From 8b9433eb4de3c26a9226c981c283f9f4896ae030 Mon Sep 17 00:00:00 2001 From: Ernesto A. Fernández Date: Mon, 8 Oct 2018 20:58:23 -0300 Subject: direct-io: allow direct writes to empty inodes On a DIO_SKIP_HOLES filesystem, the ->get_block() method is currently not allowed to create blocks for an empty inode. This confusion comes from trying to bit shift a negative number, so check the size of the inode first. The problem is most visible for hfsplus, because the fallback to buffered I/O doesn't happen and the write fails with EIO. This is in part the fault of the module, because it gives a wrong return value on ->get_block(); that will be fixed in a separate patch. Reviewed-by: Jeff Moyer Reviewed-by: Jan Kara Signed-off-by: Ernesto A. Fernández Signed-off-by: Jens Axboe --- fs/direct-io.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/direct-io.c b/fs/direct-io.c index dbc1a1f080ce..ec2fb6fe6d37 100644 --- 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; } -- cgit v1.2.3 From 698cef173983b086977e633e46476e0f925ca01e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 22 Jan 2019 16:20:17 +0800 Subject: block: cover another queue enter recursion via BIO_QUEUE_ENTERED Except for blk_queue_split(), bio_split() is used for splitting bio too, then the remained bio is often resubmit to queue via generic_make_request(). So the same queue enter recursion exits in this case too. Unfortunatley commit cd4a4ae4683dc2 doesn't help this case. This patch covers the above case by setting BIO_QUEUE_ENTERED before calling q->make_request_fn. In theory the per-bio flag is used to simulate one stack variable, it is just fine to clear it after q->make_request_fn is returned. Especially the same bio can't be submitted from another context. Fixes: cd4a4ae4683dc2 ("block: don't use blocking queue entered for recursive bio submits") Cc: Tetsuo Handa Cc: NeilBrown Reviewed-by: Mike Snitzer Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-core.c | 11 +++++++++++ block/blk-merge.c | 10 ---------- 2 files changed, 11 insertions(+), 10 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 3c5f61ceeb67..1ccec27d20c3 100644 --- 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 index 71e9ac03f621..d79a22f111d1 100644 --- 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); -- cgit v1.2.3 From 7fc5854f8c6efae9e7624970ab49a1eac2faefb1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 12 Dec 2017 08:38:30 -0800 Subject: writeback: synchronize sync(2) against cgroup writeback membership switches sync_inodes_sb() can race against cgwb (cgroup writeback) membership switches and fail to writeback some inodes. For example, if an inode switches to another wb while sync_inodes_sb() is in progress, the new wb might not be visible to bdi_split_work_to_wbs() at all or the inode might jump from a wb which hasn't issued writebacks yet to one which already has. This patch adds backing_dev_info->wb_switch_rwsem to synchronize cgwb switch path against sync_inodes_sb() so that sync_inodes_sb() is guaranteed to see all the target wbs and inodes can't jump wbs to escape syncing. v2: Fixed misplaced rwsem init. Spotted by Jiufei. Signed-off-by: Tejun Heo Reported-by: Jiufei Xue Link: http://lkml.kernel.org/r/dc694ae2-f07f-61e1-7097-7c8411cee12d@gmail.com Acked-by: Jan Kara Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 40 ++++++++++++++++++++++++++++++++++++++-- include/linux/backing-dev-defs.h | 1 + mm/backing-dev.c | 1 + 3 files changed, 40 insertions(+), 2 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index b40168fcc94a..36855c1f8daf 100644 --- 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; @@ -343,6 +354,12 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct page *page; 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 @@ -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 index c31157135598..07e02d6df5ad 100644 --- 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/mm/backing-dev.c b/mm/backing-dev.c index 8a8bb8796c6c..72e6d0c55cfa 100644 --- 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) { -- cgit v1.2.3 From 4c174e6366746ae8d49f9cc409f728eebb7a9ac9 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 8 Jan 2019 00:53:22 -0800 Subject: nvme-rdma: fix timeout handler Currently, we have several problems with the timeout handler: 1. If we timeout on the controller establishment flow, we will hang because we don't execute the error recovery (and we shouldn't because the create_ctrl flow needs to fail and cleanup on its own) 2. We might also hang if we get a disconnet on a queue while the controller is already deleting. This racy flow can cause the controller disable/shutdown admin command to hang. We cannot complete a timed out request from the timeout handler without mutual exclusion from the teardown flow (e.g. nvme_rdma_error_recovery_work). So we serialize it in the timeout handler and teardown io and admin queues to guarantee that no one races with us from completing the request. Reported-by: Jaesoo Lee Reviewed-by: Christoph Hellwig Signed-off-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/rdma.c | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 0a2fd2949ad7..4101961feb44 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1689,18 +1689,28 @@ 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, -- cgit v1.2.3 From 39d57757467b6346bbc1a1f416e3057f681cf903 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Tue, 8 Jan 2019 01:01:30 -0800 Subject: nvme-tcp: fix timeout handler Currently, we have several problems with the timeout handler: 1. If we timeout on the controller establishment flow, we will hang because we don't execute the error recovery (and we shouldn't because the create_ctrl flow needs to fail and cleanup on its own) 2. We might also hang if we get a disconnet on a queue while the controller is already deleting. This racy flow can cause the controller disable/shutdown admin command to hang. We cannot complete a timed out request from the timeout handler without mutual exclusion from the teardown flow (e.g. nvme_rdma_error_recovery_work). So we serialize it in the timeout handler and teardown io and admin queues to guarantee that no one races with us from completing the request. Reviewed-by: Christoph Hellwig Signed-off-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/tcp.