whiterose

linux unikernel
Log | Files | Refs | README | LICENSE | git clone https://git.ne02ptzero.me/git/whiterose

commit 6b8f9159166545e576b2bc8a0c984beaeae9cc05
parent ba606975938179b1e893e44e190d0001de8e5262
Author: Linus Torvalds <torvalds@linux-foundation.org>
Date:   Sat, 26 Jan 2019 12:42:41 -0800

Merge tag 'for-linus-20190125' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:
 "A collection of fixes for this release. This contains:

   - Silence sparse rightfully complaining about non-static wbt
     functions (Bart)

   - Fixes for the zoned comments/ioctl documentation (Damien)

   - direct-io fix that's been lingering for a while (Ernesto)

   - cgroup writeback fix (Tejun)

   - Set of NVMe patches for nvme-rdma/tcp (Sagi, Hannes, Raju)

   - Block recursion tracking fix (Ming)

   - Fix debugfs command flag naming for a few flags (Jianchao)"

* tag 'for-linus-20190125' of git://git.kernel.dk/linux-block:
  block: Fix comment typo
  uapi: fix ioctl documentation
  blk-wbt: Declare local functions static
  blk-mq: fix the cmd_flag_name array
  nvme-multipath: drop optimization for static ANA group IDs
  nvmet-rdma: fix null dereference under heavy load
  nvme-rdma: rework queue maps handling
  nvme-tcp: fix timeout handler
  nvme-rdma: fix timeout handler
  writeback: synchronize sync(2) against cgroup writeback membership switches
  block: cover another queue enter recursion via BIO_QUEUE_ENTERED
  direct-io: allow direct writes to empty inodes

