diff options
Diffstat (limited to 'drivers/block/xen-blkback')
| -rw-r--r-- | drivers/block/xen-blkback/Makefile | 3 | ||||
| -rw-r--r-- | drivers/block/xen-blkback/blkback.c | 1456 | ||||
| -rw-r--r-- | drivers/block/xen-blkback/common.h | 492 | ||||
| -rw-r--r-- | drivers/block/xen-blkback/xenbus.c | 934 |
4 files changed, 2885 insertions, 0 deletions
diff --git a/drivers/block/xen-blkback/Makefile b/drivers/block/xen-blkback/Makefile new file mode 100644 index 000000000..e491c1b76 --- /dev/null +++ b/drivers/block/xen-blkback/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_XEN_BLKDEV_BACKEND) := xen-blkback.o + +xen-blkback-y := blkback.o xenbus.o diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c new file mode 100644 index 000000000..713fc9ff1 --- /dev/null +++ b/drivers/block/xen-blkback/blkback.c @@ -0,0 +1,1456 @@ +/****************************************************************************** + * + * Back-end of the driver for virtual block devices. This portion of the + * driver exports a 'unified' block-device interface that can be accessed + * by any operating system that implements a compatible front end. A + * reference front-end implementation can be found in: + * drivers/block/xen-blkfront.c + * + * Copyright (c) 2003-2004, Keir Fraser & Steve Hand + * Copyright (c) 2005, Christopher Clark + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#define pr_fmt(fmt) "xen-blkback: " fmt + +#include <linux/spinlock.h> +#include <linux/kthread.h> +#include <linux/list.h> +#include <linux/delay.h> +#include <linux/freezer.h> +#include <linux/bitmap.h> + +#include <xen/events.h> +#include <xen/page.h> +#include <xen/xen.h> +#include <asm/xen/hypervisor.h> +#include <asm/xen/hypercall.h> +#include <xen/balloon.h> +#include <xen/grant_table.h> +#include "common.h" + +/* + * Maximum number of unused free pages to keep in the internal buffer. + * Setting this to a value too low will reduce memory used in each backend, + * but can have a performance penalty. + * + * A sane value is xen_blkif_reqs * BLKIF_MAX_SEGMENTS_PER_REQUEST, but can + * be set to a lower value that might degrade performance on some intensive + * IO workloads. + */ + +static int xen_blkif_max_buffer_pages = 1024; +module_param_named(max_buffer_pages, xen_blkif_max_buffer_pages, int, 0644); +MODULE_PARM_DESC(max_buffer_pages, +"Maximum number of free pages to keep in each block backend buffer"); + +/* + * Maximum number of grants to map persistently in blkback. For maximum + * performance this should be the total numbers of grants that can be used + * to fill the ring, but since this might become too high, specially with + * the use of indirect descriptors, we set it to a value that provides good + * performance without using too much memory. + * + * When the list of persistent grants is full we clean it up using a LRU + * algorithm. + */ + +static int xen_blkif_max_pgrants = 1056; +module_param_named(max_persistent_grants, xen_blkif_max_pgrants, int, 0644); +MODULE_PARM_DESC(max_persistent_grants, + "Maximum number of grants to map persistently"); + +/* + * The LRU mechanism to clean the lists of persistent grants needs to + * be executed periodically. The time interval between consecutive executions + * of the purge mechanism is set in ms. + */ +#define LRU_INTERVAL 100 + +/* + * When the persistent grants list is full we will remove unused grants + * from the list. The percent number of grants to be removed at each LRU + * execution. + */ +#define LRU_PERCENT_CLEAN 5 + +/* Run-time switchable: /sys/module/blkback/parameters/ */ +static unsigned int log_stats; +module_param(log_stats, int, 0644); + +#define BLKBACK_INVALID_HANDLE (~0) + +/* Number of free pages to remove on each call to gnttab_free_pages */ +#define NUM_BATCH_FREE_PAGES 10 + +static inline int get_free_page(struct xen_blkif *blkif, struct page **page) +{ + unsigned long flags; + + spin_lock_irqsave(&blkif->free_pages_lock, flags); + if (list_empty(&blkif->free_pages)) { + BUG_ON(blkif->free_pages_num != 0); + spin_unlock_irqrestore(&blkif->free_pages_lock, flags); + return gnttab_alloc_pages(1, page); + } + BUG_ON(blkif->free_pages_num == 0); + page[0] = list_first_entry(&blkif->free_pages, struct page, lru); + list_del(&page[0]->lru); + blkif->free_pages_num--; + spin_unlock_irqrestore(&blkif->free_pages_lock, flags); + + return 0; +} + +static inline void put_free_pages(struct xen_blkif *blkif, struct page **page, + int num) +{ + unsigned long flags; + int i; + + spin_lock_irqsave(&blkif->free_pages_lock, flags); + for (i = 0; i < num; i++) + list_add(&page[i]->lru, &blkif->free_pages); + blkif->free_pages_num += num; + spin_unlock_irqrestore(&blkif->free_pages_lock, flags); +} + +static inline void shrink_free_pagepool(struct xen_blkif *blkif, int num) +{ + /* Remove requested pages in batches of NUM_BATCH_FREE_PAGES */ + struct page *page[NUM_BATCH_FREE_PAGES]; + unsigned int num_pages = 0; + unsigned long flags; + + spin_lock_irqsave(&blkif->free_pages_lock, flags); + while (blkif->free_pages_num > num) { + BUG_ON(list_empty(&blkif->free_pages)); + page[num_pages] = list_first_entry(&blkif->free_pages, + struct page, lru); + list_del(&page[num_pages]->lru); + blkif->free_pages_num--; + if (++num_pages == NUM_BATCH_FREE_PAGES) { + spin_unlock_irqrestore(&blkif->free_pages_lock, flags); + gnttab_free_pages(num_pages, page); + spin_lock_irqsave(&blkif->free_pages_lock, flags); + num_pages = 0; + } + } + spin_unlock_irqrestore(&blkif->free_pages_lock, flags); + if (num_pages != 0) + gnttab_free_pages(num_pages, page); +} + +#define vaddr(page) ((unsigned long)pfn_to_kaddr(page_to_pfn(page))) + +static int do_block_io_op(struct xen_blkif *blkif); +static int dispatch_rw_block_io(struct xen_blkif *blkif, + struct blkif_request *req, + struct pending_req *pending_req); +static void make_response(struct xen_blkif *blkif, u64 id, + unsigned short op, int st); + +#define foreach_grant_safe(pos, n, rbtree, node) \ + for ((pos) = container_of(rb_first((rbtree)), typeof(*(pos)), node), \ + (n) = (&(pos)->node != NULL) ? rb_next(&(pos)->node) : NULL; \ + &(pos)->node != NULL; \ + (pos) = container_of(n, typeof(*(pos)), node), \ + (n) = (&(pos)->node != NULL) ? rb_next(&(pos)->node) : NULL) + + +/* + * We don't need locking around the persistent grant helpers + * because blkback uses a single-thread for each backed, so we + * can be sure that this functions will never be called recursively. + * + * The only exception to that is put_persistent_grant, that can be called + * from interrupt context (by xen_blkbk_unmap), so we have to use atomic + * bit operations to modify the flags of a persistent grant and to count + * the number of used grants. + */ +static int add_persistent_gnt(struct xen_blkif *blkif, + struct persistent_gnt *persistent_gnt) +{ + struct rb_node **new = NULL, *parent = NULL; + struct persistent_gnt *this; + + if (blkif->persistent_gnt_c >= xen_blkif_max_pgrants) { + if (!blkif->vbd.overflow_max_grants) + blkif->vbd.overflow_max_grants = 1; + return -EBUSY; + } + /* Figure out where to put new node */ + new = &blkif->persistent_gnts.rb_node; + while (*new) { + this = container_of(*new, struct persistent_gnt, node); + + parent = *new; + if (persistent_gnt->gnt < this->gnt) + new = &((*new)->rb_left); + else if (persistent_gnt->gnt > this->gnt) + new = &((*new)->rb_right); + else { + pr_alert_ratelimited("trying to add a gref that's already in the tree\n"); + return -EINVAL; + } + } + + bitmap_zero(persistent_gnt->flags, PERSISTENT_GNT_FLAGS_SIZE); + set_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags); + /* Add new node and rebalance tree. */ + rb_link_node(&(persistent_gnt->node), parent, new); + rb_insert_color(&(persistent_gnt->node), &blkif->persistent_gnts); + blkif->persistent_gnt_c++; + atomic_inc(&blkif->persistent_gnt_in_use); + return 0; +} + +static struct persistent_gnt *get_persistent_gnt(struct xen_blkif *blkif, + grant_ref_t gref) +{ + struct persistent_gnt *data; + struct rb_node *node = NULL; + + node = blkif->persistent_gnts.rb_node; + while (node) { + data = container_of(node, struct persistent_gnt, node); + + if (gref < data->gnt) + node = node->rb_left; + else if (gref > data->gnt) + node = node->rb_right; + else { + if(test_bit(PERSISTENT_GNT_ACTIVE, data->flags)) { + pr_alert_ratelimited("requesting a grant already in use\n"); + return NULL; + } + set_bit(PERSISTENT_GNT_ACTIVE, data->flags); + atomic_inc(&blkif->persistent_gnt_in_use); + return data; + } + } + return NULL; +} + +static void put_persistent_gnt(struct xen_blkif *blkif, + struct persistent_gnt *persistent_gnt) +{ + if(!test_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags)) + pr_alert_ratelimited("freeing a grant already unused\n"); + set_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags); + clear_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags); + atomic_dec(&blkif->persistent_gnt_in_use); +} + +static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root, + unsigned int num) +{ + struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct persistent_gnt *persistent_gnt; + struct rb_node *n; + int segs_to_unmap = 0; + struct gntab_unmap_queue_data unmap_data; + + unmap_data.pages = pages; + unmap_data.unmap_ops = unmap; + unmap_data.kunmap_ops = NULL; + + foreach_grant_safe(persistent_gnt, n, root, node) { + BUG_ON(persistent_gnt->handle == + BLKBACK_INVALID_HANDLE); + gnttab_set_unmap_op(&unmap[segs_to_unmap], + (unsigned long) pfn_to_kaddr(page_to_pfn( + persistent_gnt->page)), + GNTMAP_host_map, + persistent_gnt->handle); + + pages[segs_to_unmap] = persistent_gnt->page; + + if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST || + !rb_next(&persistent_gnt->node)) { + + unmap_data.count = segs_to_unmap; + BUG_ON(gnttab_unmap_refs_sync(&unmap_data)); + + put_free_pages(blkif, pages, segs_to_unmap); + segs_to_unmap = 0; + } + + rb_erase(&persistent_gnt->node, root); + kfree(persistent_gnt); + num--; + } + BUG_ON(num != 0); +} + +void xen_blkbk_unmap_purged_grants(struct work_struct *work) +{ + struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct persistent_gnt *persistent_gnt; + int segs_to_unmap = 0; + struct xen_blkif *blkif = container_of(work, typeof(*blkif), persistent_purge_work); + struct gntab_unmap_queue_data unmap_data; + + unmap_data.pages = pages; + unmap_data.unmap_ops = unmap; + unmap_data.kunmap_ops = NULL; + + while(!list_empty(&blkif->persistent_purge_list)) { + persistent_gnt = list_first_entry(&blkif->persistent_purge_list, + struct persistent_gnt, + remove_node); + list_del(&persistent_gnt->remove_node); + + gnttab_set_unmap_op(&unmap[segs_to_unmap], + vaddr(persistent_gnt->page), + GNTMAP_host_map, + persistent_gnt->handle); + + pages[segs_to_unmap] = persistent_gnt->page; + + if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) { + unmap_data.count = segs_to_unmap; + BUG_ON(gnttab_unmap_refs_sync(&unmap_data)); + put_free_pages(blkif, pages, segs_to_unmap); + segs_to_unmap = 0; + } + kfree(persistent_gnt); + } + if (segs_to_unmap > 0) { + unmap_data.count = segs_to_unmap; + BUG_ON(gnttab_unmap_refs_sync(&unmap_data)); + put_free_pages(blkif, pages, segs_to_unmap); + } +} + +static void purge_persistent_gnt(struct xen_blkif *blkif) +{ + struct persistent_gnt *persistent_gnt; + struct rb_node *n; + unsigned int num_clean, total; + bool scan_used = false, clean_used = false; + struct rb_root *root; + + if (blkif->persistent_gnt_c < xen_blkif_max_pgrants || + (blkif->persistent_gnt_c == xen_blkif_max_pgrants && + !blkif->vbd.overflow_max_grants)) { + return; + } + + if (work_pending(&blkif->persistent_purge_work)) { + pr_alert_ratelimited("Scheduled work from previous purge is still pending, cannot purge list\n"); + return; + } + + num_clean = (xen_blkif_max_pgrants / 100) * LRU_PERCENT_CLEAN; + num_clean = blkif->persistent_gnt_c - xen_blkif_max_pgrants + num_clean; + num_clean = min(blkif->persistent_gnt_c, num_clean); + if ((num_clean == 0) || + (num_clean > (blkif->persistent_gnt_c - atomic_read(&blkif->persistent_gnt_in_use)))) + return; + + /* + * At this point, we can assure that there will be no calls + * to get_persistent_grant (because we are executing this code from + * xen_blkif_schedule), there can only be calls to put_persistent_gnt, + * which means that the number of currently used grants will go down, + * but never up, so we will always be able to remove the requested + * number of grants. + */ + + total = num_clean; + + pr_debug("Going to purge %u persistent grants\n", num_clean); + + BUG_ON(!list_empty(&blkif->persistent_purge_list)); + root = &blkif->persistent_gnts; +purge_list: + foreach_grant_safe(persistent_gnt, n, root, node) { + BUG_ON(persistent_gnt->handle == + BLKBACK_INVALID_HANDLE); + + if (clean_used) { + clear_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags); + continue; + } + + if (test_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags)) + continue; + if (!scan_used && + (test_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags))) + continue; + + rb_erase(&persistent_gnt->node, root); + list_add(&persistent_gnt->remove_node, + &blkif->persistent_purge_list); + if (--num_clean == 0) + goto finished; + } + /* + * If we get here it means we also need to start cleaning + * grants that were used since last purge in order to cope + * with the requested num + */ + if (!scan_used && !clean_used) { + pr_debug("Still missing %u purged frames\n", num_clean); + scan_used = true; + goto purge_list; + } +finished: + if (!clean_used) { + pr_debug("Finished scanning for grants to clean, removing used flag\n"); + clean_used = true; + goto purge_list; + } + + blkif->persistent_gnt_c -= (total - num_clean); + blkif->vbd.overflow_max_grants = 0; + + /* We can defer this work */ + schedule_work(&blkif->persistent_purge_work); + pr_debug("Purged %u/%u\n", (total - num_clean), total); + return; +} + +/* + * Retrieve from the 'pending_reqs' a free pending_req structure to be used. + */ +static struct pending_req *alloc_req(struct xen_blkif *blkif) +{ + struct pending_req *req = NULL; + unsigned long flags; + + spin_lock_irqsave(&blkif->pending_free_lock, flags); + if (!list_empty(&blkif->pending_free)) { + req = list_entry(blkif->pending_free.next, struct pending_req, + free_list); + list_del(&req->free_list); + } + spin_unlock_irqrestore(&blkif->pending_free_lock, flags); + return req; +} + +/* + * Return the 'pending_req' structure back to the freepool. We also + * wake up the thread if it was waiting for a free page. + */ +static void free_req(struct xen_blkif *blkif, struct pending_req *req) +{ + unsigned long flags; + int was_empty; + + spin_lock_irqsave(&blkif->pending_free_lock, flags); + was_empty = list_empty(&blkif->pending_free); + list_add(&req->free_list, &blkif->pending_free); + spin_unlock_irqrestore(&blkif->pending_free_lock, flags); + if (was_empty) + wake_up(&blkif->pending_free_wq); +} + +/* + * Routines for managing virtual block devices (vbds). + */ +static int xen_vbd_translate(struct phys_req *req, struct xen_blkif *blkif, + int operation) +{ + struct xen_vbd *vbd = &blkif->vbd; + int rc = -EACCES; + + if ((operation != READ) && vbd->readonly) + goto out; + + if (likely(req->nr_sects)) { + blkif_sector_t end = req->sector_number + req->nr_sects; + + if (unlikely(end < req->sector_number)) + goto out; + if (unlikely(end > vbd_sz(vbd))) + goto out; + } + + req->dev = vbd->pdevice; + req->bdev = vbd->bdev; + rc = 0; + + out: + return rc; +} + +static void xen_vbd_resize(struct xen_blkif *blkif) +{ + struct xen_vbd *vbd = &blkif->vbd; + struct xenbus_transaction xbt; + int err; + struct xenbus_device *dev = xen_blkbk_xenbus(blkif->be); + unsigned long long new_size = vbd_sz(vbd); + + pr_info("VBD Resize: Domid: %d, Device: (%d, %d)\n", + blkif->domid, MAJOR(vbd->pdevice), MINOR(vbd->pdevice)); + pr_info("VBD Resize: new size %llu\n", new_size); + vbd->size = new_size; +again: + err = xenbus_transaction_start(&xbt); + if (err) { + pr_warn("Error starting transaction\n"); + return; + } + err = xenbus_printf(xbt, dev->nodename, "sectors", "%llu", + (unsigned long long)vbd_sz(vbd)); + if (err) { + pr_warn("Error writing new size\n"); + goto abort; + } + /* + * Write the current state; we will use this to synchronize + * the front-end. If the current state is "connected" the + * front-end will get the new size information online. + */ + err = xenbus_printf(xbt, dev->nodename, "state", "%d", dev->state); + if (err) { + pr_warn("Error writing the state\n"); + goto abort; + } + + err = xenbus_transaction_end(xbt, 0); + if (err == -EAGAIN) + goto again; + if (err) + pr_warn("Error ending transaction\n"); + return; +abort: + xenbus_transaction_end(xbt, 1); +} + +/* + * Notification from the guest OS. + */ +static void blkif_notify_work(struct xen_blkif *blkif) +{ + blkif->waiting_reqs = 1; + wake_up(&blkif->wq); +} + +irqreturn_t xen_blkif_be_int(int irq, void *dev_id) +{ + blkif_notify_work(dev_id); + return IRQ_HANDLED; +} + +/* + * SCHEDULER FUNCTIONS + */ + +static void print_stats(struct xen_blkif *blkif) +{ + pr_info("(%s): oo %3llu | rd %4llu | wr %4llu | f %4llu" + " | ds %4llu | pg: %4u/%4d\n", + current->comm, blkif->st_oo_req, + blkif->st_rd_req, blkif->st_wr_req, + blkif->st_f_req, blkif->st_ds_req, + blkif->persistent_gnt_c, + xen_blkif_max_pgrants); + blkif->st_print = jiffies + msecs_to_jiffies(10 * 1000); + blkif->st_rd_req = 0; + blkif->st_wr_req = 0; + blkif->st_oo_req = 0; + blkif->st_ds_req = 0; +} + +int xen_blkif_schedule(void *arg) +{ + struct xen_blkif *blkif = arg; + struct xen_vbd *vbd = &blkif->vbd; + unsigned long timeout; + int ret; + + xen_blkif_get(blkif); + + while (!kthread_should_stop()) { + if (try_to_freeze()) + continue; + if (unlikely(vbd->size != vbd_sz(vbd))) + xen_vbd_resize(blkif); + + timeout = msecs_to_jiffies(LRU_INTERVAL); + + timeout = wait_event_interruptible_timeout( + blkif->wq, + blkif->waiting_reqs || kthread_should_stop(), + timeout); + if (timeout == 0) + goto purge_gnt_list; + timeout = wait_event_interruptible_timeout( + blkif->pending_free_wq, + !list_empty(&blkif->pending_free) || + kthread_should_stop(), + timeout); + if (timeout == 0) + goto purge_gnt_list; + + blkif->waiting_reqs = 0; + smp_mb(); /* clear flag *before* checking for work */ + + ret = do_block_io_op(blkif); + if (ret > 0) + blkif->waiting_reqs = 1; + if (ret == -EACCES) + wait_event_interruptible(blkif->shutdown_wq, + kthread_should_stop()); + +purge_gnt_list: + if (blkif->vbd.feature_gnt_persistent && + time_after(jiffies, blkif->next_lru)) { + purge_persistent_gnt(blkif); + blkif->next_lru = jiffies + msecs_to_jiffies(LRU_INTERVAL); + } + + /* Shrink