- 28 Sep, 2020 1 commit
-
-
git://git.infradead.org/nvmeJens Axboe authored
Pull NVMe updates from Christoph: "nvme updates for 5.10 - fix keep alive timer modification (Amit Engel) - order the PCI ID list more sensibly (Andy Shevchenko) - cleanup the open by controller helper (Chaitanya Kulkarni) - use an xarray for th CSE log lookup (Chaitanya Kulkarni) - support ZNS in nvmet passthrough mode (Chaitanya Kulkarni) - fix nvme_ns_report_zones (me) - add a sanity check to nvmet-fc (James Smart) - fix interrupt allocation when too many polled queues are specified (Jeffle Xu) - small nvmet-tcp optimization (Mark Wunderlich)" * tag 'nvme-5.10-2020-09-27' of git://git.infradead.org/nvme: nvme-pci: allocate separate interrupt for the reserved non-polled I/O queue nvme: fix error handling in nvme_ns_report_zones nvmet-fc: fix missing check for no hostport struct nvmet: add passthru ZNS support nvmet: handle keep-alive timer when kato is modified by a set features cmd nvmet-tcp: have queue io_work context run on sock incoming cpu nvme-pci: Move enumeration by class to be last in the table nvme: use an xarray to lookup the Commands Supported and Effects log nvme: lift the file open code from nvme_ctrl_get_by_path
-
- 27 Sep, 2020 9 commits
-
-
Jeffle Xu authored
One queue will be reserved for non-polled IO when nvme.poll_queues is greater or equal than the number of IO queues that the nvme controller can provide. Currently the reserved queue for non-polled IO will reuse the interrupt used by admin queue in this case, e.g, vector 0. This can work and the performance may not be an issue since the admin queue is used unfrequently. However this behaviour may be inconsistent with that when nvme.poll_queues is smaller than the number of IO queues available. Thus allocate separate interrupt for this reserved queue, and thus make the behaviour consistent. Signed-off-by:
Jeffle Xu <jefflexu@linux.alibaba.com> [hch: minor cleanups, mostly to the pre-existing surrounding code] Signed-off-by:
Christoph Hellwig <hch@lst.de>
-
Christoph Hellwig authored
nvme_submit_sync_cmd can return positive NVMe error codes in addition to the negative Linux error code, which are currently ignored. Fix this by removing __nvme_ns_report_zones and handling the errors from nvme_submit_sync_cmd in the caller instead of multiplexing the return value and the number of zones reported into a single return value. Fixes: 240e6ee2 ("nvme: support for zoned namespaces") Signed-off-by:
Damien Le Moal <damien.lemoal@wdc.com>
-
James Smart authored
A hostport port pointer is allowed to be NULL as it is not allocated if the lldd does not support the new interfaces for NVME LS request support. The hostport free routine validates the handle but forgot to validate the hostport pointer. Validate the hostport pointer before using it to validate the handle. Signed-off-by:
James Smart <james.smart@broadcom.com> Reviewed-by:
Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by:
-
Chaitanya Kulkarni authored
In the default passthru implementation NVMeOF target passthru ctrl is not capable of handling Zoned Namespaces (ZNS). Update the nvmet_parse_pasthru_admin_cmd() to allow NVME_ID_CNS_CS_CTRL/NVME_CIS_ZNS and NVME_ID_CNS_CS_NS/NVME_CIS_ZNS. With this addition NVMeOF Passthru allows Zoned Namespaces. Signed-off-by:
Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Signed-off-by:
-
Amit Engel authored
A user may modify the kato by a set features cmd. To properly deal with races or a kato value of 0 (no keep alive enabled) change nvmet_set_feat_kato to first disable the timer, then set the value and then re-enable the timer. Signed-off-by:
Amit Engel <amit.engel@dell.com> Reviewed-by:
Sagi Grimberg <sagi@grimberg.me> Signed-off-by:
-
Mark Wunderlich authored
No real good need to spread queues artificially. Usually the target will serve multiple hosts, and it's better to run on the socket incoming cpu for better affinitization rather than spread queues on all online cpus. We rely on RSS to spread the work around sufficiently. Signed-off-by:
Mark Wunderlich <mark.wunderlich@intel.com> Reviewed-by:
-
Andy Shevchenko authored
It's unusual that we have enumeration by class in the middle of the table. It might potentially be problematic in the future if we add another entry after it. So, move class matching entry to be the last in the ID table. Signed-off-by:
Andy Shevchenko <andriy.shevchenko@linux.intel.com> Reviewed-by:
Keith Busch <kbusch@kernel.org> Reviewed-by:
-
Chaitanya Kulkarni authored
