linux-stable/block/elevator.c

825 lines
18 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Block device elevator/IO-scheduler.
*
* Copyright (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
*
* 30042000 Jens Axboe <axboe@kernel.dk> :
*
* Split the elevator a bit so that it is possible to choose a different
* one or even write a new "plug in". There are three pieces:
* - elevator_fn, inserts a new request in the queue list
* - elevator_merge_fn, decides whether a new buffer can be merged with
* an existing request
* - elevator_dequeue_fn, called when a request is taken off the active list
*
* 20082000 Dave Jones <davej@suse.de> :
* Removed tests for max-bomb-segments, which was breaking elvtune
* when run without -bN
*
* Jens:
* - Rework again to work with bio instead of buffer_heads
* - loose bi_dev comparisons, partition handling is right now
* - completely modularize elevator setup and teardown
*
*/
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/blktrace_api.h>
#include <linux/hash.h>
#include <linux/uaccess.h>
#include <linux/pm_runtime.h>
tracing/events: convert block trace points to TRACE_EVENT() TRACE_EVENT is a more generic way to define tracepoints. Doing so adds these new capabilities to this tracepoint: - zero-copy and per-cpu splice() tracing - binary tracing without printf overhead - structured logging records exposed under /debug/tracing/events - trace events embedded in function tracer output and other plugins - user-defined, per tracepoint filter expressions ... Cons: - no dev_t info for the output of plug, unplug_timer and unplug_io events. no dev_t info for getrq and sleeprq events if bio == NULL. no dev_t info for rq_abort,...,rq_requeue events if rq->rq_disk == NULL. This is mainly because we can't get the deivce from a request queue. But this may change in the future. - A packet command is converted to a string in TP_assign, not TP_print. While blktrace do the convertion just before output. Since pc requests should be rather rare, this is not a big issue. - In blktrace, an event can have 2 different print formats, but a TRACE_EVENT has a unique format, which means we have some unused data in a trace entry. The overhead is minimized by using __dynamic_array() instead of __array(). I've benchmarked the ioctl blktrace vs the splice based TRACE_EVENT tracing: dd dd + ioctl blktrace dd + TRACE_EVENT (splice) 1 7.36s, 42.7 MB/s 7.50s, 42.0 MB/s 7.41s, 42.5 MB/s 2 7.43s, 42.3 MB/s 7.48s, 42.1 MB/s 7.43s, 42.4 MB/s 3 7.38s, 42.6 MB/s 7.45s, 42.2 MB/s 7.41s, 42.5 MB/s So the overhead of tracing is very small, and no regression when using those trace events vs blktrace. And the binary output of TRACE_EVENT is much smaller than blktrace: # ls -l -h -rw-r--r-- 1 root root 8.8M 06-09 13:24 sda.blktrace.0 -rw-r--r-- 1 root root 195K 06-09 13:24 sda.blktrace.1 -rw-r--r-- 1 root root 2.7M 06-09 13:25 trace_splice.out Following are some comparisons between TRACE_EVENT and blktrace: plug: kjournald-480 [000] 303.084981: block_plug: [kjournald] kjournald-480 [000] 303.084981: 8,0 P N [kjournald] unplug_io: kblockd/0-118 [000] 300.052973: block_unplug_io: [kblockd/0] 1 kblockd/0-118 [000] 300.052974: 8,0 U N [kblockd/0] 1 remap: kjournald-480 [000] 303.085042: block_remap: 8,0 W 102736992 + 8 <- (8,8) 33384 kjournald-480 [000] 303.085043: 8,0 A W 102736992 + 8 <- (8,8) 33384 bio_backmerge: kjournald-480 [000] 303.085086: block_bio_backmerge: 8,0 W 102737032 + 8 [kjournald] kjournald-480 [000] 303.085086: 8,0 M W 102737032 + 8 [kjournald] getrq: kjournald-480 [000] 303.084974: block_getrq: 8,0 W 102736984 + 8 [kjournald] kjournald-480 [000] 303.084975: 8,0 G W 102736984 + 8 [kjournald] bash-2066 [001] 1072.953770: 8,0 G N [bash] bash-2066 [001] 1072.953773: block_getrq: 0,0 N 0 + 0 [bash] rq_complete: konsole-2065 [001] 300.053184: block_rq_complete: 8,0 W () 103669040 + 16 [0] konsole-2065 [001] 300.053191: 8,0 C W 103669040 + 16 [0] ksoftirqd/1-7 [001] 1072.953811: 8,0 C N (5a 00 08 00 00 00 00 00 24 00) [0] ksoftirqd/1-7 [001] 1072.953813: block_rq_complete: 0,0 N (5a 00 08 00 00 00 00 00 24 00) 0 + 0 [0] rq_insert: kjournald-480 [000] 303.084985: block_rq_insert: 8,0 W 0 () 102736984 + 8 [kjournald] kjournald-480 [000] 303.084986: 8,0 I W 102736984 + 8 [kjournald] Changelog from v2 -> v3: - use the newly introduced __dynamic_array(). Changelog from v1 -> v2: - use __string() instead of __array() to minimize the memory required to store hex dump of rq->cmd(). - support large pc requests. - add missing blk_fill_rwbs_rq() in block_rq_requeue TRACE_EVENT. - some cleanups. Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> LKML-Reference: <4A2DF669.5070905@cn.fujitsu.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-06-09 05:43:05 +00:00
#include <trace/events/block.h>
#include "elevator.h"
#include "blk.h"
#include "blk-mq-sched.h"
#include "blk-pm.h"
#include "blk-wbt.h"
#include "blk-cgroup.h"
static DEFINE_SPINLOCK(elv_list_lock);
static LIST_HEAD(elv_list);
/*
* Merge hash stuff.
*/
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
#define rq_hash_key(rq) (blk_rq_pos(rq) + blk_rq_sectors(rq))
/*
* Query io scheduler to see if the current process issuing bio may be
* merged with rq.
*/
static bool elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio)
{
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
if (e->type->ops.allow_merge)
return e->type->ops.allow_merge(q, rq, bio);
return true;
}
/*
* can we safely merge with this request?
