diff options
Diffstat (limited to 'drivers/block/rnbd/rnbd-clt.c')
| -rw-r--r-- | drivers/block/rnbd/rnbd-clt.c | 171 |
1 files changed, 118 insertions, 53 deletions
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 45a470076652..c01786afe1b1 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -110,6 +110,7 @@ static int rnbd_clt_change_capacity(struct rnbd_clt_dev *dev, static int process_msg_open_rsp(struct rnbd_clt_dev *dev, struct rnbd_msg_open_rsp *rsp) { + struct kobject *gd_kobj; int err = 0; mutex_lock(&dev->lock); @@ -128,6 +129,8 @@ static int process_msg_open_rsp(struct rnbd_clt_dev *dev, */ if (dev->nsectors != nsectors) rnbd_clt_change_capacity(dev, nsectors); + gd_kobj = &disk_to_dev(dev->gd)->kobj; + kobject_uevent(gd_kobj, KOBJ_ONLINE); rnbd_clt_info(dev, "Device online, device remapped successfully\n"); } err = rnbd_clt_set_dev_attr(dev, rsp); @@ -312,13 +315,11 @@ static void rnbd_rerun_all_if_idle(struct rnbd_clt_session *sess) static struct rtrs_permit *rnbd_get_permit(struct rnbd_clt_session *sess, enum rtrs_clt_con_type con_type, - int wait) + enum wait_type wait) { struct rtrs_permit *permit; - permit = rtrs_clt_get_permit(sess->rtrs, con_type, - wait ? RTRS_PERMIT_WAIT : - RTRS_PERMIT_NOWAIT); + permit = rtrs_clt_get_permit(sess->rtrs, con_type, wait); if (likely(permit)) /* We have a subtle rare case here, when all permits can be * consumed before busy counter increased. This is safe, @@ -344,7 +345,7 @@ static void rnbd_put_permit(struct rnbd_clt_session *sess, static struct rnbd_iu *rnbd_get_iu(struct rnbd_clt_session *sess, enum rtrs_clt_con_type con_type, - int wait) + enum wait_type wait) { struct rnbd_iu *iu; struct rtrs_permit *permit; @@ -354,9 +355,7 @@ static struct rnbd_iu *rnbd_get_iu(struct rnbd_clt_session *sess, return NULL; } - permit = rnbd_get_permit(sess, con_type, - wait ? RTRS_PERMIT_WAIT : - RTRS_PERMIT_NOWAIT); + permit = rnbd_get_permit(sess, con_type, wait); if (unlikely(!permit)) { kfree(iu); return NULL; @@ -435,16 +434,11 @@ static void msg_conf(void *priv, int errno) schedule_work(&iu->work); } -enum wait_type { - NO_WAIT = 0, - WAIT = 1 -}; - static int send_usr_msg(struct rtrs_clt *rtrs, int dir, struct rnbd_iu *iu, struct kvec *vec, size_t len, struct scatterlist *sg, unsigned int sg_len, void (*conf)(struct work_struct *work), - int *errno, enum wait_type wait) + int *errno, int wait) { int err; struct rtrs_clt_req_ops req_ops; @@ -476,7 +470,8 @@ static void msg_close_conf(struct work_struct *work) rnbd_clt_put_dev(dev); } -static int send_msg_close(struct rnbd_clt_dev *dev, u32 device_id, bool wait) +static int send_msg_close(struct rnbd_clt_dev *dev, u32 device_id, + enum wait_type wait) { struct rnbd_clt_session *sess = dev->sess; struct rnbd_msg_close msg; @@ -530,7 +525,7 @@ static void msg_open_conf(struct work_struct *work) * If server thinks its fine, but we fail to process * then be nice and send a close to server. */ - (void)send_msg_close(dev, device_id, NO_WAIT); + send_msg_close(dev, device_id, RTRS_PERMIT_NOWAIT); } } kfree(rsp); @@ -554,7 +549,7 @@ static void msg_sess_info_conf(struct work_struct *work) rnbd_clt_put_sess(sess); } -static int send_msg_open(struct rnbd_clt_dev *dev, bool wait) +static int send_msg_open(struct rnbd_clt_dev *dev, enum wait_type wait) { struct rnbd_clt_session *sess = dev->sess; struct rnbd_msg_open_rsp *rsp; @@ -583,7 +578,7 @@ static int send_msg_open(struct rnbd_clt_dev *dev, bool wait) msg.hdr.type = cpu_to_le16(RNBD_MSG_OPEN); msg.access_mode = dev->access_mode; - strlcpy(msg.dev_name, dev->pathname, sizeof(msg.dev_name)); + strscpy(msg.dev_name, dev->pathname, sizeof(msg.dev_name)); WARN_ON(!rnbd_clt_get_dev(dev)); err = send_usr_msg(sess->rtrs, READ, iu, @@ -601,7 +596,7 @@ static int send_msg_open(struct rnbd_clt_dev *dev, bool wait) return err; } -static int send_msg_sess_info(struct rnbd_clt_session *sess, bool wait) +static int send_msg_sess_info(struct rnbd_clt_session *sess, enum wait_type wait) { struct rnbd_msg_sess_info_rsp *rsp; struct rnbd_msg_sess_info msg; @@ -657,14 +652,18 @@ put_iu: static void set_dev_states_to_disconnected(struct rnbd_clt_session *sess) { struct rnbd_clt_dev *dev; + struct kobject *gd_kobj; mutex_lock(&sess->lock); list_for_each_entry(dev, &sess->devs_list, list) { rnbd_clt_err(dev, "Device disconnected.\n"); mutex_lock(&dev->lock); - if (dev->dev_state == DEV_STATE_MAPPED) + if (dev->dev_state == DEV_STATE_MAPPED) { dev->dev_state = DEV_STATE_MAPPED_DISCONNECTED; + gd_kobj = &disk_to_dev(dev->gd)->kobj; + kobject_uevent(gd_kobj, KOBJ_OFFLINE); + } mutex_unlock(&dev->lock); } mutex_unlock(&sess->lock); @@ -687,7 +686,7 @@ static void remap_devs(struct rnbd_clt_session *sess) * be asynchronous. */ - err = send_msg_sess_info(sess, NO_WAIT); + err = send_msg_sess_info(sess, RTRS_PERMIT_NOWAIT); if (err) { pr_err("send_msg_sess_info(\"%s\"): %d\n", sess->sessname, err); return; @@ -711,7 +710,7 @@ static void remap_devs(struct rnbd_clt_session *sess) continue; rnbd_clt_info(dev, "session reconnected, remapping device\n"); - err = send_msg_open(dev, NO_WAIT); + err = send_msg_open(dev, RTRS_PERMIT_NOWAIT); if (err) { rnbd_clt_err(dev, "send_msg_open(): %d\n", err); break; @@ -801,7 +800,7 @@ static struct rnbd_clt_session *alloc_sess(const char *sessname) sess = kzalloc_node(sizeof(*sess), GFP_KERNEL, NUMA_NO_NODE); if (!sess) return ERR_PTR(-ENOMEM); - strlcpy(sess->sessname, sessname, sizeof(sess->sessname)); + strscpy(sess->sessname, sessname, sizeof(sess->sessname)); atomic_set(&sess->busy, 0); mutex_init(&sess->lock); INIT_LIST_HEAD(&sess->devs_list); @@ -918,6 +917,7 @@ again: return NULL; } +/* caller is responsible for initializing 'first' to false */ static struct rnbd_clt_session *find_or_create_sess(const char *sessname, bool *first) { @@ -933,8 +933,7 @@ rnbd_clt_session *find_or_create_sess(const char *sessname, bool *first) } list_add(&sess->list, &sess_list); *first = true; - } else - *first = false; + } mutex_unlock(&sess_lock); return sess; @@ -1173,9 +1172,54 @@ static blk_status_t rnbd_queue_rq(struct blk_mq_hw_ctx *hctx, return ret; } +static int rnbd_rdma_poll(struct blk_mq_hw_ctx *hctx) +{ + struct rnbd_queue *q = hctx->driver_data; + struct rnbd_clt_dev *dev = q->dev; + int cnt; + + cnt = rtrs_clt_rdma_cq_direct(dev->sess->rtrs, hctx->queue_num); + return cnt; +} + +static int rnbd_rdma_map_queues(struct blk_mq_tag_set *set) +{ + struct rnbd_clt_session *sess = set->driver_data; + + /* shared read/write queues */ + set->map[HCTX_TYPE_DEFAULT].nr_queues = num_online_cpus(); + set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; + set->map[HCTX_TYPE_READ].nr_queues = num_online_cpus(); + set->map[HCTX_TYPE_READ].queue_offset = 0; + blk_mq_map_queues(&set->map[HCTX_TYPE_DEFAULT]); + blk_mq_map_queues(&set->map[HCTX_TYPE_READ]); + + if (sess->nr_poll_queues) { + /* dedicated queue for poll */ + set->map[HCTX_TYPE_POLL].nr_queues = sess->nr_poll_queues; + set->map[HCTX_TYPE_POLL].queue_offset = set->map[HCTX_TYPE_READ].queue_offset + + set->map[HCTX_TYPE_READ].nr_queues; + blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); + pr_info("[session=%s] mapped %d/%d/%d default/read/poll queues.\n", + sess->sessname, + set->map[HCTX_TYPE_DEFAULT].nr_queues, + set->map[HCTX_TYPE_READ].nr_queues, + set->map[HCTX_TYPE_POLL].nr_queues); + } else { + pr_info("[session=%s] mapped %d/%d default/read queues.