--- zzzz-none-000/linux-3.10.107/drivers/block/xen-blkback/xenbus.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/block/xen-blkback/xenbus.c 2021-02-04 17:41:59.000000000 +0000 @@ -14,6 +14,8 @@ */ +#define pr_fmt(fmt) "xen-blkback: " fmt + #include #include #include @@ -21,6 +23,10 @@ #include #include "common.h" +/* Enlarge the array size in order to fully show blkback name. */ +#define BLKBACK_NAME_LEN (20) +#define RINGREF_NAME_LEN (20) + struct backend_info { struct xenbus_device *dev; struct xen_blkif *blkif; @@ -35,12 +41,26 @@ static int connect_ring(struct backend_info *); static void backend_changed(struct xenbus_watch *, const char **, unsigned int); +static void xen_blkif_free(struct xen_blkif *blkif); +static void xen_vbd_free(struct xen_vbd *vbd); struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be) { return be->dev; } +/* + * The last request could free the device from softirq context and + * xen_blkif_free() can sleep. + */ +static void xen_blkif_deferred_free(struct work_struct *work) +{ + struct xen_blkif *blkif; + + blkif = container_of(work, struct xen_blkif, free_work); + xen_blkif_free(blkif); +} + static int blkback_name(struct xen_blkif *blkif, char *buf) { char *devpath, *devname; @@ -56,7 +76,7 @@ else devname = devpath; - snprintf(buf, TASK_COMM_LEN, "blkback.%d.%s", blkif->domid, devname); + snprintf(buf, BLKBACK_NAME_LEN, "blkback.%d.%s", blkif->domid, devname); kfree(devpath); return 0; @@ -65,7 +85,7 @@ static void xen_update_blkif_status(struct xen_blkif *blkif) { int err; - char name[TASK_COMM_LEN]; + char name[BLKBACK_NAME_LEN]; /* Not ready to connect? */ if (!blkif->irq || !blkif->vbd.bdev) @@ -93,11 +113,12 @@ } invalidate_inode_pages2(blkif->vbd.bdev->bd_inode->i_mapping); - blkif->xenblkd = kthread_run(xen_blkif_schedule, blkif, name); + blkif->xenblkd = kthread_run(xen_blkif_schedule, blkif, "%s", name); if (IS_ERR(blkif->xenblkd)) { err = PTR_ERR(blkif->xenblkd); blkif->xenblkd = NULL; xenbus_dev_error(blkif->be->dev, err, "start xenblkd"); + return; } } @@ -105,6 +126,8 @@ { struct xen_blkif *blkif; + BUILD_BUG_ON(MAX_INDIRECT_PAGES > BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST); + blkif = kmem_cache_zalloc(xen_blkif_cachep, GFP_KERNEL); if (!blkif) return ERR_PTR(-ENOMEM); @@ -116,14 +139,26 @@ init_completion(&blkif->drain_complete); atomic_set(&blkif->drain, 0); blkif->st_print = jiffies; - init_waitqueue_head(&blkif->waiting_to_free); blkif->persistent_gnts.rb_node = NULL; + spin_lock_init(&blkif->free_pages_lock); + INIT_LIST_HEAD(&blkif->free_pages); + INIT_LIST_HEAD(&blkif->persistent_purge_list); + blkif->free_pages_num = 0; + atomic_set(&blkif->persistent_gnt_in_use, 0); + atomic_set(&blkif->inflight, 0); + INIT_WORK(&blkif->persistent_purge_work, xen_blkbk_unmap_purged_grants); + + INIT_LIST_HEAD(&blkif->pending_free); + INIT_WORK(&blkif->free_work, xen_blkif_deferred_free); + spin_lock_init(&blkif->pending_free_lock); + init_waitqueue_head(&blkif->pending_free_wq); + init_waitqueue_head(&blkif->shutdown_wq); return blkif; } -static int xen_blkif_map(struct xen_blkif *blkif, unsigned long shared_page, - unsigned int