linux/block/blk-core.c

2907 lines
77 KiB
C
Raw Normal View History

/*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 1994, Karl Keyte: Added support for disk statistics
* Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE
* Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de>
* kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au>
* - July2000
* bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001
*/
/*
* This handles all read/write requests to block devices
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/kernel_stat.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/completion.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/fault-inject.h>
#include <linux/list_sort.h>
#include <linux/delay.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
#define CREATE_TRACE_POINTS
#include <trace/events/block.h>
#include "blk.h"
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap);
EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap);
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
EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete);
DEFINE_IDA(blk_queue_ida);
/*
* For the allocated request tables
*/
static struct kmem_cache *request_cachep;
/*
* For queue allocation
*/
struct kmem_cache *blk_requestq_cachep;
/*
* Controlling structure to kblockd
*/
static struct workqueue_struct *kblockd_workqueue;
static void drive_stat_acct(struct request *rq, int new_io)
{
struct hd_struct *part;
int rw = rq_data_dir(rq);
int cpu;
if (!blk_do_io_stat(rq))
return;
cpu = part_stat_lock();
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 15:57:38 +00:00
if (!new_io) {
part = rq->part;
part_stat_inc(cpu, part, merges[rw]);
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 15:57:38 +00:00
} else {
part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
if (!hd_struct_try_get(part)) {
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 15:57:38 +00:00
/*
* The partition is already being removed,
* the request will be accounted on the disk only
*
* We take a reference on disk->part0 although that
* partition will never be deleted, so we can treat
* it as any other partition.
*/
part = &rq->rq_disk->part0;
hd_struct_get(part);
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 15:57:38 +00:00
}
part_round_stats(cpu, part);
part_inc_in_flight(part, rw);
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 15:57:38 +00:00
rq->part = part;
}
part_stat_unlock();
}
void blk_queue_congestion_threshold(struct request_queue *q)
{
int nr;
nr = q->nr_requests - (q->nr_requests / 8) + 1;
if (nr > q->nr_requests)
nr = q->nr_requests;
q->nr_congestion_on = nr;
nr = q->nr_requests - (q->nr_requests / 8) - (q->nr_requests / 16) - 1;
if (nr < 1)
nr = 1;
q->nr_congestion_off = nr;
}
/**
* blk_get_backing_dev_info - get the address of a queue's backing_dev_info
* @bdev: device
*
* Locates the passed device's request queue and returns the address of its
* backing_dev_info
*
* Will return NULL if the request queue cannot be located.
*/
struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev)
{
struct backing_dev_info *ret = NULL;
struct request_queue *q = bdev_get_queue(bdev);
if (q)
ret = &q->backing_dev_info;
return ret;
}
EXPORT_SYMBOL(blk_get_backing_dev_info);
void blk_rq_init(struct request_queue *q, struct request *rq)
{
memset(rq, 0, sizeof(*rq));
INIT_LIST_HEAD(&rq->queuelist);
INIT_LIST_HEAD(&rq->timeout_list);
rq->cpu = -1;
rq->q = q;
rq->__sector = (sector_t) -1;
INIT_HLIST_NODE(&rq->hash);
RB_CLEAR_NODE(&rq->rb_node);
rq->cmd = rq->__cmd;
rq->cmd_len = BLK_MAX_CDB;
rq->tag = -1;
rq->ref_count = 1;
rq->start_time = jiffies;
set_start_time_ns(rq);
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 15:57:38 +00:00
rq->part = NULL;
}
EXPORT_SYMBOL(blk_rq_init);
static void req_bio_endio(struct request *rq, struct bio *bio,
unsigned int nbytes, int error)
{
if (error)
clear_bit(BIO_UPTODATE, &bio->bi_flags);
else if (!test_bit(BIO_UPTODATE, &bio->bi_flags))
error = -EIO;
if (unlikely(nbytes > bio->bi_size)) {
printk(KERN_ERR "%s: want %u bytes done, %u left\n",
__func__, nbytes, bio->bi_size);
nbytes = bio->bi_size;
}
if (unlikely(rq->cmd_flags & REQ_QUIET))
set_bit(BIO_QUIET, &bio->bi_flags);
block: Supress Buffer I/O errors when SCSI REQ_QUIET flag set Allow the scsi request REQ_QUIET flag to be propagated to the buffer file system layer. The basic ideas is to pass the flag from the scsi request to the bio (block IO) and then to the buffer layer. The buffer layer can then suppress needless printks. This patch declutters the kernel log by removed the 40-50 (per lun) buffer io error messages seen during a boot in my multipath setup . It is a good chance any real errors will be missed in the "noise" it the logs without this patch. During boot I see blocks of messages like " __ratelimit: 211 callbacks suppressed Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242847 Buffer I/O error on device sdm, logical block 1 Buffer I/O error on device sdm, logical block 5242878 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242879 Buffer I/O error on device sdm, logical block 5242872 " in my logs. My disk environment is multipath fiber channel using the SCSI_DH_RDAC code and multipathd. This topology includes an "active" and "ghost" path for each lun. IO's to the "ghost" path will never complete and the SCSI layer, via the scsi device handler rdac code, quick returns the IOs to theses paths and sets the REQ_QUIET scsi flag to suppress the scsi layer messages. I am wanting to extend the QUIET behavior to include the buffer file system layer to deal with these errors as well. I have been running this patch for a while now on several boxes without issue. A few runs of bonnie++ show no noticeable difference in performance in my setup. Thanks for John Stultz for the quiet_error finalization. Submitted-by: Keith Mannthey <kmannth@us.ibm.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-11-25 09:24:35 +00:00
bio->bi_size -= nbytes;
bio->bi_sector += (nbytes >> 9);
if (bio_integrity(bio))
bio_integrity_advance(bio, nbytes);
/* don't actually finish bio if it's part of flush sequence */
if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ))
bio_endio(bio, error);
}
void blk_dump_rq_flags(struct request *rq, char *msg)
{
int bit;
printk(KERN_INFO "%s: dev %s: type=%x, flags=%x\n", msg,
rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->cmd_type,
rq->cmd_flags);
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
printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n",
(unsigned long long)blk_rq_pos(rq),
blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
printk(KERN_INFO " bio %p, biotail %p, buffer %p, len %u\n",
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:41 +00:00
rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
if (rq->cmd_type == REQ_TYPE_BLOCK_PC) {
printk(KERN_INFO " cdb: ");
for (bit = 0; bit < BLK_MAX_CDB; bit++)
printk("%02x ", rq->cmd[bit]);
printk("\n");
}
}
EXPORT_SYMBOL(blk_dump_rq_flags);
static void blk_delay_work(struct work_struct *work)
{
struct request_queue *q;
q = container_of(work, struct request_queue, delay_work.work);
spin_lock_irq(q->queue_lock);
__blk_run_queue(q);
spin_unlock_irq(q->queue_lock);
}
/**
* blk_delay_queue - restart queueing after defined interval
* @q: The &struct request_queue in question
* @msecs: Delay in msecs
*
* Description:
* Sometimes queueing needs to be postponed for a little while, to allow
* resources to come back. This function will make sure that queueing is
* restarted around the specified time.
*/
void blk_delay_queue(struct request_queue *q, unsigned long msecs)
{
queue_delayed_work(kblockd_workqueue, &q->delay_work,
msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_delay_queue);
/**
* blk_start_queue - restart a previously stopped queue
* @q: The &struct request_queue in question
*
* Description:
* blk_start_queue() will clear the stop flag on the queue, and call
* the request_fn for the queue if it was in a stopped state when
* entered. Also see blk_stop_queue(). Queue lock must be held.
**/
void blk_start_queue(struct request_queue *q)
{
WARN_ON(!irqs_disabled());
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
__blk_run_queue(q);
}
EXPORT_SYMBOL(blk_start_queue);
/**
* blk_stop_queue - stop a queue
* @q: The &struct request_queue in question
*
* Description:
* The Linux block layer assumes that a block driver will consume all
* entries on the request queue when the request_fn strategy is called.
* Often this will not happen, because of hardware limitations (queue
* depth settings). If a device driver gets a 'queue full' response,
* or if it simply chooses not to queue more I/O at one point, it can
* call this function to prevent the request_fn from being called until
* the driver has signalled it's ready to go again. This happens by calling
* blk_start_queue() to restart queue operations. Queue lock must be held.
**/
void blk_stop_queue(struct request_queue *q)
{
__cancel_delayed_work(&q->delay_work);
queue_flag_set(QUEUE_FLAG_STOPPED, q);
}
EXPORT_SYMBOL(blk_stop_queue);
/**
* blk_sync_queue - cancel any pending callbacks on a queue
* @q: the queue
*
* Description:
* The block layer may perform asynchronous callback activity
* on a queue, such as calling the unplug function after a timeout.
* A block device may call blk_sync_queue to ensure that any
* such activity is cancelled, thus allowing it to release resources
* that the callbacks might use. The caller must already have made sure
* that its ->make_request_fn will not re-add plugging prior to calling
* this function.
*
block: Move blk_throtl_exit() call to blk_cleanup_queue() Move blk_throtl_exit() in blk_cleanup_queue() as blk_throtl_exit() is written in such a way that it needs queue lock. In blk_release_queue() there is no gurantee that ->queue_lock is still around. Initially blk_throtl_exit() was in blk_cleanup_queue() but Ingo reported one problem. https://lkml.org/lkml/2010/10/23/86 And a quick fix moved blk_throtl_exit() to blk_release_queue(). commit 7ad58c028652753814054f4e3ac58f925e7343f4 Author: Jens Axboe <jaxboe@fusionio.com> Date: Sat Oct 23 20:40:26 2010 +0200 block: fix use-after-free bug in blk throttle code This patch reverts above change and does not try to shutdown the throtl work in blk_sync_queue(). By avoiding call to throtl_shutdown_timer_wq() from blk_sync_queue(), we should also avoid the problem reported by Ingo. blk_sync_queue() seems to be used only by md driver and it seems to be using it to make sure q->unplug_fn is not called as md registers its own unplug functions and it is about to free up the data structures used by unplug_fn(). Block throttle does not call back into unplug_fn() or into md. So there is no need to cancel blk throttle work. In fact I think cancelling block throttle work is bad because it might happen that some bios are throttled and scheduled to be dispatched later with the help of pending work and if work is cancelled, these bios might never be dispatched. Block layer also uses blk_sync_queue() during blk_cleanup_queue() and blk_release_queue() time. That should be safe as we are also calling blk_throtl_exit() which should make sure all the throttling related data structures are cleaned up. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-03 00:05:33 +00:00
* This function does not cancel any asynchronous activity arising
* out of elevator or throttling code. That would require elevaotor_exit()
* and blk_throtl_exit() to be called with queue lock initialized.