When using linked list we have to open code the locking, search, and destroy operations with the loops even if data structure doesn't fall into the fast path. One of the main advantage of having XArray to store, search, and remove items is that it handles all the locking by itself, avoids the loops when using linked lists, provides clear API to replace the linked list's search and destroy loops. This patch replaces the ctrl->cel list with XArray and removes :- a. Extra code needed for the linked list for ctrl->cel item management such as nvme_find_cel(). b. Destroy loop in the nvme_free_ctrl(). c. Explicit insertion locking in the nvme_get_effects_log(). Signed-off-by:
-
Chaitanya Kulkarni authored
Lift opening the file open/close code from nvme_ctrl_get_by_path into the caller, just keeping a simple nvme_ctrl_from_file() helper. Signed-off-by:
Logan Gunthorpe <logang@deltatee.com>
-
- 25 Sep, 2020 1 commit
-
-
Jens Axboe authored
Merge branch 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-5.10/drivers Pull MD updates from Song. * 'md-next' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md: md/raid10: improve discard request for far layout md/raid10: improve raid10 discard request md/raid10: pull codes that wait for blocked dev into one function md/raid10: extend r10bio devs to raid disks md: add md_submit_discard_bio() for submitting discard bio md: Simplify code with existing definition RESYNC_SECTORS in raid10.c md/raid5: reallocate page array after setting new stripe_size md/raid5: resize stripe_head when reshape array md/raid5: let multiple devices of stripe_head share page md/raid6: let async recovery function support different page offset md/raid6: let syndrome computor support different page offset md/raid5: convert to new xor compution interface md/raid5: add new xor function to support different page offset md/raid5: make async_copy_data() to support different page offset md/raid5: add a new member of offset into r5dev md: only calculate blocksize once and use i_blocksize()
-
- 24 Sep, 2020 29 commits
-
-
Xiao Ni authored
For far layout, the discard region is not continuous on disks. So it needs far copies r10bio to cover all regions. It needs a way to know all r10bios have finish or not. Similar with raid10_sync_request, only the first r10bio master_bio records the discard bio. Other r10bios master_bio record the first r10bio. The first r10bio can finish after other r10bios finish and then return the discard bio. Signed-off-by:
Xiao Ni <xni@redhat.com> Signed-off-by:
Song Liu <songliubraving@fb.com>
-
Xiao Ni authored
Now the discard request is split by chunk size. So it takes a long time to finish mkfs on disks which support discard function. This patch improve handling raid10 discard request. It uses the similar way with patch 29efc390 (md/md0: optimize raid0 discard handling). But it's a little complex than raid0. Because raid10 has different layout. If raid10 is offset layout and the discard request is smaller than stripe size. There are some holes when we submit discard bio to underlayer disks. For example: five disks (disk1 - disk5) D01 D02 D03 D04 D05 D05 D01 D02 D03 D04 D06 D07 D08 D09 D10 D10 D06 D07 D08 D09 The discard bio just wants to discard from D03 to D10. For disk3, there is a hole between D03 and D08. For disk4, there is a hole between D04 and D09. D03 is a chunk, raid10_write_request can handle one chunk perfectly. So the part that is not aligned with stripe size is still handled by raid10_write_request. If reshape is running when discard bio comes and the discard bio spans the reshape position, raid10_write_request is responsible to handle this discard bio. I did a test with this patch set. Without patch: time mkfs.xfs /dev/md0 real4m39.775s user0m0.000s sys0m0.298s With patch: time mkfs.xfs /dev/md0 real0m0.105s user0m0.000s sys0m0.007s nvme3n1 259:1 0 477G 0 disk └─nvme3n1p1 259:10 0 50G 0 part nvme4n1 259:2 0 477G 0 disk └─nvme4n1p1 259:11 0 50G 0 part nvme5n1 259:6 0 477G 0 disk └─nvme5n1p1 259:12 0 50G 0 part nvme2n1 259:9 0 477G 0 disk └─nvme2n1p1 259:15 0 50G 0 part nvme0n1 259:13 0 477G 0 disk └─nvme0n1p1 259:14 0 50G 0 part Reviewed-by:
Coly Li <colyli@suse.de> Reviewed-by:
Guoqing Jiang <guoqing.jiang@cloud.ionos.com> Signed-off-by:
-
Xiao Ni authored
The following patch will reuse these logics, so pull the same codes into one function. Signed-off-by:
-
Xiao Ni authored
Now it allocs r10bio->devs[conf->copies]. Discard bio needs to submit to all member disks and it needs to use r10bio. So extend to r10bio->devs[geo.raid_disks]. Reviewed-by:
-
Xiao Ni authored
Move these logic from raid0.c to md.c, so that we can also use it in raid10.c. Reviewed-by:
-
Zhen Lei authored
#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9) "RESYNC_BLOCK_SIZE/512" is equal to "RESYNC_BLOCK_SIZE >> 9", replace it with RESYNC_SECTORS. Signed-off-by:
Zhen Lei <thunder.leizhen@huawei.com> Signed-off-by:
-
Yufen Yu authored
When try to resize stripe_size, we also need to free old shared page array and allocate new. Signed-off-by:
Yufen Yu <yuyufen@huawei.com> Signed-off-by:
-
Yufen Yu authored
When reshape array, we try to reuse shared pages of old stripe_head, and allocate more for the new one if needed. Signed-off-by:
-
Yufen Yu authored
In current implementation, grow_buffers() uses alloc_page() to allocate the buffers for each stripe_head, i.e. allocate a page for each dev[i] in stripe_head. After setting stripe_size as a configurable value by writing sysfs entry, it means that we always allocate 64K buffers, but just use 4K of them when stripe_size is 4K in 64KB arm64. To avoid wasting memory, we try to let multiple sh->dev share one real page. That means, multiple sh->dev[i].page will point to the only page with different offset. Example of 64K PAGE_SIZE and 4K stripe_size as following: 64K PAGE_SIZE +---+---+---+---+------------------------------+ | | | | | | | | | | +-+-+-+-+-+-+-+-+------------------------------+ ^ ^ ^ ^ | | | +----------------------------+ | | | | | | +-------------------+ | | | | | | +----------+ | | | | | | +-+ | | | | | | | +-----+-----+------+-----+------+-----+------+------+ sh | offset(0) | offset(4K) | offset(8K) | offset(12K) | + +-----------+------------+------------+-------------+ +----> dev[0].page dev[1].page dev[2].page dev[3].page A new 'pages' array will be added into stripe_head to record shared page used by this stripe_head. Allocate them when grow_buffers() and free them when shrink_buffers(). After trying to share page, the users of sh->dev[i].page need to take care of the related page offset: page of issued bio and page passed to xor compution functions. But thanks for previous different page offset supported. Here, we just need to set correct dev[i].offset. Signed-off-by: -
Yufen Yu authored
For now, asynchronous raid6 recovery calculate functions are require common offset for pages. But, we expect them to support different page offset after introducing stripe shared page. Do that by simplily adding page offset where each page address are referred. Then, replace the old interface with the new ones in raid6 and raid6test. Signed-off-by:
-
Yufen Yu authored
For now, syndrome compute functions require common offset in the pages array. However, we expect them to support different offset when try to use shared page in the following. Simplily covert them by adding page offset where each page address are referred. Since the only caller of async_gen_syndrome() and async_syndrome_val() are in raid6, we don't want to reserve the old interface but modify the interface directly. After that, replacing old interfaces with new ones for raid6 and raid6test. Signed-off-by:
-
Yufen Yu authored
We try to replace async_xor() and async_xor_val() with the new introduced interface async_xor_offs() and async_xor_val_offs() for raid456. Signed-off-by:
-
Yufen Yu authored
raid5 will call async_xor() and async_xor_val() to compute xor. For now, both of them require the common src/dst page offset. But, we want them to support different src/dst page offset for following shared page. Here, adding two new function async_xor_offs() and async_xor_val_offs() respectively for async_xor() and async_xor_val(). Signed-off-by:
-
Yufen Yu authored
ops_run_biofill() and ops_run_biodrain() will call async_copy_data() to copy sh->dev[i].page from or to bio page. For now, it implies the offset of dev[i].page is 0. But we want to support different page offset in the following. Thus, pass page offset to these functions and replace 'page_offset' with 'page_offset + poff'. No functional change. Signed-off-by:
-
Yufen Yu authored
Add a new member of offset into struct r5dev. It indicates the offset of related dev[i].page. For now, since each device have a privated page, the value is always 0. Thus, we set offset as 0 when allcate page in grow_buffers() and resize_stripes(). To support following different page offset, we try to use the page offset rather than '0' directly for async_memcpy() and ops_run_io(). We try to support different page offset for xor compution functions in the following. To avoid repeatly allocate a new array each time, we add a memory region into scribble buffer to record offset. No functional change. Signed-off-by:
-
Xianting Tian authored
We alreday has the interface i_blocksize(), which can be used to get blocksize, so use it. Only calculate blocksize once and use it within read_page(). Signed-off-by:
Xianting Tian <tian.xianting@h3c.com> Signed-off-by:
-
John Garry authored
Support a shared tag bitmap, whereby request tags are unique over all submission queues, and not just per submission queue. As such, per device total queue depth is normally hw_queue_depth * submit_queues, but hw_queue_depth when set. And a similar story for when shared_tags is set, where that is the queue depth over all null blk devices. Signed-off-by:
John Garry <john.garry@huawei.com> Tested-by:
Douglas Gilbert <dgilbert@interlog.com> Signed-off-by:
Jens Axboe <axboe@kernel.dk>
-
Jens Axboe authored
* for-5.10/block: (140 commits) bdi: replace BDI_CAP_NO_{WRITEBACK,ACCT_DIRTY} with a single flag bdi: invert BDI_CAP_NO_ACCT_WB bdi: replace BDI_CAP_STABLE_WRITES with a queue and a sb flag mm: use SWP_SYNCHRONOUS_IO more intelligently bdi: remove BDI_CAP_SYNCHRONOUS_IO bdi: remove BDI_CAP_CGROUP_WRITEBACK block: lift setting the readahead size into the block layer md: update the optimal I/O size on reshape bdi: initialize ->ra_pages and ->io_pages in bdi_init aoe: set an optimal I/O size bcache: inherit the optimal I/O size drbd: remove dead code in device_to_statistics fs: remove the unused SB_I_MULTIROOT flag block: mark blkdev_get static PM: mm: cleanup swsusp_swap_check mm: split swap_type_of PM: rewrite is_hibernate_resume_dev to not require an inode mm: cleanup claim_swapfile ocfs2: cleanup o2hb_region_dev_store dasd: cleanup dasd_scan_partitions ... -
Christoph Hellwig authored
Replace the two negative flags that are always used together with a single positive flag that indicates the writeback capability instead of two related non-capabilities. Also remove the pointless wrappers to just check the flag. Signed-off-by:
Jan Kara <jack@suse.cz> Reviewed-by:
Johannes Thumshirn <johannes.thumshirn@wdc.com> Signed-off-by:
-
Christoph Hellwig authored
Replace BDI_CAP_NO_ACCT_WB with a positive BDI_CAP_WRITEBACK_ACCT to make the checks more obvious. Also remove the pointless bdi_cap_account_writeback wrapper that just obsfucates the check. Signed-off-by:
-
Christoph Hellwig authored
The BDI_CAP_STABLE_WRITES is one of the few bits of information in the backing_dev_info shared between the block drivers and the writeback code. To help untangling the dependency replace it with a queue flag and a superblock flag derived from it. This also helps with the case of e.g. a file system requiring stable writes due to its own checksumming, but not forcing it on other users of the block device like the swap code. One downside is that we an't support the stable_pages_required bdi attribute in sysfs anymore. It is replaced with a queue attribute which also is writable for easier testing. Signed-off-by:
-
Christoph Hellwig authored
There is no point in trying to call bdev_read_page if SWP_SYNCHRONOUS_IO is not set, as the device won't support it. Signed-off-by:
-
Christoph Hellwig authored
BDI_CAP_SYNCHRONOUS_IO is only checked in the swap code, and used to decided if ->rw_page can be used on a block device. Just check up for the method instead. The only complication is that zram needs a second set of block_device_operations as it can switch between modes that actually support ->rw_page and those who don't. Signed-off-by:
-
Christoph Hellwig authored
Just checking SB_I_CGROUPWB for cgroup writeback support is enough. Either the file system allocates its own bdi (e.g. btrfs), in which case it is known to support cgroup writeback, or the bdi comes from the block layer, which always supports cgroup writeback. Signed-off-by:
-
Christoph Hellwig authored
Drivers shouldn't really mess with the readahead size, as that is a VM concept. Instead set it based on the optimal I/O size by lifting the algorithm from the md driver when registering the disk. Also set bdi->io_pages there as well by applying the same scheme based on max_sectors. To ensure the limits work well for stacking drivers a new helper is added to update the readahead limits from the block limits, which is also called from disk_stack_limits. Signed-off-by:
Mike Snitzer <snitzer@redhat.com> Reviewed-by:
Martin K. Petersen <martin.petersen@oracle.com> Acked-by:
-
Christoph Hellwig authored
The raid5 and raid10 drivers currently update the read-ahead size, but not the optimal I/O size on reshape. To prepare for deriving the read-ahead size from the optimal I/O size make sure it is updated as well. Signed-off-by:
Song Liu <song@kernel.org> Signed-off-by:
-
Christoph Hellwig authored
Set up a readahead size by default, as very few users have a good reason to change it. This means code, ecryptfs, and orangefs now set up the values while they were previously missing it, while ubifs, mtd and vboxsf manually set it to 0 to avoid readahead. Signed-off-by:
-
Christoph Hellwig authored
aoe forces a larger readahead size, but any reason to do larger I/O is not limited to readahead. Also set the optimal I/O size, and remove the local constants in favor of just using SZ_2G. Signed-off-by:
-
Christoph Hellwig authored
Inherit the optimal I/O size setting just like the readahead window, as any reason to do larger I/O does not apply to just readahead. Signed-off-by:
-
