linux/block/blk-merge.c

1250 lines
33 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 14:07:57 +00:00
// SPDX-License-Identifier: GPL-2.0
/*
* Functions related to segment and merge handling
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/blk-integrity.h>
#include <linux/scatterlist.h>
#include <linux/part_stat.h>
#include <linux/blk-cgroup.h>
#include <trace/events/block.h>
#include "blk.h"
#include "blk-mq-sched.h"
#include "blk-rq-qos.h"
#include "blk-throttle.h"
static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv)
{
*bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
}
static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv)
{
struct bvec_iter iter = bio->bi_iter;
int idx;
bio_get_first_bvec(bio, bv);
if (bv->bv_len == bio->bi_iter.bi_size)
return; /* this bio only has a single bvec */
bio_advance_iter(bio, &iter, iter.bi_size);
if (!iter.bi_bvec_done)
idx = iter.bi_idx - 1;
else /* in the middle of bvec */
idx = iter.bi_idx;
*bv = bio->bi_io_vec[idx];
/*
* iter.bi_bvec_done records actual length of the last bvec
* if this bio ends in the middle of one io vector
*/
if (iter.bi_bvec_done)
bv->bv_len = iter.bi_bvec_done;
}
static inline bool bio_will_gap(struct request_queue *q,
struct request *prev_rq, struct bio *prev, struct bio *next)
{
struct bio_vec pb, nb;
if (!bio_has_data(prev) || !queue_virt_boundary(q))
return false;
/*
* Don't merge if the 1st bio starts with non-zero offset, otherwise it
* is quite difficult to respect the sg gap limit. We work hard to
* merge a huge number of small single bios in case of mkfs.
*/
if (prev_rq)
bio_get_first_bvec(prev_rq->bio, &pb);
else
bio_get_first_bvec(prev, &pb);
if (pb.bv_offset & queue_virt_boundary(q))
return true;
/*
* We don't need to worry about the situation that the merged segment
* ends in unaligned virt boundary:
*
* - if 'pb' ends aligned, the merged segment ends aligned
* - if 'pb' ends unaligned, the next bio must include
* one single bvec of 'nb', otherwise the 'nb' can't
* merge with 'pb'
*/
bio_get_last_bvec(prev, &pb);
bio_get_first_bvec(next, &nb);
if (biovec_phys_mergeable(q, &pb, &nb))
return false;
return __bvec_gap_to_prev(&q->limits, &pb, nb.bv_offset);
}
static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
{
return bio_will_gap(req->q, req, req->biotail, bio);
}
static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
{
return bio_will_gap(req->q, NULL, bio, req->bio);
}
/*
* The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size
* is defined as 'unsigned int', meantime it has to be aligned to with the
* logical block size, which is the minimum accepted unit by hardware.
*/
static unsigned int bio_allowed_max_sectors(const struct queue_limits *lim)
{
return round_down(UINT_MAX, lim->logical_block_size) >> SECTOR_SHIFT;
}
static struct bio *bio_split_discard(struct bio *bio,
const struct queue_limits *lim,
unsigned *nsegs, struct bio_set *bs)
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
{
unsigned int max_discard_sectors, granularity;
sector_t tmp;
unsigned split_sectors;
*nsegs = 1;
granularity = max(lim->discard_granularity >> 9, 1U);
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
max_discard_sectors =
min(lim->max_discard_sectors, bio_allowed_max_sectors(lim));
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
max_discard_sectors -= max_discard_sectors % granularity;
if (unlikely(!max_discard_sectors))
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
return NULL;
if (bio_sectors(bio) <= max_discard_sectors)
return NULL;
split_sectors = max_discard_sectors;
/*
* If the next starting sector would be misaligned, stop the discard at
* the previous aligned sector.
*/
tmp = bio->bi_iter.bi_sector + split_sectors -
((lim->discard_alignment >> 9) % granularity);
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
tmp = sector_div(tmp, granularity);
if (split_sectors > tmp)
split_sectors -= tmp;
return bio_split(bio, split_sectors, GFP_NOIO, bs);
}
static struct bio *bio_split_write_zeroes(struct bio *bio,
const struct queue_limits *lim,
unsigned *nsegs, struct bio_set *bs)
{
*nsegs = 0;
if (!lim->max_write_zeroes_sectors)
return NULL;
if (bio_sectors(bio) <= lim->max_write_zeroes_sectors)
return NULL;
return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs);
}
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
static inline unsigned int blk_boundary_sectors(const struct queue_limits *lim,
bool is_atomic)
{
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
/*
* chunk_sectors must be a multiple of atomic_write_boundary_sectors if
* both non-zero.
*/
if (is_atomic && lim->atomic_write_boundary_sectors)
return lim->atomic_write_boundary_sectors;
return lim->chunk_sectors;
}
/*
* Return the maximum number of sectors from the start of a bio that may be
* submitted as a single request to a block device. If enough sectors remain,
* align the end to the physical block size. Otherwise align the end to the
* logical block size. This approach minimizes the number of non-aligned
* requests that are submitted to a block device if the start of a bio is not
* aligned to a physical block boundary.
*/
static inline unsigned get_max_io_size(struct bio *bio,
const struct queue_limits *lim)
{
unsigned pbs = lim->physical_block_size >> SECTOR_SHIFT;
unsigned lbs = lim->logical_block_size >> SECTOR_SHIFT;
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
bool is_atomic = bio->bi_opf & REQ_ATOMIC;
unsigned boundary_sectors = blk_boundary_sectors(lim, is_atomic);
unsigned max_sectors, start, end;
/*
* We ignore lim->max_sectors for atomic writes because it may less
* than the actual bio size, which we cannot tolerate.
*/
if (is_atomic)
max_sectors = lim->atomic_write_max_sectors;
else
max_sectors = lim->max_sectors;
if (boundary_sectors) {
max_sectors = min(max_sectors,
blk_boundary_sectors_left(bio->bi_iter.bi_sector,
boundary_sectors));
}
start = bio->bi_iter.bi_sector & (pbs - 1);
end = (start + max_sectors) & ~(pbs - 1);
if (end > start)
return end - start;
return max_sectors & ~(lbs - 1);
}
/**
* get_max_segment_size() - maximum number of bytes to add as a single segment
* @lim: Request queue limits.
* @paddr: address of the range to add
* @len: maximum length available to add at @paddr
*
* Returns the maximum number of bytes of the range starting at @paddr that can
* be added to a single segment.
*/
static inline unsigned get_max_segment_size(const struct queue_limits *lim,
phys_addr_t paddr, unsigned int len)
{
/*
* Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1
* after having calculated the minimum.
*/
return min_t(unsigned long, len,
min(lim->seg_boundary_mask - (lim->seg_boundary_mask & paddr),
(unsigned long)lim->max_segment_size - 1) + 1);
}
/**
* bvec_split_segs - verify whether or not a bvec should be split in the middle
* @lim: [in] queue limits to split based on
* @bv: [in] bvec to examine
* @nsegs: [in,out] Number of segments in the bio being built. Incremented
* by the number of segments from @bv that may be appended to that
* bio without exceeding @max_segs
* @bytes: [in,out] Number of bytes in the bio being built. Incremented
* by the number of bytes from @bv that may be appended to that
* bio without exceeding @max_bytes
* @max_segs: [in] upper bound for *@nsegs
* @max_bytes: [in] upper bound for *@bytes
*
* When splitting a bio, it can happen that a bvec is encountered that is too
* big to fit in a single segment and hence that it has to be split in the
* middle. This function verifies whether or not that should happen. The value
* %true is returned if and only if appending the entire @bv to a bio with
* *@nsegs segments and *@sectors sectors would make that bio unacceptable for
* the block driver.
*/
static bool bvec_split_segs(const struct queue_limits *lim,
const struct bio_vec *bv, unsigned *nsegs, unsigned *bytes,
unsigned max_segs, unsigned max_bytes)
{
unsigned max_len = min(max_bytes, UINT_MAX) - *bytes;
unsigned len = min(bv->bv_len, max_len);
unsigned total_len = 0;
unsigned seg_size = 0;
while (len && *nsegs < max_segs) {
seg_size = get_max_segment_size(lim, bvec_phys(bv) + total_len, len);
(*nsegs)++;
total_len += seg_size;
len -= seg_size;
if ((bv->bv_offset + total_len) & lim->virt_boundary_mask)
break;
}
*bytes += total_len;
/* tell the caller to split the bvec if it is too big to fit */
return len > 0 || bv->bv_len > max_len;
}
/**
* bio_split_rw - split a bio in two bios
* @bio: [in] bio to be split
* @lim: [in] queue limits to split based on
* @segs: [out] number of segments in the bio with the first half of the sectors
* @bs: [in] bio set to allocate the clone from
* @max_bytes: [in] maximum number of bytes per bio
*
* Clone @bio, update the bi_iter of the clone to represent the first sectors
* of @bio and update @bio->bi_iter to represent the remaining sectors. The
* following is guaranteed for the cloned bio:
* - That it has at most @max_bytes worth of data
* - That it has at most queue_max_segments(@q) segments.
*
* Except for discard requests the cloned bio will point at the bi_io_vec of
* the original bio. It is the responsibility of the caller to ensure that the
* original bio is not freed before the cloned bio. The caller is also
* responsible for ensuring that @bs is only destroyed after processing of the
* split bio has finished.
*/
struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
unsigned *segs, struct bio_set *bs, unsigned max_bytes)
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
{
struct bio_vec bv, bvprv, *bvprvp = NULL;
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
struct bvec_iter iter;
unsigned nsegs = 0, bytes = 0;
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
bio_for_each_bvec(bv, bio, iter) {
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
/*
* If the queue doesn't support SG gaps and adding this
* offset would create a gap, disallow it.
*/
if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv.bv_offset))
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
goto split;
if (nsegs < lim->max_segments &&
bytes + bv.bv_len <= max_bytes &&
bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
nsegs++;
bytes += bv.bv_len;
} else {
if (bvec_split_segs(lim, &bv, &nsegs, &bytes,
lim->max_segments, max_bytes))
goto split;
}
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
bvprv = bv;
bvprvp = &bvprv;
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
}
*segs = nsegs;
return NULL;
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
split:
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
if (bio->bi_opf & REQ_ATOMIC) {
bio->bi_status = BLK_STS_INVAL;
bio_endio(bio);
return ERR_PTR(-EINVAL);
}
/*
* We can't sanely support splitting for a REQ_NOWAIT bio. End it
* with EAGAIN if splitting is required and return an error pointer.
*/
if (bio->bi_opf & REQ_NOWAIT) {
bio->bi_status = BLK_STS_AGAIN;
bio_endio(bio);
return ERR_PTR(-EAGAIN);
}
*segs = nsegs;
block: disable iopoll for split bio iopoll is initially for small size, latency sensitive IO. It doesn't work well for big IO, especially when it needs to be split to multiple bios. In this case, the returned cookie of __submit_bio_noacct_mq() is indeed the cookie of the last split bio. The completion of *this* last split bio done by iopoll doesn't mean the whole original bio has completed. Callers of iopoll still need to wait for completion of other split bios. Besides bio splitting may cause more trouble for iopoll which isn't supposed to be used in case of big IO. iopoll for split bio may cause potential race if CPU migration happens during bio submission. Since the returned cookie is that of the last split bio, polling on the corresponding hardware queue doesn't help complete other split bios, if these split bios are enqueued into different hardware queues. Since interrupts are disabled for polling queues, the completion of these other split bios depends on timeout mechanism, thus causing a potential hang. iopoll for split bio may also cause hang for sync polling. Currently both the blkdev and iomap-based fs (ext4/xfs, etc) support sync polling in direct IO routine. These routines will submit bio without REQ_NOWAIT flag set, and then start sync polling in current process context. The process may hang in blk_mq_get_tag() if the submitted bio has to be split into multiple bios and can rapidly exhaust the queue depth. The process are waiting for the completion of the previously allocated requests, which should be reaped by the following polling, and thus causing a deadlock. To avoid these subtle trouble described above, just disable iopoll for split bio and return BLK_QC_T_NONE in this case. The side effect is that non-HIPRI IO also returns BLK_QC_T_NONE now. It should be acceptable since the returned cookie is never used for non-HIPRI IO. Suggested-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-11-26 09:18:52 +00:00
/*
* Individual bvecs might not be logical block aligned. Round down the
* split size so that each bio is properly block size aligned, even if
* we do not use the full hardware limits.
*/
bytes = ALIGN_DOWN(bytes, lim->logical_block_size);
block: disable iopoll for split bio iopoll is initially for small size, latency sensitive IO. It doesn't work well for big IO, especially when it needs to be split to multiple bios. In this case, the returned cookie of __submit_bio_noacct_mq() is indeed the cookie of the last split bio. The completion of *this* last split bio done by iopoll doesn't mean the whole original bio has completed. Callers of iopoll still need to wait for completion of other split bios. Besides bio splitting may cause more trouble for iopoll which isn't supposed to be used in case of big IO. iopoll for split bio may cause potential race if CPU migration happens during bio submission. Since the returned cookie is that of the last split bio, polling on the corresponding hardware queue doesn't help complete other split bios, if these split bios are enqueued into different hardware queues. Since interrupts are disabled for polling queues, the completion of these other split bios depends on timeout mechanism, thus causing a potential hang. iopoll for split bio may also cause hang for sync polling. Currently both the blkdev and iomap-based fs (ext4/xfs, etc) support sync polling in direct IO routine. These routines will submit bio without REQ_NOWAIT flag set, and then start sync polling in current process context. The process may hang in blk_mq_get_tag() if the submitted bio has to be split into multiple bios and can rapidly exhaust the queue depth. The process are waiting for the completion of the previously allocated requests, which should be reaped by the following polling, and thus causing a deadlock. To avoid these subtle trouble described above, just disable iopoll for split bio and return BLK_QC_T_NONE in this case. The side effect is that non-HIPRI IO also returns BLK_QC_T_NONE now. It should be acceptable since the returned cookie is never used for non-HIPRI IO. Suggested-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jeffle Xu <jefflexu@linux.alibaba.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-11-26 09:18:52 +00:00
/*
* Bio splitting may cause subtle trouble such as hang when doing sync
* iopoll in direct IO routine. Given performance gain of iopoll for
* big IO can be trival, disable iopoll when split needed.
