- 20 Dec, 2023 2 commits
-
-
Christoph Hellwig authored
virtblk_revalidate_zones is called unconditionally from virtblk_config_changed_work from the virtio config_changed callback. virtblk_revalidate_zones is a bit odd in that it re-clears the zoned state for host aware or non-zoned devices, which isn't needed unless the zoned mode changed - but a zone mode change to a host managed model isn't handled at all, and virtio_blk also doesn't handle any other config change except for a capacity change is handled (and even if it was the upper layers above virtio_blk wouldn't handle it very well). But even the useful case of a size change that would add or remove zones isn't handled properly as blk_revalidate_disk_zones expects the device capacity to cover all zones, but the capacity is only updated after virtblk_revalidate_zones. As this code appears to be entirely untested and is getting in the way remove it for now, but it can be readded in a fixed version with proper test coverage if needed. Fixes: 95bfec41 ("virtio-blk: add support for zoned block devices") Fixes: f1ba4e67 ("virtio-blk: fix to match virtio spec") Signed-off-by:
Christoph Hellwig <hch@lst.de> Reviewed-by:
Damien Le Moal <dlemoal@kernel.org> Reviewed-by:
Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by:
Martin K. Petersen <martin.petersen@oracle.com> Link: https://lore.kernel.org/r/20231217165359.604246-3-hch@lst.deSigned-off-by:
Jens Axboe <axboe@kernel.dk>
-
Christoph Hellwig authored
Move reading and checking the zoned model from virtblk_probe_zoned_device into the caller, leaving only the code to perform the actual setup for host managed zoned devices in virtblk_probe_zoned_device. This allows to share the model reading and sharing between builds with and without CONFIG_BLK_DEV_ZONED, and improve it for the !CONFIG_BLK_DEV_ZONED case. Signed-off-by:
-
- 19 Dec, 2023 5 commits
-
-
Jens Axboe authored
Merge tag 'md-next-20231219' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.8/block Pull MD updates from Song: "1. Remove deprecated flavors, by Song Liu; 2. raid1 read error check support, by Li Nan; 3. Better handle events off-by-1 case, by Alex Lyakas." * tag 'md-next-20231219' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md: md: Remove deprecated CONFIG_MD_FAULTY md: Remove deprecated CONFIG_MD_MULTIPATH md: Remove deprecated CONFIG_MD_LINEAR md/raid1: support read error check md: factor out a helper exceed_read_errors() to check read_errors md: Whenassemble the array, consult the superblock of the freshest device md/raid1: remove unnecessary null checking
-
Song Liu authored
md-faulty has been marked as deprecated for 2.5 years. Remove it. Cc: Christoph Hellwig <hch@lst.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Neil Brown <neilb@suse.de> Cc: Guoqing Jiang <guoqing.jiang@linux.dev> Cc: Mateusz Grzonka <mateusz.grzonka@intel.com> Cc: Jes Sorensen <jes@trained-monkey.org> Signed-off-by:
Song Liu <song@kernel.org> Reviewed-by:
Hannes Reinecke <hare@suse.de> Link: https://lore.kernel.org/r/20231214222107.2016042-4-song@kernel.org
-
Song Liu authored
md-multipath has been marked as deprecated for 2.5 years. Remove it. Cc: Christoph Hellwig <hch@lst.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Neil Brown <neilb@suse.de> Cc: Guoqing Jiang <guoqing.jiang@linux.dev> Cc: Mateusz Grzonka <mateusz.grzonka@intel.com> Cc: Jes Sorensen <jes@trained-monkey.org> Signed-off-by:
-
Song Liu authored
md-linear has been marked as deprecated for 2.5 years. Remove it. Cc: Christoph Hellwig <hch@lst.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: Neil Brown <neilb@suse.de> Cc: Guoqing Jiang <guoqing.jiang@linux.dev> Cc: Mateusz Grzonka <mateusz.grzonka@intel.com> Cc: Jes Sorensen <jes@trained-monkey.org> Signed-off-by:
-
Li Nan authored
'first_minor' represents the starting minor number of disks, and 'minors' represents the number of partitions in the device. Neither of them can be greater than MINORMASK + 1. Commit e338924b ("block: check minor range in device_add_disk()") only added the check of 'first_minor + minors'. However, their sum might be less than MINORMASK but their values are wrong. Complete the checks now. Fixes: e338924b ("block: check minor range in device_add_disk()") Signed-off-by:
Li Nan <linan122@huawei.com> Reviewed-by:
-
- 18 Dec, 2023 1 commit
-
-
Kundan Kumar authored