*
*/
void blk_sync_queue(struct request_queue *q)
{
del_timer_sync(&q->timeout);
cancel_delayed_work_sync(&q->delay_work);
}
EXPORT_SYMBOL(blk_sync_queue);
/**
* __blk_run_queue - run a single device queue
* @q: The queue to run
*
* Description:
* See @blk_run_queue. This variant must be called with the queue lock
* held and interrupts disabled.
*/
void __blk_run_queue(struct request_queue *q)
{
if (unlikely(blk_queue_stopped(q)))
return;
q->request_fn(q);
}
EXPORT_SYMBOL(__blk_run_queue);
/**
* blk_run_queue_async - run a single device queue in workqueue context
* @q: The queue to run
*
* Description:
* Tells kblockd to perform the equivalent of @blk_run_queue on behalf
* of us.
*/
void blk_run_queue_async(struct request_queue *q)
{
if (likely(!blk_queue_stopped(q))) {
__cancel_delayed_work(&q->delay_work);
queue_delayed_work(kblockd_workqueue, &q->delay_work, 0);
}
}
EXPORT_SYMBOL(blk_run_queue_async);
/**
* blk_run_queue - run a single device queue
* @q: The queue to run
*
* Description:
* Invoke request handling on this queue, if it has pending work to do.
* May be used to restart queueing when a request has completed.
*/
void blk_run_queue(struct request_queue *q)
{
unsigned long flags;
spin_lock_irqsave(q->queue_lock, flags);
__blk_run_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_run_queue);
void blk_put_queue(struct request_queue *q)
{
kobject_put(&q->kobj);
}
EXPORT_SYMBOL(blk_put_queue);
/**
* blk_drain_queue - drain requests from request_queue
* @q: queue to drain
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
* @drain_all: whether to drain all requests or only the ones w/ ELVPRIV
*
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
* Drain requests from @q. If @drain_all is set, all requests are drained.
* If not, only ELVPRIV requests are drained. The caller is responsible
* for ensuring that no new requests which need to be drained are queued.
*/
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
void blk_drain_queue(struct request_queue *q, bool drain_all)
{
while (true) {
bool drain = false;
int i;
spin_lock_irq(q->queue_lock);
elv_drain_elevator(q);
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
if (drain_all)
blk_throtl_drain(q);
block: don't kick empty queue in blk_drain_queue() While probing, fd sets up queue, probes hardware and tears down the queue if probing fails. In the process, blk_drain_queue() kicks the queue which failed to finish initialization and fd is unhappy about that. floppy0: no floppy controllers found ------------[ cut here ]------------ WARNING: at drivers/block/floppy.c:2929 do_fd_request+0xbf/0xd0() Hardware name: To Be Filled By O.E.M. VFS: do_fd_request called on non-open device Modules linked in: Pid: 1, comm: swapper Not tainted 3.2.0-rc4-00077-g5983fe2 #2 Call Trace: [<ffffffff81039a6a>] warn_slowpath_common+0x7a/0xb0 [<ffffffff81039b41>] warn_slowpath_fmt+0x41/0x50 [<ffffffff813d657f>] do_fd_request+0xbf/0xd0 [<ffffffff81322b95>] blk_drain_queue+0x65/0x80 [<ffffffff81322c93>] blk_cleanup_queue+0xe3/0x1a0 [<ffffffff818a809d>] floppy_init+0xdeb/0xe28 [<ffffffff818a72b2>] ? daring+0x6b/0x6b [<ffffffff810002af>] do_one_initcall+0x3f/0x170 [<ffffffff81884b34>] kernel_init+0x9d/0x11e [<ffffffff810317c2>] ? schedule_tail+0x22/0xa0 [<ffffffff815dbb14>] kernel_thread_helper+0x4/0x10 [<ffffffff81884a97>] ? start_kernel+0x2be/0x2be [<ffffffff815dbb10>] ? gs_change+0xb/0xb Avoid it by making blk_drain_queue() kick queue iff dispatch queue has something on it. Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Ralf Hildebrandt <Ralf.Hildebrandt@charite.de> Reported-by: Wu Fengguang <fengguang.wu@intel.com> Tested-by: Sergei Trofimovich <slyich@gmail.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-15 19:03:04 +00:00
/*
* This function might be called on a queue which failed
* driver init after queue creation. Some drivers
* (e.g. fd) get unhappy in such cases. Kick queue iff
* dispatch queue has something on it.
*/
if (!list_empty(&q->queue_head))
__blk_run_queue(q);
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
drain |= q->rq.elvpriv;
/*
* Unfortunately, requests are queued at and tracked from
* multiple places and there's no single counter which can
* be drained. Check all the queues and counters.
*/
if (drain_all) {
drain |= !list_empty(&q->queue_head);
for (i = 0; i < 2; i++) {
drain |= q->rq.count[i];
drain |= q->in_flight[i];
drain |= !list_empty(&q->flush_queue[i]);
}
}
spin_unlock_irq(q->queue_lock);
if (!drain)
break;
msleep(10);
}
}
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
/**
* blk_cleanup_queue - shutdown a request queue
* @q: request queue to shutdown
*
* Mark @q DEAD, drain all pending requests, destroy and put it. All
* future requests will be failed immediately with -ENODEV.
block: Initialize ->queue_lock to internal lock at queue allocation time There does not seem to be a clear convention whether q->queue_lock is initialized or not when blk_cleanup_queue() is called. In the past it was not necessary but now blk_throtl_exit() takes up queue lock by default and needs queue lock to be available. In fact elevator_exit() code also has similar requirement just that it is less stringent in the sense that elevator_exit() is called only if elevator is initialized. Two problems have been noticed because of ambiguity about spin lock status. - If a driver calls blk_alloc_queue() and then soon calls blk_cleanup_queue() almost immediately, (because some other driver structure allocation failed or some other error happened) then blk_throtl_exit() will run into issues as queue lock is not initialized. Loop driver ran into this issue recently and I noticed error paths in md driver too. Similar error paths should exist in other drivers too. - If some driver provided external spin lock and zapped the lock before blk_cleanup_queue(), then it can lead to issues. So this patch initializes the default queue lock at queue allocation time. block throttling code is one of the users of queue lock and it is initialized at the queue allocation time, so it makes sense to initialize ->queue_lock also to internal lock. A driver can overide that lock later. This will take care of the issue where a driver does not have to worry about initializing the queue lock to default before calling blk_cleanup_queue() Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-03 00:04:42 +00:00
*/
void blk_cleanup_queue(struct request_queue *q)
{
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
spinlock_t *lock = q->queue_lock;
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
/* mark @q DEAD, no new request or merges will be allowed afterwards */
mutex_lock(&q->sysfs_lock);
queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
spin_lock_irq(lock);
queue_flag_set(QUEUE_FLAG_NOMERGES, q);
queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
queue_flag_set(QUEUE_FLAG_DEAD, q);
if (q->queue_lock != &q->__queue_lock)
q->queue_lock = &q->__queue_lock;
block: Move blk_throtl_exit() call to blk_cleanup_queue() Move blk_throtl_exit() in blk_cleanup_queue() as blk_throtl_exit() is written in such a way that it needs queue lock. In blk_release_queue() there is no gurantee that ->queue_lock is still around. Initially blk_throtl_exit() was in blk_cleanup_queue() but Ingo reported one problem. https://lkml.org/lkml/2010/10/23/86 And a quick fix moved blk_throtl_exit() to blk_release_queue(). commit 7ad58c028652753814054f4e3ac58f925e7343f4 Author: Jens Axboe <jaxboe@fusionio.com> Date: Sat Oct 23 20:40:26 2010 +0200 block: fix use-after-free bug in blk throttle code This patch reverts above change and does not try to shutdown the throtl work in blk_sync_queue(). By avoiding call to throtl_shutdown_timer_wq() from blk_sync_queue(), we should also avoid the problem reported by Ingo. blk_sync_queue() seems to be used only by md driver and it seems to be using it to make sure q->unplug_fn is not called as md registers its own unplug functions and it is about to free up the data structures used by unplug_fn(). Block throttle does not call back into unplug_fn() or into md. So there is no need to cancel blk throttle work. In fact I think cancelling block throttle work is bad because it might happen that some bios are throttled and scheduled to be dispatched later with the help of pending work and if work is cancelled, these bios might never be dispatched. Block layer also uses blk_sync_queue() during blk_cleanup_queue() and blk_release_queue() time. That should be safe as we are also calling blk_throtl_exit() which should make sure all the throttling related data structures are cleaned up. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-03 00:05:33 +00:00
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
spin_unlock_irq(lock);
mutex_unlock(&q->sysfs_lock);
/*
* Drain all requests queued before DEAD marking. The caller might
* be trying to tear down @q before its elevator is initialized, in
* which case we don't want to call into draining.