*/
bio_clear_polled(bio);
return bio_split(bio, bytes >> SECTOR_SHIFT, GFP_NOIO, bs);
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
}
EXPORT_SYMBOL_GPL(bio_split_rw);
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
/**
* __bio_split_to_limits - split a bio to fit the queue limits
* @bio: bio to be split
* @lim: queue limits to split based on
* @nr_segs: returns the number of segments in the returned bio
*
* Check if @bio needs splitting based on the queue limits, and if so split off
* a bio fitting the limits from the beginning of @bio and return it. @bio is
* shortened to the remainder and re-submitted.
*
* The split bio is allocated from @q->bio_split, which is provided by the
* block layer.
*/
struct bio *__bio_split_to_limits(struct bio *bio,
const struct queue_limits *lim,
unsigned int *nr_segs)
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
{
struct bio_set *bs = &bio->bi_bdev->bd_disk->bio_split;
struct bio *split;
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
switch (bio_op(bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
split = bio_split_discard(bio, lim, nr_segs, bs);
break;
case REQ_OP_WRITE_ZEROES:
split = bio_split_write_zeroes(bio, lim, nr_segs, bs);
break;
default:
split = bio_split_rw(bio, lim, nr_segs, bs,
get_max_io_size(bio, lim) << SECTOR_SHIFT);
if (IS_ERR(split))
return NULL;
break;
}
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
if (split) {
/* there isn't chance to merge the split bio */
split->bi_opf |= REQ_NOMERGE;
blkcg_bio_issue_init(split);
bio_chain(split, bio);
trace_block_split(split, bio->bi_iter.bi_sector);
block: Introduce zone write plugging Zone write plugging implements a per-zone "plug" for write operations to control the submission and execution order of write operations to sequential write required zones of a zoned block device. Per-zone plugging guarantees that at any time there is at most only one write request per zone being executed. This mechanism is intended to replace zone write locking which implements a similar per-zone write throttling at the scheduler level, but is implemented only by mq-deadline. Unlike zone write locking which operates on requests, zone write plugging operates on BIOs. A zone write plug is simply a BIO list that is atomically manipulated using a spinlock and a kblockd submission work. A write BIO to a zone is "plugged" to delay its execution if a write BIO for the same zone was already issued, that is, if a write request for the same zone is being executed. The next plugged BIO is unplugged and issued once the write request completes. This mechanism allows to: - Untangle zone write ordering from block IO schedulers. This allows removing the restriction on using mq-deadline for writing to zoned block devices. Any block IO scheduler, including "none" can be used. - Zone write plugging operates on BIOs instead of requests. Plugged BIOs waiting for execution thus do not hold scheduling tags and thus are not preventing other BIOs from executing (reads or writes to other zones). Depending on the workload, this can significantly improve the device use (higher queue depth operation) and performance. - Both blk-mq (request based) zoned devices and BIO-based zoned devices (e.g. device mapper) can use zone write plugging. It is mandatory for the former but optional for the latter. BIO-based drivers can use zone write plugging to implement write ordering guarantees, or the drivers can implement their own if needed. - The code is less invasive in the block layer and is mostly limited to blk-zoned.c with some small changes in blk-mq.c, blk-merge.c and bio.c. Zone write plugging is implemented using struct blk_zone_wplug. This structure includes a spinlock, a BIO list and a work structure to handle the submission of plugged BIOs. Zone write plugs structures are managed using a per-disk hash table. Plugging of zone write BIOs is done using the function blk_zone_write_plug_bio() which returns false if a BIO execution does not need to be delayed and true otherwise. This function is called from blk_mq_submit_bio() after a BIO is split to avoid large BIOs spanning multiple zones which would cause mishandling of zone write plugs. This ichange enables by default zone write plugging for any mq request-based block device. BIO-based device drivers can also use zone write plugging by expliclty calling blk_zone_write_plug_bio() in their ->submit_bio method. For such devices, the driver must ensure that a BIO passed to blk_zone_write_plug_bio() is already split and not straddling zone boundaries. Only write and write zeroes BIOs are plugged. Zone write plugging does not introduce any significant overhead for other operations. A BIO that is being handled through zone write plugging is flagged using the new BIO flag BIO_ZONE_WRITE_PLUGGING. A request handling a BIO flagged with this new flag is flagged with the new RQF_ZONE_WRITE_PLUGGING flag. The completion of BIOs and requests flagged trigger respectively calls to the functions blk_zone_write_bio_endio() and blk_zone_write_complete_request(). The latter function is used to trigger submission of the next plugged BIO using the zone plug work. blk_zone_write_bio_endio() does the same for BIO-based devices. This ensures that at any time, at most one request (blk-mq devices) or one BIO (BIO-based devices) is being executed for any zone. The handling of zone write plugs using a per-zone plug spinlock maximizes parallelism and device usage by allowing multiple zones to be writen simultaneously without lock contention. Zone write plugging ignores flush BIOs without data. Hovever, any flush BIO that has data is always plugged so that the write part of the flush sequence is serialized with other regular writes. Given that any BIO handled through zone write plugging will be the only BIO in flight for the target zone when it is executed, the unplugging and submission of a BIO will have no chance of successfully merging with plugged requests or requests in the scheduler. To overcome this potential performance degradation, blk_mq_submit_bio() calls the function blk_zone_write_plug_attempt_merge() to try to merge other plugged BIOs with the one just unplugged and submitted. Successful merging is signaled using blk_zone_write_plug_bio_merged(), called from bio_attempt_back_merge(). Furthermore, to avoid recalculating the number of segments of plugged BIOs to attempt merging, the number of segments of a plugged BIO is saved using the new struct bio field __bi_nr_segments. To avoid growing the size of struct bio, this field is added as a union with the bio_cookie field. This is safe to do as polling is always disabled for plugged BIOs. When BIOs are plugged in a zone write plug, the device request queue usage counter is always incremented. This reference is kept and reused for blk-mq devices when the plugged BIO is unplugged and submitted again using submit_bio_noacct_nocheck(). For this case, the unplugged BIO is already flagged with BIO_ZONE_WRITE_PLUGGING and blk_mq_submit_bio() proceeds directly to allocating a new request for the BIO, re-using the usage reference count taken when the BIO was plugged. This extra reference count is dropped in blk_zone_write_plug_attempt_merge() for any plugged BIO that is successfully merged. Given that BIO-based devices will not take this path, the extra reference is dropped after a plugged BIO is unplugged and submitted. Zone write plugs are dynamically allocated and managed using a hash table (an array of struct hlist_head) with RCU protection. A zone write plug is allocated when a write BIO is received for the zone and not freed until the zone is fully written, reset or finished. To detect when a zone write plug can be freed, the write state of each zone is tracked using a write pointer offset which corresponds to the offset of a zone write pointer relative to the zone start. Write operations always increment this write pointer offset. Zone reset operations set it to 0 and zone finish operations set it to the zone size. If a write error happens, the wp_offset value of a zone write plug may become incorrect and out of sync with the device managed write pointer. This is handled using the zone write plug flag BLK_ZONE_WPLUG_ERROR. The function blk_zone_wplug_handle_error() is called from the new disk zone write plug work when this flag is set. This function executes a report zone to update the zone write pointer offset to the current value as indicated by the device. The disk zone write plug work is scheduled whenever a BIO flagged with BIO_ZONE_WRITE_PLUGGING completes with an error or when bio_zone_wplug_prepare_bio() detects an unaligned write. Once scheduled, the disk zone write plugs work keeps running until all zone errors are handled. To match the new data structures used for zoned disks, the function disk_free_zone_bitmaps() is renamed to the more generic disk_free_zone_resources(). The function disk_init_zone_resources() is also introduced to initialize zone write plugs resources when a gendisk is allocated. In order to guarantee that the user can simultaneously write up to a number of zones equal to a device max active zone limit or max open zone limit, zone write plugs are allocated using a mempool sized to the maximum of these 2 device limits. For a device that does not have active and open zone limits, 128 is used as the default mempool size. If a change to the device active and open zone limits is detected, the disk mempool is resized when blk_revalidate_disk_zones() is executed. This commit contains contributions from Christoph Hellwig <hch@lst.de>. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Tested-by: Hans Holmberg <hans.holmberg@wdc.com> Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Link: https://lore.kernel.org/r/20240408014128.205141-8-dlemoal@kernel.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-04-08 01:41:07 +00:00
WARN_ON_ONCE(bio_zone_write_plugging(bio));
submit_bio_noacct(bio);
return split;
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
}
return bio;
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
}
/**
* bio_split_to_limits - split a bio to fit the queue limits
* @bio: bio to be split
*
* Check if @bio needs splitting based on the queue limits of @bio->bi_bdev, and
* if so split off a bio fitting the limits from the beginning of @bio and
* return it. @bio is shortened to the remainder and re-submitted.
*
* The split bio is allocated from @q->bio_split, which is provided by the
* block layer.
*/
struct bio *bio_split_to_limits(struct bio *bio)
{
const struct queue_limits *lim = &bdev_get_queue(bio->bi_bdev)->limits;
unsigned int nr_segs;
if (bio_may_exceed_limits(bio, lim))
return __bio_split_to_limits(bio, lim, &nr_segs);
return bio;
}
EXPORT_SYMBOL(bio_split_to_limits);
block: make generic_make_request handle arbitrarily sized bios The way the block layer is currently written, it goes to great lengths to avoid having to split bios; upper layer code (such as bio_add_page()) checks what the underlying device can handle and tries to always create bios that don't need to be split. But this approach becomes unwieldy and eventually breaks down with stacked devices and devices with dynamic limits, and it adds a lot of complexity. If the block layer could split bios as needed, we could eliminate a lot of complexity elsewhere - particularly in stacked drivers. Code that creates bios can then create whatever size bios are convenient, and more importantly stacked drivers don't have to deal with both their own bio size limitations and the limitations of the (potentially multiple) devices underneath them. In the future this will let us delete merge_bvec_fn and a bunch of other code. We do this by adding calls to blk_queue_split() to the various make_request functions that need it - a few can already handle arbitrary size bios. Note that we add the call _after_ any call to blk_queue_bounce(); this means that blk_queue_split() and blk_recalc_rq_segments() don't need to be concerned with bouncing affecting segment merging. Some make_request_fn() callbacks were simple enough to audit and verify they don't need blk_queue_split() calls. The skipped ones are: * nfhd_make_request (arch/m68k/emu/nfblock.c) * axon_ram_make_request (arch/powerpc/sysdev/axonram.c) * simdisk_make_request (arch/xtensa/platforms/iss/simdisk.c) * brd_make_request (ramdisk - drivers/block/brd.c) * mtip_submit_request (drivers/block/mtip32xx/mtip32xx.c) * loop_make_request * null_queue_bio * bcache's make_request fns Some others are almost certainly safe to remove now, but will be left for future patches. Cc: Jens Axboe <axboe@kernel.dk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Ming Lei <ming.lei@canonical.com> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: drbd-user@lists.linbit.com Cc: Jiri Kosina <jkosina@suse.cz> Cc: Geoff Levand <geoff@infradead.org> Cc: Jim Paris <jim@jtan.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Oleg Drokin <oleg.drokin@intel.com> Cc: Andreas Dilger <andreas.dilger@intel.com> Acked-by: NeilBrown <neilb@suse.de> (for the 'md/md.c' bits) Acked-by: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com> [dpark: skip more mq-based drivers, resolve merge conflicts, etc.] Signed-off-by: Dongsu Park <dpark@posteo.net> Signed-off-by: Ming Lin <ming.l@ssi.samsung.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2015-04-24 05:37:18 +00:00
