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---
#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 = {
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 |
#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)
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)
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;
---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".
#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)
{
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)
} 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;
}
{
__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)
/* 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 {
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
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). */
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);
else
virtio_pci_modern_remove(vp_dev);
- pci_release_regions(pci_dev);
pci_disable_device(pci_dev);
}
/* 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;
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)
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;
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)
struct pci_dev *pci_dev = vp_dev->pci_dev;
pci_iounmap(pci_dev, vp_dev->ioaddr);
+ pci_release_region(pci_dev, 0);
}
* 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;
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;
/* 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");
/* 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",
* 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,
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);
}
#include <linux/types.h>
#include <uapi/linux/virtio_types.h>
-/*
- * Low-level memory accessors for handling virtio in modern little endian and in
- * compatibility native endian format.
- */
+static inline bool virtio_legacy_is_little_endian(void)
+{
+#ifdef __LITTLE_ENDIAN
+ return true;
+#else
+ return false;
+#endif
+}
static inline u16 __virtio16_to_cpu(bool little_endian, __virtio16 val)
{
if (little_endian)
return le16_to_cpu((__force __le16)val);
else
- return (__force u16)val;
+ return be16_to_cpu((__force __be16)val);
}
static inline __virtio16 __cpu_to_virtio16(bool little_endian, u16 val)
if (little_endian)
return (__force __virtio16)cpu_to_le16(val);
else
- return (__force __virtio16)val;
+ return (__force __virtio16)cpu_to_be16(val);
}
static inline u32 __virtio32_to_cpu(bool little_endian, __virtio32 val)
if (little_endian)
return le32_to_cpu((__force __le32)val);
else
- return (__force u32)val;
+ return be32_to_cpu((__force __be32)val);
}
static inline __virtio32 __cpu_to_virtio32(bool little_endian, u32 val)
if (little_endian)
return (__force __virtio32)cpu_to_le32(val);
else
- return (__force __virtio32)val;
+ return (__force __virtio32)cpu_to_be32(val);
}
static inline u64 __virtio64_to_cpu(bool little_endian, __virtio64 val)
if (little_endian)
return le64_to_cpu((__force __le64)val);
else
- return (__force u64)val;
+ return be64_to_cpu((__force __be64)val);
}
static inline __virtio64 __cpu_to_virtio64(bool little_endian, u64 val)
if (little_endian)
return (__force __virtio64)cpu_to_le64(val);
else
- return (__force __virtio64)val;
+ return (__force __virtio64)cpu_to_be64(val);
}
#endif /* _LINUX_VIRTIO_BYTEORDER */
return 0;
}
+static inline bool virtio_is_little_endian(struct virtio_device *vdev)
+{
+ return virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
+ virtio_legacy_is_little_endian();
+}
+
/* Memory accessors */
static inline u16 virtio16_to_cpu(struct virtio_device *vdev, __virtio16 val)
{
- return __virtio16_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __virtio16_to_cpu(virtio_is_little_endian(vdev), val);
}
static inline __virtio16 cpu_to_virtio16(struct virtio_device *vdev, u16 val)
{
- return __cpu_to_virtio16(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __cpu_to_virtio16(virtio_is_little_endian(vdev), val);
}
static inline u32 virtio32_to_cpu(struct virtio_device *vdev, __virtio32 val)
{
- return __virtio32_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __virtio32_to_cpu(virtio_is_little_endian(vdev), val);
}
static inline __virtio32 cpu_to_virtio32(struct virtio_device *vdev, u32 val)
{
- return __cpu_to_virtio32(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __cpu_to_virtio32(virtio_is_little_endian(vdev), val);
}
static inline u64 virtio64_to_cpu(struct virtio_device *vdev, __virtio64 val)
{
- return __virtio64_to_cpu(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __virtio64_to_cpu(virtio_is_little_endian(vdev), val);
}
static inline __virtio64 cpu_to_virtio64(struct virtio_device *vdev, u64 val)
{
- return __cpu_to_virtio64(virtio_has_feature(vdev, VIRTIO_F_VERSION_1), val);
+ return __cpu_to_virtio64(virtio_is_little_endian(vdev), val);
}
/* Config space accessors. */
vrh->notify(vrh);
}
+static inline bool vringh_is_little_endian(const struct vringh *vrh)
+{
+ return vrh->little_endian ||
+ virtio_legacy_is_little_endian();
+}
+
static inline u16 vringh16_to_cpu(const struct vringh *vrh, __virtio16 val)
{
- return __virtio16_to_cpu(vrh->little_endian, val);
+ return __virtio16_to_cpu(vringh_is_little_endian(vrh), val);
}
static inline __virtio16 cpu_to_vringh16(const struct vringh *vrh, u16 val)
{
- return __cpu_to_virtio16(vrh->little_endian, val);
+ return __cpu_to_virtio16(vringh_is_little_endian(vrh), val);
}
static inline u32 vringh32_to_cpu(const struct vringh *vrh, __virtio32 val)
{
- return __virtio32_to_cpu(vrh->little_endian, val);
+ return __virtio32_to_cpu(vringh_is_little_endian(vrh), val);
}
static inline __virtio32 cpu_to_vringh32(const struct vringh *vrh, u32 val)
{
- return __cpu_to_virtio32(vrh->little_endian, val);
+ return __cpu_to_virtio32(vringh_is_little_endian(vrh), val);
}
static inline u64 vringh64_to_cpu(const struct vringh *vrh, __virtio64 val)
{
- return __virtio64_to_cpu(vrh->little_endian, val);
+ return __virtio64_to_cpu(vringh_is_little_endian(vrh), val);
}
static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val)
{
- return __cpu_to_virtio64(vrh->little_endian, val);
+ return __cpu_to_virtio64(vringh_is_little_endian(vrh), val);
}
#endif /* _LINUX_VRINGH_H */
#define TUNGETFILTER _IOR('T', 219, struct sock_fprog)
#define TUNSETVNETLE _IOW('T', 220, int)
#define TUNGETVNETLE _IOR('T', 221, int)
+/* The TUNSETVNETBE and TUNGETVNETBE ioctls are for cross-endian support on
+ * little-endian hosts. Not all kernel configurations support them, but all
+ * configurations that support SET also support GET.
+ */
+#define TUNSETVNETBE _IOW('T', 222, int)
+#define TUNGETVNETBE _IOR('T', 223, int)
/* TUNSETIFF ifr flags */
#define IFF_TUN 0x0001
/* Get accessor: reads index, writes value in num */
#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+/* Set the vring byte order in num. Valid values are VHOST_VRING_LITTLE_ENDIAN
+ * or VHOST_VRING_BIG_ENDIAN (other values return -EINVAL).
+ * The byte order cannot be changed while the device is active: trying to do so
+ * returns -EBUSY.
+ * This is a legacy only API that is simply ignored when VIRTIO_F_VERSION_1 is
+ * set.
+ * Not all kernel configurations support this ioctl, but all configurations that
+ * support SET also support GET.
+ */
+#define VHOST_VRING_LITTLE_ENDIAN 0
+#define VHOST_VRING_BIG_ENDIAN 1
+#define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
+#define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
+
/* The following ioctls use eventfd file descriptors to signal and poll
* for events. */
projects / firefly-linux-kernel-4.4.55.git / commitdiff