From 2751c9882b947292fcfb084c4f604e01724af804 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Fri, 24 Apr 2015 14:27:24 +0200 Subject: vhost: cross-endian support for legacy devices This patch brings cross-endian support to vhost when used to implement legacy virtio devices. Since it is a relatively rare situation, the feature availability is controlled by a kernel config option (not set by default). The vq->is_le boolean field is added to cache the endianness to be used for ring accesses. It defaults to native endian, as expected by legacy virtio devices. When the ring gets active, we force little endian if the device is modern. When the ring is deactivated, we revert to the native endian default. If cross-endian was compiled in, a vq->user_be boolean field is added so that userspace may request a specific endianness. This field is used to override the default when activating the ring of a legacy device. It has no effect on modern devices. Signed-off-by: Greg Kurz Signed-off-by: Michael S. Tsirkin Reviewed-by: Cornelia Huck Reviewed-by: David Gibson --- include/uapi/linux/vhost.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index bb6a5b4cb3c5..ab3731917bac 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -103,6 +103,20 @@ struct vhost_memory { /* 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. */ -- cgit v1.2.3 From 8b8e658b16336f0f50aba733f51db636ef121f50 Mon Sep 17 00:00:00 2001 From: Greg Kurz Date: Fri, 24 Apr 2015 14:50:36 +0200 Subject: macvtap/tun: cross-endian support for little-endian hosts The VNET_LE flag was introduced to fix accesses to virtio 1.0 headers that are always little-endian. It can also be used to handle the special case of a legacy little-endian device implemented by a big-endian host. Let's add a flag and ioctls for big-endian devices as well. If both flags are set, little-endian wins. Since this is isn't a common usecase, the feature is controlled by a kernel config option (not set by default). Both macvtap and tun are covered by this patch since they share the same API with userland. Signed-off-by: Greg Kurz Signed-off-by: Michael S. Tsirkin Reviewed-by: David Gibson --- drivers/net/Kconfig | 14 +++++++++++ drivers/net/macvtap.c | 57 ++++++++++++++++++++++++++++++++++++++++++- drivers/net/tun.c | 59 ++++++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/if_tun.h | 6 +++++ 4 files changed, 134 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index df51d6025a90..71ac0ece2d75 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -244,6 +244,20 @@ 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 072ccbaf7c45..928f3f4db629 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -48,11 +48,60 @@ 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 || - virtio_legacy_is_little_endian(); + macvtap_legacy_is_little_endian(q); } static inline u16 macvtap16_to_cpu(struct macvtap_queue *q, __virtio16 val) @@ -1096,6 +1145,12 @@ 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 b210139bef8f..cb376b2d548a 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) @@ -206,10 +207,58 @@ 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 || - virtio_legacy_is_little_endian(); + tun_legacy_is_little_endian(tun); } static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val) @@ -2062,6 +2111,14 @@ 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/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index 50ae24335444..3cb5e1d85ddd 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -50,6 +50,12 @@ #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 -- cgit v1.2.3 From 00c570f4ba43ae73b41fa0a2269c3b0ac20386ef Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Wed, 1 Jul 2015 16:26:08 +0200 Subject: fuse: device fd clone Allow an open fuse device to be "cloned". Userspace can create a clone by: newfd = open("/dev/fuse", O_RDWR) ioctl(newfd, FUSE_DEV_IOC_CLONE, &oldfd); At this point newfd will refer to the same fuse connection as oldfd. Signed-off-by: Miklos Szeredi Reviewed-by: Ashish Samant --- Documentation/ioctl/ioctl-number.txt | 1 + fs/fuse/dev.c | 40 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/fuse.h | 3 +++ 3 files changed, 44 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 51f4221657bf..611c52267d24 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -321,6 +321,7 @@ Code