| 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: <f0bca831-207c-6cbb-48e9-7d2ea02229ff@gmail.com>
Date: Thu, 27 Jul 2023 10:53:14 +0300
From: Arseniy Krasnov <oxffffaa@...il.com>
To: Bobby Eshleman <bobbyeshleman@...il.com>
Cc: Bobby Eshleman <bobby.eshleman@...edance.com>,
Stefan Hajnoczi <stefanha@...hat.com>,
Stefano Garzarella <sgarzare@...hat.com>, "Michael S. Tsirkin"
<mst@...hat.com>, Jason Wang <jasowang@...hat.com>,
Xuan Zhuo <xuanzhuo@...ux.alibaba.com>, "David S. Miller"
<davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>, Paolo Abeni <pabeni@...hat.com>,
"K. Y. Srinivasan" <kys@...rosoft.com>,
Haiyang Zhang <haiyangz@...rosoft.com>, Wei Liu <wei.liu@...nel.org>,
Dexuan Cui <decui@...rosoft.com>, Bryan Tan <bryantan@...are.com>,
Vishnu Dasa <vdasa@...are.com>,
VMware PV-Drivers Reviewers <pv-drivers@...are.com>,
Dan Carpenter <dan.carpenter@...aro.org>,
Simon Horman <simon.horman@...igine.com>, kvm@...r.kernel.org,
virtualization@...ts.linux-foundation.org, netdev@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-hyperv@...r.kernel.org,
bpf@...r.kernel.org
Subject: Re: [PATCH RFC net-next v5 01/14] af_vsock: generalize
vsock_dgram_recvmsg() to all transports
On 26.07.2023 21:21, Bobby Eshleman wrote:
> On Mon, Jul 24, 2023 at 09:11:44PM +0300, Arseniy Krasnov wrote:
>>
>>
>> On 19.07.2023 03:50, Bobby Eshleman wrote:
>>> This commit drops the transport->dgram_dequeue callback and makes
>>> vsock_dgram_recvmsg() generic to all transports.
>>>
>>> To make this possible, two transport-level changes are introduced:
>>> - implementation of the ->dgram_addr_init() callback to initialize
>>> the sockaddr_vm structure with data from incoming socket buffers.
>>> - transport implementations set the skb->data pointer to the beginning
>>> of the payload prior to adding the skb to the socket's receive queue.
>>> That is, they must use skb_pull() before enqueuing. This is an
>>> agreement between the transport and the socket layer that skb->data
>>> always points to the beginning of the payload (and not, for example,
>>> the packet header).
>>>
>>> Signed-off-by: Bobby Eshleman <bobby.eshleman@...edance.com>
>>> ---
>>> drivers/vhost/vsock.c | 1 -
>>> include/linux/virtio_vsock.h | 5 ---
>>> include/net/af_vsock.h | 3 +-
>>> net/vmw_vsock/af_vsock.c | 40 ++++++++++++++++++++++-
>>> net/vmw_vsock/hyperv_transport.c | 7 ----
>>> net/vmw_vsock/virtio_transport.c | 1 -
>>> net/vmw_vsock/virtio_transport_common.c | 9 -----
>>> net/vmw_vsock/vmci_transport.c | 58 ++++++---------------------------
>>> net/vmw_vsock/vsock_loopback.c | 1 -
>>> 9 files changed, 50 insertions(+), 75 deletions(-)
>>>
>>> diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
>>> index 6578db78f0ae..ae8891598a48 100644
>>> --- a/drivers/vhost/vsock.c
>>> +++ b/drivers/vhost/vsock.c
>>> @@ -410,7 +410,6 @@ static struct virtio_transport vhost_transport = {
>>> .cancel_pkt = vhost_transport_cancel_pkt,
>>>
>>> .dgram_enqueue = virtio_transport_dgram_enqueue,
>>> - .dgram_dequeue = virtio_transport_dgram_dequeue,
>>> .dgram_bind = virtio_transport_dgram_bind,
>>> .dgram_allow = virtio_transport_dgram_allow,
>>>
>>> diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