if we have more than xen_blkif_max_buffer_pages */ + shrink_free_pagepool(blkif, xen_blkif_max_buffer_pages); + + if (log_stats && time_after(jiffies, blkif->st_print)) + print_stats(blkif); + } + + /* Drain pending purge work */ + flush_work(&blkif->persistent_purge_work); + + if (log_stats) + print_stats(blkif); + + blkif->xenblkd = NULL; + xen_blkif_put(blkif); + + return 0; +} + +/* + * Remove persistent grants and empty the pool of free pages + */ +void xen_blkbk_free_caches(struct xen_blkif *blkif) +{ + /* Free all persistent grant pages */ + if (!RB_EMPTY_ROOT(&blkif->persistent_gnts)) + free_persistent_gnts(blkif, &blkif->persistent_gnts, + blkif->persistent_gnt_c); + + BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts)); + blkif->persistent_gnt_c = 0; + + /* Since we are shutting down remove all pages from the buffer */ + shrink_free_pagepool(blkif, 0 /* All */); +} + +static unsigned int xen_blkbk_unmap_prepare( + struct xen_blkif *blkif, + struct grant_page **pages, + unsigned int num, + struct gnttab_unmap_grant_ref *unmap_ops, + struct page **unmap_pages) +{ + unsigned int i, invcount = 0; + + for (i = 0; i < num; i++) { + if (pages[i]->persistent_gnt != NULL) { + put_persistent_gnt(blkif, pages[i]->persistent_gnt); + continue; + } + if (pages[i]->handle == BLKBACK_INVALID_HANDLE) + continue; + unmap_pages[invcount] = pages[i]->page; + gnttab_set_unmap_op(&unmap_ops[invcount], vaddr(pages[i]->page), + GNTMAP_host_map, pages[i]->handle); + pages[i]->handle = BLKBACK_INVALID_HANDLE; + invcount++; + } + + return invcount; +} + +static void xen_blkbk_unmap_and_respond_callback(int result, struct gntab_unmap_queue_data *data) +{ + struct pending_req* pending_req = (struct pending_req*) (data->data); + struct xen_blkif *blkif = pending_req->blkif; + + /* BUG_ON used to reproduce existing behaviour, + but is this the best way to deal with this? */ + BUG_ON(result); + + put_free_pages(blkif, data->pages, data->count); + make_response(blkif, pending_req->id, + pending_req->operation, pending_req->status); + free_req(blkif, pending_req); + /* + * Make sure the request is freed before releasing blkif, + * or there could be a race between free_req and the + * cleanup done in xen_blkif_free during shutdown. + * + * NB: The fact that we might try to wake up pending_free_wq + * before drain_complete (in case there's a drain going on) + * it's not a problem with our current implementation + * because we can assure there's no thread waiting on + * pending_free_wq if there's a drain going on, but it has + * to be taken into account if the current model is changed. + */ + if (atomic_dec_and_test(&blkif->inflight) && atomic_read(&blkif->drain)) { + complete(&blkif->drain_complete); + } + xen_blkif_put(blkif); +} + +static void xen_blkbk_unmap_and_respond(struct pending_req *req) +{ + struct gntab_unmap_queue_data* work = &req->gnttab_unmap_data; + struct xen_blkif *blkif = req->blkif; + struct grant_page **pages = req->segments; + unsigned int invcount; + + invcount = xen_blkbk_unmap_prepare(blkif, pages, req->nr_pages, + req->unmap, req->unmap_pages); + + work->data = req; + work->done = xen_blkbk_unmap_and_respond_callback; + work->unmap_ops = req->unmap; + work->kunmap_ops = NULL; + work->pages = req->unmap_pages; + work->count = invcount; + + gnttab_unmap_refs_async(&req->gnttab_unmap_data); +} + + +/* + * Unmap the grant references. + * + * This could accumulate ops up to the batch size to reduce the number + * of hypercalls, but since this is only used in error paths there's + * no real need. + */ +static void xen_blkbk_unmap(struct xen_blkif *blkif, + struct grant_page *pages[], + int num) +{ + struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct page *unmap_pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + unsigned int invcount = 0; + int ret; + + while (num) { + unsigned int batch = min(num, BLKIF_MAX_SEGMENTS_PER_REQUEST); + + invcount = xen_blkbk_unmap_prepare(blkif, pages, batch, + unmap, unmap_pages); + if (invcount) { + ret = gnttab_unmap_refs(unmap, NULL, unmap_pages, invcount); + BUG_ON(ret); + put_free_pages(blkif, unmap_pages, invcount); + } + pages += batch; + num -= batch; + } +} + +static int xen_blkbk_map(struct xen_blkif *blkif, + struct grant_page *pages[], + int num, bool ro) +{ + struct gnttab_map_grant_ref map[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct page *pages_to_gnt[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct persistent_gnt *persistent_gnt = NULL; + phys_addr_t addr = 0; + int i, seg_idx, new_map_idx; + int segs_to_map = 0; + int ret = 0; + int last_map = 0, map_until = 0; + int use_persistent_gnts; + + use_persistent_gnts = (blkif->vbd.feature_gnt_persistent); + + /* + * Fill out preq.nr_sects with proper amount of sectors, and setup + * assign map[..] with the PFN of the page in our domain with the + * corresponding grant reference for each page. + */ +again: + for (i = map_until; i < num; i++) { + uint32_t flags; + + if (use_persistent_gnts) + persistent_gnt = get_persistent_gnt( + blkif, + pages[i]->gref); + + if (persistent_gnt) { + /* + * We are using persistent grants and + * the grant is already mapped + */ + pages[i]->page = persistent_gnt->page; + pages[i]->persistent_gnt = persistent_gnt; + } else { + if (get_free_page(blkif, &pages[i]->page)) + goto out_of_memory; + addr = vaddr(pages[i]->page); + pages_to_gnt[segs_to_map] = pages[i]->page; + pages[i]->persistent_gnt = NULL; + flags = GNTMAP_host_map; + if (!use_persistent_gnts && ro) + flags |= GNTMAP_readonly; + gnttab_set_map_op(&map[segs_to_map++], addr, + flags, pages[i]->gref, + blkif->domid); + } + map_until = i + 1; + if (segs_to_map == BLKIF_MAX_SEGMENTS_PER_REQUEST) + break; + } + + if (segs_to_map) { + ret = gnttab_map_refs(map, NULL, pages_to_gnt, segs_to_map); + BUG_ON(ret); + } + + /* + * Now swizzle the MFN in our domain with the MFN from the other domain + * so that when we access vaddr(pending_req,i) it has the contents of + * the page from the other domain. + */ + for (seg_idx = last_map, new_map_idx = 0; seg_idx < map_until; seg_idx++) { + if (!pages[seg_idx]->persistent_gnt) { + /* This is a newly mapped grant */ + BUG_ON(new_map_idx >= segs_to_map); + if (unlikely(map[new_map_idx].status != 0)) { + pr_debug("invalid buffer -- could not remap it\n"); + put_free_pages(blkif, &pages[seg_idx]->page, 1); + pages[seg_idx]->handle = BLKBACK_INVALID_HANDLE; + ret |= 1; + goto next; + } + pages[seg_idx]->handle = map[new_map_idx].handle; + } else { + continue; + } + if (use_persistent_gnts && + blkif->persistent_gnt_c < xen_blkif_max_pgrants) { + /* + * We are using persistent grants, the grant is + * not mapped but we might have room for it. + */ + persistent_gnt = kmalloc(sizeof(struct persistent_gnt), + GFP_KERNEL); + if (!persistent_gnt) { + /* + * If we don't have enough memory to + * allocate the persistent_gnt struct + * map this grant non-persistenly + */ + goto next; + } + persistent_gnt->gnt = map[new_map_idx].ref; + persistent_gnt->handle = map[new_map_idx].handle; + persistent_gnt->page = pages[seg_idx]->page; + if (add_persistent_gnt(blkif, + persistent_gnt)) { + kfree(persistent_gnt); + persistent_gnt = NULL; + goto next; + } + pages[seg_idx]->persistent_gnt = persistent_gnt; + pr_debug("grant %u added to the tree of persistent grants, using %u/%u\n", + persistent_gnt->gnt, blkif->persistent_gnt_c, + xen_blkif_max_pgrants); + goto next; + } + if (use_persistent_gnts && !blkif->vbd.overflow_max_grants) { + blkif->vbd.overflow_max_grants = 1; + pr_debug("domain %u, device %#x is using maximum number of persistent grants\n", + blkif->domid, blkif->vbd.handle); + } + /* + * We could not map this grant persistently, so use it as + * a non-persistent grant. + */ +next: + new_map_idx++; + } + segs_to_map = 0; + last_map = map_until; + if (map_until != num) + goto again; + + return ret; + +out_of_memory: + pr_alert("%s: out of memory\n", __func__); + put_free_pages(blkif, pages_to_gnt, segs_to_map); + return -ENOMEM; +} + +static int xen_blkbk_map_seg(struct pending_req *pending_req) +{ + int rc; + + rc = xen_blkbk_map(pending_req->blkif, pending_req->segments, + pending_req->nr_pages, + (pending_req->operation != BLKIF_OP_READ)); + + return rc; +} + +static int xen_blkbk_parse_indirect(struct blkif_request *req, + struct pending_req *pending_req, + struct seg_buf seg[], + struct phys_req *preq) +{ + struct grant_page **pages = pending_req->indirect_pages; + struct xen_blkif *blkif = pending_req->blkif; + int indirect_grefs, rc, n, nseg, i; + struct blkif_request_segment *segments = NULL; + + nseg = pending_req->nr_pages; + indirect_grefs = INDIRECT_PAGES(nseg); + BUG_ON(indirect_grefs > BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST); + + for (i = 0; i < indirect_grefs; i++) + pages[i]->gref = req->u.indirect.indirect_grefs[i]; + + rc = xen_blkbk_map(blkif, pages, indirect_grefs, true); + if (rc) + goto unmap; + + for (n = 0, i = 0; n < nseg; n++) { + if ((n % SEGS_PER_INDIRECT_FRAME) == 0) { + /* Map indirect segments */ + if (segments) + kunmap_atomic(segments); + segments = kmap_atomic(pages[n/SEGS_PER_INDIRECT_FRAME]->page); + } + i = n % SEGS_PER_INDIRECT_FRAME; + pending_req->segments[n]->gref = segments[i].gref; + seg[n].nsec = segments[i].last_sect - + segments[i].first_sect + 