diff options
Diffstat (limited to 'drivers/block/drbd/drbd_main.c')
| -rw-r--r-- | drivers/block/drbd/drbd_main.c | 115 |
1 files changed, 43 insertions, 72 deletions
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 79ab532aabaf..c73376886e7a 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -114,20 +114,10 @@ struct kmem_cache *drbd_al_ext_cache; /* activity log extents */ mempool_t drbd_request_mempool; mempool_t drbd_ee_mempool; mempool_t drbd_md_io_page_pool; +mempool_t drbd_buffer_page_pool; struct bio_set drbd_md_io_bio_set; struct bio_set drbd_io_bio_set; -/* I do not use a standard mempool, because: - 1) I want to hand out the pre-allocated objects first. - 2) I want to be able to interrupt sleeping allocation with a signal. - Note: This is a single linked list, the next pointer is the private - member of struct page. - */ -struct page *drbd_pp_pool; -DEFINE_SPINLOCK(drbd_pp_lock); -int drbd_pp_vacant; -wait_queue_head_t drbd_pp_wait; - DEFINE_RATELIMIT_STATE(drbd_ratelimit_state, 5 * HZ, 5); static const struct block_device_operations drbd_ops = { @@ -471,20 +461,6 @@ void _drbd_thread_stop(struct drbd_thread *thi, int restart, int wait) wait_for_completion(&thi->stop); } -int conn_lowest_minor(struct drbd_connection *connection) -{ - struct drbd_peer_device *peer_device; - int vnr = 0, minor = -1; - - rcu_read_lock(); - peer_device = idr_get_next(&connection->peer_devices, &vnr); - if (peer_device) - minor = device_to_minor(peer_device->device); - rcu_read_unlock(); - - return minor; -} - #ifdef CONFIG_SMP /* * drbd_calc_cpu_mask() - Generate CPU masks, spread over all CPUs @@ -1550,14 +1526,14 @@ static int _drbd_send_page(struct drbd_peer_device *peer_device, struct page *pa * put_page(); and would cause either a VM_BUG directly, or * __page_cache_release a page that would actually still be referenced * by someone, leading to some obscure delayed Oops somewhere else. */ - if (!drbd_disable_sendpage && sendpage_ok(page)) + if (!drbd_disable_sendpage && sendpages_ok(page, len, offset)) msg.msg_flags |= MSG_NOSIGNAL | MSG_SPLICE_PAGES; drbd_update_congested(peer_device->connection); do { int sent; - bvec_set_page(&bvec, page, offset, len); + bvec_set_page(&bvec, page, len, offset); iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, len); sent = sock_sendmsg(socket, &msg); @@ -1625,6 +1601,7 @@ static int _drbd_send_zc_bio(struct drbd_peer_device *peer_device, struct bio *b static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device, struct drbd_peer_request *peer_req) { + bool use_sendpage = !(peer_req->flags & EE_RELEASE_TO_MEMPOOL); struct page *page = peer_req->pages; unsigned len = peer_req->i.size; int err; @@ -1633,8 +1610,13 @@ static int _drbd_send_zc_ee(struct drbd_peer_device *peer_device, page_chain_for_each(page) { unsigned l = min_t(unsigned, len, PAGE_SIZE); - err = _drbd_send_page(peer_device, page, 0, l, - page_chain_next(page) ? MSG_MORE : 0); + if (likely(use_sendpage)) + err = _drbd_send_page(peer_device, page, 0, l, + page_chain_next(page) ? MSG_MORE : 0); + else + err = _drbd_no_send_page(peer_device, page, 0, l, + page_chain_next(page) ? MSG_MORE : 0); + if (err) return err; len -= l; @@ -1976,7 +1958,6 @@ void drbd_init_set_defaults(struct drbd_device *device) INIT_LIST_HEAD(&device->sync_ee); INIT_LIST_HEAD(&device->done_ee); INIT_LIST_HEAD(&device->read_ee); - INIT_LIST_HEAD(&device->net_ee); INIT_LIST_HEAD(&device->resync_reads); INIT_LIST_HEAD(&device->resync_work.list); INIT_LIST_HEAD(&device->unplug_work.list); @@ -2057,7 +2038,6 @@ void drbd_device_cleanup(struct drbd_device *device) D_ASSERT(device, list_empty(&device->sync_ee)); D_ASSERT(device, list_empty(&device->done_ee)); D_ASSERT(device, list_empty(&device->read_ee)); - D_ASSERT(device, list_empty(&device->net_ee)); D_ASSERT(device, list_empty(&device->resync_reads)); D_ASSERT(device, list_empty(&first_peer_device(device)->connection->sender_work.q)); D_ASSERT(device, list_empty(&device->resync_work.list)); @@ -2069,19 +2049,11 @@ void drbd_device_cleanup(struct drbd_device *device) static void drbd_destroy_mempools(void) { - struct page *page; - - while (drbd_pp_pool) { - page = drbd_pp_pool; - drbd_pp_pool = (struct page *)page_private(page); - __free_page(page); - drbd_pp_vacant--; - } - /* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */ bioset_exit(&drbd_io_bio_set); bioset_exit(&drbd_md_io_bio_set); + mempool_exit(&drbd_buffer_page_pool); mempool_exit(&drbd_md_io_page_pool); mempool_exit(&drbd_ee_mempool); mempool_exit(&drbd_request_mempool); @@ -2100,9 +2072,8 @@ static void drbd_destroy_mempools(void) static int drbd_create_mempools(void) { - struct page *page; const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count; - int i, ret; + int ret; /* caches */ drbd_request_cache = kmem_cache_create( @@ -2139,6 +2110,10 @@ static int drbd_create_mempools(void) if (ret) goto Enomem; + ret = mempool_init_page_pool(&drbd_buffer_page_pool, number, 0); + if (ret) + goto Enomem; + ret = mempool_init_slab_pool(&drbd_request_mempool, number, drbd_request_cache); if (ret) @@ -2148,15 +2123,6 @@ static int drbd_create_mempools(void) if (ret) goto Enomem; - for (i = 0; i < number; i++) { - page = alloc_page(GFP_HIGHUSER); - if (!page) - goto Enomem; - set_page_private(page, (unsigned long)drbd_pp_pool); - drbd_pp_pool = page; - } - drbd_pp_vacant = number; - return 0; Enomem: @@ -2183,10 +2149,6 @@ static void drbd_release_all_peer_reqs(struct drbd_device *device) rr = drbd_free_peer_reqs(device, &device->done_ee); if (rr) drbd_err(device, "%d EEs in done list found!\n", rr); - - rr = drbd_free_peer_reqs(device, &device->net_ee); - if (rr) - drbd_err(device, "%d EEs in net list found!\n", rr); } /* caution. no locking. */ @@ -2690,6 +2652,17 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig int id; int vnr = adm_ctx->volume; enum drbd_ret_code err = ERR_NOMEM; + struct queue_limits lim = { + /* + * Setting the max_hw_sectors to an odd value of 8kibyte here. + * This triggers a max_bio_size message upon first attach or + * connect. + */ + .max_hw_sectors = DRBD_MAX_BIO_SIZE_SAFE >> 8, + .features = BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | + BLK_FEAT_ROTATIONAL | + BLK_FEAT_STABLE_WRITES, + }; device = minor_to_device(minor); if (device) @@ -2708,9 +2681,11 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_init_set_defaults(device); - disk = blk_alloc_disk(NUMA_NO_NODE); - if (!disk) + disk = blk_alloc_disk(&lim, NUMA_NO_NODE); + if (IS_ERR(disk)) { + err = PTR_ERR(disk); goto out_no_disk; + } device->vdisk = disk; device->rq_queue = disk->queue; @@ -2725,12 +2700,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig sprintf(disk->disk_name, "drbd%d", minor); disk->private_data = device; - blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue); - blk_queue_write_cache(disk->queue, true, true); - /* Setting the max_hw_sectors to an odd value of 8kibyte here - This triggers a max_bio_size message upon first attach or connect */ - blk_queue_max_hw_sectors(disk->queue, DRBD_MAX_BIO_SIZE_SAFE >> 8); - device->md_io.page = alloc_page(GFP_KERNEL); if (!device->md_io.page) goto out_no_io_page; @@ -2870,11 +2839,6 @@ static int __init drbd_init(void) return err; } - /* - * allocate all necessary structs - */ - init_waitqueue_head(&drbd_pp_wait); - drbd_proc = NULL; /* play safe for drbd_cleanup */ idr_init(&drbd_devices); @@ -3041,7 +3005,7 @@ void drbd_md_sync(struct drbd_device *device) BUILD_BUG_ON(UI_SIZE != 4); BUILD_BUG_ON(sizeof(struct meta_data_on_disk) != 4096); - del_timer(&device->md_sync_timer); + timer_delete(&device->md_sync_timer); /* timer may be rearmed by drbd_md_mark_dirty() now. */ if (!test_and_clear_bit(MD_DIRTY, &device->flags)) return; @@ -3392,10 +3356,12 @@ void drbd_uuid_new_current(struct drbd_device *device) __must_hold(local) void drbd_uuid_set_bm(struct drbd_device *device, u64 val) __must_hold(local) { unsigned long flags; - if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0) + spin_lock_irqsave(&device->ldev->md.uuid_lock, flags); + if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0) { + spin_unlock_irqrestore(&device->ldev->md.uuid_lock, flags); return; + } - spin_lock_irqsave(&device->ldev->md.uuid_lock, flags); if (val == 0) { drbd_uuid_move_history(device); device->ldev->md.uuid[UI_HISTORY_START] = device->ldev->md.uuid[UI_BITMAP]; @@ -3415,6 +3381,7 @@ void drbd_uuid_set_bm(struct drbd_device *device, u64 val) __must_hold(local) /** * drbd_bmio_set_n_write() - io_fn for drbd_queue_bitmap_io() or drbd_bitmap_io() * @device: DRBD device. + * @peer_device: Peer DRBD device. * * Sets all bits in the bitmap and writes the whole bitmap to stable storage. */ @@ -3441,6 +3408,7 @@ int drbd_bmio_set_n_write(struct drbd_device *device, /** * drbd_bmio_clear_n_write() - io_fn for drbd_queue_bitmap_io() or drbd_bitmap_io() * @device: DRBD device. + * @peer_device: Peer DRBD device. * * Clears all bits in the bitmap and writes the whole bitmap to stable storage. */ @@ -3494,6 +3462,7 @@ static int w_bitmap_io(struct drbd_work *w, int unused) * @done: callback to be called after the bitmap IO was performed * @why: Descriptive text of the reason for doing the IO * @flags: Bitmap flags + * @peer_device: Peer DRBD device. * * While IO on the bitmap happens we freeze application IO thus we ensure * that drbd_set_out_of_sync() can not be called. This function MAY ONLY be @@ -3542,6 +3511,7 @@ void drbd_queue_bitmap_io(struct drbd_device *device, * @io_fn: IO callback to be called when bitmap IO is possible * @why: Descriptive text of the reason for doing the IO * @flags: Bitmap flags + * @peer_device: Peer DRBD device. * * freezes application IO while that the actual IO operations runs. This * functions MAY NOT be called from worker context. @@ -3592,7 +3562,8 @@ int drbd_md_test_flag(struct drbd_backing_dev *bdev, int flag) static void md_sync_timer_fn(struct timer_list *t) { - struct drbd_device *device = from_timer(device, t, md_sync_timer); + struct drbd_device *device = timer_container_of(device, t, + md_sync_timer); drbd_device_post_work(device, MD_SYNC); } |