>>> index c58453699ee9..18cbe8d37fca 100644
>>> --- a/include/linux/virtio_vsock.h
>>> +++ b/include/linux/virtio_vsock.h
>>> @@ -167,11 +167,6 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk,
>>> size_t len,
>>> int type);
>>> int
>>> -virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
>>> - struct msghdr *msg,
>>> - size_t len, int flags);
>>> -
>>> -int
>>> virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk,
>>> struct msghdr *msg,
>>> size_t len);
>>> diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
>>> index 0e7504a42925..305d57502e89 100644
>>> --- a/include/net/af_vsock.h
>>> +++ b/include/net/af_vsock.h
>>> @@ -120,11 +120,10 @@ struct vsock_transport {
>>>
>>> /* DGRAM. */
>>> int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *);
>>> - int (*dgram_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
>>> - size_t len, int flags);
>>> int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *,
>>> struct msghdr *, size_t len);
>>> bool (*dgram_allow)(u32 cid, u32 port);
>>> + void (*dgram_addr_init)(struct sk_buff *skb, struct sockaddr_vm *addr);
>>>
>>> /* STREAM. */
>>> /* TODO: stream_bind() */
>>> diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
>>> index deb72a8c44a7..ad71e084bf2f 100644
>>> --- a/net/vmw_vsock/af_vsock.c
>>> +++ b/net/vmw_vsock/af_vsock.c
>>> @@ -1272,11 +1272,15 @@ static int vsock_dgram_connect(struct socket *sock,
>>> int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
>>> size_t len, int flags)
>>> {
>>> + const struct vsock_transport *transport;
>>> #ifdef CONFIG_BPF_SYSCALL
>>> const struct proto *prot;
>>> #endif
>>> struct vsock_sock *vsk;
>>> + struct sk_buff *skb;
>>> + size_t payload_len;
>>> struct sock *sk;
>>> + int err;
>>>
>>> sk = sock->sk;
>>> vsk = vsock_sk(sk);
>>> @@ -1287,7 +1291,41 @@ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
>>> return prot->recvmsg(sk, msg, len, flags, NULL);
>>> #endif
>>>
>>> - return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
>>> + if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
>>> + return -EOPNOTSUPP;
>>> +
>>> + transport = vsk->transport;
>>> +
>>> + /* Retrieve the head sk_buff from the socket's receive queue. */
>>> + err = 0;
>>> + skb = skb_recv_datagram(sk_vsock(vsk), flags, &err);
>>> + if (!skb)
>>> + return err;
>>> +
>>> + payload_len = skb->len;
>>> +
>>> + if (payload_len > len) {
>>> + payload_len = len;
>>> + msg->msg_flags |= MSG_TRUNC;
>>> + }
>>> +
>>> + /* Place the datagram payload in the user's iovec. */
>>> + err = skb_copy_datagram_msg(skb, 0, msg, payload_len);
>>> + if (err)
>>> + goto out;
>>> +
>>> + if (msg->msg_name) {
>>> + /* Provide the address of the sender. */
>>> + DECLARE_SOCKADDR(struct sockaddr_vm *, vm_addr, msg->msg_name);
>>> +
>>> + transport->dgram_addr_init(skb, vm_addr);
>>
>> Do we need check that dgram_addr_init != NULL? because I see that not all transports have this
>> callback set in this patch
>>
>
> How about adding the check somewhere outside of the hotpath, such as
> when the transport is assigned?
Yes, may be we can return ESOCKTNOSUPPORT if this callback is not provided by transport (as we dereference
it here without any checks).
