--- zzzz-none-000/linux-3.10.107/drivers/block/xen-blkback/blkback.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/drivers/block/xen-blkback/blkback.c 2021-02-04 17:41:59.000000000 +0000 @@ -34,6 +34,8 @@ * IN THE SOFTWARE. */ +#define pr_fmt(fmt) "xen-blkback: " fmt + #include #include #include @@ -47,113 +49,129 @@ #include #include #include +#include #include "common.h" /* - * These are rather arbitrary. They are fairly large because adjacent requests - * pulled from a communication ring are quite likely to end up being part of - * the same scatter/gather request at the disc. - * - * ** TRY INCREASING 'xen_blkif_reqs' IF WRITE SPEEDS SEEM TOO LOW ** + * 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. * - * This will increase the chances of being able to write whole tracks. - * 64 should be enough to keep us competitive with Linux. + * 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_reqs = 64; -module_param_named(reqs, xen_blkif_reqs, int, 0); -MODULE_PARM_DESC(reqs, "Number of blkback requests to allocate"); -/* Run-time switchable: /sys/module/blkback/parameters/ */ -static unsigned int log_stats; -module_param(log_stats, int, 0644); +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"); /* - * 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. + * 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. */ -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; - DECLARE_BITMAP(unmap_seg, BLKIF_MAX_SEGMENTS_PER_REQUEST); -}; - -#define BLKBACK_INVALID_HANDLE (~0) -struct xen_blkbk { - struct pending_req *pending_reqs; - /* 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; - /* The list of all pages that are available. */ - struct page **pending_pages; - /* And the grant handles that are available. */ - grant_handle_t *pending_grant_handles; -}; +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"); -static struct xen_blkbk *blkbk; +/* + * Maximum order of pages to be used for the shared ring between front and + * backend, 4KB page granularity is used. + */ +unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER; +module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO); +MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring"); +/* + * 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 /* - * Maximum number of grant pages that can be mapped in blkback. - * BLKIF_MAX_SEGMENTS_PER_REQUEST * RING_SIZE is the maximum number of - * pages that blkback will persistently map. - * Currently, this is: - * RING_SIZE = 32 (for all known ring types) - * BLKIF_MAX_SEGMENTS_PER_REQUEST = 11 - * sizeof(struct persistent_gnt) = 48 - * So the maximum memory used to store the grants is: - * 32 * 11 * 48 = 16896 bytes + * 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. */ -static inline unsigned int max_mapped_grant_pages(enum blkif_protocol protocol) +#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) { - switch (protocol) { - case BLKIF_PROTOCOL_NATIVE: - return __CONST_RING_SIZE(blkif, PAGE_SIZE) * - BLKIF_MAX_SEGMENTS_PER_REQUEST; - case BLKIF_PROTOCOL_X86_32: - return __CONST_RING_SIZE(blkif_x86_32, PAGE_SIZE) * - BLKIF_MAX_SEGMENTS_PER_REQUEST; - case BLKIF_PROTOCOL_X86_64: - return __CONST_RING_SIZE(blkif_x86_64, PAGE_SIZE) * - BLKIF_MAX_SEGMENTS_PER_REQUEST; - default: - BUG(); - } + 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; } - -/* - * Little helpful macro to figure out the index and virtual address of the - * pending_pages[..]. For each 'pending_req' we have have up to - * BLKIF_MAX_SEGMENTS_PER_REQUEST (11) pages. The seg would be from 0 through - * 10 and would index in the pending_pages[..]