/*
* (c) 2017 Stefano Stabellini <stefano@aporeto.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
#include <linux/inet.h>
#include <linux/kthread.h>
#include <linux/list.h>
#include <linux/radix-tree.h>
#include <linux/module.h>
#include <linux/semaphore.h>
#include <linux/wait.h>
#include <net/sock.h>
#include <net/inet_common.h>
#include <net/inet_connection_sock.h>
#include <net/request_sock.h>
#include <xen/events.h>
#include <xen/grant_table.h>
#include <xen/xen.h>
#include <xen/xenbus.h>
#include <xen/interface/io/pvcalls.h>
#define PVCALLS_VERSIONS "1"
#define MAX_RING_ORDER XENBUS_MAX_RING_GRANT_ORDER
struct pvcalls_back_global {
struct list_head frontends;
struct semaphore frontends_lock;
} pvcalls_back_global;
/*
* Per-frontend data structure. It contains pointers to the command
* ring, its event channel, a list of active sockets and a tree of
* passive sockets.
*/
struct pvcalls_fedata {
struct list_head list;
struct xenbus_device *dev;
struct xen_pvcalls_sring *sring;
struct xen_pvcalls_back_ring ring;
int irq;
struct list_head socket_mappings;
struct radix_tree_root socketpass_mappings;
struct semaphore socket_lock;
};
static int pvcalls_back_socket(struct xenbus_device *dev,
struct xen_pvcalls_request *req)
{
struct pvcalls_fedata *fedata;
int ret;
struct xen_pvcalls_response *rsp;
fedata = dev_get_drvdata(&dev->dev);
if (req->u.socket.domain != AF_INET ||
req->u.socket.type != SOCK_STREAM ||
(req->u.socket.protocol != IPPROTO_IP &&
req->u.socket.protocol != AF_INET))
ret = -EAFNOSUPPORT;
else
ret = 0;
/* leave the actual socket allocation for later */
rsp = RING_GET_RESPONSE(&fedata->ring, fedata->ring.rsp_prod_pvt++);
rsp->req_id = req->req_id;
rsp->cmd = req->cmd;
rsp->u.socket.id = req->u.socket.id;
rsp->ret = ret;
return 0;
}
static int pvcalls_back_connect(struct xenbus_device *dev,
struct xen_pvcalls_request *req)
{
return 0;
}
static int pvcalls_back_release(struct xenbus_device *dev,
struct xen_pvcalls_request *req)
{
return 0;
}
static int pvcalls_back_bind(struct xenbus_device *dev,
struct xen_pvcalls_request *req)
{
return 0;
}
static int pvcalls_back_listen(struct xenbus_device *dev,
struct xen_pvcalls_request *req)
{
return 0;
}
static int pvcalls_back_accept(struct xenbus_device *dev,
struct xen_pvcalls_request *req)
{
return 0;
}
static int pvcalls_back_poll(struct xenbus_device *dev,
struct xen_pvcalls_request *req)
{
return 0;
}
static int pvcalls_back_handle_cmd(struct xenbus_device *dev,
struct xen_pvcalls_request *req)
{
int ret = 0;
switch (req->cmd) {
case PVCALLS_SOCKET:
ret = pvcalls_back_socket(dev, req);
break;
case PVCALLS_CONNECT:
ret = pvcalls_back_connect(dev, req);
break;
case PVCALLS_RELEASE:
ret = pvcalls_back_release(dev, req);
break;
case PVCALLS_BIND:
ret = pvcalls_back_bind(dev, req);
break;
case PVCALLS_LISTEN:
ret = pvcalls_back_listen(dev, req);
break;
case PVCALLS_ACCEPT:
ret = pvcalls_back_accept(dev, req);
break;
case PVCALLS_POLL:
ret = pvcalls_back_poll(dev, req);
break;
default:
{
struct pvcalls_fedata *fedata;
struct xen_pvcalls_response *rsp;
fedata = dev_get_drvdata(&dev->dev);
rsp = RING_GET_RESPONSE(
&fedata->ring, fedata->ring.rsp_prod_pvt++);
