From 56887cffe946bb0a90c74429fa94d6110a73119d Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 22 Feb 2021 10:48:09 +0100 Subject: [PATCH 01/20] block: Try to handle busy underlying device on discard Commit 384d87ef2c95 ("block: Do not discard buffers under a mounted filesystem") made paths issuing discard or zeroout requests to the underlying device try to grab block device in exclusive mode. If that failed we returned EBUSY to userspace. This however caused unexpected fallout in userspace where e.g. FUSE filesystems issue discard requests from userspace daemons although the device is open exclusively by the kernel. Also shrinking of logical volume by LVM issues discard requests to a device which may be claimed exclusively because there's another LV on the same PV. So to avoid these userspace regressions, fall back to invalidate_inode_pages2_range() instead of returning EBUSY to userspace and return EBUSY only of that call fails as well (meaning that there's indeed someone using the particular device range we are trying to discard). Link: https://bugzilla.kernel.org/show_bug.cgi?id=211167 Fixes: 384d87ef2c95 ("block: Do not discard buffers under a mounted filesystem") CC: stable@vger.kernel.org Signed-off-by: Jan Kara Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/block_dev.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 4aa1f88d5bf8..03166b3dea4d 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -118,13 +118,22 @@ int truncate_bdev_range(struct block_device *bdev, fmode_t mode, if (!(mode & FMODE_EXCL)) { int err = bd_prepare_to_claim(bdev, truncate_bdev_range); if (err) - return err; + goto invalidate; } truncate_inode_pages_range(bdev->bd_inode->i_mapping, lstart, lend); if (!(mode & FMODE_EXCL)) bd_abort_claiming(bdev, truncate_bdev_range); return 0; + +invalidate: + /* + * Someone else has handle exclusively open. Try invalidating instead. + * The 'end' argument is inclusive so the rounding is safe. + */ + return invalidate_inode_pages2_range(bdev->bd_inode->i_mapping, + lstart >> PAGE_SHIFT, + lend >> PAGE_SHIFT); } static void set_init_blocksize(struct block_device *bdev) From 7d365bd0bff3c0310c39ebaffc9a8458e036d666 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Fri, 5 Mar 2021 13:54:38 +0100 Subject: [PATCH 02/20] s390/dasd: fix hanging DASD driver unbind In case of an unbind of the DASD device driver the function dasd_generic_remove() is called which shuts down the device. Among others this functions removes the int_handler from the cdev. During shutdown the device cancels all outstanding IO requests and waits for completion of the clear request. Unfortunately the clear interrupt will never be received when there is no interrupt handler connected. Fix by moving the int_handler removal after the call to the state machine where no request or interrupt is outstanding. Cc: stable@vger.kernel.org Signed-off-by: Stefan Haberland Tested-by: Bjoern Walk Reviewed-by: Jan Hoeppner Signed-off-by: Jens Axboe --- drivers/s390/block/dasd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 28c04a4efa66..22805115ebc2 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -3487,8 +3487,6 @@ void dasd_generic_remove(struct ccw_device *cdev) struct dasd_device *device; struct dasd_block *block; - cdev->handler = NULL; - device = dasd_device_from_cdev(cdev); if (IS_ERR(device)) { dasd_remove_sysfs_files(cdev); @@ -3507,6 +3505,7 @@ void dasd_generic_remove(struct ccw_device *cdev) * no quite down yet. */ dasd_set_target_state(device, DASD_STATE_NEW); + cdev->handler = NULL; /* dasd_delete_device destroys the device reference. */ block = device->block; dasd_delete_device(device); From 66f669a272898feb1c69b770e1504aa2ec7723d1 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Fri, 5 Mar 2021 13:54:39 +0100 Subject: [PATCH 03/20] s390/dasd: fix hanging IO request during DASD driver unbind Prevent that an IO request is build during device shutdown initiated by a driver unbind. This request will never be able to be processed or canceled and will hang forever. This will lead also to a hanging unbind. Fix by checking not only if the device is in READY state but also check that there is no device offline initiated before building a new IO request. Fixes: e443343e509a ("s390/dasd: blk-mq conversion") Cc: # v4.14+ Signed-off-by: Stefan Haberland Tested-by: Bjoern Walk Reviewed-by: Jan Hoeppner Signed-off-by: Jens Axboe --- drivers/s390/block/dasd.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 22805115ebc2..ba9ce4e0d30a 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -3052,7 +3052,8 @@ static blk_status_t do_dasd_request(struct blk_mq_hw_ctx *hctx, basedev = block->base; spin_lock_irq(&dq->lock); - if (basedev->state < DASD_STATE_READY) { + if (basedev->state < DASD_STATE_READY || + test_bit(DASD_FLAG_OFFLINE, &basedev->flags)) { DBF_DEV_EVENT(DBF_ERR, basedev, "device not ready for request %p", req); rc = BLK_STS_IOERR; From 4f44657d74873735e93a50eb25014721a66aac19 Mon Sep 17 00:00:00 2001 From: Xunlei Pang Date: Fri, 5 Mar 2021 16:13:27 +0800 Subject: [PATCH 04/20] blk-cgroup: Fix the recursive blkg rwstat The current blkio.throttle.io_service_bytes_recursive doesn't work correctly. As an example, for the following blkcg hierarchy: (Made 1GB READ in test1, 512MB READ in test2) test / \ test1 test2 $ head -n 1 test/test1/blkio.throttle.io_service_bytes_recursive 8:0 Read 1073684480 $ head -n 1 test/test2/blkio.throttle.io_service_bytes_recursive 8:0 Read 537448448 $ head -n 1 test/blkio.throttle.io_service_bytes_recursive 8:0 Read 537448448 Clearly, above data of "test" reflects "test2" not "test1"+"test2". Do the correct summary in blkg_rwstat_recursive_sum(). Signed-off-by: Xunlei Pang Signed-off-by: Jens Axboe --- block/blk-cgroup-rwstat.