*/
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
bool elv_bio_merge_ok(struct request *rq, struct bio *bio)
{
if (!blk_rq_merge_ok(rq, bio))
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
return false;
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
if (!elv_iosched_allow_bio_merge(rq, bio))
return false;
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
return true;
}
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
EXPORT_SYMBOL(elv_bio_merge_ok);
static inline bool elv_support_features(struct request_queue *q,
const struct elevator_type *e)
{
return (q->required_elevator_features & e->elevator_features) ==
q->required_elevator_features;
block: Introduce elevator features Introduce the definition of elevator features through the elevator_features flags in the elevator_type structure. Each flag can represent a feature supported by an elevator. The first feature defined by this patch is support for zoned block device sequential write constraint with the flag ELEVATOR_F_ZBD_SEQ_WRITE, which is implemented by the mq-deadline elevator using zone write locking. Other possible features are IO priorities, write hints, latency targets or single-LUN dual-actuator disks (for which the elevator could maintain one LBA ordered list per actuator). The required_elevator_features field is also added to the request_queue structure to allow a device driver to specify elevator feature flags that an elevator must support for the correct operation of the device (e.g. device drivers for zoned block devices can have the ELEVATOR_F_ZBD_SEQ_WRITE flag as a required feature). The helper function blk_queue_required_elevator_features() is defined for setting this new field. With these two new fields in place, the elevator functions elevator_match() and elevator_find() are modified to allow a user to set only an elevator with a set of features that satisfies the device required features. Elevators not matching the device requirements are not shown in the device sysfs queue/scheduler file to prevent their use. The "none" elevator can always be selected as before. Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-09-05 09:51:31 +00:00
}
/**
* elevator_match - Check whether @e's name or alias matches @name
block: Introduce elevator features Introduce the definition of elevator features through the elevator_features flags in the elevator_type structure. Each flag can represent a feature supported by an elevator. The first feature defined by this patch is support for zoned block device sequential write constraint with the flag ELEVATOR_F_ZBD_SEQ_WRITE, which is implemented by the mq-deadline elevator using zone write locking. Other possible features are IO priorities, write hints, latency targets or single-LUN dual-actuator disks (for which the elevator could maintain one LBA ordered list per actuator). The required_elevator_features field is also added to the request_queue structure to allow a device driver to specify elevator feature flags that an elevator must support for the correct operation of the device (e.g. device drivers for zoned block devices can have the ELEVATOR_F_ZBD_SEQ_WRITE flag as a required feature). The helper function blk_queue_required_elevator_features() is defined for setting this new field. With these two new fields in place, the elevator functions elevator_match() and elevator_find() are modified to allow a user to set only an elevator with a set of features that satisfies the device required features. Elevators not matching the device requirements are not shown in the device sysfs queue/scheduler file to prevent their use. The "none" elevator can always be selected as before. Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-09-05 09:51:31 +00:00
* @e: Scheduler to test
* @name: Elevator name to test
*
* Return true if the elevator @e's name or alias matches @name.
block: Introduce elevator features Introduce the definition of elevator features through the elevator_features flags in the elevator_type structure. Each flag can represent a feature supported by an elevator. The first feature defined by this patch is support for zoned block device sequential write constraint with the flag ELEVATOR_F_ZBD_SEQ_WRITE, which is implemented by the mq-deadline elevator using zone write locking. Other possible features are IO priorities, write hints, latency targets or single-LUN dual-actuator disks (for which the elevator could maintain one LBA ordered list per actuator). The required_elevator_features field is also added to the request_queue structure to allow a device driver to specify elevator feature flags that an elevator must support for the correct operation of the device (e.g. device drivers for zoned block devices can have the ELEVATOR_F_ZBD_SEQ_WRITE flag as a required feature). The helper function blk_queue_required_elevator_features() is defined for setting this new field. With these two new fields in place, the elevator functions elevator_match() and elevator_find() are modified to allow a user to set only an elevator with a set of features that satisfies the device required features. Elevators not matching the device requirements are not shown in the device sysfs queue/scheduler file to prevent their use. The "none" elevator can always be selected as before. Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-09-05 09:51:31 +00:00
*/
static bool elevator_match(const struct elevator_type *e, const char *name)
block: Introduce elevator features Introduce the definition of elevator features through the elevator_features flags in the elevator_type structure. Each flag can represent a feature supported by an elevator. The first feature defined by this patch is support for zoned block device sequential write constraint with the flag ELEVATOR_F_ZBD_SEQ_WRITE, which is implemented by the mq-deadline elevator using zone write locking. Other possible features are IO priorities, write hints, latency targets or single-LUN dual-actuator disks (for which the elevator could maintain one LBA ordered list per actuator). The required_elevator_features field is also added to the request_queue structure to allow a device driver to specify elevator feature flags that an elevator must support for the correct operation of the device (e.g. device drivers for zoned block devices can have the ELEVATOR_F_ZBD_SEQ_WRITE flag as a required feature). The helper function blk_queue_required_elevator_features() is defined for setting this new field. With these two new fields in place, the elevator functions elevator_match() and elevator_find() are modified to allow a user to set only an elevator with a set of features that satisfies the device required features. Elevators not matching the device requirements are not shown in the device sysfs queue/scheduler file to prevent their use. The "none" elevator can always be selected as before. Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-09-05 09:51:31 +00:00
{
return !strcmp(e->elevator_name, name) ||
(e->elevator_alias && !strcmp(e->elevator_alias, name));
}
static struct elevator_type *__elevator_find(const char *name)
{
struct elevator_type *e;
list_for_each_entry(e, &elv_list, list)
if (elevator_match(e, name))
return e;
return NULL;
}
static struct elevator_type *elevator_find_get(struct request_queue *q,
const char *name)
{
struct elevator_type *e;
spin_lock(&elv_list_lock);
e = __elevator_find(name);
if (e && (!elv_support_features(q, e) || !elevator_tryget(e)))
e = NULL;
spin_unlock(&elv_list_lock);
return e;
}
static const struct kobj_type elv_ktype;
struct elevator_queue *elevator_alloc(struct request_queue *q,
struct elevator_type *e)
{
struct elevator_queue *eq;
eq = kzalloc_node(sizeof(*eq), GFP_KERNEL, q->node);
if (unlikely(!eq))
return NULL;
block: fix up elevator_type refcounting The current reference management logic of io scheduler modules contains refcnt problems. For example, blk_mq_init_sched may fail before or after the calling of e->ops.init_sched. If it fails before the calling, it does nothing to the reference to the io scheduler module. But if it fails after the calling, it releases the reference by calling kobject_put(&eq->kobj). As the callers of blk_mq_init_sched can't know exactly where the failure happens, they can't handle the reference to the io scheduler module properly: releasing the reference on failure results in double-release if blk_mq_init_sched has released it, and not releasing the reference results in ghost reference if blk_mq_init_sched did not release it either. The same problem also exists in io schedulers' init_sched implementations. We can address the problem by adding releasing statements to the error handling procedures of blk_mq_init_sched and init_sched implementations. But that is counterintuitive and requires modifications to existing io schedulers. Instead, We make elevator_alloc get the io scheduler module references that will be released by elevator_release. And then, we match each elevator_get with an elevator_put. Therefore, each reference to an io scheduler module explicitly has its own getter and releaser, and we no longer need to worry about the refcnt problems. The bugs and the patch can be validated with tools here: https://github.com/nickyc975/linux_elv_refcnt_bug.git [hch: split out a few bits into separate patches, use a non-try module_get in elevator_alloc] Signed-off-by: Jinlong Chen <nickyc975@zju.edu.cn> Signed-off-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/20221020064819.1469928-5-hch@lst.de Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-10-20 06:48:19 +00:00