evtchn) +static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref, + unsigned int nr_grefs, unsigned int evtchn) { int err; @@ -131,7 +166,8 @@ if (blkif->irq) return 0; - err = xenbus_map_ring_valloc(blkif->be->dev, shared_page, &blkif->blk_ring); + err = xenbus_map_ring_valloc(blkif->be->dev, gref, nr_grefs, + &blkif->blk_ring); if (err < 0) return err; @@ -140,21 +176,24 @@ { struct blkif_sring *sring; sring = (struct blkif_sring *)blkif->blk_ring; - BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE); + BACK_RING_INIT(&blkif->blk_rings.native, sring, + XEN_PAGE_SIZE * nr_grefs); break; } case BLKIF_PROTOCOL_X86_32: { struct blkif_x86_32_sring *sring_x86_32; sring_x86_32 = (struct blkif_x86_32_sring *)blkif->blk_ring; - BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, PAGE_SIZE); + BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, + XEN_PAGE_SIZE * nr_grefs); break; } case BLKIF_PROTOCOL_X86_64: { struct blkif_x86_64_sring *sring_x86_64; sring_x86_64 = (struct blkif_x86_64_sring *)blkif->blk_ring; - BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, PAGE_SIZE); + BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, + XEN_PAGE_SIZE * nr_grefs); break; } default: @@ -174,16 +213,23 @@ return 0; } -static void xen_blkif_disconnect(struct xen_blkif *blkif) +static int xen_blkif_disconnect(struct xen_blkif *blkif) { + struct pending_req *req, *n; + int i = 0, j; + if (blkif->xenblkd) { kthread_stop(blkif->xenblkd); + wake_up(&blkif->shutdown_wq); blkif->xenblkd = NULL; } - atomic_dec(&blkif->refcnt); - wait_event(blkif->waiting_to_free, atomic_read(&blkif->refcnt) == 0); - atomic_inc(&blkif->refcnt); + /* The above kthread_stop() guarantees that at this point we + * don't have any discard_io or other_io requests. So, checking + * for inflight IO is enough. + */ + if (atomic_read(&blkif->inflight) > 0) + return -EBUSY; if (blkif->irq) { unbind_from_irqhandler(blkif->irq, blkif); @@ -194,12 +240,44 @@ xenbus_unmap_ring_vfree(blkif->be->dev, blkif->blk_ring); blkif->blk_rings.common.sring = NULL; } + + /* Remove all persistent grants and the cache of ballooned pages. */ + xen_blkbk_free_caches(blkif); + + /* Check that there is no request in use */ + list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) { + list_del(&req->free_list); + + for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) + kfree(req->segments[j]); + + for (j = 0; j < MAX_INDIRECT_PAGES; j++) + kfree(req->indirect_pages[j]); + + kfree(req); + i++; + } + + WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages)); + blkif->nr_ring_pages = 0; + + return 0; } static void xen_blkif_free(struct xen_blkif *blkif) { - if (!atomic_dec_and_test(&blkif->refcnt)) - BUG(); + + xen_blkif_disconnect(blkif); + xen_vbd_free(&blkif->vbd); + + /* Make sure everything is drained before shutting down */ + BUG_ON(blkif->persistent_gnt_c != 0); + BUG_ON(atomic_read(&blkif->persistent_gnt_in_use) != 0); + BUG_ON(blkif->free_pages_num != 0); + BUG_ON(!list_empty(&blkif->persistent_purge_list)); + BUG_ON(!list_empty(&blkif->free_pages)); + BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts)); + kmem_cache_free(xen_blkif_cachep, blkif); } @@ -315,14 +393,14 @@ FMODE_READ : FMODE_WRITE, NULL); if (IS_ERR(bdev)) { - DPRINTK("xen_vbd_create: device %08x could not be opened.