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/blk-cgroup-rwstat.c b/block/blk-cgroup-rwstat.c index 85d5790ac49b..3304e841df7c 100644 --- a/block/blk-cgroup-rwstat.c +++ b/block/blk-cgroup-rwstat.c @@ -109,6 +109,7 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, lockdep_assert_held(&blkg->q->queue_lock); + memset(sum, 0, sizeof(*sum)); rcu_read_lock(); blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { struct blkg_rwstat *rwstat; @@ -122,7 +123,7 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, rwstat = (void *)pos_blkg + off; for (i = 0; i < BLKG_RWSTAT_NR; i++) - sum->cnt[i] = blkg_rwstat_read_counter(rwstat, i); + sum->cnt[i] += blkg_rwstat_read_counter(rwstat, i); } rcu_read_unlock(); } From eeb05595d22c19c8f814ff893dcf88ec277a2365 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Mon, 8 Mar 2021 12:35:01 +0000 Subject: [PATCH 05/20] umem: fix error return code in mm_pci_probe() Fix to return negative error code -ENOMEM from the blk_alloc_queue() and dma_alloc_coherent() error handling cases instead of 0, as done elsewhere in this function. Reported-by: Hulk Robot Signed-off-by: Wei Yongjun Link: https://lore.kernel.org/r/20210308123501.2573816-1-weiyongjun1@huawei.com Signed-off-by: Jens Axboe --- drivers/block/umem.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/block/umem.c b/drivers/block/umem.c index 982732dbe82e..664280f23bee 100644 --- a/drivers/block/umem.c +++ b/drivers/block/umem.c @@ -877,6 +877,7 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) if (card->mm_pages[0].desc == NULL || card->mm_pages[1].desc == NULL) { dev_printk(KERN_ERR, &card->dev->dev, "alloc failed\n"); + ret = -ENOMEM; goto failed_alloc; } reset_page(&card->mm_pages[0]); @@ -888,8 +889,10 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) spin_lock_init(&card->lock); card->queue = blk_alloc_queue(NUMA_NO_NODE); - if (!card->queue) + if (!card->queue) { + ret = -ENOMEM; goto failed_alloc; + } tasklet_init(&card->tasklet, process_page, (unsigned long)card); From faa44c69daf9ccbd5b8a1aee13e0e0d037c0be17 Mon Sep 17 00:00:00 2001 From: Damien Le Moal Date: Wed, 10 Mar 2021 18:09:19 +0900 Subject: [PATCH 06/20] block: Fix REQ_OP_ZONE_RESET_ALL handling Similarly to a single zone reset operation (REQ_OP_ZONE_RESET), execute REQ_OP_ZONE_RESET_ALL operations with REQ_SYNC set. Signed-off-by: Damien Le Moal Signed-off-by: Jens Axboe --- block/blk-zoned.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 833978c02e60..8b9f3fc5a690 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -240,7 +240,7 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, */ if (op == REQ_OP_ZONE_RESET && blkdev_allow_reset_all_zones(bdev, sector, nr_sectors)) { - bio->bi_opf = REQ_OP_ZONE_RESET_ALL; + bio->bi_opf = REQ_OP_ZONE_RESET_ALL | REQ_SYNC; break; } From df66617bfe87487190a60783d26175b65d2502ce Mon Sep 17 00:00:00 2001 From: Jia-Ju Bai Date: Tue, 9 Mar 2021 19:30:17 -0800 Subject: [PATCH 07/20] block: rsxx: fix error return code of rsxx_pci_probe() When create_singlethread_workqueue returns NULL to card->event_wq, no error return code of rsxx_pci_probe() is assigned. To fix this bug, st is assigned with -ENOMEM in this case. Fixes: 8722ff8cdbfa ("block: IBM RamSan 70/80 device driver") Reported-by: TOTE Robot Signed-off-by: Jia-Ju Bai Link: https://lore.kernel.org/r/20210310033017.4023-1-baijiaju1990@gmail.com Signed-off-by: Jens Axboe --- drivers/block/rsxx/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c index 5ac1881396af..227e1be4c6f9 100644 --- a/drivers/block/rsxx/core.c +++ b/drivers/block/rsxx/core.c @@ -871,6 +871,7 @@ static int rsxx_pci_probe(struct pci_dev *dev, card->event_wq = create_singlethread_workqueue(DRIVER_NAME"_event"); if (!card->event_wq) { dev_err(CARD_TO_DEV(card), "Failed card event setup.\n"); + st = -ENOMEM; goto failed_event_handler; } From e6ad55988b968bd4c54fd182d0bd3d7fcb969779 Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Wed, 3 Mar 2021 14:47:17 -0800 Subject: [PATCH 08/20] nvme: set max_zone_append_sectors nvme_revalidate_zones The chunk_sectors value affects max_zone_append_sectors. Signed-off-by: Chaitanya Kulkarni Reviewed-by: Keith Busch Tested-by: Kanchan Joshi Signed-off-by: Christoph Hellwig --- drivers/nvme/host/zns.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index c7e3ec561ba0..bc2f344f0ae0 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -9,7 +9,13 @@ int nvme_revalidate_zones(struct nvme_ns *ns) { - return blk_revalidate_disk_zones(ns->disk, NULL); + struct request_queue *q = ns->queue; + int ret; + + ret = blk_revalidate_disk_zones(ns->disk, NULL); + if (!ret) + blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append); + return ret; } static int nvme_set_max_append(struct nvme_ctrl *ctrl) @@ -107,7 +113,6 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf) blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q); blk_queue_max_open_zones(q, le32_to_cpu(id->mor) + 1); blk_queue_max_active_zones(q, le32_to_cpu(id->mar) + 1); - blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append); free_data: kfree(id); return status; From d95c1f4179a7f3ea8aa728ed00252a8ed0f8158f Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 26 Feb 2021 08:17:25 +0100 Subject: [PATCH 09/20] nvme: simplify error logic in nvme_validate_ns() We only should remove namespaces when we get fatal error back from the device or when the namespace IDs have changed. So instead of painfully masking out error numbers which might indicate that the error should be ignored we could use an NVME status code to indicated when the namespace should be removed. That simplifies the final logic and makes it less error-prone. Signed-off-by: Hannes Reinecke Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Daniel Wagner Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e68a8c4ac5a6..e084120c3453 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1440,7 +1440,7 @@ static int nvme_identify_ns(struct nvme_ctrl *ctrl, unsigned nsid, goto out_free_id; } - error = -ENODEV; + error = NVME_SC_INVALID_NS | NVME_SC_DNR; if ((*id)->ncap == 0) /* namespace not allocated or attached */ goto out_free_id; @@ -4038,7 +4038,7 @@ static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid) static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids) { struct nvme_id_ns *id; - int ret = -ENODEV; + int ret = NVME_SC_INVALID_NS | NVME_SC_DNR; if (test_bit(NVME_NS_DEAD, &ns->flags)) goto out; @@ -4047,7 +4047,7 @@ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_ids *ids) if (ret) goto out; - ret = -ENODEV; + ret = NVME_SC_INVALID_NS | NVME_SC_DNR; if (!nvme_ns_ids_equal(&ns->head->ids, ids)) { dev_err(ns->ctrl->device, "identifiers changed for nsid %d\n", ns->head->ns_id); @@ -4065,7 +4065,7 @@ out: * * TODO: we should probably schedule a delayed retry here. */ - if (ret && ret != -ENOMEM && !