__elevator_get(e);
eq->type = e;
kobject_init(&eq->kobj, &elv_ktype);
mutex_init(&eq->sysfs_lock);
hash_init(eq->hash);
return eq;
}
EXPORT_SYMBOL(elevator_alloc);
static void elevator_release(struct kobject *kobj)
{
struct elevator_queue *e;
e = container_of(kobj, struct elevator_queue, kobj);
elevator_put(e->type);
kfree(e);
}
void elevator_exit(struct request_queue *q)
{
struct elevator_queue *e = q->elevator;
ioc_clear_queue(q);
blk_mq_sched_free_rqs(q);
mutex_lock(&e->sysfs_lock);
blk_mq_exit_sched(q, e);
mutex_unlock(&e->sysfs_lock);
kobject_put(&e->kobj);
}
static inline void __elv_rqhash_del(struct request *rq)
{
hash_del(&rq->hash);
rq->rq_flags &= ~RQF_HASHED;
}
void elv_rqhash_del(struct request_queue *q, struct request *rq)
{
if (ELV_ON_HASH(rq))
__elv_rqhash_del(rq);
}
EXPORT_SYMBOL_GPL(elv_rqhash_del);
void elv_rqhash_add(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
BUG_ON(ELV_ON_HASH(rq));
hash_add(e->hash, &rq->hash, rq_hash_key(rq));
rq->rq_flags |= RQF_HASHED;
}
EXPORT_SYMBOL_GPL(elv_rqhash_add);
void elv_rqhash_reposition(struct request_queue *q, struct request *rq)
{
__elv_rqhash_del(rq);
elv_rqhash_add(q, rq);
}
struct request *elv_rqhash_find(struct request_queue *q, sector_t offset)
{
struct elevator_queue *e = q->elevator;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
struct hlist_node *next;
struct request *rq;
Merge branch 'for-3.9/core' of git://git.kernel.dk/linux-block Pull block IO core bits from Jens Axboe: "Below are the core block IO bits for 3.9. It was delayed a few days since my workstation kept crashing every 2-8h after pulling it into current -git, but turns out it is a bug in the new pstate code (divide by zero, will report separately). In any case, it contains: - The big cfq/blkcg update from Tejun and and Vivek. - Additional block and writeback tracepoints from Tejun. - Improvement of the should sort (based on queues) logic in the plug flushing. - _io() variants of the wait_for_completion() interface, using io_schedule() instead of schedule() to contribute to io wait properly. - Various little fixes. You'll get two trivial merge conflicts, which should be easy enough to fix up" Fix up the trivial conflicts due to hlist traversal cleanups (commit b67bfe0d42ca: "hlist: drop the node parameter from iterators"). * 'for-3.9/core' of git://git.kernel.dk/linux-block: (39 commits) block: remove redundant check to bd_openers() block: use i_size_write() in bd_set_size() cfq: fix lock imbalance with failed allocations drivers/block/swim3.c: fix null pointer dereference block: don't select PERCPU_RWSEM block: account iowait time when waiting for completion of IO request sched: add wait_for_completion_io[_timeout] writeback: add more tracepoints block: add block_{touch|dirty}_buffer tracepoint buffer: make touch_buffer() an exported function block: add @req to bio_{front|back}_merge tracepoints block: add missing block_bio_complete() tracepoint block: Remove should_sort judgement when flush blk_plug block,elevator: use new hashtable implementation cfq-iosched: add hierarchical cfq_group statistics cfq-iosched: collect stats from dead cfqgs cfq-iosched: separate out cfqg_stats_reset() from cfq_pd_reset_stats() blkcg: make blkcg_print_blkgs() grab q locks instead of blkcg lock block: RCU free request_queue blkcg: implement blkg_[rw]stat_recursive_sum() and blkg_[rw]stat_merge() ...
2013-02-28 20:52:24 +00:00
hash_for_each_possible_safe(e->hash, rq, next, hash, offset) {
BUG_ON(!ELV_ON_HASH(rq));
if (unlikely(!rq_mergeable(rq))) {
__elv_rqhash_del(rq);
continue;
}
if (rq_hash_key(rq) == offset)
return rq;
}
return NULL;
}
/*
* RB-tree support functions for inserting/lookup/removal of requests
* in a sorted RB tree.
*/
void elv_rb_add(struct rb_root *root, struct request *rq)
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct request *__rq;
while (*p) {
parent = *p;
__rq = rb_entry(parent, struct request, rb_node);
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
if (blk_rq_pos(rq) < blk_rq_pos(__rq))
p = &(*p)->rb_left;
else if (blk_rq_pos(rq) >= blk_rq_pos(__rq))
p = &(*p)->rb_right;
}
rb_link_node(&rq->rb_node, parent, p);
rb_insert_color(&rq->rb_node, root);
}
EXPORT_SYMBOL(elv_rb_add);
void elv_rb_del(struct rb_root *root, struct request *rq)
{
BUG_ON(RB_EMPTY_NODE(&rq->rb_node));
rb_erase(&rq->rb_node, root);
RB_CLEAR_NODE(&rq->rb_node);
}
EXPORT_SYMBOL(elv_rb_del);
struct request *elv_rb_find(struct rb_root *root, sector_t sector)
{
struct rb_node *n = root->rb_node;
struct request *rq;
while (n) {
rq = rb_entry(n, struct request, rb_node);
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
if (sector < blk_rq_pos(rq))
n = n->rb_left;
block: convert to pos and nr_sectors accessors With recent cleanups, there is no place where low level driver directly manipulates request fields. This means that the 'hard' request fields always equal the !hard fields. Convert all rq->sectors, nr_sectors and current_nr_sectors references to accessors. While at it, drop superflous blk_rq_pos() < 0 test in swim.c. [ Impact: use pos and nr_sectors accessors ] Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Tested-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Grant Likely <grant.likely@secretlab.ca> Tested-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Adrian McMenamin <adrian@mcmen.demon.co.uk> Acked-by: Mike Miller <mike.miller@hp.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Dario Ballabio <ballabio_dario@emc.com> Cc: David S. Miller <davem@davemloft.net> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: unsik Kim <donari75@gmail.com> Cc: Laurent Vivier <Laurent@lvivier.info> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:39 +00:00
else if (sector > blk_rq_pos(rq))
n = n->rb_right;
else
return rq;
}
return NULL;
}
EXPORT_SYMBOL(elv_rb_find);
enum elv_merge elv_merge(struct request_queue *q, struct request **req,
struct bio *bio)
{
struct elevator_queue *e = q->elevator;
struct request *__rq;
/*
* Levels of merges:
* nomerges: No merges at all attempted
* noxmerges: Only simple one-hit cache try
* merges: All merge tries attempted
*/
if (blk_queue_nomerges(q) || !bio_mergeable(bio))
return ELEVATOR_NO_MERGE;
/*
* First try one-hit cache.
*/
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
if (q->last_merge && elv_bio_merge_ok(q->last_merge, bio)) {
enum elv_merge ret = blk_try_merge(q->last_merge, bio);
if (ret != ELEVATOR_NO_MERGE) {
*req = q->last_merge;
return ret;
}
}
if (blk_queue_noxmerges(q))
return ELEVATOR_NO_MERGE;
/*
* See if our hash lookup can find a potential backmerge.
*/
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
__rq = elv_rqhash_find(q, bio->bi_iter.bi_sector);
block: do not merge requests without consulting with io scheduler Before merging a bio into an existing request, io scheduler is called to get its approval first. However, the requests that come from a plug flush may get merged by block layer without consulting with io scheduler. In case of CFQ, this can cause fairness problems. For instance, if a request gets merged into a low weight cgroup's request, high weight cgroup now will depend on low weight cgroup to get scheduled. If high weigt cgroup needs that io request to complete before submitting more requests, then it will also lose its timeslice. Following script demonstrates the problem. Group g1 has a low weight, g2 and g3 have equal high weights but g2's requests are adjacent to g1's requests so they are subject to merging. Due to these merges, g2 gets poor disk time allocation. cat > cfq-merge-repro.sh << "EOF" #!/bin/bash set -e IO_ROOT=/mnt-cgroup/io mkdir -p $IO_ROOT if ! mount | grep -qw $IO_ROOT; then mount -t cgroup none -oblkio $IO_ROOT fi cd $IO_ROOT for i in g1 g2 g3; do if [ -d $i ]; then rmdir $i fi done mkdir g1 && echo 10 > g1/blkio.weight mkdir g2 && echo 495 > g2/blkio.weight mkdir g3 && echo 495 > g3/blkio.weight RUNTIME=10 (echo $BASHPID > g1/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=0k &> /dev/null)& (echo $BASHPID > g2/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=64k &> /dev/null)& (echo $BASHPID > g3/cgroup.procs && fio --readonly --name name1 --filename /dev/sdb \ --rw read --size 64k --bs 64k --time_based \ --runtime=$RUNTIME --offset=256k &> /dev/null)& sleep $((RUNTIME+1)) for i in g1 g2 g3; do echo ---- $i ---- cat $i/blkio.time done EOF # ./cfq-merge-repro.sh ---- g1 ---- 8:16 162 ---- g2 ---- 8:16 165 ---- g3 ---- 8:16 686 After applying the patch: # ./cfq-merge-repro.sh ---- g1 ---- 8:16 90 ---- g2 ---- 8:16 445 ---- g3 ---- 8:16 471 Signed-off-by: Tahsin Erdogan <tahsin@google.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-07 18:48:22 +00:00
if (__rq && elv_bio_merge_ok(__rq, bio)) {
*req = __rq;
if (blk_discard_mergable(__rq))
return ELEVATOR_DISCARD_MERGE;
return ELEVATOR_BACK_MERGE;
}
if (e->type->ops.request_merge)
return e->type->ops.request_merge(q, req, bio);
return ELEVATOR_NO_MERGE;
}
/*
* Attempt to do an insertion back merge. Only check for the case where
* we can append 'rq' to an existing request, so we can throw 'rq' away
* afterwards.