. - */ -static inline int vaddr_pagenr(struct pending_req *req, int seg) +static inline void put_free_pages(struct xen_blkif *blkif, struct page **page, + int num) { - return (req - blkbk->pending_reqs) * - BLKIF_MAX_SEGMENTS_PER_REQUEST + seg; -} + unsigned long flags; + int i; -#define pending_page(req, seg) pending_pages[vaddr_pagenr(req, seg)] + 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 unsigned long vaddr(struct pending_req *req, int seg) +static inline void shrink_free_pagepool(struct xen_blkif *blkif, int num) { - unsigned long pfn = page_to_pfn(blkbk->pending_page(req, seg)); - return (unsigned long)pfn_to_kaddr(pfn); -} + /* 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; -#define pending_handle(_req, _seg) \ - (blkbk->pending_grant_handles[vaddr_pagenr(_req, _seg)]) + 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, @@ -170,13 +188,29 @@ (n) = (&(pos)->node != NULL) ? rb_next(&(pos)->node) : NULL) -static void add_persistent_gnt(struct rb_root *root, +/* + * 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 = &(root->rb_node), *parent = NULL; + 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); @@ -186,22 +220,28 @@ else if (persistent_gnt->gnt > this->gnt) new = &((*new)->rb_right); else { - pr_alert(DRV_PFX " trying to add a gref that's already in the tree\n"); - BUG(); + 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), root); + 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 rb_root *root, +static struct persistent_gnt *get_persistent_gnt(struct xen_blkif *blkif, grant_ref_t gref) { struct persistent_gnt *data; - struct rb_node *node = root->rb_node; + struct rb_node *node = NULL; + node = blkif->persistent_gnts.rb_node; while (node) { data = container_of(node, struct persistent_gnt, node); @@ -209,20 +249,42 @@ node = node->rb_left; else if (gref > data->gnt) node = node->rb_right; - else + 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 free_persistent_gnts(struct rb_root *root, unsigned int num) +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 ret = 0; 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 == @@ -237,10 +299,11 @@ if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST || !rb_next(&persistent_gnt->node)) { - ret = gnttab_unmap_refs(unmap, NULL, pages, - segs_to_unmap); - BUG_ON(ret); - free_xenballooned_pages(segs_to_unmap, pages); + + 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; } @@ -251,21 +314,151 @@ 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_busy(&blkif->persistent_purge_work)) { + pr_alert_ratelimited("Scheduled work from previous purge is still busy, 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(void) +static struct pending_req *alloc_req(struct xen_blkif *blkif) { struct pending_req *req = NULL; unsigned long flags; - spin_lock_irqsave(&blkbk->pending_free_lock, flags); - if (!list_empty(&blkbk->pending_free)) { - req = list_entry(blkbk->pending_free.next, struct pending_req, + 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(&blkbk->pending_free_lock, flags); + spin_unlock_irqrestore(&blkif->pending_free_lock, flags); return req; } @@ -273,17 +466,17 @@ * 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 pending_req *req) +static void free_req(struct xen_blkif *blkif, struct pending_req *req) { unsigned long flags; int was_empty; - spin_lock_irqsave(&blkbk->pending_free_lock, flags); - was_empty = list_empty(&blkbk->pending_free); - list_add(&req->free_list, &blkbk->pending_free); - spin_unlock_irqrestore(&blkbk->pending_free_lock, flags); + 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(&blkbk->pending_free_wq); + wake_up(&blkif->pending_free_wq); } /* @@ -323,20 +516,20 @@ struct xenbus_device *dev = xen_blkbk_xenbus(blkif->be); unsigned long long new_size = vbd_sz(vbd); - pr_info(DRV_PFX "VBD Resize: Domid: %d, Device: (%d, %d)\n", + pr_info("VBD Resize: Domid: %d, Device: (%d, %d)\n", blkif->domid, MAJOR(vbd->pdevice), MINOR(vbd->pdevice)); - pr_info(DRV_PFX "VBD Resize: new size %llu\n", new_size); + pr_info("VBD Resize: new size %llu\n", new_size); vbd->size = new_size; again: err = xenbus_transaction_start(&xbt); if (err) { - pr_warn(DRV_PFX "Error starting transaction"); + 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(DRV_PFX "Error writing new size"); + pr_warn("Error writing new size\n"); goto abort; } /* @@ -346,7 +539,7 @@ */ err = xenbus_printf(xbt, dev->nodename, "state", "%d", dev->state); if (err) { - pr_warn(DRV_PFX "Error writing the state"); + pr_warn("Error writing the state\n"); goto abort; } @@ -354,7 +547,7 @@ if (err == -EAGAIN) goto again; if (err) - pr_warn(DRV_PFX "Error