*/
if (q->elevator)
blk_drain_queue(q, true);
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown request_queue is refcounted but actually depdends on lifetime management from the queue owner - on blk_cleanup_queue(), block layer expects that there's no request passing through request_queue and no new one will. This is fundamentally broken. The queue owner (e.g. SCSI layer) doesn't have a way to know whether there are other active users before calling blk_cleanup_queue() and other users (e.g. bsg) don't have any guarantee that the queue is and would stay valid while it's holding a reference. With delay added in blk_queue_bio() before queue_lock is grabbed, the following oops can be easily triggered when a device is removed with in-flight IOs. sd 0:0:1:0: [sdb] Stopping disk ata1.01: disabled general protection fault: 0000 [#1] PREEMPT SMP CPU 2 Modules linked in: Pid: 648, comm: test_rawio Not tainted 3.1.0-rc3-work+ #56 Bochs Bochs RIP: 0010:[<ffffffff8137d651>] [<ffffffff8137d651>] elv_rqhash_find+0x61/0x100 ... Process test_rawio (pid: 648, threadinfo ffff880019efa000, task ffff880019ef8a80) ... Call Trace: [<ffffffff8137d774>] elv_merge+0x84/0xe0 [<ffffffff81385b54>] blk_queue_bio+0xf4/0x400 [<ffffffff813838ea>] generic_make_request+0xca/0x100 [<ffffffff81383994>] submit_bio+0x74/0x100 [<ffffffff811c53ec>] dio_bio_submit+0xbc/0xc0 [<ffffffff811c610e>] __blockdev_direct_IO+0x92e/0xb40 [<ffffffff811c39f7>] blkdev_direct_IO+0x57/0x60 [<ffffffff8113b1c5>] generic_file_aio_read+0x6d5/0x760 [<ffffffff8118c1ca>] do_sync_read+0xda/0x120 [<ffffffff8118ce55>] vfs_read+0xc5/0x180 [<ffffffff8118cfaa>] sys_pread64+0x9a/0xb0 [<ffffffff81afaf6b>] system_call_fastpath+0x16/0x1b This happens because blk_queue_cleanup() destroys the queue and elevator whether IOs are in progress or not and DEAD tests are sprinkled in the request processing path without proper synchronization. Similar problem exists for blk-throtl. On queue cleanup, blk-throtl is shutdown whether it has requests in it or not. Depending on timing, it either oopses or throttled bios are lost putting tasks which are waiting for bio completion into eternal D state. The way it should work is having the usual clear distinction between shutdown and release. Shutdown drains all currently pending requests, marks the queue dead, and performs partial teardown of the now unnecessary part of the queue. Even after shutdown is complete, reference holders are still allowed to issue requests to the queue although they will be immmediately failed. The rest of teardown happens on release. This patch makes the following changes to make blk_queue_cleanup() behave as proper shutdown. * QUEUE_FLAG_DEAD is now set while holding both q->exit_mutex and queue_lock. * Unsynchronized DEAD check in generic_make_request_checks() removed. This couldn't make any meaningful difference as the queue could die after the check. * blk_drain_queue() updated such that it can drain all requests and is now called during cleanup. * blk_throtl updated such that it checks DEAD on grabbing queue_lock, drains all throttled bios during cleanup and free td when queue is released. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-10-19 12:42:16 +00:00
/* @q won't process any more request, flush async actions */
del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer);
blk_sync_queue(q);
/* @q is and will stay empty, shutdown and put */
blk_put_queue(q);
}
EXPORT_SYMBOL(blk_cleanup_queue);
static int blk_init_free_list(struct request_queue *q)
{
struct request_list *rl = &q->rq;
if (unlikely(rl->rq_pool))
return 0;
rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0;
rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0;
rl->elvpriv = 0;
init_waitqueue_head(&rl->wait[BLK_RW_SYNC]);
init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]);
rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, mempool_alloc_slab,
mempool_free_slab, request_cachep, q->node);
if (!rl->rq_pool)
return -ENOMEM;
return 0;
}
struct request_queue *blk_alloc_queue(gfp_t gfp_mask)
{
return blk_alloc_queue_node(gfp_mask, -1);
}
EXPORT_SYMBOL(blk_alloc_queue);
struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
{
struct request_queue *q;
int err;
q = kmem_cache_alloc_node(blk_requestq_cachep,
gfp_mask | __GFP_ZERO, node_id);
if (!q)
return NULL;
q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL);
if (q->id < 0)
goto fail_q;
q->backing_dev_info.ra_pages =
(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
q->backing_dev_info.state = 0;
q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY;
q->backing_dev_info.name = "block";
q->node = node_id;
err = bdi_init(&q->backing_dev_info);
if (err)
goto fail_id;
if (blk_throtl_init(q))
goto fail_id;
setup_timer(&q->backing_dev_info.laptop_mode_wb_timer,
laptop_mode_timer_fn, (unsigned long) q);
setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);
INIT_LIST_HEAD(&q->timeout_list);
INIT_LIST_HEAD(&q->icq_list);
block: reimplement FLUSH/FUA to support merge The current FLUSH/FUA support has evolved from the implementation which had to perform queue draining. As such, sequencing is done queue-wide one flush request after another. However, with the draining requirement gone, there's no reason to keep the queue-wide sequential approach. This patch reimplements FLUSH/FUA support such that each FLUSH/FUA request is sequenced individually. The actual FLUSH execution is double buffered and whenever a request wants to execute one for either PRE or POSTFLUSH, it queues on the pending queue. Once certain conditions are met, a flush request is issued and on its completion all pending requests proceed to the next sequence. This allows arbitrary merging of different type of flushes. How they are merged can be primarily controlled and tuned by adjusting the above said 'conditions' used to determine when to issue the next flush. This is inspired by Darrick's patches to merge multiple zero-data flushes which helps workloads with highly concurrent fsync requests. * As flush requests are never put on the IO scheduler, request fields used for flush share space with rq->rb_node. rq->completion_data is moved out of the union. This increases the request size by one pointer. As rq->elevator_private* are used only by the iosched too, it is possible to reduce the request size further. However, to do that, we need to modify request allocation path such that iosched data is not allocated for flush requests. * FLUSH/FUA processing happens on insertion now instead of dispatch. - Comments updated as per Vivek and Mike. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: "Darrick J. Wong" <djwong@us.ibm.com> Cc: Shaohua Li <shli@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-25 11:43:54 +00:00
INIT_LIST_HEAD(&q->flush_queue[0]);
INIT_LIST_HEAD(&q->flush_queue[1]);
INIT_LIST_HEAD(&q->flush_data_in_flight);
INIT_DELAYED_WORK(&q->delay_work, blk_delay_work);
kobject_init(&q->kobj, &blk_queue_ktype);
mutex_init(&q->sysfs_lock);
spin_lock_init(&q->__queue_lock);
block: Initialize ->queue_lock to internal lock at queue allocation time There does not seem to be a clear convention whether q->queue_lock is initialized or not when blk_cleanup_queue() is called. In the past it was not necessary but now blk_throtl_exit() takes up queue lock by default and needs queue lock to be available. In fact elevator_exit() code also has similar requirement just that it is less stringent in the sense that elevator_exit() is called only if elevator is initialized. Two problems have been noticed because of ambiguity about spin lock status. - If a driver calls blk_alloc_queue() and then soon calls blk_cleanup_queue() almost immediately, (because some other driver structure allocation failed or some other error happened) then blk_throtl_exit() will run into issues as queue lock is not initialized. Loop driver ran into this issue recently and I noticed error paths in md driver too. Similar error paths should exist in other drivers too. - If some driver provided external spin lock and zapped the lock before blk_cleanup_queue(), then it can lead to issues. So this patch initializes the default queue lock at queue allocation time. block throttling code is one of the users of queue lock and it is initialized at the queue allocation time, so it makes sense to initialize ->queue_lock also to internal lock. A driver can overide that lock later. This will take care of the issue where a driver does not have to worry about initializing the queue lock to default before calling blk_cleanup_queue() Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-03 00:04:42 +00:00
/*
* By default initialize queue_lock to internal lock and driver can
* override it later if need be.
*/
q->queue_lock = &q->__queue_lock;
return q;
fail_id:
ida_simple_remove(&blk_queue_ida, q->id);
fail_q:
kmem_cache_free(blk_requestq_cachep, q);
return NULL;
}
EXPORT_SYMBOL(blk_alloc_queue_node);
/**
* blk_init_queue - prepare a request queue for use with a block device
* @rfn: The function to be called to process requests that have been
* placed on the queue.
* @lock: Request queue spin lock
*
* Description:
* If a block device wishes to use the standard request handling procedures,
* which sorts requests and coalesces adjacent requests, then it must
* call blk_init_queue(). The function @rfn will be called when there
* are requests on the queue that need to be processed. If the device
* supports plugging, then @rfn may not be called immediately when requests
* are available on the queue, but may be called at some time later instead.
* Plugged queues are generally unplugged when a buffer belonging to one
* of the requests on the queue is needed, or due to memory pressure.
*
* @rfn is not required, or even expected, to remove all requests off the
* queue, but only as many as it can handle at a time. If it does leave
* requests on the queue, it is responsible for arranging that the requests
* get dealt with eventually.
*
* The queue spin lock must be held while manipulating the requests on the
* request queue; this lock will be taken also from interrupt context, so irq
* disabling is needed for it.
*
* Function returns a pointer to the initialized request queue, or %NULL if
* it didn't succeed.
*
* Note:
* blk_init_queue() must be paired with a blk_cleanup_queue() call
* when the block device is deactivated (such as at module unload).
**/
struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock)
{
return blk_init_queue_node(rfn, lock, -1);
}
EXPORT_SYMBOL(blk_init_queue);
struct request_queue *
blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
{
struct request_queue *uninit_q, *q;
uninit_q = blk_alloc_queue_node(GFP_KERNEL, node_id);
if (!uninit_q)
return NULL;
q = blk_init_allocated_queue(uninit_q, rfn, lock);
if (!q)
blk_cleanup_queue(uninit_q);
return q;
}
EXPORT_SYMBOL(blk_init_queue_node);
struct request_queue *
blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn,
spinlock_t *lock)
{
if (!q)
return NULL;
if (blk_init_free_list(q))
return NULL;
q->request_fn = rfn;
q->prep_rq_fn = NULL;
q->unprep_rq_fn = NULL;
q->queue_flags = QUEUE_FLAG_DEFAULT;
block: Initialize ->queue_lock to internal lock at queue allocation time There does not seem to be a clear convention whether q->queue_lock is initialized or not when blk_cleanup_queue() is called. In the past it was not necessary but now blk_throtl_exit() takes up queue lock by default and needs queue lock to be available. In fact elevator_exit() code also has similar requirement just that it is less stringent in the sense that elevator_exit() is called only if elevator is initialized. Two problems have been noticed because of ambiguity about spin lock status. - If a driver calls blk_alloc_queue() and then soon calls blk_cleanup_queue() almost immediately, (because some other driver structure allocation failed or some other error happened) then blk_throtl_exit() will run into issues as queue lock is not initialized. Loop driver ran into this issue recently and I noticed error paths in md driver too. Similar error paths should exist in other drivers too. - If some driver provided external spin lock and zapped the lock before blk_cleanup_queue(), then it can lead to issues. So this patch initializes the default queue lock at queue allocation time. block throttling code is one of the users of queue lock and it is initialized at the queue allocation time, so it makes sense to initialize ->queue_lock also to internal lock. A driver can overide that lock later. This will take care of the issue where a driver does not have to worry about initializing the queue lock to default before calling blk_cleanup_queue() Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-03-03 00:04:42 +00:00
/* Override internal queue lock with supplied lock pointer */
if (lock)
q->queue_lock = lock;
/*
* This also sets hw/phys segments, boundary and size
*/
blk_queue_make_request(q, blk_queue_bio);
q->sg_reserved_size = INT_MAX;
/*
* all done
*/
if (!elevator_init(q, NULL)) {
blk_queue_congestion_threshold(q);
return q;
}
return NULL;
}
EXPORT_SYMBOL(blk_init_allocated_queue);
bool blk_get_queue(struct request_queue *q)
{
if (likely(!blk_queue_dead(q))) {
__blk_get_queue(q);
return true;
}
return false;
}
EXPORT_SYMBOL(blk_get_queue);
static inline void blk_free_request(struct request_queue *q, struct request *rq)
{
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
if (rq->cmd_flags & REQ_ELVPRIV) {
elv_put_request(q, rq);
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
if (rq->elv.icq)
put_io_context(rq->elv.icq->ioc, q);
}
mempool_free(rq, q->rq.rq_pool);
}
static struct request *
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
blk_alloc_request(struct request_queue *q, struct io_cq *icq,
unsigned int flags, gfp_t gfp_mask)
{
struct request *rq = mempool_alloc(q->rq.rq_pool, gfp_mask);
if (!rq)
return NULL;
blk_rq_init(q, rq);
rq->cmd_flags = flags | REQ_ALLOCED;
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
if (flags & REQ_ELVPRIV) {
rq->elv.icq = icq;
if (unlikely(elv_set_request(q, rq, gfp_mask))) {
mempool_free(rq, q->rq.rq_pool);
return NULL;
}
/* @rq->elv.icq holds on to io_context until @rq is freed */
if (icq)
get_io_context(icq->ioc);
}
return rq;
}
/*
* ioc_batching returns true if the ioc is a valid batching request and
* should be given priority access to a request.
