diff options
Diffstat (limited to 'drivers/block')
| -rw-r--r-- | drivers/block/Kconfig | 8 | ||||
| -rw-r--r-- | drivers/block/drbd/Kconfig | 2 | ||||
| -rw-r--r-- | drivers/block/loop.c | 121 | ||||
| -rw-r--r-- | drivers/block/null_blk/main.c | 2 | ||||
| -rw-r--r-- | drivers/block/ublk_drv.c | 565 |
5 files changed, 319 insertions, 379 deletions
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index a97f2c40c640..e48b24be45ee 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -367,7 +367,7 @@ config BLK_DEV_RBD tristate "Rados block device (RBD)" depends on INET && BLOCK select CEPH_LIB - select LIBCRC32C + select CRC32 select CRYPTO_AES select CRYPTO help @@ -388,12 +388,6 @@ config BLK_DEV_UBLK definition isn't finalized yet, and might change according to future requirement, so mark is as experimental now. - Say Y if you want to get better performance because task_work_add() - can be used in IO path for replacing io_uring cmd, which will become - shared between IO tasks and ubq daemon, meantime task_work_add() can - can handle batch more effectively, but task_work_add() isn't exported - for module, so ublk has to be built to kernel. - config BLKDEV_UBLK_LEGACY_OPCODES bool "Support legacy command opcode" depends on BLK_DEV_UBLK diff --git a/drivers/block/drbd/Kconfig b/drivers/block/drbd/Kconfig index 6fb4e38fca88..495a72da04c6 100644 --- a/drivers/block/drbd/Kconfig +++ b/drivers/block/drbd/Kconfig @@ -10,7 +10,7 @@ config BLK_DEV_DRBD tristate "DRBD Distributed Replicated Block Device support" depends on PROC_FS && INET select LRU_CACHE - select LIBCRC32C + select CRC32 help NOTE: In order to authenticate connections you have to select diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 674527d770dc..46cba261075f 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -211,72 +211,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size) kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); } -static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) -{ - struct iov_iter i; - ssize_t bw; - - iov_iter_bvec(&i, ITER_SOURCE, bvec, 1, bvec->bv_len); - - bw = vfs_iter_write(file, &i, ppos, 0); - - if (likely(bw == bvec->bv_len)) - return 0; - - printk_ratelimited(KERN_ERR - "loop: Write error at byte offset %llu, length %i.\n", - (unsigned long long)*ppos, bvec->bv_len); - if (bw >= 0) - bw = -EIO; - return bw; -} - -static int lo_write_simple(struct loop_device *lo, struct request *rq, - loff_t pos) -{ - struct bio_vec bvec; - struct req_iterator iter; - int ret = 0; - - rq_for_each_segment(bvec, rq, iter) { - ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos); - if (ret < 0) - break; - cond_resched(); - } - - return ret; -} - -static int lo_read_simple(struct loop_device *lo, struct request *rq, - loff_t pos) -{ - struct bio_vec bvec; - struct req_iterator iter; - struct iov_iter i; - ssize_t len; - - rq_for_each_segment(bvec, rq, iter) { - iov_iter_bvec(&i, ITER_DEST, &bvec, 1, bvec.bv_len); - len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); - if (len < 0) - return len; - - flush_dcache_page(bvec.bv_page); - - if (len != bvec.bv_len) { - struct bio *bio; - - __rq_for_each_bio(bio, rq) - zero_fill_bio(bio); - break; - } - cond_resched(); - } - - return 0; -} - static void loop_clear_limits(struct loop_device *lo, int mode) { struct queue_limits lim = queue_limits_start_update(lo->lo_queue); @@ -342,7 +276,7 @@ static void lo_complete_rq(struct request *rq) struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); blk_status_t ret = BLK_STS_OK; - if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || + if (cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || req_op(rq) != REQ_OP_READ) { if (cmd->ret < 0) ret = errno_to_blk_status(cmd->ret); @@ -358,14 +292,13 @@ static void lo_complete_rq(struct request *rq) cmd->ret = 0; blk_mq_requeue_request(rq, true); } else { - if (cmd->use_aio) { - struct bio *bio = rq->bio; + struct bio *bio = rq->bio; - while (bio) { - zero_fill_bio(bio); - bio = bio->bi_next; - } + while (bio) { + zero_fill_bio(bio); + bio = bio->bi_next; } + ret = BLK_STS_IOERR; end_io: blk_mq_end_request(rq, ret); @@ -445,9 +378,14 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, cmd->iocb.ki_pos = pos; cmd->iocb.ki_filp = file; - cmd->iocb.ki_complete = lo_rw_aio_complete; - cmd->iocb.ki_flags = IOCB_DIRECT; - cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); + cmd->iocb.ki_ioprio = req_get_ioprio(rq); + if (cmd->use_aio) { + cmd->iocb.ki_complete = lo_rw_aio_complete; + cmd->iocb.ki_flags = IOCB_DIRECT; + } else { + cmd->iocb.ki_complete = NULL; + cmd->iocb.ki_flags = 0; + } if (rw == ITER_SOURCE) ret = file->f_op->write_iter(&cmd->iocb, &iter); @@ -458,7 +396,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, if (ret != -EIOCBQUEUED) lo_rw_aio_complete(&cmd->iocb, ret); - return 0; + return -EIOCBQUEUED; } static int do_req_filebacked(struct loop_device *lo, struct request *rq) @@ -466,15 +404,6 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; - /* - * lo_write_simple and lo_read_simple should have been covered - * by io submit style function like lo_rw_aio(), one blocker - * is that lo_read_simple() need to call flush_dcache_page after - * the page is written from kernel, and it isn't easy to handle - * this in io submit style function which submits all segments - * of the req at one time. And direct read IO doesn't need to - * run flush_dcache_page(). - */ switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); @@ -490,15 +419,9 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) case REQ_OP_DISCARD: return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: - if (cmd->use_aio) - return lo_rw_aio(lo, cmd, pos, ITER_SOURCE); - else - return lo_write_simple(lo, rq, pos); + return lo_rw_aio(lo, cmd, pos, ITER_SOURCE); case REQ_OP_READ: - if (cmd->use_aio) - return lo_rw_aio(lo, cmd, pos, ITER_DEST); - else - return lo_read_simple(lo, rq, pos); + return lo_rw_aio(lo, cmd, pos, ITER_DEST); default: WARN_ON_ONCE(1); return -EIO; @@ -662,19 +585,20 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, * dependency. */ fput(old_file); + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); if (partscan) loop_reread_partitions(lo); error = 0; done: - /* enable and uncork uevent now that we are done */ - dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); return error; out_err: loop_global_unlock(lo, is_loop); out_putf: fput(file); + dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); goto done; } @@ -1129,8 +1053,8 @@ static int loop_configure(struct loop_device *lo, blk_mode_t mode, if (partscan) clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); - /* enable and uncork uevent now that we are done */ dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); + kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); loop_global_unlock(lo, is_loop); if (partscan) @@ -1921,7 +1845,6 @@ static void loop_handle_cmd(struct loop_cmd *cmd) struct loop_device *lo = rq->q->queuedata; int ret = 0; struct mem_cgroup *old_memcg = NULL; - const bool use_aio = cmd->use_aio; if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) { ret = -EIO; @@ -1951,7 +1874,7 @@ static void loop_handle_cmd(struct loop_cmd *cmd) } failed: /* complete non-aio request */ - if (!use_aio || ret) { + if (ret != -EIOCBQUEUED) { if (ret == -EOPNOTSUPP) cmd->ret = ret; else diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 3bb9cee0a9b5..aa163ae9b2aa 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -2031,7 +2031,7 @@ static int null_add_dev(struct nullb_device *dev) nullb->disk->minors = 1; nullb->disk->fops = &null_ops; nullb->disk->private_data = nullb; - strscpy_pad(nullb->disk->disk_name, nullb->disk_name, DISK_NAME_LEN); + strscpy(nullb->disk->disk_name, nullb->disk_name); if (nullb->dev->zoned) { rv = null_register_zoned_dev(nullb); diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 2fd05c1bd30b..2de7b2bd409d 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -123,15 +123,6 @@ struct ublk_uring_cmd_pdu { #define UBLK_IO_FLAG_OWNED_BY_SRV 0x02 /* - * IO command is aborted, so this flag is set in case of - * !UBLK_IO_FLAG_ACTIVE. - * - * After this flag is observed, any pending or new incoming request - * associated with this io command will be failed immediately - */ -#define UBLK_IO_FLAG_ABORTED 0x04 - -/* * UBLK_IO_FLAG_NEED_GET_DATA is set because IO command requires * get data buffer address from ublksrv. * @@ -199,8 +190,6 @@ struct ublk_device { struct completion completion; unsigned int nr_queues_ready; unsigned int nr_privileged_daemon; - - struct work_struct nosrv_work; }; /* header of ublk_params */ @@ -209,8 +198,8 @@ struct ublk_params_header { __u32 types; }; -static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq); - +static void ublk_stop_dev_unlocked(struct ublk_device *ub); +static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq); static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub, struct ublk_queue *ubq, int tag, size_t offset); static inline unsigned int ublk_req_build_flags(struct request *req); @@ -1074,7 +1063,7 @@ static inline struct ublk_uring_cmd_pdu *ublk_get_uring_cmd_pdu( static inline bool ubq_daemon_is_dying(struct ublk_queue *ubq) { - return ubq->ubq_daemon->flags & PF_EXITING; + return !ubq->ubq_daemon || ubq->ubq_daemon->flags & PF_EXITING; } /* todo: handle partial completion */ @@ -1085,12 +1074,6 @@ static inline void __ublk_complete_rq(struct request *req) unsigned int unmapped_bytes; blk_status_t res = BLK_STS_OK; - /* called from ublk_abort_queue() code path */ - if (io->flags & UBLK_IO_FLAG_ABORTED) { - res = BLK_STS_IOERR; - goto exit; - } - /* failed read IO if nothing is read */ if (!io->res && req_op(req) == REQ_OP_READ) io->res = -EIO; @@ -1140,25 +1123,6 @@ static void ublk_complete_rq(struct kref *ref) __ublk_complete_rq(req); } -/* - * Since ublk_rq_task_work_cb always fails requests immediately during - * exiting, __ublk_fail_req() is only called from abort context during - * exiting. So lock is unnecessary. - * - * Also aborting may not be started yet, keep in mind that one failed - * request may be issued by block layer again. - */ -static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, - struct request *req) -{ - WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE); - - if (ublk_nosrv_should_reissue_outstanding(ubq->dev)) - blk_mq_requeue_request(req, false); - else - ublk_put_req_ref(ubq, req); -} - static void ubq_complete_io_cmd(struct ublk_io *io, int res, unsigned issue_flags) { @@ -1314,8 +1278,6 @@ static void ublk_queue_cmd_list(struct ublk_queue *ubq, struct rq_list *l) static enum blk_eh_timer_return ublk_timeout(struct request *rq) { struct ublk_queue *ubq = rq->mq_hctx->driver_data; - unsigned int nr_inflight = 0; - int i; if (ubq->flags & UBLK_F_UNPRIVILEGED_DEV) { if (!ubq->timeout) { @@ -1326,30 +1288,11 @@ static enum blk_eh_timer_return ublk_timeout(struct request *rq) return BLK_EH_DONE; } - if (!ubq_daemon_is_dying(ubq)) - return BLK_EH_RESET_TIMER; - - for (i = 0; i < ubq->q_depth; i++) { - struct ublk_io *io = &ubq->ios[i]; - - if (!(io->flags & UBLK_IO_FLAG_ACTIVE)) - nr_inflight++; - } - - /* cancelable uring_cmd can't help us if all commands are in-flight */ - if (nr_inflight == ubq->q_depth) { - struct ublk_device *ub = ubq->dev; - - if (ublk_abort_requests(ub, ubq)) { - schedule_work(&ub->nosrv_work); - } - return BLK_EH_DONE; - } - return BLK_EH_RESET_TIMER; } -static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq) +static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq, + bool check_cancel) { blk_status_t res; @@ -1368,7 +1311,7 @@ static blk_status_t ublk_prep_req(struct ublk_queue *ubq, struct request *rq) if (ublk_nosrv_should_queue_io(ubq) && unlikely(ubq->force_abort)) return BLK_STS_IOERR; - if (unlikely(ubq->canceling)) + if (check_cancel && unlikely(ubq->canceling)) return BLK_STS_IOERR; /* fill iod to slot in io cmd buffer */ @@ -1387,7 +1330,7 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq = bd->rq; blk_status_t res; - res = ublk_prep_req(ubq, rq); + res = ublk_prep_req(ubq, rq, false); if (res != BLK_STS_OK) return res; @@ -1419,7 +1362,7 @@ static void ublk_queue_rqs(struct rq_list *rqlist) ublk_queue_cmd_list(ubq, &submit_list); ubq = this_q; - if (ublk_prep_req(ubq, req) == BLK_STS_OK) + if (ublk_prep_req(ubq, req, true) == BLK_STS_OK) rq_list_add_tail(&submit_list, req); else rq_list_add_tail(&requeue_list, req); @@ -1447,6 +1390,37 @@ static const struct blk_mq_ops ublk_mq_ops = { .timeout = ublk_timeout, }; +static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) +{ + int i; + + /* All old ioucmds have to be completed */ + ubq->nr_io_ready = 0; + + /* + * old daemon is PF_EXITING, put it now + * + * It could be NULL in case of closing one quisced device. + */ + if (ubq->ubq_daemon) + put_task_struct(ubq->ubq_daemon); + /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ + ubq->ubq_daemon = NULL; + ubq->timeout = false; + + for (i = 0; i < ubq->q_depth; i++) { + struct ublk_io *io = &ubq->ios[i]; + + /* + * UBLK_IO_FLAG_CANCELED is kept for avoiding to touch + * io->cmd + */ + io->flags &= UBLK_IO_FLAG_CANCELED; + io->cmd = NULL; + io->addr = 0; + } +} + static int ublk_ch_open(struct inode *inode, struct file *filp) { struct ublk_device *ub = container_of(inode->i_cdev, @@ -1458,10 +1432,119 @@ static int ublk_ch_open(struct inode *inode, struct file *filp) return 0; } +static void ublk_reset_ch_dev(struct ublk_device *ub) +{ + int i; + + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_queue_reinit(ub, ublk_get_queue(ub, i)); + + /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */ + ub->mm = NULL; + ub->nr_queues_ready = 0; + ub->nr_privileged_daemon = 0; +} + +static struct gendisk *ublk_get_disk(struct ublk_device *ub) +{ + struct gendisk *disk; + + spin_lock(&ub->lock); + disk = ub->ub_disk; + if (disk) + get_device(disk_to_dev(disk)); + spin_unlock(&ub->lock); + + return disk; +} + +static void ublk_put_disk(struct gendisk *disk) +{ + if (disk) + put_device(disk_to_dev(disk)); +} + static int ublk_ch_release(struct inode *inode, struct file *filp) { struct ublk_device *ub = filp->private_data; + struct gendisk *disk; + int i; + /* + * disk isn't attached yet, either device isn't live, or it has + * been removed already, so we needn't to do anything + */ + disk = ublk_get_disk(ub); + if (!disk) + goto out; + + /* + * All uring_cmd are done now, so abort any request outstanding to + * the ublk server + * + * This can be done in lockless way because ublk server has been + * gone + * + * More importantly, we have to provide forward progress guarantee + * without holding ub->mutex, otherwise control task grabbing + * ub->mutex triggers deadlock + * + * All requests may be inflight, so ->canceling may not be set, set + * it now. + */ + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + struct ublk_queue *ubq = ublk_get_queue(ub, i); + + ubq->canceling = true; + ublk_abort_queue(ub, ubq); + } + blk_mq_kick_requeue_list(disk->queue); + + /* + * All infligh requests have been completed or requeued and any new + * request will be failed or requeued via `->canceling` now, so it is + * fine to grab ub->mutex now. + */ + mutex_lock(&ub->mutex); + + /* double check after grabbing lock */ + if (!ub->ub_disk) + goto unlock; + + /* + * Transition the device to the nosrv state. What exactly this + * means depends on the recovery flags + */ + blk_mq_quiesce_queue(disk->queue); + if (ublk_nosrv_should_stop_dev(ub)) { + /* + * Allow any pending/future I/O to pass through quickly + * with an error. This is needed because del_gendisk + * waits for all pending I/O to complete + */ + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_get_queue(ub, i)->force_abort = true; + blk_mq_unquiesce_queue(disk->queue); + + ublk_stop_dev_unlocked(ub); + } else { + if (ublk_nosrv_dev_should_queue_io(ub)) { + /* ->canceling is set and all requests are aborted */ + ub->dev_info.state = UBLK_S_DEV_QUIESCED; + } else { + ub->dev_info.state = UBLK_S_DEV_FAIL_IO; + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) + ublk_get_queue(ub, i)->fail_io = true; + } + blk_mq_unquiesce_queue(disk->queue); + } +unlock: + mutex_unlock(&ub->mutex); + ublk_put_disk(disk); + + /* all uring_cmd has been done now, reset device & ubq */ + ublk_reset_ch_dev(ub); +out: clear_bit(UB_STATE_OPEN, &ub->state); return 0; } @@ -1528,10 +1611,26 @@ static void ublk_commit_completion(struct ublk_device *ub, ublk_put_req_ref(ubq, req); } +static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, + struct request *req) +{ + WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_ACTIVE); + + if (ublk_nosrv_should_reissue_outstanding(ubq->dev)) + blk_mq_requeue_request(req, false); + else { + io->res = -EIO; + __ublk_complete_rq(req); + } +} + /* - * Called from ubq_daemon context via cancel fn, meantime quiesce ublk - * blk-mq queue, so we are called exclusively with blk-mq and ubq_daemon - * context, so everything is serialized. + * Called from ublk char device release handler, when any uring_cmd is + * done, meantime request queue is "quiesced" since all inflight requests + * can't be completed because ublk server is dead. + * + * So no one can hold our request IO reference any more, simply