ending transaction"); + pr_warn("Error ending transaction\n"); return; abort: xenbus_transaction_end(xbt, 1); @@ -381,11 +574,13 @@ static void print_stats(struct xen_blkif *blkif) { - pr_info("xen-blkback (%s): oo %3llu | rd %4llu | wr %4llu | f %4llu" - " | ds %4llu\n", + 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->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; @@ -397,6 +592,8 @@ { struct xen_blkif *blkif = arg; struct xen_vbd *vbd = &blkif->vbd; + unsigned long timeout; + int ret; xen_blkif_get(blkif); @@ -406,31 +603,48 @@ if (unlikely(vbd->size != vbd_sz(vbd))) xen_vbd_resize(blkif); - wait_event_interruptible( + timeout = msecs_to_jiffies(LRU_INTERVAL); + + timeout = wait_event_interruptible_timeout( blkif->wq, - blkif->waiting_reqs || kthread_should_stop()); - wait_event_interruptible( - blkbk->pending_free_wq, - !list_empty(&blkbk->pending_free) || - kthread_should_stop()); + 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 */ - if (do_block_io_op(blkif)) + 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); } - /* Free all persistent grant pages */ - if (!RB_EMPTY_ROOT(&blkif->persistent_gnts)) - free_persistent_gnts(&blkif->persistent_gnts, - blkif->persistent_gnt_c); - - BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts)); - blkif->persistent_gnt_c = 0; + /* Drain pending purge work */ + flush_work(&blkif->persistent_purge_work); if (log_stats) print_stats(blkif); @@ -441,148 +655,185 @@ return 0; } -struct seg_buf { - unsigned int offset; - unsigned int nsec; -}; /* - * Unmap the grant references, and also remove the M2P over-rides - * used in the 'pending_req'. + * Remove persistent grants and empty the pool of free pages */ -static void xen_blkbk_unmap(struct pending_req *req) +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) { - struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST]; - struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; unsigned int i, invcount = 0; - grant_handle_t handle; - int ret; - for (i = 0; i < req->nr_pages; i++) { - if (!test_bit(i, req->unmap_seg)) + for (i = 0; i < num; i++) { + if (pages[i]->persistent_gnt != NULL) { + put_persistent_gnt(blkif, pages[i]->persistent_gnt); continue; - handle = pending_handle(req, i); - if (handle == BLKBACK_INVALID_HANDLE) + } + if (pages[i]->handle == BLKBACK_INVALID_HANDLE) continue; - gnttab_set_unmap_op(&unmap[invcount], vaddr(req, i), - GNTMAP_host_map, handle); - pending_handle(req, i) = BLKBACK_INVALID_HANDLE; - pages[invcount] = virt_to_page(vaddr(req, i)); + 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); +} - ret = gnttab_unmap_refs(unmap, NULL, pages, invcount); - BUG_ON(ret); +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_segs, + 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); } -static int xen_blkbk_map(struct blkif_request *req, - struct pending_req *pending_req, - struct seg_buf seg[], - struct page *pages[]) + +/* + * 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 persistent_gnt *persistent_gnts[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct page *pages_to_gnt[BLKIF_MAX_SEGMENTS_PER_REQUEST]; struct persistent_gnt *persistent_gnt = NULL; - struct xen_blkif *blkif = pending_req->blkif; phys_addr_t addr = 0; - int i, j; - bool new_map; - int nseg = req->u.rw.nr_segments; + 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); - BUG_ON(blkif->persistent_gnt_c > - max_mapped_grant_pages(pending_req->blkif->blk_protocol)); - /* * 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. */ - for (i = 0; i < nseg; i++) { +again: + for (i = map_until; i < num; i++) { uint32_t flags; if (use_persistent_gnts) persistent_gnt = get_persistent_gnt( - &blkif->persistent_gnts, - req->u.rw.seg[i].gref); + blkif, + pages[i]->gref); if (persistent_gnt) { /* * We are using persistent grants and * the grant is already mapped */ - new_map = false; - } else if (use_persistent_gnts && - blkif->persistent_gnt_c < - max_mapped_grant_pages(blkif->blk_protocol)) { - /* - * We are using persistent grants, the grant is - * not mapped but we have room for it - */ - new_map = true; - persistent_gnt = kmalloc( - sizeof(struct persistent_gnt), - GFP_KERNEL); - if (!persistent_gnt) - return -ENOMEM; - if (alloc_xenballooned_pages(1, &persistent_gnt->page, - false)) { - kfree(persistent_gnt); - return -ENOMEM; - } - persistent_gnt->gnt = req->u.rw.seg[i].gref; - persistent_gnt->handle = BLKBACK_INVALID_HANDLE; - - pages_to_gnt[segs_to_map] = - persistent_gnt->page; - addr = (unsigned long) pfn_to_kaddr( - page_to_pfn(persistent_gnt->page)); - - add_persistent_gnt(&blkif->persistent_gnts, - persistent_gnt); - blkif->persistent_gnt_c++; - pr_debug(DRV_PFX " grant %u added to the tree of persistent grants, using %u/%u\n", - persistent_gnt->gnt, blkif->persistent_gnt_c, - max_mapped_grant_pages(blkif->blk_protocol)); + pages[i]->page = persistent_gnt->page; + pages[i]->persistent_gnt = persistent_gnt; } else { - /* - * We are either using persistent grants and - * hit the maximum limit of grants mapped, - * or we are not using persistent grants. - */ - if (use_persistent_gnts && - !blkif->vbd.overflow_max_grants) { - blkif->vbd.overflow_max_grants = 1; - pr_alert(DRV_PFX " domain %u, device %#x is using maximum number of persistent grants\n", - blkif->domid, blkif->vbd.handle); - } - new_map = true; - pages[i] = blkbk->pending_page(pending_req, i); - addr = vaddr(pending_req, i); - pages_to_gnt[segs_to_map] = - blkbk->pending_page(pending_req, i); - } - - if (persistent_gnt) { - pages[i] = persistent_gnt->page; - persistent_gnts[i] = persistent_gnt; - } else { - persistent_gnts[i] = NULL; - } - - if (new_map) { + 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 (!persistent_gnt && - (pending_req->operation != BLKIF_OP_READ)) + if (!use_persistent_gnts && ro) flags |= GNTMAP_readonly; gnttab_set_map_op(&map[segs_to_map++], addr, - flags, req->u.rw.seg[i].gref, + flags, pages[i]->gref, blkif->domid); } + map_until = i + 1; + if (segs_to_map == BLKIF_MAX_SEGMENTS_PER_REQUEST) + break; } if (segs_to_map) { @@ -595,49 +846,139 @@ * so that when we access vaddr(pending_req,i) it has the contents of * the page from the other domain. */ - bitmap_zero(pending_req->unmap_seg, BLKIF_MAX_SEGMENTS_PER_REQUEST); - for (i = 0, j = 0; i < nseg; i++) { - if (!persistent_gnts[i] || - persistent_gnts[i]->handle == BLKBACK_INVALID_HANDLE) { + 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(j >= segs_to_map); - if (unlikely(map[j].status != 0)) { - pr_debug(DRV_PFX "invalid buffer -- could not remap it\n"); - map[j].handle = BLKBACK_INVALID_HANDLE; + 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; - if (persistent_gnts[i]) { - rb_erase(&persistent_gnts[i]->node, - &blkif->persistent_gnts); - blkif->persistent_gnt_c--; - kfree(persistent_gnts[i]); - persistent_gnts[i] = NULL; - } + goto next; } + pages[seg_idx]->handle = map[new_map_idx].handle; + } else { + continue; } - if (persistent_gnts[i]) { - if (persistent_gnts[i]->handle == - BLKBACK_INVALID_HANDLE) { + 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 this is a new persistent grant - * save the handler + * If we don't have enough memory to + * allocate the persistent_gnt struct + * map this grant non-persistenly */ - persistent_gnts[i]->handle = map[j++].handle; + 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; } - pending_handle(pending_req, i) = - persistent_gnts[i]->handle; + 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; - if (ret) - continue; - } else { - pending_handle(pending_req, i) = map[j++].handle; - bitmap_set(pending_req->unmap_seg, i, 1); + 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_segs, + (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_segs; + indirect_grefs = INDIRECT_PAGES(nseg); + BUG_ON(indirect_grefs > BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST); - if (ret) - continue; + 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++) { + uint8_t first_sect, last_sect; + + 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); } - seg[i].offset = (req->u.rw.seg[i].first_sect << 9); + i = n % SEGS_PER_INDIRECT_FRAME; + + pending_req->segments[n]->gref = segments[i].gref; + + first_sect = READ_ONCE(segments[i].first_sect); + last_sect = READ_ONCE(segments[i].last_sect); + if (last_sect >= (XEN_PAGE_SIZE >> 9) || last_sect < first_sect) { + rc = -EINVAL; + goto unmap; + } + + seg[n].nsec = last_sect - first_sect + 1; + seg[n].offset = first_sect << 9; + preq->nr_sects += seg[n].nsec; } - return ret; + +unmap: + if (segments) + kunmap_atomic(segments); + xen_blkbk_unmap(blkif, pages, indirect_grefs); + return rc; } static int dispatch_discard_io(struct xen_blkif *blkif, @@ -656,7 +997,7 @@ err = xen_vbd_translate(&preq, blkif, WRITE); if (err) { - pr_warn(DRV_PFX "access denied: DISCARD [%llu->%llu] on dev=%04x\n", + 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; @@ -672,7 +1013,7 @@ GFP_KERNEL, secure); fail_response: if (err == -EOPNOTSUPP) { - pr_debug(DRV_PFX "discard op failed, not supported\n"); + pr_debug("discard op failed, not supported\n"); status = BLKIF_RSP_EOPNOTSUPP; } else if (err) status = BLKIF_RSP_ERROR; @@ -686,7 +1027,7 @@ struct blkif_request *req, struct pending_req *pending_req) { - free_req(pending_req); + free_req(blkif, pending_req); make_response(blkif, req->u.other.id, req->operation, BLKIF_RSP_EOPNOTSUPP); return -EIO; @@ -696,9 +1037,7 @@ { atomic_set(&blkif->drain, 1); do { - /* The initial value is one, and one refcnt taken at the - * start of the xen_blkif_schedule thread. */ - if (atomic_read(&blkif->refcnt) <= 2) + if (atomic_read(&blkif->inflight) == 0) break; wait_for_completion_interruptible_timeout( &blkif->drain_complete, HZ); @@ -718,16 +1057,16 @@ /* An error fails the entire request. */ if ((pending_req->operation == BLKIF_OP_FLUSH_DISKCACHE) && (error == -EOPNOTSUPP)) { - pr_debug(DRV_PFX "flush diskcache op failed, not supported\n"); + 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(DRV_PFX "write barrier op failed, not supported\n"); + 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(DRV_PFX "Buffer not up-to-date at end of operation," + pr_debug("Buffer not up-to-date at end of operation," " error=%d\n", error); pending_req->status = BLKIF_RSP_ERROR; } @@ -737,25 +1076,16 @@ * 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(pending_req); - make_response(pending_req->blkif, pending_req->id, - pending_req->operation, pending_req->status); - xen_blkif_put(pending_req->blkif); - if (atomic_read(&pending_req->blkif->refcnt) <= 2) { - if (atomic_read(&pending_req->blkif->drain)) - complete(&pending_req->blkif->drain_complete); - } - free_req(pending_req); - } + 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) +static void end_block_io_op(struct bio *bio) { - __end_block_io_op(bio->bi_private, error); + __end_block_io_op(bio->bi_private, bio->bi_error); bio_put(bio); } @@ -779,6 +1109,12 @@ 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)) @@ -789,7 +1125,7 @@ break; } - pending_req = alloc_req(); + pending_req = alloc_req(blkif); if (NULL == pending_req) { blkif->st_oo_req++; more_to_do = 1; @@ -819,11 +1155,12 @@ 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(pending_req); + free_req(blkif, pending_req); if (dispatch_discard_io(blkif, &req)) goto done; break; @@ -865,17 +1202,28 @@ struct pending_req *pending_req) { struct phys_req preq; - struct seg_buf seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct seg_buf *seg = pending_req->seg; unsigned int nseg; struct bio *bio = NULL; - struct bio *biolist[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct bio **biolist = pending_req->biolist; int i, nbio = 0; int operation; struct blk_plug plug; bool drain = false; - struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST]; + struct grant_page **pages = pending_req->segments; + unsigned short req_operation; - switch (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; @@ -897,37 +1245,50 @@ } /* Check that the number of segments is sane. */ - nseg = req->u.rw.nr_segments; + nseg = req->operation == BLKIF_OP_INDIRECT ? + req->u.indirect.nr_segments : req->u.rw.nr_segments; if (unlikely(nseg == 0 && operation != WRITE_FLUSH) || - unlikely(nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST)) { - pr_debug(DRV_PFX "Bad number of segments in request (%d)\n", - nseg); + 