rsp->req_id = req->req_id;
rsp->cmd = req->cmd;
rsp->ret = -ENOTSUPP;
break;
}
}
return ret;
}
static void pvcalls_back_work(struct pvcalls_fedata *fedata)
{
int notify, notify_all = 0, more = 1;
struct xen_pvcalls_request req;
struct xenbus_device *dev = fedata->dev;
while (more) {
while (RING_HAS_UNCONSUMED_REQUESTS(&fedata->ring)) {
RING_COPY_REQUEST(&fedata->ring,
fedata->ring.req_cons++,
&req);
if (!pvcalls_back_handle_cmd(dev, &req)) {
RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(
&fedata->ring, notify);
notify_all += notify;
}
}
if (notify_all) {
notify_remote_via_irq(fedata->irq);
notify_all = 0;
}
RING_FINAL_CHECK_FOR_REQUESTS(&fedata->ring, more);
}
}
static irqreturn_t pvcalls_back_event(int irq, void *dev_id)
{
struct xenbus_device *dev = dev_id;
struct pvcalls_fedata *fedata = NULL;
if (dev == NULL)
return IRQ_HANDLED;
fedata = dev_get_drvdata(&dev->dev);
if (fedata == NULL)
return IRQ_HANDLED;
pvcalls_back_work(fedata);
return IRQ_HANDLED;
}
static int backend_connect(struct xenbus_device *dev)
{
int err, evtchn;
grant_ref_t ring_ref;
struct pvcalls_fedata *fedata = NULL;
fedata = kzalloc(sizeof(struct pvcalls_fedata), GFP_KERNEL);
if (!fedata)
return -ENOMEM;
fedata->irq = -1;
err = xenbus_scanf(XBT_NIL, dev->otherend, "port", "%u",
&evtchn);
if (err != 1) {
err = -EINVAL;
xenbus_dev_fatal(dev, err, "reading %s/event-channel",
dev->otherend);
goto error;
}
err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-ref", "%u", &ring_ref);
if (err != 1) {
err = -EINVAL;
xenbus_dev_fatal(dev, err, "reading %s/ring-ref",
dev->otherend);
goto error;
}
err = bind_interdomain_evtchn_to_irq(dev->otherend_id, evtchn);
if (err < 0)
goto error;
fedata->irq = err;
err = request_threaded_irq(fedata->irq, NULL, pvcalls_back_event,
IRQF_ONESHOT, "pvcalls-back", dev);
if (err < 0)
goto error;
err = xenbus_map_ring_valloc(dev, &ring_ref, 1,
(void **)&fedata->sring);
if (err < 0)
goto error;
BACK_RING_INIT(&fedata->ring, fedata->sring, XEN_PAGE_SIZE * 1);
fedata->dev = dev;
INIT_LIST_HEAD(&fedata->socket_mappings);
INIT_RADIX_TREE(&fedata->socketpass_mappings, GFP_KERNEL);
sema_init(&fedata->socket_lock, 1);
dev_set_drvdata(&dev->dev, fedata);
down(&pvcalls_back_global.frontends_lock);
list_add_tail(&fedata->list, &pvcalls_back_global.frontends);
up(&pvcalls_back_global.frontends_lock);
return 0;
error:
if (fedata->irq >= 0)
unbind_from_irqhandler(fedata->irq, dev);
if (fedata->sring != NULL)
xenbus_unmap_ring_vfree(dev, fedata->sring);
kfree(fedata);
return err;
}
static int backend_disconnect(struct xenbus_device *dev)
{
return 0;
}
static int pvcalls_back_probe(struct xenbus_device *dev,
const struct xenbus_device_id *id)
{
int err, abort;
struct xenbus_transaction xbt;
again:
abort = 1;
err = xenbus_transaction_start(&xbt);
if (err) {
pr_warn("%s cannot create xenstore transaction\n", __func__);
return err;
}
err = xenbus_printf(xbt, dev->nodename, "versions", "%s",
PVCALLS_VERSIONS);
if (err) {
pr_warn("%s write out 'versions' failed\n", __func__);
goto abort;
}
err = xenbus_printf(xbt, dev->nodename, "max-page-order", "%u",
MAX_RING_ORDER);
if (err) {
pr_warn("%s write out 'max-page-order' failed\n", __func__);
goto abort;
}