*
* Returns true if we merged, false otherwise. 'free' will contain all
* requests that need to be freed.
*/
bool elv_attempt_insert_merge(struct request_queue *q, struct request *rq,
struct list_head *free)
{
struct request *__rq;
bool ret;
if (blk_queue_nomerges(q))
return false;
/*
* First try one-hit cache.
*/
if (q->last_merge && blk_attempt_req_merge(q, q->last_merge, rq)) {
list_add(&rq->queuelist, free);
return true;
}
if (blk_queue_noxmerges(q))
return false;
ret = false;
/*
* See if our hash lookup can find a potential backmerge.
*/
while (1) {
__rq = elv_rqhash_find(q, blk_rq_pos(rq));
if (!__rq || !blk_attempt_req_merge(q, __rq, rq))
break;
list_add(&rq->queuelist, free);
/* The merged request could be merged with others, try again */
ret = true;
rq = __rq;
}
return ret;
}
void elv_merged_request(struct request_queue *q, struct request *rq,
enum elv_merge type)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.request_merged)
e->type->ops.request_merged(q, rq, type);
if (type == ELEVATOR_BACK_MERGE)
elv_rqhash_reposition(q, rq);
q->last_merge = rq;
}
void elv_merge_requests(struct request_queue *q, struct request *rq,
struct request *next)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.requests_merged)
e->type->ops.requests_merged(q, rq, next);
elv_rqhash_reposition(q, rq);
q->last_merge = rq;
}
struct request *elv_latter_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.next_request)
return e->type->ops.next_request(q, rq);
return NULL;
}
struct request *elv_former_request(struct request_queue *q, struct request *rq)
{
struct elevator_queue *e = q->elevator;
if (e->type->ops.former_request)
return e->type->ops.former_request(q, rq);
return NULL;
}
#define to_elv(atr) container_of((atr), struct elv_fs_entry, attr)
static ssize_t
elv_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
struct elv_fs_entry *entry = to_elv(attr);
struct elevator_queue *e;
ssize_t error;
if (!entry->show)
return -EIO;
e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
error = e->type ? entry->show(e, page) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
return error;
}
static ssize_t
elv_attr_store(struct kobject *kobj, struct attribute *attr,
const char *page, size_t length)
{
struct elv_fs_entry *entry = to_elv(attr);
struct elevator_queue *e;
ssize_t error;
if (!entry->store)
return -EIO;
e = container_of(kobj, struct elevator_queue, kobj);
mutex_lock(&e->sysfs_lock);
error = e->type ? entry->store(e, page, length) : -ENOENT;
mutex_unlock(&e->sysfs_lock);
return error;
}
static const struct sysfs_ops elv_sysfs_ops = {
.show = elv_attr_show,
.store = elv_attr_store,
};
static const struct kobj_type elv_ktype = {
.sysfs_ops = &elv_sysfs_ops,
.release = elevator_release,
};
block: split .sysfs_lock into two locks The kernfs built-in lock of 'kn->count' is held in sysfs .show/.store path. Meantime, inside block's .show/.store callback, q->sysfs_lock is required. However, when mq & iosched kobjects are removed via blk_mq_unregister_dev() & elv_unregister_queue(), q->sysfs_lock is held too. This way causes AB-BA lock because the kernfs built-in lock of 'kn-count' is required inside kobject_del() too, see the lockdep warning[1]. On the other hand, it isn't necessary to acquire q->sysfs_lock for both blk_mq_unregister_dev() & elv_unregister_queue() because clearing REGISTERED flag prevents storing to 'queue/scheduler' from being happened. Also sysfs write(store) is exclusive, so no necessary to hold the lock for elv_unregister_queue() when it is called in switching elevator path. So split .sysfs_lock into two: one is still named as .sysfs_lock for covering sync .store, the other one is named as .sysfs_dir_lock for covering kobjects and related status change. sysfs itself can handle the race between add/remove kobjects and showing/storing attributes under kobjects. For switching scheduler via storing to 'queue/scheduler', we use the queue flag of QUEUE_FLAG_REGISTERED with .sysfs_lock for avoiding the race, then we can avoid to hold .sysfs_lock during removing/adding kobjects. [1] lockdep warning ====================================================== WARNING: possible circular locking dependency detected 5.3.0-rc3-00044-g73277fc75ea0 #1380 Not tainted ------------------------------------------------------ rmmod/777 is trying to acquire lock: 00000000ac50e981 (kn->count#202){++++}, at: kernfs_remove_by_name_ns+0x59/0x72 but task is already holding lock: 00000000fb16ae21 (&q->sysfs_lock){+.+.}, at: blk_unregister_queue+0x78/0x10b which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&q->sysfs_lock){+.+.}: __lock_acquire+0x95f/0xa2f lock_acquire+0x1b4/0x1e8 __mutex_lock+0x14a/0xa9b blk_mq_hw_sysfs_show+0x63/0xb6 sysfs_kf_seq_show+0x11f/0x196 seq_read+0x2cd/0x5f2 vfs_read+0xc7/0x18c ksys_read+0xc4/0x13e do_syscall_64+0xa7/0x295 entry_SYSCALL_64_after_hwframe+0x49/0xbe -> #0 (kn->count#202){++++}: check_prev_add+0x5d2/0xc45 validate_chain+0xed3/0xf94 __lock_acquire+0x95f/0xa2f lock_acquire+0x1b4/0x1e8 __kernfs_remove+0x237/0x40b kernfs_remove_by_name_ns+0x59/0x72 remove_files+0x61/0x96 sysfs_remove_group+0x81/0xa4 sysfs_remove_groups+0x3b/0x44 kobject_del+0x44/0x94 blk_mq_unregister_dev+0x83/0xdd blk_unregister_queue+0xa0/0x10b del_gendisk+0x259/0x3fa null_del_dev+0x8b/0x1c3 [null_blk] null_exit+0x5c/0x95 [null_blk] __se_sys_delete_module+0x204/0x337 do_syscall_64+0xa7/0x295 entry_SYSCALL_64_after_hwframe+0x49/0xbe other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&q->sysfs_lock); lock(kn->count#202); lock(&q->sysfs_lock); lock(kn->count#202); *** DEADLOCK *** 2 locks held by rmmod/777: #0: 00000000e69bd9de (&lock){+.+.}, at: null_exit+0x2e/0x95 [null_blk] #1: 00000000fb16ae21 (&q->sysfs_lock){+.+.