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.sector_number = req->u.rw.sector_number; preq.nr_sects = 0; pending_req->blkif = blkif; pending_req->id = req->u.rw.id; - pending_req->operation = req->operation; + pending_req->operation = req_operation; pending_req->status = BLKIF_RSP_OKAY; - pending_req->nr_pages = nseg; + pending_req->nr_segs = nseg; - for (i = 0; i < nseg; i++) { - seg[i].nsec = req->u.rw.seg[i].last_sect - - req->u.rw.seg[i].first_sect + 1; - 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)) + 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 >= (XEN_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; - preq.nr_sects += seg[i].nsec; - } if (xen_vbd_translate(&preq, blkif, operation) != 0) { - pr_debug(DRV_PFX "access denied: %s of [%llu,%llu] on dev=%04x\n", + 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, @@ -942,7 +1303,7 @@ 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(DRV_PFX "Misaligned I/O request from domain %d", + pr_debug("Misaligned I/O request from domain %d\n", blkif->domid); goto fail_response; } @@ -960,7 +1321,7 @@ * the hypercall to unmap the grants - that is all done in * xen_blkbk_unmap. */ - if (xen_blkbk_map(req, pending_req, seg, pages)) + if (xen_blkbk_map_seg(pending_req)) goto fail_flush; /* @@ -968,15 +1329,17 @@ * 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], + pages[i]->page, seg[i].nsec << 9, seg[i].offset) == 0)) { - bio = bio_alloc(GFP_KERNEL, nseg-i); + 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; @@ -984,7 +1347,7 @@ bio->bi_bdev = preq.bdev; bio->bi_private = pending_req; bio->bi_end_io = end_block_io_op; - bio->bi_sector = preq.sector_number; + bio->bi_iter.bi_sector = preq.sector_number; } preq.sector_number += seg[i].nsec; @@ -1021,11 +1384,12 @@ return 0; fail_flush: - xen_blkbk_unmap(pending_req); + xen_blkbk_unmap(blkif, pending_req->segments, + pending_req->nr_segs); fail_response: /* Haven't submitted any bio's yet. */ - make_response(blkif, req->u.rw.id, req->operation, BLKIF_RSP_ERROR); - free_req(pending_req); + 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; @@ -1082,73 +1446,26 @@ static int __init xen_blkif_init(void) { - int i, mmap_pages; int rc = 0; if (!xen_domain()) return -ENODEV; - blkbk = kzalloc(sizeof(struct xen_blkbk), GFP_KERNEL); - if (!blkbk) { - pr_alert(DRV_PFX "%s: out of memory!\n", __func__); - return -ENOMEM; - } - - mmap_pages = xen_blkif_reqs * BLKIF_MAX_SEGMENTS_PER_REQUEST; - - blkbk->pending_reqs = kzalloc(sizeof(blkbk->pending_reqs[0]) * - xen_blkif_reqs, GFP_KERNEL); - blkbk->pending_grant_handles = kmalloc(sizeof(blkbk->pending_grant_handles[0]) * - mmap_pages, GFP_KERNEL); - blkbk->pending_pages = kzalloc(sizeof(blkbk->pending_pages[0]) * - mmap_pages, GFP_KERNEL); - - if (!blkbk->pending_reqs || !blkbk->pending_grant_handles || - !blkbk->pending_pages) { - rc = -ENOMEM; - goto out_of_memory; - } - - for (i = 0; i < mmap_pages; i++) { - blkbk->pending_grant_handles[i] = BLKBACK_INVALID_HANDLE; - blkbk->pending_pages[i] = alloc_page(GFP_KERNEL); - if (blkbk->pending_pages[i] == NULL) { - rc = -ENOMEM; - goto out_of_memory; - } + if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) { + pr_info("Invalid max_ring_order (%d), will use default max: %d.\n", + xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER); + xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER; } + rc = xen_blkif_interface_init(); if (rc) goto failed_init; - INIT_LIST_HEAD(&blkbk->pending_free); - spin_lock_init(&blkbk->pending_free_lock); - init_waitqueue_head(&blkbk->pending_free_wq); - - for (i = 0; i < xen_blkif_reqs; i++) - list_add_tail(&blkbk->pending_reqs[i].free_list, - &blkbk->pending_free); - rc = xen_blkif_xenbus_init(); if (rc) goto failed_init; - return 0; - - out_of_memory: - pr_alert(DRV_PFX "%s: out of memory\n", __func__); failed_init: - kfree(blkbk->pending_reqs); - kfree(blkbk->pending_grant_handles); - if (blkbk->pending_pages) { - for (i = 0; i < mmap_pages; i++) { - if (blkbk->pending_pages[i]) - __free_page(blkbk->pending_pages[i]); - } - kfree(blkbk->pending_pages); - } - kfree(blkbk); - blkbk = NULL; return rc; }