unsigned int blk_recalc_rq_segments(struct request *rq)
{
unsigned int nr_phys_segs = 0;
unsigned int bytes = 0;
struct req_iterator iter;
struct bio_vec bv;
if (!rq->bio)
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 08:03:10 +00:00
return 0;
switch (bio_op(rq->bio)) {
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
block: recalculate segment count for multi-segment discards correctly When a stacked block device inserts a request into another block device using blk_insert_cloned_request, the request's nr_phys_segments field gets recalculated by a call to blk_recalc_rq_segments in blk_cloned_rq_check_limits. But blk_recalc_rq_segments does not know how to handle multi-segment discards. For disk types which can handle multi-segment discards like nvme, this results in discard requests which claim a single segment when it should report several, triggering a warning in nvme and causing nvme to fail the discard from the invalid state. WARNING: CPU: 5 PID: 191 at drivers/nvme/host/core.c:700 nvme_setup_discard+0x170/0x1e0 [nvme_core] ... nvme_setup_cmd+0x217/0x270 [nvme_core] nvme_loop_queue_rq+0x51/0x1b0 [nvme_loop] __blk_mq_try_issue_directly+0xe7/0x1b0 blk_mq_request_issue_directly+0x41/0x70 ? blk_account_io_start+0x40/0x50 dm_mq_queue_rq+0x200/0x3e0 blk_mq_dispatch_rq_list+0x10a/0x7d0 ? __sbitmap_queue_get+0x25/0x90 ? elv_rb_del+0x1f/0x30 ? deadline_remove_request+0x55/0xb0 ? dd_dispatch_request+0x181/0x210 __blk_mq_do_dispatch_sched+0x144/0x290 ? bio_attempt_discard_merge+0x134/0x1f0 __blk_mq_sched_dispatch_requests+0x129/0x180 blk_mq_sched_dispatch_requests+0x30/0x60 __blk_mq_run_hw_queue+0x47/0xe0 __blk_mq_delay_run_hw_queue+0x15b/0x170 blk_mq_sched_insert_requests+0x68/0xe0 blk_mq_flush_plug_list+0xf0/0x170 blk_finish_plug+0x36/0x50 xlog_cil_committed+0x19f/0x290 [xfs] xlog_cil_process_committed+0x57/0x80 [xfs] xlog_state_do_callback+0x1e0/0x2a0 [xfs] xlog_ioend_work+0x2f/0x80 [xfs] process_one_work+0x1b6/0x350 worker_thread+0x53/0x3e0 ? process_one_work+0x350/0x350 kthread+0x11b/0x140 ? __kthread_bind_mask+0x60/0x60 ret_from_fork+0x22/0x30 This patch fixes blk_recalc_rq_segments to be aware of devices which can have multi-segment discards. It calculates the correct discard segment count by counting the number of bio as each discard bio is considered its own segment. Fixes: 1e739730c5b9 ("block: optionally merge discontiguous discard bios into a single request") Signed-off-by: David Jeffery <djeffery@redhat.com> Reviewed-by: Ming Lei <ming.lei@redhat.com> Reviewed-by: Laurence Oberman <loberman@redhat.com> Link: https://lore.kernel.org/r/20210211143807.GA115624@redhat Signed-off-by: Jens Axboe <axboe@kernel.dk>
2021-02-11 14:38:07 +00:00
if (queue_max_discard_segments(rq->q) > 1) {
struct bio *bio = rq->bio;
for_each_bio(bio)
nr_phys_segs++;
return nr_phys_segs;
}
return 1;
case REQ_OP_WRITE_ZEROES:
return 0;
default:
break;
}
rq_for_each_bvec(bv, rq, iter)
bvec_split_segs(&rq->q->limits, &bv, &nr_phys_segs, &bytes,
UINT_MAX, UINT_MAX);
block: reduce stack footprint of blk_recount_segments() blk_recalc_rq_segments() requires a request structure passed in, which we don't have from blk_recount_segments(). So the latter allocates one on the stack, using > 400 bytes of stack for that. This can cause us to spill over one page of stack from ext4 at least: 0) 4560 400 blk_recount_segments+0x43/0x62 1) 4160 32 bio_phys_segments+0x1c/0x24 2) 4128 32 blk_rq_bio_prep+0x2a/0xf9 3) 4096 32 init_request_from_bio+0xf9/0xfe 4) 4064 112 __make_request+0x33c/0x3f6 5) 3952 144 generic_make_request+0x2d1/0x321 6) 3808 64 submit_bio+0xb9/0xc3 7) 3744 48 submit_bh+0xea/0x10e 8) 3696 368 ext4_mb_init_cache+0x257/0xa6a [ext4] 9) 3328 288 ext4_mb_regular_allocator+0x421/0xcd9 [ext4] 10) 3040 160 ext4_mb_new_blocks+0x211/0x4b4 [ext4] 11) 2880 336 ext4_ext_get_blocks+0xb61/0xd45 [ext4] 12) 2544 96 ext4_get_blocks_wrap+0xf2/0x200 [ext4] 13) 2448 80 ext4_da_get_block_write+0x6e/0x16b [ext4] 14) 2368 352 mpage_da_map_blocks+0x7e/0x4b3 [ext4] 15) 2016 352 ext4_da_writepages+0x2ce/0x43c [ext4] 16) 1664 32 do_writepages+0x2d/0x3c 17) 1632 144 __writeback_single_inode+0x162/0x2cd 18) 1488 96 generic_sync_sb_inodes+0x1e3/0x32b 19) 1392 16 sync_sb_inodes+0xe/0x10 20) 1376 48 writeback_inodes+0x69/0xb3 21) 1328 208 balance_dirty_pages_ratelimited_nr+0x187/0x2f9 22) 1120 224 generic_file_buffered_write+0x1d4/0x2c4 23) 896 176 __generic_file_aio_write_nolock+0x35f/0x393 24) 720 80 generic_file_aio_write+0x6c/0xc8 25) 640 80 ext4_file_write+0xa9/0x137 [ext4] 26) 560 320 do_sync_write+0xf0/0x137 27) 240 48 vfs_write+0xb3/0x13c 28) 192 64 sys_write+0x4c/0x74 29) 128 128 system_call_fastpath+0x16/0x1b Split the segment counting out into a __blk_recalc_rq_segments() helper to avoid allocating an onstack request just for checking the physical segment count. Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-02-23 08:03:10 +00:00
return nr_phys_segs;
}
static inline struct scatterlist *blk_next_sg(struct scatterlist **sg,
struct scatterlist *sglist)
{
if (!*sg)
return sglist;
/*
* If the driver previously mapped a shorter list, we could see a
* termination bit prematurely unless it fully inits the sg table
* on each mapping. We KNOW that there must be more entries here
* or the driver would be buggy, so force clear the termination bit
* to avoid doing a full sg_init_table() in drivers for each command.
*/
sg_unmark_end(*sg);
return sg_next(*sg);
}
static unsigned blk_bvec_map_sg(struct request_queue *q,
struct bio_vec *bvec, struct scatterlist *sglist,
struct scatterlist **sg)
{
unsigned nbytes = bvec->bv_len;
unsigned nsegs = 0, total = 0;
while (nbytes > 0) {
unsigned offset = bvec->bv_offset + total;
unsigned len = get_max_segment_size(&q->limits,
bvec_phys(bvec) + total, nbytes);
struct page *page = bvec->bv_page;
/*
* Unfortunately a fair number of drivers barf on scatterlists
* that have an offset larger than PAGE_SIZE, despite other
* subsystems dealing with that invariant just fine. For now
* stick to the legacy format where we never present those from
* the block layer, but the code below should be removed once
* these offenders (mostly MMC/SD drivers) are fixed.
*/
page += (offset >> PAGE_SHIFT);
offset &= ~PAGE_MASK;
*sg = blk_next_sg(sg, sglist);
sg_set_page(*sg, page, len, offset);
total += len;
nbytes -= len;
nsegs++;
}
return nsegs;
}
static inline int __blk_bvec_map_sg(struct bio_vec bv,
struct scatterlist *sglist, struct scatterlist **sg)
{
*sg = blk_next_sg(sg, sglist);
sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
return 1;
}
/* only try to merge bvecs into one sg if they are from two bios */
static inline bool
__blk_segment_map_sg_merge(struct request_queue *q, struct bio_vec *bvec,
struct bio_vec *bvprv, struct scatterlist **sg)
{
int nbytes = bvec->bv_len;
if (!*sg)
return false;
if ((*sg)->length + nbytes > queue_max_segment_size(q))
return false;
if (!biovec_phys_mergeable(q, bvprv, bvec))
return false;
(*sg)->length += nbytes;
return true;
}
static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio,
struct scatterlist *sglist,
struct scatterlist **sg)
{
treewide: Remove uninitialized_var() usage Using uninitialized_var() is dangerous as it papers over real bugs[1] (or can in the future), and suppresses unrelated compiler warnings (e.g. "unused variable"). If the compiler thinks it is uninitialized, either simply initialize the variable or make compiler changes. In preparation for removing[2] the[3] macro[4], remove all remaining needless uses with the following script: git grep '\buninitialized_var\b' | cut -d: -f1 | sort -u | \ xargs perl -pi -e \ 's/\buninitialized_var\(([^\)]+)\)/\1/g; s:\s*/\* (GCC be quiet|to make compiler happy) \*/$::g;' drivers/video/fbdev/riva/riva_hw.c was manually tweaked to avoid pathological white-space. No outstanding warnings were found building allmodconfig with GCC 9.3.0 for x86_64, i386, arm64, arm, powerpc, powerpc64le, s390x, mips, sparc64, alpha, and m68k. [1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/ [2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/ [3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/ [4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/ Reviewed-by: Leon Romanovsky <leonro@mellanox.com> # drivers/infiniband and mlx4/mlx5 Acked-by: Jason Gunthorpe <jgg@mellanox.com> # IB Acked-by: Kalle Valo <kvalo@codeaurora.org> # wireless drivers Reviewed-by: Chao Yu <yuchao0@huawei.com> # erofs Signed-off-by: Kees Cook <keescook@chromium.org>
2020-06-03 20:09:38 +00:00
struct bio_vec bvec, bvprv = { NULL };
struct bvec_iter iter;
int nsegs = 0;
bool new_bio = false;
for_each_bio(bio) {
bio_for_each_bvec(bvec, bio, iter) {
/*
* Only try to merge bvecs from two bios given we
* have done bio internal merge when adding pages
* to bio
*/
if (new_bio &&
__blk_segment_map_sg_merge(q, &bvec, &bvprv, sg))
goto next_bvec;
if (bvec.bv_offset + bvec.bv_len <= PAGE_SIZE)
nsegs += __blk_bvec_map_sg(bvec, sglist, sg);
else
nsegs += blk_bvec_map_sg(q, &bvec, sglist, sg);
next_bvec:
new_bio = false;
}
if (likely(bio->bi_iter.bi_size)) {
bvprv = bvec;
new_bio = true;
}
}
return nsegs;
}
/*
* map a request to scatterlist, return number of sg entries setup. Caller
* must make sure sg can hold rq->nr_phys_segments entries
*/
int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
struct scatterlist *sglist, struct scatterlist **last_sg)
{
int nsegs = 0;
if (rq->rq_flags & RQF_SPECIAL_PAYLOAD)
nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg);
else if (rq->bio)
nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg);
if (*last_sg)
sg_mark_end(*last_sg);
/*
* Something must have been wrong if the figured number of
* segment is bigger than number of req's physical segments
*/
WARN_ON(nsegs > blk_rq_nr_phys_segments(rq));
return nsegs;
}
EXPORT_SYMBOL(__blk_rq_map_sg);
static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
sector_t offset)
{
struct request_queue *q = rq->q;
struct queue_limits *lim = &q->limits;
unsigned int max_sectors, boundary_sectors;
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
bool is_atomic = rq->cmd_flags & REQ_ATOMIC;
if (blk_rq_is_passthrough(rq))
return q->limits.max_hw_sectors;
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
boundary_sectors = blk_boundary_sectors(lim, is_atomic);
max_sectors = blk_queue_get_max_sectors(rq);
if (!boundary_sectors ||
req_op(rq) == REQ_OP_DISCARD ||
req_op(rq) == REQ_OP_SECURE_ERASE)
return max_sectors;
return min(max_sectors,
blk_boundary_sectors_left(offset, boundary_sectors));
}
static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
unsigned int nr_phys_segs)
{
if (!blk_cgroup_mergeable(req, bio))
goto no_merge;
if (blk_integrity_merge_bio(req->q, req, bio) == false)
goto no_merge;
/* discard request merge won't add new segment */
if (req_op(req) == REQ_OP_DISCARD)
return 1;
if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req))
goto no_merge;
/*
* This will form the start of a new hw segment. Bump both
* counters.