Seq#(hex) Include File Comments 0xDB 00-0F drivers/char/mwave/mwavepub.h 0xDD 00-3F ZFCP device driver see drivers/s390/scsi/ +0xE5 00-3F linux/fuse.h 0xEC 00-01 drivers/platform/chrome/cros_ec_dev.h ChromeOS EC driver 0xF3 00-3F drivers/usb/misc/sisusbvga/sisusb.h sisfb (in development) diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index dcfc87172a47..d405c1fa4618 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2197,6 +2197,44 @@ static int fuse_dev_fasync(int fd, struct file *file, int on) return fasync_helper(fd, file, on, &fc->iq.fasync); } +static int fuse_device_clone(struct fuse_conn *fc, struct file *new) +{ + if (new->private_data) + return -EINVAL; + + new->private_data = fuse_conn_get(fc); + + return 0; +} + +static long fuse_dev_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + int err = -ENOTTY; + + if (cmd == FUSE_DEV_IOC_CLONE) { + int oldfd; + + err = -EFAULT; + if (!get_user(oldfd, (__u32 __user *) arg)) { + struct file *old = fget(oldfd); + + err = -EINVAL; + if (old) { + struct fuse_conn *fc = fuse_get_conn(old); + + if (fc) { + mutex_lock(&fuse_mutex); + err = fuse_device_clone(fc, file); + mutex_unlock(&fuse_mutex); + } + fput(old); + } + } + } + return err; +} + const struct file_operations fuse_dev_operations = { .owner = THIS_MODULE, .open = fuse_dev_open, @@ -2208,6 +2246,8 @@ const struct file_operations fuse_dev_operations = { .poll = fuse_dev_poll, .release = fuse_dev_release, .fasync = fuse_dev_fasync, + .unlocked_ioctl = fuse_dev_ioctl, + .compat_ioctl = fuse_dev_ioctl, }; EXPORT_SYMBOL_GPL(fuse_dev_operations); diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 25084a052a1e..c9aca042e61d 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -755,4 +755,7 @@ struct fuse_notify_retrieve_in { uint64_t dummy4; }; +/* Device ioctls: */ +#define FUSE_DEV_IOC_CLONE _IOR(229, 0, uint32_t) + #endif /* _LINUX_FUSE_H */ -- cgit v1.2.3 From 974d7af5fcc295dcf8315255142b2fe44fd74b0c Mon Sep 17 00:00:00 2001 From: Andy Gospodarek Date: Tue, 7 Jul 2015 13:56:57 -0400 Subject: ipv4: add support for linkdown sysctl to netconf This kernel patch exports the value of the new ignore_routes_with_linkdown via netconf. v2: changes to notify userspace via netlink when sysctl values change and proposed for 'net' since this could be considered a bugfix Signed-off-by: Andy Gospodarek Suggested-by: Nicolas Dichtel Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- include/uapi/linux/netconf.h | 1 + net/ipv4/devinet.c | 13 +++++++++++++ 2 files changed, 14 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h index 669a1f0b1d97..23cbd34e4ac7 100644 --- a/include/uapi/linux/netconf.h +++ b/include/uapi/linux/netconf.h @@ -15,6 +15,7 @@ enum { NETCONFA_RP_FILTER, NETCONFA_MC_FORWARDING, NETCONFA_PROXY_NEIGH, + NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, __NETCONFA_MAX }; #define NETCONFA_MAX (__NETCONFA_MAX - 1) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 7498716e8f54..e813196c91c7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1740,6 +1740,8 @@ static int inet_netconf_msgsize_devconf(int type) size += nla_total_size(4); if (type == -1 || type == NETCONFA_PROXY_NEIGH) size += nla_total_size(4); + if (type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) + size += nla_total_size(4); return size; } @@ -1780,6 +1782,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex, nla_put_s32(skb, NETCONFA_PROXY_NEIGH, IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0) goto nla_put_failure; + if ((type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) && + nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -1819,6 +1825,7 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_FORWARDING] = { .len = sizeof(int) }, [NETCONFA_RP_FILTER] = { .len = sizeof(int) }, [NETCONFA_PROXY_NEIGH] = { .len = sizeof(int) }, + [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; static int inet_netconf_get_devconf(struct sk_buff *in_skb, @@ -2048,6 +2055,12 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write, inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH, ifindex, cnf); } + if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 && + new_value != old_value) { + ifindex = devinet_conf_ifindex(net, cnf); + inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN, + ifindex, cnf); + } } return ret; -- cgit v1.2.3