1; + seg[n].offset = (segments[i].first_sect << 9); + if ((segments[i].last_sect >= (PAGE_SIZE >> 9)) || + (segments[i].last_sect < segments[i].first_sect)) { + rc = -EINVAL; + goto unmap; + } + preq->nr_sects += seg[n].nsec; + } + +unmap: + if (segments) + kunmap_atomic(segments); + xen_blkbk_unmap(blkif, pages, indirect_grefs); + return rc; +} + +static int dispatch_discard_io(struct xen_blkif *blkif, + struct blkif_request *req) +{ + int err = 0; + int status = BLKIF_RSP_OKAY; + struct block_device *bdev = blkif->vbd.bdev; + unsigned long secure; + struct phys_req preq; + + xen_blkif_get(blkif); + + preq.sector_number = req->u.discard.sector_number; + preq.nr_sects = req->u.discard.nr_sectors; + + err = xen_vbd_translate(&preq, blkif, WRITE); + if (err) { + pr_warn("access denied: DISCARD [%llu->%llu] on dev=%04x\n", + preq.sector_number, + preq.sector_number + preq.nr_sects, blkif->vbd.pdevice); + goto fail_response; + } + blkif->st_ds_req++; + + secure = (blkif->vbd.discard_secure && + (req->u.discard.flag & BLKIF_DISCARD_SECURE)) ? + BLKDEV_DISCARD_SECURE : 0; + + err = blkdev_issue_discard(bdev, req->u.discard.sector_number, + req->u.discard.nr_sectors, + GFP_KERNEL, secure); +fail_response: + if (err == -EOPNOTSUPP) { + pr_debug("discard op failed, not supported\n"); + status = BLKIF_RSP_EOPNOTSUPP; + } else if (err) + status = BLKIF_RSP_ERROR; + + make_response(blkif, req->u.discard.id, req->operation, status); + xen_blkif_put(blkif); + return err; +} + +static int dispatch_other_io(struct xen_blkif *blkif, + struct blkif_request *req, + struct pending_req *pending_req) +{ + free_req(blkif, pending_req); + make_response(blkif, req->u.other.id, req->operation, + BLKIF_RSP_EOPNOTSUPP); + return -EIO; +} + +static void xen_blk_drain_io(struct xen_blkif *blkif) +{ + atomic_set(&blkif->drain, 1); + do { + if (atomic_read(&blkif->inflight) == 0) + break; + wait_for_completion_interruptible_timeout( + &blkif->drain_complete, HZ); + + if (!atomic_read(&blkif->drain)) + break; + } while (!kthread_should_stop()); + atomic_set(&blkif->drain, 0); +} + +/* + * Completion callback on the bio's. Called as bh->b_end_io() + */ + +static void __end_block_io_op(struct pending_req *pending_req, int error) +{ + /* An error fails the entire request. */ + if ((pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE) && + (error == -EOPNOTSUPP)) { + pr_debug("flush diskcache op failed, not supported\n"); + xen_blkbk_flush_diskcache(XBT_NIL, pending_req->blkif->be, 0); + pending_req->status = BLKIF_RSP_EOPNOTSUPP; + } else if ((pending_req->operation == BLKIF_OP_WRITE_BARRIER) && + (error == -EOPNOTSUPP)) { + pr_debug("write barrier op failed, not supported\n"); + xen_blkbk_barrier(XBT_NIL, pending_req->blkif->be, 0); + pending_req->status = BLKIF_RSP_EOPNOTSUPP; + } else if (error) { + pr_debug("Buffer not up-to-date at end of operation," + " error=%d\n", error); + pending_req->status = BLKIF_RSP_ERROR; + } + + /* + * If all of the bio's have completed it is time to unmap + * the grant references associated with 'request' and provide + * the proper response on the ring. + */ + if (atomic_dec_and_test(&pending_req->pendcnt)) + xen_blkbk_unmap_and_respond(pending_req); +} + +/* + * bio callback. + */ +static void end_block_io_op(struct bio *bio, int error) +{ + __end_block_io_op(bio->bi_private, error); + bio_put(bio); +} + + + +/* + * Function to copy the from the ring buffer the 'struct blkif_request' + * (which has the sectors we want, number of them, grant references, etc), + * and transmute it to the block API to hand it over to the proper block disk. + */ +static int +__do_block_io_op(struct xen_blkif *blkif) +{ + union blkif_back_rings *blk_rings = &blkif->blk_rings; + struct blkif_request req; + struct pending_req *pending_req; + RING_IDX rc, rp; + int more_to_do = 0; + + rc = blk_rings->common.req_cons; + rp = blk_rings->common.sring->req_prod; + rmb(); /* Ensure we see queued requests up to 'rp'. */ + + if (RING_REQUEST_PROD_OVERFLOW(&blk_rings->common, rp)) { + rc = blk_rings->common.rsp_prod_pvt; + pr_warn("Frontend provided bogus ring requests (%d - %d = %d). Halting ring processing on dev=%04x\n", + rp, rc, rp - rc, blkif->vbd.pdevice); + return -EACCES; + } + while (rc != rp) { + + if (RING_REQUEST_CONS_OVERFLOW(&blk_rings->common, rc)) + break; + + if (kthread_should_stop()) { + more_to_do = 1; + break; + } + + pending_req = alloc_req(blkif); + if (NULL == pending_req) { + blkif->st_oo_req++; + more_to_do = 1; + break; + } + + switch (blkif->blk_protocol) { + case BLKIF_PROTOCOL_NATIVE: + memcpy(&req, RING_GET_REQUEST(&blk_rings->native, rc), sizeof(req)); + break; + case BLKIF_PROTOCOL_X86_32: + blkif_get_x86_32_req(&req, RING_GET_REQUEST(&blk_rings->x86_32, rc)); + break; + case BLKIF_PROTOCOL_X86_64: + blkif_get_x86_64_req(&req, RING_GET_REQUEST(&blk_rings->x86_64, rc)); + break; + default: + BUG(); + } + blk_rings->common.req_cons = ++rc; /* before make_response() */ + + /* Apply all sanity checks to /private copy/ of request. */ + barrier(); + + switch (req.operation) { + case BLKIF_OP_READ: + case BLKIF_OP_WRITE: + case BLKIF_OP_WRITE_BARRIER: + case BLKIF_OP_FLUSH_DISKCACHE: + case BLKIF_OP_INDIRECT: + if (dispatch_rw_block_io(blkif, &req, pending_req)) + goto done; + break; + case BLKIF_OP_DISCARD: + free_req(blkif, pending_req); + if (dispatch_discard_io(blkif, &req)) + goto done; + break; + default: + if (dispatch_other_io(blkif, &req, pending_req)) + goto done; + break; + } + + /* Yield point for this unbounded loop. */ + cond_resched(); + } +done: + return more_to_do; +} + +static int +do_block_io_op(struct xen_blkif *blkif) +{ + union blkif_back_rings *blk_rings = &blkif->blk_rings; + int more_to_do; + + do { + more_to_do = __do_block_io_op(blkif); + if (more_to_do) + break; + + RING_FINAL_CHECK_FOR_REQUESTS(&blk_rings->common, more_to_do); + } while (more_to_do); + + return more_to_do; +} +/* + * Transmutation of the 'struct blkif_request' to a proper 'struct bio' + * and call the 'submit_bio' to pass it to the underlying storage. + */ +static int dispatch_rw_block_io(struct xen_blkif *blkif, + struct blkif_request *req, + struct pending_req *pending_req) +{ + struct phys_req preq; + struct seg_buf *seg = pending_req->seg; + unsigned int nseg; + struct bio *bio = NULL; + struct bio **biolist = pending_req->biolist; + int i, nbio = 0; + int operation; + struct blk_plug plug; + bool drain = false; + struct grant_page **pages = pending_req->segments; + unsigned short req_operation; + + req_operation = req->operation == BLKIF_OP_INDIRECT ? + req->u.indirect.indirect_op : req->operation; + if ((req->operation == BLKIF_OP_INDIRECT) && + (req_operation != BLKIF_OP_READ) && + (req_operation != BLKIF_OP_WRITE)) { + pr_debug("Invalid indirect operation (%u)\n", req_operation); + goto fail_response; + } + + switch (req_operation) { + case BLKIF_OP_READ: + blkif->st_rd_req++; + operation = READ; + break; + case BLKIF_OP_WRITE: + blkif->st_wr_req++; + operation = WRITE_ODIRECT; + break; + case BLKIF_OP_WRITE_BARRIER: + drain = true; + case BLKIF_OP_FLUSH_DISKCACHE: + blkif->st_f_req++; + operation = WRITE_FLUSH; + break; + default: + operation = 0; /* make gcc happy */ + goto fail_response; + break; + } + + /* Check that the number of segments is sane. */ + nseg = req->operation == BLKIF_OP_INDIRECT ? + req->u.indirect.nr_segments : req->u.rw.nr_segments; + + if (unlikely(nseg == 0 && operation != WRITE_FLUSH) || + unlikely((req->operation != BLKIF_OP_INDIRECT) && + (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST)) || + unlikely((req->operation == BLKIF_OP_INDIRECT) && + (nseg > MAX_INDIRECT_SEGMENTS))) { + pr_debug("Bad number of segments in request (%d)\n", nseg); + /* Haven't submitted any bio's yet. */ + goto fail_response; + } + + preq.nr_sects = 0; + + pending_req->blkif = blkif; + pending_req->id = req->u.rw.id; + pending_req->operation = req_operation; + pending_req->status = BLKIF_RSP_OKAY; + pending_req->nr_pages = nseg; + + if (req->operation != BLKIF_OP_INDIRECT) { + preq.dev = req->u.rw.handle; + preq.sector_number = req->u.rw.sector_number; + for (i = 0; i < nseg; i++) { + pages[i]->gref = req->u.rw.seg[i].gref; + seg[i].nsec = req->u.rw.seg[i].last_sect - + req->u.rw.seg[i].first_sect + 1; + seg[i].offset = (req->u.rw.seg[i].first_sect << 9); + if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) || + (req->u.rw.seg[i].last_sect < + req->u.rw.seg[i].first_sect)) + goto fail_response; + preq.nr_sects += seg[i].nsec; + } + } else { + preq.dev = req->u.indirect.handle; + preq.sector_number = req->u.indirect.sector_number; + if (xen_blkbk_parse_indirect(req, pending_req, seg, &preq)) + goto fail_response; + } + + if (xen_vbd_translate(&preq, blkif, operation) != 0) { + pr_debug("access denied: %s of [%llu,%llu] on dev=%04x\n", + operation == READ ? "read" : "write", + preq.sector_number, + preq.sector_number + preq.nr_sects, + blkif->vbd.pdevice); + goto fail_response; + } + + /* + * This check _MUST_ be done after xen_vbd_translate as the preq.bdev + * is set there. + */ + for (i = 0; i < nseg; i++) { + if (((int)preq.sector_number|(int)seg[i].nsec) & + ((bdev_logical_block_size(preq.bdev) >> 9) - 1)) { + pr_debug("Misaligned I/O request from domain %d\n", + blkif->domid); + goto fail_response; + } + } + + /* Wait on all outstanding I/O's and