Thanks, Arseniy
>
>>> + msg->msg_namelen = sizeof(*vm_addr);
>>> + }
>>> + err = payload_len;
>>> +
>>> +out:
>>> + skb_free_datagram(&vsk->sk, skb);
>>> + return err;
>>> }
>>> EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg);
>>>
>>> diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
>>> index 7cb1a9d2cdb4..7f1ea434656d 100644
>>> --- a/net/vmw_vsock/hyperv_transport.c
>>> +++ b/net/vmw_vsock/hyperv_transport.c
>>> @@ -556,12 +556,6 @@ static int hvs_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr)
>>> return -EOPNOTSUPP;
>>> }
>>>
>>> -static int hvs_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg,
>>> - size_t len, int flags)
>>> -{
>>> - return -EOPNOTSUPP;
>>> -}
>>> -
>>> static int hvs_dgram_enqueue(struct vsock_sock *vsk,
>>> struct sockaddr_vm *remote, struct msghdr *msg,
>>> size_t dgram_len)
>>> @@ -833,7 +827,6 @@ static struct vsock_transport hvs_transport = {
>>> .shutdown = hvs_shutdown,
>>>
>>> .dgram_bind = hvs_dgram_bind,
>>> - .dgram_dequeue = hvs_dgram_dequeue,
>>> .dgram_enqueue = hvs_dgram_enqueue,
>>> .dgram_allow = hvs_dgram_allow,
>>>
>>> diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
>>> index e95df847176b..66edffdbf303 100644
>>> --- a/net/vmw_vsock/virtio_transport.c
>>> +++ b/net/vmw_vsock/virtio_transport.c
>>> @@ -429,7 +429,6 @@ static struct virtio_transport virtio_transport = {
>>> .cancel_pkt = virtio_transport_cancel_pkt,
>>>
>>> .dgram_bind = virtio_transport_dgram_bind,
>>> - .dgram_dequeue = virtio_transport_dgram_dequeue,
>>> .dgram_enqueue = virtio_transport_dgram_enqueue,
>>> .dgram_allow = virtio_transport_dgram_allow,
>>>
>>> diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
>>> index b769fc258931..01ea1402ad40 100644
>>> --- a/net/vmw_vsock/virtio_transport_common.c
>>> +++ b/net/vmw_vsock/virtio_transport_common.c
>>> @@ -583,15 +583,6 @@ virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk,
>>> }
>>> EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue);
>>>
>>> -int
>>> -virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
>>> - struct msghdr *msg,
>>> - size_t len, int flags)
>>> -{
>>> - return -EOPNOTSUPP;
>>> -}
>>> -EXPORT_SYMBOL_GPL(virtio_transport_dgram_dequeue);
>>> -
>>> s64 virtio_transport_stream_has_data(struct vsock_sock *vsk)
>>> {
>>> struct virtio_vsock_sock *vvs = vsk->trans;
>>> diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
>>> index b370070194fa..0bbbdb222245 100644
>>> --- a/net/vmw_vsock/vmci_transport.c
>>> +++ b/net/vmw_vsock/vmci_transport.c
>>> @@ -641,6 +641,7 @@ static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg)
>>> sock_hold(sk);
>>> skb_put(skb, size);
>>> memcpy(skb->data, dg, size);
>>> + skb_pull(skb, VMCI_DG_HEADERSIZE);
>>> sk_receive_skb(sk, skb, 0);
>>>
>>> return VMCI_SUCCESS;
>>> @@ -1731,57 +1732,18 @@ static int vmci_transport_dgram_enqueue(
>>> return err - sizeof(*dg);
>>> }
>>>
>>> -static int vmci_transport_dgram_dequeue(struct vsock_sock *vsk,
>>> - struct msghdr *msg, size_t len,
>>> - int flags)
>>> +static void vmci_transport_dgram_addr_init(struct sk_buff *skb,
>>> + struct sockaddr_vm *addr)
>>> {
>>> - int err;
