aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)AuthorFilesLines
2021-08-23st: do not allocate a gendiskChristoph Hellwig2-38/+13
st is a character driver and thus does not need to allocate a gendisk, which is only used for file system-like block layer I/O on block devices. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-23nvme: use blk_mq_alloc_diskChristoph Hellwig1-20/+13
Switch to use the blk_mq_alloc_disk helper for allocating the request_queue and gendisk. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Keith Busch <[email protected]> Reviewed-by: Sagi Grimberg <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-20block: add back the bd_holder_dir reference in bd_link_disk_holderChristoph Hellwig1-0/+7
This essentially reverts "block: remove the extra kobject reference in bd_link_disk_holder". That commit dropped the extra reference because the condition in the comment can't be true. But it turns out that comment did not actually describe the problematic situation, so add back the extra reference and document it properly. Fixes: fbd9a39542ec ("block: remove the extra kobject reference in bd_link_disk_holder") Reported-by: Tushar Sugandhi <[email protected]> Reviewed-by: Mike Snitzer <[email protected]> Signed-off-by: Christoph Hellwig <[email protected]> Signed-off-by: Jens Axboe <[email protected]>
2021-08-18block: fix default IO priority handlingDamien Le Moal4-7/+13
The default IO priority is the best effort (BE) class with the normal priority level IOPRIO_NORM (4). However, get_task_ioprio() returns IOPRIO_CLASS_NONE/IOPRIO_NORM as the default priority and get_current_ioprio() returns IOPRIO_CLASS_NONE/0. Let's be consistent with the defined default and have both of these functions return the default priority IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM) when the user did not define another default IO priority for the task. In include/uapi/linux/ioprio.h, introduce the IOPRIO_BE_NORM macro as an alias to IOPRIO_NORM to clarify that this default level applies to the BE priotity class. In include/linux/ioprio.h, define the macro IOPRIO_DEFAULT as IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_BE_NORM) and use this new macro when setting a priority to the default. Signed-off-by: Damien Le Moal <[email protected]> Link: https://lore.kernel.org/r/[email protected] [axboe: drop unnecessary lightnvm change] Signed-off-by: Jens Axboe <[email protected]>
2021-08-18block: Introduce IOPRIO_NR_LEVELSDamien Le Moal6-14/+14
The BFQ scheduler and ioprio_check_cap() both assume that the RT priority class (IOPRIO_CLASS_RT) can have up to 8 different priority levels, similarly to the BE class (IOPRIO_CLASS_iBE). This is controlled using the IOPRIO_BE_NR macro , which is badly named as the number of levels also applies to the RT class. Introduce the class independent IOPRIO_NR_LEVELS macro, defined to 8, to make things clear. Keep the old IOPRIO_BE_NR macro definition as an alias for IOPRIO_NR_LEVELS. Signed-off-by: Damien Le Moal <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-18block: fix IOPRIO_PRIO_CLASS() and IOPRIO_PRIO_VALUE() macrosDamien Le Moal1-4/+8
The ki_ioprio field of struct kiocb is 16-bits (u16) but often handled as an int in the block layer. E.g. ioprio_check_cap() takes an int as argument. With such implicit int casting function calls, the upper 16-bits of the int argument may be left uninitialized by the compiler, resulting in invalid values for the IOPRIO_PRIO_CLASS() macro (garbage upper bits) and in an error return for functions such as ioprio_check_cap(). Fix this by masking the result of the shift by IOPRIO_CLASS_SHIFT bits in the IOPRIO_PRIO_CLASS() macro. The new macro IOPRIO_CLASS_MASK defines the 3-bits mask for the priority class. Similarly, apply the IOPRIO_PRIO_MASK mask to the data argument of the IOPRIO_PRIO_VALUE() macro to ignore the upper bits of the data value. The IOPRIO_CLASS_MASK mask is also applied to the class argument of this macro before shifting the result by IOPRIO_CLASS_SHIFT bits. While at it, also change the argument name of the IOPRIO_PRIO_CLASS() and IOPRIO_PRIO_DATA() macros from "mask" to "ioprio" to reflect the fact that a priority value should be passed rather than a mask. Signed-off-by: Damien Le Moal <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-18block: change ioprio_valid() to an inline functionDamien Le Moal2-2/+10
