| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <0497f70f-3c6a-4ecc-97e9-4487b3531810@daynix.com>
Date: Sun, 8 Jun 2025 15:16:54 +0900
From: Akihiko Odaki <akihiko.odaki@...nix.com>
To: Paolo Abeni <pabeni@...hat.com>, netdev@...r.kernel.org
Cc: Willem de Bruijn <willemdebruijn.kernel@...il.com>,
Jason Wang <jasowang@...hat.com>, Andrew Lunn <andrew+netdev@...n.ch>,
"David S. Miller" <davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>, "Michael S. Tsirkin" <mst@...hat.com>,
Xuan Zhuo <xuanzhuo@...ux.alibaba.com>, Eugenio Pérez
<eperezma@...hat.com>, Yuri Benditovich <yuri.benditovich@...nix.com>
Subject: Re: [PATCH RFC v3 3/8] vhost-net: allow configuring extended features
On 2025/06/06 20:45, Paolo Abeni wrote:
> Use the extended feature type for 'acked_features' and implement
> two new ioctls operation allowing the user-space to set/query an
> unbounded amount of features.
>
> The actual number of processed features is limited by VIRTIO_FEATURES_MAX
> and attempts to set features above such limit fail with
> EOPNOTSUPP.
>
> Note that: the legacy ioctls implicitly truncate the negotiated
> features to the lower 64 bits range and the 'acked_backend_features'
> field don't need conversion, as the only negotiated feature there
> is in the low 64 bit range.
>
> Signed-off-by: Paolo Abeni <pabeni@...hat.com>
> ---
> v2 -> v3:
> - virtio_features_t -> u64[2]
> - add __counted_by annotation to vhost_features_array
>
> v1 -> v2:
> - change the ioctl to use an extensible API
> ---
> drivers/vhost/net.c | 85 +++++++++++++++++++++++++++-----
> drivers/vhost/vhost.c | 2 +-
> drivers/vhost/vhost.h | 4 +-
> include/uapi/linux/vhost.h | 7 +++
> include/uapi/linux/vhost_types.h | 5 ++
> 5 files changed, 88 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 7cbfc7d718b3..0291fce24bbf 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -77,6 +77,8 @@ enum {
> (1ULL << VIRTIO_F_RING_RESET)
> };
>
> +const u64 VHOST_NET_ALL_FEATURES[VIRTIO_FEATURES_DWORDS] = { VHOST_NET_FEATURES };
This should have static.
Probably it should be lower-case too.
Documentation/process/coding-style.rst says: "Names of macros defining
constants and labels in enums are capitalized". Note that variables are
not named here.
I think it's also better to remove the definition of VHOST_NET_FEATURES
since having two definitions with similar names and meaning is
confusing. (Just in case you wonder: GCC is able to optimize accesses
like "VHOST_NET_ALL_FEATURES[0]" to eliminate array accesses, by the way.)
> +
> enum {
> VHOST_NET_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2)
> };
> @@ -1614,16 +1616,17 @@ static long vhost_net_reset_owner(struct vhost_net *n)
> return err;
> }
>
> -static int vhost_net_set_features(struct vhost_net *n, u64 features)
> +static int vhost_net_set_features(struct vhost_net *n, const u64 *features)
> {
> size_t vhost_hlen, sock_hlen, hdr_len;
> int i;
>
> - hdr_len = (features & ((1ULL << VIRTIO_NET_F_MRG_RXBUF) |
> - (1ULL << VIRTIO_F_VERSION_1))) ?
> - sizeof(struct virtio_net_hdr_mrg_rxbuf) :
> - sizeof(struct virtio_net_hdr);
> - if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) {
> + hdr_len = virtio_features_test_bit(features, VIRTIO_NET_F_MRG_RXBUF) ||
> + virtio_features_test_bit(features, VIRTIO_F_VERSION_1) ?
> + sizeof(struct virtio_net_hdr_mrg_rxbuf) :
> + sizeof(struct virtio_net_hdr);
> +
> + if (virtio_features_test_bit(features, VHOST_NET_F_VIRTIO_NET_HDR)) {
> /* vhost provides vnet_hdr */
> vhost_hlen = hdr_len;
> sock_hlen = 0;
> @@ -1633,18 +1636,19 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
> sock_hlen = hdr_len;
> }
> mutex_lock(&n->dev.mutex);
> - if ((features & (1 << VHOST_F_LOG_ALL)) &&
> + if (virtio_features_test_bit(features, VHOST_F_LOG_ALL) &&
> !vhost_log_access_ok(&n->dev))
> goto out_unlock;
>
> - if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
> + if (virtio_features_test_bit(features, VIRTIO_F_ACCESS_PLATFORM)) {
> if (vhost_init_device_iotlb(&n->dev))
> goto out_unlock;
> }
>
> for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
> mutex_lock(&n->vqs[i].vq.mutex);
> - n->vqs[i].vq.acked_features = features;
> + virtio_features_copy(n->vqs[i].vq.acked_features_array,
> + features);
> n->vqs[i].vhost_hlen = vhost_hlen;
> n->vqs[i].sock_hlen = sock_hlen;
> mutex_unlock(&n->vqs[i].vq.mutex);
> @@ -1681,12 +1685,13 @@ static long vhost_net_set_owner(struct vhost_net *n)
> static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
> unsigned long arg)
> {
> + u64 all_features[VIRTIO_FEATURES_DWORDS];
> struct vhost_net *n = f->private_data;
> void __user *argp = (void __user *)arg;
> u64 __user *featurep = argp;
> struct vhost_vring_file backend;
> - u64 features;
> - int r;
> + u64 features, count;
> + int r, i;
>
> switch (ioctl) {
> case VHOST_NET_SET_BACKEND:
> @@ -1703,7 +1708,63 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
> return -EFAULT;
> if (features & ~VHOST_NET_FEATURES)
> return -EOPNOTSUPP;
> - return vhost_net_set_features(n, features);
> +
> + virtio_features_from_u64(all_features, features);
> + return vhost_net_set_features(n, all_features);
> + case VHOST_GET_FEATURES_ARRAY:
> + {
> + if (copy_from_user(&count, argp, sizeof(u64)))
> + return -EFAULT;
> +
> + /* Copy the net features, up to the user-provided buffer size */
> + virtio_features_copy(all_features, VHOST_NET_ALL_FEATURES);
> + argp += sizeof(u64);
> + for (i = 0; i < min(count, VIRTIO_FEATURES_DWORDS); ++i) {
> + i = array_index_nospec(i, VIRTIO_FEATURES_DWORDS);
> + if (copy_to_user(argp, &all_features[i], sizeof(u64)))
> + return -EFAULT;
> +
> + argp += sizeof(u64);
> + }
Simpler:
copy_to_user(argp, all_features, min(count, VIRTIO_FEATURES_DWORDS) *
sizeof(u64));
> +
> + /* Zero the trailing space provided by user-space, if any */
> + if (i < count && clear_user(argp, (count - i) * sizeof(u64)))
I think checking i < count is a premature optimization; it doesn't
matter even if we spend a bit longer because of the lack of the check.