*/
static inline int ioc_batching(struct request_queue *q, struct io_context *ioc)
{
if (!ioc)
return 0;
/*
* Make sure the process is able to allocate at least 1 request
* even if the batch times out, otherwise we could theoretically
* lose wakeups.
*/
return ioc->nr_batch_requests == q->nr_batching ||
(ioc->nr_batch_requests > 0
&& time_before(jiffies, ioc->last_waited + BLK_BATCH_TIME));
}
/*
* ioc_set_batching sets ioc to be a new "batcher" if it is not one. This
* will cause the process to be a "batcher" on all queues in the system. This
* is the behaviour we want though - once it gets a wakeup it should be given
* a nice run.
*/
static void ioc_set_batching(struct request_queue *q, struct io_context *ioc)
{
if (!ioc || ioc_batching(q, ioc))
return;
ioc->nr_batch_requests = q->nr_batching;
ioc->last_waited = jiffies;
}
static void __freed_request(struct request_queue *q, int sync)
{
struct request_list *rl = &q->rq;
if (rl->count[sync] < queue_congestion_off_threshold(q))
blk_clear_queue_congested(q, sync);
if (rl->count[sync] + 1 <= q->nr_requests) {
if (waitqueue_active(&rl->wait[sync]))
wake_up(&rl->wait[sync]);
blk_clear_queue_full(q, sync);
}
}
/*
* A request has just been released. Account for it, update the full and
* congestion status, wake up any waiters. Called under q->queue_lock.
*/
static void freed_request(struct request_queue *q, unsigned int flags)
{
struct request_list *rl = &q->rq;
int sync = rw_is_sync(flags);
rl->count[sync]--;
if (flags & REQ_ELVPRIV)
rl->elvpriv--;
__freed_request(q, sync);
if (unlikely(rl->starved[sync ^ 1]))
__freed_request(q, sync ^ 1);
}
/*
* Determine if elevator data should be initialized when allocating the
* request associated with @bio.
*/
static bool blk_rq_should_init_elevator(struct bio *bio)
{
if (!bio)
return true;
/*
* Flush requests do not use the elevator so skip initialization.
* This allows a request to share the flush and elevator data.
*/
if (bio->bi_rw & (REQ_FLUSH | REQ_FUA))
return false;
return true;
}
/**
* get_request - get a free request
* @q: request_queue to allocate request from
* @rw_flags: RW and SYNC flags
* @bio: bio to allocate request for (can be %NULL)
* @gfp_mask: allocation mask
*
* Get a free request from @q. This function may fail under memory
* pressure or if @q is dead.
*
* Must be callled with @q->queue_lock held and,
* Returns %NULL on failure, with @q->queue_lock held.
* Returns !%NULL on success, with @q->queue_lock *not held*.
*/
static struct request *get_request(struct request_queue *q, int rw_flags,
struct bio *bio, gfp_t gfp_mask)
{
struct request *rq = NULL;
struct request_list *rl = &q->rq;
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
struct elevator_type *et;
struct io_context *ioc;
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
struct io_cq *icq = NULL;
const bool is_sync = rw_is_sync(rw_flags) != 0;
bool retried = false;
int may_queue;
retry:
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
et = q->elevator->type;
ioc = current->io_context;
if (unlikely(blk_queue_dead(q)))
return NULL;
may_queue = elv_may_queue(q, rw_flags);
if (may_queue == ELV_MQUEUE_NO)
goto rq_starved;
if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) {
if (rl->count[is_sync]+1 >= q->nr_requests) {
/*
* We want ioc to record batching state. If it's
* not already there, creating a new one requires
* dropping queue_lock, which in turn requires
* retesting conditions to avoid queue hang.
*/
if (!ioc && !retried) {
spin_unlock_irq(q->queue_lock);
create_io_context(current, gfp_mask, q->node);
spin_lock_irq(q->queue_lock);
retried = true;
goto retry;
}
/*
* The queue will fill after this allocation, so set
* it as full, and mark this process as "batching".
* This process will be allowed to complete a batch of
* requests, others will be blocked.
*/
if (!blk_queue_full(q, is_sync)) {
ioc_set_batching(q, ioc);
blk_set_queue_full(q, is_sync);
} else {
if (may_queue != ELV_MQUEUE_MUST
&& !ioc_batching(q, ioc)) {
/*
* The queue is full and the allocating
* process is not a "batcher", and not
* exempted by the IO scheduler
*/
goto out;
}
}
}
blk_set_queue_congested(q, is_sync);
}
/*
* Only allow batching queuers to allocate up to 50% over the defined
* limit of requests, otherwise we could have thousands of requests
* allocated with any setting of ->nr_requests
*/
if (rl->count[is_sync] >= (3 * q->nr_requests / 2))
goto out;
rl->count[is_sync]++;
rl->starved[is_sync] = 0;
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
/*
* Decide whether the new request will be managed by elevator. If
* so, mark @rw_flags and increment elvpriv. Non-zero elvpriv will
* prevent the current elevator from being destroyed until the new
* request is freed. This guarantees icq's won't be destroyed and
* makes creating new ones safe.
*
* Also, lookup icq while holding queue_lock. If it doesn't exist,
* it will be created after releasing queue_lock.
*/
if (blk_rq_should_init_elevator(bio) &&
!test_bit(QUEUE_FLAG_ELVSWITCH, &q->queue_flags)) {
rw_flags |= REQ_ELVPRIV;
rl->elvpriv++;
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
if (et->icq_cache && ioc)
icq = ioc_lookup_icq(ioc, q);
}
if (blk_queue_io_stat(q))
rw_flags |= REQ_IO_STAT;
spin_unlock_irq(q->queue_lock);
block, cfq: move icq creation and rq->elv.icq association to block core Now block layer knows everything necessary to create and associate icq's with requests. Move ioc_create_icq() to blk-ioc.c and update get_request() such that, if elevator_type->icq_size is set, requests are automatically associated with their matching icq's before elv_set_request(). io_context reference is also managed by block core on request alloc/free. * Only ioprio/cgroup changed handling remains from cfq_get_cic(). Collapsed into cfq_set_request(). * This removes queue kicking on icq allocation failure (for now). As icq allocation failure is rare and the only effect of queue kicking achieved was possibily accelerating queue processing, this change shouldn't be noticeable. There is a larger underlying problem. Unlike request allocation, icq allocation is not guaranteed to succeed eventually after retries. The number of icq is unbound and thus mempool can't be the solution either. This effectively adds allocation dependency on memory free path and thus possibility of deadlock. This usually wouldn't happen because icq allocation is not a hot path and, even when the condition triggers, it's highly unlikely that none of the writeback workers already has icq. However, this is still possible especially if elevator is being switched under high memory pressure, so we better get it fixed. Probably the only solution is just bypassing elevator and appending to dispatch queue on any elevator allocation failure. * Comment added to explain how icq's are managed and synchronized. This completes cleanup of io_context interface. Signed-off-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2011-12-13 23:33:42 +00:00
/* create icq if missing */
if (unlikely(et->icq_cache && !icq))
icq = ioc_create_icq(q, gfp_mask);
/* rqs are guaranteed to have icq on elv_set_request() if requested */
if (likely(!et->icq_cache || icq))
rq = blk_alloc_request(q, icq, rw_flags, gfp_mask);
if (unlikely(!rq)) {
/*
* Allocation failed presumably due to memory. Undo anything
* we might have messed up.
*
* Allocating task should really be put onto the front of the
* wait queue, but this is pretty rare.
*/
spin_lock_irq(q->queue_lock);
freed_request(q, rw_flags);
/*
* in the very unlikely event that allocation failed and no
* requests for this direction was pending, mark us starved
* so that freeing of a request in the other direction will
* notice us. another possible fix would be to split the
* rq mempool into READ and WRITE
*/
rq_starved:
if (unlikely(rl->count[is_sync] == 0))
rl->starved[is_sync] = 1;
goto out;
}
/*
* ioc may be NULL here, and ioc_batching will be false. That's
* OK, if the queue is under the request limit then requests need
* not count toward the nr_batch_requests limit. There will always
* be some limit enforced by BLK_BATCH_TIME.
*/
if (ioc_batching(q, ioc))
ioc->nr_batch_requests--;
trace_block_getrq(q, bio, rw_flags & 1);
out:
return rq;
}
/**
* get_request_wait - get a free request with retry
* @q: request_queue to allocate request from
* @rw_flags: RW and SYNC flags
* @bio: bio to allocate request for (can be %NULL)
*
* Get a free request from @q. This function keeps retrying under memory
* pressure and fails iff @q is dead.
*
* Must be callled with @q->queue_lock held and,
* Returns %NULL on failure, with @q->queue_lock held.
* Returns !%NULL on success, with @q->queue_lock *not held*.
*/
static struct request *get_request_wait(struct request_queue *q, int rw_flags,
struct bio *bio)
{
const bool is_sync = rw_is_sync(rw_flags) != 0;
struct request *rq;
rq = get_request(q, rw_flags, bio, GFP_NOIO);
while (!rq) {
DEFINE_WAIT(wait);
struct request_list *rl = &q->rq;
if (unlikely(blk_queue_dead(q)))
return NULL;
prepare_to_wait_exclusive(&rl->wait[is_sync], &wait,
TASK_UNINTERRUPTIBLE);
trace_block_sleeprq(q, bio, rw_flags & 1);
spin_unlock_irq(q->queue_lock);
io_schedule();
/*
* After sleeping, we become a "batching" process and
* will be able to allocate at least one request, and
* up to a big batch of them for a small period time.
* See ioc_batching, ioc_set_batching
*/
create_io_context(current, GFP_NOIO, q->node);
ioc_set_batching(q, current->io_context);
spin_lock_irq(q->queue_lock);
finish_wait(&rl->wait[is_sync], &wait);
rq = get_request(q, rw_flags, bio, GFP_NOIO);
};
return rq;
}
struct request *blk_get_request(struct request_queue *q, int rw, gfp_t gfp_mask)
{
struct request *rq;
BUG_ON(rw != READ && rw != WRITE);
spin_lock_irq(q->queue_lock);
if (gfp_mask & __GFP_WAIT)
rq = get_request_wait(q, rw, NULL);
else
rq = get_request(q, rw, NULL, gfp_mask);
if (!rq)
spin_unlock_irq(q->queue_lock);
/* q->queue_lock is unlocked at this point */
return rq;
}
EXPORT_SYMBOL(blk_get_request);
/**
* blk_make_request - given a bio, allocate a corresponding struct request.
