Subject: Re: [PATCH v4 04/13] xen/pvcalls: implement socket command and handle
 events
To: Stefano Stabellini <sstabellini@kernel.org>, xen-devel@lists.xen.org
Cc: linux-kernel@vger.kernel.org, jgross@suse.com,
        Stefano Stabellini <stefano@aporeto.com>
References: <alpine.DEB.2.10.1709121550270.9439@sstabellini-ThinkPad-X260>
 <1505516440-11111-1-git-send-email-sstabellini@kernel.org>
 <1505516440-11111-4-git-send-email-sstabellini@kernel.org>
From: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Message-ID: <e352bbba-e1d9-83df-239c-589f1639aff3@oracle.com>
Date: Thu, 21 Sep 2017 13:42:56 -0400
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101
 Thunderbird/52.3.0
MIME-Version: 1.0
In-Reply-To: <1505516440-11111-4-git-send-email-sstabellini@kernel.org>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 4183
Lines: 153


> +
> +static inline int get_request(struct pvcalls_bedata *bedata, int *req_id)
> +{
> +	*req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1);
> +	if (RING_FULL(&bedata->ring) ||
> +	    READ_ONCE(bedata->rsp[*req_id].req_id) != PVCALLS_INVALID_ID)
> +		return -EAGAIN;
> +	return 0;
> +}
> +
>   static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id)
>   {
> +	struct xenbus_device *dev = dev_id;
> +	struct pvcalls_bedata *bedata;
> +	struct xen_pvcalls_response *rsp;
> +	uint8_t *src, *dst;
> +	int req_id = 0, more = 0, done = 0;
> +
> +	if (dev == NULL)
> +		return IRQ_HANDLED;
> +
> +	pvcalls_enter;
> +	bedata = dev_get_drvdata(&dev->dev);
> +	if (bedata == NULL) {
> +		pvcalls_exit;
> +		return IRQ_HANDLED;
> +	}
> +
> +again:
> +	while (RING_HAS_UNCONSUMED_RESPONSES(&bedata->ring)) {
> +		rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons);
> +
> +		req_id = rsp->req_id;
> +		dst = (uint8_t *)&bedata->rsp[req_id] + sizeof(rsp->req_id);
> +		src = (uint8_t *)rsp + sizeof(rsp->req_id);
> +		memcpy(dst, src, sizeof(*rsp) - sizeof(rsp->req_id));
> +		/*
> +		 * First copy the rest of the data, then req_id. It is
> +		 * paired with the barrier when accessing bedata->rsp.
> +		 */
> +		smp_wmb();
> +		WRITE_ONCE(bedata->rsp[req_id].req_id, rsp->req_id);
> +
> +		done = 1;
> +		bedata->ring.rsp_cons++;
> +	}
> +
> +	RING_FINAL_CHECK_FOR_RESPONSES(&bedata->ring, more);
> +	if (more)
> +		goto again;
> +	if (done)
> +		wake_up(&bedata->inflight_req);
> +	pvcalls_exit;
>   	return IRQ_HANDLED;
>   }
>   
> +int pvcalls_front_socket(struct socket *sock)
> +{
> +	struct pvcalls_bedata *bedata;
> +	struct sock_mapping *map = NULL;
> +	struct xen_pvcalls_request *req;
> +	int notify, req_id, ret;
> +
> +	pvcalls_enter;


Can you define enter/exit macros with parentheses (i.e. 
"pvcalls_enter/exit()')?


> +	if (!pvcalls_front_dev) {
> +		pvcalls_exit;
> +		return -EACCES;
> +	}
> +	/*
> +	 * PVCalls only supports domain AF_INET,
> +	 * type SOCK_STREAM and protocol 0 sockets for now.
> +	 *
> +	 * Check socket type here, AF_INET and protocol checks are done
> +	 * by the caller.
> +	 */
> +	if (sock->type != SOCK_STREAM) {
> +		pvcalls_exit;
> +		return -ENOTSUPP;
> +	}


This can be done without entering pvcalls. I think you can enter pvcalls 
at least right before grabbing socket lock (you may need to move 
dev_get_drvdata() lower).

(possibly in later patches too)


> +
> +	bedata = dev_get_drvdata(&pvcalls_front_dev->dev);
> +
> +	map = kzalloc(sizeof(*map), GFP_KERNEL);
> +	if (map == NULL) {
> +		pvcalls_exit;
> +		return -ENOMEM;
> +	}
> +
> +	spin_lock(&bedata->socket_lock);
> +
> +	ret = get_request(bedata, &req_id);
> +	if (ret < 0) {
> +		kfree(map);
> +		spin_unlock(&bedata->socket_lock);
> +		pvcalls_exit;
> +		return ret;
> +	}
> +
> +	/*
> +	 * sock->sk->sk_send_head is not used for ip sockets: reuse the
> +	 * field to store a pointer to the struct sock_mapping
> +	 * corresponding to the socket. This way, we can easily get the
> +	 * struct sock_mapping from the struct socket.
> +	 */
> +	sock->sk->sk_send_head = (void *)map;
> +	list_add_tail(&map->list, &bedata->socket_mappings);
> +
> +	req = RING_GET_REQUEST(&bedata->ring, req_id);
> +	req->req_id = req_id;
> +	req->cmd = PVCALLS_SOCKET;
> +	req->u.socket.id = (uint64_t) map;
> +	req->u.socket.domain = AF_INET;
> +	req->u.socket.type = SOCK_STREAM;
> +	req->u.socket.protocol = IPPROTO_IP;
> +
> +	bedata->ring.req_prod_pvt++;
> +	RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify);
> +	spin_unlock(&bedata->socket_lock);
> +	if (notify)
> +		notify_remote_via_irq(bedata->irq);
> +
> +	wait_event(bedata->inflight_req,
> +		   READ_ONCE(bedata->rsp[req_id].req_id) == req_id);
> +
> +	ret = bedata->rsp[req_id].ret;
> +	/* read ret, then set this rsp slot to be reused */
> +	smp_mb();
> +	WRITE_ONCE(bedata->rsp[req_id].req_id, PVCALLS_INVALID_ID);

Now that I looked at what *_ONCE macros do I am not sure this is needed, 
given the smp_mb() above. In pvcalls_front_event_handler() too. And, in 
fact, in get_request() as well.

(Again, this will probably be also applicable to subsequent patches)

-boris