From 5bf859081f6a7575a3f7509d7a70d0a9baa88ce3 Mon Sep 17 00:00:00 2001 From: Paolo Valente Date: Thu, 6 Dec 2018 19:18:19 +0100 Subject: block, bfq: fix comments on __bfq_deactivate_entity Comments on function __bfq_deactivate_entity contains two imprecise or wrong statements: 1) The function performs the deactivation of the entity. 2) The function must be invoked only if the entity is on a service tree. This commits replaces both statements with the correct ones: 1) The functions updates sched_data and service trees for the entity, so as to represent entity as inactive (which is only part of the steps needed for the deactivation of the entity). 2) The function must be invoked on every entity being deactivated. Signed-off-by: Paolo Valente Signed-off-by: Jens Axboe --- block/bfq-wf2q.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index 63e0f12be7c9..72adbbe975d5 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -1154,15 +1154,14 @@ static void bfq_activate_requeue_entity(struct bfq_entity *entity, } /** - * __bfq_deactivate_entity - deactivate an entity from its service tree. - * @entity: the entity to deactivate. + * __bfq_deactivate_entity - update sched_data and service trees for + * entity, so as to represent entity as inactive + * @entity: the entity being deactivated. * @ins_into_idle_tree: if false, the entity will not be put into the * idle tree. * - * Deactivates an entity, independently of its previous state. Must - * be invoked only if entity is on a service tree. Extracts the entity - * from that tree, and if necessary and allowed, puts it into the idle - * tree. + * If necessary and allowed, puts entity into the idle tree. NOTE: + * entity may be on no tree if in service. */ bool __bfq_deactivate_entity(struct bfq_entity *entity, bool ins_into_idle_tree) { -- cgit v1.2.3-70-g09d2 From 6251691a92170d3a781aaf7b5f2c31b50d669809 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Mon, 14 Jan 2019 06:31:56 -0700 Subject: md: Make bio_alloc_mddev use bio_alloc_bioset bio_alloc_bioset returns a bio pointer or NULL, so we can avoid storing the returned data into a new variable. Acked-by: Guoqing Jiang Acked-by: Artur Paszkiewicz Signed-off-by: Marcos Paulo de Souza Signed-off-by: Jens Axboe --- drivers/md/md.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index fd4af4de03b4..05ffffb8b769 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -207,15 +207,10 @@ static bool create_on_open = true; struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs, struct mddev *mddev) { - struct bio *b; - if (!mddev || !bioset_initialized(&mddev->bio_set)) return bio_alloc(gfp_mask, nr_iovecs); - b = bio_alloc_bioset(gfp_mask, nr_iovecs, &mddev->bio_set); - if (!b) - return NULL; - return b; + return bio_alloc_bioset(gfp_mask, nr_iovecs, &mddev->bio_set); } EXPORT_SYMBOL_GPL(bio_alloc_mddev); -- cgit v1.2.3-70-g09d2 From c8a83a6b54d0ca078de036aafb3f6af58c1dc5eb Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 14 Jan 2019 09:48:09 +0100 Subject: nbd: Use set_blocksize() to set device blocksize NBD can update block device block size implicitely through bd_set_size(). Make it explicitely set blocksize with set_blocksize() as this behavior of bd_set_size() is going away. CC: Josef Bacik Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- drivers/block/nbd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 08696f5f00bb..7c9a949e876b 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -288,9 +288,10 @@ static void nbd_size_update(struct nbd_device *nbd) blk_queue_physical_block_size(nbd->disk->queue, config->blksize); set_capacity(nbd->disk, config->bytesize >> 9); if (bdev) { - if (bdev->bd_disk) + if (bdev->bd_disk) { bd_set_size(bdev, config->bytesize); - else + set_blocksize(bdev, config->blksize); + } else bdev->bd_invalidated = 1; bdput(bdev); } -- cgit v1.2.3-70-g09d2 From 04906b2f542c23626b0ef6219b808406f8dddbe9 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 14 Jan 2019 09:48:10 +0100 Subject: blockdev: Fix livelocks on loop device bd_set_size() updates also block device's block size. This is somewhat unexpected from its name and at this point, only blkdev_open() uses this functionality. Furthermore, this can result in changing block size under a filesystem mounted on a loop device which leads to livelocks inside __getblk_gfp() like: Sending NMI from CPU 0 to CPUs 1: NMI backtrace for cpu 1 CPU: 1 PID: 10863 Comm: syz-executor0 Not tainted 4.18.0-rc5+ #151 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:__sanitizer_cov_trace_pc+0x3f/0x50 kernel/kcov.c:106 ... Call Trace: init_page_buffers+0x3e2/0x530 