacy_is_little_endian(tun);
+}
+
 static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val)
 {
-	return __virtio16_to_cpu(tun->flags & TUN_VNET_LE, val);
+	return __virtio16_to_cpu(tun_is_little_endian(tun), val);
 }
 
 static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
 {
-	return __cpu_to_virtio16(tun->flags & TUN_VNET_LE, val);
+	return __cpu_to_virtio16(tun_is_little_endian(tun), val);
 }
 
 static inline u32 tun_hashfn(u32 rxhash)
@@ -2044,6 +2099,14 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 			tun->flags &= ~TUN_VNET_LE;
 		break;
 
+	case TUNGETVNETBE:
+		ret = tun_get_vnet_be(tun, argp);
+		break;
+
+	case TUNSETVNETBE:
+		ret = tun_set_vnet_be(tun, argp);
+		break;
+
 	case TUNATTACHFILTER:
 		/* Can be set only for TAPs */
 		ret = -EINVAL;
diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
index 017a1e8a8f6f..533eaf04f12f 100644
--- a/drivers/vhost/Kconfig
+++ b/drivers/vhost/Kconfig
@@ -32,3 +32,18 @@ config VHOST
 	---help---
 	  This option is selected by any driver which needs to access
 	  the core of vhost.
+
+config VHOST_CROSS_ENDIAN_LEGACY
+	bool "Cross-endian support for vhost"
+	default n
+	---help---
+	  This option allows vhost to support guests with a different byte
+	  ordering from host while using legacy virtio.
+
+	  Userspace programs can control the feature using the
+	  VHOST_SET_VRING_ENDIAN and VHOST_GET_VRING_ENDIAN ioctls.
+
+	  This is only useful on a few platforms (ppc64 and arm64). Since it
+	  adds some overhead, it is disabled by default.
+
+	  If unsure, say "N".
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 2ee28266fd07..9e8e004bb1c3 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -36,6 +36,77 @@ enum {
 #define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num])
 #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])
 
+#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
+static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq)
+{
+	vq->user_be = !virtio_legacy_is_little_endian();
+}
+
+static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
+{
+	struct vhost_vring_state s;
+
+	if (vq->private_data)
+		return -EBUSY;
+
+	if (copy_from_user(&s, argp, sizeof(s)))
+		return -EFAULT;
+
+	if (s.num != VHOST_VRING_LITTLE_ENDIAN &&
+	    s.num != VHOST_VRING_BIG_ENDIAN)
+		return -EINVAL;
+
+	vq->user_be = s.num;
+
+	return 0;
+}
+
+static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx,
+				   int __user *argp)
+{
+	struct vhost_vring_state s = {
+		.index = idx,
+		.num = vq->user_be
+	};
+
+	if (copy_to_user(argp, &s, sizeof(s)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static void vhost_init_is_le(struct vhost_virtqueue *vq)
+{
+	/* Note for legacy virtio: user_be is initialized at reset time
+	 * according to the host endianness. If userspace does not set an
+	 * explicit endianness, the default behavior is native endian, as
+	 * expected by legacy virtio.
+	 */
+	vq->is_le = vhost_has_feature(vq, VIRTIO_F_VERSION_1) || !vq->user_be;
+}
+#else
+static void vhost_vq_reset_user_be(struct vhost_virtqueue *vq)
+{
+}
+
+static long vhost_set_vring_endian(struct vhost_virtqueue *vq, int __user *argp)
+{
+	return -ENOIOCTLCMD;
+}
+
+static long vhost_get_vring_endian(struct vhost_virtqueue *vq, u32 idx,
+				   int __user *argp)
+{
+	return -ENOIOCTLCMD;
+}
+
+static void vhost_init_is_le(struct vhost_virtqueue *vq)
+{
+	if (vhost_has_feature(vq, VIRTIO_F_VERSION_1))
+		vq->is_le = true;
+}
+#endif /* CONFIG_VHOST_CROSS_ENDIAN_LEGACY */
+
 static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
 			    poll_table *pt)
 {
@@ -199,6 +270,8 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->call = NULL;
 	vq->log_ctx = NULL;
 	vq->memory = NULL;
+	vq->is_le = virtio_legacy_is_little_endian();
+	vhost_vq_reset_user_be(vq);
 }
 