\n", + sess->sessname, + set->map[HCTX_TYPE_DEFAULT].nr_queues, + set->map[HCTX_TYPE_READ].nr_queues); + } + + return 0; +} + static struct blk_mq_ops rnbd_mq_ops = { .queue_rq = rnbd_queue_rq, .complete = rnbd_softirq_done_fn, + .map_queues = rnbd_rdma_map_queues, + .poll = rnbd_rdma_poll, }; static int setup_mq_tags(struct rnbd_clt_session *sess) @@ -1189,7 +1233,15 @@ static int setup_mq_tags(struct rnbd_clt_session *sess) tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_TAG_QUEUE_SHARED; tag_set->cmd_size = sizeof(struct rnbd_iu) + RNBD_RDMA_SGL_SIZE; - tag_set->nr_hw_queues = num_online_cpus(); + + /* for HCTX_TYPE_DEFAULT, HCTX_TYPE_READ, HCTX_TYPE_POLL */ + tag_set->nr_maps = sess->nr_poll_queues ? HCTX_MAX_TYPES : 2; + /* + * HCTX_TYPE_DEFAULT and HCTX_TYPE_READ share one set of queues + * others are for HCTX_TYPE_POLL + */ + tag_set->nr_hw_queues = num_online_cpus() + sess->nr_poll_queues; + tag_set->driver_data = sess; return blk_mq_alloc_tag_set(tag_set); } @@ -1197,18 +1249,27 @@ static int setup_mq_tags(struct rnbd_clt_session *sess) static struct rnbd_clt_session * find_and_get_or_create_sess(const char *sessname, const struct rtrs_addr *paths, - size_t path_cnt, u16 port_nr) + size_t path_cnt, u16 port_nr, u32 nr_poll_queues) { struct rnbd_clt_session *sess; struct rtrs_attrs attrs; int err; - bool first; + bool first = false; struct rtrs_clt_ops rtrs_ops; sess = find_or_create_sess(sessname, &first); if (sess == ERR_PTR(-ENOMEM)) return ERR_PTR(-ENOMEM); - else if (!first) + else if ((nr_poll_queues && !first) || (!nr_poll_queues && sess->nr_poll_queues)) { + /* + * A device MUST have its own session to use the polling-mode. + * It must fail to map new device with the same session. + */ + err = -EINVAL; + goto put_sess; + } + + if (!first) return sess; if (!path_cnt) { @@ -1228,8 +1289,7 @@ find_and_get_or_create_sess(const char *sessname, paths, path_cnt, port_nr, 0, /* Do not use pdu of rtrs */ RECONNECT_DELAY, BMAX_SEGMENTS, - BLK_MAX_SEGMENT_SIZE, - MAX_RECONNECTS); + MAX_RECONNECTS, nr_poll_queues); if (IS_ERR(sess->rtrs)) { err = PTR_ERR(sess->rtrs); goto wake_up_and_put; @@ -1237,12 +1297,13 @@ find_and_get_or_create_sess(const char *sessname, rtrs_clt_query(sess->rtrs, &attrs); sess->max_io_size = attrs.max_io_size; sess->queue_depth = attrs.queue_depth; + sess->nr_poll_queues = nr_poll_queues; err = setup_mq_tags(sess); if (err) goto close_rtrs; - err = send_msg_sess_info(sess, WAIT); + err = send_msg_sess_info(sess, RTRS_PERMIT_WAIT); if (err) goto close_rtrs; @@ -1352,12 +1413,12 @@ static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) if (!dev->rotational) blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue); + add_disk(dev->gd); } -static int rnbd_client_setup_device(struct rnbd_clt_session *sess, - struct rnbd_clt_dev *dev, int idx) +static int rnbd_client_setup_device(struct rnbd_clt_dev *dev) { - int err; + int err, idx = dev->clt_device_id; dev->size = dev->nsectors * dev->logical_block_size; @@ -1380,7 +1441,8 @@ static int rnbd_client_setup_device(struct rnbd_clt_session *sess, static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, enum rnbd_access_mode access_mode, - const char *pathname) + const char *pathname, + u32 nr_poll_queues) { struct rnbd_clt_dev *dev; int ret; @@ -1389,7 +1451,12 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, if (!dev) return ERR_PTR(-ENOMEM); - dev->hw_queues = kcalloc(nr_cpu_ids, sizeof(*dev->hw_queues), + /* + * nr_cpu_ids: the number of softirq queues + * nr_poll_queues: the number of polling queues + */ + dev->hw_queues = kcalloc(nr_cpu_ids + nr_poll_queues, + sizeof(*dev->hw_queues), GFP_KERNEL); if (!dev->hw_queues) { ret = -ENOMEM; @@ -1415,6 +1482,7 @@ static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, dev->clt_device_id = ret; dev->sess = sess; dev->access_mode = access_mode; + dev->nr_poll_queues = nr_poll_queues; mutex_init(&dev->lock); refcount_set(&dev->refcount, 1); dev->dev_state = DEV_STATE_INIT; @@ -1471,14 +1539,13 @@ static bool exists_devpath(const char *pathname, const char *sessname) return found; } -static bool insert_dev_if_not_exists_devpath(const char *pathname, - struct rnbd_clt_session *sess, - struct rnbd_clt_dev *dev) +static bool insert_dev_if_not_exists_devpath(struct rnbd_clt_dev *dev) { bool found; + struct rnbd_clt_session *sess = dev->sess; mutex_lock(&sess_lock); - found = __exists_dev(pathname, sess->sessname); + found = __exists_dev(dev->pathname, sess->sessname); if (!found) { mutex_lock(&sess->lock); list_add_tail(&dev->list, &sess->devs_list); @@ -1502,7 +1569,8 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, struct rtrs_addr *paths, size_t path_cnt, u16 port_nr, const char *pathname, - enum rnbd_access_mode access_mode) + enum rnbd_access_mode access_mode, + u32 nr_poll_queues) { struct rnbd_clt_session *sess; struct rnbd_clt_dev *dev; @@ -1511,22 +1579,22 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, if (unlikely(exists_devpath(pathname, sessname))) return ERR_PTR(-EEXIST); - sess = find_and_get_or_create_sess(sessname, paths, path_cnt, port_nr); + sess = find_and_get_or_create_sess(sessname, paths, path_cnt, port_nr, nr_poll_queues); if (IS_ERR(sess)) return ERR_CAST(sess); - dev = init_dev(sess, access_mode, pathname); + dev = init_dev(sess, access_mode, pathname, nr_poll_queues); if (IS_ERR(dev)) { pr_err("map_device: failed to map device '%s' from session %s, can't initialize device, err: %ld\n", pathname, sess->sessname, PTR_ERR(dev)); ret = PTR_ERR(dev); goto put_sess; } - if (insert_dev_if_not_exists_devpath(pathname, sess, dev)) { + if (insert_dev_if_not_exists_devpath(dev)) { ret = -EEXIST; goto put_dev; } - ret = send_msg_open(dev, WAIT); + ret = send_msg_open(dev, RTRS_PERMIT_WAIT); if (ret) { rnbd_clt_err(dev, "map_device: failed, can't open remote device, err: %d\n", @@ -1536,7 +1604,7 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, mutex_lock(&dev->lock); pr_debug("Opened remote device: session=%s, path='%s'\n", sess->sessname, pathname); - ret = rnbd_client_setup_device(sess, dev, dev->clt_device_id); + ret = rnbd_client_setup_device(dev); if (ret) { rnbd_clt_err(dev, "map_device: Failed to configure device, err: %d\n", @@ -1555,14 +1623,12 @@ struct rnbd_clt_dev *rnbd_clt_map_device(const char *sessname, dev->max_hw_sectors, dev->rotational, dev->wc, dev->fua); mutex_unlock(&dev->lock); - - add_disk(dev->gd); rnbd_clt_put_sess(sess); return dev; send_close: - send_msg_close(dev, dev->device_id, WAIT); + send_msg_close(dev, dev->device_id, RTRS_PERMIT_WAIT); del_dev: delete_dev(dev); put_dev: @@ -1622,7 +1688,7 @@ int rnbd_clt_unmap_device(struct rnbd_clt_dev *dev, bool force, destroy_sysfs(dev, sysfs_self); destroy_gen_disk(dev); if (was_mapped && sess->rtrs) - send_msg_close(dev, dev->device_id, WAIT); + send_msg_close(dev, dev->device_id, RTRS_PERMIT_WAIT); rnbd_clt_info(dev, "Device is unmapped\n"); @@ -1656,7 +1722,7 @@ int rnbd_clt_remap_device(struct rnbd_clt_dev *dev) mutex_unlock(&dev->lock); if (!err) { rnbd_clt_info(dev, "Remapping device.\n"); - err = send_msg_open(dev, WAIT); + err = send_msg_open(dev, RTRS_PERMIT_WAIT); if (err) rnbd_clt_err(dev, "remap_device: %d\n", err); } @@ -1678,7 +1744,6 @@ static void rnbd_destroy_sessions(void) struct rnbd_clt_dev *dev, *tn; /* Firstly forbid access through sysfs interface */ - rnbd_clt_destroy_default_group(); rnbd_clt_destroy_sysfs_files(); /* |