ignore the + * reference, and complete the request immediately */ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq) { @@ -1548,46 +1647,29 @@ static void ublk_abort_queue(struct ublk_device *ub, struct ublk_queue *ubq) * will do it */ rq = blk_mq_tag_to_rq(ub->tag_set.tags[ubq->q_id], i); - if (rq && blk_mq_request_started(rq)) { - io->flags |= UBLK_IO_FLAG_ABORTED; + if (rq && blk_mq_request_started(rq)) __ublk_fail_req(ubq, io, rq); - } } } } /* Must be called when queue is frozen */ -static bool ublk_mark_queue_canceling(struct ublk_queue *ubq) +static void ublk_mark_queue_canceling(struct ublk_queue *ubq) { - bool canceled; - spin_lock(&ubq->cancel_lock); - canceled = ubq->canceling; - if (!canceled) + if (!ubq->canceling) ubq->canceling = true; spin_unlock(&ubq->cancel_lock); - - return canceled; } -static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq) +static void ublk_start_cancel(struct ublk_queue *ubq) { - bool was_canceled = ubq->canceling; - struct gendisk *disk; - - if (was_canceled) - return false; - - spin_lock(&ub->lock); - disk = ub->ub_disk; - if (disk) - get_device(disk_to_dev(disk)); - spin_unlock(&ub->lock); + struct ublk_device *ub = ubq->dev; + struct gendisk *disk = ublk_get_disk(ub); /* Our disk has been dead */ if (!disk) - return false; - + return; /* * Now we are serialized with ublk_queue_rq() * @@ -1596,15 +1678,9 @@ static bool ublk_abort_requests(struct ublk_device *ub, struct ublk_queue *ubq) * touch completed uring_cmd */ blk_mq_quiesce_queue(disk->queue); - was_canceled = ublk_mark_queue_canceling(ubq); - if (!was_canceled) { - /* abort queue is for making forward progress */ - ublk_abort_queue(ub, ubq); - } + ublk_mark_queue_canceling(ubq); blk_mq_unquiesce_queue(disk->queue); - put_device(disk_to_dev(disk)); - - return !was_canceled; + ublk_put_disk(disk); } static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io, @@ -1628,6 +1704,17 @@ static void ublk_cancel_cmd(struct ublk_queue *ubq, struct ublk_io *io, /* * The ublk char device won't be closed when calling cancel fn, so both * ublk device and queue are guaranteed to be live + * + * Two-stage cancel: + * + * - make every active uring_cmd done in ->cancel_fn() + * + * - aborting inflight ublk IO requests in ublk char device release handler, + * which depends on 1st stage because device can only be closed iff all + * uring_cmd are done + * + * Do _not_ try to acquire ub->mutex before all inflight requests are + * aborted, otherwise deadlock may be caused. */ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd, unsigned int issue_flags) @@ -1635,8 +1722,6 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd, struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); struct ublk_queue *ubq = pdu->ubq; struct task_struct *task; - struct ublk_device *ub; - bool need_schedule; struct ublk_io *io; if (WARN_ON_ONCE(!ubq)) @@ -1649,16 +1734,12 @@ static void ublk_uring_cmd_cancel_fn(struct io_uring_cmd *cmd, if (WARN_ON_ONCE(task && task != ubq->ubq_daemon)) return; - ub = ubq->dev; - need_schedule = ublk_abort_requests(ub, ubq); + if (!ubq->canceling) + ublk_start_cancel(ubq); io = &ubq->ios[pdu->tag]; WARN_ON_ONCE(io->cmd != cmd); ublk_cancel_cmd(ubq, io, issue_flags); - - if (need_schedule) { - schedule_work(&ub->nosrv_work); - } } static inline bool ublk_queue_ready(struct ublk_queue *ubq) @@ -1709,33 +1790,20 @@ static void ublk_wait_tagset_rqs_idle(struct ublk_device *ub) } } -static void __ublk_quiesce_dev(struct ublk_device *ub) -{ - pr_devel("%s: quiesce ub: dev_id %d state %s\n", - __func__, ub->dev_info.dev_id, - ub->dev_info.state == UBLK_S_DEV_LIVE ? - "LIVE" : "QUIESCED"); - blk_mq_quiesce_queue(ub->ub_disk->queue); - ublk_wait_tagset_rqs_idle(ub); - ub->dev_info.state = UBLK_S_DEV_QUIESCED; -} - -static void ublk_unquiesce_dev(struct ublk_device *ub) +static void ublk_force_abort_dev(struct ublk_device *ub) { int i; - pr_devel("%s: unquiesce ub: dev_id %d state %s\n", + pr_devel("%s: force abort ub: dev_id %d state %s\n", __func__, ub->dev_info.dev_id, ub->dev_info.state == UBLK_S_DEV_LIVE ? "LIVE" : "QUIESCED"); - /* quiesce_work has run. We let requeued rqs be aborted - * before running fallback_wq. "force_abort" must be seen - * after request queue is unqiuesced. Then del_gendisk() - * can move on. - */ + blk_mq_quiesce_queue(ub->ub_disk->queue); + if (ub->dev_info.state == UBLK_S_DEV_LIVE) + ublk_wait_tagset_rqs_idle(ub); + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) ublk_get_queue(ub, i)->force_abort = true; - blk_mq_unquiesce_queue(ub->ub_disk->queue); /* We may have requeued some rqs in ublk_quiesce_queue() */ blk_mq_kick_requeue_list(ub->ub_disk->queue); @@ -1756,61 +1824,51 @@ static struct gendisk *ublk_detach_disk(struct ublk_device *ub) return disk; } -static void ublk_stop_dev(struct ublk_device *ub) +static void ublk_stop_dev_unlocked(struct ublk_device *ub) + __must_hold(&ub->mutex) { struct gendisk *disk; - mutex_lock(&ub->mutex); if (ub->dev_info.state == UBLK_S_DEV_DEAD) - goto unlock; - if (ublk_nosrv_dev_should_queue_io(ub)) { - if (ub->dev_info.state == UBLK_S_DEV_LIVE) - __ublk_quiesce_dev(ub); - ublk_unquiesce_dev(ub); - } + return; + + if (ublk_nosrv_dev_should_queue_io(ub)) + ublk_force_abort_dev(ub); del_gendisk(ub->ub_disk); disk = ublk_detach_disk(ub); put_disk(disk); - unlock: +} + +static void ublk_stop_dev(struct ublk_device *ub) +{ + mutex_lock(&ub->mutex); + ublk_stop_dev_unlocked(ub); mutex_unlock(&ub->mutex); ublk_cancel_dev(ub); } -static void ublk_nosrv_work(struct work_struct *work) +/* reset ublk io_uring queue & io flags */ +static void ublk_reset_io_flags(struct ublk_device *ub) { - struct ublk_device *ub = - container_of(work, struct ublk_device, nosrv_work); - int i; - - if (ublk_nosrv_should_stop_dev(ub)) { - ublk_stop_dev(ub); - return; - } + int i, j; - mutex_lock(&ub->mutex); - if (ub->dev_info.state != UBLK_S_DEV_LIVE) - goto unlock; + for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { + struct ublk_queue *ubq = ublk_get_queue(ub, i); - if (ublk_nosrv_dev_should_queue_io(ub)) { - __ublk_quiesce_dev(ub); - } else { - blk_mq_quiesce_queue(ub->ub_disk->queue); - ub->dev_info.state = UBLK_S_DEV_FAIL_IO; - for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { - ublk_get_queue(ub, i)->fail_io = true; - } - blk_mq_unquiesce_queue(ub->ub_disk->queue); + /* UBLK_IO_FLAG_CANCELED can be cleared now */ + spin_lock(&ubq->cancel_lock); + for (j = 0; j < ubq->q_depth; j++) + ubq->ios[j].flags &= ~UBLK_IO_FLAG_CANCELED; + spin_unlock(&ubq->cancel_lock); + ubq->canceling = false; + ubq->fail_io = false; } - - unlock: - mutex_unlock(&ub->mutex); - ublk_cancel_dev(ub); } /* device can only be started after all IOs are ready */ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) + __must_hold(&ub->mutex) { - mutex_lock(&ub->mutex); ubq->nr_io_ready++; if (ublk_queue_ready(ubq)) { ubq->ubq_daemon = current; @@ -1820,9 +1878,12 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq) if (capable(CAP_SYS_ADMIN)) ub->nr_privileged_daemon++; } - if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) + + if (ub->nr_queues_ready == ub->dev_info.nr_hw_queues) { + /* now we are ready for handling ublk io request */ + ublk_reset_io_flags(ub); complete_all(&ub->completion); - mutex_unlock(&ub->mutex); + } } static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id, @@ -1906,6 +1967,52 @@ static int ublk_unregister_io_buf(struct io_uring_cmd *cmd, return io_buffer_unregister_bvec(cmd, index, issue_flags); } +static int ublk_fetch(struct io_uring_cmd *cmd, struct ublk_queue *ubq, + struct ublk_io *io, __u64 buf_addr) +{ + struct ublk_device *ub = ubq->dev; + int ret = 0; + + /* + * When handling FETCH command for setting up ublk uring queue, + * ub->mutex is the innermost lock, and we won't block for handling + * FETCH, so it is fine even for IO_URING_F_NONBLOCK. + */ + mutex_lock(&ub->mutex); + /* UBLK_IO_FETCH_REQ is only allowed before queue is setup */ + if (ublk_queue_ready(ubq)) { + ret = -EBUSY; + goto out; + } + + /* allow each command to be FETCHed at most once */ + if (io->flags & UBLK_IO_FLAG_ACTIVE) { + ret = -EINVAL; + goto out; + } + + WARN_ON_ONCE(io->flags & UBLK_IO_FLAG_OWNED_BY_SRV); + + if (ublk_need_map_io(ubq)) { + /* + * FETCH_RQ has to provide IO buffer if NEED GET + * DATA is not enabled + */ + if (!buf_addr && !ublk_need_get_data(ubq)) + goto out; + } else if (buf_addr) { + /* User copy requires addr to be unset */ + ret = -EINVAL; + goto out; + } + + ublk_fill_io_cmd(io, cmd, buf_addr); + ublk_mark_io_ready(ub, ubq); +out: + mutex_unlock(&ub->mutex); + return ret; +} + static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags, const