Diffstat:
Mblock/blk-core.c | 11+++++++++++
Mblock/blk-merge.c | 10----------
Mblock/blk-mq-debugfs.c | 3++-
Mblock/blk-wbt.c | 4++--
Mdrivers/nvme/host/multipath.c | 3+--
Mdrivers/nvme/host/rdma.c | 64+++++++++++++++++++++++++++++++++++++++++++---------------------
Mdrivers/nvme/host/tcp.c | 19+++++++++++--------
Mdrivers/nvme/target/rdma.c | 15++++++++++++++-
Mfs/direct-io.c | 5+++--
Mfs/fs-writeback.c | 40++++++++++++++++++++++++++++++++++++++--
Minclude/linux/backing-dev-defs.h | 1+
Minclude/linux/blk_types.h | 2+-
Minclude/uapi/linux/blkzoned.h | 1+
Mmm/backing-dev.c | 1+
14 files changed, 129 insertions(+), 50 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c @@ -1083,7 +1083,18 @@ blk_qc_t generic_make_request(struct bio *bio) /* Create a fresh bio_list for all subordinate requests */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); + + /* + * Since we're recursing into make_request here, ensure + * that we mark this bio as already having entered the queue. + * If not, and the queue is going away, we can get stuck + * forever on waiting for the queue reference to drop. But + * that will never happen, as we're already holding a + * reference to it. + */ + bio_set_flag(bio, BIO_QUEUE_ENTERED); ret = q->make_request_fn(q, bio); + bio_clear_flag(bio, BIO_QUEUE_ENTERED); /* sort new bios into those for a lower level * and those for the same level diff --git a/block/blk-merge.c b/block/blk-merge.c @@ -272,16 +272,6 @@ void blk_queue_split(struct request_queue *q, struct bio **bio) /* there isn't chance to merge the splitted bio */ split->bi_opf |= REQ_NOMERGE; - /* - * Since we're recursing into make_request here, ensure - * that we mark this bio as already having entered the queue. - * If not, and the queue is going away, we can get stuck - * forever on waiting for the queue reference to drop. But - * that will never happen, as we're already holding a - * reference to it. - */ - bio_set_flag(*bio, BIO_QUEUE_ENTERED); - bio_chain(split, *bio); trace_block_split(q, split, (*bio)->bi_iter.bi_sector); generic_make_request(*bio); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c @@ -308,8 +308,9 @@ static const char *const cmd_flag_name[] = { CMD_FLAG_NAME(PREFLUSH), CMD_FLAG_NAME(RAHEAD), CMD_FLAG_NAME(BACKGROUND), - CMD_FLAG_NAME(NOUNMAP), CMD_FLAG_NAME(NOWAIT), + CMD_FLAG_NAME(NOUNMAP), + CMD_FLAG_NAME(HIPRI), }; #undef CMD_FLAG_NAME diff --git a/block/blk-wbt.c b/block/blk-wbt.c @@ -597,7 +597,7 @@ static void wbt_track(struct rq_qos *rqos, struct request *rq, struct bio *bio) rq->wbt_flags |= bio_to_wbt_flags(rwb, bio); } -void wbt_issue(struct rq_qos *rqos, struct request *rq) +static void wbt_issue(struct rq_qos *rqos, struct request *rq) { struct rq_wb *rwb = RQWB(rqos); @@ -617,7 +617,7 @@ void wbt_issue(struct rq_qos *rqos, struct request *rq) } } -void wbt_requeue(struct rq_qos *rqos, struct request *rq) +static void wbt_requeue(struct rq_qos *rqos, struct request *rq) { struct rq_wb *rwb = RQWB(rqos); if (!rwb_enabled(rwb)) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c @@ -545,8 +545,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0); ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) + ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc); - if (!(ctrl->anacap & (1 << 6))) - ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32); + ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32); if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) { dev_err(ctrl->device, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c @@ -119,6 +119,7 @@ struct nvme_rdma_ctrl { struct nvme_ctrl ctrl; bool use_inline_data; + u32 io_queues[HCTX_MAX_TYPES]; }; static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl) @@ -165,8 +166,8 @@ static inline int nvme_rdma_queue_idx(struct nvme_rdma_queue *queue) static bool nvme_rdma_poll_queue(struct nvme_rdma_queue *queue) { return nvme_rdma_queue_idx(queue) > - queue->ctrl->ctrl.opts->nr_io_queues + - queue->ctrl->ctrl.opts->nr_write_queues; + queue->ctrl->io_queues[HCTX_TYPE_DEFAULT] + + queue->ctrl->io_queues[HCTX_TYPE_READ]; } static inline size_t nvme_rdma_inline_data_size(struct nvme_rdma_queue *queue) @@ -661,8 +662,21 @@ static int nvme_rdma_alloc_io_queues(struct nvme_rdma_ctrl *ctrl) nr_io_queues = min_t(unsigned int, nr_io_queues, ibdev->num_comp_vectors); - nr_io_queues += min(opts->nr_write_queues, num_online_cpus()); - nr_io_queues += min(opts->nr_poll_queues, num_online_cpus()); + if (opts->nr_write_queues) { + ctrl->io_queues[HCTX_TYPE_DEFAULT] = + min(opts->nr_write_queues, nr_io_queues); + nr_io_queues += ctrl->io_queues[HCTX_TYPE_DEFAULT]; + } else { + ctrl->io_queues[HCTX_TYPE_DEFAULT] = nr_io_queues; + } + + ctrl->io_queues[HCTX_TYPE_READ] = nr_io_queues; + + if (opts->nr_poll_queues) { + ctrl->io_queues[HCTX_TYPE_POLL] = + min(opts->nr_poll_queues, num_online_cpus()); + nr_io_queues += ctrl->io_queues[HCTX_TYPE_POLL]; + } ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues); if (ret) @@ -1689,18 +1703,28 @@ static enum blk_eh_timer_return nvme_rdma_timeout(struct request *rq, bool reserved) { struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq); + struct nvme_rdma_queue *queue = req->queue; + struct nvme_rdma_ctrl *ctrl = queue->ctrl; - dev_warn(req->queue->ctrl->ctrl.device, - "I/O %d QID %d timeout, reset controller\n", - rq->tag, nvme_rdma_queue_idx(req->queue)); + dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n", + rq->tag, nvme_rdma_queue_idx(queue)); - /* queue error recovery */ - nvme_rdma_error_recovery(req->queue->ctrl); + if (ctrl->ctrl.state != NVME_CTRL_LIVE) { + /* + * Teardown immediately if controller times out while starting + * or we are already started error recovery. all outstanding + * requests are completed on shutdown, so we return BLK_EH_DONE. + */ + flush_work(&ctrl->err_work); + nvme_rdma_teardown_io_queues(ctrl, false); + nvme_rdma_teardown_admin_queue(ctrl, false); + return BLK_EH_DONE; + } - /* fail with DNR on cmd timeout */ - nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR; + dev_warn(ctrl->ctrl.device, "starting error recovery\n"); + nvme_rdma_error_recovery(ctrl); - return BLK_EH_DONE; + return BLK_EH_RESET_TIMER; } static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx, @@ -1779,17 +1803,15 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) struct nvme_rdma_ctrl *ctrl = set->driver_data; set->map[HCTX_TYPE_DEFAULT].queue_offset = 0; - set->map[HCTX_TYPE_READ].nr_queues = ctrl->ctrl.opts->nr_io_queues; + set->map[HCTX_TYPE_DEFAULT].nr_queues = + ctrl->io_queues[HCTX_TYPE_DEFAULT]; + set->map[HCTX_TYPE_READ].nr_queues = ctrl->io_queues[HCTX_TYPE_READ]; if (ctrl->ctrl.opts->nr_write_queues) { /* separate read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->ctrl.opts->nr_write_queues; set->map[HCTX_TYPE_READ].queue_offset = - ctrl->ctrl.opts->nr_write_queues; + ctrl->io_queues[HCTX_TYPE_DEFAULT]; } else { /* mixed read/write queues */ - set->map[HCTX_TYPE_DEFAULT].nr_queues = - ctrl->ctrl.opts->nr_io_queues; set->map[HCTX_TYPE_READ].queue_offset = 0; } blk_mq_rdma_map_queues(&set->map[HCTX_TYPE_DEFAULT], @@ -1799,12 +1821,12 @@ static int nvme_rdma_map_queues(struct blk_mq_tag_set *set) if (ctrl->ctrl.opts->nr_poll_queues) { set->map[HCTX_TYPE_POLL].nr_queues = - ctrl->ctrl.opts->nr_poll_queues; + ctrl->io_queues[HCTX_TYPE_POLL]; set->map[HCTX_TYPE_POLL].queue_offset = - ctrl->ctrl.opts->nr_io_queues; + ctrl->io_queues[HCTX_TYPE_DEFAULT]; if (ctrl->ctrl.opts->nr_write_queues) set->map[HCTX_TYPE_POLL].queue_offset += - ctrl->ctrl.opts->nr_write_queues; + ctrl->io_queues[HCTX_TYPE_READ]; blk_mq_map_queues(&set->map[HCTX_TYPE_POLL]); } return 0; diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c @@ -1948,20 +1948,23 @@ nvme_tcp_timeout(struct request *rq, bool reserved) struct nvme_tcp_ctrl *ctrl = req->queue->ctrl; struct nvme_tcp_cmd_pdu *pdu = req->pdu; - dev_dbg(ctrl->ctrl.device, + dev_warn(ctrl->ctrl.device, "queue %d: timeout request %#x type %d\n", - nvme_tcp_queue_id(req->queue), rq->tag, - pdu->hdr.type); + nvme_tcp_queue_id(req->queue), rq->tag, pdu->hdr.type); if (ctrl->ctrl.state != NVME_CTRL_LIVE) { - union nvme_result res = {}; - - nvme_req(rq)->flags |= NVME_REQ_CANCELLED; - nvme_end_request(rq, cpu_to_le16(NVME_SC_ABORT_REQ), res); + /* + * Teardown immediately if controller times out while starting + * or we are already started error recovery. all outstanding + * requests are completed on shutdown, so we return BLK_EH_DONE. + */ + flush_work(&ctrl->err_work); + nvme_tcp_teardown_io_queues(&ctrl->ctrl, false); + nvme_tcp_teardown_admin_queue(&ctrl->ctrl, false); return BLK_EH_DONE; } - /* queue error recovery */ + dev_warn(ctrl->ctrl.device, "starting error recovery\n"); nvme_tcp_error_recovery(&ctrl->ctrl); return BLK_EH_RESET_TIMER; diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c @@ -139,6 +139,10 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc); static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc); static void nvmet_rdma_qp_event(struct ib_event *event, void *priv); static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue); +static void nvmet_rdma_free_rsp(struct nvmet_rdma_device *ndev, + struct nvmet_rdma_rsp *r); +static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev, + struct nvmet_rdma_rsp *r); static const struct nvmet_fabrics_ops nvmet_rdma_ops; @@ -182,9 +186,17 @@ nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue) spin_unlock_irqrestore(&queue->rsps_lock, flags); if (unlikely(!rsp)) { - rsp = kmalloc(sizeof(*rsp), GFP_KERNEL); + int ret; + + rsp = kzalloc(sizeof(*rsp), GFP_KERNEL); if (unlikely(!rsp)) return NULL; + ret = nvmet_rdma_alloc_rsp(queue->dev, rsp); + if (unlikely(ret)) { + kfree(rsp); + return NULL; + } + rsp->allocated = true; } @@ -197,6 +209,7 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp) unsigned long flags; if (unlikely(rsp->allocated)) { + nvmet_rdma_free_rsp(rsp->queue->dev, rsp); kfree(rsp); return; } diff --git a/fs/direct-io.c b/fs/direct-io.c @@ -679,6 +679,7 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, unsigned long fs_count; /* Number of filesystem-sized blocks */ int create; unsigned int i_blkbits = sdio->blkbits + sdio->blkfactor; + loff_t i_size; /* * If there was a memory error and we've overwritten all the @@ -708,8 +709,8 @@ static int get_more_blocks(struct dio *dio, struct dio_submit *sdio, */ create = dio->op == REQ_OP_WRITE; if (dio->flags & DIO_SKIP_HOLES) { - if (fs_startblk <= ((i_size_read(dio->inode) - 1) >> - i_blkbits)) + i_size = i_size_read(dio->inode); + if (i_size && fs_startblk <= (i_size - 1) >> i_blkbits) create = 0; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c @@ -331,11 +331,22 @@ struct inode_switch_wbs_context { struct work_struct work; }; +static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) +{ + down_write(&bdi->wb_switch_rwsem); +} + +static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) +{ + up_write(&bdi->wb_switch_rwsem); +} + static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; + struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -344,6 +355,12 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) bool switched = false; /* + * If @inode switches cgwb membership while sync_inodes_sb() is + * being issued, sync_inodes_sb() might miss it. Synchronize. + */ + down_read(&bdi->wb_switch_rwsem); + + /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be @@ -428,6 +445,8 @@ skip_switch: spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); + up_read(&bdi->wb_switch_rwsem); + if (switched) { wb_wakeup(new_wb); wb_put(old_wb); @@ -468,9 +487,18 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) if (inode->i_state & I_WB_SWITCH) return; + /* + * Avoid starting new switches while sync_inodes_sb() is in + * progress. Otherwise, if the down_write protected issue path + * blocks heavily, we might end up starting a large number of + * switches which will block on the rwsem. + */ + if (!down_read_trylock(&bdi->wb_switch_rwsem)) + return; + isw = kzalloc(sizeof(*isw), GFP_ATOMIC); if (!isw) - return; + goto out_unlock; /* find and pin the new wb */ rcu_read_lock(); @@ -504,12 +532,14 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); - return; + goto out_unlock; out_free: if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); +out_unlock: + up_read(&bdi->wb_switch_rwsem); } /** @@ -887,6 +917,9 @@ fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ +static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } +static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } + static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) @@ -2413,8 +2446,11 @@ void sync_inodes_sb(struct super_block *sb) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); + /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ + bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(bdi, &done); + bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h @@ -190,6 +190,7 @@ struct backing_dev_info { struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ + struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #else struct bdi_writeback_congested *wb_congested; #endif diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h @@ -287,7 +287,7 @@ enum req_opf { REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, - /* seset a zone write pointer */ + /* reset a zone write pointer */ REQ_OP_ZONE_RESET = 6, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h @@ -138,6 +138,7 @@ struct blk_zone_range { * @BLKRESETZONE: Reset the write pointer of the zones in the specified * sector range. The sector range must be zone aligned. * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors. + * @BLKGETNRZONES: Get the total number of zones of the device. */ #define BLKREPORTZONE _IOWR(0x12, 130, struct blk_zone_report) #define BLKRESETZONE _IOW(0x12, 131, struct blk_zone_range) diff --git a/mm/backing-dev.c b/mm/backing-dev.c @@ -689,6 +689,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi) INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); bdi->cgwb_congested_tree = RB_ROOT; mutex_init(&bdi->cgwb_release_mutex); + init_rwsem(&bdi->wb_switch_rwsem); ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); if (!ret) {