* @q: target request queue
* @bio: The bio describing the memory mappings that will be submitted for IO.
* It may be a chained-bio properly constructed by block/bio layer.
* @gfp_mask: gfp flags to be used for memory allocation
*
* blk_make_request is the parallel of generic_make_request for BLOCK_PC
* type commands. Where the struct request needs to be farther initialized by
* the caller. It is passed a &struct bio, which describes the memory info of
* the I/O transfer.
*
* The caller of blk_make_request must make sure that bi_io_vec
* are set to describe the memory buffers. That bio_data_dir() will return
* the needed direction of the request. (And all bio's in the passed bio-chain
* are properly set accordingly)
*
* If called under none-sleepable conditions, mapped bio buffers must not
* need bouncing, by calling the appropriate masked or flagged allocator,
* suitable for the target device. Otherwise the call to blk_queue_bounce will
* BUG.
*
* WARNING: When allocating/cloning a bio-chain, careful consideration should be
* given to how you allocate bios. In particular, you cannot use __GFP_WAIT for
* anything but the first bio in the chain. Otherwise you risk waiting for IO
* completion of a bio that hasn't been submitted yet, thus resulting in a
* deadlock. Alternatively bios should be allocated using bio_kmalloc() instead
* of bio_alloc(), as that avoids the mempool deadlock.
* If possible a big IO should be split into smaller parts when allocation
* fails. Partial allocation should not be an error, or you risk a live-lock.
*/
struct request *blk_make_request(struct request_queue *q, struct bio *bio,
gfp_t gfp_mask)
{
struct request *rq = blk_get_request(q, bio_data_dir(bio), gfp_mask);
if (unlikely(!rq))
return ERR_PTR(-ENOMEM);
for_each_bio(bio) {
struct bio *bounce_bio = bio;
int ret;
blk_queue_bounce(q, &bounce_bio);
ret = blk_rq_append_bio(q, rq, bounce_bio);
if (unlikely(ret)) {
blk_put_request(rq);
return ERR_PTR(ret);
}
}
return rq;
}
EXPORT_SYMBOL(blk_make_request);
/**
* blk_requeue_request - put a request back on queue
* @q: request queue where request should be inserted
* @rq: request to be inserted
*
* Description:
* Drivers often keep queueing requests until the hardware cannot accept
* more, when that condition happens we need to put the request back
* on the queue. Must be called with queue lock held.
*/
void blk_requeue_request(struct request_queue *q, struct request *rq)
{
blk_delete_timer(rq);
blk_clear_rq_complete(rq);
trace_block_rq_requeue(q, rq);
if (blk_rq_tagged(rq))
blk_queue_end_tag(q, rq);
BUG_ON(blk_queued_rq(rq));
elv_requeue_request(q, rq);
}
EXPORT_SYMBOL(blk_requeue_request);
static void add_acct_request(struct request_queue *q, struct request *rq,
int where)
{
drive_stat_acct(rq, 1);
__elv_add_request(q, rq, where);
}
static void part_round_stats_single(int cpu, struct hd_struct *part,
unsigned long now)
{
if (now == part->stamp)
return;
if (part_in_flight(part)) {
__part_stat_add(cpu, part, time_in_queue,
part_in_flight(part) * (now - part->stamp));
__part_stat_add(cpu, part, io_ticks, (now - part->stamp));
}
part->stamp = now;
}
/**
* part_round_stats() - Round off the performance stats on a struct disk_stats.
* @cpu: cpu number for stats access
* @part: target partition
*
* The average IO queue length and utilisation statistics are maintained
* by observing the current state of the queue length and the amount of
* time it has been in this state for.
*
* Normally, that accounting is done on IO completion, but that can result
* in more than a second's worth of IO being accounted for within any one
* second, leading to >100% utilisation. To deal with that, we call this
* function to do a round-off before returning the results when reading
* /proc/diskstats. This accounts immediately for all queue usage up to
* the current jiffies and restarts the counters again.
*/
void part_round_stats(int cpu, struct hd_struct *part)
{
unsigned long now = jiffies;
if (part->partno)
part_round_stats_single(cpu, &part_to_disk(part)->part0, now);
part_round_stats_single(cpu, part, now);
}
EXPORT_SYMBOL_GPL(part_round_stats);
/*
* queue lock must be held
*/
void __blk_put_request(struct request_queue *q, struct request *req)
{
if (unlikely(!q))
return;
if (unlikely(--req->ref_count))
return;
elv_completed_request(q, req);
/* this is a bio leak */
WARN_ON(req->bio != NULL);
/*
* Request may not have originated from ll_rw_blk. if not,
* it didn't come out of our reserved rq pools
*/
if (req->cmd_flags & REQ_ALLOCED) {
unsigned int flags = req->cmd_flags;
BUG_ON(!list_empty(&req->queuelist));
BUG_ON(!hlist_unhashed(&req->hash));
blk_free_request(q, req);
freed_request(q, flags);
}
}
EXPORT_SYMBOL_GPL(__blk_put_request);
void blk_put_request(struct request *req)
{
unsigned long flags;
struct request_queue *q = req->q;
spin_lock_irqsave(q->queue_lock, flags);
__blk_put_request(q, req);
spin_unlock_irqrestore(q->queue_lock, flags);
}
EXPORT_SYMBOL(blk_put_request);
/**
* blk_add_request_payload - add a payload to a request
* @rq: request to update
* @page: page backing the payload
* @len: length of the payload.
*
* This allows to later add a payload to an already submitted request by
* a block driver. The driver needs to take care of freeing the payload
* itself.
*
* Note that this is a quite horrible hack and nothing but handling of
* discard requests should ever use it.
*/
void blk_add_request_payload(struct request *rq, struct page *page,
unsigned int len)
{
struct bio *bio = rq->bio;
bio->bi_io_vec->bv_page = page;
bio->bi_io_vec->bv_offset = 0;
bio->bi_io_vec->bv_len = len;
bio->bi_size = len;
bio->bi_vcnt = 1;
bio->bi_phys_segments = 1;
rq->__data_len = rq->resid_len = len;
rq->nr_phys_segments = 1;
rq->buffer = bio_data(bio);
}
EXPORT_SYMBOL_GPL(blk_add_request_payload);
static bool bio_attempt_back_merge(struct request_queue *q, struct request *req,
struct bio *bio)
{
const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
if (!ll_back_merge_fn(q, req, bio))
return false;
trace_block_bio_backmerge(q, bio);
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
blk_rq_set_mixed_merge(req);
req->biotail->bi_next = bio;
req->biotail = bio;
req->__data_len += bio->bi_size;
req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
drive_stat_acct(req, 0);
elv_bio_merged(q, req, bio);
return true;
}
static bool bio_attempt_front_merge(struct request_queue *q,
struct request *req, struct bio *bio)
{
const int ff = bio->bi_rw & REQ_FAILFAST_MASK;
if (!ll_front_merge_fn(q, req, bio))
return false;
trace_block_bio_frontmerge(q, bio);
if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff)
blk_rq_set_mixed_merge(req);
bio->bi_next = req->bio;
req->bio = bio;
/*
* may not be valid. if the low level driver said
* it didn't need a bounce buffer then it better
* not touch req->buffer either...
*/
req->buffer = bio_data(bio);
req->__sector = bio->bi_sector;
req->__data_len += bio->bi_size;
req->ioprio = ioprio_best(req->ioprio, bio_prio(bio));
drive_stat_acct(req, 0);
elv_bio_merged(q, req, bio);
return true;
}
/**
* 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
* @request_count: out parameter for number of traversed plugged requests
*
* Determine whether @bio being queued on @q can be merged with a request
* on %current's plugged list. Returns %true if merge was successful,
* otherwise %false.
*
* This function is called without @q->queue_lock; however, elevator is
* accessed iff there already are requests on the plugged list which in
* turn guarantees validity of the elevator.
*
* Note that, on successful merge, elevator operation
* elevator_bio_merged_fn() will be called without queue lock. Elevator
* must be ready for this.