(ret > 0 && !(ret & NVME_SC_DNR))) + if (ret > 0 && (ret & NVME_SC_DNR)) nvme_ns_remove(ns); } From d3589381987ec879b03f8ce3039df57e87f05901 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 26 Feb 2021 08:17:26 +0100 Subject: [PATCH 10/20] nvme: add NVME_REQ_CANCELLED flag in nvme_cancel_request() NVME_REQ_CANCELLED is translated into -EINTR in nvme_submit_sync_cmd(), so we should be setting this flags during nvme_cancel_request() to ensure that the callers to nvme_submit_sync_cmd() will get the correct error code when the controller is reset. Signed-off-by: Hannes Reinecke Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Chao Leng Reviewed-by: Daniel Wagner Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index e084120c3453..63bb1da0861e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -380,6 +380,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved) return true; nvme_req(req)->status = NVME_SC_HOST_ABORTED_CMD; + nvme_req(req)->flags |= NVME_REQ_CANCELLED; blk_mq_complete_request(req); return true; } From 3c7aafbc8d3d4d90430dfa126847a796c3e4ecfc Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 26 Feb 2021 08:17:27 +0100 Subject: [PATCH 11/20] nvme-fc: set NVME_REQ_CANCELLED in nvme_fc_terminate_exchange() nvme_fc_terminate_exchange() is being called when exchanges are being deleted, and as such we should be setting the NVME_REQ_CANCELLED flag to have identical behaviour on all transports. Signed-off-by: Hannes Reinecke Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: James Smart Reviewed-by: Daniel Wagner Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 20dadd86e981..ef12a619daec 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2443,6 +2443,7 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved) struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl); struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(req); + op->nreq.flags |= NVME_REQ_CANCELLED; __nvme_fc_abort_op(ctrl, op); return true; } From ae3afe6308b43bbf49953101d4ba2c1c481133a8 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 26 Feb 2021 08:17:28 +0100 Subject: [PATCH 12/20] nvme-fc: return NVME_SC_HOST_ABORTED_CMD when a command has been aborted When a command has been aborted we should return NVME_SC_HOST_ABORTED_CMD to be consistent with the other transports. Signed-off-by: Hannes Reinecke Reviewed-by: Sagi Grimberg Reviewed-by: James Smart Reviewed-by: Daniel Wagner Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index ef12a619daec..97e3424c7b03 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1956,7 +1956,7 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req) sizeof(op->rsp_iu), DMA_FROM_DEVICE); if (opstate == FCPOP_STATE_ABORTED) - status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1); + status = cpu_to_le16(NVME_SC_HOST_ABORTED_CMD << 1); else if (freq->status) { status = cpu_to_le16(NVME_SC_HOST_PATH_ERROR << 1); dev_info(ctrl->ctrl.device, From f20ef34d71abc1fc56b322aaa251f90f94320140 Mon Sep 17 00:00:00 2001 From: James Smart Date: Mon, 8 Mar 2021 16:51:26 -0800 Subject: [PATCH 13/20] nvme-fc: fix racing controller reset and create association Recent patch to prevent calling __nvme_fc_abort_outstanding_ios in interrupt context results in a possible race condition. A controller reset results in errored io completions, which schedules error work. The change of error work to a work element allows it to fire after the ctrl state transition to NVME_CTRL_CONNECTING, causing any outstanding io (used to initialize the controller) to fail and cause problems for connect_work. Add a state check to only schedule error work if not in the RESETTING state. Fixes: 19fce0470f05 ("nvme-fc: avoid calling _nvme_fc_abort_outstanding_ios from interrupt context") Signed-off-by: Nigel Kirkland Signed-off-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/host/fc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 97e3424c7b03..73d073748389 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2055,7 +2055,7 @@ done: nvme_fc_complete_rq(rq); check_error: - if (terminate_assoc) + if (terminate_assoc && ctrl->ctrl.state != NVME_CTRL_RESETTING) queue_work(nvme_reset_wq, &ctrl->ioerr_work); } From 0ec84df4953bd42c6583a555773f1d4996a061eb Mon Sep 17 00:00:00 2001 From: Chaitanya Kulkarni Date: Mon, 8 Mar 2021 20:58:21 -0800 Subject: [PATCH 14/20] nvme-core: check ctrl css before setting up zns Ensure multiple Command Sets are supported before starting to setup a ZNS namespace. Signed-off-by: Chaitanya Kulkarni [hch: move the check around a bit] Signed-off-by: Christoph Hellwig --- drivers/nvme/host/core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 63bb1da0861e..82ad5eef9d0c 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4096,6 +4096,12 @@ static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) nsid); break; } + if (!nvme_multi_css(ctrl)) { + dev_warn(ctrl->device, + "command set not reported for nsid: %d\n", + ns->head->ns_id); + break; + } nvme_alloc_ns(ctrl, nsid, &ids); break; default: From abec6561fc4e0fbb19591a0b35676d8c783b5493 Mon Sep 17 00:00:00 2001 From: Lv Yunlong Date: Wed, 10 Mar 2021 21:44:13 -0800 Subject: [PATCH 15/20] nvme-rdma: Fix a use after free in nvmet_rdma_write_data_done In nvmet_rdma_write_data_done, rsp is recoverd by wc->wr_cqe and freed by nvmet_rdma_release_rsp(). But after that, pr_info() used the freed chunk's member object and could leak the freed chunk address with wc->wr_cqe by computing the offset. Signed-off-by: Lv Yunlong Signed-off-by: Christoph Hellwig --- drivers/nvme/target/rdma.