Even if BLK_CGROUP is enabled, it does not work for passthrough io. So skip setting up blkg for passthrough bio. Reduced processing gives ~5% hike in peak-performance workload. Signed-off-by:
Kundan Kumar <kundan.kumar@samsung.com> Signed-off-by:
Kanchan Joshi <joshi.k@samsung.com> Reviewed-by:
Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20231218152722.1768-1-joshi.k@samsung.comSigned-off-by:
-
- 15 Dec, 2023 7 commits
-
-
Li Nan authored
After commit 1e50915f ("raid: improve MD/raid10 handling of correctable read errors."), rdev will be set to faulty if it reads data error to many times in raid10. Add this mechanism to raid1 now. Signed-off-by:
-
Li Nan authored
Move check_decay_read_errors() to raid1-10.c and factor out a helper exceed_read_errors() to check if read_errors exceeds the limit, so that raid1 can also use it. There are no functional changes. Signed-off-by:
-
Alex Lyakas authored
Upon assembling the array, both kernel and mdadm allow the devices to have event counter difference of 1, and still consider them as up-to-date. However, a device whose event count is behind by 1, may in fact not be up-to-date, and array resync with such a device may cause data corruption. To avoid this, consult the superblock of the freshest device about the status of a device, whose event counter is behind by 1. Signed-off-by:
Alex Lyakas <alex.lyakas@zadara.com> Signed-off-by:
-
Jens Axboe authored
It's clearly been a while since someone looked at this, so I gave it a quick shot. There are few issues in here: - Random bundling of members that are mostly read-only and often written - Random holes that need not be there This moves the most frequently used bits into cacheline 1 and 2, with the 2nd one being more write intensive than the first one, which is basically read-only. Outside of making this work a bit more efficiently, it also reduces the size of struct request_queue for my test setup from 864 bytes (spanning 14 cachelines!) to 832 bytes and 13 cachelines. Reviewed-by:
-
Christoph Hellwig authored
bio_add_hw_page currently always fails or succeeds. This is fine for the existing callers that always add PAGE_SIZE worth given that the max_segment_size and max_sectors must always allow at least a page worth of data. But when we want to add it for bigger amounts of data this means it can also fail when adding the data to a bio, and creating a fallback for that becomes really annoying in the callers. Make use of the existing API design that allows to return a smaller length than the one passed in and add up to max_segment_size worth of data from a larger input. All the existing callers are fine with this - not because they handle this return correctly, but because they never pass more than a page in. Signed-off-by:
Johannes Thumshirn <johannes.thumshirn@wdc.com> Link: https://lore.kernel.org/r/20231204173419.782378-3-hch@lst.deSigned-off-by:
-
Christoph Hellwig authored
Reordered a check to avoid a possible overflow when adding len to bv_len. Signed-off-by:
-
Gou Hao authored
If %__GFP_DIRECT_RECLAIM is set then bio_alloc_bioset will always be able to allocate a bio. See comment of bio_alloc_bioset. Signed-off-by:
Gou Hao <gouhao@uniontech.com> Signed-off-by:
-
- 14 Dec, 2023 1 commit
-
-
Bart Van Assche authored
Switch to the modern style of printing kernel messages. Use %u instead of %d to print unsigned integers. Reviewed-by:
Luis Chamberlain <mcgrof@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Ming Lei <ming.lei@redhat.com> Cc: Keith Busch <kbusch@kernel.org> Signed-off-by:
Bart Van Assche <bvanassche@acm.org> Reviewed-by:
-
- 13 Dec, 2023 3 commits
-
-
Min Li authored
Before calling add partition or resize partition, there is no check on whether the length is aligned with the logical block size. If the logical block size of the disk is larger than 512 bytes, then the partition size maybe not the multiple of the logical block size, and when the last sector is read, bio_truncate() will adjust the bio size, resulting in an IO error if the size of the read command is smaller than the logical block size.If integrity data is supported, this will also result in a null pointer dereference when calling bio_integrity_free. Cc: <stable@vger.kernel.org> Signed-off-by:
Min Li <min15.li@samsung.com> Reviewed-by:
Chaitanya Kulkarni <kch@nvidia.com> Reviewed-by:
-
Li Nan authored
On the error path of device_add_disk(), device's memalloc_noio flag was set but not cleared. As the comment of pm_runtime_set_memalloc_noio(), "The function should be called between device_add() and device_del()". Clear this flag before device_del() now. Fixes: 25e823c8 ("block/genhd.c: apply pm_runtime_set_memalloc_noio on block devices") Signed-off-by:
-
Kees Cook authored
Since "dev_search_path" can technically be as large as PATH_MAX, there was a risk of truncation when copying it and a second string into "full_path" since it was also PATH_MAX sized. The W=1 builds were reporting this warning: drivers/block/rnbd/rnbd-srv.c: In function 'process_msg_open.isra': drivers/block/rnbd/rnbd-srv.c:616:51: warning: '%s' directive output may be truncated writing up to 254 bytes into a region of size between 0 and 4095 [-Wformat-truncation=] 616 | snprintf(full_path, PATH_MAX, "%s/%s", | ^~ In function 'rnbd_srv_get_full_path', inlined from 'process_msg_open.isra' at drivers/block/rnbd/rnbd-srv.c:721:14: drivers/block/rnbd/rnbd-srv.c:616:17: note: 'snprintf' output between 2 and 4351 bytes into a destination of size 4096 616 | snprintf(full_path, PATH_MAX, "%s/%s", | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 617 | dev_search_path, dev_name); | ~~~~~~~~~~~~~~~~~~~~~~~~~~ To fix this, unconditionally check for truncation (as was already done for the case where "%SESSNAME%" was present). Reported-by:kernel test robot <lkp@intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202312100355.lHoJPgKy-lkp@intel.com/ Cc: Md. Haris Iqbal <haris.iqbal@ionos.com> Cc: Jack Wang <jinpu.wang@ionos.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: <linux-block@vger.kernel.org> Signed-off-by:
Kees Cook <keescook@chromium.org> Acked-by:
Guoqing Jiang <guoqing.jiang@linux.dev> Acked-by:
Jack Wang <jinpu.wang@ionos.com> Link: https://lore.kernel.org/r/20231212214738.work.169-kees@kernel.orgSigned-off-by:
-
- 08 Dec, 2023 1 commit
-
-
Jens Axboe authored
Merge tag 'md-next-20231208' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.8/block Pull MD updates from Song: "1. Fix/Cleanup RCU usage from conf->disks[i].rdev, by Yu Kuai; 2. Fix raid5 hang issue, by Junxiao Bi; 3. Add Yu Kuai as Reviewer of the md subsystem." * tag 'md-next-20231208' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md: md: synchronize flush io with array reconfiguration MAINTAINERS: SOFTWARE RAID: Add Yu Kuai as Reviewer md/md-multipath: remove rcu protection to access rdev from conf md/raid5: remove rcu protection to access rdev from conf md/raid1: remove rcu protection to access rdev from conf md/raid10: remove rcu protection to access rdev from conf md: remove flag RemoveSynchronized Revert "md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d" md: bypass block throttle for superblock update
-
- 07 Dec, 2023 1 commit
-
-
Matthew Wilcox (Oracle) authored
The special casing was originally added in pre-git history; reproducing the commit log here: > commit a318a92567d77 > Author: Andrew Morton <akpm@osdl.org> > Date: Sun Sep 21 01:42:22 2003 -0700 > > [PATCH] Speed up direct-io hugetlbpage handling > > This patch short-circuits all the direct-io page dirtying logic for > higher-order pages. Without this, we pointlessly bounce BIOs up to > keventd all the time. In the last twenty years, compound pages have become used for more than just hugetlb. Rewrite these functions to operate on folios instead of pages and remove the special case for hugetlbfs; I don't think it's needed any more (and if it is, we can put it back in as a call to folio_test_hugetlb()). This was found by inspection; as far as I can tell, this bug can lead to pages used as the destination of a direct I/O read not being marked as dirty. If those pages are then reclaimed by the MM without being dirtied for some other reason, they won't be written out. Then when they're faulted back in, they will not contain the data they should. It'll take a pretty unusual setup to produce this problem with several races all going the wrong way. This problem predates the folio work; it could for example have been triggered by mmaping a THP in tmpfs and using that as the target of an O_DIRECT read. Fixes: 800d8c63 ("shmem: add huge pages support") Cc: <stable@vger.kernel.org> Signed-off-by:
Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by:
-
- 02 Dec, 2023 5 commits
-
-
Kundan Kumar authored
Write-back throttling (WBT) enables QUEUE_FLAG_STATS on the request queue. But WBT does not make sense for passthrough io, so skip QUEUE_FLAG_STATS processing. Also skip rq_qos_issue/done for passthrough io. Overall, the change gives ~11% hike in peak performance. Signed-off-by:
-
Keith Busch authored
No more users of this field. Reviewed-by:
-
Keith Busch authored
No more users of this flag. Reviewed-by:
-
Keith Busch authored
Map user metadata buffers directly. Now that the bio tracks the metadata, nvme doesn't need special metadata handling and tracking with callbacks and additional fields in the pdu. Reviewed-by:
-
Keith Busch authored
Passthrough commands that utilize metadata currently need to bounce the user space buffer through the kernel. Add support for mapping user space directly so that we can avoid this costly overhead. This is similar to how the normal bio data payload utilizes user addresses with bio_map_user_iov(). If the user address can't directly be used for reason, like too many segments or address unalignement, fallback to a copy of the user vec while keeping the user address pinned for the IO duration so that it can safely be copied on completion in any process context. Signed-off-by:
-
- 01 Dec, 2023 1 commit
-
-
Yu Kuai authored
Currently rcu is used to protect iterating rdev from submit_flushes(): submit_flushes remove_and_add_spares synchronize_rcu pers->hot_remove_disk() rcu_read_lock() rdev_for_each_rcu if (rdev->raid_disk >= 0) rdev->radi_disk = -1; atomic_inc(&rdev->nr_pending) rcu_read_unlock() bi = bio_alloc_bioset() bi->bi_end_io = md_end_flush bi->private = rdev submit_bio // issue io for removed rdev Fix this problem by grabbing 'acive_io' before iterating rdev, make sure that remove_and_add_spares() won't concurrent with submit_flushes(). Fixes: a2826aa9 ("md: support barrier requests on all personalities.") Signed-off-by:
Yu Kuai <yukuai3@huawei.com> Signed-off-by:
-
- 28 Nov, 2023 2 commits
-
-
Song Liu authored
Add Yu Kuai as reviewer for md/raid subsystem. Signed-off-by:
-
Song Liu authored
From Yu Kuai: md: remove rcu protection to access rdev from conf The lifetime of rdev: 1. md_import_device() generate a rdev based on underlying disk; mddev_lock() rdev = kzalloc(); rdev->bdev = blkdev_get_by_dev(); mddev_unlock() 2. bind_rdev_to_array() add this rdev to mddev->disks; mddev_lock() kobject_add(&rdev->kobj, &mddev->kobj, ...); list_add_rcu(&rdev->same_set, &mddev->disks); mddev_unlock() 3. remove_and_add_spares() add this rdev to conf; mddev_lock() rdev_addable(); pers->hot_add_disk(); rcu_assign_pointer(conf->rdev, rdev); mddev_unlock() 4. Use this array with rdev; 5. remove_and_add_spares() remove rdev from conf; // triggered by sysfs/ioctl mddev_lock() rdev_removeable(); pers->hot_remove_disk(); rcu_assign_pointer(conf->rdev, NULL); synchronize_rcu(); mddev_unlock() // triggered by daemon mddev_lock() rdev_removeable(); synchronize_rcu(); -> this can't protect accessing rdev from conf pers->hot_remove_disk(); rcu_assign_pointer(conf->rdev, NULL); mddev_unlock() 6. md_kick_rdev_from_array() remove rdev from mddev->disks; mddev_lock() list_del_rcu(&rdev->same_set); synchronize_rcu(); list_add(&rdev->same_set, &mddev->deleting) mddev_unlock() export_rdev There are two separate rcu protection for rdev, and this pathset remove the protection of conf(step 3 and 5), because it's safe to access rdev from conf in following cases: - If 'reconfig_mutex' is held, because rdev can't be added or rmoved to conf; - If there is normal IO inflight, because mddev_suspend() will wait for IO to be done and prevent rdev to be added or removed to conf; - If sync thread is running, because remove_and_add_spares() can only be called from daemon thread when sync thread is done, and 'MD_RECOVERY_RUNNING' is also checked for ioctl/sysfs; - if any spinlock or rcu_read_lock() is held, because synchronize_rcu() from step 6 prevent rdev to be freed until spinlock is released or rcu_read_unlock();
-
- 27 Nov, 2023 11 commits
-
-
Yu Kuai authored
Because it's safe to accees rdev from conf: - If any spinlock is held, because synchronize_rcu() from md_kick_rdev_from_array() will prevent 'rdev' to be freed until spinlock is released; - If there is normal IO inflight, because mddev_suspend() will prevent rdev to be added or removed from array; And these will cover all the scenarios in md-multipath. Signed-off-by:
-
Yu Kuai authored