err = xenbus_printf(xbt, dev->nodename, "function-calls",
XENBUS_FUNCTIONS_CALLS);
if (err) {
pr_warn("%s write out 'function-calls' failed\n", __func__);
goto abort;
}
abort = 0;
abort:
err = xenbus_transaction_end(xbt, abort);
if (err) {
if (err == -EAGAIN && !abort)
goto again;
pr_warn("%s cannot complete xenstore transaction\n", __func__);
return err;
}
if (abort)
return -EFAULT;
xenbus_switch_state(dev, XenbusStateInitWait);
return 0;
}
static void set_backend_state(struct xenbus_device *dev,
enum xenbus_state state)
{
while (dev->state != state) {
switch (dev->state) {
case XenbusStateClosed:
switch (state) {
case XenbusStateInitWait:
case XenbusStateConnected:
xenbus_switch_state(dev, XenbusStateInitWait);
break;
case XenbusStateClosing:
xenbus_switch_state(dev, XenbusStateClosing);
break;
default:
__WARN();
}
break;
case XenbusStateInitWait:
case XenbusStateInitialised:
switch (state) {
case XenbusStateConnected:
backend_connect(dev);
xenbus_switch_state(dev, XenbusStateConnected);
break;
case XenbusStateClosing:
case XenbusStateClosed:
xenbus_switch_state(dev, XenbusStateClosing);
break;
default:
__WARN();
}
break;
case XenbusStateConnected:
switch (state) {
case XenbusStateInitWait:
case XenbusStateClosing:
case XenbusStateClosed:
down(&pvcalls_back_global.frontends_lock);
backend_disconnect(dev);
up(&pvcalls_back_global.frontends_lock);
xenbus_switch_state(dev, XenbusStateClosing);
break;
default:
__WARN();
}
break;
case XenbusStateClosing:
switch (state) {
case XenbusStateInitWait:
case XenbusStateConnected:
case XenbusStateClosed:
xenbus_switch_state(dev, XenbusStateClosed);
break;
default:
__WARN();
}
break;
default:
__WARN();
}
}
}
static void pvcalls_back_changed(struct xenbus_device *dev,
enum xenbus_state frontend_state)
{
switch (frontend_state) {
case XenbusStateInitialising:
set_backend_state(dev, XenbusStateInitWait);
break;
case XenbusStateInitialised:
case XenbusStateConnected:
set_backend_state(dev, XenbusStateConnected);
break;
case XenbusStateClosing:
set_backend_state(dev, XenbusStateClosing);
break;
case XenbusStateClosed:
set_backend_state(dev, XenbusStateClosed);
if (xenbus_dev_is_online(dev))
break;
device_unregister(&dev->dev);
break;
case XenbusStateUnknown:
set_backend_state(dev, XenbusStateClosed);
device_unregister(&dev->dev);
break;
default:
xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend",
frontend_state);
break;
}
}
static int pvcalls_back_remove(struct xenbus_device *dev)
{
return 0;
}
static int pvcalls_back_uevent(struct xenbus_device *xdev,
struct kobj_uevent_env *env)
{
return 0;
}
static const struct xenbus_device_id pvcalls_back_ids[] = {
{ "pvcalls" },
{ "" }
};
static struct xenbus_driver pvcalls_back_driver = {
.ids = pvcalls_back_ids,
.probe = pvcalls_back_probe,
.remove = pvcalls_back_remove,
.uevent = pvcalls_back_uevent,
.otherend_changed = pvcalls_back_changed,
};
static int __init pvcalls_back_init(void)
{
int ret;
if (!xen_domain())
return -ENODEV;
ret = xenbus_register_backend(&pvcalls_back_driver);
if (ret < 0)
return ret;
sema_init(&pvcalls_back_global.frontends_lock, 1);
INIT_LIST_HEAD(&pvcalls_back_global.frontends);
return 0;
}
module_init(pvcalls_back_init);