Change the ioprio_valid() macro in include/usapi/linux/ioprio.h to an inline function declared on the kernel side in include/linux/ioprio.h. Also improve checks on the class value by checking the upper bound value. Signed-off-by: Damien Le Moal <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-18block: improve ioprio class description commentDamien Le Moal1-4/+6
In include/usapi/linux/ioprio.h, change the ioprio class enum comment to remove the outdated reference to CFQ and mention BFQ and mq-deadline instead. Also document the high priority NCQ command use for RT class IOs directed at ATA drives that support NCQ priority. Signed-off-by: Damien Le Moal <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-18block: bfq: fix bfq_set_next_ioprio_data()Damien Le Moal1-1/+1
For a request that has a priority level equal to or larger than IOPRIO_BE_NR, bfq_set_next_ioprio_data() prints a critical warning but defaults to setting the request new_ioprio field to IOPRIO_BE_NR. This is not consistent with the warning and the allowed values for priority levels. Fix this by setting the request new_ioprio field to IOPRIO_BE_NR - 1, the lowest priority level allowed. Cc: <[email protected]> Fixes: aee69d78dec0 ("block, bfq: introduce the BFQ-v0 I/O scheduler as an extra scheduler") Signed-off-by: Damien Le Moal <[email protected]> Reviewed-by: Hannes Reinecke <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16block: unexport blk_register_queueChristoph Hellwig1-1/+0
Not actually used in any modular code. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16blk-cgroup: stop using seq_get_bufChristoph Hellwig5-64/+39
seq_get_buf is a crutch that undoes all the memory safety of the seq_file interface. Use the normal seq_printf interfaces instead. Signed-off-by: Christoph Hellwig <[email protected]> Acked-by: Tejun Heo <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16blk-cgroup: refactor blkcg_print_statChristoph Hellwig1-74/+74
Factor out a helper to deal with a single blkcg_gq to make the code a little bit easier to follow. Signed-off-by: Christoph Hellwig <[email protected]> Acked-by: Tejun Heo <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16nvme: use bvec_virtChristoph Hellwig1-3/+2
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Keith Busch <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16dcssblk: use bvec_virtChristoph Hellwig1-2/+1
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16dasd: use bvec_virtChristoph Hellwig3-10/+10
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Stefan Haberland <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16ps3vram: use bvec_virtChristoph Hellwig1-1/+1
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16ubd: use bvec_virtChristoph Hellwig1-2/+1
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Acked-By: Anton Ivanov <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16sd: use bvec_virtChristoph Hellwig1-1/+1
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Acked-by: Martin K. Petersen <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16bcache: use bvec_virtChristoph Hellwig1-1/+1
Use bvec_virt instead of open coding it. Note that the existing code is fine despite ignoring bv_offset as the bio is known to contain exactly one page from the page allocator per bio_vec. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Coly Li <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16virtio_blk: use bvec_virtChristoph Hellwig1-5/+2
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Stefan Hajnoczi <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16rbd: use bvec_virtChristoph Hellwig1-2/+1
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Jeff Layton <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16squashfs: use bvec_virtChristoph Hellwig6-9/+8
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16dm-integrity: use bvec_virtChristoph Hellwig1-2/+2
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16dm-ebs: use bvec_virtChristoph Hellwig1-1/+1
Use bvec_virt instead of open coding it. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16dm: make EBS depend on !HIGHMEMChristoph Hellwig1-1/+1
__ebs_rw_bvec use page_address on the submitted bios data, and thus can't deal with highmem. Disable the target on highmem configs. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16block: use bvec_virt in bio_integrity_{process,free}Christoph Hellwig1-5/+2
Use the bvec_virt helper to clean up the bio integrity processing a little bit. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Chaitanya Kulkarni <[email protected]> Acked-by: Martin K. Petersen <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16bvec: add a bvec_virt helperChristoph Hellwig1-0/+12