*/
req->nr_phys_segments += nr_phys_segs;
return 1;
no_merge:
req_set_nomerge(req->q, req);
return 0;
}
int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs)
{
if (req_gap_back_merge(req, bio))
return 0;
if (blk_integrity_rq(req) &&
integrity_req_gap_back_merge(req, bio))
return 0;
block: Inline encryption support for blk-mq We must have some way of letting a storage device driver know what encryption context it should use for en/decrypting a request. However, it's the upper layers (like the filesystem/fscrypt) that know about and manages encryption contexts. As such, when the upper layer submits a bio to the block layer, and this bio eventually reaches a device driver with support for inline encryption, the device driver will need to have been told the encryption context for that bio. We want to communicate the encryption context from the upper layer to the storage device along with the bio, when the bio is submitted to the block layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can represent an encryption context (note that we can't use the bi_private field in struct bio to do this because that field does not function to pass information across layers in the storage stack). We also introduce various functions to manipulate the bio_crypt_ctx and make the bio/request merging logic aware of the bio_crypt_ctx. We also make changes to blk-mq to make it handle bios with encryption contexts. blk-mq can merge many bios into the same request. These bios need to have contiguous data unit numbers (the necessary changes to blk-merge are also made to ensure this) - as such, it suffices to keep the data unit number of just the first bio, since that's all a storage driver needs to infer the data unit number to use for each data block in each bio in a request. blk-mq keeps track of the encryption context to be used for all the bios in a request with the request's rq_crypt_ctx. When the first bio is added to an empty request, blk-mq will program the encryption context of that bio into the request_queue's keyslot manager, and store the returned keyslot in the request's rq_crypt_ctx. All the functions to operate on encryption contexts are in blk-crypto.c. Upper layers only need to call bio_crypt_set_ctx with the encryption key, algorithm and data_unit_num; they don't have to worry about getting a keyslot for each encryption context, as blk-mq/blk-crypto handles that. Blk-crypto also makes it possible for request-based layered devices like dm-rq to make use of inline encryption hardware by cloning the rq_crypt_ctx and programming a keyslot in the new request_queue when necessary. Note that any user of the block layer can submit bios with an encryption context, such as filesystems, device-mapper targets, etc. Signed-off-by: Satya Tangirala <satyat@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-05-14 00:37:18 +00:00
if (!bio_crypt_ctx_back_mergeable(req, bio))
return 0;
if (blk_rq_sectors(req) + bio_sectors(bio) >
blk_rq_get_max_sectors(req, blk_rq_pos(req))) {
req_set_nomerge(req->q, req);
return 0;
}
return ll_new_hw_segment(req, bio, nr_segs);
}
static int ll_front_merge_fn(struct request *req, struct bio *bio,
unsigned int nr_segs)
{
if (req_gap_front_merge(req, bio))
return 0;
if (blk_integrity_rq(req) &&
integrity_req_gap_front_merge(req, bio))
return 0;
block: Inline encryption support for blk-mq We must have some way of letting a storage device driver know what encryption context it should use for en/decrypting a request. However, it's the upper layers (like the filesystem/fscrypt) that know about and manages encryption contexts. As such, when the upper layer submits a bio to the block layer, and this bio eventually reaches a device driver with support for inline encryption, the device driver will need to have been told the encryption context for that bio. We want to communicate the encryption context from the upper layer to the storage device along with the bio, when the bio is submitted to the block layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can represent an encryption context (note that we can't use the bi_private field in struct bio to do this because that field does not function to pass information across layers in the storage stack). We also introduce various functions to manipulate the bio_crypt_ctx and make the bio/request merging logic aware of the bio_crypt_ctx. We also make changes to blk-mq to make it handle bios with encryption contexts. blk-mq can merge many bios into the same request. These bios need to have contiguous data unit numbers (the necessary changes to blk-merge are also made to ensure this) - as such, it suffices to keep the data unit number of just the first bio, since that's all a storage driver needs to infer the data unit number to use for each data block in each bio in a request. blk-mq keeps track of the encryption context to be used for all the bios in a request with the request's rq_crypt_ctx. When the first bio is added to an empty request, blk-mq will program the encryption context of that bio into the request_queue's keyslot manager, and store the returned keyslot in the request's rq_crypt_ctx. All the functions to operate on encryption contexts are in blk-crypto.c. Upper layers only need to call bio_crypt_set_ctx with the encryption key, algorithm and data_unit_num; they don't have to worry about getting a keyslot for each encryption context, as blk-mq/blk-crypto handles that. Blk-crypto also makes it possible for request-based layered devices like dm-rq to make use of inline encryption hardware by cloning the rq_crypt_ctx and programming a keyslot in the new request_queue when necessary. Note that any user of the block layer can submit bios with an encryption context, such as filesystems, device-mapper targets, etc. Signed-off-by: Satya Tangirala <satyat@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-05-14 00:37:18 +00:00
if (!bio_crypt_ctx_front_mergeable(req, bio))
return 0;
if (blk_rq_sectors(req) + bio_sectors(bio) >
blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) {
req_set_nomerge(req->q, req);
return 0;
}
return ll_new_hw_segment(req, bio, nr_segs);
}
blk-mq: fix discard merge with scheduler attached I ran into an issue on my laptop that triggered a bug on the discard path: WARNING: CPU: 2 PID: 207 at drivers/nvme/host/core.c:527 nvme_setup_cmd+0x3d3/0x430 Modules linked in: rfcomm fuse ctr ccm bnep arc4 binfmt_misc snd_hda_codec_hdmi nls_iso8859_1 nls_cp437 vfat snd_hda_codec_conexant fat snd_hda_codec_generic iwlmvm snd_hda_intel snd_hda_codec snd_hwdep mac80211 snd_hda_core snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq x86_pkg_temp_thermal intel_powerclamp kvm_intel uvcvideo iwlwifi btusb snd_seq_device videobuf2_vmalloc btintel videobuf2_memops kvm snd_timer videobuf2_v4l2 bluetooth irqbypass videobuf2_core aesni_intel aes_x86_64 crypto_simd cryptd snd glue_helper videodev cfg80211 ecdh_generic soundcore hid_generic usbhid hid i915 psmouse e1000e ptp pps_core xhci_pci xhci_hcd intel_gtt CPU: 2 PID: 207 Comm: jbd2/nvme0n1p7- Tainted: G U 4.15.0+ #176 Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET59W (1.33 ) 12/19/2017 RIP: 0010:nvme_setup_cmd+0x3d3/0x430 RSP: 0018:ffff880423e9f838 EFLAGS: 00010217 RAX: 0000000000000000 RBX: ffff880423e9f8c8 RCX: 0000000000010000 RDX: ffff88022b200010 RSI: 0000000000000002 RDI: 00000000327f0000 RBP: ffff880421251400 R08: ffff88022b200000 R09: 0000000000000009 R10: 0000000000000000 R11: 0000000000000000 R12: 000000000000ffff R13: ffff88042341e280 R14: 000000000000ffff R15: ffff880421251440 FS: 0000000000000000(0000) GS:ffff880441500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055b684795030 CR3: 0000000002e09006 CR4: 00000000001606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: nvme_queue_rq+0x40/0xa00 ? __sbitmap_queue_get+0x24/0x90 ? blk_mq_get_tag+0xa3/0x250 ? wait_woken+0x80/0x80 ? blk_mq_get_driver_tag+0x97/0xf0 blk_mq_dispatch_rq_list+0x7b/0x4a0 ? deadline_remove_request+0x49/0xb0 blk_mq_do_dispatch_sched+0x4f/0xc0 blk_mq_sched_dispatch_requests+0x106/0x170 __blk_mq_run_hw_queue+0x53/0xa0 __blk_mq_delay_run_hw_queue+0x83/0xa0 blk_mq_run_hw_queue+0x6c/0xd0 blk_mq_sched_insert_request+0x96/0x140 __blk_mq_try_issue_directly+0x3d/0x190 blk_mq_try_issue_directly+0x30/0x70 blk_mq_make_request+0x1a4/0x6a0 generic_make_request+0xfd/0x2f0 ? submit_bio+0x5c/0x110 submit_bio+0x5c/0x110 ? __blkdev_issue_discard+0x152/0x200 submit_bio_wait+0x43/0x60 ext4_process_freed_data+0x1cd/0x440 ? account_page_dirtied+0xe2/0x1a0 ext4_journal_commit_callback+0x4a/0xc0 jbd2_journal_commit_transaction+0x17e2/0x19e0 ? kjournald2+0xb0/0x250 kjournald2+0xb0/0x250 ? wait_woken+0x80/0x80 ? commit_timeout+0x10/0x10 kthread+0x111/0x130 ? kthread_create_worker_on_cpu+0x50/0x50 ? do_group_exit+0x3a/0xa0 ret_from_fork+0x1f/0x30 Code: 73 89 c1 83 ce 10 c1 e1 10 09 ca 83 f8 04 0f 87 0f ff ff ff 8b 4d 20 48 8b 7d 00 c1 e9 09 48 01 8c c7 00 08 00 00 e9 f8 fe ff ff <0f> ff 4c 89 c7 41 bc 0a 00 00 00 e8 0d 78 d6 ff e9 a1 fc ff ff ---[ end trace 50d361cc444506c8 ]--- print_req_error: I/O error, dev nvme0n1, sector 847167488 Decoding the assembly, the request claims to have 0xffff segments, while nvme counts two. This turns out to be because we don't check for a data carrying request on the mq scheduler path, and since blk_phys_contig_segment() returns true for a non-data request, we decrement the initial segment count of 0 and end up with 0xffff in the unsigned short. There are a few issues here: 1) We should initialize the segment count for a discard to 1. 2) The discard merging is currently using the data limits for segments and sectors. Fix this up by having attempt_merge() correctly identify the request, and by initializing the segment count correctly for discards. This can only be triggered with mq-deadline on discard capable devices right now, which isn't a common configuration. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-01 21:01:02 +00:00
static bool req_attempt_discard_merge(struct request_queue *q, struct request *req,
struct request *next)
{
unsigned short segments = blk_rq_nr_discard_segments(req);
if (segments >= queue_max_discard_segments(q))
goto no_merge;
if (blk_rq_sectors(req) + bio_sectors(next->bio) >
blk_rq_get_max_sectors(req, blk_rq_pos(req)))
goto no_merge;
req->nr_phys_segments = segments + blk_rq_nr_discard_segments(next);
return true;
no_merge:
req_set_nomerge(q, req);
return false;
}
static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
struct request *next)
{
int total_phys_segments;
if (req_gap_back_merge(req, next->bio))
return 0;
/*
* Will it become too large?
*/
if ((blk_rq_sectors(req) + blk_rq_sectors(next)) >
blk_rq_get_max_sectors(req, blk_rq_pos(req)))
return 0;
total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
if (total_phys_segments > blk_rq_get_max_segments(req))
return 0;
if (!blk_cgroup_mergeable(req, next->bio))
return 0;
if (blk_integrity_merge_rq(q, req, next) == false)
return 0;
block: Inline encryption support for blk-mq We must have some way of letting a storage device driver know what encryption context it should use for en/decrypting a request. However, it's the upper layers (like the filesystem/fscrypt) that know about and manages encryption contexts. As such, when the upper layer submits a bio to the block layer, and this bio eventually reaches a device driver with support for inline encryption, the device driver will need to have been told the encryption context for that bio. We want to communicate the encryption context from the upper layer to the storage device along with the bio, when the bio is submitted to the block layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can represent an encryption context (note that we can't use the bi_private field in struct bio to do this because that field does not function to pass information across layers in the storage stack). We also introduce various functions to manipulate the bio_crypt_ctx and make the bio/request merging logic aware of the bio_crypt_ctx. We also make changes to blk-mq to make it handle bios with encryption contexts. blk-mq can merge many bios into the same request. These bios need to have contiguous data unit numbers (the necessary changes to blk-merge are also made to ensure this) - as such, it suffices to keep the data unit number of just the first bio, since that's all a storage driver needs to infer the data unit number to use for each data block in each bio in a request. blk-mq keeps track of the encryption context to be used for all the bios in a request with the request's rq_crypt_ctx. When the first bio is added to an empty request, blk-mq will program the encryption context of that bio into the request_queue's keyslot manager, and store the returned keyslot in the request's rq_crypt_ctx. All the functions to operate on encryption contexts are in blk-crypto.c. Upper layers only need to call bio_crypt_set_ctx with the encryption key, algorithm and data_unit_num; they don't have to worry about getting a keyslot for each encryption context, as blk-mq/blk-crypto handles that. Blk-crypto also makes it possible for request-based layered devices like dm-rq to make use of inline encryption hardware by cloning the rq_crypt_ctx and programming a keyslot in the new request_queue when necessary. Note that any user of the block layer can submit bios with an encryption context, such as filesystems, device-mapper targets, etc. Signed-off-by: Satya Tangirala <satyat@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-05-14 00:37:18 +00:00
if (!bio_crypt_ctx_merge_rq(req, next))
return 0;
/* Merge is OK... */
req->nr_phys_segments = total_phys_segments;
return 1;
}
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 08:48:17 +00:00
/**
* blk_rq_set_mixed_merge - mark a request as mixed merge
* @rq: request to mark as mixed merge
*
* Description:
* @rq is about to be mixed merged. Make sure the attributes
* which can be mixed are set in each bio and mark @rq as mixed
* merged.
*/
static void blk_rq_set_mixed_merge(struct request *rq)
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 08:48:17 +00:00
{
blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK;
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 08:48:17 +00:00
struct bio *bio;
if (rq->rq_flags & RQF_MIXED_MERGE)
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 08:48:17 +00:00
return;
/*
* @rq will no longer represent mixable attributes for all the
* contained bios. It will just track those of the first one.
* Distributes the attributs to each bio.
*/
for (bio = rq->bio; bio; bio = bio->bi_next) {
WARN_ON_ONCE((bio->bi_opf & REQ_FAILFAST_MASK) &&
(bio->bi_opf & REQ_FAILFAST_MASK) != ff);
bio->bi_opf |= ff;
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 08:48:17 +00:00
}
rq->rq_flags |= RQF_MIXED_MERGE;
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 08:48:17 +00:00
}
static inline blk_opf_t bio_failfast(const struct bio *bio)
block: sync mixed merged request's failfast with 1st bio's We support mixed merge for requests/bios with different fastfail settings. When request fails, each time we only handle the portion with same failfast setting, then bios with failfast can be failed immediately, and bios without failfast can be retried. The idea is pretty good, but the current implementation has several defects: 1) initially RA bio doesn't set failfast, however bio merge code doesn't consider this point, and just check its failfast setting for deciding if mixed merge is required. Fix this issue by adding helper of bio_failfast(). 2) when merging bio to request front, if this request is mixed merged, we have to sync request's faifast setting with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). 3) when merging bio to request back, if this request is mixed merged, we have to mark the bio as failfast, because blk_update_request simply updates request failfast with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). Fixes one normal EXT4 READ IO failure issue, because it is observed that the normal READ IO is merged with RA IO, and the mixed merged request has different failfast setting with 1st bio's, so finally the normal READ IO doesn't get retried. Cc: Tejun Heo <tj@kernel.org> Fixes: 80a761fd33cf ("block: implement mixed merge of different failfast requests") Signed-off-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/20230209125527.667004-1-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-02-09 12:55:27 +00:00
{
if (bio->bi_opf & REQ_RAHEAD)
return REQ_FAILFAST_MASK;
return bio->bi_opf & REQ_FAILFAST_MASK;
}
/*
* After we are marked as MIXED_MERGE, any new RA bio has to be updated
* as failfast, and request's failfast has to be updated in case of
* front merge.