fs/buffer.c:904 grow_dev_page fs/buffer.c:947 [inline] grow_buffers fs/buffer.c:1009 [inline] __getblk_slow fs/buffer.c:1036 [inline] __getblk_gfp+0x906/0xb10 fs/buffer.c:1313 __bread_gfp+0x2d/0x310 fs/buffer.c:1347 sb_bread include/linux/buffer_head.h:307 [inline] fat12_ent_bread+0x14e/0x3d0 fs/fat/fatent.c:75 fat_ent_read_block fs/fat/fatent.c:441 [inline] fat_alloc_clusters+0x8ce/0x16e0 fs/fat/fatent.c:489 fat_add_cluster+0x7a/0x150 fs/fat/inode.c:101 __fat_get_block fs/fat/inode.c:148 [inline] ... Trivial reproducer for the problem looks like: truncate -s 1G /tmp/image losetup /dev/loop0 /tmp/image mkfs.ext4 -b 1024 /dev/loop0 mount -t ext4 /dev/loop0 /mnt losetup -c /dev/loop0 l /mnt Fix the problem by moving initialization of a block device block size into a separate function and call it when needed. Thanks to Tetsuo Handa for help with debugging the problem. Reported-by: syzbot+9933e4476f365f5d5a1b@syzkaller.appspotmail.com Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- fs/block_dev.c | 28 ++++++++++++++++++---------- 1 file changed, 18 insertions(+), 10 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index c546cdce77e6..58a4c1217fa8 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -104,6 +104,20 @@ void invalidate_bdev(struct block_device *bdev) } EXPORT_SYMBOL(invalidate_bdev); +static void set_init_blocksize(struct block_device *bdev) +{ + unsigned bsize = bdev_logical_block_size(bdev); + loff_t size = i_size_read(bdev->bd_inode); + + while (bsize < PAGE_SIZE) { + if (size & bsize) + break; + bsize <<= 1; + } + bdev->bd_block_size = bsize; + bdev->bd_inode->i_blkbits = blksize_bits(bsize); +} + int set_blocksize(struct block_device *bdev, int size) { /* Size must be a power of two, and between 512 and PAGE_SIZE */ @@ -1431,18 +1445,9 @@ EXPORT_SYMBOL(check_disk_change); void bd_set_size(struct block_device *bdev, loff_t size) { - unsigned bsize = bdev_logical_block_size(bdev); - inode_lock(bdev->bd_inode); i_size_write(bdev->bd_inode, size); inode_unlock(bdev->bd_inode); - while (bsize < PAGE_SIZE) { - if (size & bsize) - break; - bsize <<= 1; - } - bdev->bd_block_size = bsize; - bdev->bd_inode->i_blkbits = blksize_bits(bsize); } EXPORT_SYMBOL(bd_set_size); @@ -1519,8 +1524,10 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret) + if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); + set_init_blocksize(bdev); + } /* * If the device is invalidated, rescan partition @@ -1555,6 +1562,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); + set_init_blocksize(bdev); } if (bdev->bd_bdi == &noop_backing_dev_info) -- cgit v1.2.3-70-g09d2 From 7809167da5c86fd6bf309b33dee7a797e263342f Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 16 Jan 2019 19:08:15 +0800 Subject: block: don't lose track of REQ_INTEGRITY flag We need to pass bio->bi_opf after bio intergrity preparing, otherwise the flag of REQ_INTEGRITY may not be set on the allocated request, then breaks block integrity. Fixes: f9afca4d367b ("blk-mq: pass in request/bio flags to queue mapping") Cc: Hannes Reinecke Cc: Keith Busch Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 3ba37b9e15e9..8f5b533764ca 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1906,7 +1906,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) { const int is_sync = op_is_sync(bio->bi_opf); const int is_flush_fua = op_is_flush(bio->bi_opf); - struct blk_mq_alloc_data data = { .flags = 0, .cmd_flags = bio->bi_opf }; + struct blk_mq_alloc_data data = { .flags = 0}; struct request *rq; struct blk_plug *plug; struct request *same_queue_rq = NULL; @@ -1928,6 +1928,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) rq_qos_throttle(q, bio); + data.cmd_flags = bio->bi_opf; rq = blk_mq_get_request(q, bio, &data); if (unlikely(!rq)) { rq_qos_cleanup(q, bio); -- cgit v1.2.3-70-g09d2 From fb8658581a150a859b654b154cefe3118ff4f1e0 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 9 Jan 2019 14:56:32 -0800 Subject: nvmet-tcp: fix uninitialized variable access If we end up in nvmet_tcp_try_recv_one with a bogus state queue receive state we will access result which is uninitialized. Initialize restult to 0 which will be considered as if no data was received by the tcp socket. Fixes: 872d26a391da ("nvmet-tcp: add NVMe over TCP target driver") Reported-by: Dan Carpenter Signed-off-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/target/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 44b37b202e39..ad0df786fe93 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1089,7 +1089,7 @@ out: static int nvmet_tcp_try_recv_one(struct nvmet_tcp_queue *queue) { - int result; + int