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 06b6b742bb21..6c1f3ab7649c 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -802,9 +802,8 @@ static void nvmet_rdma_write_data_done(struct ib_cq *cq, struct ib_wc *wc) nvmet_req_uninit(&rsp->req); nvmet_rdma_release_rsp(rsp); if (wc->status != IB_WC_WR_FLUSH_ERR) { - pr_info("RDMA WRITE for CQE 0x%p failed with status %s (%d).\n", - wc->wr_cqe, ib_wc_status_msg(wc->status), - wc->status); + pr_info("RDMA WRITE for CQE failed with status %s (%d).\n", + ib_wc_status_msg(wc->status), wc->status); nvmet_rdma_error_comp(queue); } return; From abbb5f5929ec6c52574c430c5475c158a65c2a8c Mon Sep 17 00:00:00 2001 From: Dmitry Monakhov Date: Wed, 10 Mar 2021 12:06:41 +0000 Subject: [PATCH 16/20] nvme-pci: add the DISABLE_WRITE_ZEROES quirk for a Samsung PM1725a This adds a quirk for Samsung PM1725a drive which fixes timeouts and I/O errors due to the fact that the controller does not properly handle the Write Zeroes command, dmesg log: nvme nvme0: I/O 528 QID 10 timeout, aborting nvme nvme0: I/O 529 QID 10 timeout, aborting nvme nvme0: I/O 530 QID 10 timeout, aborting nvme nvme0: I/O 531 QID 10 timeout, aborting nvme nvme0: I/O 532 QID 10 timeout, aborting nvme nvme0: I/O 533 QID 10 timeout, aborting nvme nvme0: I/O 534 QID 10 timeout, aborting nvme nvme0: I/O 535 QID 10 timeout, aborting nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: Abort status: 0x0 nvme nvme0: I/O 528 QID 10 timeout, reset controller nvme nvme0: controller is down; will reset: CSTS=0x3, PCI_STATUS=0x10 nvme nvme0: Device not ready; aborting reset, CSTS=0x3 nvme nvme0: Device not ready; aborting reset, CSTS=0x3 nvme nvme0: Removing after probe failure status: -19 nvme0n1: detected capacity change from 6251233968 to 0 blk_update_request: I/O error, dev nvme0n1, sector 32776 op 0x1:(WRITE) flags 0x3000 phys_seg 6 prio class 0 blk_update_request: I/O error, dev nvme0n1, sector 113319936 op 0x9:(WRITE_ZEROES) flags 0x800 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 1, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113319680 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 2, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113319424 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 3, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113319168 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 4, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113318912 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 5, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113318656 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Buffer I/O error on dev nvme0n1p2, logical block 6, lost async page write blk_update_request: I/O error, dev nvme0n1, sector 113318400 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 blk_update_request: I/O error, dev nvme0n1, sector 113318144 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 blk_update_request: I/O error, dev nvme0n1, sector 113317888 op 0x9:(WRITE_ZEROES) flags 0x0 phys_seg 0 prio class 0 Signed-off-by: Dmitry Monakhov Signed-off-by: Christoph Hellwig --- drivers/nvme/host/pci.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 17ab3320d28b..7249ae74f71f 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3246,6 +3246,7 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY, }, { PCI_DEVICE(0x144d, 0xa822), /* Samsung PM1725a */ .driver_data = NVME_QUIRK_DELAY_BEFORE_CHK_RDY | + NVME_QUIRK_DISABLE_WRITE_ZEROES| NVME_QUIRK_IGNORE_DEV_SUBNQN, }, { PCI_DEVICE(0x1987, 0x5016), /* Phison E16 */ .driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, }, From a8affc03a9b375e19bc81573de0c9108317d78c7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Mar 2021 12:01:37 +0100 Subject: [PATCH 17/20] block: rename BIO_MAX_PAGES to BIO_MAX_VECS Ever since the addition of multipage bio_vecs BIO_MAX_PAGES has been horribly confusingly misnamed. Rename it to BIO_MAX_VECS to stop confusing users of the bio API. Signed-off-by: Christoph Hellwig Reviewed-by: Matthew Wilcox (Oracle) Reviewed-by: Martin K. Petersen Link: https://lore.kernel.org/r/20210311110137.1132391-2-hch@lst.de Signed-off-by: Jens Axboe --- block/bio.c | 14 +++++++------- block/blk-crypto-fallback.c | 2 +- block/blk-lib.c | 2 +- block/blk-map.c | 2 +- block/bounce.c | 6 +++--- drivers/block/drbd/drbd_int.h | 2 +- drivers/md/bcache/super.c | 2 +- drivers/md/dm-crypt.c | 8 ++++---- drivers/md/dm-writecache.c | 4 ++-- drivers/md/raid5-cache.c | 4 ++-- drivers/md/raid5-ppl.c | 2 +- drivers/nvme/target/passthru.c | 6 +++--- fs/block_dev.c | 6 +++--- fs/btrfs/extent_io.c | 2 +- fs/btrfs/scrub.c | 2 +- fs/crypto/bio.c | 6 +++--- fs/erofs/zdata.c | 2 +- fs/ext4/page-io.c | 2 +- fs/f2fs/checkpoint.c | 2 +- fs/f2fs/data.c | 4 ++-- fs/f2fs/segment.c | 2 +- fs/f2fs/segment.h | 4 ++-- fs/f2fs/super.c | 4 ++-- fs/gfs2/lops.c | 2 +- fs/iomap/buffered-io.c | 4 ++-- fs/iomap/direct-io.c | 4 ++-- fs/mpage.c | 2 +- fs/nilfs2/segbuf.c | 2 +- fs/squashfs/block.c | 2 +- fs/zonefs/super.c | 2 +- include/linux/bio.h | 4 ++-- 31 files changed, 56 insertions(+), 56 deletions(-) diff --git a/block/bio.c b/block/bio.c index a1c4d2900c7a..26b7f721cda8 100644 --- a/block/bio.c +++ b/block/bio.c @@ -33,7 +33,7 @@ static struct biovec_slab { { .nr_vecs = 16, .name = "biovec-16" }, { .nr_vecs = 64, .name = "biovec-64" }, { .nr_vecs = 128, .name = "biovec-128" }, - { .nr_vecs = BIO_MAX_PAGES, .name = "biovec-max" }, + { .nr_vecs = BIO_MAX_VECS, .name = "biovec-max" }, }; static struct biovec_slab *biovec_slab(unsigned short nr_vecs) @@ -46,7 +46,7 @@ static struct biovec_slab *biovec_slab(unsigned short nr_vecs) return &bvec_slabs[1]; case 65 ... 128: return &bvec_slabs[2]; - case 129 ... BIO_MAX_PAGES: + case 129 ... BIO_MAX_VECS: return &bvec_slabs[3]; default: BUG(); @@ -151,9 +151,9 @@ out: void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs) { - BIO_BUG_ON(nr_vecs > BIO_MAX_PAGES); + BIO_BUG_ON(nr_vecs > BIO_MAX_VECS); - if (nr_vecs == BIO_MAX_PAGES) + if (nr_vecs == BIO_MAX_VECS) mempool_free(bv, pool); else if (nr_vecs > BIO_INLINE_VECS) kmem_cache_free(biovec_slab(nr_vecs)->slab, bv); @@ -186,15 +186,15 @@ struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs, /* * Try a slab allocation first for all smaller allocations. If that * fails and __GFP_DIRECT_RECLAIM is set retry with the mempool. - * The mempool is sized to handle up to BIO_MAX_PAGES entries. + * The mempool is sized to handle up to BIO_MAX_VECS entries. */ - if (*nr_vecs < BIO_MAX_PAGES) { + if (*nr_vecs < BIO_MAX_VECS) { struct bio_vec *bvl; bvl = kmem_cache_alloc(bvs->slab, bvec_alloc_gfp(gfp_mask)); if (likely(bvl) || !