once that has been completed + * issue the WRITE_FLUSH. + */ + if (drain) + xen_blk_drain_io(pending_req->blkif); + + /* + * If we have failed at this point, we need to undo the M2P override, + * set gnttab_set_unmap_op on all of the grant references and perform + * the hypercall to unmap the grants - that is all done in + * xen_blkbk_unmap. + */ + if (xen_blkbk_map_seg(pending_req)) + goto fail_flush; + + /* + * This corresponding xen_blkif_put is done in __end_block_io_op, or + * below (in "!bio") if we are handling a BLKIF_OP_DISCARD. + */ + xen_blkif_get(blkif); + atomic_inc(&blkif->inflight); + + for (i = 0; i < nseg; i++) { + while ((bio == NULL) || + (bio_add_page(bio, + pages[i]->page, + seg[i].nsec << 9, + seg[i].offset) == 0)) { + + int nr_iovecs = min_t(int, (nseg-i), BIO_MAX_PAGES); + bio = bio_alloc(GFP_KERNEL, nr_iovecs); + if (unlikely(bio == NULL)) + goto fail_put_bio; + + biolist[nbio++] = bio; + bio->bi_bdev = preq.bdev; + bio->bi_private = pending_req; + bio->bi_end_io = end_block_io_op; + bio->bi_iter.bi_sector = preq.sector_number; + } + + preq.sector_number += seg[i].nsec; + } + + /* This will be hit if the operation was a flush or discard. */ + if (!bio) { + BUG_ON(operation != WRITE_FLUSH); + + bio = bio_alloc(GFP_KERNEL, 0); + if (unlikely(bio == NULL)) + goto fail_put_bio; + + biolist[nbio++] = bio; + bio->bi_bdev = preq.bdev; + bio->bi_private = pending_req; + bio->bi_end_io = end_block_io_op; + } + + atomic_set(&pending_req->pendcnt, nbio); + blk_start_plug(&plug); + + for (i = 0; i < nbio; i++) + submit_bio(operation, biolist[i]); + + /* Let the I/Os go.. */ + blk_finish_plug(&plug); + + if (operation == READ) + blkif->st_rd_sect += preq.nr_sects; + else if (operation & WRITE) + blkif->st_wr_sect += preq.nr_sects; + + return 0; + + fail_flush: + xen_blkbk_unmap(blkif, pending_req->segments, + pending_req->nr_pages); + fail_response: + /* Haven't submitted any bio's yet. */ + make_response(blkif, req->u.rw.id, req_operation, BLKIF_RSP_ERROR); + free_req(blkif, pending_req); + msleep(1); /* back off a bit */ + return -EIO; + + fail_put_bio: + for (i = 0; i < nbio; i++) + bio_put(biolist[i]); + atomic_set(&pending_req->pendcnt, 1); + __end_block_io_op(pending_req, -EINVAL); + msleep(1); /* back off a bit */ + return -EIO; +} + + + +/* + * Put a response on the ring on how the operation fared. + */ +static void make_response(struct xen_blkif *blkif, u64 id, + unsigned short op, int st) +{ + struct blkif_response resp; + unsigned long flags; + union blkif_back_rings *blk_rings = &blkif->blk_rings; + int notify; + + resp.id = id; + resp.operation = op; + resp.status = st; + + spin_lock_irqsave(&blkif->blk_ring_lock, flags); + /* Place on the response ring for the relevant domain. */ + switch (blkif->blk_protocol) { + case BLKIF_PROTOCOL_NATIVE: + memcpy(RING_GET_RESPONSE(&blk_rings->native, blk_rings->native.rsp_prod_pvt), + &resp, sizeof(resp)); + break; + case BLKIF_PROTOCOL_X86_32: + memcpy(RING_GET_RESPONSE(&blk_rings->x86_32, blk_rings->x86_32.rsp_prod_pvt), + &resp, sizeof(resp)); + break; + case BLKIF_PROTOCOL_X86_64: + memcpy(RING_GET_RESPONSE(&blk_rings->x86_64, blk_rings->x86_64.rsp_prod_pvt), + &resp, sizeof(resp)); + break; + default: + BUG(); + } + blk_rings->common.rsp_prod_pvt++; + RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(&blk_rings->common, notify); + spin_unlock_irqrestore(&blkif->blk_ring_lock, flags); + if (notify) + notify_remote_via_irq(blkif->irq); +} + +static int __init xen_blkif_init(void) +{ + int rc = 0; + + if (!xen_domain()) + return -ENODEV; + + rc = xen_blkif_interface_init(); + if (rc) + goto failed_init; + + rc = xen_blkif_xenbus_init(); + if (rc) + goto failed_init; + + failed_init: + return rc; +} + +module_init(xen_blkif_init); + +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_ALIAS("xen-backend:vbd"); diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h new file mode 100644 index 000000000..f620b5d3f --- /dev/null +++ b/drivers/block/xen-blkback/common.h @@ -0,0 +1,492 @@ +/* + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef __XEN_BLKIF__BACKEND__COMMON_H__ +#define __XEN_BLKIF__BACKEND__COMMON_H__ + +#include <linux/module.h> +#include <linux/interrupt.h> +#include <linux/slab.h> +#include <linux/blkdev.h> +#include <linux/vmalloc.h> +#include <linux/wait.h> +#include <linux/io.h> +#include <linux/rbtree.h> +#include <asm/setup.h> +#include <asm/pgalloc.h> +#include <asm/hypervisor.h> +#include <xen/grant_table.h> +#include <xen/xenbus.h> +#include <xen/interface/io/ring.h> +#include <xen/interface/io/blkif.h> +#include <xen/interface/io/protocols.h> + +/* + * This is the maximum number of segments that would be allowed in indirect + * requests. This value will also be passed to the frontend. + */ +#define MAX_INDIRECT_SEGMENTS 256 + +#define SEGS_PER_INDIRECT_FRAME \ + (PAGE_SIZE/sizeof(struct blkif_request_segment)) +#define MAX_INDIRECT_PAGES \ + ((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME) +#define INDIRECT_PAGES(_segs) \ + ((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME) + +/* Not a real protocol. Used to generate ring structs which contain + * the elements common to all protocols only. This way we get a + * compiler-checkable way to use common struct elements, so we can + * avoid using switch(protocol) in a number of places. */ +struct blkif_common_request { + char dummy; +}; +struct blkif_common_response { + char dummy; +}; + +struct blkif_x86_32_request_rw { + uint8_t nr_segments; /* number of segments */ + blkif_vdev_t handle; /* only for read/write requests */ + uint64_t id; /* private guest value, echoed in resp */ + blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ + struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; +} __attribute__((__packed__)); + +struct blkif_x86_32_request_discard { + uint8_t flag; /* BLKIF_DISCARD_SECURE or zero */ + blkif_vdev_t _pad1; /* was "handle" for read/write requests */ + uint64_t id; /* private guest value, echoed in resp */ + blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ + uint64_t nr_sectors; +} __attribute__((__packed__)); + +struct blkif_x86_32_request_other { + uint8_t _pad1; + blkif_vdev_t _pad2; + uint64_t id; /* private guest value, echoed in resp */ +} __attribute__((__packed__)); + +struct blkif_x86_32_request_indirect { + uint8_t indirect_op; + uint16_t nr_segments; + uint64_t id; + blkif_sector_t sector_number; + blkif_vdev_t handle; + uint16_t _pad1; + grant_ref_t indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST]; + /* + * The maximum number of indirect segments (and pages) that will + * be used is determined by MAX_INDIRECT_SEGMENTS, this value + * is also exported to the guest (via xenstore + * feature-max-indirect-segments entry), so the frontend knows how + * many indirect segments the backend supports. + */ + uint64_t _pad2; /* make it 64 byte aligned */ +} __attribute__((__packed__)); + +struct blkif_x86_32_request { + uint8_t operation; /* BLKIF_OP_??? */ + union { + struct blkif_x86_32_request_rw rw; + struct blkif_x86_32_request_discard discard; + struct blkif_x86_32_request_other other; + struct blkif_x86_32_request_indirect indirect; + } u; +} __attribute__((__packed__)); + +/* i386 protocol version */ +#pragma pack(push, 4) +struct blkif_x86_32_response { + uint64_t id; /* copied from request */ + uint8_t operation; /* copied from request */ + int16_t status; /* BLKIF_RSP_??? */ +}; +#pragma pack(pop) +/* x86_64 protocol version */ + +struct blkif_x86_64_request_rw { + uint8_t nr_segments; /* number of segments */ + blkif_vdev_t handle; /* only for read/write requests */ + uint32_t _pad1; /* offsetof(blkif_reqest..,u.rw.id)==8 */ + uint64_t id; + blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ + struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; +} __attribute__((__packed__)); + +struct blkif_x86_64_request_discard { + uint8_t flag; /* BLKIF_DISCARD_SECURE or zero */ + blkif_vdev_t _pad1; /* was "handle" for read/write requests */ + uint32_t _pad2; /* offsetof(blkif_..,u.discard.id)==8 */ + uint64_t id; + blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ + uint64_t nr_sectors; +} __attribute__((__packed__)); + +struct blkif_x86_64_request_other { + uint8_t _pad1; + blkif_vdev_t _pad2; + uint32_t _pad3; /* offsetof(blkif_..,u.discard.id)==8 */ + uint64_t id; /* private guest value, echoed in resp */ +} __attribute__((__packed__)); + +struct blkif_x86_64_request_indirect { + uint8_t indirect_op; + uint16_t nr_segments; + uint32_t _pad1; /* offsetof(blkif_..,u.indirect.id)==8 */ + uint64_t id; + blkif_sector_t sector_number; + blkif_vdev_t handle; + uint16_t _pad2; + grant_ref_t indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST]; + /* + * The maximum number of indirect segments (and pages) that will + * be used is determined by MAX_INDIRECT_SEGMENTS, this value + * is also exported to the guest (via xenstore + * feature-max-indirect-segments entry), so the frontend knows how + * many indirect segments the backend supports. + */ + uint32_t _pad3; /* make it 64 byte aligned */ +} __attribute__((__packed__)); + +struct blkif_x86_64_request { + uint8_t operation; /* BLKIF_OP_??? */ + union { + struct blkif_x86_64_request_rw rw; + struct blkif_x86_64_request_discard discard; + struct blkif_x86_64_request_other other; + struct