result = 0; if (unlikely(queue->rcv_state == NVMET_TCP_RECV_ERR)) return 0; -- cgit v1.2.3-70-g09d2 From c45b1fa2433c65e44bdf48f513cb37289f3116b9 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Thu, 3 Jan 2019 09:34:39 +0800 Subject: nvme-pci: fix nvme_setup_irqs() When -ENOSPC is returned from pci_alloc_irq_vectors_affinity(), we still try to allocate multiple irq vectors again, so irq queues covers the admin queue actually. But we don't consider that, then number of the allocated irq vector may be same with sum of io_queues[HCTX_TYPE_DEFAULT] and io_queues[HCTX_TYPE_READ], this way is obviously wrong, and finally breaks nvme_pci_map_queues(), and warning from pci_irq_get_affinity() is triggered. IRQ queues should cover admin queues, this patch makes this point explicitely in nvme_calc_io_queues(). We got severl boot failure internal report on aarch64, so please consider to fix it in v4.20. Fixes: 6451fe73fa0f ("nvme: fix irq vs io_queue calculations") Signed-off-by: Ming Lei Reviewed-by: Keith Busch Tested-by: fin4478 Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fc9d17c317b8..89f9dd72135a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2041,14 +2041,18 @@ static int nvme_setup_host_mem(struct nvme_dev *dev) return ret; } +/* irq_queues covers admin queue */ static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues) { unsigned int this_w_queues = write_queues; + WARN_ON(!irq_queues); + /* - * Setup read/write queue split + * Setup read/write queue split, assign admin queue one independent + * irq vector if irq_queues is > 1. */ - if (irq_queues == 1) { + if (irq_queues <= 2) { dev->io_queues[HCTX_TYPE_DEFAULT] = 1; dev->io_queues[HCTX_TYPE_READ] = 0; return; @@ -2056,21 +2060,21 @@ static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues) /* * If 'write_queues' is set, ensure it leaves room for at least - * one read queue + * one read queue and one admin queue */ if (this_w_queues >= irq_queues) - this_w_queues = irq_queues - 1; + this_w_queues = irq_queues - 2; /* * If 'write_queues' is set to zero, reads and writes will share * a queue set. */ if (!this_w_queues) { - dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues; + dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues - 1; dev->io_queues[HCTX_TYPE_READ] = 0; } else { dev->io_queues[HCTX_TYPE_DEFAULT] = this_w_queues; - dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues; + dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues - 1; } } @@ -2095,7 +2099,7 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) this_p_queues = nr_io_queues - 1; irq_queues = 1; } else { - irq_queues = nr_io_queues - this_p_queues; + irq_queues = nr_io_queues - this_p_queues + 1; } dev->io_queues[HCTX_TYPE_POLL] = this_p_queues; @@ -2115,8 +2119,9 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues) * If we got a failure and we're down to asking for just * 1 + 1 queues, just ask for a single vector. We'll share * that between the single IO queue and the admin queue. + * Otherwise, we assign one independent vector to admin queue. */ - if (result >= 0 && irq_queues > 1) + if (irq_queues > 1) irq_queues = irq_sets[0] + irq_sets[1] + 1; result = pci_alloc_irq_vectors_affinity(pdev, irq_queues, -- cgit v1.2.3-70-g09d2 From 38197ca176fc259fa4c871d07bcf8389d044a895 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 18 Jan 2019 00:14:17 +0100 Subject: block: Cleanup license notice Remove the imprecise and sloppy: "This files is licensed under the GPL." license notice in the top level comment. 1) The file already contains a SPDX license identifier which clearly states that the license of the file is GPL V2 only 2) The notice resolves to GPL v1 or later for scanners which is just contrary to the intent of SPDX identifiers to provide clear and non ambiguous license information. Aside of that the value add of this notice is below zero, Cc: Damien Le Moal Cc: Matias Bjorling Cc: Christoph Hellwig Cc: Jens Axboe Cc: linux-block@vger.kernel.org Fixes: 6a5ac9846508 ("block: Make struct request_queue smaller for CONFIG_BLK_DEV_ZONED=n") Reviewed-by: Bart Van Assche Signed-off-by: Thomas Gleixner Signed-off-by: Jens Axboe --- block/blk-mq-debugfs-zoned.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/block/blk-mq-debugfs-zoned.c b/block/blk-mq-debugfs-zoned.c index fb2c82c351e4..038cb627c868 100644 --- a/block/blk-mq-debugfs-zoned.c +++ b/block/blk-mq-debugfs-zoned.c @@ -1,8 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2017 Western Digital Corporation or its affiliates. - * - * This file is released under the GPL. */ #include -- cgit v1.2.3-70-g09d2