struct ublksrv_io_cmd *ub_cmd) @@ -1962,33 +2069,9 @@ static int __ublk_ch_uring_cmd(struct io_uring_cmd *cmd, case UBLK_IO_UNREGISTER_IO_BUF: return ublk_unregister_io_buf(cmd, ub_cmd->addr, issue_flags); case UBLK_IO_FETCH_REQ: - /* UBLK_IO_FETCH_REQ is only allowed before queue is setup */ - if (ublk_queue_ready(ubq)) { - ret = -EBUSY; - goto out; - } - /* - * The io is being handled by server, so COMMIT_RQ is expected - * instead of FETCH_REQ - */ - if (io->flags & UBLK_IO_FLAG_OWNED_BY_SRV) - goto out; - - if (ublk_need_map_io(ubq)) { - /* - * FETCH_RQ has to provide IO buffer if NEED GET - * DATA is not enabled - */ - if (!ub_cmd->addr && !ublk_need_get_data(ubq)) - goto out; - } else if (ub_cmd->addr) { - /* User copy requires addr to be unset */ - ret = -EINVAL; + ret = ublk_fetch(cmd, ubq, io, ub_cmd->addr); + if (ret) goto out; - } - - ublk_fill_io_cmd(io, cmd, ub_cmd->addr); - ublk_mark_io_ready(ub, ubq); break; case UBLK_IO_COMMIT_AND_FETCH_REQ: req = blk_mq_tag_to_rq(ub->tag_set.tags[ub_cmd->q_id], tag); @@ -2388,7 +2471,6 @@ static void ublk_remove(struct ublk_device *ub) bool unprivileged; ublk_stop_dev(ub); - cancel_work_sync(&ub->nosrv_work); cdev_device_del(&ub->cdev, &ub->cdev_dev); unprivileged = ub->dev_info.flags & UBLK_F_UNPRIVILEGED_DEV; ublk_put_device(ub); @@ -2413,9 +2495,9 @@ static struct ublk_device *ublk_get_device_from_id(int idx) return ub; } -static int ublk_ctrl_start_dev(struct ublk_device *ub, struct io_uring_cmd *cmd) +static int ublk_ctrl_start_dev(struct ublk_device *ub, + const struct ublksrv_ctrl_cmd *header) { - const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); const struct ublk_param_basic *p = &ub->params.basic; int ublksrv_pid = (int)header->data[0]; struct queue_limits lim = { @@ -2534,9 +2616,8 @@ out_unlock: } static int ublk_ctrl_get_queue_affinity(struct ublk_device *ub, - struct io_uring_cmd *cmd) + const struct ublksrv_ctrl_cmd *header) { - const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; cpumask_var_t cpumask; unsigned long queue; @@ -2585,9 +2666,8 @@ static inline void ublk_dump_dev_info(struct ublksrv_ctrl_dev_info *info) info->nr_hw_queues, info->queue_depth); } -static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) +static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header) { - const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; struct ublksrv_ctrl_dev_info info; struct ublk_device *ub; @@ -2675,7 +2755,6 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd) goto out_unlock; mutex_init(&ub->mutex); spin_lock_init(&ub->lock); - INIT_WORK(&ub->nosrv_work, ublk_nosrv_work); ret = ublk_alloc_dev_number(ub, header->dev_id); if (ret < 0) @@ -2807,14 +2886,12 @@ static inline void ublk_ctrl_cmd_dump(struct io_uring_cmd *cmd) static int ublk_ctrl_stop_dev(struct ublk_device *ub) { ublk_stop_dev(ub); - cancel_work_sync(&ub->nosrv_work); return 0; } static int ublk_ctrl_get_dev_info(struct ublk_device *ub, - struct io_uring_cmd *cmd) + const struct ublksrv_ctrl_cmd *header) { - const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; if (header->len < sizeof(struct ublksrv_ctrl_dev_info) || !header->addr) @@ -2843,9 +2920,8 @@ static void ublk_ctrl_fill_params_devt(struct ublk_device *ub) } static int ublk_ctrl_get_params(struct ublk_device *ub, - struct io_uring_cmd *cmd) + const struct ublksrv_ctrl_cmd *header) { - const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; struct ublk_params_header ph; int ret; @@ -2874,9 +2950,8 @@ static int ublk_ctrl_get_params(struct ublk_device *ub, } static int ublk_ctrl_set_params(struct ublk_device *ub, - struct io_uring_cmd *cmd) + const struct ublksrv_ctrl_cmd *header) { - const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; struct ublk_params_header ph; int ret = -EFAULT; @@ -2914,43 +2989,14 @@ static int ublk_ctrl_set_params(struct ublk_device *ub, return ret; } -static void ublk_queue_reinit(struct ublk_device *ub, struct ublk_queue *ubq) -{ - int i; - - WARN_ON_ONCE(!