*/
static inline void blk_update_mixed_merge(struct request *req,
struct bio *bio, bool front_merge)
{
if (req->rq_flags & RQF_MIXED_MERGE) {
if (bio->bi_opf & REQ_RAHEAD)
bio->bi_opf |= REQ_FAILFAST_MASK;
if (front_merge) {
req->cmd_flags &= ~REQ_FAILFAST_MASK;
req->cmd_flags |= bio->bi_opf & REQ_FAILFAST_MASK;
}
}
}
static void blk_account_io_merge_request(struct request *req)
{
if (blk_do_io_stat(req)) {
part_stat_lock();
part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
block: support to account io_ticks precisely Currently, io_ticks is accounted based on sampling, specifically update_io_ticks() will always account io_ticks by 1 jiffies from bdev_start_io_acct()/blk_account_io_start(), and the result can be inaccurate, for example(HZ is 250): Test script: fio -filename=/dev/sda -bs=4k -rw=write -direct=1 -name=test -thinktime=4ms Test result: util is about 90%, while the disk is really idle. This behaviour is introduced by commit 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting"), however, there was a key point that is missed that this patch also improve performance a lot: Before the commit: part_round_stats: if (part->stamp != now) stats |= 1; part_in_flight() -> there can be lots of task here in 1 jiffies. part_round_stats_single() __part_stat_add() part->stamp = now; After the commit: update_io_ticks: stamp = part->bd_stamp; if (time_after(now, stamp)) if (try_cmpxchg()) __part_stat_add() -> only one task can reach here in 1 jiffies. Hence in order to account io_ticks precisely, we only need to know if there are IO inflight at most once in one jiffies. Noted that for rq-based device, iterating tags should not be used here because 'tags->lock' is grabbed in blk_mq_find_and_get_req(), hence part_stat_lock_inc/dec() and part_in_flight() is used to trace inflight. The additional overhead is quite little: - per cpu add/dec for each IO for rq-based device; - per cpu sum for each jiffies; And it's verified by null-blk that there are no performance degration under heavy IO pressure. Fixes: 5b18b5a73760 ("block: delete part_round_stats and switch to less precise counting") Signed-off-by: Yu Kuai <yukuai3@huawei.com> Link: https://lore.kernel.org/r/20240509123717.3223892-2-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-05-09 12:37:16 +00:00
part_stat_local_dec(req->part,
in_flight[op_is_write(req_op(req))]);
part_stat_unlock();
}
}
static enum elv_merge blk_try_req_merge(struct request *req,
struct request *next)
{
if (blk_discard_mergable(req))
return ELEVATOR_DISCARD_MERGE;
else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next))
return ELEVATOR_BACK_MERGE;
return ELEVATOR_NO_MERGE;
}
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
static bool blk_atomic_write_mergeable_rq_bio(struct request *rq,
struct bio *bio)
{
return (rq->cmd_flags & REQ_ATOMIC) == (bio->bi_opf & REQ_ATOMIC);
}
static bool blk_atomic_write_mergeable_rqs(struct request *rq,
struct request *next)
{
return (rq->cmd_flags & REQ_ATOMIC) == (next->cmd_flags & REQ_ATOMIC);
}
/*
* For non-mq, this has to be called with the request spinlock acquired.
* For mq with scheduling, the appropriate queue wide lock should be held.
*/
static struct request *attempt_merge(struct request_queue *q,
struct request *req, struct request *next)
{
if (!rq_mergeable(req) || !rq_mergeable(next))
return NULL;
if (req_op(req) != req_op(next))
return NULL;
if (rq_data_dir(req) != rq_data_dir(next))
return NULL;
/* Don't merge requests with different write hints. */
if (req->write_hint != next->write_hint)
return NULL;
if (req->ioprio != next->ioprio)
return NULL;
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
if (!blk_atomic_write_mergeable_rqs(req, next))
return NULL;
/*
* If we are allowed to merge, then append bio list
* from next to rq and release next. merge_requests_fn
* will have updated segment counts, update sector
blk-mq: fix discard merge with scheduler attached I ran into an issue on my laptop that triggered a bug on the discard path: WARNING: CPU: 2 PID: 207 at drivers/nvme/host/core.c:527 nvme_setup_cmd+0x3d3/0x430 Modules linked in: rfcomm fuse ctr ccm bnep arc4 binfmt_misc snd_hda_codec_hdmi nls_iso8859_1 nls_cp437 vfat snd_hda_codec_conexant fat snd_hda_codec_generic iwlmvm snd_hda_intel snd_hda_codec snd_hwdep mac80211 snd_hda_core snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq x86_pkg_temp_thermal intel_powerclamp kvm_intel uvcvideo iwlwifi btusb snd_seq_device videobuf2_vmalloc btintel videobuf2_memops kvm snd_timer videobuf2_v4l2 bluetooth irqbypass videobuf2_core aesni_intel aes_x86_64 crypto_simd cryptd snd glue_helper videodev cfg80211 ecdh_generic soundcore hid_generic usbhid hid i915 psmouse e1000e ptp pps_core xhci_pci xhci_hcd intel_gtt CPU: 2 PID: 207 Comm: jbd2/nvme0n1p7- Tainted: G U 4.15.0+ #176 Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET59W (1.33 ) 12/19/2017 RIP: 0010:nvme_setup_cmd+0x3d3/0x430 RSP: 0018:ffff880423e9f838 EFLAGS: 00010217 RAX: 0000000000000000 RBX: ffff880423e9f8c8 RCX: 0000000000010000 RDX: ffff88022b200010 RSI: 0000000000000002 RDI: 00000000327f0000 RBP: ffff880421251400 R08: ffff88022b200000 R09: 0000000000000009 R10: 0000000000000000 R11: 0000000000000000 R12: 000000000000ffff R13: ffff88042341e280 R14: 000000000000ffff R15: ffff880421251440 FS: 0000000000000000(0000) GS:ffff880441500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055b684795030 CR3: 0000000002e09006 CR4: 00000000001606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: nvme_queue_rq+0x40/0xa00 ? __sbitmap_queue_get+0x24/0x90 ? blk_mq_get_tag+0xa3/0x250 ? wait_woken+0x80/0x80 ? blk_mq_get_driver_tag+0x97/0xf0 blk_mq_dispatch_rq_list+0x7b/0x4a0 ? deadline_remove_request+0x49/0xb0 blk_mq_do_dispatch_sched+0x4f/0xc0 blk_mq_sched_dispatch_requests+0x106/0x170 __blk_mq_run_hw_queue+0x53/0xa0 __blk_mq_delay_run_hw_queue+0x83/0xa0 blk_mq_run_hw_queue+0x6c/0xd0 blk_mq_sched_insert_request+0x96/0x140 __blk_mq_try_issue_directly+0x3d/0x190 blk_mq_try_issue_directly+0x30/0x70 blk_mq_make_request+0x1a4/0x6a0 generic_make_request+0xfd/0x2f0 ? submit_bio+0x5c/0x110 submit_bio+0x5c/0x110 ? __blkdev_issue_discard+0x152/0x200 submit_bio_wait+0x43/0x60 ext4_process_freed_data+0x1cd/0x440 ? account_page_dirtied+0xe2/0x1a0 ext4_journal_commit_callback+0x4a/0xc0 jbd2_journal_commit_transaction+0x17e2/0x19e0 ? kjournald2+0xb0/0x250 kjournald2+0xb0/0x250 ? wait_woken+0x80/0x80 ? commit_timeout+0x10/0x10 kthread+0x111/0x130 ? kthread_create_worker_on_cpu+0x50/0x50 ? do_group_exit+0x3a/0xa0 ret_from_fork+0x1f/0x30 Code: 73 89 c1 83 ce 10 c1 e1 10 09 ca 83 f8 04 0f 87 0f ff ff ff 8b 4d 20 48 8b 7d 00 c1 e9 09 48 01 8c c7 00 08 00 00 e9 f8 fe ff ff <0f> ff 4c 89 c7 41 bc 0a 00 00 00 e8 0d 78 d6 ff e9 a1 fc ff ff ---[ end trace 50d361cc444506c8 ]--- print_req_error: I/O error, dev nvme0n1, sector 847167488 Decoding the assembly, the request claims to have 0xffff segments, while nvme counts two. This turns out to be because we don't check for a data carrying request on the mq scheduler path, and since blk_phys_contig_segment() returns true for a non-data request, we decrement the initial segment count of 0 and end up with 0xffff in the unsigned short. There are a few issues here: 1) We should initialize the segment count for a discard to 1. 2) The discard merging is currently using the data limits for segments and sectors. Fix this up by having attempt_merge() correctly identify the request, and by initializing the segment count correctly for discards. This can only be triggered with mq-deadline on discard capable devices right now, which isn't a common configuration. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-01 21:01:02 +00:00
* counts here. Handle DISCARDs separately, as they
* have separate settings.
*/
switch (blk_try_req_merge(req, next)) {
case ELEVATOR_DISCARD_MERGE:
blk-mq: fix discard merge with scheduler attached I ran into an issue on my laptop that triggered a bug on the discard path: WARNING: CPU: 2 PID: 207 at drivers/nvme/host/core.c:527 nvme_setup_cmd+0x3d3/0x430 Modules linked in: rfcomm fuse ctr ccm bnep arc4 binfmt_misc snd_hda_codec_hdmi nls_iso8859_1 nls_cp437 vfat snd_hda_codec_conexant fat snd_hda_codec_generic iwlmvm snd_hda_intel snd_hda_codec snd_hwdep mac80211 snd_hda_core snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq x86_pkg_temp_thermal intel_powerclamp kvm_intel uvcvideo iwlwifi btusb snd_seq_device videobuf2_vmalloc btintel videobuf2_memops kvm snd_timer videobuf2_v4l2 bluetooth irqbypass videobuf2_core aesni_intel aes_x86_64 crypto_simd cryptd snd glue_helper videodev cfg80211 ecdh_generic soundcore hid_generic usbhid hid i915 psmouse e1000e ptp pps_core xhci_pci xhci_hcd intel_gtt CPU: 2 PID: 207 Comm: jbd2/nvme0n1p7- Tainted: G U 4.15.0+ #176 Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET59W (1.33 ) 12/19/2017 RIP: 0010:nvme_setup_cmd+0x3d3/0x430 RSP: 0018:ffff880423e9f838 EFLAGS: 00010217 RAX: 0000000000000000 RBX: ffff880423e9f8c8 RCX: 0000000000010000 RDX: ffff88022b200010 RSI: 0000000000000002 RDI: 00000000327f0000 RBP: ffff880421251400 R08: ffff88022b200000 R09: 0000000000000009 R10: 0000000000000000 R11: 0000000000000000 R12: 000000000000ffff R13: ffff88042341e280 R14: 000000000000ffff R15: ffff880421251440 FS: 0000000000000000(0000) GS:ffff880441500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055b684795030 CR3: 0000000002e09006 CR4: 00000000001606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: nvme_queue_rq+0x40/0xa00 ? __sbitmap_queue_get+0x24/0x90 ? blk_mq_get_tag+0xa3/0x250 ? wait_woken+0x80/0x80 ? blk_mq_get_driver_tag+0x97/0xf0 blk_mq_dispatch_rq_list+0x7b/0x4a0 ? deadline_remove_request+0x49/0xb0 blk_mq_do_dispatch_sched+0x4f/0xc0 blk_mq_sched_dispatch_requests+0x106/0x170 __blk_mq_run_hw_queue+0x53/0xa0 __blk_mq_delay_run_hw_queue+0x83/0xa0 blk_mq_run_hw_queue+0x6c/0xd0 blk_mq_sched_insert_request+0x96/0x140 __blk_mq_try_issue_directly+0x3d/0x190 blk_mq_try_issue_directly+0x30/0x70 blk_mq_make_request+0x1a4/0x6a0 generic_make_request+0xfd/0x2f0 ? submit_bio+0x5c/0x110 submit_bio+0x5c/0x110 ? __blkdev_issue_discard+0x152/0x200 submit_bio_wait+0x43/0x60 ext4_process_freed_data+0x1cd/0x440 ? account_page_dirtied+0xe2/0x1a0 ext4_journal_commit_callback+0x4a/0xc0 jbd2_journal_commit_transaction+0x17e2/0x19e0 ? kjournald2+0xb0/0x250 kjournald2+0xb0/0x250 ? wait_woken+0x80/0x80 ? commit_timeout+0x10/0x10 kthread+0x111/0x130 ? kthread_create_worker_on_cpu+0x50/0x50 ? do_group_exit+0x3a/0xa0 ret_from_fork+0x1f/0x30 Code: 73 89 c1 83 ce 10 c1 e1 10 09 ca 83 f8 04 0f 87 0f ff ff ff 8b 4d 20 48 8b 7d 00 c1 e9 09 48 01 8c c7 00 08 00 00 e9 f8 fe ff ff <0f> ff 4c 89 c7 41 bc 0a 00 00 00 e8 0d 78 d6 ff e9 a1 fc ff ff ---[ end trace 50d361cc444506c8 ]--- print_req_error: I/O error, dev nvme0n1, sector 847167488 Decoding the assembly, the request claims to have 0xffff segments, while nvme counts two. This turns out to be because we don't check for a data carrying request on the mq scheduler path, and since blk_phys_contig_segment() returns true for a non-data request, we decrement the initial segment count of 0 and end up with 0xffff in the unsigned short. There are a few issues here: 1) We should initialize the segment count for a discard to 1. 2) The discard merging is currently using the data limits for segments and sectors. Fix this up by having attempt_merge() correctly identify the request, and by initializing the segment count correctly for discards. This can only be triggered with mq-deadline on discard capable devices right now, which isn't a common configuration. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-01 21:01:02 +00:00
if (!req_attempt_discard_merge(q, req, next))
return NULL;
break;
case ELEVATOR_BACK_MERGE:
if (!ll_merge_requests_fn(q, req, next))
return NULL;
break;
default:
return NULL;
}
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 08:48:17 +00:00
/*
* If failfast settings disagree or any of the two is already
* a mixed merge, mark both as mixed before proceeding. This
* makes sure that all involved bios have mixable attributes
* set properly.