*/
static bool attempt_plug_merge(struct request_queue *q, struct bio *bio,
unsigned int *request_count)
{
struct blk_plug *plug;
struct request *rq;
bool ret = false;
plug = current->plug;
if (!plug)
goto out;
*request_count = 0;
list_for_each_entry_reverse(rq, &plug->list, queuelist) {
int el_ret;
(*request_count)++;
if (rq->q != q)
continue;
el_ret = elv_try_merge(rq, bio);
if (el_ret == ELEVATOR_BACK_MERGE) {
ret = bio_attempt_back_merge(q, rq, bio);
if (ret)
break;
} else if (el_ret == ELEVATOR_FRONT_MERGE) {
ret = bio_attempt_front_merge(q, rq, bio);
if (ret)
break;
}
}
out:
return ret;
}
void init_request_from_bio(struct request *req, struct bio *bio)
{
req->cmd_type = REQ_TYPE_FS;
req->cmd_flags |= bio->bi_rw & REQ_COMMON_MASK;
if (bio->bi_rw & REQ_RAHEAD)
req->cmd_flags |= REQ_FAILFAST_MASK;
req->errors = 0;
req->__sector = bio->bi_sector;
req->ioprio = bio_prio(bio);
blk_rq_bio_prep(req->q, req, bio);
}
void blk_queue_bio(struct request_queue *q, struct bio *bio)
{
const bool sync = !!(bio->bi_rw & REQ_SYNC);
struct blk_plug *plug;
int el_ret, rw_flags, where = ELEVATOR_INSERT_SORT;
struct request *req;
unsigned int request_count = 0;
/*
* low level driver can indicate that it wants pages above a
* certain limit bounced to low memory (ie for highmem, or even
* ISA dma in theory)
*/
blk_queue_bounce(q, &bio);
block: implement REQ_FLUSH/FUA based interface for FLUSH/FUA requests Now that the backend conversion is complete, export sequenced FLUSH/FUA capability through REQ_FLUSH/FUA flags. REQ_FLUSH means the device cache should be flushed before executing the request. REQ_FUA means that the data in the request should be on non-volatile media on completion. Block layer will choose the correct way of implementing the semantics and execute it. The request may be passed to the device directly if the device can handle it; otherwise, it will be sequenced using one or more proxy requests. Devices will never see REQ_FLUSH and/or FUA which it doesn't support. Also, unlike the original REQ_HARDBARRIER, REQ_FLUSH/FUA requests are never failed with -EOPNOTSUPP. If the underlying device doesn't support FLUSH/FUA, the block layer simply make those noop. IOW, it no longer distinguishes between writeback cache which doesn't support cache flush and writethrough/no cache. Devices which have WB cache w/o flush are very difficult to come by these days and there's nothing much we can do anyway, so it doesn't make sense to require everyone to implement -EOPNOTSUPP handling. This will simplify filesystems and block drivers as they can drop -EOPNOTSUPP retry logic for barriers. * QUEUE_ORDERED_* are removed and QUEUE_FSEQ_* are moved into blk-flush.c. * REQ_FLUSH w/o data can also be directly passed to drivers without sequencing but some drivers assume that zero length requests don't have rq->bio which isn't true for these requests requiring the use of proxy requests. * REQ_COMMON_MASK now includes REQ_FLUSH | REQ_FUA so that they are copied from bio to request. * WRITE_BARRIER is marked deprecated and WRITE_FLUSH, WRITE_FUA and WRITE_FLUSH_FUA are added. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-09-03 09:56:17 +00:00
if (bio->bi_rw & (REQ_FLUSH | REQ_FUA)) {
spin_lock_irq(q->queue_lock);
block: reimplement FLUSH/FUA to support merge The current FLUSH/FUA support has evolved from the implementation which had to perform queue draining. As such, sequencing is done queue-wide one flush request after another. However, with the draining requirement gone, there's no reason to keep the queue-wide sequential approach. This patch reimplements FLUSH/FUA support such that each FLUSH/FUA request is sequenced individually. The actual FLUSH execution is double buffered and whenever a request wants to execute one for either PRE or POSTFLUSH, it queues on the pending queue. Once certain conditions are met, a flush request is issued and on its completion all pending requests proceed to the next sequence. This allows arbitrary merging of different type of flushes. How they are merged can be primarily controlled and tuned by adjusting the above said 'conditions' used to determine when to issue the next flush. This is inspired by Darrick's patches to merge multiple zero-data flushes which helps workloads with highly concurrent fsync requests. * As flush requests are never put on the IO scheduler, request fields used for flush share space with rq->rb_node. rq->completion_data is moved out of the union. This increases the request size by one pointer. As rq->elevator_private* are used only by the iosched too, it is possible to reduce the request size further. However, to do that, we need to modify request allocation path such that iosched data is not allocated for flush requests. * FLUSH/FUA processing happens on insertion now instead of dispatch. - Comments updated as per Vivek and Mike. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: "Darrick J. Wong" <djwong@us.ibm.com> Cc: Shaohua Li <shli@kernel.org> Cc: Christoph Hellwig <hch@lst.de> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-25 11:43:54 +00:00
where = ELEVATOR_INSERT_FLUSH;
block: drop barrier ordering by queue draining Filesystems will take all the responsibilities for ordering requests around commit writes and will only indicate how the commit writes themselves should be handled by block layers. This patch drops barrier ordering by queue draining from block layer. Ordering by draining implementation was somewhat invasive to request handling. List of notable changes follow. * Each queue has 1 bit color which is flipped on each barrier issue. This is used to track whether a given request is issued before the current barrier or not. REQ_ORDERED_COLOR flag and coloring implementation in __elv_add_request() are removed. * Requests which shouldn't be processed yet for draining were stalled by returning -EAGAIN from blk_do_ordered() according to the test result between blk_ordered_req_seq() and blk_blk_ordered_cur_seq(). This logic is removed. * Draining completion logic in elv_completed_request() removed. * All barrier sequence requests were queued to request queue and then trckled to lower layer according to progress and thus maintaining request orders during requeue was necessary. This is replaced by queueing the next request in the barrier sequence only after the current one is complete from blk_ordered_complete_seq(), which removes the need for multiple proxy requests in struct request_queue and the request sorting logic in the ELEVATOR_INSERT_REQUEUE path of elv_insert(). * As barriers no longer have ordering constraints, there's no need to dump the whole elevator onto the dispatch queue on each barrier. Insert barriers at the front instead. * If other barrier requests come to the front of the dispatch queue while one is already in progress, they are stored in q->pending_barriers and restored to dispatch queue one-by-one after each barrier completion from blk_ordered_complete_seq(). Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2010-09-03 09:56:16 +00:00
goto get_rq;
}
/*
* Check if we can merge with the plugged list before grabbing
* any locks.
*/
if (attempt_plug_merge(q, bio, &request_count))
return;
spin_lock_irq(q->queue_lock);
el_ret = elv_merge(q, &req, bio);
if (el_ret == ELEVATOR_BACK_MERGE) {
if (bio_attempt_back_merge(q, req, bio)) {
if (!attempt_back_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out_unlock;
}
} else if (el_ret == ELEVATOR_FRONT_MERGE) {
if (bio_attempt_front_merge(q, req, bio)) {
if (!attempt_front_merge(q, req))
elv_merged_request(q, req, el_ret);
goto out_unlock;
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
}
}
get_rq:
/*
* This sync check and mask will be re-done in init_request_from_bio(),
* but we need to set it earlier to expose the sync flag to the
* rq allocator and io schedulers.
*/
rw_flags = bio_data_dir(bio);
if (sync)
rw_flags |= REQ_SYNC;
/*
* Grab a free request. This is might sleep but can not fail.
* Returns with the queue unlocked.
*/
req = get_request_wait(q, rw_flags, bio);
if (unlikely(!req)) {
bio_endio(bio, -ENODEV); /* @q is dead */
goto out_unlock;
}
/*
* After dropping the lock and possibly sleeping here, our request
* may now be mergeable after it had proven unmergeable (above).
* We don't worry about that case for efficiency. It won't happen
* often, and the elevators are able to handle it.
*/
init_request_from_bio(req, bio);
if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags))
req->cpu = raw_smp_processor_id();
plug = current->plug;
if (plug) {
/*
* If this is the first request added after a plug, fire
* of a plug trace. If others have been added before, check
* if we have multiple devices in this plug. If so, make a
* note to sort the list before dispatch.
*/
if (list_empty(&plug->list))
trace_block_plug(q);
else {
if (!plug->should_sort) {
struct request *__rq;
__rq = list_entry_rq(plug->list.prev);
if (__rq->q != q)
plug->should_sort = 1;
}
if (request_count >= BLK_MAX_REQUEST_COUNT) {
blk_flush_plug_list(plug, false);
trace_block_plug(q);
}
}
list_add_tail(&req->queuelist, &plug->list);
drive_stat_acct(req, 1);
} else {
spin_lock_irq(q->queue_lock);
add_acct_request(q, req, where);
__blk_run_queue(q);
out_unlock:
spin_unlock_irq(q->queue_lock);
}
}
EXPORT_SYMBOL_GPL(blk_queue_bio); /* for device mapper only */
/*
* If bio->bi_dev is a partition, remap the location
*/
static inline void blk_partition_remap(struct bio *bio)
{
struct block_device *bdev = bio->bi_bdev;
if (bio_sectors(bio) && bdev != bdev->bd_contains) {
struct hd_struct *p = bdev->bd_part;
bio->bi_sector += p->start_sect;
bio->bi_bdev = bdev->bd_contains;
trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio,
bdev->bd_dev,
bio->bi_sector - p->start_sect);
}
}
static void handle_bad_sector(struct bio *bio)
{
char b[BDEVNAME_SIZE];
printk(KERN_INFO "attempt to access beyond end of device\n");
printk(KERN_INFO "%s: rw=%ld, want=%Lu, limit=%Lu\n",
bdevname(bio->bi_bdev, b),
bio->bi_rw,
(unsigned long long)bio->bi_sector + bio_sectors(bio),
(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
set_bit(BIO_EOF, &bio->bi_flags);
}
#ifdef CONFIG_FAIL_MAKE_REQUEST
static DECLARE_FAULT_ATTR(fail_make_request);
static int __init setup_fail_make_request(char *str)
{
return setup_fault_attr(&fail_make_request, str);
}
__setup("fail_make_request=", setup_fail_make_request);
static bool should_fail_request(struct hd_struct *part, unsigned int bytes)
{
return part->make_it_fail && should_fail(&fail_make_request, bytes);
}
static int __init fail_make_request_debugfs(void)
{
struct dentry *dir = fault_create_debugfs_attr("fail_make_request",
NULL, &fail_make_request);
return IS_ERR(dir) ? PTR_ERR(dir) : 0;
}
late_initcall(fail_make_request_debugfs);
#else /* CONFIG_FAIL_MAKE_REQUEST */
static inline bool should_fail_request(struct hd_struct *part,
unsigned int bytes)
{
return false;
}
#endif /* CONFIG_FAIL_MAKE_REQUEST */
/*
* Check whether this bio extends beyond the end of the device.
*/
static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
{
sector_t maxsector;
if (!nr_sectors)
return 0;
/* Test device or partition size, when known. */
maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
if (maxsector) {
sector_t sector = bio->bi_sector;
if (maxsector < nr_sectors || maxsector - nr_sectors < sector) {
/*
* This may well happen - the kernel calls bread()
* without checking the size of the device, e.g., when
* mounting a device.
*/
handle_bad_sector(bio);
return 1;
}
}
return 0;
}
static noinline_for_stack bool
generic_make_request_checks(struct bio *bio)
{
struct request_queue *q;
int nr_sectors = bio_sectors(bio);
int err = -EIO;
char b[BDEVNAME_SIZE];
struct hd_struct *part;
might_sleep();
if (bio_check_eod(bio, nr_sectors))
goto end_io;
q = bdev_get_queue(bio->bi_bdev);
if (unlikely(!q)) {
printk(KERN_ERR
"generic_make_request: Trying to access "
"nonexistent block-device %s (%Lu)\n",
bdevname(bio->bi_bdev, b),
(long long) bio->bi_sector);
goto end_io;
}
if (unlikely(!(bio->bi_rw & REQ_DISCARD) &&
nr_sectors > queue_max_hw_sectors(q))) {
printk(KERN_ERR "bio too big device %s (%u > %u)\n",
bdevname(bio->bi_bdev, b),
bio_sectors(bio),
queue_max_hw_sectors(q));
goto end_io;
}
part = bio->bi_bdev->bd_part;
if (should_fail_request(part, bio->bi_size) ||
should_fail_request(&part_to_disk(part)->part0,
bio->bi_size))
goto end_io;
/*
* If this device has partitions, remap block n
* of partition p to block n+start(p) of the disk.
*/
blk_partition_remap(bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
goto end_io;
if (bio_check_eod(bio, nr_sectors))
goto end_io;
/*
* Filter flush bio's early so that make_request based
* drivers without flush support don't have to worry
* about them.
*/
if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) {
bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA);
if (!nr_sectors) {
err = 0;
goto end_io;
}
}
if ((bio->bi_rw & REQ_DISCARD) &&
(!blk_queue_discard(q) ||
((bio->bi_rw & REQ_SECURE) &&
!blk_queue_secdiscard(q)))) {
err = -EOPNOTSUPP;
goto end_io;
}
if (blk_throtl_bio(q, bio))
return false; /* throttled, will be resubmitted later */
trace_block_bio_queue(q, bio);
return true;
end_io:
bio_endio(bio, err);
return false;
}
/**
* generic_make_request - hand a buffer to its device driver for I/O
* @bio: The bio describing the location in memory and on the device.
*
* generic_make_request() is used to make I/O requests of block
* devices. It is passed a &struct bio, which describes the I/O that needs
* to be done.