\n", + pr_warn("xen_vbd_create: device %08x could not be opened\n", vbd->pdevice); return -ENOENT; } vbd->bdev = bdev; if (vbd->bdev->bd_disk == NULL) { - DPRINTK("xen_vbd_create: device %08x doesn't exist.\n", + pr_warn("xen_vbd_create: device %08x doesn't exist\n", vbd->pdevice); xen_vbd_free(vbd); return -ENOENT; @@ -341,7 +419,7 @@ if (q && blk_queue_secdiscard(q)) vbd->discard_secure = true; - DPRINTK("Successful creation of handle=%04x (dom=%u)\n", + pr_debug("Successful creation of handle=%04x (dom=%u)\n", handle, blkif->domid); return 0; } @@ -349,7 +427,7 @@ { struct backend_info *be = dev_get_drvdata(&dev->dev); - DPRINTK(""); + pr_debug("%s %p %d\n", __func__, dev, dev->otherend_id); if (be->major || be->minor) xenvbd_sysfs_delif(dev); @@ -360,16 +438,15 @@ be->backend_watch.node = NULL; } + dev_set_drvdata(&dev->dev, NULL); + if (be->blkif) { xen_blkif_disconnect(be->blkif); - xen_vbd_free(&be->blkif->vbd); - xen_blkif_free(be->blkif); - be->blkif = NULL; + xen_blkif_put(be->blkif); } kfree(be->mode); kfree(be); - dev_set_drvdata(&dev->dev, NULL); return 0; } @@ -392,10 +469,15 @@ struct xenbus_device *dev = be->dev; struct xen_blkif *blkif = be->blkif; int err; - int state = 0; + int state = 0, discard_enable; struct block_device *bdev = be->blkif->vbd.bdev; struct request_queue *q = bdev_get_queue(bdev); + err = xenbus_scanf(XBT_NIL, dev->nodename, "discard-enable", "%d", + &discard_enable); + if (err == 1 && !discard_enable) + return; + if (blk_queue_discard(q)) { err = xenbus_printf(xbt, dev->nodename, "discard-granularity", "%u", @@ -451,6 +533,10 @@ int err; struct backend_info *be = kzalloc(sizeof(struct backend_info), GFP_KERNEL); + + /* match the pr_debug in xen_blkbk_remove */ + pr_debug("%s %p %d\n", __func__, dev, dev->otherend_id); + if (!be) { xenbus_dev_fatal(dev, -ENOMEM, "allocating backend structure"); @@ -475,6 +561,11 @@ if (err) goto fail; + err = xenbus_printf(XBT_NIL, dev->nodename, "max-ring-page-order", "%u", + xen_blkif_max_ring_order); + if (err) + pr_warn("%s write out 'max-ring-page-order' failed\n", __func__); + err = xenbus_switch_state(dev, XenbusStateInitWait); if (err) goto fail; @@ -482,7 +573,7 @@ return 0; fail: - DPRINTK("failed"); + pr_warn("%s failed\n", __func__); xen_blkbk_remove(dev); return err; } @@ -506,7 +597,7 @@ unsigned long handle; char *device_type; - DPRINTK(""); + pr_debug("%s %p %d\n", __func__, dev, dev->otherend_id); err = xenbus_scanf(XBT_NIL, dev->nodename, "physical-device", "%x:%x", &major, &minor); @@ -525,7 +616,7 @@ if (be->major | be->minor) { if (be->major != major || be->minor != minor) - pr_warn(DRV_PFX "changing physical device (from %x:%x to %x:%x) not supported.\n", + pr_warn("changing physical device (from %x:%x to %x:%x) not supported.