*/
if (((req->rq_flags | next->rq_flags) & RQF_MIXED_MERGE) ||
block: implement mixed merge of different failfast requests Failfast has characteristics from other attributes. When issuing, executing and successuflly completing requests, failfast doesn't make any difference. It only affects how a request is handled on failure. Allowing requests with different failfast settings to be merged cause normal IOs to fail prematurely while not allowing has performance penalties as failfast is used for read aheads which are likely to be located near in-flight or to-be-issued normal IOs. This patch introduces the concept of 'mixed merge'. A request is a mixed merge if it is merge of segments which require different handling on failure. Currently the only mixable attributes are failfast ones (or lack thereof). When a bio with different failfast settings is added to an existing request or requests of different failfast settings are merged, the merged request is marked mixed. Each bio carries failfast settings and the request always tracks failfast state of the first bio. When the request fails, blk_rq_err_bytes() can be used to determine how many bytes can be safely failed without crossing into an area which requires further retrials. This allows request merging regardless of failfast settings while keeping the failure handling correct. This patch only implements mixed merge but doesn't enable it. The next one will update SCSI to make use of mixed merge. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Niel Lambrechts <niel.lambrechts@gmail.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-07-03 08:48:17 +00:00
(req->cmd_flags & REQ_FAILFAST_MASK) !=
(next->cmd_flags & REQ_FAILFAST_MASK)) {
blk_rq_set_mixed_merge(req);
blk_rq_set_mixed_merge(next);
}
/*
* At this point we have either done a back merge or front merge. We
* need the smaller start_time_ns of the merged requests to be the
* current request for accounting purposes.
*/
if (next->start_time_ns < req->start_time_ns)
req->start_time_ns = next->start_time_ns;
req->biotail->bi_next = next->bio;
req->biotail = next->biotail;
req->__data_len += blk_rq_bytes(next);
block: fix single range discard merge There are actually two kinds of discard merge: - one is the normal discard merge, just like normal read/write request, and call it single-range discard - another is the multi-range discard, queue_max_discard_segments(rq->q) > 1 For the former case, queue_max_discard_segments(rq->q) is 1, and we should handle this kind of discard merge like the normal read/write request. This patch fixes the following kernel panic issue[1], which is caused by not removing the single-range discard request from elevator queue. Guangwu has one raid discard test case, in which this issue is a bit easier to trigger, and I verified that this patch can fix the kernel panic issue in Guangwu's test case. [1] kernel panic log from Jens's report BUG: unable to handle kernel NULL pointer dereference at 0000000000000148 PGD 0 P4D 0. Oops: 0000 [#1] SMP PTI CPU: 37 PID: 763 Comm: kworker/37:1H Not tainted \ 4.20.0-rc3-00649-ge64d9a554a91-dirty #14 Hardware name: Wiwynn \ Leopard-Orv2/Leopard-DDR BW, BIOS LBM08 03/03/2017 Workqueue: kblockd \ blk_mq_run_work_fn RIP: \ 0010:blk_mq_get_driver_tag+0x81/0x120 Code: 24 \ 10 48 89 7c 24 20 74 21 83 fa ff 0f 95 c0 48 8b 4c 24 28 65 48 33 0c 25 28 00 00 00 \ 0f 85 96 00 00 00 48 83 c4 30 5b 5d c3 <48> 8b 87 48 01 00 00 8b 40 04 39 43 20 72 37 \ f6 87 b0 00 00 00 02 RSP: 0018:ffffc90004aabd30 EFLAGS: 00010246 \ RAX: 0000000000000003 RBX: ffff888465ea1300 RCX: ffffc90004aabde8 RDX: 00000000ffffffff RSI: ffffc90004aabde8 RDI: 0000000000000000 RBP: 0000000000000000 R08: ffff888465ea1348 R09: 0000000000000000 R10: 0000000000001000 R11: 00000000ffffffff R12: ffff888465ea1300 R13: 0000000000000000 R14: ffff888465ea1348 R15: ffff888465d10000 FS: 0000000000000000(0000) GS:ffff88846f9c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000148 CR3: 000000000220a003 CR4: 00000000003606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: blk_mq_dispatch_rq_list+0xec/0x480 ? elv_rb_del+0x11/0x30 blk_mq_do_dispatch_sched+0x6e/0xf0 blk_mq_sched_dispatch_requests+0xfa/0x170 __blk_mq_run_hw_queue+0x5f/0xe0 process_one_work+0x154/0x350 worker_thread+0x46/0x3c0 kthread+0xf5/0x130 ? process_one_work+0x350/0x350 ? kthread_destroy_worker+0x50/0x50 ret_from_fork+0x1f/0x30 Modules linked in: sb_edac x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel \ kvm switchtec irqbypass iTCO_wdt iTCO_vendor_support efivars cdc_ether usbnet mii \ cdc_acm i2c_i801 lpc_ich mfd_core ipmi_si ipmi_devintf ipmi_msghandler acpi_cpufreq \ button sch_fq_codel nfsd nfs_acl lockd grace auth_rpcgss oid_registry sunrpc nvme \ nvme_core fuse sg loop efivarfs autofs4 CR2: 0000000000000148 \ ---[ end trace 340a1fb996df1b9b ]--- RIP: 0010:blk_mq_get_driver_tag+0x81/0x120 Code: 24 10 48 89 7c 24 20 74 21 83 fa ff 0f 95 c0 48 8b 4c 24 28 65 48 33 0c 25 28 \ 00 00 00 0f 85 96 00 00 00 48 83 c4 30 5b 5d c3 <48> 8b 87 48 01 00 00 8b 40 04 39 43 \ 20 72 37 f6 87 b0 00 00 00 02 Fixes: 445251d0f4d329a ("blk-mq: fix discard merge with scheduler attached") Reported-by: Jens Axboe <axboe@kernel.dk> Cc: Guangwu Zhang <guazhang@redhat.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Jianchao Wang <jianchao.w.wang@oracle.com> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-11-30 16:38:18 +00:00
if (!blk_discard_mergable(req))
blk-mq: fix discard merge with scheduler attached I ran into an issue on my laptop that triggered a bug on the discard path: WARNING: CPU: 2 PID: 207 at drivers/nvme/host/core.c:527 nvme_setup_cmd+0x3d3/0x430 Modules linked in: rfcomm fuse ctr ccm bnep arc4 binfmt_misc snd_hda_codec_hdmi nls_iso8859_1 nls_cp437 vfat snd_hda_codec_conexant fat snd_hda_codec_generic iwlmvm snd_hda_intel snd_hda_codec snd_hwdep mac80211 snd_hda_core snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi snd_seq x86_pkg_temp_thermal intel_powerclamp kvm_intel uvcvideo iwlwifi btusb snd_seq_device videobuf2_vmalloc btintel videobuf2_memops kvm snd_timer videobuf2_v4l2 bluetooth irqbypass videobuf2_core aesni_intel aes_x86_64 crypto_simd cryptd snd glue_helper videodev cfg80211 ecdh_generic soundcore hid_generic usbhid hid i915 psmouse e1000e ptp pps_core xhci_pci xhci_hcd intel_gtt CPU: 2 PID: 207 Comm: jbd2/nvme0n1p7- Tainted: G U 4.15.0+ #176 Hardware name: LENOVO 20FBCTO1WW/20FBCTO1WW, BIOS N1FET59W (1.33 ) 12/19/2017 RIP: 0010:nvme_setup_cmd+0x3d3/0x430 RSP: 0018:ffff880423e9f838 EFLAGS: 00010217 RAX: 0000000000000000 RBX: ffff880423e9f8c8 RCX: 0000000000010000 RDX: ffff88022b200010 RSI: 0000000000000002 RDI: 00000000327f0000 RBP: ffff880421251400 R08: ffff88022b200000 R09: 0000000000000009 R10: 0000000000000000 R11: 0000000000000000 R12: 000000000000ffff R13: ffff88042341e280 R14: 000000000000ffff R15: ffff880421251440 FS: 0000000000000000(0000) GS:ffff880441500000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000055b684795030 CR3: 0000000002e09006 CR4: 00000000001606e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: nvme_queue_rq+0x40/0xa00 ? __sbitmap_queue_get+0x24/0x90 ? blk_mq_get_tag+0xa3/0x250 ? wait_woken+0x80/0x80 ? blk_mq_get_driver_tag+0x97/0xf0 blk_mq_dispatch_rq_list+0x7b/0x4a0 ? deadline_remove_request+0x49/0xb0 blk_mq_do_dispatch_sched+0x4f/0xc0 blk_mq_sched_dispatch_requests+0x106/0x170 __blk_mq_run_hw_queue+0x53/0xa0 __blk_mq_delay_run_hw_queue+0x83/0xa0 blk_mq_run_hw_queue+0x6c/0xd0 blk_mq_sched_insert_request+0x96/0x140 __blk_mq_try_issue_directly+0x3d/0x190 blk_mq_try_issue_directly+0x30/0x70 blk_mq_make_request+0x1a4/0x6a0 generic_make_request+0xfd/0x2f0 ? submit_bio+0x5c/0x110 submit_bio+0x5c/0x110 ? __blkdev_issue_discard+0x152/0x200 submit_bio_wait+0x43/0x60 ext4_process_freed_data+0x1cd/0x440 ? account_page_dirtied+0xe2/0x1a0 ext4_journal_commit_callback+0x4a/0xc0 jbd2_journal_commit_transaction+0x17e2/0x19e0 ? kjournald2+0xb0/0x250 kjournald2+0xb0/0x250 ? wait_woken+0x80/0x80 ? commit_timeout+0x10/0x10 kthread+0x111/0x130 ? kthread_create_worker_on_cpu+0x50/0x50 ? do_group_exit+0x3a/0xa0 ret_from_fork+0x1f/0x30 Code: 73 89 c1 83 ce 10 c1 e1 10 09 ca 83 f8 04 0f 87 0f ff ff ff 8b 4d 20 48 8b 7d 00 c1 e9 09 48 01 8c c7 00 08 00 00 e9 f8 fe ff ff <0f> ff 4c 89 c7 41 bc 0a 00 00 00 e8 0d 78 d6 ff e9 a1 fc ff ff ---[ end trace 50d361cc444506c8 ]--- print_req_error: I/O error, dev nvme0n1, sector 847167488 Decoding the assembly, the request claims to have 0xffff segments, while nvme counts two. This turns out to be because we don't check for a data carrying request on the mq scheduler path, and since blk_phys_contig_segment() returns true for a non-data request, we decrement the initial segment count of 0 and end up with 0xffff in the unsigned short. There are a few issues here: 1) We should initialize the segment count for a discard to 1. 2) The discard merging is currently using the data limits for segments and sectors. Fix this up by having attempt_merge() correctly identify the request, and by initializing the segment count correctly for discards. This can only be triggered with mq-deadline on discard capable devices right now, which isn't a common configuration. Signed-off-by: Jens Axboe <axboe@kernel.dk>
2018-02-01 21:01:02 +00:00
elv_merge_requests(q, req, next);
blk_crypto_rq_put_keyslot(next);
/*
* 'next' is going away, so update stats accordingly
*/
blk_account_io_merge_request(next);
trace_block_rq_merge(next);
/*
* ownership of bio passed from next to req, return 'next' for
* the caller to free
*/
next->bio = NULL;
return next;
}
static struct request *attempt_back_merge(struct request_queue *q,
struct request *rq)
{
struct request *next = elv_latter_request(q, rq);
if (next)
return attempt_merge(q, rq, next);
return NULL;
}
static struct request *attempt_front_merge(struct request_queue *q,
struct request *rq)
{
struct request *prev = elv_former_request(q, rq);
if (prev)
return attempt_merge(q, prev, rq);
return NULL;
}
/*
* Try to merge 'next' into 'rq'. Return true if the merge happened, false
* otherwise. The caller is responsible for freeing 'next' if the merge
* happened.