blkif_x86_64_request_indirect indirect; + } u; +} __attribute__((__packed__)); + +struct blkif_x86_64_response { + uint64_t __attribute__((__aligned__(8))) id; + uint8_t operation; /* copied from request */ + int16_t status; /* BLKIF_RSP_??? */ +}; + +DEFINE_RING_TYPES(blkif_common, struct blkif_common_request, + struct blkif_common_response); +DEFINE_RING_TYPES(blkif_x86_32, struct blkif_x86_32_request, + struct blkif_x86_32_response); +DEFINE_RING_TYPES(blkif_x86_64, struct blkif_x86_64_request, + struct blkif_x86_64_response); + +union blkif_back_rings { + struct blkif_back_ring native; + struct blkif_common_back_ring common; + struct blkif_x86_32_back_ring x86_32; + struct blkif_x86_64_back_ring x86_64; +}; + +enum blkif_protocol { + BLKIF_PROTOCOL_NATIVE = 1, + BLKIF_PROTOCOL_X86_32 = 2, + BLKIF_PROTOCOL_X86_64 = 3, +}; + +/* + * Default protocol if the frontend doesn't specify one. + */ +#ifdef CONFIG_X86 +# define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_X86_32 +#else +# define BLKIF_PROTOCOL_DEFAULT BLKIF_PROTOCOL_NATIVE +#endif + +struct xen_vbd { + /* What the domain refers to this vbd as. */ + blkif_vdev_t handle; + /* Non-zero -> read-only */ + unsigned char readonly; + /* VDISK_xxx */ + unsigned char type; + /* phys device that this vbd maps to. */ + u32 pdevice; + struct block_device *bdev; + /* Cached size parameter. */ + sector_t size; + unsigned int flush_support:1; + unsigned int discard_secure:1; + unsigned int feature_gnt_persistent:1; + unsigned int overflow_max_grants:1; +}; + +struct backend_info; + +/* Number of available flags */ +#define PERSISTENT_GNT_FLAGS_SIZE 2 +/* This persistent grant is currently in use */ +#define PERSISTENT_GNT_ACTIVE 0 +/* + * This persistent grant has been used, this flag is set when we remove the + * PERSISTENT_GNT_ACTIVE, to know that this grant has been used recently. + */ +#define PERSISTENT_GNT_WAS_ACTIVE 1 + +/* Number of requests that we can fit in a ring */ +#define XEN_BLKIF_REQS 32 + +struct persistent_gnt { + struct page *page; + grant_ref_t gnt; + grant_handle_t handle; + DECLARE_BITMAP(flags, PERSISTENT_GNT_FLAGS_SIZE); + struct rb_node node; + struct list_head remove_node; +}; + +struct xen_blkif { + /* Unique identifier for this interface. */ + domid_t domid; + unsigned int handle; + /* Physical parameters of the comms window. */ + unsigned int irq; + /* Comms information. */ + enum blkif_protocol blk_protocol; + union blkif_back_rings blk_rings; + void *blk_ring; + /* The VBD attached to this interface. */ + struct xen_vbd vbd; + /* Back pointer to the backend_info. */ + struct backend_info *be; + /* Private fields. */ + spinlock_t blk_ring_lock; + atomic_t refcnt; + + wait_queue_head_t wq; + /* for barrier (drain) requests */ + struct completion drain_complete; + atomic_t drain; + atomic_t inflight; + /* One thread per one blkif. */ + struct task_struct *xenblkd; + unsigned int waiting_reqs; + + /* tree to store persistent grants */ + struct rb_root persistent_gnts; + unsigned int persistent_gnt_c; + atomic_t persistent_gnt_in_use; + unsigned long next_lru; + + /* used by the kworker that offload work from the persistent purge */ + struct list_head persistent_purge_list; + struct work_struct persistent_purge_work; + + /* buffer of free pages to map grant refs */ + spinlock_t free_pages_lock; + int free_pages_num; + struct list_head free_pages; + + /* List of all 'pending_req' available */ + struct list_head pending_free; + /* And its spinlock. */ + spinlock_t pending_free_lock; + wait_queue_head_t pending_free_wq; + + /* statistics */ + unsigned long st_print; + unsigned long long st_rd_req; + unsigned long long st_wr_req; + unsigned long long st_oo_req; + unsigned long long st_f_req; + unsigned long long st_ds_req; + unsigned long long st_rd_sect; + unsigned long long st_wr_sect; + + struct work_struct free_work; + /* Thread shutdown wait queue. */ + wait_queue_head_t shutdown_wq; +}; + +struct seg_buf { + unsigned long offset; + unsigned int nsec; +}; + +struct grant_page { + struct page *page; + struct persistent_gnt *persistent_gnt; + grant_handle_t handle; + grant_ref_t gref; +}; + +/* + * Each outstanding request that we've passed to the lower device layers has a + * 'pending_req' allocated to it. Each buffer_head that completes decrements + * the pendcnt towards zero. When it hits zero, the specified domain has a + * response queued for it, with the saved 'id' passed back. + */ +struct pending_req { + struct xen_blkif *blkif; + u64 id; + int nr_pages; + atomic_t pendcnt; + unsigned short operation; + int status; + struct list_head free_list; + struct grant_page *segments[MAX_INDIRECT_SEGMENTS]; + /* Indirect descriptors */ + struct grant_page *indirect_pages[MAX_INDIRECT_PAGES]; + struct seg_buf seg[MAX_INDIRECT_SEGMENTS]; + struct bio *biolist[MAX_INDIRECT_SEGMENTS]; + struct gnttab_unmap_grant_ref unmap[MAX_INDIRECT_SEGMENTS]; + struct page *unmap_pages[MAX_INDIRECT_SEGMENTS]; + struct gntab_unmap_queue_data gnttab_unmap_data; +}; + + +#define vbd_sz(_v) ((_v)->bdev->bd_part ? \ + (_v)->bdev->bd_part->nr_sects : \ + get_capacity((_v)->bdev->bd_disk)) + +#define xen_blkif_get(_b) (atomic_inc(&(_b)->refcnt)) +#define xen_blkif_put(_b) \ + do { \ + if (atomic_dec_and_test(&(_b)->refcnt)) \ + schedule_work(&(_b)->free_work);\ + } while (0) + +struct phys_req { + unsigned short dev; + blkif_sector_t nr_sects; + struct block_device *bdev; + blkif_sector_t sector_number; +}; +int xen_blkif_interface_init(void); + +int xen_blkif_xenbus_init(void); + +irqreturn_t xen_blkif_be_int(int irq, void *dev_id); +int xen_blkif_schedule(void *arg); +int xen_blkif_purge_persistent(void *arg); +void xen_blkbk_free_caches(struct xen_blkif *blkif); + +int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt, + struct backend_info *be, int state); + +int xen_blkbk_barrier(struct xenbus_transaction xbt, + struct backend_info *be, int state); +struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be); +void xen_blkbk_unmap_purged_grants(struct work_struct *work); + +static inline void blkif_get_x86_32_req(struct blkif_request *dst, + struct blkif_x86_32_request *src) +{ + int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j; + dst->operation = src->operation; + switch (src->operation) { + case BLKIF_OP_READ: + case BLKIF_OP_WRITE: + case BLKIF_OP_WRITE_BARRIER: + case BLKIF_OP_FLUSH_DISKCACHE: + dst->u.rw.nr_segments = src->u.rw.nr_segments; + dst->u.rw.handle = src->u.rw.handle; + dst->u.rw.id = src->u.rw.id; + dst->u.rw.sector_number = src->u.rw.sector_number; + barrier(); + if (n > dst->u.rw.nr_segments) + n = dst->u.rw.nr_segments; + for (i = 0; i < n; i++) + dst->u.rw.seg[i] = src->u.rw.seg[i]; + break; + case BLKIF_OP_DISCARD: + dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; + dst->u.discard.sector_number = src->u.discard.sector_number; + dst->u.discard.nr_sectors = src->u.discard.nr_sectors; + break; + case BLKIF_OP_INDIRECT: + dst->u.indirect.indirect_op = src->u.indirect.indirect_op; + dst->u.indirect.nr_segments = src->u.indirect.nr_segments; + dst->u.indirect.handle = src->u.indirect.handle; + dst->u.indirect.id = src->u.indirect.id; + dst->u.indirect.sector_number = src->u.indirect.sector_number; + barrier(); + j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments)); + for (i = 0; i < j; i++) + dst->u.indirect.indirect_grefs[i] = + src->u.indirect.indirect_grefs[i]; + break; + default: + /* + * Don't know how to translate this op. Only get the + * ID so failure can be reported to the frontend. + */ + dst->u.other.id = src->u.other.id; + break; + } +} + +static inline void blkif_get_x86_64_req(struct blkif_request *dst, + struct blkif_x86_64_request *src) +{ + int i, n = BLKIF_MAX_SEGMENTS_PER_REQUEST, j; + dst->operation = src->operation; + switch (src->operation) { + case BLKIF_OP_READ: + case BLKIF_OP_WRITE: + case BLKIF_OP_WRITE_BARRIER: + case BLKIF_OP_FLUSH_DISKCACHE: + dst->u.rw.nr_segments = src->u.rw.nr_segments; + dst->u.rw.handle = src->u.rw.handle; + dst->u.rw.id = src->u.rw.id; + dst->u.rw.sector_number = src->u.rw.sector_number; + barrier(); + if (n > dst->u.rw.nr_segments) + n = dst->u.rw.nr_segments; + for (i = 0; i < n; i++) + dst->u.rw.seg[i] = src->u.rw.seg[i]; + break; + case BLKIF_OP_DISCARD: + dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; + dst->u.discard.sector_number = src->u.discard.sector_number; + dst->u.discard.nr_sectors = src->u.discard.nr_sectors; + break; + case BLKIF_OP_INDIRECT: + dst->u.indirect.indirect_op = src->u.indirect.indirect_op; + dst->u.indirect.nr_segments = src->u.indirect.nr_segments; + dst->u.indirect.handle = src->u.indirect.handle; + dst->u.indirect.id = src->u.indirect.id; + dst->u.indirect.sector_number = src->u.indirect.sector_number; + barrier(); + j = min(MAX_INDIRECT_PAGES, INDIRECT_PAGES(dst->u.indirect.nr_segments)); + for (i = 0; i < j; i++) + dst->u.indirect.indirect_grefs[i] = + src->u.indirect.indirect_grefs[i]; + break; + default: + /* + * Don't know how to translate this op. Only get the + * ID so failure can be reported to the frontend. + */ + dst->u.other.id = src->u.other.id; + break; + } +} + +#endif /* __XEN_BLKIF__BACKEND__COMMON_H__ */ diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c new file mode 100644 index 000000000..6ab69ad61 --- /dev/null +++ b/drivers/block/xen-blkback/xenbus.c @@ -0,0 +1,934 @@ +/* Xenbus code for blkif backend + Copyright (C) 2005 Rusty Russell <rusty@rustcorp.com.au> + Copyright (C) 2005 XenSource Ltd + + 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. + +*/ + +#define pr_fmt(fmt) "xen-blkback: " fmt + +#include <stdarg.h> +#include <linux/module.h> +#include <linux/kthread.h> +#include <xen/events.h> +#include <xen/grant_table.h> +#include "common.h" + +/* Enlarge the array size in order to fully show blkback name. */ +#define BLKBACK_NAME_LEN (20) + +struct backend_info { + struct xenbus_device *dev; + struct xen_blkif *blkif; + struct xenbus_watch backend_watch; + unsigned major; + unsigned minor; + char *mode; +}; + +static struct kmem_cache *xen_blkif_cachep; +static void connect(struct backend_info *); +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; + struct xenbus_device *dev = blkif->be->dev; + + devpath = xenbus_read(XBT_NIL, dev->nodename, "dev", NULL); + if (IS_ERR(devpath)) + return PTR_ERR(devpath); + + devname = strstr(devpath, "/dev/"); + if (devname != NULL) + devname += strlen("/dev/"); + else + devname = devpath; + + snprintf(buf, BLKBACK_NAME_LEN, "blkback.