(gfp_mask & __GFP_DIRECT_RECLAIM)) return bvl; - *nr_vecs = BIO_MAX_PAGES; + *nr_vecs = BIO_MAX_VECS; } return mempool_alloc(pool, gfp_mask); diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c index c176b7af56a7..c322176a1e09 100644 --- a/block/blk-crypto-fallback.c +++ b/block/blk-crypto-fallback.c @@ -219,7 +219,7 @@ static bool blk_crypto_split_bio_if_needed(struct bio **bio_ptr) bio_for_each_segment(bv, bio, iter) { num_sectors += bv.bv_len >> SECTOR_SHIFT; - if (++i == BIO_MAX_PAGES) + if (++i == BIO_MAX_VECS) break; } if (num_sectors < bio_sectors(bio)) { diff --git a/block/blk-lib.c b/block/blk-lib.c index 752f9c722062..7b256131b20b 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -296,7 +296,7 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects) { sector_t pages = DIV_ROUND_UP_SECTOR_T(nr_sects, PAGE_SIZE / 512); - return min(pages, (sector_t)BIO_MAX_PAGES); + return min(pages, (sector_t)BIO_MAX_VECS); } static int __blkdev_issue_zero_pages(struct block_device *bdev, diff --git a/block/blk-map.c b/block/blk-map.c index 369e204d14d0..1ffef782fcf2 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -249,7 +249,7 @@ static int bio_map_user_iov(struct request *rq, struct iov_iter *iter, if (!iov_iter_count(iter)) return -EINVAL; - bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_PAGES)); + bio = bio_kmalloc(gfp_mask, iov_iter_npages(iter, BIO_MAX_VECS)); if (!bio) return -ENOMEM; bio->bi_opf |= req_op(rq); diff --git a/block/bounce.c b/block/bounce.c index 87983a35079c..6c441f4f1cd4 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -229,10 +229,10 @@ static struct bio *bounce_clone_bio(struct bio *bio_src) * - The point of cloning the biovec is to produce a bio with a biovec * the caller can modify: bi_idx and bi_bvec_done should be 0. * - * - The original bio could've had more than BIO_MAX_PAGES biovecs; if + * - The original bio could've had more than BIO_MAX_VECS biovecs; if * we tried to clone the whole thing bio_alloc_bioset() would fail. * But the clone should succeed as long as the number of biovecs we - * actually need to allocate is fewer than BIO_MAX_PAGES. + * actually need to allocate is fewer than BIO_MAX_VECS. * * - Lastly, bi_vcnt should not be looked at or relied upon by code * that does not own the bio - reason being drivers don't use it for @@ -299,7 +299,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig, int sectors = 0; bio_for_each_segment(from, *bio_orig, iter) { - if (i++ < BIO_MAX_PAGES) + if (i++ < BIO_MAX_VECS) sectors += from.bv_len >> 9; if (page_to_pfn(from.bv_page) > q->limits.bounce_pfn) bounce = true; diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 7d9cc433b758..5d9181382ce1 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1324,7 +1324,7 @@ struct bm_extent { * A followup commit may allow even bigger BIO sizes, * once we thought that through. */ #define DRBD_MAX_BIO_SIZE (1U << 20) -#if DRBD_MAX_BIO_SIZE > (BIO_MAX_PAGES << PAGE_SHIFT) +#if DRBD_MAX_BIO_SIZE > (BIO_MAX_VECS << PAGE_SHIFT) #error Architecture not supported: DRBD_MAX_BIO_SIZE > BIO_MAX_SIZE #endif #define DRBD_MAX_BIO_SIZE_SAFE (1U << 12) /* Works always = 4k */ diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 71691f32959b..03e1fe4de53d 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -965,7 +965,7 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, q->limits.max_hw_sectors = UINT_MAX; q->limits.max_sectors = UINT_MAX; q->limits.max_segment_size = UINT_MAX; - q->limits.max_segments = BIO_MAX_PAGES; + q->limits.max_segments = BIO_MAX_VECS; blk_queue_max_discard_sectors(q, UINT_MAX); q->limits.discard_granularity = 512; q->limits.io_min = block_size; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 11c105ecd165..b0ab080f2567 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -229,7 +229,7 @@ static DEFINE_SPINLOCK(dm_crypt_clients_lock); static unsigned dm_crypt_clients_n = 0; static volatile unsigned long dm_crypt_pages_per_client; #define DM_CRYPT_MEMORY_PERCENT 2 -#define DM_CRYPT_MIN_PAGES_PER_CLIENT (BIO_MAX_PAGES * 16) +#define DM_CRYPT_MIN_PAGES_PER_CLIENT (BIO_MAX_VECS * 16) static void clone_init(struct dm_crypt_io *, struct bio *); static void kcryptd_queue_crypt(struct dm_crypt_io *io); @@ -3246,7 +3246,7 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv) ALIGN(sizeof(struct dm_crypt_io) + cc->dmreq_start + additional_req_size, ARCH_KMALLOC_MINALIGN); - ret = mempool_init(&cc->page_pool, BIO_MAX_PAGES, crypt_page_alloc, crypt_page_free, cc); + ret = mempool_init(&cc->page_pool, BIO_MAX_VECS, crypt_page_alloc, crypt_page_free, cc); if (ret) { ti->error = "Cannot allocate page mempool"; goto bad; @@ -3373,9 +3373,9 @@ static int crypt_map(struct dm_target *ti, struct bio *bio) /* * Check if bio is too large, split as needed. */ - if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_PAGES << PAGE_SHIFT)) && + if (unlikely(bio->bi_iter.bi_size > (BIO_MAX_VECS << PAGE_SHIFT)) && (bio_data_dir(bio) == WRITE || cc->on_disk_tag_size)) - dm_accept_partial_bio(bio, ((BIO_MAX_PAGES << PAGE_SHIFT) >> SECTOR_SHIFT)); + dm_accept_partial_bio(bio, ((BIO_MAX_VECS << PAGE_SHIFT) >> SECTOR_SHIFT)); /* * Ensure that bio is a multiple of internal sector encryption size diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 844c4be11768..4f72b6f66c3a 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -1892,10 +1892,10 @@ restart: list_add(&g->lru, &wbl.list); wbl.size++; g->write_in_progress = true; - g->wc_list_contiguous = BIO_MAX_PAGES; + g->wc_list_contiguous = BIO_MAX_VECS; f = g; e->wc_list_contiguous++; - if (unlikely(e->wc_list_contiguous == BIO_MAX_PAGES)) { + if (unlikely(e->wc_list_contiguous == BIO_MAX_VECS)) { if (unlikely(wc->writeback_all)) { next_node = rb_next(&f->rb_node); if (likely(next_node)) diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 4337ae0e6af2..0b5dcaabbc15 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -735,7 +735,7 @@ static void r5l_submit_current_io(struct r5l_log *log) static struct bio *r5l_bio_alloc(struct r5l_log *log) { - struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, &log->bs); + struct bio *bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS, &log->bs); bio_set_op_attrs(bio, REQ_OP_WRITE, 0); bio_set_dev(bio, log->rdev->bdev); @@ -1634,7 +1634,7 @@ static int r5l_recovery_allocate_ra_pool(struct r5l_log *log, { struct page *page; - ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_PAGES, &log->bs); + ctx->ra_bio = bio_alloc_bioset(GFP_KERNEL, BIO_MAX_VECS, &log->bs); if (!ctx->ra_bio) return -ENOMEM; diff --git a/drivers/md/raid5-ppl.c b/drivers/md/raid5-ppl.c index e8c118e05dfd..3ddc2aa0b530 100644 --- a/drivers/md/raid5-ppl.c +++ b/drivers/md/raid5-ppl.c @@ -496,7 +496,7 @@ static void ppl_submit_iounit(struct ppl_io_unit *io) if (!bio_add_page(bio, sh->ppl_page, PAGE_SIZE, 0)) { struct bio *prev = bio; - bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_PAGES, + bio = bio_alloc_bioset(GFP_NOIO, BIO_MAX_VECS, &ppl_conf->bs); bio->bi_opf = prev->bi_opf; bio->bi_write_hint = prev->bi_write_hint; diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 26c587ccd152..2798944899b7 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -50,9 +50,9 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req) /* * nvmet_passthru_map_sg is limitted to using a single bio so limit - * the mdts based on BIO_MAX_PAGES as well + * the mdts based on BIO_MAX_VECS as well */ - max_hw_sectors = min_not_zero(BIO_MAX_PAGES << (PAGE_SHIFT - 9), + max_hw_sectors = min_not_zero(BIO_MAX_VECS << (PAGE_SHIFT - 9), max_hw_sectors); page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12; @@ -191,7 +191,7 @@ static int nvmet_passthru_map_sg(struct nvmet_req *req, struct request *rq) struct bio *bio; int i; - if (req->sg_cnt > BIO_MAX_PAGES) + if (req->sg_cnt > BIO_MAX_VECS) return -EINVAL; if (req->transfer_len <= NVMET_MAX_INLINE_DATA_LEN) { diff --git a/fs/block_dev.c b/fs/block_dev.c index 03166b3dea4d..92ed7d5df677 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -432,7 +432,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; - nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_PAGES); + nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS); if (!nr_pages) { bool polled = false; @@ -500,8 +500,8 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) if (!iov_iter_count(iter)) return 0; - nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_PAGES + 1); - if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES) + nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1); + if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS) return __blkdev_direct_IO_simple(iocb, iter, nr_pages); return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages)); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4dfb3ead1175..db8cb98c020c 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3048,7 +3048,7 @@ struct bio *btrfs_bio_alloc(u64 first_byte) { struct bio *bio; - bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &btrfs_bioset); + bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_VECS, &btrfs_bioset); bio->bi_iter.bi_sector = first_byte >> 9; btrfs_io_bio_init(btrfs_io_bio(bio)); return bio; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 582df11d298a..6daa4309c974 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -1428,7 +1428,7 @@ static void scrub_recheck_block_on_raid56(struct btrfs_fs_info *fs_info, if (!first_page->dev->bdev) goto out; - bio = btrfs_io_bio_alloc(BIO_MAX_PAGES); + bio = btrfs_io_bio_alloc(BIO_MAX_VECS); bio_set_dev(bio, first_page->dev->bdev); for (page_num = 0; page_num < sblock->page_count; page_num++) { diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c index b048a0e38516..68a2de6b5a9b 100644 --- a/fs/crypto/bio.c +++ b/fs/crypto/bio.c @@ -52,7 +52,7 @@ static int fscrypt_zeroout_range_inline_crypt(const struct inode *inode, int num_pages = 0; /* This always succeeds since __GFP_DIRECT_RECLAIM is set. */ - bio = bio_alloc(GFP_NOFS, BIO_MAX_PAGES); + bio = bio_alloc(GFP_NOFS, BIO_MAX_VECS); while (len) { unsigned int blocks_this_page = min(len, blocks_per_page); @@ -74,7 +74,7 @@ static int fscrypt_zeroout_range_inline_crypt(const struct inode *inode, len -= blocks_this_page; lblk += blocks_this_page; pblk += blocks_this_page; - if (num_pages == BIO_MAX_PAGES || !len || + if (num_pages == BIO_MAX_VECS || !len || !fscrypt_mergeable_bio(bio, inode, lblk)) { err = submit_bio_wait(bio); if (err) @@ -126,7 +126,7 @@ int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk, return fscrypt_zeroout_range_inline_crypt(inode, lblk, pblk, len); - BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_PAGES); + BUILD_BUG_ON(ARRAY_SIZE(pages) > BIO_MAX_VECS); nr_pages = min_t(unsigned int, ARRAY_SIZE(pages), (len + blocks_per_page - 1) >> blocks_per_page_bits); diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 6cb356c4217b..3851e1a64f73 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1235,7 +1235,7 @@ submit_bio_retry: } if (!bio) { - bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); + bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS); bio->bi_end_io = z_erofs_decompressqueue_endio; bio_set_dev(bio, sb->s_bdev); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 03a44a0de86a..f038d578d8d8 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -398,7 +398,7 @@ static void io_submit_init_bio(struct ext4_io_submit *io, * bio_alloc will _always_ be able to allocate a bio if * __GFP_DIRECT_RECLAIM is set, see comments for bio_alloc_bioset(). */ - bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); + bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS); fscrypt_set_bio_crypt_ctx_bh(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index 174a0819ad96..be5415a0dbbc 