> + return -EFAULT;
> + return 0;
> + }
> + case VHOST_SET_FEATURES_ARRAY:
> + {
> + u64 tmp[VIRTIO_FEATURES_DWORDS];
> +
> + if (copy_from_user(&count, argp, sizeof(u64)))
> + return -EFAULT;
> +
> + virtio_features_zero(all_features);
> + for (i = 0; i < min(count, VIRTIO_FEATURES_DWORDS); ++i) {
> + argp += sizeof(u64);
> + if (copy_from_user(&features, argp, sizeof(u64)))
> + return -EFAULT;
> +
> + all_features[i] = features;
> + }
> +
> + /* Any feature specified by user-space above VIRTIO_FEATURES_MAX is
> + * not supported by definition.
> + */
> + for (; i < count; ++i) {
> + if (copy_from_user(&features, argp, sizeof(u64)))
> + return -EFAULT;
> + if (features)
> + return -EOPNOTSUPP;
> + }
> +
> + virtio_features_and_not(tmp, all_features, VHOST_NET_ALL_FEATURES);
> + for (i = 0; i < VIRTIO_FEATURES_DWORDS; i++)
> + if (tmp[i])
I think using virtio_features_and_not() helps much. Instead, we can
check all_features[i] & ~VHOST_NET_ALL_FEATURES[i] here, allowing to
remove the tmp array.
Regards,
Akihiko Odaki
> + return -EOPNOTSUPP;> +
> + return vhost_net_set_features(n, all_features);
> + }
> case VHOST_GET_BACKEND_FEATURES:
> features = VHOST_NET_BACKEND_FEATURES;
> if (copy_to_user(featurep, &features, sizeof(features)))
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 63612faeab72..6d3b9f0a9163 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -372,7 +372,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
> vq->log_used = false;
> vq->log_addr = -1ull;
> vq->private_data = NULL;
> - vq->acked_features = 0;
> + virtio_features_zero(vq->acked_features_array);
> vq->acked_backend_features = 0;
> vq->log_base = NULL;
> vq->error_ctx = NULL;
> diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
> index bb75a292d50c..d1aed35c4b07 100644
> --- a/drivers/vhost/vhost.h
> +++ b/drivers/vhost/vhost.h
> @@ -133,7 +133,7 @@ struct vhost_virtqueue {
> struct vhost_iotlb *umem;
> struct vhost_iotlb *iotlb;
> void *private_data;
> - u64 acked_features;
> + VIRTIO_DECLARE_FEATURES(acked_features);
> u64 acked_backend_features;
> /* Log write descriptors */
> void __user *log_base;
> @@ -291,7 +291,7 @@ static inline void *vhost_vq_get_backend(struct vhost_virtqueue *vq)
>
> static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
> {
> - return vq->acked_features & (1ULL << bit);
> + return virtio_features_test_bit(vq->acked_features_array, bit);
> }
>
> static inline bool vhost_backend_has_feature(struct vhost_virtqueue *vq, int bit)
> diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
> index d4b3e2ae1314..d6ad01fbb8d2 100644
> --- a/include/uapi/linux/vhost.h
> +++ b/include/uapi/linux/vhost.h
> @@ -235,4 +235,11 @@
> */
> #define VHOST_VDPA_GET_VRING_SIZE _IOWR(VHOST_VIRTIO, 0x82, \
> struct vhost_vring_state)
> +
> +/* Extended features manipulation */
> +#define VHOST_GET_FEATURES_ARRAY _IOR(VHOST_VIRTIO, 0x83, \
> + struct vhost_features_array)
> +#define VHOST_SET_FEATURES_ARRAY _IOW(VHOST_VIRTIO, 0x83, \
> + struct vhost_features_array)
> +
> #endif
> diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
> index d7656908f730..1c39cc5f5a31 100644
> --- a/include/uapi/linux/vhost_types.h
> +++ b/include/uapi/linux/vhost_types.h
> @@ -110,6 +110,11 @@ struct vhost_msg_v2 {
> };
> };
>
> +struct vhost_features_array {
> + __u64 count; /* number of entries present in features array */
> + __u64 features[] __counted_by(count);
> +};
> +
> struct vhost_memory_region {
> __u64 guest_phys_addr;
> __u64 memory_size; /* bytes */
Powered by blists - more mailing lists