%d.%s", blkif->domid, devname); + kfree(devpath); + + return 0; +} + +static void xen_update_blkif_status(struct xen_blkif *blkif) +{ + int err; + char name[BLKBACK_NAME_LEN]; + + /* Not ready to connect? */ + if (!blkif->irq || !blkif->vbd.bdev) + return; + + /* Already connected? */ + if (blkif->be->dev->state == XenbusStateConnected) + return; + + /* Attempt to connect: exit if we fail to. */ + connect(blkif->be); + if (blkif->be->dev->state != XenbusStateConnected) + return; + + err = blkback_name(blkif, name); + if (err) { + xenbus_dev_error(blkif->be->dev, err, "get blkback dev name"); + return; + } + + err = filemap_write_and_wait(blkif->vbd.bdev->bd_inode->i_mapping); + if (err) { + xenbus_dev_error(blkif->be->dev, err, "block flush"); + return; + } + invalidate_inode_pages2(blkif->vbd.bdev->bd_inode->i_mapping); + + 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; + } +} + +static struct xen_blkif *xen_blkif_alloc(domid_t domid) +{ + struct xen_blkif *blkif; + struct pending_req *req, *n; + int i, j; + + 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); + + blkif->domid = domid; + spin_lock_init(&blkif->blk_ring_lock); + atomic_set(&blkif->refcnt, 1); + init_waitqueue_head(&blkif->wq); + init_completion(&blkif->drain_complete); + atomic_set(&blkif->drain, 0); + blkif->st_print = jiffies; + 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); + + for (i = 0; i < XEN_BLKIF_REQS; i++) { + req = kzalloc(sizeof(*req), GFP_KERNEL); + if (!req) + goto fail; + list_add_tail(&req->free_list, + &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; + } + } + spin_lock_init(&blkif->pending_free_lock); + init_waitqueue_head(&blkif->pending_free_wq); + init_waitqueue_head(&blkif->shutdown_wq); + + return blkif; + +fail: + 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++) { + 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); + } + + kmem_cache_free(xen_blkif_cachep, blkif); + + return ERR_PTR(-ENOMEM); +} + +static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t gref, + unsigned int evtchn) +{ + int err; + + /* Already connected through? */ + if (blkif->irq) + return 0; + + err = xenbus_map_ring_valloc(blkif->be->dev, &gref, 1, + &blkif->blk_ring); + if (err < 0) + return err; + + switch (blkif->blk_protocol) { + case BLKIF_PROTOCOL_NATIVE: + { + struct blkif_sring *sring; + sring = (struct blkif_sring *)blkif->blk_ring; + BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE); + 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); + 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); + break; + } + default: + BUG(); + } + + err = bind_interdomain_evtchn_to_irqhandler(blkif->domid, evtchn, + xen_blkif_be_int, 0, + "blkif-backend", blkif); + if (err < 0) { + xenbus_unmap_ring_vfree(blkif->be->dev, blkif->blk_ring); + blkif->blk_rings.common.sring = NULL; + return err; + } + blkif->irq = err; + + return 0; +} + +static int xen_blkif_disconnect(struct xen_blkif *blkif) +{ + if (blkif->xenblkd) { + kthread_stop(blkif->xenblkd); + wake_up(&blkif->shutdown_wq); + blkif->xenblkd = NULL; + } + + /* 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); + blkif->irq = 0; + } + + if (blkif->blk_rings.common.sring) { + 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); + + return 0; +} + +static void xen_blkif_free(struct xen_blkif *blkif) +{ + struct pending_req *req, *n; + int i = 0, j; + + 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)); + + /* 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); + + kmem_cache_free(xen_blkif_cachep, blkif); +} + +int __init xen_blkif_interface_init(void) +{ + xen_blkif_cachep = kmem_cache_create("blkif_cache", + sizeof(struct xen_blkif), + 0, 0, NULL); + if (!xen_blkif_cachep) + return -ENOMEM; + + return 0; +} + +/* + * sysfs interface for VBD I/O requests + */ + +#define VBD_SHOW(name, format, args...) \ + static ssize_t show_##name(struct device *_dev, \ + struct device_attribute *attr, \ + char *buf) \ + { \ + struct xenbus_device *dev = to_xenbus_device(_dev); \ + struct backend_info *be = dev_get_drvdata(&dev->dev); \ + \ + return sprintf(buf, format, ##args); \ + } \ + static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL) + +VBD_SHOW(oo_req, "%llu\n", be->blkif->st_oo_req); +VBD_SHOW(rd_req, "%llu\n", be->blkif->st_rd_req); +VBD_SHOW(wr_req, "%llu\n", be->blkif->st_wr_req); +VBD_SHOW(f_req, "%llu\n", be->blkif->st_f_req); +VBD_SHOW(ds_req, "%llu\n", be->blkif->st_ds_req); +VBD_SHOW(rd_sect, "%llu\n", be->blkif->st_rd_sect); +VBD_SHOW(wr_sect, "%llu\n", be->blkif->st_wr_sect); + +static struct attribute *xen_vbdstat_attrs[] = { + &dev_attr_oo_req.attr, + &dev_attr_rd_req.attr, + &dev_attr_wr_req.attr, + &dev_attr_f_req.attr, + &dev_attr_ds_req.attr, + &dev_attr_rd_sect.attr, + &dev_attr_wr_sect.attr, + NULL +}; + +static struct attribute_group xen_vbdstat_group = { + .name = "statistics", + .attrs = xen_vbdstat_attrs, +}; + +VBD_SHOW(physical_device, "%x:%x\n", be->major, be->minor); +VBD_SHOW(mode, "%s\n", be->mode); + +static int xenvbd_sysfs_addif(struct xenbus_device *dev) +{ + int error; + + error = device_create_file(&dev->dev, &dev_attr_physical_device); + if (error) + goto fail1; + + error = device_create_file(&dev->dev, &dev_attr_mode); + if (error) + goto fail2; + + error = sysfs_create_group(&dev->dev.kobj, &xen_vbdstat_group); + if (error) + goto fail3; + + return 0; + +fail3: sysfs_remove_group(&dev->dev.kobj, &xen_vbdstat_group); +fail2: device_remove_file(&dev->dev, &dev_attr_mode); +fail1: device_remove_file(&dev->dev, &dev_attr_physical_device); + return error; +} + +static void xenvbd_sysfs_delif(struct xenbus_device *dev) +{ + sysfs_remove_group(&dev->dev.kobj, &xen_vbdstat_group); + device_remove_file(&dev->dev, &dev_attr_mode); + device_remove_file(&dev->dev, &dev_attr_physical_device); +} + + +static void xen_vbd_free(struct xen_vbd *vbd) +{ + if (vbd->bdev) + blkdev_put(vbd->bdev, vbd->readonly ? FMODE_READ : FMODE_WRITE); + vbd->bdev = NULL; +} + +static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, + unsigned major, unsigned minor, int readonly, + int cdrom) +{ + struct xen_vbd *vbd; + struct block_device *bdev; + struct request_queue *q; + + vbd = &blkif->vbd; + vbd->handle = handle; + vbd->readonly = readonly; + vbd->type = 0; + + vbd->pdevice = MKDEV(major, minor); + + bdev = blkdev_get_by_dev(vbd->pdevice, vbd->readonly ? + FMODE_READ : FMODE_WRITE, NULL); + + if (IS_ERR(bdev)) { + 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) { + pr_warn("xen_vbd_create: device %08x doesn't exist\n", + vbd->pdevice); + xen_vbd_free(vbd); + return -ENOENT; + } + vbd->size = vbd_sz(vbd); + + if (vbd->bdev->bd_disk->flags & GENHD_FL_CD || cdrom) + vbd->type |= VDISK_CDROM; + if (vbd->bdev->bd_disk->flags & GENHD_FL_REMOVABLE) + vbd->type |= VDISK_REMOVABLE; + + q = bdev_get_queue(bdev); + if (q && q->flush_flags) + vbd->flush_support = true; + + if (q && blk_queue_secdiscard(q)) + vbd->discard_secure = true; + + pr_debug("Successful creation of handle=%04x (dom=%u)\n", + handle, blkif->domid); + return 0; +} +static int xen_blkbk_remove(struct xenbus_device *dev) +{ + struct backend_info *be = dev_get_drvdata(&dev->dev); + + pr_debug("%s %p %d\n", __func__, dev, dev->otherend_id); + + if (be->major || be->minor) + xenvbd_sysfs_delif(dev); + + if (be->backend_watch.node) { + unregister_xenbus_watch(&be->backend_watch); + kfree(be->backend_watch.node); + be->backend_watch.node = NULL; + } + + dev_set_drvdata(&dev->dev, NULL); + + if (be->blkif) { + xen_blkif_disconnect(be->blkif); + xen_blkif_put(be->blkif); + } + + kfree(be->mode); + kfree(be); + return 0; +} + +int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt, + struct backend_info *be, int state) +{ + struct xenbus_device *dev = be->dev; + int err; + + err = xenbus_printf(xbt, dev->nodename, "feature-flush-cache", + "%d", state); + if (err) + dev_warn(&dev->dev, "writing feature-flush-cache (%d)", err); + + return err; +} + +static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info *be) +{ + struct xenbus_device *dev = be->dev; + struct xen_blkif *blkif = be->blkif; + int err; + 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", + q->limits.discard_granularity); + if (err) { + dev_warn(&dev->dev, "writing discard-granularity (%d)", err); + return; + } + err = xenbus_printf(xbt, dev->nodename, + "discard-alignment", "%u", + q->limits.discard_alignment); + if (err) { + dev_warn(&dev->dev, "writing discard-alignment (%d)", err); + return; + } + state = 1; + /* Optional. */ + err = xenbus_printf(xbt, dev->nodename, + "discard-secure", "%d", + blkif->vbd.discard_secure); + if (err) { + dev_warn(&dev->dev, "writing discard-secure (%d)", err); + return; + } + } + err = xenbus_printf(xbt, dev->nodename, "feature-discard", + "%d", state); + if (err) + dev_warn(&dev->dev, "writing feature-discard (%d)", err); +} +int xen_blkbk_barrier(struct xenbus_transaction xbt, + struct backend_info *be, int state) +{ + struct xenbus_device *dev = be->dev; + int err; + + err = xenbus_printf(xbt, dev->nodename, "feature-barrier", + "%d", state); + if (err) + dev_warn(&dev->dev, "writing feature-barrier (%d)", err); + + return err; +} + +/* + * Entry point to this code when a new device is created. Allocate the basic + * structures, and watch the store waiting for the hotplug scripts to tell us + * the device's physical major and minor numbers. Switch to InitWait. + */ +static int xen_blkbk_probe(struct xenbus_device *dev, + const struct xenbus_device_id *id) +{ + 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"); + return -ENOMEM; + } + be->dev = dev; + dev_set_drvdata(&dev->dev, be); + + be->blkif = xen_blkif_alloc(dev->otherend_id); + if (IS_ERR(be->blkif)) { + err = PTR_ERR(be->blkif); + be->blkif = NULL; + xenbus_dev_fatal(dev, err, "creating block interface"); + goto fail; + } + + /* setup back pointer */ + be->blkif->be = be; + + err = xenbus_watch_pathfmt(dev, &be->backend_watch, backend_changed, + "%s/%s", dev->nodename, "physical-device"); + if (err) + goto fail; + + err = xenbus_switch_state(dev, XenbusStateInitWait); + if (err) + goto fail; + + return 0; + +fail: + pr_warn("%s failed\n", __func__); + xen_blkbk_remove(dev); + return err; +} + + +/* + * Callback received when the hotplug scripts have placed the physical-device + * node. Read it and the mode node, and create a vbd. If the frontend is + * ready, connect. + */ +static void backend_changed(struct xenbus_watch *watch, + const char **vec, unsigned int len) +{ + int err; + unsigned major; + unsigned minor; + struct backend_info *be + = container_of(watch, struct backend_info, backend_watch); + struct xenbus_device *dev = be->dev; + int cdrom = 0; + unsigned long handle; + char *device_type; + + pr_debug("%s %p %d\n", __func__, dev, dev->otherend_id); + + err = xenbus_scanf(XBT_NIL, dev->nodename, "physical-device", "%x:%x", + &major, &minor); + if (XENBUS_EXIST_ERR(err)) { + /* + * Since this watch will fire once immediately after it is + * registered, we expect this. Ignore it, and wait for the + * hotplug scripts. + */ + return; + } + if (err != 2) { + xenbus_dev_fatal(dev, err, "reading physical-device"); + return; + } + + if (be->major | be->minor) { + if (be->major != major || be->minor != minor) + pr_warn("changing physical device (from %x:%x to %x:%x) not supported.\n", + be->major, be->minor, major, minor); + return; + } + + be->mode = xenbus_read(XBT_NIL, dev->nodename, "mode", NULL); + if (IS_ERR(be->mode)) { + err = PTR_ERR(be->mode); + be->mode = NULL; + xenbus_dev_fatal(dev, err, "reading mode"); + return; + } + + device_type = xenbus_read(XBT_NIL, dev->otherend, "device-type", NULL); + if (!IS_ERR(device_type)) { + cdrom = strcmp(device_type, "cdrom") == 0; + kfree(device_type); + } + + /* Front end dir is a number, which is used as the handle. */ + err = kstrtoul(strrchr(dev->otherend, '/') + 1, 0, &handle); + if (err) + return; + + be->major = major; + be->minor = minor; + + err = xen_vbd_create(be->blkif, handle, major, minor, + !strchr(be->mode, 'w'), cdrom); + + if (err) + xenbus_dev_fatal(dev, err, "creating vbd structure"); + else { + err = xenvbd_sysfs_addif(dev); + if (err) { + xen_vbd_free(&be->blkif->vbd); + xenbus_dev_fatal(dev, err, "creating sysfs entries"); + } + } + + if (err) { + kfree(be->mode); + be->mode = NULL; + be->major = 0; + be->minor = 0; + } else { + /* We're potentially connected now */ + xen_update_blkif_status(be->blkif); + } +} + + +/* + * Callback received when the frontend's state changes. + */ +static void frontend_changed(struct xenbus_device *dev, + enum xenbus_state frontend_state) +{ + struct backend_info *be = dev_get_drvdata(&dev->dev); + int err; + + pr_debug("%s %p %s\n", __func__, dev, xenbus_strstate(frontend_state)); + + switch (frontend_state) { + case XenbusStateInitialising: + if (dev->state == XenbusStateClosed) { + pr_info("%s: prepare for reconnect\n", dev->nodename); + xenbus_switch_state(dev, XenbusStateInitWait); + } + break; + + case XenbusStateInitialised: + case XenbusStateConnected: + /* + * Ensure we connect even when two watches fire in + * close succession and we miss the intermediate value + * of frontend_state. + */ + if (dev->state == XenbusStateConnected) + break; + + /* + * Enforce precondition before potential leak point. + * xen_blkif_disconnect() is idempotent. + */ + err = xen_blkif_disconnect(be->blkif); + if (err) { + xenbus_dev_fatal(dev, err, "pending I/O"); + break; + } + + err = connect_ring(be); + if (err) + break; + xen_update_blkif_status(be->blkif); + break; + + case XenbusStateClosing: + xenbus_switch_state(dev, XenbusStateClosing); + break; + + case XenbusStateClosed: + xen_blkif_disconnect(be->blkif); + xenbus_switch_state(dev, XenbusStateClosed); + if (xenbus_dev_is_online(dev)) + break; + /* fall through if not online */ + case XenbusStateUnknown: + /* implies xen_blkif_disconnect() via xen_blkbk_remove() */ + device_unregister(&dev->dev); + break; + + default: + xenbus_dev_fatal(dev, -EINVAL, "saw state %d at frontend", + frontend_state); + break; + } +} + + +/* ** Connection ** */ + + +/* + * Write the physical details regarding the block device to the store, and + * switch to Connected state. + */ +static void connect(struct backend_info *be) +{ + struct xenbus_transaction xbt; + int err; + struct xenbus_device *dev = be->dev; + + pr_debug("%s %s\n", __func__, dev->otherend); + + /* Supply the information about the device the frontend needs */ +again: + err = xenbus_transaction_start(&xbt); + if (err) { + xenbus_dev_fatal(dev, err, "starting transaction"); + return; + } + + /* If we can't advertise it is OK. */ + xen_blkbk_flush_diskcache(xbt, be, be->blkif->vbd.flush_support); + + xen_blkbk_discard(xbt, be); + + xen_blkbk_barrier(xbt, be, be->blkif->vbd.flush_support); + + err = xenbus_printf(xbt, dev->nodename, "feature-persistent", "%u", 1); + if (err) { + xenbus_dev_fatal(dev, err, "writing %s/feature-persistent", + 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)); + if (err) { + xenbus_dev_fatal(dev, err, "writing %s/sectors", + dev->nodename); + goto abort; + } + + /* FIXME: use a typename instead */ + err = xenbus_printf(xbt, dev->nodename, "info", "%u", + be->blkif->vbd.type | + (be->blkif->vbd.readonly ? VDISK_READONLY : 0)); + if (err) { + xenbus_dev_fatal(dev, err, "writing %s/info", + dev->nodename); + goto abort; + } + err = xenbus_printf(xbt, dev->nodename, "sector-size", "%lu", + (unsigned long) + bdev_logical_block_size(be->blkif->vbd.bdev)); + if (err) { + xenbus_dev_fatal(dev, err, "writing %s/sector-size", + 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) + goto again; + if (err) + xenbus_dev_fatal(dev, err, "ending transaction"); + + err = xenbus_switch_state(dev, XenbusStateConnected); + if (err) + xenbus_dev_fatal(dev, err, "%s: switching to Connected state", + dev->nodename); + + return; + abort: + xenbus_transaction_end(xbt, 1); +} + + +static int connect_ring(struct backend_info *be) +{ + struct xenbus_device *dev = be->dev; + unsigned long ring_ref; + unsigned int evtchn; + unsigned int pers_grants; + char protocol[64] = ""; + int err; + + 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", + dev->otherend); + return err; + } + + be->blkif->blk_protocol = BLKIF_PROTOCOL_DEFAULT; + err = xenbus_gather(XBT_NIL, dev->otherend, "protocol", + "%63s", protocol, NULL); + if (err) + 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)) + be->blkif->blk_protocol = BLKIF_PROTOCOL_X86_32; + else if (0 == strcmp(protocol, XEN_IO_PROTO_ABI_X86_64)) + be->blkif->blk_protocol = BLKIF_PROTOCOL_X86_64; + else { + xenbus_dev_fatal(dev, err, "unknown fe protocol %s", protocol); + return -1; + } + err = xenbus_gather(XBT_NIL, dev->otherend, + "feature-persistent", "%u", + &pers_grants, NULL); + if (err) + pers_grants = 0; + + be->blkif->vbd.feature_gnt_persistent = pers_grants; + be->blkif->vbd.overflow_max_grants = 0; + + pr_info("ring-ref %ld, event-channel %d, protocol %d (%s) %s\n", + ring_ref, evtchn, be->blkif->blk_protocol, protocol, + pers_grants ? "persistent grants" : ""); + + /* Map the shared frame, irq etc. */ + err = xen_blkif_map(be->blkif, ring_ref, evtchn); + if (err) { + xenbus_dev_fatal(dev, err, "mapping ring-ref %lu port %u", + ring_ref, evtchn); + return err; + } + + return 0; +} + +static const struct xenbus_device_id xen_blkbk_ids[] = { + { "vbd" }, + { "" } +}; + +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) +{ + return xenbus_register_backend(&xen_blkbk_driver); +} |