Add a helper to get the virtual address for a bvec. This avoids that all callers need to know about the page + offset representation. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Chaitanya Kulkarni <[email protected]> Reviewed-by: Martin K. Petersen <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16block: ensure the bdi is freed after inode_detach_wbChristoph Hellwig2-4/+4
inode_detach_wb references the "main" bdi of the inode. With the recent change to move the bdi from the request_queue to the gendisk this causes a guaranteed use after free when using certain cgroup configurations. The big itself is older through as any non-default inode reference (e.g. an open file descriptor) could have injected this use after free even before that. Fixes: 52ebea749aae ("writeback: make backing_dev_info host cgroup-specific bdi_writebacks") Reported-by: Qian Cai <[email protected]> Reported-by: syzbot <[email protected]> Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-16block: free the extended dev_t minor laterChristoph Hellwig3-4/+5
The dev_t is used as the inode hash, so we should only released it once then block device inode is gone from the inode cache. Move it to bdev_free_inode to ensure that. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-14blk-throtl: optimize IOPS throttle for large IO scenariosChunguang Xu3-0/+36
After patch 54efd50 (block: make generic_make_request handle arbitrarily sized bios), the IO through io-throttle may be larger, and these IOs may be further split into more small IOs. However, IOPS throttle does not seem to be aware of this change, which makes the calculation of IOPS of large IOs incomplete, resulting in disk-side IOPS that does not meet expectations. Maybe we should fix this problem. We can reproduce it by set max_sectors_kb of disk to 128, set blkio.write_iops_throttle to 100, run a dd instance inside blkio and use iostat to watch IOPS: dd if=/dev/zero of=/dev/sdb bs=1M count=1000 oflag=direct As a result, without this change the average IOPS is 1995, with this change the IOPS is 98. Signed-off-by: Chunguang Xu <[email protected]> Acked-by: Tejun Heo <[email protected]> Link: https://lore.kernel.org/r/65869aaad05475797d63b4c3fed4f529febe3c26.1627876014.git.brookxu@tencent.com Signed-off-by: Jens Axboe <[email protected]>
2021-08-12block: pass a gendisk to bdev_resize_partitionChristoph Hellwig3-9/+9
bdev_resize_partition can only operate on the whole device. Make that clear by passing a gendisk instead of a block_device. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12block: pass a gendisk to bdev_del_partitionChristoph Hellwig3-6/+6
bdev_del_partition can only operate on the whole device. Make that clear by passing a gendisk instead of a block_device. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12block: pass a gendisk to bdev_add_partitionChristoph Hellwig3-6/+6
bdev_add_partition can only operate on the whole device. Make that clear by passing a gendisk instead of a block_device. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12block: store a gendisk in struct parsed_partitionsChristoph Hellwig14-73/+52
Partition scanning only happens on the whole device, so pass a struct gendisk instead of the whole device block_device to the scanners. This allows to simplify printing the device name in various places as the disk name is available in disk->name. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Stefan Haberland <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12block: remove GENHD_FL_UPChristoph Hellwig6-15/+12
Just check inode_unhashed on the whole device bdev inode instead, and provide a helper to check for that information. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12bcache: move the del_gendisk call out of bcache_device_freeChristoph Hellwig1-6/+4
Let the callers call del_gendisk so that we can check if add_disk has been called properly for the cached device case instead of relying on the block layer internal GENHD_FL_UP flag. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Coly Li <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12bcache: add proper error unwinding in bcache_device_initChristoph Hellwig1-5/+11
Except for the IDA none of the allocations in bcache_device_init is unwound on error, fix that. Signed-off-by: Christoph Hellwig <[email protected]> Acked-by: Coly Li <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12sx8: use the internal state machine to check if del_gendisk needs to be calledChristoph Hellwig1-1/+1