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -292,7 +292,7 @@ void f2fs_ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index) f2fs_put_page(page, 0); if (readahead) - f2fs_ra_meta_pages(sbi, index, BIO_MAX_PAGES, META_POR, true); + f2fs_ra_meta_pages(sbi, index, BIO_MAX_VECS, META_POR, true); } static int __f2fs_write_meta_page(struct page *page, diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 7c95818639a6..4e5257c763d0 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -857,7 +857,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio) f2fs_submit_merged_ipu_write(fio->sbi, &bio, NULL); alloc_new: if (!bio) { - bio = __bio_alloc(fio, BIO_MAX_PAGES); + bio = __bio_alloc(fio, BIO_MAX_VECS); __attach_io_flag(fio); f2fs_set_bio_crypt_ctx(bio, fio->page->mapping->host, fio->page->index, fio, GFP_NOIO); @@ -932,7 +932,7 @@ alloc_new: fio->retry = true; goto skip; } - io->bio = __bio_alloc(fio, BIO_MAX_PAGES); + io->bio = __bio_alloc(fio, BIO_MAX_VECS); f2fs_set_bio_crypt_ctx(io->bio, fio->page->mapping->host, bio_page->index, fio, GFP_NOIO); io->fio = *fio; diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 993004f06a77..c2866561263e 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -4381,7 +4381,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi) block_t total_node_blocks = 0; do { - readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES, + readed = f2fs_ra_meta_pages(sbi, start_blk, BIO_MAX_VECS, META_SIT, true); start = start_blk * sit_i->sents_per_block; diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 229814b4f4a6..e9a7a637d688 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -851,7 +851,7 @@ static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type) else if (type == NODE) return 8 * sbi->blocks_per_seg; else if (type == META) - return 8 * BIO_MAX_PAGES; + return 8 * BIO_MAX_VECS; else return 0; } @@ -868,7 +868,7 @@ static inline long nr_pages_to_write(struct f2fs_sb_info *sbi, int type, return 0; nr_to_write = wbc->nr_to_write; - desired = BIO_MAX_PAGES; + desired = BIO_MAX_VECS; if (type == NODE) desired <<= 1; diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c index 7069793752f1..82592b19b4e0 100644 --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -753,9 +753,9 @@ static int parse_options(struct super_block *sb, char *options, bool is_remount) case Opt_io_size_bits: if (args->from && match_int(args, &arg)) return -EINVAL; - if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_PAGES)) { + if (arg <= 0 || arg > __ilog2_u32(BIO_MAX_VECS)) { f2fs_warn(sbi, "Not support %d, larger than %d", - 1 << arg, BIO_MAX_PAGES); + 1 << arg, BIO_MAX_VECS); return -EINVAL; } F2FS_OPTION(sbi).write_io_size_bits = arg; diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index dc1b93a877c6..a82f4747aa8d 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -267,7 +267,7 @@ static struct bio *gfs2_log_alloc_bio(struct gfs2_sbd *sdp, u64 blkno, bio_end_io_t *end_io) { struct super_block *sb = sdp->sd_vfs; - struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); + struct bio *bio = bio_alloc(GFP_NOIO, BIO_MAX_VECS); bio->bi_iter.bi_sector = blkno << sdp->sd_fsb2bb_shift; bio_set_dev(bio, sb->s_bdev); diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 7ffcd7ef33d4..414769a6ad11 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -1221,7 +1221,7 @@ iomap_alloc_ioend(struct inode *inode, struct iomap_writepage_ctx *wpc, struct iomap_ioend *ioend; struct bio *bio; - bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &iomap_ioend_bioset); + bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_VECS, &iomap_ioend_bioset); bio_set_dev(bio, wpc->iomap.bdev); bio->bi_iter.bi_sector = sector; bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc); @@ -1252,7 +1252,7 @@ iomap_chain_bio(struct bio *prev) { struct bio *new; - new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES); + new = bio_alloc(GFP_NOFS, BIO_MAX_VECS); bio_copy_dev(new, prev);/* also copies over blkcg information */ new->bi_iter.bi_sector = bio_end_sector(prev); new->bi_opf = prev->bi_opf; diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index e2c4991833b8..bdd0d89bbf0a 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -296,7 +296,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, */ bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua); - nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_PAGES); + nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS); do { size_t n; if (dio->error) { @@ -338,7 +338,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, copied += n; nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, - BIO_MAX_PAGES); + BIO_MAX_VECS); iomap_dio_submit_bio(dio, iomap, bio, pos); pos += n; } while (nr_pages); diff --git a/fs/mpage.c b/fs/mpage.c index 961234d68779..334e7d09aa65 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -616,7 +616,7 @@ alloc_new: goto out; } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), - BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH); + BIO_MAX_VECS, GFP_NOFS|__GFP_HIGH); if (bio == NULL) goto confused; diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 1e75417bfe6e..56872e93823d 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -399,7 +399,7 @@ static void nilfs_segbuf_prepare_write(struct nilfs_segment_buffer *segbuf, { wi->bio = NULL; wi->rest_blocks = segbuf->sb_sum.nblocks; - wi->max_pages = BIO_MAX_PAGES; + wi->max_pages = BIO_MAX_VECS; wi->nr_vecs = min(wi->max_pages, wi->rest_blocks); wi->start = wi->end = 0; wi->blocknr = segbuf->sb_pseg_start; diff --git a/fs/squashfs/block.c b/fs/squashfs/block.c index 45f44425d856..b9e87ebb1060 100644 --- a/fs/squashfs/block.c +++ b/fs/squashfs/block.c @@ -87,7 +87,7 @@ static int squashfs_bio_read(struct super_block *sb, u64 index, int length, int error, i; struct bio *bio; - if (page_count <= BIO_MAX_PAGES) + if (page_count <= BIO_MAX_VECS) bio = bio_alloc(GFP_NOIO, page_count); else bio = bio_kmalloc(GFP_NOIO, page_count); diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c index b6ff4a21abac..0fe76f376dee 100644 --- a/fs/zonefs/super.c +++ b/fs/zonefs/super.c @@ -684,7 +684,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize); iov_iter_truncate(from, max); - nr_pages = iov_iter_npages(from, BIO_MAX_PAGES); + nr_pages = iov_iter_npages(from, BIO_MAX_VECS); if (!nr_pages) return 0; diff --git a/include/linux/bio.h b/include/linux/bio.h index 983ed2fe7c85..d0246c92a6e8 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -20,11 +20,11 @@ #define BIO_BUG_ON #endif -#define BIO_MAX_PAGES 256U +#define BIO_MAX_VECS 256U static inline unsigned int bio_max_segs(unsigned int nr_segs) { - return min(nr_segs, BIO_MAX_PAGES); + return min(nr_segs, BIO_MAX_VECS); } #define bio_prio(bio) (bio)->bi_ioprio From 9ec491447b90ad6a4056a9656b13f0b3a1e83043 Mon Sep 17 00:00:00 2001 From: Daniel Wagner Date: Thu, 11 Mar 2021 16:19:17 +0100 Subject: [PATCH 18/20] block: Suppress uevent for hidden device when removed register_disk() suppress uevents for devices with the GENHD_FL_HIDDEN but enables uevents at the end again in order to announce disk after possible partitions are created. When the device is removed the uevents are still on and user land sees 'remove' messages for devices which were never 'add'ed to the system. KERNEL[95481.571887] remove /devices/virtual/nvme-fabrics/ctl/nvme5/nvme0c5n1 (block) Let's suppress the uevents for GENHD_FL_HIDDEN by not enabling the uevents at all. Signed-off-by: Daniel Wagner Reviewed-by: Christoph Hellwig Reviewed-by: Martin Wilck Link: https://lore.kernel.org/r/20210311151917.136091-1-dwagner@suse.de Signed-off-by: Jens Axboe --- block/genhd.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/block/genhd.c b/block/genhd.c index c55e8f0fced1..8c8f543572e6 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -534,10 +534,8 @@ static void register_disk(struct device *parent, struct gendisk *disk, kobject_create_and_add("holders", &ddev->kobj); disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); - if (disk->flags & GENHD_FL_HIDDEN) { - dev_set_uevent_suppress(ddev, 0); + if (disk->flags & GENHD_FL_HIDDEN) return; - } disk_scan_partitions(disk); From e5113505904ea1c1c0e1f92c1cfa91fbf4da1694 Mon Sep 17 00:00:00 2001 From: Shin'ichiro Kawasaki Date: Thu, 11 Mar 2021 16:25:46 +0900 Subject: [PATCH 19/20] block: Discard page cache of zone reset target range When zone reset ioctl and data read race for a same zone on zoned block devices, the data read leaves stale page cache even though the zone reset ioctl zero clears all the zone data on the device. To avoid non-zero data read from the stale page cache after zone reset, discard page cache of reset target zones in blkdev_zone_mgmt_ioctl(). Introduce the helper function blkdev_truncate_zone_range() to discard the page cache. Ensure the page cache discarded by calling the helper function before and after zone reset in same manner as fallocate does. This patch can be applied back to the stable kernel version v5.10.y. Rework is needed for older stable kernels. Signed-off-by: Shin'ichiro Kawasaki Fixes: 3ed05a987e0f ("blk-zoned: implement ioctls") Cc: # 5.10+ Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Link: https://lore.kernel.org/r/20210311072546.678999-1-shinichiro.kawasaki@wdc.com Signed-off-by: Jens Axboe --- block/blk-zoned.c | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 8b9f3fc5a690..c0276b42d9fb 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -318,6 +318,22 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, return 0; } +static int blkdev_truncate_zone_range(struct block_device *bdev, fmode_t mode, + const struct blk_zone_range *zrange) +{ + loff_t start, end; + + if (zrange->sector + zrange->nr_sectors <= zrange->sector || + zrange->sector + zrange->nr_sectors > get_capacity(bdev->bd_disk)) + /* Out of range */ + return -EINVAL; + + start = zrange->sector << SECTOR_SHIFT; + end = ((zrange->sector + zrange->nr_sectors) << SECTOR_SHIFT) - 1; + + return truncate_bdev_range(bdev, mode, start, end); +} + /* * BLKRESETZONE, BLKOPENZONE, BLKCLOSEZONE and BLKFINISHZONE ioctl processing. * Called from blkdev_ioctl. @@ -329,6 +345,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, struct request_queue *q; struct blk_zone_range zrange; enum req_opf op; + int ret; if (!argp) return -EINVAL; @@ -352,6 +369,11 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, switch (cmd) { case BLKRESETZONE: op = REQ_OP_ZONE_RESET; + + /* Invalidate the page cache, including dirty pages. */ + ret = blkdev_truncate_zone_range(bdev, mode, &zrange); + if (ret) + return ret; break; case BLKOPENZONE: op = REQ_OP_ZONE_OPEN; @@ -366,8 +388,20 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, return -ENOTTY; } - return blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors, - GFP_KERNEL); + ret = blkdev_zone_mgmt(bdev, op, zrange.sector, zrange.nr_sectors, + GFP_KERNEL); + + /* + * Invalidate the page cache again for zone reset: writes can only be + * direct for zoned devices so concurrent writes would not add any page + * to the page cache after/during reset. The page cache may be filled + * again due to concurrent reads though and dropping the pages for + * these is fine. + */ + if (!ret && cmd == BLKRESETZONE) + ret = blkdev_truncate_zone_range(bdev, mode, &zrange); + + return ret; } static inline unsigned long *blk_alloc_zone_bitmap(int node, From f4f9fc29e56b6fa9d7fa65ec51d3c82aff99c99b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 12 Mar 2021 20:55:36 +0100 Subject: [PATCH 20/20] nvme: fix the nsid value to print in nvme_validate_or_alloc_ns ns can be NULL at this point, and my move of the check from the original patch by Chaitanya broke this. Fixes: 0ec84df4953b ("nvme-core: check ctrl css before setting up zns") Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 82ad5eef9d0c..a5653892d773 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -4099,7 +4099,7 @@ static void nvme_validate_or_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) if (!nvme_multi_css(ctrl)) { dev_warn(ctrl->device, "command set not reported for nsid: %d\n", - ns->head->ns_id); + nsid); break; } nvme_alloc_ns(ctrl, nsid, &ids);