}, at: blk_unregister_queue+0x78/0x10b stack backtrace: CPU: 0 PID: 777 Comm: rmmod Not tainted 5.3.0-rc3-00044-g73277fc75ea0 #1380 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20180724_192412-buildhw-07.phx4 Call Trace: dump_stack+0x9a/0xe6 check_noncircular+0x207/0x251 ? print_circular_bug+0x32a/0x32a ? find_usage_backwards+0x84/0xb0 check_prev_add+0x5d2/0xc45 validate_chain+0xed3/0xf94 ? check_prev_add+0xc45/0xc45 ? mark_lock+0x11b/0x804 ? check_usage_forwards+0x1ca/0x1ca __lock_acquire+0x95f/0xa2f lock_acquire+0x1b4/0x1e8 ? kernfs_remove_by_name_ns+0x59/0x72 __kernfs_remove+0x237/0x40b ? kernfs_remove_by_name_ns+0x59/0x72 ? kernfs_next_descendant_post+0x7d/0x7d ? strlen+0x10/0x23 ? strcmp+0x22/0x44 kernfs_remove_by_name_ns+0x59/0x72 remove_files+0x61/0x96 sysfs_remove_group+0x81/0xa4 sysfs_remove_groups+0x3b/0x44 kobject_del+0x44/0x94 blk_mq_unregister_dev+0x83/0xdd blk_unregister_queue+0xa0/0x10b del_gendisk+0x259/0x3fa ? disk_events_poll_msecs_store+0x12b/0x12b ? check_flags+0x1ea/0x204 ? mark_held_locks+0x1f/0x7a null_del_dev+0x8b/0x1c3 [null_blk] null_exit+0x5c/0x95 [null_blk] __se_sys_delete_module+0x204/0x337 ? free_module+0x39f/0x39f ? blkcg_maybe_throttle_current+0x8a/0x718 ? rwlock_bug+0x62/0x62 ? __blkcg_punt_bio_submit+0xd0/0xd0 ? trace_hardirqs_on_thunk+0x1a/0x20 ? mark_held_locks+0x1f/0x7a ? do_syscall_64+0x4c/0x295 do_syscall_64+0xa7/0x295 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fb696cdbe6b Code: 73 01 c3 48 8b 0d 1d 20 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 008 RSP: 002b:00007ffec9588788 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 RAX: ffffffffffffffda RBX: 0000559e589137c0 RCX: 00007fb696cdbe6b RDX: 000000000000000a RSI: 0000000000000800 RDI: 0000559e58913828 RBP: 0000000000000000 R08: 00007ffec9587701 R09: 0000000000000000 R10: 00007fb696d4eae0 R11: 0000000000000206 R12: 00007ffec95889b0 R13: 00007ffec95896b3 R14: 0000559e58913260 R15: 0000559e589137c0 Cc: Christoph Hellwig <hch@infradead.org> Cc: Hannes Reinecke <hare@suse.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-08-27 11:01:48 +00:00
int elv_register_queue(struct request_queue *q, bool uevent)
{
struct elevator_queue *e = q->elevator;
int error;
lockdep_assert_held(&q->sysfs_lock);
error = kobject_add(&e->kobj, &q->disk->queue_kobj, "iosched");
if (!error) {
struct elv_fs_entry *attr = e->type->elevator_attrs;
if (attr) {
while (attr->attr.name) {
if (sysfs_create_file(&e->kobj, &attr->attr))
break;
attr++;
}
}
block: split .sysfs_lock into two locks The kernfs built-in lock of 'kn->count' is held in sysfs .show/.store path. Meantime, inside block's .show/.store callback, q->sysfs_lock is required. However, when mq & iosched kobjects are removed via blk_mq_unregister_dev() & elv_unregister_queue(), q->sysfs_lock is held too. This way causes AB-BA lock because the kernfs built-in lock of 'kn-count' is required inside kobject_del() too, see the lockdep warning[1]. On the other hand, it isn't necessary to acquire q->sysfs_lock for both blk_mq_unregister_dev() & elv_unregister_queue() because clearing REGISTERED flag prevents storing to 'queue/scheduler' from being happened. Also sysfs write(store) is exclusive, so no necessary to hold the lock for elv_unregister_queue() when it is called in switching elevator path. So split .sysfs_lock into two: one is still named as .sysfs_lock for covering sync .store, the other one is named as .sysfs_dir_lock for covering kobjects and related status change. sysfs itself can handle the race between add/remove kobjects and showing/storing attributes under kobjects. For switching scheduler via storing to 'queue/scheduler', we use the queue flag of QUEUE_FLAG_REGISTERED with .sysfs_lock for avoiding the race, then we can avoid to hold .sysfs_lock during removing/adding kobjects. [1] lockdep warning ====================================================== WARNING: possible circular locking dependency detected 5.3.0-rc3-00044-g73277fc75ea0 #1380 Not tainted ------------------------------------------------------ rmmod/777 is trying to acquire lock: 00000000ac50e981 (kn->count#202){++++}, at: kernfs_remove_by_name_ns+0x59/0x72 but task is already holding lock: 00000000fb16ae21 (&q->sysfs_lock){+.+.}, at: blk_unregister_queue+0x78/0x10b which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&q->sysfs_lock){+.+.}: __lock_acquire+0x95f/0xa2f lock_acquire+0x1b4/0x1e8 __mutex_lock+0x14a/0xa9b blk_mq_hw_sysfs_show+0x63/0xb6 sysfs_kf_seq_show+0x11f/0x196 seq_read+0x2cd/0x5f2 vfs_read+0xc7/0x18c ksys_read+0xc4/0x13e do_syscall_64+0xa7/0x295 entry_SYSCALL_64_after_hwframe+0x49/0xbe -> #0 (kn->count#202){++++}: check_prev_add+0x5d2/0xc45 validate_chain+0xed3/0xf94 __lock_acquire+0x95f/0xa2f lock_acquire+0x1b4/0x1e8 __kernfs_remove+0x237/0x40b kernfs_remove_by_name_ns+0x59/0x72 remove_files+0x61/0x96 sysfs_remove_group+0x81/0xa4 sysfs_remove_groups+0x3b/0x44 kobject_del+0x44/0x94 blk_mq_unregister_dev+0x83/0xdd blk_unregister_queue+0xa0/0x10b del_gendisk+0x259/0x3fa null_del_dev+0x8b/0x1c3 [null_blk] null_exit+0x5c/0x95 [null_blk] __se_sys_delete_module+0x204/0x337 do_syscall_64+0xa7/0x295 entry_SYSCALL_64_after_hwframe+0x49/0xbe other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&q->sysfs_lock); lock(kn->count#202); lock(&q->sysfs_lock); lock(kn->count#202); *** DEADLOCK *** 2 locks held by rmmod/777: #0: 00000000e69bd9de (&lock){+.+.}, at: null_exit+0x2e/0x95 [null_blk] #1: 00000000fb16ae21 (&q->sysfs_lock){+.+.}, at: blk_unregister_queue+0x78/0x10b stack backtrace: CPU: 0 PID: 777 Comm: rmmod Not tainted 5.3.0-rc3-00044-g73277fc75ea0 #1380 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS ?-20180724_192412-buildhw-07.phx4 Call Trace: dump_stack+0x9a/0xe6 check_noncircular+0x207/0x251 ? print_circular_bug+0x32a/0x32a ? find_usage_backwards+0x84/0xb0 check_prev_add+0x5d2/0xc45 validate_chain+0xed3/0xf94 ? check_prev_add+0xc45/0xc45 ? mark_lock+0x11b/0x804 ? check_usage_forwards+0x1ca/0x1ca __lock_acquire+0x95f/0xa2f lock_acquire+0x1b4/0x1e8 ? kernfs_remove_by_name_ns+0x59/0x72 __kernfs_remove+0x237/0x40b ? kernfs_remove_by_name_ns+0x59/0x72 ? kernfs_next_descendant_post+0x7d/0x7d ? strlen+0x10/0x23 ? strcmp+0x22/0x44 kernfs_remove_by_name_ns+0x59/0x72 remove_files+0x61/0x96 sysfs_remove_group+0x81/0xa4 sysfs_remove_groups+0x3b/0x44 kobject_del+0x44/0x94 blk_mq_unregister_dev+0x83/0xdd blk_unregister_queue+0xa0/0x10b del_gendisk+0x259/0x3fa ? disk_events_poll_msecs_store+0x12b/0x12b ? check_flags+0x1ea/0x204 ? mark_held_locks+0x1f/0x7a null_del_dev+0x8b/0x1c3 [null_blk] null_exit+0x5c/0x95 [null_blk] __se_sys_delete_module+0x204/0x337 ? free_module+0x39f/0x39f ? blkcg_maybe_throttle_current+0x8a/0x718 ? rwlock_bug+0x62/0x62 ? __blkcg_punt_bio_submit+0xd0/0xd0 ? trace_hardirqs_on_thunk+0x1a/0x20 ? mark_held_locks+0x1f/0x7a ? do_syscall_64+0x4c/0x295 do_syscall_64+0xa7/0x295 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x7fb696cdbe6b Code: 73 01 c3 48 8b 0d 1d 20 0c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 008 RSP: 002b:00007ffec9588788 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 RAX: ffffffffffffffda RBX: 0000559e589137c0 RCX: 00007fb696cdbe6b RDX: 000000000000000a RSI: 0000000000000800 RDI: 0000559e58913828 RBP: 0000000000000000 R08: 00007ffec9587701 R09: 0000000000000000 R10: 00007fb696d4eae0 R11: 0000000000000206 R12: 00007ffec95889b0 R13: 00007ffec95896b3 R14: 0000559e58913260 R15: 0000559e589137c0 Cc: Christoph Hellwig <hch@infradead.org> Cc: Hannes Reinecke <hare@suse.com> Cc: Greg KH <gregkh@linuxfoundation.org> Cc: Mike Snitzer <snitzer@redhat.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Signed-off-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-08-27 11:01:48 +00:00
if (uevent)
kobject_uevent(&e->kobj, KOBJ_ADD);
set_bit(ELEVATOR_FLAG_REGISTERED, &e->flags);
}
return error;
}
void elv_unregister_queue(struct request_queue *q)
{
struct elevator_queue *e = q->elevator;
lockdep_assert_held(&q->sysfs_lock);
if (e && test_and_clear_bit(ELEVATOR_FLAG_REGISTERED, &e->flags)) {
kobject_uevent(&e->kobj, KOBJ_REMOVE);
kobject_del(&e->kobj);
}
}
int elv_register(struct elevator_type *e)
{
blk-mq: release scheduler resource when request completes Chuck reported [1] an IO hang problem on NFS exports that reside on SATA devices and bisected to commit 615939a2ae73 ("blk-mq: defer to the normal submission path for post-flush requests"). We analysed the IO hang problem, found there are two postflush requests waiting for each other. The first postflush request completed the REQ_FSEQ_DATA sequence, so go to the REQ_FSEQ_POSTFLUSH sequence and added in the flush pending list, but failed to blk_kick_flush() because of the second postflush request which is inflight waiting in scheduler queue. The second postflush waiting in scheduler queue can't be dispatched because the first postflush hasn't released scheduler resource even though it has completed by itself. Fix it by releasing scheduler resource when the first postflush request completed, so the second postflush can be dispatched and completed, then make blk_kick_flush() succeed. While at it, remove the check for e->ops.finish_request, as all schedulers set that. Reaffirm this requirement by adding a WARN_ON_ONCE() at scheduler registration time, just like we do for insert_requests and dispatch_request. [1] https://lore.kernel.org/all/7A57C7AE-A51A-4254-888B-FE15CA21F9E9@oracle.com/ Link: https://lore.kernel.org/linux-block/20230819031206.2744005-1-chengming.zhou@linux.dev/ Reported-by: kernel test robot <oliver.sang@intel.com> Closes: https://lore.kernel.org/oe-lkp/202308172100.8ce4b853-oliver.sang@intel.com Fixes: 615939a2ae73 ("blk-mq: defer to the normal submission path for post-flush requests") Reported-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> Tested-by: Chuck Lever <chuck.lever@oracle.com> Link: https://lore.kernel.org/r/20230813152325.3017343-1-chengming.zhou@linux.dev [axboe: folded in incremental fix and added tags] Signed-off-by: Jens Axboe <axboe@kernel.dk>
2023-08-13 15:23:25 +00:00
/* finish request is mandatory */
if (WARN_ON_ONCE(!e->ops.finish_request))
return -EINVAL;
/* insert_requests and dispatch_request are mandatory */
if (WARN_ON_ONCE(!e->ops.insert_requests || !e->ops.dispatch_request))
return -EINVAL;
/* create icq_cache if requested */
if (e->icq_size) {
if (WARN_ON(e->icq_size < sizeof(struct io_cq)) ||
WARN_ON(e->icq_align < __alignof__(struct io_cq)))
return -EINVAL;
snprintf(e->icq_cache_name, sizeof(e->icq_cache_name),
"%s_io_cq", e->elevator_name);
e->icq_cache = kmem_cache_create(e->icq_cache_name, e->icq_size,
e->icq_align, 0, NULL);
if (!e->icq_cache)
return -ENOMEM;
}
/* register, don't allow duplicate names */
spin_lock(&elv_list_lock);
if (__elevator_find(e->elevator_name)) {
spin_unlock(&elv_list_lock);
kmem_cache_destroy(e->icq_cache);
return -EBUSY;
}
list_add_tail(&e->list, &elv_list);
spin_unlock(&elv_list_lock);
printk(KERN_INFO "io scheduler %s registered\n", e->elevator_name);
return 0;
}
EXPORT_SYMBOL_GPL(elv_register);
void elv_unregister(struct elevator_type *e)
{
/* unregister */
spin_lock(&elv_list_lock);
list_del_init(&e->list);
spin_unlock(&elv_list_lock);
/*
* Destroy icq_cache if it exists. icq's are RCU managed. Make
* sure all RCU operations are complete before proceeding.
*/
if (e->icq_cache) {
rcu_barrier();
kmem_cache_destroy(e->icq_cache);
e->icq_cache = NULL;
}
}
EXPORT_SYMBOL_GPL(elv_unregister);
static inline bool elv_support_iosched(struct request_queue *q)
{
if (!queue_is_mq(q) ||
(q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED)))
return false;
return true;
}
/*
* For single queue devices, default to using mq-deadline. If we have multiple
* queues or mq-deadline is not available, default to "none".
*/
static struct elevator_type *elevator_get_default(struct request_queue *q)
{
if (q->tag_set && q->tag_set->flags & BLK_MQ_F_NO_SCHED_BY_DEFAULT)
return NULL;
if (q->nr_hw_queues != 1 &&
!blk_mq_is_shared_tags(q->tag_set->flags))
return NULL;
return elevator_find_get(q, "mq-deadline");
}
/*
* Get the first elevator providing the features required by the request queue.