>>> struct vmci_datagram *dg;
>>> - size_t payload_len;
>>> - struct sk_buff *skb;
>>> -
>>> - if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
>>> - return -EOPNOTSUPP;
>>> -
>>> - /* Retrieve the head sk_buff from the socket's receive queue. */
>>> - err = 0;
>>> - skb = skb_recv_datagram(&vsk->sk, flags, &err);
>>> - if (!skb)
>>> - return err;
>>> -
>>> - dg = (struct vmci_datagram *)skb->data;
>>> - if (!dg)
>>> - /* err is 0, meaning we read zero bytes. */
>>> - goto out;
>>> -
>>> - payload_len = dg->payload_size;
>>> - /* Ensure the sk_buff matches the payload size claimed in the packet. */
>>> - if (payload_len != skb->len - sizeof(*dg)) {
>>> - err = -EINVAL;
>>> - goto out;
>>> - }
>>> -
>>> - if (payload_len > len) {
>>> - payload_len = len;
>>> - msg->msg_flags |= MSG_TRUNC;
>>> - }
>>> + unsigned int cid, port;
>>>
>>> - /* Place the datagram payload in the user's iovec. */
>>> - err = skb_copy_datagram_msg(skb, sizeof(*dg), msg, payload_len);
>>> - if (err)
>>> - goto out;
>>> -
>>> - if (msg->msg_name) {
>>> - /* Provide the address of the sender. */
>>> - DECLARE_SOCKADDR(struct sockaddr_vm *, vm_addr, msg->msg_name);
>>> - vsock_addr_init(vm_addr, dg->src.context, dg->src.resource);
>>> - msg->msg_namelen = sizeof(*vm_addr);
>>> - }
>>> - err = payload_len;
>>> + WARN_ONCE(skb->head == skb->data, "vmci vsock bug: bad dgram skb");
>>>
>>> -out:
>>> - skb_free_datagram(&vsk->sk, skb);
>>> - return err;
>>> + dg = (struct vmci_datagram *)skb->head;
>>> + cid = dg->src.context;
>>> + port = dg->src.resource;
>>> + vsock_addr_init(addr, cid, port);
>>
>> I think we
>>
>> 1) can short this to:
>>
>> vsock_addr_init(addr, dg->src.context, dg->src.resource);
>>
>> 2) w/o previous point, cid and port better be u32, as VMCI structure has u32 fields 'context' and
>> 'resource' and 'vsock_addr_init()' also has u32 type for both arguments.
>>
>> Thanks, Arseniy
>
> Sounds good, thanks.
>
>>
>>> }
>>>
>>> static bool vmci_transport_dgram_allow(u32 cid, u32 port)
>>> @@ -2040,9 +2002,9 @@ static struct vsock_transport vmci_transport = {
>>> .release = vmci_transport_release,
>>> .connect = vmci_transport_connect,
>>> .dgram_bind = vmci_transport_dgram_bind,
>>> - .dgram_dequeue = vmci_transport_dgram_dequeue,
>>> .dgram_enqueue = vmci_transport_dgram_enqueue,
>>> .dgram_allow = vmci_transport_dgram_allow,
>>> + .dgram_addr_init = vmci_transport_dgram_addr_init,
>>> .stream_dequeue = vmci_transport_stream_dequeue,
>>> .stream_enqueue = vmci_transport_stream_enqueue,
>>> .stream_has_data = vmci_transport_stream_has_data,
>>> diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
>>> index 5c6360df1f31..2a59dd177c74 100644
>>> --- a/net/vmw_vsock/vsock_loopback.c
>>> +++ b/net/vmw_vsock/vsock_loopback.c
>>> @@ -62,7 +62,6 @@ static struct virtio_transport loopback_transport = {
>>> .cancel_pkt = vsock_loopback_cancel_pkt,
>>>
>>> .dgram_bind = virtio_transport_dgram_bind,
>>> - .dgram_dequeue = virtio_transport_dgram_dequeue,
>>> .dgram_enqueue = virtio_transport_dgram_enqueue,
>>> .dgram_allow = virtio_transport_dgram_allow,
>>>
>>>
>
> Thanks,
> Bobby
Powered by blists - more mailing lists