Because it's safe to accees rdev from conf: - If any spinlock is held, because synchronize_rcu() from md_kick_rdev_from_array() will prevent 'rdev' to be freed until spinlock is released; - If 'reconfig_lock' is held, because rdev can't be added or removed from array; - If there is normal IO inflight, because mddev_suspend() will prevent rdev to be added or removed from array; - If there is sync IO inflight, because 'MD_RECOVERY_RUNNING' is checked in remove_and_add_spares(). And these will cover all the scenarios in raid456. Signed-off-by:
-
Yu Kuai authored
Because it's safe to accees rdev from conf: - If any spinlock is held, because synchronize_rcu() from md_kick_rdev_from_array() will prevent 'rdev' to be freed until spinlock is released; - If 'reconfig_lock' is held, because rdev can't be added or removed from array; - If there is normal IO inflight, because mddev_suspend() will prevent rdev to be added or removed from array; - If there is sync IO inflight, because 'MD_RECOVERY_RUNNING' is checked in remove_and_add_spares(). And these will cover all the scenarios in raid1. Signed-off-by:
-
Yu Kuai authored
Because it's safe to accees rdev from conf: - If any spinlock is held, because synchronize_rcu() from md_kick_rdev_from_array() will prevent 'rdev' to be freed until spinlock is released; - If 'reconfig_lock' is held, because rdev can't be added or removed from array; - If there is normal IO inflight, because mddev_suspend() will prevent rdev to be added or removed from array; - If there is sync IO inflight, because 'MD_RECOVERY_RUNNING' is checked in remove_and_add_spares(). And these will cover all the scenarios in raid10. This patch also cleanup the code to handle the case that replacement replace rdev while IO is still inflight. Signed-off-by:
-
Yu Kuai authored
rcu is not used correctly here, because synchronize_rcu() is called before replacing old value, for example: remove_and_add_spares // other path synchronize_rcu // called before replacing old value set_bit(RemoveSynchronized) rcu_read_lock() rdev = conf->mirros[].rdev pers->hot_remove_disk conf->mirros[].rdev = NULL; if (!test_bit(RemoveSynchronized)) synchronize_rcu /* * won't be called, and won't wait * for concurrent readers to be done. */ // access rdev after remove_and_add_spares() rcu_read_unlock() Fortunately, there is a separate rcu protection to prevent such rdev to be freed: md_kick_rdev_from_array //other path rcu_read_lock() rdev = conf->mirros[].rdev list_del_rcu(&rdev->same_set) rcu_read_unlock() /* * rdev can be removed from conf, but * rdev won't be freed. */ synchronize_rcu() free rdev Hence remove this useless flag and prepare to remove rcu protection to access rdev from 'conf'. Signed-off-by: -
Junxiao Bi authored
This reverts commit 5e2cf333. That commit introduced the following race and can cause system hung. md_write_start: raid5d: // mddev->in_sync == 1 set "MD_SB_CHANGE_PENDING" // running before md_write_start wakeup it waiting "MD_SB_CHANGE_PENDING" cleared >>>>>>>>> hung wakeup mddev->thread ... waiting "MD_SB_CHANGE_PENDING" cleared >>>> hung, raid5d should clear this flag but get hung by same flag. The issue reverted commit fixing is fixed by last patch in a new way. Fixes: 5e2cf333 ("md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d") Cc: stable@vger.kernel.org # v5.19+ Signed-off-by:
Junxiao Bi <junxiao.bi@oracle.com> Reviewed-by:
-
Junxiao Bi authored
commit 5e2cf333 ("md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d") introduced a hung bug and will be reverted in next patch, since the issue that commit is fixing is due to md superblock write is throttled by wbt, to fix it, we can have superblock write bypass block layer throttle. Fixes: 5e2cf333 ("md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d") Cc: stable@vger.kernel.org # v5.19+ Suggested-by:
Logan Gunthorpe <logang@deltatee.com> Reviewed-by:
-
Christoph Hellwig authored
Allow using a few symbols with IS_ENABLED instead of #idef by moving the declarations out of #idef CONFIG_BLK_DEV_ZONED, and move bdev_nr_zones into the remaining #idef CONFIG_BLK_DEV_ZONED, #else block below. Signed-off-by:
-
Supriti Singh authored
While printing error, replace %ld by %pe. %pe prints a string whereas %ld would print an error code. Signed-off-by:
Supriti Singh <supriti.singh@ionos.com> Signed-off-by:
Grzegorz Prajsner <grzegorz.prajsner@ionos.com> Signed-off-by:
Md Haris Iqbal <haris.iqbal@ionos.com> Link: https://lore.kernel.org/r/20231124213422.113449-3-haris.iqbal@ionos.comSigned-off-by:
-
Santosh Pradhan authored
Remove REQ_OP_WRITE_SAME in favour of REQ_OP_WRITE_ZEROES. Signed-off-by:
Santosh Pradhan <santosh.pradhan@ionos.com> Reviewed-by:
-
Linus Torvalds authored
-
