linux-kernel - Re: [PATCH v3 10/13] xen/pvcalls: implement recvmsg

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
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <f9e15125-bf79-fc8d-2df3-2857aab62f9a@oracle.com>
Date:   Mon, 14 Aug 2017 22:39:02 -0400
From:   Boris Ostrovsky <boris.ostrovsky@...cle.com>
To:     Stefano Stabellini <sstabellini@...nel.org>,
        xen-devel@...ts.xen.org
Cc:     linux-kernel@...r.kernel.org, jgross@...e.com,
        Stefano Stabellini <stefano@...reto.com>
Subject: Re: [PATCH v3 10/13] xen/pvcalls: implement recvmsg



On 07/31/2017 06:57 PM, Stefano Stabellini wrote:
> Implement recvmsg by copying data from the "in" ring. If not enough data
> is available and the recvmsg call is blocking, then wait on the
> inflight_conn_req waitqueue. Take the active socket in_mutex so that
> only one function can access the ring at any given time.
> 
> If no data is available on the ring, rather than returning immediately
> or sleep-waiting, spin for up to 5000 cycles. This small optimization
> turns out to improve performance and latency significantly.
> 
> Signed-off-by: Stefano Stabellini <stefano@...reto.com>
> CC: boris.ostrovsky@...cle.com
> CC: jgross@...e.com
> ---
>   drivers/xen/pvcalls-front.c | 102 ++++++++++++++++++++++++++++++++++++++++++++
>   drivers/xen/pvcalls-front.h |   4 ++
>   2 files changed, 106 insertions(+)
> 
> diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c
> index 369acde..635a83a 100644
> --- a/drivers/xen/pvcalls-front.c
> +++ b/drivers/xen/pvcalls-front.c
> @@ -105,6 +105,20 @@ static int pvcalls_front_write_todo(struct sock_mapping *map)
>   	return size - pvcalls_queued(prod, cons, size);
>   }
>   
> +static bool pvcalls_front_read_todo(struct sock_mapping *map)
> +{
> +	struct pvcalls_data_intf *intf = map->active.ring;
> +	RING_IDX cons, prod;
> +	int32_t error;
> +
> +	cons = intf->in_cons;
> +	prod = intf->in_prod;
> +	error = intf->in_error;
> +	return (error != 0 ||
> +		pvcalls_queued(prod, cons,
> +			       XEN_FLEX_RING_SIZE(intf->ring_order)) != 0);
> +}
> +
>   static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
>   {
>   	struct xenbus_device *dev = dev_id;
> @@ -434,6 +448,94 @@ int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg,
>   	return tot_sent;
>   }
>   
> +static int __read_ring(struct pvcalls_data_intf *intf,
> +		       struct pvcalls_data *data,
> +		       struct iov_iter *msg_iter,
> +		       size_t len, int flags)
> +{
> +	RING_IDX cons, prod, size, masked_prod, masked_cons;
> +	RING_IDX array_size = XEN_FLEX_RING_SIZE(intf->ring_order);
> +	int32_t error;
> +
> +	cons = intf->in_cons;
> +	prod = intf->in_prod;
> +	error = intf->in_error;
> +	/* get pointers before reading from the ring */
> +	virt_rmb();
> +	if (error < 0)
> +		return error;
> +
> +	size = pvcalls_queued(prod, cons, array_size);
> +	masked_prod = pvcalls_mask(prod, array_size);
> +	masked_cons = pvcalls_mask(cons, array_size);
> +
> +	if (size == 0)
> +		return 0;
> +
> +	if (len > size)
> +		len = size;
> +
> +	if (masked_prod > masked_cons) {
> +		copy_to_iter(data->in + masked_cons, len, msg_iter);
> +	} else {
> +		if (len > (array_size - masked_cons)) {
> +			copy_to_iter(data->in + masked_cons,
> +				     array_size - masked_cons, msg_iter);
> +			copy_to_iter(data->in,
> +				     len - (array_size - masked_cons),
> +				     msg_iter);
> +		} else {
> +			copy_to_iter(data->in + masked_cons, len, msg_iter);
> +		}
> +	}
> +	/* read data from the ring before increasing the index */
> +	virt_mb();
> +	if (!(flags & MSG_PEEK))
> +		intf->in_cons += len;
> +
> +	return len;
> +}
> +
> +int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
> +		     int flags)
> +{
> +	struct pvcalls_bedata *bedata;
> +	int ret = -EAGAIN;

Not necessary to initialize.

> +	struct sock_mapping *map;
> +
> +	if (!pvcalls_front_dev)
> +		return -ENOTCONN;
> +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> +
> +	map = (struct sock_mapping *) READ_ONCE(sock->sk->sk_send_head);
> +	if (!map)
> +		return -ENOTSOCK;
> +
> +	if (flags & (MSG_CMSG_CLOEXEC|MSG_ERRQUEUE|MSG_OOB|MSG_TRUNC))
> +		return -EOPNOTSUPP;
> +
> +	mutex_lock(&map->active.in_mutex);
> +	if (len > XEN_FLEX_RING_SIZE(map->active.ring->ring_order))
> +		len = XEN_FLEX_RING_SIZE(map->active.ring->ring_order);
> +
> +	while (!(flags & MSG_DONTWAIT) && !pvcalls_front_read_todo(map)) {
> +		wait_event_interruptible(map->active.inflight_conn_req,
> +					 pvcalls_front_read_todo(map));
> +	}
> +	ret = __read_ring(map->active.ring, &map->active.data,
> +			  &msg->msg_iter, len, flags);
> +
> +	if (ret > 0)
> +		notify_remote_via_irq(map->active.irq);
> +	if (ret == 0)
> +		ret = -EAGAIN;
> +	if (ret == -ENOTCONN)
> +		ret = 0;
> +
> +	mutex_unlock(&map->active.in_mutex);
> +	return ret;

Are errors converted by the caller? (I am asking because recvmsg can 
only return -1 for errors)

-boris

> +}
> +
>   int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
>   {
>   	struct pvcalls_bedata *bedata;
> diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h
> index d937c24..de24041 100644
> --- a/drivers/xen/pvcalls-front.h
> +++ b/drivers/xen/pvcalls-front.h
> @@ -16,5 +16,9 @@ int pvcalls_front_accept(struct socket *sock,
>   int pvcalls_front_sendmsg(struct socket *sock,
>   			  struct msghdr *msg,
>   			  size_t len);
> +int pvcalls_front_recvmsg(struct socket *sock,
> +			  struct msghdr *msg,
> +			  size_t len,
> +			  int flags);
>   
>   #endif
>