 static int vhost_worker(void *data)
@@ -806,6 +879,12 @@ long vhost_vring_ioctl(struct vhost_dev *d, int ioctl, void __user *argp)
 		} else
 			filep = eventfp;
 		break;
+	case VHOST_SET_VRING_ENDIAN:
+		r = vhost_set_vring_endian(vq, argp);
+		break;
+	case VHOST_GET_VRING_ENDIAN:
+		r = vhost_get_vring_endian(vq, idx, argp);
+		break;
 	default:
 		r = -ENOIOCTLCMD;
 	}
@@ -1044,8 +1123,12 @@ int vhost_init_used(struct vhost_virtqueue *vq)
 {
 	__virtio16 last_used_idx;
 	int r;
-	if (!vq->private_data)
+	if (!vq->private_data) {
+		vq->is_le = virtio_legacy_is_little_endian();
 		return 0;
+	}
+
+	vhost_init_is_le(vq);
 
 	r = vhost_update_used_flags(vq);
 	if (r)
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 8c1c792900ba..ce6f6da4b09f 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -106,6 +106,14 @@ struct vhost_virtqueue {
 	/* Log write descriptors */
 	void __user *log_base;
 	struct vhost_log *log;
+
+	/* Ring endianness. Defaults to legacy native endianness.
+	 * Set to true when starting a modern virtio device. */
+	bool is_le;
+#ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
+	/* Ring endianness requested by userspace for cross-endian support. */
+	bool user_be;
+#endif
 };
 
 struct vhost_dev {
@@ -173,34 +181,39 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
 	return vq->acked_features & (1ULL << bit);
 }
 
+static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
+{
+	return vq->is_le;
+}
+
 /* Memory accessors */
 static inline u16 vhost16_to_cpu(struct vhost_virtqueue *vq, __virtio16 val)
 {
-	return __virtio16_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __virtio16_to_cpu(vhost_is_little_endian(vq), val);
 }
 
 static inline __virtio16 cpu_to_vhost16(struct vhost_virtqueue *vq, u16 val)
 {
-	return __cpu_to_virtio16(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio16(vhost_is_little_endian(vq), val);
 }
 
 static inline u32 vhost32_to_cpu(struct vhost_virtqueue *vq, __virtio32 val)
 {
-	return __virtio32_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __virtio32_to_cpu(vhost_is_little_endian(vq), val);
 }
 
 static inline __virtio32 cpu_to_vhost32(struct vhost_virtqueue *vq, u32 val)
 {
-	return __cpu_to_virtio32(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio32(vhost_is_little_endian(vq), val);
 }
 
 static inline u64 vhost64_to_cpu(struct vhost_virtqueue *vq, __virtio64 val)
 {
-	return __virtio64_to_cpu(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __virtio64_to_cpu(vhost_is_little_endian(vq), val);
 }
 
 static inline __virtio64 cpu_to_vhost64(struct vhost_virtqueue *vq, u64 val)
 {
-	return __cpu_to_virtio64(vhost_has_feature(vq, VIRTIO_F_VERSION_1), val);
+	return __cpu_to_virtio64(vhost_is_little_endian(vq), val);
 }
 #endif
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 5447b8186332..78f804af6c20 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -507,10 +507,6 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	if (rc)
 		goto err_enable_device;
 
-	rc = pci_request_regions(pci_dev, "virtio-pci");
-	if (rc)
-		goto err_request_regions;
-
 	if (force_legacy) {
 		rc = virtio_pci_legacy_probe(vp_dev);
 		/* Also try modern mode if we can't map BAR0 (no IO space). */
@@ -540,8 +536,6 @@ err_register:
 	else
 	     virtio_pci_modern_remove(vp_dev);
 err_probe:
-	pci_release_regions(pci_dev);
-err_request_regions:
 	pci_disable_device(pci_dev);
 err_enable_device:
 	kfree(vp_dev);
@@ -559,7 +553,6 @@ static void virtio_pci_remove(struct pci_dev *pci_dev)
 	else
 		virtio_pci_modern_remove(vp_dev);
 