*/
bool blk_attempt_req_merge(struct request_queue *q, struct request *rq,
struct request *next)
{
return attempt_merge(q, rq, next);
}
bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
{
if (!rq_mergeable(rq) || !bio_mergeable(bio))
return false;
if (req_op(rq) != bio_op(bio))
return false;
/* different data direction or already started, don't merge */
if (bio_data_dir(bio) != rq_data_dir(rq))
return false;
/* don't merge across cgroup boundaries */
if (!blk_cgroup_mergeable(rq, bio))
return false;
/* only merge integrity protected bio into ditto rq */
if (blk_integrity_merge_bio(rq->q, rq, bio) == false)
return false;
block: Inline encryption support for blk-mq We must have some way of letting a storage device driver know what encryption context it should use for en/decrypting a request. However, it's the upper layers (like the filesystem/fscrypt) that know about and manages encryption contexts. As such, when the upper layer submits a bio to the block layer, and this bio eventually reaches a device driver with support for inline encryption, the device driver will need to have been told the encryption context for that bio. We want to communicate the encryption context from the upper layer to the storage device along with the bio, when the bio is submitted to the block layer. To do this, we add a struct bio_crypt_ctx to struct bio, which can represent an encryption context (note that we can't use the bi_private field in struct bio to do this because that field does not function to pass information across layers in the storage stack). We also introduce various functions to manipulate the bio_crypt_ctx and make the bio/request merging logic aware of the bio_crypt_ctx. We also make changes to blk-mq to make it handle bios with encryption contexts. blk-mq can merge many bios into the same request. These bios need to have contiguous data unit numbers (the necessary changes to blk-merge are also made to ensure this) - as such, it suffices to keep the data unit number of just the first bio, since that's all a storage driver needs to infer the data unit number to use for each data block in each bio in a request. blk-mq keeps track of the encryption context to be used for all the bios in a request with the request's rq_crypt_ctx. When the first bio is added to an empty request, blk-mq will program the encryption context of that bio into the request_queue's keyslot manager, and store the returned keyslot in the request's rq_crypt_ctx. All the functions to operate on encryption contexts are in blk-crypto.c. Upper layers only need to call bio_crypt_set_ctx with the encryption key, algorithm and data_unit_num; they don't have to worry about getting a keyslot for each encryption context, as blk-mq/blk-crypto handles that. Blk-crypto also makes it possible for request-based layered devices like dm-rq to make use of inline encryption hardware by cloning the rq_crypt_ctx and programming a keyslot in the new request_queue when necessary. Note that any user of the block layer can submit bios with an encryption context, such as filesystems, device-mapper targets, etc. Signed-off-by: Satya Tangirala <satyat@google.com> Reviewed-by: Eric Biggers <ebiggers@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-05-14 00:37:18 +00:00
/* Only merge if the crypt contexts are compatible */
if (!bio_crypt_rq_ctx_compatible(rq, bio))
return false;
/* Don't merge requests with different write hints. */
if (rq->write_hint != bio->bi_write_hint)
return false;
if (rq->ioprio != bio_prio(bio))
return false;
block: Add core atomic write support Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated. All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now. An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also. New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors. FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO. Flag REQ_ATOMIC is used for indicating an atomic write. Co-developed-by: Himanshu Madhani <himanshu.madhani@oracle.com> Signed-off-by: Himanshu Madhani <himanshu.madhani@oracle.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: John Garry <john.g.garry@oracle.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Link: https://lore.kernel.org/r/20240620125359.2684798-6-john.g.garry@oracle.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-06-20 12:53:54 +00:00
if (blk_atomic_write_mergeable_rq_bio(rq, bio) == false)
return false;
return true;
}
enum elv_merge blk_try_merge(struct request *rq, struct bio *bio)
{
if (blk_discard_mergable(rq))
return ELEVATOR_DISCARD_MERGE;
else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector)
return ELEVATOR_BACK_MERGE;
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector)
return ELEVATOR_FRONT_MERGE;
return ELEVATOR_NO_MERGE;
}
static void blk_account_io_merge_bio(struct request *req)
{
if (!blk_do_io_stat(req))
return;
part_stat_lock();
part_stat_inc(req->part, merges[op_stat_group(req_op(req))]);
part_stat_unlock();
}
enum bio_merge_status bio_attempt_back_merge(struct request *req,
struct bio *bio, unsigned int nr_segs)
{
block: sync mixed merged request's failfast with 1st bio's We support mixed merge for requests/bios with different fastfail settings. When request fails, each time we only handle the portion with same failfast setting, then bios with failfast can be failed immediately, and bios without failfast can be retried. The idea is pretty good, but the current implementation has several defects: 1) initially RA bio doesn't set failfast, however bio merge code doesn't consider this point, and just check its failfast setting for deciding if mixed merge is required. Fix this issue by adding helper of bio_failfast(). 2) when merging bio to request front, if this request is mixed merged, we have to sync request's faifast setting with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). 3) when merging bio to request back, if this request is mixed merged, we have to mark the bio as failfast, because blk_update_request simply updates request failfast with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). Fixes one normal EXT4 READ IO failure issue, because it is observed that the normal READ IO is merged with RA IO, and the mixed merged request has different failfast setting with 1st bio's, so finally the normal READ IO doesn't get retried. Cc: Tejun Heo <tj@kernel.org> Fixes: 80a761fd33cf ("block: implement mixed merge of different failfast requests") Signed-off-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/20230209125527.667004-1-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-02-09 12:55:27 +00:00
const blk_opf_t ff = bio_failfast(bio);
if (!ll_back_merge_fn(req, bio, nr_segs))
return BIO_MERGE_FAILED;
trace_block_bio_backmerge(bio);
rq_qos_merge(req->q, req, bio);
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
blk_rq_set_mixed_merge(req);
block: sync mixed merged request's failfast with 1st bio's We support mixed merge for requests/bios with different fastfail settings. When request fails, each time we only handle the portion with same failfast setting, then bios with failfast can be failed immediately, and bios without failfast can be retried. The idea is pretty good, but the current implementation has several defects: 1) initially RA bio doesn't set failfast, however bio merge code doesn't consider this point, and just check its failfast setting for deciding if mixed merge is required. Fix this issue by adding helper of bio_failfast(). 2) when merging bio to request front, if this request is mixed merged, we have to sync request's faifast setting with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). 3) when merging bio to request back, if this request is mixed merged, we have to mark the bio as failfast, because blk_update_request simply updates request failfast with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). Fixes one normal EXT4 READ IO failure issue, because it is observed that the normal READ IO is merged with RA IO, and the mixed merged request has different failfast setting with 1st bio's, so finally the normal READ IO doesn't get retried. Cc: Tejun Heo <tj@kernel.org> Fixes: 80a761fd33cf ("block: implement mixed merge of different failfast requests") Signed-off-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/20230209125527.667004-1-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-02-09 12:55:27 +00:00
blk_update_mixed_merge(req, bio, false);
block: Introduce zone write plugging Zone write plugging implements a per-zone "plug" for write operations to control the submission and execution order of write operations to sequential write required zones of a zoned block device. Per-zone plugging guarantees that at any time there is at most only one write request per zone being executed. This mechanism is intended to replace zone write locking which implements a similar per-zone write throttling at the scheduler level, but is implemented only by mq-deadline. Unlike zone write locking which operates on requests, zone write plugging operates on BIOs. A zone write plug is simply a BIO list that is atomically manipulated using a spinlock and a kblockd submission work. A write BIO to a zone is "plugged" to delay its execution if a write BIO for the same zone was already issued, that is, if a write request for the same zone is being executed. The next plugged BIO is unplugged and issued once the write request completes. This mechanism allows to: - Untangle zone write ordering from block IO schedulers. This allows removing the restriction on using mq-deadline for writing to zoned block devices. Any block IO scheduler, including "none" can be used. - Zone write plugging operates on BIOs instead of requests. Plugged BIOs waiting for execution thus do not hold scheduling tags and thus are not preventing other BIOs from executing (reads or writes to other zones). Depending on the workload, this can significantly improve the device use (higher queue depth operation) and performance. - Both blk-mq (request based) zoned devices and BIO-based zoned devices (e.g. device mapper) can use zone write plugging. It is mandatory for the former but optional for the latter. BIO-based drivers can use zone write plugging to implement write ordering guarantees, or the drivers can implement their own if needed. - The code is less invasive in the block layer and is mostly limited to blk-zoned.c with some small changes in blk-mq.c, blk-merge.c and bio.c. Zone write plugging is implemented using struct blk_zone_wplug. This structure includes a spinlock, a BIO list and a work structure to handle the submission of plugged BIOs. Zone write plugs structures are managed using a per-disk hash table. Plugging of zone write BIOs is done using the function blk_zone_write_plug_bio() which returns false if a BIO execution does not need to be delayed and true otherwise. This function is called from blk_mq_submit_bio() after a BIO is split to avoid large BIOs spanning multiple zones which would cause mishandling of zone write plugs. This ichange enables by default zone write plugging for any mq request-based block device. BIO-based device drivers can also use zone write plugging by expliclty calling blk_zone_write_plug_bio() in their ->submit_bio method. For such devices, the driver must ensure that a BIO passed to blk_zone_write_plug_bio() is already split and not straddling zone boundaries. Only write and write zeroes BIOs are plugged. Zone write plugging does not introduce any significant overhead for other operations. A BIO that is being handled through zone write plugging is flagged using the new BIO flag BIO_ZONE_WRITE_PLUGGING. A request handling a BIO flagged with this new flag is flagged with the new RQF_ZONE_WRITE_PLUGGING flag. The completion of BIOs and requests flagged trigger respectively calls to the functions blk_zone_write_bio_endio() and blk_zone_write_complete_request(). The latter function is used to trigger submission of the next plugged BIO using the zone plug work. blk_zone_write_bio_endio() does the same for BIO-based devices. This ensures that at any time, at most one request (blk-mq devices) or one BIO (BIO-based devices) is being executed for any zone. The handling of zone write plugs using a per-zone plug spinlock maximizes parallelism and device usage by allowing multiple zones to be writen simultaneously without lock contention. Zone write plugging ignores flush BIOs without data. Hovever, any flush BIO that has data is always plugged so that the write part of the flush sequence is serialized with other regular writes. Given that any BIO handled through zone write plugging will be the only BIO in flight for the target zone when it is executed, the unplugging and submission of a BIO will have no chance of successfully merging with plugged requests or requests in the scheduler. To overcome this potential performance degradation, blk_mq_submit_bio() calls the function blk_zone_write_plug_attempt_merge() to try to merge other plugged BIOs with the one just unplugged and submitted. Successful merging is signaled using blk_zone_write_plug_bio_merged(), called from bio_attempt_back_merge(). Furthermore, to avoid recalculating the number of segments of plugged BIOs to attempt merging, the number of segments of a plugged BIO is saved using the new struct bio field __bi_nr_segments. To avoid growing the size of struct bio, this field is added as a union with the bio_cookie field. This is safe to do as polling is always disabled for plugged BIOs. When BIOs are plugged in a zone write plug, the device request queue usage counter is always incremented. This reference is kept and reused for blk-mq devices when the plugged BIO is unplugged and submitted again using submit_bio_noacct_nocheck(). For this case, the unplugged BIO is already flagged with BIO_ZONE_WRITE_PLUGGING and blk_mq_submit_bio() proceeds directly to allocating a new request for the BIO, re-using the usage reference count taken when the BIO was plugged. This extra reference count is dropped in blk_zone_write_plug_attempt_merge() for any plugged BIO that is successfully merged. Given that BIO-based devices will not take this path, the extra reference is dropped after a plugged BIO is unplugged and submitted. Zone write plugs are dynamically allocated and managed using a hash table (an array of struct hlist_head) with RCU protection. A zone write plug is allocated when a write BIO is received for the zone and not freed until the zone is fully written, reset or finished. To detect when a zone write plug can be freed, the write state of each zone is tracked using a write pointer offset which corresponds to the offset of a zone write pointer relative to the zone start. Write operations always increment this write pointer offset. Zone reset operations set it to 0 and zone finish operations set it to the zone size. If a write error happens, the wp_offset value of a zone write plug may become incorrect and out of sync with the device managed write pointer. This is handled using the zone write plug flag BLK_ZONE_WPLUG_ERROR. The function blk_zone_wplug_handle_error() is called from the new disk zone write plug work when this flag is set. This function executes a report zone to update the zone write pointer offset to the current value as indicated by the device. The disk zone write plug work is scheduled whenever a BIO flagged with BIO_ZONE_WRITE_PLUGGING completes with an error or when bio_zone_wplug_prepare_bio() detects an unaligned write. Once scheduled, the disk zone write plugs work keeps running until all zone errors are handled. To match the new data structures used for zoned disks, the function disk_free_zone_bitmaps() is renamed to the more generic disk_free_zone_resources(). The function disk_init_zone_resources() is also introduced to initialize zone write plugs resources when a gendisk is allocated. In order to guarantee that the user can simultaneously write up to a number of zones equal to a device max active zone limit or max open zone limit, zone write plugs are allocated using a mempool sized to the maximum of these 2 device limits. For a device that does not have active and open zone limits, 128 is used as the default mempool size. If a change to the device active and open zone limits is detected, the disk mempool is resized when blk_revalidate_disk_zones() is executed. This commit contains contributions from Christoph Hellwig <hch@lst.de>. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Tested-by: Hans Holmberg <hans.holmberg@wdc.com> Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Link: https://lore.kernel.org/r/20240408014128.205141-8-dlemoal@kernel.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-04-08 01:41:07 +00:00
