--- zzzz-none-000/linux-3.10.107/drivers/net/xen-netback/xenbus.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/net/xen-netback/xenbus.c 2021-02-04 17:41:59.000000000 +0000 @@ -15,11 +15,12 @@ * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * along with this program; if not, see . */ #include "common.h" +#include +#include struct backend_info { struct xenbus_device *dev; @@ -37,13 +38,194 @@ const char *hotplug_script; }; -static int connect_rings(struct backend_info *); -static void connect(struct backend_info *); -static void backend_create_xenvif(struct backend_info *be); +static int connect_rings(struct backend_info *be, struct xenvif_queue *queue); +static void connect(struct backend_info *be); +static int read_xenbus_vif_flags(struct backend_info *be); +static int backend_create_xenvif(struct backend_info *be); static void unregister_hotplug_status_watch(struct backend_info *be); +static void xen_unregister_watchers(struct xenvif *vif); static void set_backend_state(struct backend_info *be, enum xenbus_state state); +#ifdef CONFIG_DEBUG_FS +struct dentry *xen_netback_dbg_root = NULL; + +static int xenvif_read_io_ring(struct seq_file *m, void *v) +{ + struct xenvif_queue *queue = m->private; + struct xen_netif_tx_back_ring *tx_ring = &queue->tx; + struct xen_netif_rx_back_ring *rx_ring = &queue->rx; + struct netdev_queue *dev_queue; + + if (tx_ring->sring) { + struct xen_netif_tx_sring *sring = tx_ring->sring; + + seq_printf(m, "Queue %d\nTX: nr_ents %u\n", queue->id, + tx_ring->nr_ents); + seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n", + sring->req_prod, + sring->req_prod - sring->rsp_prod, + tx_ring->req_cons, + tx_ring->req_cons - sring->rsp_prod, + sring->req_event, + sring->req_event - sring->rsp_prod); + seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n", + sring->rsp_prod, + tx_ring->rsp_prod_pvt, + tx_ring->rsp_prod_pvt - sring->rsp_prod, + sring->rsp_event, + sring->rsp_event - sring->rsp_prod); + seq_printf(m, "pending prod %u pending cons %u nr_pending_reqs %u\n", + queue->pending_prod, + queue->pending_cons, + nr_pending_reqs(queue)); + seq_printf(m, "dealloc prod %u dealloc cons %u dealloc_queue %u\n\n", + queue->dealloc_prod, + queue->dealloc_cons, + queue->dealloc_prod - queue->dealloc_cons); + } + + if (rx_ring->sring) { + struct xen_netif_rx_sring *sring = rx_ring->sring; + + seq_printf(m, "RX: nr_ents %u\n", rx_ring->nr_ents); + seq_printf(m, "req prod %u (%d) cons %u (%d) event %u (%d)\n", + sring->req_prod, + sring->req_prod - sring->rsp_prod, + rx_ring->req_cons, + rx_ring->req_cons - sring->rsp_prod, + sring->req_event, + sring->req_event - sring->rsp_prod); + seq_printf(m, "rsp prod %u (base) pvt %u (%d) event %u (%d)\n\n", + sring->rsp_prod, + rx_ring->rsp_prod_pvt, + rx_ring->rsp_prod_pvt - sring->rsp_prod, + sring->rsp_event, + sring->rsp_event - sring->rsp_prod); + } + + seq_printf(m, "NAPI state: %lx NAPI weight: %d TX queue len %u\n" + "Credit timer_pending: %d, credit: %lu, usec: %lu\n" + "remaining: %lu, expires: %lu, now: %lu\n", + queue->napi.state, queue->napi.weight, + skb_queue_len(&queue->tx_queue), + timer_pending(&queue->credit_timeout), + queue->credit_bytes, + queue->credit_usec, + queue->remaining_credit, + queue->credit_timeout.expires, + jiffies); + + dev_queue = netdev_get_tx_queue(queue->vif->dev, queue->id); + + seq_printf(m, "\nRx internal queue: len %u max %u pkts %u %s\n", + queue->rx_queue_len, queue->rx_queue_max, + skb_queue_len(&queue->rx_queue), + netif_tx_queue_stopped(dev_queue) ? "stopped" : "running"); + + return 0; +} + +#define XENVIF_KICK_STR "kick" +#define BUFFER_SIZE 32 + +static ssize_t +xenvif_write_io_ring(struct file *filp, const char __user *buf, size_t count, + loff_t *ppos) +{ + struct xenvif_queue *queue = + ((struct seq_file *)filp->private_data)->private; + int len; + char write[BUFFER_SIZE]; + + /* don't allow partial writes and check the length */ + if (*ppos != 0) + return 0; + if (count >= sizeof(write)) + return -ENOSPC; + + len = simple_write_to_buffer(write, + sizeof(write) - 1, + ppos, + buf, + count); + if (len < 0) + return len; + + write[len] = '\0'; + + if (!strncmp(write, XENVIF_KICK_STR, sizeof(XENVIF_KICK_STR) - 1)) + xenvif_interrupt(0, (void *)queue); + else { + pr_warn("Unknown command to io_ring_q%d. Available: kick\n", + queue->id); + count = -EINVAL; + } + return count; +} + +static int xenvif_dump_open(struct inode *inode, struct file *filp) +{ + int ret; + void *queue = NULL; + + if (inode->i_private) + queue = inode->i_private; + ret = single_open(filp, xenvif_read_io_ring, queue); + filp->f_mode |= FMODE_PWRITE; + return ret; +} + +static const struct file_operations xenvif_dbg_io_ring_ops_fops = { + .owner = THIS_MODULE, + .open = xenvif_dump_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, + .write = xenvif_write_io_ring, +}; + +static void xenvif_debugfs_addif(struct xenvif *vif) +{ + struct dentry *pfile; + int i; + + if (IS_ERR_OR_NULL(xen_netback_dbg_root)) + return; + + vif->xenvif_dbg_root = debugfs_create_dir(vif->dev->name, + xen_netback_dbg_root); + if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) { + for (i = 0; i < vif->num_queues; ++i) { + char filename[sizeof("io_ring_q") + 4]; + + snprintf(filename, sizeof(filename), "io_ring_q%d", i); + pfile = debugfs_create_file(filename, + S_IRUSR | S_IWUSR, + vif->xenvif_dbg_root, + &vif->queues[i], + &xenvif_dbg_io_ring_ops_fops); + if (IS_ERR_OR_NULL(pfile)) + pr_warn("Creation of io_ring file returned %ld!\n", + PTR_ERR(pfile)); + } + } else + netdev_warn(vif->dev, + "Creation of vif debugfs dir returned %ld!\n", + PTR_ERR(vif->xenvif_dbg_root)); +} + +static void xenvif_debugfs_delif(struct xenvif *vif) +{ + if (IS_ERR_OR_NULL(xen_netback_dbg_root)) + return; + + if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) + debugfs_remove_recursive(vif->xenvif_dbg_root); + vif->xenvif_dbg_root = NULL; +} +#endif /* CONFIG_DEBUG_FS */ + static int netback_remove(struct xenbus_device *dev) { struct backend_info *be = dev_get_drvdata(&dev->dev); @@ -53,6 +235,7 @@ unregister_hotplug_status_watch(be); if (be->vif) { kobject_uevent(&dev->dev.kobj, KOBJ_OFFLINE); + xen_unregister_watchers(be->vif); xenbus_rm(XBT_NIL, dev->nodename, "hotplug-status"); xenvif_free(be->vif); be->vif = NULL; @@ -109,6 +292,22 @@ goto abort_transaction; } + err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv6", + "%d", sg); + if (err) { + message = "writing feature-gso-tcpv6"; + goto abort_transaction; + } + + /* We support partial checksum setup for IPv6 packets */ + err = xenbus_printf(xbt, dev->nodename, + "feature-ipv6-csum-offload", + "%d", 1); + if (err) { + message = "writing feature-ipv6-csum-offload"; + goto abort_transaction; + } + /* We support rx-copy path. */ err = xenbus_printf(xbt, dev->nodename, "feature-rx-copy", "%d", 1); @@ -128,6 +327,14 @@ goto abort_transaction; } + /* We support multicast-control. */ + err = xenbus_printf(xbt, dev->nodename, + "feature-multicast-control", "%d", 1); + if (err) { + message = "writing feature-multicast-control"; + goto abort_transaction; + } + err = xenbus_transaction_end(xbt, 0); } while (err == -EAGAIN); @@ -136,6 +343,22 @@ goto fail; } + /* + * Split event channels support, this is optional so it is not + * put inside the above loop. + */ + err = xenbus_printf(XBT_NIL, dev->nodename, + "feature-split-event-channels", + "%u", separate_tx_rx_irq); + if (err) + pr_debug("Error writing feature-split-event-channels\n"); + + /* Multi-queue support: This is an optional feature. */ + err = xenbus_printf(XBT_NIL, dev->nodename, + "multi-queue-max-queues", "%u", xenvif_max_queues); + if (err) + pr_debug("Error writing multi-queue-max-queues\n"); + script = xenbus_read(XBT_NIL, dev->nodename, "script", NULL); if (IS_ERR(script)) { err = PTR_ERR(script); @@ -152,7 +375,9 @@ be->state = XenbusStateInitWait; /* This kicks hotplug scripts, so do it immediately. */ - backend_create_xenvif(be); + err = backend_create_xenvif(be); + if (err) + goto fail; return 0; @@ -160,7 +385,7 @@ xenbus_transaction_end(xbt, 1); xenbus_dev_fatal(dev, err, "%s", message); fail: - pr_debug("failed"); + pr_debug("failed\n"); netback_remove(dev); return err; } @@ -189,36 +414,43 @@ } -static void backend_create_xenvif(struct backend_info *be) +static int backend_create_xenvif(struct backend_info *be) { int err; long handle; struct xenbus_device *dev = be->dev; + struct xenvif *vif; if (be->vif != NULL) - return; + return 0; err = xenbus_scanf(XBT_NIL, dev->nodename, "handle", "%li", &handle); if (err != 1) { xenbus_dev_fatal(dev, err, "reading handle"); - return; + return (err < 0) ? err : -EINVAL; } - be->vif = xenvif_alloc(&dev->dev, dev->otherend_id, handle); - if (IS_ERR(be->vif)) { - err = PTR_ERR(be->vif); - be->vif = NULL; + vif = xenvif_alloc(&dev->dev, dev->otherend_id, handle); + if (IS_ERR(vif)) { + err = PTR_ERR(vif); xenbus_dev_fatal(dev, err, "creating interface"); - return; + return err; } + be->vif = vif; kobject_uevent(&dev->dev.kobj, KOBJ_ONLINE); + return 0; } static void backend_disconnect(struct backend_info *be) { - if (be->vif) + if (be->vif) { + xen_unregister_watchers(be->vif); +#ifdef CONFIG_DEBUG_FS + xenvif_debugfs_delif(be->vif); +#endif /* CONFIG_DEBUG_FS */ xenvif_disconnect(be->vif); + } } static void backend_connect(struct backend_info *be) @@ -429,6 +661,62 @@ return 0; } +static void xen_net_rate_changed(struct xenbus_watch *watch, + const char **vec, unsigned int len) +{ + struct xenvif *vif = container_of(watch, struct xenvif, credit_watch); + struct xenbus_device *dev = xenvif_to_xenbus_device(vif); + unsigned long credit_bytes; + unsigned long credit_usec; + unsigned int queue_index; + + xen_net_read_rate(dev, &credit_bytes, &credit_usec); + for (queue_index = 0; queue_index < vif->num_queues; queue_index++) { + struct xenvif_queue *queue = &vif->queues[queue_index]; + + queue->credit_bytes = credit_bytes; + queue->credit_usec = credit_usec; + if (!mod_timer_pending(&queue->credit_timeout, jiffies) && + queue->remaining_credit > queue->credit_bytes) { + queue->remaining_credit = queue->credit_bytes; + } + } +} + +static int xen_register_watchers(struct xenbus_device *dev, struct xenvif *vif) +{ + int err = 0; + char *node; + unsigned maxlen = strlen(dev->nodename) + sizeof("/rate"); + + if (vif->credit_watch.node) + return -EADDRINUSE; + + node = kmalloc(maxlen, GFP_KERNEL); + if (!node) + return -ENOMEM; + snprintf(node, maxlen, "%s/rate", dev->nodename); + vif->credit_watch.node = node; + vif->credit_watch.callback = xen_net_rate_changed; + err = register_xenbus_watch(&vif->credit_watch); + if (err) { + pr_err("Failed to set watcher %s\n", vif->credit_watch.node); + kfree(node); + vif->credit_watch.node = NULL; + vif->credit_watch.callback = NULL; + } + return err; +} + +static void xen_unregister_watchers(struct xenvif *vif) +{ + if (vif->credit_watch.node) { + unregister_xenbus_watch(&vif->credit_watch); + kfree(vif->credit_watch.node); + vif->credit_watch.node = NULL; + } +} + static void unregister_hotplug_status_watch(struct backend_info *be) { if (be->have_hotplug_status_watch) { @@ -465,10 +753,26 @@ { int err; struct xenbus_device *dev = be->dev; + unsigned long credit_bytes, credit_usec; + unsigned int queue_index; + unsigned int requested_num_queues; + struct xenvif_queue *queue; - err = connect_rings(be); - if (err) + /* Check whether the frontend requested multiple queues + * and read the number requested. + */ + err = xenbus_scanf(XBT_NIL, dev->otherend, + "multi-queue-num-queues", + "%u", &requested_num_queues); + if (err < 0) { + requested_num_queues = 1; /* Fall back to single queue */ + } else if (requested_num_queues > xenvif_max_queues) { + /* buggy or malicious guest */ + xenbus_dev_fatal(dev, err, + "guest requested %u queues, exceeding the maximum of %u.", + requested_num_queues, xenvif_max_queues); return; + } err = xen_net_read_mac(dev, be->vif->fe_dev_addr); if (err) { @@ -476,9 +780,71 @@ return; } - xen_net_read_rate(dev, &be->vif->credit_bytes, - &be->vif->credit_usec); - be->vif->remaining_credit = be->vif->credit_bytes; + xen_net_read_rate(dev, &credit_bytes, &credit_usec); + xen_unregister_watchers(be->vif); + xen_register_watchers(dev, be->vif); + read_xenbus_vif_flags(be); + + /* Use the number of queues requested by the frontend */ + be->vif->queues = vzalloc(requested_num_queues * + sizeof(struct xenvif_queue)); + if (!be->vif->queues) { + xenbus_dev_fatal(dev, -ENOMEM, + "allocating queues"); + return; + } + + be->vif->num_queues = requested_num_queues; + be->vif->stalled_queues = requested_num_queues; + + for (queue_index = 0; queue_index < requested_num_queues; ++queue_index) { + queue = &be->vif->queues[queue_index]; + queue->vif = be->vif; + queue->id = queue_index; + snprintf(queue->name, sizeof(queue->name), "%s-q%u", + be->vif->dev->name, queue->id); + + err = xenvif_init_queue(queue); + if (err) { + /* xenvif_init_queue() cleans up after itself on + * failure, but we need to clean up any previously + * initialised queues. Set num_queues to i so that + * earlier queues can be destroyed using the regular + * disconnect logic. + */ + be->vif->num_queues = queue_index; + goto err; + } + + queue->credit_bytes = credit_bytes; + queue->remaining_credit = credit_bytes; + queue->credit_usec = credit_usec; + + err = connect_rings(be, queue); + if (err) { + /* connect_rings() cleans up after itself on failure, + * but we need to clean up after xenvif_init_queue() here, + * and also clean up any previously initialised queues. + */ + xenvif_deinit_queue(queue); + be->vif->num_queues = queue_index; + goto err; + } + } + +#ifdef CONFIG_DEBUG_FS + xenvif_debugfs_addif(be->vif); +#endif /* CONFIG_DEBUG_FS */ + + /* Initialisation completed, tell core driver the number of + * active queues. + */ + rtnl_lock(); + netif_set_real_num_tx_queues(be->vif->dev, requested_num_queues); + netif_set_real_num_rx_queues(be->vif->dev, requested_num_queues); + rtnl_unlock(); + + xenvif_carrier_on(be->vif); unregister_hotplug_status_watch(be); err = xenbus_watch_pathfmt(dev, &be->hotplug_status_watch, @@ -487,30 +853,107 @@ if (!err) be->have_hotplug_status_watch = 1; - netif_wake_queue(be->vif->dev); + netif_tx_wake_all_queues(be->vif->dev); + + return; + +err: + if (be->vif->num_queues > 0) + xenvif_disconnect(be->vif); /* Clean up existing queues */ + vfree(be->vif->queues); + be->vif->queues = NULL; + be->vif->num_queues = 0; + return; } -static int connect_rings(struct backend_info *be) +static int connect_rings(struct backend_info *be, struct xenvif_queue *queue) { - struct xenvif *vif = be->vif; struct xenbus_device *dev = be->dev; + unsigned int num_queues = queue->vif->num_queues; unsigned long tx_ring_ref, rx_ring_ref; - unsigned int evtchn, rx_copy; + unsigned int tx_evtchn, rx_evtchn; int err; - int val; + char *xspath; + size_t xspathsize; + const size_t xenstore_path_ext_size = 11; /* sufficient for "/queue-NNN" */ + + /* If the frontend requested 1 queue, or we have fallen back + * to single queue due to lack of frontend support for multi- + * queue, expect the remaining XenStore keys in the toplevel + * directory. Otherwise, expect them in a subdirectory called + * queue-N. + */ + if (num_queues == 1) { + xspath = kzalloc(strlen(dev->otherend) + 1, GFP_KERNEL); + if (!xspath) { + xenbus_dev_fatal(dev, -ENOMEM, + "reading ring references"); + return -ENOMEM; + } + strcpy(xspath, dev->otherend); + } else { + xspathsize = strlen(dev->otherend) + xenstore_path_ext_size; + xspath = kzalloc(xspathsize, GFP_KERNEL); + if (!xspath) { + xenbus_dev_fatal(dev, -ENOMEM, + "reading ring references"); + return -ENOMEM; + } + snprintf(xspath, xspathsize, "%s/queue-%u", dev->otherend, + queue->id); + } - err = xenbus_gather(XBT_NIL, dev->otherend, + err = xenbus_gather(XBT_NIL, xspath, "tx-ring-ref", "%lu", &tx_ring_ref, - "rx-ring-ref", "%lu", &rx_ring_ref, - "event-channel", "%u", &evtchn, NULL); + "rx-ring-ref", "%lu", &rx_ring_ref, NULL); if (err) { xenbus_dev_fatal(dev, err, - "reading %s/ring-ref and event-channel", - dev->otherend); - return err; + "reading %s/ring-ref", + xspath); + goto err; + } + + /* Try split event channels first, then single event channel. */ + err = xenbus_gather(XBT_NIL, xspath, + "event-channel-tx", "%u", &tx_evtchn, + "event-channel-rx", "%u", &rx_evtchn, NULL); + if (err < 0) { + err = xenbus_scanf(XBT_NIL, xspath, + "event-channel", "%u", &tx_evtchn); + if (err < 0) { + xenbus_dev_fatal(dev, err, + "reading %s/event-channel(-tx/rx)", + xspath); + goto err; + } + rx_evtchn = tx_evtchn; } + /* Map the shared frame, irq etc. */ + err = xenvif_connect(queue, tx_ring_ref, rx_ring_ref, + tx_evtchn, rx_evtchn); + if (err) { + xenbus_dev_fatal(dev, err, + "mapping shared-frames %lu/%lu port tx %u rx %u", + tx_ring_ref, rx_ring_ref, + tx_evtchn, rx_evtchn); + goto err; + } + + err = 0; +err: /* Regular return falls through with err == 0 */ + kfree(xspath); + return err; +} + +static int read_xenbus_vif_flags(struct backend_info *be) +{ + struct xenvif *vif = be->vif; + struct xenbus_device *dev = be->dev; + unsigned int rx_copy; + int err, val; + err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u", &rx_copy); if (err == -ENOENT) { @@ -525,15 +968,16 @@ if (!rx_copy) return -EOPNOTSUPP; - if (vif->dev->tx_queue_len != 0) { - if (xenbus_scanf(XBT_NIL, dev->otherend, - "feature-rx-notify", "%d", &val) < 0) - val = 0; - if (val) - vif->can_queue = 1; - else - /* Must be non-zero for pfifo_fast to work. */ - vif->dev->tx_queue_len = 1; + if (xenbus_scanf(XBT_NIL, dev->otherend, + "feature-rx-notify", "%d", &val) < 0) + val = 0; + if (!val) { + /* - Reduce drain timeout to poll more frequently for + * Rx requests. + * - Disable Rx stall detection. + */ + be->vif->drain_timeout = msecs_to_jiffies(30); + be->vif->stall_timeout = 0; } if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg", @@ -541,50 +985,78 @@ val = 0; vif->can_sg = !!val; + vif->gso_mask = 0; + vif->gso_prefix_mask = 0; + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4", "%d", &val) < 0) val = 0; - vif->gso = !!val; + if (val) + vif->gso_mask |= GSO_BIT(TCPV4); if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4-prefix", "%d", &val) < 0) val = 0; - vif->gso_prefix = !!val; + if (val) + vif->gso_prefix_mask |= GSO_BIT(TCPV4); - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload", + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6", "%d", &val) < 0) val = 0; - vif->csum = !val; + if (val) + vif->gso_mask |= GSO_BIT(TCPV6); - /* Map the shared frame, irq etc. */ - err = xenvif_connect(vif, tx_ring_ref, rx_ring_ref, evtchn); - if (err) { + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6-prefix", + "%d", &val) < 0) + val = 0; + if (val) + vif->gso_prefix_mask |= GSO_BIT(TCPV6); + + if (vif->gso_mask & vif->gso_prefix_mask) { xenbus_dev_fatal(dev, err, - "mapping shared-frames %lu/%lu port %u", - tx_ring_ref, rx_ring_ref, evtchn); - return err; + "%s: gso and gso prefix flags are not " + "mutually exclusive", + dev->otherend); + return -EOPNOTSUPP; } - return 0; -} + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload", + "%d", &val) < 0) + val = 0; + vif->ip_csum = !val; + + if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-ipv6-csum-offload", + "%d", &val) < 0) + val = 0; + vif->ipv6_csum = !!val; -/* ** Driver Registration ** */ + if (xenbus_scanf(XBT_NIL, dev->otherend, "request-multicast-control", + "%d", &val) < 0) + val = 0; + vif->multicast_control = !!val; + return 0; +} static const struct xenbus_device_id netback_ids[] = { { "vif" }, { "" } }; - -static DEFINE_XENBUS_DRIVER(netback, , +static struct xenbus_driver netback_driver = { + .ids = netback_ids, .probe = netback_probe, .remove = netback_remove, .uevent = netback_uevent, .otherend_changed = frontend_changed, -); +}; int xenvif_xenbus_init(void) { return xenbus_register_backend(&netback_driver); } + +void xenvif_xenbus_fini(void) +{ + return xenbus_unregister_driver(&netback_driver); +}