\n", be->major, be->minor, major, minor); return; } @@ -545,7 +636,7 @@ } /* Front end dir is a number, which is used as the handle. */ - err = strict_strtoul(strrchr(dev->otherend, '/') + 1, 0, &handle); + err = kstrtoul(strrchr(dev->otherend, '/') + 1, 0, &handle); if (err) return; @@ -586,13 +677,12 @@ struct backend_info *be = dev_get_drvdata(&dev->dev); int err; - DPRINTK("%s", xenbus_strstate(frontend_state)); + pr_debug("%s %p %s\n", __func__, dev, xenbus_strstate(frontend_state)); switch (frontend_state) { case XenbusStateInitialising: if (dev->state == XenbusStateClosed) { - pr_info(DRV_PFX "%s: prepare for reconnect\n", - dev->nodename); + pr_info("%s: prepare for reconnect\n", dev->nodename); xenbus_switch_state(dev, XenbusStateInitWait); } break; @@ -611,7 +701,11 @@ * Enforce precondition before potential leak point. * xen_blkif_disconnect() is idempotent. */ - xen_blkif_disconnect(be->blkif); + err = xen_blkif_disconnect(be->blkif); + if (err) { + xenbus_dev_fatal(dev, err, "pending I/O"); + break; + } err = connect_ring(be); if (err) @@ -655,7 +749,7 @@ int err; struct xenbus_device *dev = be->dev; - DPRINTK("%s", dev->otherend); + pr_debug("%s %s\n", __func__, dev->otherend); /* Supply the information about the device the frontend needs */ again: @@ -678,6 +772,11 @@ dev->nodename); goto abort; } + err = xenbus_printf(xbt, dev->nodename, "feature-max-indirect-segments", "%u", + MAX_INDIRECT_SEGMENTS); + if (err) + dev_warn(&dev->dev, "writing %s/feature-max-indirect-segments (%d)", + dev->nodename, err); err = xenbus_printf(xbt, dev->nodename, "sectors", "%llu", (unsigned long long)vbd_sz(&be->blkif->vbd)); @@ -704,6 +803,11 @@ dev->nodename); goto abort; } + err = xenbus_printf(xbt, dev->nodename, "physical-sector-size", "%u", + bdev_physical_block_size(be->blkif->vbd.bdev)); + if (err) + xenbus_dev_error(dev, err, "writing %s/physical-sector-size", + dev->nodename); err = xenbus_transaction_end(xbt, 0); if (err == -EAGAIN) @@ -725,28 +829,72 @@ static int connect_ring(struct backend_info *be) { struct xenbus_device *dev = be->dev; - unsigned long ring_ref; - unsigned int evtchn; + unsigned int ring_ref[XENBUS_MAX_RING_GRANTS]; + unsigned int evtchn, nr_grefs, ring_page_order; unsigned int pers_grants; char protocol[64] = ""; - int err; + struct pending_req *req, *n; + int err, i, j; - DPRINTK("%s", dev->otherend); + pr_debug("%s %s\n", __func__, dev->otherend); - err = xenbus_gather(XBT_NIL, dev->otherend, "ring-ref", "%lu", - &ring_ref, "event-channel", "%u", &evtchn, NULL); - if (err) { - xenbus_dev_fatal(dev, err, - "reading %s/ring-ref and event-channel", + err = xenbus_scanf(XBT_NIL, dev->otherend, "event-channel", "%u", + &evtchn); + if (err != 1) { + err = -EINVAL; + xenbus_dev_fatal(dev, err, "reading %s/event-channel", dev->otherend); return err; } + pr_info("event-channel %u\n", evtchn); + + err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-page-order", "%u", + &ring_page_order); + if (err != 1) { + err = xenbus_scanf(XBT_NIL, dev->otherend, "ring-ref", + "%u", &ring_ref[0]); + if (err != 1) { + err = -EINVAL; + xenbus_dev_fatal(dev, err, "reading %s/ring-ref", + dev->otherend); + return err; + } + nr_grefs = 1; + pr_info("%s:using single page: ring-ref %d\n", dev->otherend, + ring_ref[0]); + } else { + unsigned int i; - be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE; + if (ring_page_order > xen_blkif_max_ring_order) { + err = -EINVAL; + xenbus_dev_fatal(dev, err, "%s/request %d ring page order exceed max:%d", + dev->otherend, ring_page_order, + xen_blkif_max_ring_order); + return err; + } + + nr_grefs = 1 << ring_page_order; + for (i = 0; i < nr_grefs; i++) { + char ring_ref_name[RINGREF_NAME_LEN]; + + snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i); + err = xenbus_scanf(XBT_NIL, dev->otherend, ring_ref_name, + "%u", &ring_ref[i]); + if (err != 1) { + err = -EINVAL; + xenbus_dev_fatal(dev, err, "reading %s/%s", + dev->otherend, ring_ref_name); + return err; + } + pr_info("ring-ref%u: %u\n", i, ring_ref[i]); + } + } + + be->blkif->blk_protocol = BLKIF_PROTOCOL_DEFAULT; err = xenbus_gather(XBT_NIL, dev->otherend, "protocol", "%63s", protocol, NULL); if (err) - strcpy(protocol, "unspecified, assuming native"); + strcpy(protocol, "unspecified, assuming default"); else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_NATIVE)) be->blkif->blk_protocol = BLKIF_PROTOCOL_NATIVE; else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_X86_32)) @@ -765,38 +913,68 @@ be->blkif->vbd.feature_gnt_persistent = pers_grants; be->blkif->vbd.overflow_max_grants = 0; + be->blkif->nr_ring_pages = nr_grefs; - pr_info(DRV_PFX "ring-ref %ld, event-channel %d, protocol %d (%s) %s\n", - ring_ref, evtchn, be->blkif->blk_protocol, protocol, + pr_info("ring-pages:%d, event-channel %d, protocol %d (%s) %s\n", + nr_grefs, evtchn, be->blkif->blk_protocol, protocol, pers_grants ? "persistent grants" : ""); + for (i = 0; i < nr_grefs * XEN_BLKIF_REQS_PER_PAGE; i++) { + req = kzalloc(sizeof(*req), GFP_KERNEL); + if (!req) + goto fail; + list_add_tail(&req->free_list, &be->blkif->pending_free); + for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) { + req->segments[j] = kzalloc(sizeof(*req->segments[0]), GFP_KERNEL); + if (!req->segments[j]) + goto fail; + } + for (j = 0; j < MAX_INDIRECT_PAGES; j++) { + req->indirect_pages[j] = kzalloc(sizeof(*req->indirect_pages[0]), + GFP_KERNEL); + if (!req->indirect_pages[j]) + goto fail; + } + } + /* Map the shared frame, irq etc. */ - err = xen_blkif_map(be->blkif, ring_ref, evtchn); + err = xen_blkif_map(be->blkif, ring_ref, nr_grefs, evtchn); if (err) { - xenbus_dev_fatal(dev, err, "mapping ring-ref %lu port %u", - ring_ref, evtchn); + xenbus_dev_fatal(dev, err, "mapping ring-ref port %u", evtchn); return err; } return 0; -} - - -/* ** Driver Registration ** */ +fail: + list_for_each_entry_safe(req, n, &be->blkif->pending_free, free_list) { + list_del(&req->free_list); + for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++) { + if (!req->segments[j]) + break; + kfree(req->segments[j]); + } + for (j = 0; j < MAX_INDIRECT_PAGES; j++) { + if (!req->indirect_pages[j]) + break; + kfree(req->indirect_pages[j]); + } + kfree(req); + } + return -ENOMEM; +} static const struct xenbus_device_id xen_blkbk_ids[] = { { "vbd" }, { "" } }; - -static DEFINE_XENBUS_DRIVER(xen_blkbk, , +static struct xenbus_driver xen_blkbk_driver = { + .ids = xen_blkbk_ids, .probe = xen_blkbk_probe, .remove = xen_blkbk_remove, .otherend_changed = frontend_changed -); - +}; int xen_blkif_xenbus_init(void) {