if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
blk_zone_write_plug_bio_merged(bio);
req->biotail->bi_next = bio;
req->biotail = bio;
req->__data_len += bio->bi_iter.bi_size;
bio_crypt_free_ctx(bio);
blk_account_io_merge_bio(req);
return BIO_MERGE_OK;
}
static enum bio_merge_status bio_attempt_front_merge(struct request *req,
struct bio *bio, unsigned int nr_segs)
{
block: sync mixed merged request's failfast with 1st bio's We support mixed merge for requests/bios with different fastfail settings. When request fails, each time we only handle the portion with same failfast setting, then bios with failfast can be failed immediately, and bios without failfast can be retried. The idea is pretty good, but the current implementation has several defects: 1) initially RA bio doesn't set failfast, however bio merge code doesn't consider this point, and just check its failfast setting for deciding if mixed merge is required. Fix this issue by adding helper of bio_failfast(). 2) when merging bio to request front, if this request is mixed merged, we have to sync request's faifast setting with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). 3) when merging bio to request back, if this request is mixed merged, we have to mark the bio as failfast, because blk_update_request simply updates request failfast with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). Fixes one normal EXT4 READ IO failure issue, because it is observed that the normal READ IO is merged with RA IO, and the mixed merged request has different failfast setting with 1st bio's, so finally the normal READ IO doesn't get retried. Cc: Tejun Heo <tj@kernel.org> Fixes: 80a761fd33cf ("block: implement mixed merge of different failfast requests") Signed-off-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/20230209125527.667004-1-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-02-09 12:55:27 +00:00
const blk_opf_t ff = bio_failfast(bio);
block: Introduce zone write plugging Zone write plugging implements a per-zone "plug" for write operations to control the submission and execution order of write operations to sequential write required zones of a zoned block device. Per-zone plugging guarantees that at any time there is at most only one write request per zone being executed. This mechanism is intended to replace zone write locking which implements a similar per-zone write throttling at the scheduler level, but is implemented only by mq-deadline. Unlike zone write locking which operates on requests, zone write plugging operates on BIOs. A zone write plug is simply a BIO list that is atomically manipulated using a spinlock and a kblockd submission work. A write BIO to a zone is "plugged" to delay its execution if a write BIO for the same zone was already issued, that is, if a write request for the same zone is being executed. The next plugged BIO is unplugged and issued once the write request completes. This mechanism allows to: - Untangle zone write ordering from block IO schedulers. This allows removing the restriction on using mq-deadline for writing to zoned block devices. Any block IO scheduler, including "none" can be used. - Zone write plugging operates on BIOs instead of requests. Plugged BIOs waiting for execution thus do not hold scheduling tags and thus are not preventing other BIOs from executing (reads or writes to other zones). Depending on the workload, this can significantly improve the device use (higher queue depth operation) and performance. - Both blk-mq (request based) zoned devices and BIO-based zoned devices (e.g. device mapper) can use zone write plugging. It is mandatory for the former but optional for the latter. BIO-based drivers can use zone write plugging to implement write ordering guarantees, or the drivers can implement their own if needed. - The code is less invasive in the block layer and is mostly limited to blk-zoned.c with some small changes in blk-mq.c, blk-merge.c and bio.c. Zone write plugging is implemented using struct blk_zone_wplug. This structure includes a spinlock, a BIO list and a work structure to handle the submission of plugged BIOs. Zone write plugs structures are managed using a per-disk hash table. Plugging of zone write BIOs is done using the function blk_zone_write_plug_bio() which returns false if a BIO execution does not need to be delayed and true otherwise. This function is called from blk_mq_submit_bio() after a BIO is split to avoid large BIOs spanning multiple zones which would cause mishandling of zone write plugs. This ichange enables by default zone write plugging for any mq request-based block device. BIO-based device drivers can also use zone write plugging by expliclty calling blk_zone_write_plug_bio() in their ->submit_bio method. For such devices, the driver must ensure that a BIO passed to blk_zone_write_plug_bio() is already split and not straddling zone boundaries. Only write and write zeroes BIOs are plugged. Zone write plugging does not introduce any significant overhead for other operations. A BIO that is being handled through zone write plugging is flagged using the new BIO flag BIO_ZONE_WRITE_PLUGGING. A request handling a BIO flagged with this new flag is flagged with the new RQF_ZONE_WRITE_PLUGGING flag. The completion of BIOs and requests flagged trigger respectively calls to the functions blk_zone_write_bio_endio() and blk_zone_write_complete_request(). The latter function is used to trigger submission of the next plugged BIO using the zone plug work. blk_zone_write_bio_endio() does the same for BIO-based devices. This ensures that at any time, at most one request (blk-mq devices) or one BIO (BIO-based devices) is being executed for any zone. The handling of zone write plugs using a per-zone plug spinlock maximizes parallelism and device usage by allowing multiple zones to be writen simultaneously without lock contention. Zone write plugging ignores flush BIOs without data. Hovever, any flush BIO that has data is always plugged so that the write part of the flush sequence is serialized with other regular writes. Given that any BIO handled through zone write plugging will be the only BIO in flight for the target zone when it is executed, the unplugging and submission of a BIO will have no chance of successfully merging with plugged requests or requests in the scheduler. To overcome this potential performance degradation, blk_mq_submit_bio() calls the function blk_zone_write_plug_attempt_merge() to try to merge other plugged BIOs with the one just unplugged and submitted. Successful merging is signaled using blk_zone_write_plug_bio_merged(), called from bio_attempt_back_merge(). Furthermore, to avoid recalculating the number of segments of plugged BIOs to attempt merging, the number of segments of a plugged BIO is saved using the new struct bio field __bi_nr_segments. To avoid growing the size of struct bio, this field is added as a union with the bio_cookie field. This is safe to do as polling is always disabled for plugged BIOs. When BIOs are plugged in a zone write plug, the device request queue usage counter is always incremented. This reference is kept and reused for blk-mq devices when the plugged BIO is unplugged and submitted again using submit_bio_noacct_nocheck(). For this case, the unplugged BIO is already flagged with BIO_ZONE_WRITE_PLUGGING and blk_mq_submit_bio() proceeds directly to allocating a new request for the BIO, re-using the usage reference count taken when the BIO was plugged. This extra reference count is dropped in blk_zone_write_plug_attempt_merge() for any plugged BIO that is successfully merged. Given that BIO-based devices will not take this path, the extra reference is dropped after a plugged BIO is unplugged and submitted. Zone write plugs are dynamically allocated and managed using a hash table (an array of struct hlist_head) with RCU protection. A zone write plug is allocated when a write BIO is received for the zone and not freed until the zone is fully written, reset or finished. To detect when a zone write plug can be freed, the write state of each zone is tracked using a write pointer offset which corresponds to the offset of a zone write pointer relative to the zone start. Write operations always increment this write pointer offset. Zone reset operations set it to 0 and zone finish operations set it to the zone size. If a write error happens, the wp_offset value of a zone write plug may become incorrect and out of sync with the device managed write pointer. This is handled using the zone write plug flag BLK_ZONE_WPLUG_ERROR. The function blk_zone_wplug_handle_error() is called from the new disk zone write plug work when this flag is set. This function executes a report zone to update the zone write pointer offset to the current value as indicated by the device. The disk zone write plug work is scheduled whenever a BIO flagged with BIO_ZONE_WRITE_PLUGGING completes with an error or when bio_zone_wplug_prepare_bio() detects an unaligned write. Once scheduled, the disk zone write plugs work keeps running until all zone errors are handled. To match the new data structures used for zoned disks, the function disk_free_zone_bitmaps() is renamed to the more generic disk_free_zone_resources(). The function disk_init_zone_resources() is also introduced to initialize zone write plugs resources when a gendisk is allocated. In order to guarantee that the user can simultaneously write up to a number of zones equal to a device max active zone limit or max open zone limit, zone write plugs are allocated using a mempool sized to the maximum of these 2 device limits. For a device that does not have active and open zone limits, 128 is used as the default mempool size. If a change to the device active and open zone limits is detected, the disk mempool is resized when blk_revalidate_disk_zones() is executed. This commit contains contributions from Christoph Hellwig <hch@lst.de>. Signed-off-by: Damien Le Moal <dlemoal@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Hannes Reinecke <hare@suse.de> Tested-by: Hans Holmberg <hans.holmberg@wdc.com> Tested-by: Dennis Maisenbacher <dennis.maisenbacher@wdc.com> Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Link: https://lore.kernel.org/r/20240408014128.205141-8-dlemoal@kernel.org Signed-off-by: Jens Axboe <axboe@kernel.dk>
2024-04-08 01:41:07 +00:00
/*
* A front merge for writes to sequential zones of a zoned block device
* can happen only if the user submitted writes out of order. Do not
* merge such write to let it fail.
*/
if (req->rq_flags & RQF_ZONE_WRITE_PLUGGING)
return BIO_MERGE_FAILED;
if (!ll_front_merge_fn(req, bio, nr_segs))
return BIO_MERGE_FAILED;
trace_block_bio_frontmerge(bio);
rq_qos_merge(req->q, req, bio);
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
blk_rq_set_mixed_merge(req);
block: sync mixed merged request's failfast with 1st bio's We support mixed merge for requests/bios with different fastfail settings. When request fails, each time we only handle the portion with same failfast setting, then bios with failfast can be failed immediately, and bios without failfast can be retried. The idea is pretty good, but the current implementation has several defects: 1) initially RA bio doesn't set failfast, however bio merge code doesn't consider this point, and just check its failfast setting for deciding if mixed merge is required. Fix this issue by adding helper of bio_failfast(). 2) when merging bio to request front, if this request is mixed merged, we have to sync request's faifast setting with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). 3) when merging bio to request back, if this request is mixed merged, we have to mark the bio as failfast, because blk_update_request simply updates request failfast with 1st bio's failfast. Fix it by calling blk_update_mixed_merge(). Fixes one normal EXT4 READ IO failure issue, because it is observed that the normal READ IO is merged with RA IO, and the mixed merged request has different failfast setting with 1st bio's, so finally the normal READ IO doesn't get retried. Cc: Tejun Heo <tj@kernel.org> Fixes: 80a761fd33cf ("block: implement mixed merge of different failfast requests") Signed-off-by: Ming Lei <ming.lei@redhat.com> Link: https://lore.kernel.org/r/20230209125527.667004-1-ming.lei@redhat.com Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-02-09 12:55:27 +00:00
blk_update_mixed_merge(req, bio, true);
bio->bi_next = req->bio;
req->bio = bio;
req->__sector = bio->bi_iter.bi_sector;
req->__data_len += bio->bi_iter.bi_size;
bio_crypt_do_front_merge(req, bio);
blk_account_io_merge_bio(req);
return BIO_MERGE_OK;
}
static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q,
struct request *req, struct bio *bio)
{
unsigned short segments = blk_rq_nr_discard_segments(req);
if (segments >= queue_max_discard_segments(q))
goto no_merge;
if (blk_rq_sectors(req) + bio_sectors(bio) >
blk_rq_get_max_sectors(req, blk_rq_pos(req)))
goto no_merge;
rq_qos_merge(q, req, bio);
req->biotail->bi_next = bio;
req->biotail = bio;
req->__data_len += bio->bi_iter.bi_size;
req->nr_phys_segments = segments + 1;
blk_account_io_merge_bio(req);
return BIO_MERGE_OK;
no_merge:
req_set_nomerge(q, req);
return BIO_MERGE_FAILED;
}
static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
struct request *rq,
struct bio *bio,
unsigned int nr_segs,
bool sched_allow_merge)
{
if (!blk_rq_merge_ok(rq, bio))
return BIO_MERGE_NONE;
switch (blk_try_merge(rq, bio)) {
case ELEVATOR_BACK_MERGE:
if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio))
return bio_attempt_back_merge(rq, bio, nr_segs);
break;
case ELEVATOR_FRONT_MERGE:
if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio))
return bio_attempt_front_merge(rq, bio, nr_segs);
break;
case ELEVATOR_DISCARD_MERGE:
return bio_attempt_discard_merge(q, rq, bio);
default:
return BIO_MERGE_NONE;
}
return BIO_MERGE_FAILED;
}
/**
* blk_attempt_plug_merge - try to merge with %current's plugged list
* @q: request_queue new bio is being queued at
* @bio: new bio being queued
* @nr_segs: number of segments in @bio
* from the passed in @q already in the plug list
*
* Determine whether @bio being queued on @q can be merged with the previous
* request on %current's plugged list. Returns %true if merge was successful,
* otherwise %false.
*
* Plugging coalesces IOs from the same issuer for the same purpose without
* going through @q->queue_lock. As such it's more of an issuing mechanism
* than scheduling, and the request, while may have elvpriv data, is not
* added on the elevator at this point. In addition, we don't have
* reliable access to the elevator outside queue lock. Only check basic
* merging parameters without querying the elevator.
*
* Caller must ensure !blk_queue_nomerges(q) beforehand.
*/
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
unsigned int nr_segs)
{
struct blk_plug *plug = current->plug;
struct request *rq;
if (!plug || rq_list_empty(plug->mq_list))
return false;
rq_list_for_each(&plug->mq_list, rq) {
if (rq->q == q) {
if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
BIO_MERGE_OK)
return true;
break;
}
/*
* Only keep iterating plug list for merges if we have multiple
* queues
*/
if (!plug->multiple_queues)
break;
}
return false;
}
/*
* Iterate list of requests and see if we can merge this bio with any
* of them.
*/
bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
struct bio *bio, unsigned int nr_segs)
{
struct request *rq;
int checked = 8;
list_for_each_entry_reverse(rq, list, queuelist) {
if (!checked--)
break;
switch (blk_attempt_bio_merge(q, rq, bio, nr_segs, true)) {
case BIO_MERGE_NONE:
continue;
case BIO_MERGE_OK:
return true;
case BIO_MERGE_FAILED:
return false;
}
}
return false;
}
EXPORT_SYMBOL_GPL(blk_bio_list_merge);
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
unsigned int nr_segs, struct request **merged_request)
{
struct request *rq;
switch (elv_merge(q, &rq, bio)) {
case ELEVATOR_BACK_MERGE:
if (!blk_mq_sched_allow_merge(q, rq, bio))
return false;
if (bio_attempt_back_merge(rq, bio, nr_segs) != BIO_MERGE_OK)
return false;
*merged_request = attempt_back_merge(q, rq);
if (!*merged_request)
elv_merged_request(q, rq, ELEVATOR_BACK_MERGE);
return true;
case ELEVATOR_FRONT_MERGE:
if (!blk_mq_sched_allow_merge(q, rq, bio))
return false;
if (bio_attempt_front_merge(rq, bio, nr_segs) != BIO_MERGE_OK)
return false;
*merged_request = attempt_front_merge(q, rq);
if (!*merged_request)
elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE);
return true;
case ELEVATOR_DISCARD_MERGE:
return bio_attempt_discard_merge(q, rq, bio) == BIO_MERGE_OK;
default:
return false;
}
}
EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);