* Default to "none" if no matching elevator is found.
*/
static struct elevator_type *elevator_get_by_features(struct request_queue *q)
{
struct elevator_type *e, *found = NULL;
spin_lock(&elv_list_lock);
list_for_each_entry(e, &elv_list, list) {
if (elv_support_features(q, e)) {
found = e;
break;
}
}
if (found && !elevator_tryget(found))
found = NULL;
spin_unlock(&elv_list_lock);
return found;
}
/*
* For a device queue that has no required features, use the default elevator
* settings. Otherwise, use the first elevator available matching the required
* features. If no suitable elevator is find or if the chosen elevator
* initialization fails, fall back to the "none" elevator (no elevator).
*/
void elevator_init_mq(struct request_queue *q)
{
struct elevator_type *e;
int err;
if (!elv_support_iosched(q))
return;
WARN_ON_ONCE(blk_queue_registered(q));
if (unlikely(q->elevator))
return;
if (!q->required_elevator_features)
e = elevator_get_default(q);
else
e = elevator_get_by_features(q);
if (!e)
return;
/*
* We are called before adding disk, when there isn't any FS I/O,
* so freezing queue plus canceling dispatch work is enough to
* drain any dispatch activities originated from passthrough
* requests, then no need to quiesce queue which may add long boot
* latency, especially when lots of disks are involved.
*/
block: Delay default elevator initialization When elevator_init_mq() is called from blk_mq_init_allocated_queue(), the only information known about the device is the number of hardware queues as the block device scan by the device driver is not completed yet for most drivers. The device type and elevator required features are not set yet, preventing to correctly select the default elevator most suitable for the device. This currently affects all multi-queue zoned block devices which default to the "none" elevator instead of the required "mq-deadline" elevator. These drives currently include host-managed SMR disks connected to a smartpqi HBA and null_blk block devices with zoned mode enabled. Upcoming NVMe Zoned Namespace devices will also be affected. Fix this by adding the boolean elevator_init argument to blk_mq_init_allocated_queue() to control the execution of elevator_init_mq(). Two cases exist: 1) elevator_init = false is used for calls to blk_mq_init_allocated_queue() within blk_mq_init_queue(). In this case, a call to elevator_init_mq() is added to __device_add_disk(), resulting in the delayed initialization of the queue elevator after the device driver finished probing the device information. This effectively allows elevator_init_mq() access to more information about the device. 2) elevator_init = true preserves the current behavior of initializing the elevator directly from blk_mq_init_allocated_queue(). This case is used for the special request based DM devices where the device gendisk is created before the queue initialization and device information (e.g. queue limits) is already known when the queue initialization is executed. Additionally, to make sure that the elevator initialization is never done while requests are in-flight (there should be none when the device driver calls device_add_disk()), freeze and quiesce the device request queue before calling blk_mq_init_sched() in elevator_init_mq(). Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-09-05 09:51:33 +00:00
blk_mq_freeze_queue(q);
blk_mq_cancel_work_sync(q);
block: Delay default elevator initialization When elevator_init_mq() is called from blk_mq_init_allocated_queue(), the only information known about the device is the number of hardware queues as the block device scan by the device driver is not completed yet for most drivers. The device type and elevator required features are not set yet, preventing to correctly select the default elevator most suitable for the device. This currently affects all multi-queue zoned block devices which default to the "none" elevator instead of the required "mq-deadline" elevator. These drives currently include host-managed SMR disks connected to a smartpqi HBA and null_blk block devices with zoned mode enabled. Upcoming NVMe Zoned Namespace devices will also be affected. Fix this by adding the boolean elevator_init argument to blk_mq_init_allocated_queue() to control the execution of elevator_init_mq(). Two cases exist: 1) elevator_init = false is used for calls to blk_mq_init_allocated_queue() within blk_mq_init_queue(). In this case, a call to elevator_init_mq() is added to __device_add_disk(), resulting in the delayed initialization of the queue elevator after the device driver finished probing the device information. This effectively allows elevator_init_mq() access to more information about the device. 2) elevator_init = true preserves the current behavior of initializing the elevator directly from blk_mq_init_allocated_queue(). This case is used for the special request based DM devices where the device gendisk is created before the queue initialization and device information (e.g. queue limits) is already known when the queue initialization is executed. Additionally, to make sure that the elevator initialization is never done while requests are in-flight (there should be none when the device driver calls device_add_disk()), freeze and quiesce the device request queue before calling blk_mq_init_sched() in elevator_init_mq(). Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-09-05 09:51:33 +00:00
err = blk_mq_init_sched(q, e);
block: Delay default elevator initialization When elevator_init_mq() is called from blk_mq_init_allocated_queue(), the only information known about the device is the number of hardware queues as the block device scan by the device driver is not completed yet for most drivers. The device type and elevator required features are not set yet, preventing to correctly select the default elevator most suitable for the device. This currently affects all multi-queue zoned block devices which default to the "none" elevator instead of the required "mq-deadline" elevator. These drives currently include host-managed SMR disks connected to a smartpqi HBA and null_blk block devices with zoned mode enabled. Upcoming NVMe Zoned Namespace devices will also be affected. Fix this by adding the boolean elevator_init argument to blk_mq_init_allocated_queue() to control the execution of elevator_init_mq(). Two cases exist: 1) elevator_init = false is used for calls to blk_mq_init_allocated_queue() within blk_mq_init_queue(). In this case, a call to elevator_init_mq() is added to __device_add_disk(), resulting in the delayed initialization of the queue elevator after the device driver finished probing the device information. This effectively allows elevator_init_mq() access to more information about the device. 2) elevator_init = true preserves the current behavior of initializing the elevator directly from blk_mq_init_allocated_queue(). This case is used for the special request based DM devices where the device gendisk is created before the queue initialization and device information (e.g. queue limits) is already known when the queue initialization is executed. Additionally, to make sure that the elevator initialization is never done while requests are in-flight (there should be none when the device driver calls device_add_disk()), freeze and quiesce the device request queue before calling blk_mq_init_sched() in elevator_init_mq(). Reviewed-by: Ming Lei <ming.lei@redhat.com> Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2019-09-05 09:51:33 +00:00
blk_mq_unfreeze_queue(q);
if (err) {
pr_warn("\"%s\" elevator initialization failed, "
"falling back to \"none\"\n", e->elevator_name);
}
block: fix up elevator_type refcounting The current reference management logic of io scheduler modules contains refcnt problems. For example, blk_mq_init_sched may fail before or after the calling of e->ops.init_sched. If it fails before the calling, it does nothing to the reference to the io scheduler module. But if it fails after the calling, it releases the reference by calling kobject_put(&eq->kobj). As the callers of blk_mq_init_sched can't know exactly where the failure happens, they can't handle the reference to the io scheduler module properly: releasing the reference on failure results in double-release if blk_mq_init_sched has released it, and not releasing the reference results in ghost reference if blk_mq_init_sched did not release it either. The same problem also exists in io schedulers' init_sched implementations. We can address the problem by adding releasing statements to the error handling procedures of blk_mq_init_sched and init_sched implementations. But that is counterintuitive and requires modifications to existing io schedulers. Instead, We make elevator_alloc get the io scheduler module references that will be released by elevator_release. And then, we match each elevator_get with an elevator_put. Therefore, each reference to an io scheduler module explicitly has its own getter and releaser, and we no longer need to worry about the refcnt problems. The bugs and the patch can be validated with tools here: https://github.com/nickyc975/linux_elv_refcnt_bug.git [hch: split out a few bits into separate patches, use a non-try module_get in elevator_alloc] Signed-off-by: Jinlong Chen <nickyc975@zju.edu.cn> Signed-off-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/20221020064819.1469928-5-hch@lst.de Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-10-20 06:48:19 +00:00
elevator_put(e);
}
/*
* Switch to new_e io scheduler.