(ubq->ubq_daemon && ubq_daemon_is_dying(ubq))); - - /* All old ioucmds have to be completed */ - ubq->nr_io_ready = 0; - /* old daemon is PF_EXITING, put it now */ - put_task_struct(ubq->ubq_daemon); - /* We have to reset it to NULL, otherwise ub won't accept new FETCH_REQ */ - ubq->ubq_daemon = NULL; - ubq->timeout = false; - ubq->canceling = false; - - for (i = 0; i < ubq->q_depth; i++) { - struct ublk_io *io = &ubq->ios[i]; - - /* forget everything now and be ready for new FETCH_REQ */ - io->flags = 0; - io->cmd = NULL; - io->addr = 0; - } -} - static int ublk_ctrl_start_recovery(struct ublk_device *ub, - struct io_uring_cmd *cmd) + const struct ublksrv_ctrl_cmd *header) { - const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); int ret = -EINVAL; - int i; mutex_lock(&ub->mutex); if (ublk_nosrv_should_stop_dev(ub)) goto out_unlock; - if (!ub->nr_queues_ready) - goto out_unlock; /* * START_RECOVERY is only allowd after: * @@ -2974,12 +3020,6 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub, goto out_unlock; } pr_devel("%s: start recovery for dev id %d.\n", __func__, header->dev_id); - for (i = 0; i < ub->dev_info.nr_hw_queues; i++) - ublk_queue_reinit(ub, ublk_get_queue(ub, i)); - /* set to NULL, otherwise new ubq_daemon cannot mmap the io_cmd_buf */ - ub->mm = NULL; - ub->nr_queues_ready = 0; - ub->nr_privileged_daemon = 0; init_completion(&ub->completion); ret = 0; out_unlock: @@ -2988,12 +3028,10 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub, } static int ublk_ctrl_end_recovery(struct ublk_device *ub, - struct io_uring_cmd *cmd) + const struct ublksrv_ctrl_cmd *header) { - const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); int ublksrv_pid = (int)header->data[0]; int ret = -EINVAL; - int i; pr_devel("%s: Waiting for new ubq_daemons(nr: %d) are ready, dev id %d...\n", __func__, ub->dev_info.nr_hw_queues, header->dev_id); @@ -3013,33 +3051,18 @@ static int ublk_ctrl_end_recovery(struct ublk_device *ub, goto out_unlock; } ub->dev_info.ublksrv_pid = ublksrv_pid; + ub->dev_info.state = UBLK_S_DEV_LIVE; pr_devel("%s: new ublksrv_pid %d, dev id %d\n", __func__, ublksrv_pid, header->dev_id); - - if (ublk_nosrv_dev_should_queue_io(ub)) { - ub->dev_info.state = UBLK_S_DEV_LIVE; - blk_mq_unquiesce_queue(ub->ub_disk->queue); - pr_devel("%s: queue unquiesced, dev id %d.\n", - __func__, header->dev_id); - blk_mq_kick_requeue_list(ub->ub_disk->queue); - } else { - blk_mq_quiesce_queue(ub->ub_disk->queue); - ub->dev_info.state = UBLK_S_DEV_LIVE; - for (i = 0; i < ub->dev_info.nr_hw_queues; i++) { - ublk_get_queue(ub, i)->fail_io = false; - } - blk_mq_unquiesce_queue(ub->ub_disk->queue); - } - + blk_mq_kick_requeue_list(ub->ub_disk->queue); ret = 0; out_unlock: mutex_unlock(&ub->mutex); return ret; } -static int ublk_ctrl_get_features(struct io_uring_cmd *cmd) +static int ublk_ctrl_get_features(const struct ublksrv_ctrl_cmd *header) { - const struct ublksrv_ctrl_cmd *header = io_uring_sqe_cmd(cmd->sqe); void __user *argp = (void __user *)(unsigned long)header->addr; u64 features = UBLK_F_ALL; @@ -3178,7 +3201,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, goto out; if (cmd_op == UBLK_U_CMD_GET_FEATURES) { - ret = ublk_ctrl_get_features(cmd); + ret = ublk_ctrl_get_features(header); goto out; } @@ -3195,17 +3218,17 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, switch (_IOC_NR(cmd_op)) { case UBLK_CMD_START_DEV: - ret = ublk_ctrl_start_dev(ub, cmd); + ret = ublk_ctrl_start_dev(ub, header); break; case UBLK_CMD_STOP_DEV: ret = ublk_ctrl_stop_dev(ub); break; case UBLK_CMD_GET_DEV_INFO: case UBLK_CMD_GET_DEV_INFO2: - ret = ublk_ctrl_get_dev_info(ub, cmd); + ret = ublk_ctrl_get_dev_info(ub, header); break; case UBLK_CMD_ADD_DEV: - ret = ublk_ctrl_add_dev(cmd); + ret = ublk_ctrl_add_dev(header); break; case UBLK_CMD_DEL_DEV: ret = ublk_ctrl_del_dev(&ub, true); @@ -3214,19 +3237,19 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, ret = ublk_ctrl_del_dev(&ub, false); break; case UBLK_CMD_GET_QUEUE_AFFINITY: - ret = ublk_ctrl_get_queue_affinity(ub, cmd); + ret = ublk_ctrl_get_queue_affinity(ub, header); break; case UBLK_CMD_GET_PARAMS: - ret = ublk_ctrl_get_params(ub, cmd); + ret = ublk_ctrl_get_params(ub, header); break; case UBLK_CMD_SET_PARAMS: - ret = ublk_ctrl_set_params(ub, cmd); + ret = ublk_ctrl_set_params(ub, header); break; case UBLK_CMD_START_USER_RECOVERY: - ret = ublk_ctrl_start_recovery(ub, cmd); + ret = ublk_ctrl_start_recovery(ub, header); break; case UBLK_CMD_END_USER_RECOVERY: - ret = ublk_ctrl_end_recovery(ub, cmd); + ret = ublk_ctrl_end_recovery(ub, header); break; default: ret = -EOPNOTSUPP; |