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 265a0543b381..5f0a00425242 100644 --- 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; -- cgit v1.2.3 From b1064d3e337b4d0b67d641b5f771187d8f1f027d Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Fri, 18 Jan 2019 16:43:24 -0800 Subject: nvme-rdma: rework queue maps handling If the device supports less queues than provided (if the device has less completion vectors), we might hit a bug due to the fact that we ignore that in nvme_rdma_map_queues (we override the maps nr_queues with user opts). Instead, keep track of how many default/read/poll queues we actually allocated (rather than asked by the user) and use that to assign our queue mappings. Fixes: b65bb777ef22 (" nvme-rdma: support separate queue maps for read and write") Reported-by: Saleem, Shiraz Reviewed-by: Christoph Hellwig Signed-off-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/rdma.c | 38 +++++++++++++++++++++++++------------- 1 file changed, 25 insertions(+), 13 deletions(-) diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 4101961feb44..52abc3a6de12 100644 --- 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) @@ -1789,17 +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], @@ -1809,12 +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; -- cgit v1.2.3 From 5cbab6303b4791a3e6713dfe2c5fda6a867f9adc Mon Sep 17 00:00:00 2001 From: Raju Rangoju Date: Thu, 3 Jan 2019 23:05:31 +0530 Subject: nvmet-rdma: fix null dereference under heavy load Under heavy load if we don't have any pre-allocated rsps left, we dynamically allocate a rsp, but we are not actually allocating memory for nvme_completion (rsp->req.rsp). In such a case, accessing pointer fields (req->rsp->status) in nvmet_req_init() will result in crash. To fix this, allocate the memory for nvme_completion by calling nvmet_rdma_alloc_rsp() Fixes: 8407879c("nvmet-rdma:fix possible bogus dereference under heavy load") Cc: Reviewed-by: Max Gurtovoy Reviewed-by: Christoph Hellwig Signed-off-by: Raju Rangoju Signed-off-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/target/rdma.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index a8d23eb80192..a884e3a0e8af 100644 --- 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; } -- cgit v1.2.3 From 78a61cd42a64f3587862b372a79e1d6aaf131fd7 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 9 Jan 2019 09:45:15 +0100 Subject: nvme-multipath: drop optimization for static ANA group IDs Bit 6 in the ANACAP field is used to indicate that the ANA group ID doesn't change while the namespace is attached to the controller. There is an optimisation in the code to only allocate space for the ANA group header, as the namespace list won't change and hence would not need to be refreshed. However, this optimisation was never carried over to the actual workflow, which always assumes that the buffer is large enough to hold the ANA header _and_ the namespace list. So drop this optimisation and always allocate enough space. Reviewed-by: Christoph Hellwig Signed-off-by: Hannes Reinecke Signed-off-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/multipath.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index df4b3a6db51b..b9fff3b8ed1b 100644 --- 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, -- cgit v1.2.3 From 1c26010c5e1b9ad22a77968428b68150d27ae65f Mon Sep 17 00:00:00 2001 From: Jianchao Wang Date: Thu, 24 Jan 2019 18:28:55 +0800 Subject: blk-mq: fix the cmd_flag_name array Swap REQ_NOWAIT and REQ_NOUNMAP and add REQ_HIPRI. Acked-by: Jeff Moyer Signed-off-by: Jianchao Wang Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 90d68760af08..f8120832ca7b 100644 --- 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 -- cgit v1.2.3 From c83f536a87d9dd6d6bf989c0b0882459a902eb07 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Wed, 23 Jan 2019 11:05:57 -0800 Subject: blk-wbt: Declare local functions static This patch avoids that sparse reports the following warnings: CHECK block/blk-wbt.c block/blk-wbt.c:600:6: warning: symbol 'wbt_issue' was not declared. Should it be static? block/blk-wbt.c:620:6: warning: symbol 'wbt_requeue' was not declared. Should it be static? CC block/blk-wbt.o block/blk-wbt.c:600:6: warning: no previous prototype for wbt_issue [-Wmissing-prototypes] void wbt_issue(struct rq_qos *rqos, struct request *rq) ^~~~~~~~~ block/blk-wbt.c:620:6: warning: no previous prototype for wbt_requeue [-Wmissing-prototypes] void wbt_requeue(struct rq_qos *rqos, struct request *rq) ^~~~~~~~~~~ Reviewed-by: Chaitanya Kulkarni Signed-off-by: Bart Van Assche Signed-off-by: Jens Axboe --- block/blk-wbt.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index f0c56649775f..fd166fbb0f65 100644 --- 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)) -- cgit v1.2.3 From 745815f955f65f22d378d69822da11043d00aaff Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 24 Jan 2019 18:20:13 +0900 Subject: uapi: fix ioctl documentation The description of the BLKGETNRZONES zoned block device ioctl was not added as a comment together with this ioctl definition in commit 65e4e3eee83d7 ("block: Introduce BLKGETNRZONES ioctl"). Add its description here. Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/uapi/linux/blkzoned.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h index 6fa38d001d84..498eec813494 100644 --- 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) -- cgit v1.2.3 From 8367de2c99a13d35960a51d6084631c883e93a4d Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Thu, 24 Jan 2019 18:20:14 +0900 Subject: block: Fix comment typo Fix typo in REQ_OP_ZONE_RESET description. Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 5c7e7f859a24..d66bf5f32610 100644 --- 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, -- cgit v1.2.3