*
* generic_make_request() does not return any status. The
* success/failure status of the request, along with notification of
* completion, is delivered asynchronously through the bio->bi_end_io
* function described (one day) else where.
*
* The caller of generic_make_request must make sure that bi_io_vec
* are set to describe the memory buffer, and that bi_dev and bi_sector are
* set to describe the device address, and the
* bi_end_io and optionally bi_private are set to describe how
* completion notification should be signaled.
*
* generic_make_request and the drivers it calls may use bi_next if this
* bio happens to be merged with someone else, and may resubmit the bio to
* a lower device by calling into generic_make_request recursively, which
* means the bio should NOT be touched after the call to ->make_request_fn.
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 07:53:42 +00:00
*/
void generic_make_request(struct bio *bio)
{
struct bio_list bio_list_on_stack;
if (!generic_make_request_checks(bio))
return;
/*
* We only want one ->make_request_fn to be active at a time, else
* stack usage with stacked devices could be a problem. So use
* current->bio_list to keep a list of requests submited by a
* make_request_fn function. current->bio_list is also used as a
* flag to say if generic_make_request is currently active in this
* task or not. If it is NULL, then no make_request is active. If
* it is non-NULL, then a make_request is active, and new requests
* should be added at the tail
*/
if (current->bio_list) {
bio_list_add(current->bio_list, bio);
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 07:53:42 +00:00
return;
}
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 07:53:42 +00:00
/* following loop may be a bit non-obvious, and so deserves some
* explanation.
* Before entering the loop, bio->bi_next is NULL (as all callers
* ensure that) so we have a list with a single bio.
* We pretend that we have just taken it off a longer list, so
* we assign bio_list to a pointer to the bio_list_on_stack,
* thus initialising the bio_list of new bios to be
* added. ->make_request() may indeed add some more bios
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 07:53:42 +00:00
* through a recursive call to generic_make_request. If it
* did, we find a non-NULL value in bio_list and re-enter the loop
* from the top. In this case we really did just take the bio
* of the top of the list (no pretending) and so remove it from
* bio_list, and call into ->make_request() again.
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 07:53:42 +00:00
*/
BUG_ON(bio->bi_next);
bio_list_init(&bio_list_on_stack);
current->bio_list = &bio_list_on_stack;
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 07:53:42 +00:00
do {
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
q->make_request_fn(q, bio);
bio = bio_list_pop(current->bio_list);
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 07:53:42 +00:00
} while (bio);
current->bio_list = NULL; /* deactivate */
When stacked block devices are in-use (e.g. md or dm), the recursive calls to generic_make_request can use up a lot of space, and we would rather they didn't. As generic_make_request is a void function, and as it is generally not expected that it will have any effect immediately, it is safe to delay any call to generic_make_request until there is sufficient stack space available. As ->bi_next is reserved for the driver to use, it can have no valid value when generic_make_request is called, and as __make_request implicitly assumes it will be NULL (ELEVATOR_BACK_MERGE fork of switch) we can be certain that all callers set it to NULL. We can therefore safely use bi_next to link pending requests together, providing we clear it before making the real call. So, we choose to allow each thread to only be active in one generic_make_request at a time. If a subsequent (recursive) call is made, the bio is linked into a per-thread list, and is handled when the active call completes. As the list of pending bios is per-thread, there are no locking issues to worry about. I say above that it is "safe to delay any call...". There are, however, some behaviours of a make_request_fn which would make it unsafe. These include any behaviour that assumes anything will have changed after a recursive call to generic_make_request. These could include: - waiting for that call to finish and call it's bi_end_io function. md use to sometimes do this (marking the superblock dirty before completing a write) but doesn't any more - inspecting the bio for fields that generic_make_request might change, such as bi_sector or bi_bdev. It is hard to see a good reason for this, and I don't think anyone actually does it. - inspecing the queue to see if, e.g. it is 'full' yet. Again, I think this is very unlikely to be useful, or to be done. Signed-off-by: Neil Brown <neilb@suse.de> Cc: Jens Axboe <axboe@kernel.dk> Cc: <dm-devel@redhat.com> Alasdair G Kergon <agk@redhat.com> said: I can see nothing wrong with this in principle. For device-mapper at the moment though it's essential that, while the bio mappings may now get delayed, they still get processed in exactly the same order as they were passed to generic_make_request(). My main concern is whether the timing changes implicit in this patch will make the rare data-corrupting races in the existing snapshot code more likely. (I'm working on a fix for these races, but the unfinished patch is already several hundred lines long.) It would be helpful if some people on this mailing list would test this patch in various scenarios and report back. Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-05-01 07:53:42 +00:00
}
EXPORT_SYMBOL(generic_make_request);
/**
* submit_bio - submit a bio to the block device layer for I/O
* @rw: whether to %READ or %WRITE, or maybe to %READA (read ahead)
* @bio: The &struct bio which describes the I/O
*
* submit_bio() is very similar in purpose to generic_make_request(), and
* uses that function to do most of the work. Both are fairly rough
* interfaces; @bio must be presetup and ready for I/O.
*
*/
void submit_bio(int rw, struct bio *bio)
{
int count = bio_sectors(bio);
bio->bi_rw |= rw;
/*
* If it's a regular read/write or a barrier with data attached,
* go through the normal accounting stuff before submission.
*/
if (bio_has_data(bio) && !(rw & REQ_DISCARD)) {
if (rw & WRITE) {
count_vm_events(PGPGOUT, count);
} else {
task_io_account_read(bio->bi_size);
count_vm_events(PGPGIN, count);
}
if (unlikely(block_dump)) {
char b[BDEVNAME_SIZE];
printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n",
current->comm, task_pid_nr(current),
(rw & WRITE) ? "WRITE" : "READ",
(unsigned long long)bio->bi_sector,
bdevname(bio->bi_bdev, b),
count);
}
}
generic_make_request(bio);
}
EXPORT_SYMBOL(submit_bio);
/**
* blk_rq_check_limits - Helper function to check a request for the queue limit
* @q: the queue
* @rq: the request being checked
*
* Description:
* @rq may have been made based on weaker limitations of upper-level queues
* in request stacking drivers, and it may violate the limitation of @q.
* Since the block layer and the underlying device driver trust @rq
* after it is inserted to @q, it should be checked against @q before
* the insertion using this generic function.
*
* This function should also be useful for request stacking drivers
* in some cases below, so export this function.
* Request stacking drivers like request-based dm may change the queue
* limits while requests are in the queue (e.g. dm's table swapping).
* Such request stacking drivers should check those requests agaist
* the new queue limits again when they dispatch those requests,
* although such checkings are also done against the old queue limits
* when submitting requests.
*/
int blk_rq_check_limits(struct request_queue *q, struct request *rq)
{
if (rq->cmd_flags & REQ_DISCARD)
return 0;
if (blk_rq_sectors(rq) > queue_max_sectors(q) ||
blk_rq_bytes(rq) > queue_max_hw_sectors(q) << 9) {
printk(KERN_ERR "%s: over max size limit.\n", __func__);
return -EIO;
}
/*
* queue's settings related to segment counting like q->bounce_pfn
* may differ from that of other stacking queues.
* Recalculate it to check the request correctly on this queue's
* limitation.
*/
blk_recalc_rq_segments(rq);
if (rq->nr_phys_segments > queue_max_segments(q)) {
printk(KERN_ERR "%s: over max segments limit.\n", __func__);
return -EIO;
}
return 0;
}
EXPORT_SYMBOL_GPL(blk_rq_check_limits);
/**
* blk_insert_cloned_request - Helper for stacking drivers to submit a request
* @q: the queue to submit the request
* @rq: the request being queued
*/
int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
{
unsigned long flags;
block: fix flush machinery for stacking drivers with differring flush flags Commit ae1b1539622fb46e51b4d13b3f9e5f4c713f86ae, block: reimplement FLUSH/FUA to support merge, introduced a performance regression when running any sort of fsyncing workload using dm-multipath and certain storage (in our case, an HP EVA). The test I ran was fs_mark, and it dropped from ~800 files/sec on ext4 to ~100 files/sec. It turns out that dm-multipath always advertised flush+fua support, and passed commands on down the stack, where those flags used to get stripped off. The above commit changed that behavior: static inline struct request *__elv_next_request(struct request_queue *q) { struct request *rq; while (1) { - while (!list_empty(&q->queue_head)) { + if (!list_empty(&q->queue_head)) { rq = list_entry_rq(q->queue_head.next); - if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) || - (rq->cmd_flags & REQ_FLUSH_SEQ)) - return rq; - rq = blk_do_flush(q, rq); - if (rq) - return rq; + return rq; } Note that previously, a command would come in here, have REQ_FLUSH|REQ_FUA set, and then get handed off to blk_do_flush: struct request *blk_do_flush(struct request_queue *q, struct request *rq) { unsigned int fflags = q->flush_flags; /* may change, cache it */ bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA; bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH); bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA); unsigned skip = 0; ... if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) { rq->cmd_flags &= ~REQ_FLUSH; if (!has_fua) rq->cmd_flags &= ~REQ_FUA; return rq; } So, the flush machinery was bypassed in such cases (q->flush_flags == 0 && rq->cmd_flags & (REQ_FLUSH|REQ_FUA)). Now, however, we don't get into the flush machinery at all. Instead, __elv_next_request just hands a request with flush and fua bits set to the scsi_request_fn, even if the underlying request_queue does not support flush or fua. The agreed upon approach is to fix the flush machinery to allow stacking. While this isn't used in practice (since there is only one request-based dm target, and that target will now reflect the flush flags of the underlying device), it does future-proof the solution, and make it function as designed. In order to make this work, I had to add a field to the struct request, inside the flush structure (to store the original req->end_io). Shaohua had suggested overloading the union with rb_node and completion_data, but the completion data is used by device mapper and can also be used by other drivers. So, I didn't see a way around the additional field. I tested this patch on an HP EVA with both ext4 and xfs, and it recovers the lost performance. Comments and other testers, as always, are appreciated. Cheers, Jeff Signed-off-by: Jeff Moyer <jmoyer@redhat.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-08-15 19:37:25 +00:00
int where = ELEVATOR_INSERT_BACK;
if (blk_rq_check_limits(q, rq))
return -EIO;
if (rq->rq_disk &&
should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq)))
return -EIO;
spin_lock_irqsave(q->queue_lock, flags);
if (unlikely(blk_queue_dead(q))) {
spin_unlock_irqrestore(q->queue_lock, flags);
return -ENODEV;
}
/*
* Submitting request must be dequeued before calling this function
* because it will be linked to another request_queue
*/
BUG_ON(blk_queued_rq(rq));
block: fix flush machinery for stacking drivers with differring flush flags Commit ae1b1539622fb46e51b4d13b3f9e5f4c713f86ae, block: reimplement FLUSH/FUA to support merge, introduced a performance regression when running any sort of fsyncing workload using dm-multipath and certain storage (in our case, an HP EVA). The test I ran was fs_mark, and it dropped from ~800 files/sec on ext4 to ~100 files/sec. It turns out that dm-multipath always advertised flush+fua support, and passed commands on down the stack, where those flags used to get stripped off. The above commit changed that behavior: static inline struct request *__elv_next_request(struct request_queue *q) { struct request *rq; while (1) { - while (!list_empty(&q->queue_head)) { + if (!list_empty(&q->queue_head)) { rq = list_entry_rq(q->queue_head.next); - if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) || - (rq->cmd_flags & REQ_FLUSH_SEQ)) - return rq; - rq = blk_do_flush(q, rq); - if (rq) - return rq; + return rq; } Note that previously, a command would come in here, have REQ_FLUSH|REQ_FUA set, and then get handed off to blk_do_flush: struct request *blk_do_flush(struct request_queue *q, struct request *rq) { unsigned int fflags = q->flush_flags; /* may change, cache it */ bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA; bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH); bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA); unsigned skip = 0; ... if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) { rq->cmd_flags &= ~REQ_FLUSH; if (!has_fua) rq->cmd_flags &= ~REQ_FUA; return rq; } So, the flush machinery was bypassed in such cases (q->flush_flags == 0 && rq->cmd_flags & (REQ_FLUSH|REQ_FUA)). Now, however, we don't get into the flush machinery at all. Instead, __elv_next_request just hands a request with flush and fua bits set to the scsi_request_fn, even if the underlying request_queue does not support flush or fua. The agreed upon approach is to fix the flush machinery to allow stacking. While this isn't used in practice (since there is only one request-based dm target, and that target will now reflect the flush flags of the underlying device), it does future-proof the solution, and make it function as designed. In order to make this work, I had to add a field to the struct request, inside the flush structure (to store the original req->end_io). Shaohua had suggested overloading the union with rb_node and completion_data, but the completion data is used by device mapper and can also be used by other drivers. So, I didn't see a way around the additional field. I tested this patch on an HP EVA with both ext4 and xfs, and it recovers the lost performance. Comments and other testers, as always, are appreciated. Cheers, Jeff Signed-off-by: Jeff Moyer <jmoyer@redhat.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-08-15 19:37:25 +00:00
if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA))
where = ELEVATOR_INSERT_FLUSH;
add_acct_request(q, rq, where);
if (where == ELEVATOR_INSERT_FLUSH)
__blk_run_queue(q);
spin_unlock_irqrestore(q->queue_lock, flags);
return 0;
}
EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
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_err_bytes - determine number of bytes till the next failure boundary
* @rq: request to examine
*
* Description:
* A request could be merge of IOs which require different failure
* handling. This function determines the number of bytes which
* can be failed from the beginning of the request without
* crossing into area which need to be retried further.