*
* If switching fails, we are most likely running out of memory and not able
* to restore the old io scheduler, so leaving the io scheduler being none.
*/
int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
{
int ret;
lockdep_assert_held(&q->sysfs_lock);
blk_mq_freeze_queue(q);
blk_mq_quiesce_queue(q);
if (q->elevator) {
elv_unregister_queue(q);
elevator_exit(q);
}
ret = blk_mq_init_sched(q, new_e);
if (ret)
goto out_unfreeze;
ret = elv_register_queue(q, true);
if (ret) {
elevator_exit(q);
goto out_unfreeze;
}
blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name);
out_unfreeze:
blk_mq_unquiesce_queue(q);
blk_mq_unfreeze_queue(q);
if (ret) {
pr_warn("elv: switch to \"%s\" failed, falling back to \"none\"\n",
new_e->elevator_name);
}
return ret;
}
void elevator_disable(struct request_queue *q)
{
lockdep_assert_held(&q->sysfs_lock);
blk_mq_freeze_queue(q);
blk_mq_quiesce_queue(q);
elv_unregister_queue(q);
elevator_exit(q);
blk_queue_flag_clear(QUEUE_FLAG_SQ_SCHED, q);
q->elevator = NULL;
q->nr_requests = q->tag_set->queue_depth;
blk_add_trace_msg(q, "elv switch: none");
blk_mq_unquiesce_queue(q);
blk_mq_unfreeze_queue(q);
}
/*
* Switch this queue to the given IO scheduler.
*/
static int elevator_change(struct request_queue *q, const char *elevator_name)
{
struct elevator_type *e;
block: fix up elevator_type refcounting The current reference management logic of io scheduler modules contains refcnt problems. For example, blk_mq_init_sched may fail before or after the calling of e->ops.init_sched. If it fails before the calling, it does nothing to the reference to the io scheduler module. But if it fails after the calling, it releases the reference by calling kobject_put(&eq->kobj). As the callers of blk_mq_init_sched can't know exactly where the failure happens, they can't handle the reference to the io scheduler module properly: releasing the reference on failure results in double-release if blk_mq_init_sched has released it, and not releasing the reference results in ghost reference if blk_mq_init_sched did not release it either. The same problem also exists in io schedulers' init_sched implementations. We can address the problem by adding releasing statements to the error handling procedures of blk_mq_init_sched and init_sched implementations. But that is counterintuitive and requires modifications to existing io schedulers. Instead, We make elevator_alloc get the io scheduler module references that will be released by elevator_release. And then, we match each elevator_get with an elevator_put. Therefore, each reference to an io scheduler module explicitly has its own getter and releaser, and we no longer need to worry about the refcnt problems. The bugs and the patch can be validated with tools here: https://github.com/nickyc975/linux_elv_refcnt_bug.git [hch: split out a few bits into separate patches, use a non-try module_get in elevator_alloc] Signed-off-by: Jinlong Chen <nickyc975@zju.edu.cn> Signed-off-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/20221020064819.1469928-5-hch@lst.de Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-10-20 06:48:19 +00:00
int ret;
/* Make sure queue is not in the middle of being removed */
if (!blk_queue_registered(q))
return -ENOENT;
if (!strncmp(elevator_name, "none", 4)) {
if (q->elevator)
elevator_disable(q);
return 0;
}
if (q->elevator && elevator_match(q->elevator->type, elevator_name))
return 0;
e = elevator_find_get(q, elevator_name);
if (!e) {
request_module("%s-iosched", elevator_name);
e = elevator_find_get(q, elevator_name);
if (!e)
return -EINVAL;
}
block: fix up elevator_type refcounting The current reference management logic of io scheduler modules contains refcnt problems. For example, blk_mq_init_sched may fail before or after the calling of e->ops.init_sched. If it fails before the calling, it does nothing to the reference to the io scheduler module. But if it fails after the calling, it releases the reference by calling kobject_put(&eq->kobj). As the callers of blk_mq_init_sched can't know exactly where the failure happens, they can't handle the reference to the io scheduler module properly: releasing the reference on failure results in double-release if blk_mq_init_sched has released it, and not releasing the reference results in ghost reference if blk_mq_init_sched did not release it either. The same problem also exists in io schedulers' init_sched implementations. We can address the problem by adding releasing statements to the error handling procedures of blk_mq_init_sched and init_sched implementations. But that is counterintuitive and requires modifications to existing io schedulers. Instead, We make elevator_alloc get the io scheduler module references that will be released by elevator_release. And then, we match each elevator_get with an elevator_put. Therefore, each reference to an io scheduler module explicitly has its own getter and releaser, and we no longer need to worry about the refcnt problems. The bugs and the patch can be validated with tools here: https://github.com/nickyc975/linux_elv_refcnt_bug.git [hch: split out a few bits into separate patches, use a non-try module_get in elevator_alloc] Signed-off-by: Jinlong Chen <nickyc975@zju.edu.cn> Signed-off-by: Christoph Hellwig <hch@lst.de> Link: https://lore.kernel.org/r/20221020064819.1469928-5-hch@lst.de Signed-off-by: Jens Axboe <axboe@kernel.dk>
2022-10-20 06:48:19 +00:00
ret = elevator_switch(q, e);
elevator_put(e);
return ret;
}
ssize_t elv_iosched_store(struct request_queue *q, const char *buf,
size_t count)
{
char elevator_name[ELV_NAME_MAX];
int ret;
if (!elv_support_iosched(q))
return count;
strscpy(elevator_name, buf, sizeof(elevator_name));
ret = elevator_change(q, strstrip(elevator_name));
if (!ret)
return count;
return ret;
}
ssize_t elv_iosched_show(struct request_queue *q, char *name)
{
struct elevator_queue *eq = q->elevator;
struct elevator_type *cur = NULL, *e;
int len = 0;
if (!elv_support_iosched(q))
return sprintf(name, "none\n");
if (!q->elevator) {
len += sprintf(name+len, "[none] ");
} else {
len += sprintf(name+len, "none ");
cur = eq->type;
}
spin_lock(&elv_list_lock);
list_for_each_entry(e, &elv_list, list) {
if (e == cur)
len += sprintf(name+len, "[%s] ", e->elevator_name);
else if (elv_support_features(q, e))
len += sprintf(name+len, "%s ", e->elevator_name);
}
spin_unlock(&elv_list_lock);
len += sprintf(name+len, "\n");
return len;
}
struct request *elv_rb_former_request(struct request_queue *q,
struct request *rq)
{
struct rb_node *rbprev = rb_prev(&rq->rb_node);
if (rbprev)
return rb_entry_rq(rbprev);
return NULL;
}
EXPORT_SYMBOL(elv_rb_former_request);
struct request *elv_rb_latter_request(struct request_queue *q,
struct request *rq)
{
struct rb_node *rbnext = rb_next(&rq->rb_node);
if (rbnext)
return rb_entry_rq(rbnext);
return NULL;
}
EXPORT_SYMBOL(elv_rb_latter_request);
static int __init elevator_setup(char *str)
{
pr_warn("Kernel parameter elevator= does not have any effect anymore.\n"
"Please use sysfs to set IO scheduler for individual devices.\n");
return 1;
}
__setup("elevator=", elevator_setup);