Remove usage of the block layer internal GENHD_FL_UP by just looking at the host state. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12nvme: replace the GENHD_FL_UP check in nvme_mpath_shutdown_diskChristoph Hellwig1-1/+1
Use the nvme-internal NVME_NSHEAD_DISK_LIVE flag instead of abusing the block layer state. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12nvme: remove the GENHD_FL_UP check in nvme_ns_removeChristoph Hellwig1-8/+6
Early probe failure never reaches nvme_ns_remove, so GENHD_FL_UP must be set at this point. Remove the check. Signed-off-by: Christoph Hellwig <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12mmc: block: cleanup gendisk creationChristoph Hellwig1-32/+17
Restructure mmc_blk_probe to avoid a failure path with a half created disk. Signed-off-by: Christoph Hellwig <[email protected]> Acked-by: Ulf Hansson <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-12mmc: block: let device_add_disk create disk attributesChristoph Hellwig1-57/+45
Pass the attribute group for the attributes on the gendisk to device_add_disk so that they are created atomically with the disk creation. Signed-off-by: Christoph Hellwig <[email protected]> Acked-by: Ulf Hansson <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-11block: move some macros to blkdev.hGuoqing Jiang5-10/+4
Move them (PAGE_SECTORS_SHIFT, PAGE_SECTORS and SECTOR_MASK) to the generic header file to remove redundancy. Signed-off-by: Guoqing Jiang <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-10writeback: make the laptop_mode prototypes available unconditionallyChristoph Hellwig1-5/+0
Fix the !CONFIG_BLOCK build after the recent cleanup. Fixes: 5ed964f8e54e ("mm: hide laptop_mode_wb_timer entirely behind the BDI API") Reported-by: Stephen Rothwell <[email protected]> Signed-off-by: Christoph Hellwig <[email protected]> Signed-off-by: Jens Axboe <[email protected]>
2021-08-09block: return ELEVATOR_DISCARD_MERGE if possibleMing Lei5-16/+24
When merging one bio to request, if they are discard IO and the queue supports multi-range discard, we need to return ELEVATOR_DISCARD_MERGE because both block core and related drivers(nvme, virtio-blk) doesn't handle mixed discard io merge(traditional IO merge together with discard merge) well. Fix the issue by returning ELEVATOR_DISCARD_MERGE in this situation, so both blk-mq and drivers just need to handle multi-range discard. Reported-by: Oleksandr Natalenko <[email protected]> Signed-off-by: Ming Lei <[email protected]> Tested-by: Oleksandr Natalenko <[email protected]> Fixes: 2705dfb20947 ("block: fix discard request merge") Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-09block: remove the bd_bdi in struct block_deviceChristoph Hellwig7-20/+9
Just retrieve the bdi from the disk. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Jan Kara <[email protected]> Reviewed-by: Johannes Thumshirn <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-09block: move the bdi from the request_queue to the gendiskChristoph Hellwig14-63/+58
The backing device information only makes sense for file system I/O, and thus belongs into the gendisk and not the lower level request_queue structure. Move it there. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Johannes Thumshirn <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-09block: add a queue_has_disk helperChristoph Hellwig1-0/+1
Add a helper to check if a gendisk is associated with a request_queue. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Jan Kara <[email protected]> Reviewed-by: Johannes Thumshirn <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-09block: pass a gendisk to blk_queue_update_readaheadChristoph Hellwig6-8/+10
.. and rename the function to disk_update_readahead. This is in preparation for moving the BDI from the request_queue to the gendisk. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Jan Kara <[email protected]> Reviewed-by: Johannes Thumshirn <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
2021-08-09mm: hide laptop_mode_wb_timer entirely behind the BDI APIChristoph Hellwig3-7/+3
Don't leak the detaŃ–ls of the timer into the block layer, instead initialize the timer in bdi_alloc and delete it in bdi_unregister. Note that this means the timer is initialized (but not armed) for non-block queues as well now. Signed-off-by: Christoph Hellwig <[email protected]> Reviewed-by: Jan Kara <[email protected]> Reviewed-by: Johannes Thumshirn <[email protected]> Link: https://lore.kernel.org/r/[email protected] Signed-off-by: Jens Axboe <[email protected]>
Powered by cgit, Gruvboxed by Blaster4385.