-	pci_release_regions(pci_dev);
 	pci_disable_device(pci_dev);
 }
 
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 28ee4e56badf..b976d968e793 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -75,6 +75,8 @@ struct virtio_pci_device {
 	/* Multiply queue_notify_off by this value. (non-legacy mode). */
 	u32 notify_offset_multiplier;
 
+	int modern_bars;
+
 	/* Legacy only field */
 	/* the IO mapping for the PCI config space */
 	void __iomem *ioaddr;
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index 256a5278a515..48bc9797e530 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -215,6 +215,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
 {
 	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	int rc;
 
 	/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
 	if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
@@ -226,9 +227,14 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
 		return -ENODEV;
 	}
 
+	rc = pci_request_region(pci_dev, 0, "virtio-pci-legacy");
+	if (rc)
+		return rc;
+
+	rc = -ENOMEM;
 	vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
 	if (!vp_dev->ioaddr)
-		return -ENOMEM;
+		goto err_iomap;
 
 	vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR;
 
@@ -246,6 +252,10 @@ int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
 	vp_dev->del_vq = del_vq;
 
 	return 0;
+
+err_iomap:
+	pci_release_region(pci_dev, 0);
+	return rc;
 }
 
 void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
@@ -253,4 +263,5 @@ void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 	struct pci_dev *pci_dev = vp_dev->pci_dev;
 
 	pci_iounmap(pci_dev, vp_dev->ioaddr);
+	pci_release_region(pci_dev, 0);
 }
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index e88e0997a889..8e5cf194cc0b 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -499,7 +499,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
  * Returns offset of the capability, or 0.
  */
 static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
-					     u32 ioresource_types)
+					     u32 ioresource_types, int *bars)
 {
 	int pos;
 
@@ -520,8 +520,10 @@ static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
 
 		if (type == cfg_type) {
 			if (pci_resource_len(dev, bar) &&
-			    pci_resource_flags(dev, bar) & ioresource_types)
+			    pci_resource_flags(dev, bar) & ioresource_types) {
+				*bars |= (1 << bar);
 				return pos;
+			}
 		}
 	}
 	return 0;
@@ -617,7 +619,8 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 
 	/* check for a common config: if not, use legacy mode (bar 0). */
 	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
-					    IORESOURCE_IO | IORESOURCE_MEM);
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &vp_dev->modern_bars);
 	if (!common) {
 		dev_info(&pci_dev->dev,
 			 "virtio_pci: leaving for legacy driver\n");
@@ -626,9 +629,11 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 
 	/* If common is there, these should be too... */
 	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
-					 IORESOURCE_IO | IORESOURCE_MEM);
+					 IORESOURCE_IO | IORESOURCE_MEM,
+					 &vp_dev->modern_bars);
 	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
-					    IORESOURCE_IO | IORESOURCE_MEM);
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &vp_dev->modern_bars);
 	if (!isr || !notify) {
 		dev_err(&pci_dev->dev,
 			"virtio_pci: missing capabilities %i/%i/%i\n",
@@ -640,7 +645,13 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
 	 * device-specific configuration.
 	 */
 	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
-					    IORESOURCE_IO | IORESOURCE_MEM);
+					    IORESOURCE_IO | IORESOURCE_MEM,
+					    &vp_dev->modern_bars);
+
+	err = pci_request_selected_regions(pci_dev, vp_dev->modern_bars,
+					   "virtio-pci-modern");
+	if (err)
+		return err;
 
 	err = -EINVAL;
 	vp_dev->common = map_capability(pci_dev, common,
@@ -727,4 +738,5 @@ void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
 		pci_iounmap(pci_dev, vp_dev->notify_base);
 	pci_iounmap(pci_dev, vp_dev->isr);
 	pci_iounmap(pci_dev, vp_dev->common);
+	pci_release_selected_regions(pci_dev, vp_dev->modern_bars);
 }