*
* Return:
* The number of bytes to fail.
*
* Context:
* queue_lock must be held.
*/
unsigned int blk_rq_err_bytes(const struct request *rq)
{
unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK;
unsigned int bytes = 0;
struct bio *bio;
if (!(rq->cmd_flags & REQ_MIXED_MERGE))
return blk_rq_bytes(rq);
/*
* Currently the only 'mixing' which can happen is between
* different fastfail types. We can safely fail portions
* which have all the failfast bits that the first one has -
* the ones which are at least as eager to fail as the first
* one.
*/
for (bio = rq->bio; bio; bio = bio->bi_next) {
if ((bio->bi_rw & ff) != ff)
break;
bytes += bio->bi_size;
}
/* this could lead to infinite loop */
BUG_ON(blk_rq_bytes(rq) && !bytes);
return bytes;
}
EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
static void blk_account_io_completion(struct request *req, unsigned int bytes)
{
if (blk_do_io_stat(req)) {
const int rw = rq_data_dir(req);
struct hd_struct *part;
int cpu;
cpu = part_stat_lock();
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 15:57:38 +00:00
part = req->part;
part_stat_add(cpu, part, sectors[rw], bytes >> 9);
part_stat_unlock();
}
}
static void blk_account_io_done(struct request *req)
{
/*
* Account IO completion. flush_rq isn't accounted as a
* normal IO on queueing nor completion. Accounting the
* containing request is enough.
*/
if (blk_do_io_stat(req) && !(req->cmd_flags & REQ_FLUSH_SEQ)) {
unsigned long duration = jiffies - req->start_time;
const int rw = rq_data_dir(req);
struct hd_struct *part;
int cpu;
cpu = part_stat_lock();
block: fix accounting bug on cross partition merges /proc/diskstats would display a strange output as follows. $ cat /proc/diskstats |grep sda 8 0 sda 90524 7579 102154 20464 0 0 0 0 0 14096 20089 8 1 sda1 19085 1352 21841 4209 0 0 0 0 4294967064 15689 4293424691 ~~~~~~~~~~ 8 2 sda2 71252 3624 74891 15950 0 0 0 0 232 23995 1562390 8 3 sda3 54 487 2188 92 0 0 0 0 0 88 92 8 4 sda4 4 0 8 0 0 0 0 0 0 0 0 8 5 sda5 81 2027 2130 138 0 0 0 0 0 87 137 Its reason is the wrong way of accounting hd_struct->in_flight. When a bio is merged into a request belongs to different partition by ELEVATOR_FRONT_MERGE. The detailed root cause is as follows. Assuming that there are two partition, sda1 and sda2. 1. A request for sda2 is in request_queue. Hence sda1's hd_struct->in_flight is 0 and sda2's one is 1. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 2. A bio belongs to sda1 is issued and is merged into the request mentioned on step1 by ELEVATOR_BACK_MERGE. The first sector of the request is changed from sda2 region to sda1 region. However the two partition's hd_struct->in_flight are not changed. | hd_struct->in_flight --------------------------- sda1 | 0 sda2 | 1 --------------------------- 3. The request is finished and blk_account_io_done() is called. In this case, sda2's hd_struct->in_flight, not a sda1's one, is decremented. | hd_struct->in_flight --------------------------- sda1 | -1 sda2 | 1 --------------------------- The patch fixes the problem by caching the partition lookup inside the request structure, hence making sure that the increment and decrement will always happen on the same partition struct. This also speeds up IO with accounting enabled, since it cuts down on the number of lookups we have to do. Also add a refcount to struct hd_struct to keep the partition in memory as long as users exist. We use kref_test_and_get() to ensure we don't add a reference to a partition which is going away. Signed-off-by: Jerome Marchand <jmarchan@redhat.com> Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: stable@kernel.org Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-01-05 15:57:38 +00:00
part = req->part;
part_stat_inc(cpu, part, ios[rw]);
part_stat_add(cpu, part, ticks[rw], duration);
part_round_stats(cpu, part);
part_dec_in_flight(part, rw);
hd_struct_put(part);
part_stat_unlock();
}
}
/**
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 02:54:16 +00:00
* blk_peek_request - peek at the top of a request queue
* @q: request queue to peek at
*
* Description:
* Return the request at the top of @q. The returned request
* should be started using blk_start_request() before LLD starts
* processing it.
*
* Return:
* Pointer to the request at the top of @q if available. Null
* otherwise.
*
* Context:
* queue_lock must be held.
*/
struct request *blk_peek_request(struct request_queue *q)
{
struct request *rq;
int ret;
while ((rq = __elv_next_request(q)) != NULL) {
if (!(rq->cmd_flags & REQ_STARTED)) {
/*
* This is the first time the device driver
* sees this request (possibly after
* requeueing). Notify IO scheduler.
*/
if (rq->cmd_flags & REQ_SORTED)
elv_activate_rq(q, rq);
/*
* just mark as started even if we don't start
* it, a request that has been delayed should
* not be passed by new incoming requests
*/
rq->cmd_flags |= REQ_STARTED;
trace_block_rq_issue(q, rq);
}
if (!q->boundary_rq || q->boundary_rq == rq) {
q->end_sector = rq_end_sector(rq);
q->boundary_rq = NULL;
}
if (rq->cmd_flags & REQ_DONTPREP)
break;
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:41 +00:00
if (q->dma_drain_size && blk_rq_bytes(rq)) {
/*
* make sure space for the drain appears we
* know we can do this because max_hw_segments
* has been adjusted to be one fewer than the
* device can handle
*/
rq->nr_phys_segments++;
}
if (!q->prep_rq_fn)
break;
ret = q->prep_rq_fn(q, rq);
if (ret == BLKPREP_OK) {
break;
} else if (ret == BLKPREP_DEFER) {
/*
* the request may have been (partially) prepped.
* we need to keep this request in the front to
* avoid resource deadlock. REQ_STARTED will
* prevent other fs requests from passing this one.
*/
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:41 +00:00
if (q->dma_drain_size && blk_rq_bytes(rq) &&
!(rq->cmd_flags & REQ_DONTPREP)) {
/*
* remove the space for the drain we added
* so that we don't add it again
*/
--rq->nr_phys_segments;
}
rq = NULL;
break;
} else if (ret == BLKPREP_KILL) {
rq->cmd_flags |= REQ_QUIET;
/*
* Mark this request as started so we don't trigger
* any debug logic in the end I/O path.
*/
blk_start_request(rq);
__blk_end_request_all(rq, -EIO);
} else {
printk(KERN_ERR "%s: bad return=%d\n", __func__, ret);
break;
}
}
return rq;
}
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 02:54:16 +00:00
EXPORT_SYMBOL(blk_peek_request);
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 02:54:16 +00:00
void blk_dequeue_request(struct request *rq)
{
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 02:54:16 +00:00
struct request_queue *q = rq->q;
BUG_ON(list_empty(&rq->queuelist));
BUG_ON(ELV_ON_HASH(rq));
list_del_init(&rq->queuelist);
/*
* the time frame between a request being removed from the lists
* and to it is freed is accounted as io that is in progress at
* the driver side.
*/
if (blk_account_rq(rq)) {
q->in_flight[rq_is_sync(rq)]++;
set_io_start_time_ns(rq);
}
}
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 02:54:16 +00:00
/**
* blk_start_request - start request processing on the driver
* @req: request to dequeue
*
* Description:
* Dequeue @req and start timeout timer on it. This hands off the
* request to the driver.
*
* Block internal functions which don't want to start timer should
* call blk_dequeue_request().
*
* Context:
* queue_lock must be held.
*/
void blk_start_request(struct request *req)
{
blk_dequeue_request(req);
/*
block: set rq->resid_len to blk_rq_bytes() on issue In commit c3a4d78c580de4edc9ef0f7c59812fb02ceb037f, while introducing rq->resid_len, the default value of residue count was changed from full count to zero. The conversion was done under the assumption that when a request fails residue count wasn't defined. However, Boaz and James pointed out that this wasn't true and the residue count should be preserved for failed requests too. This patchset restores the original behavior by setting rq->resid_len to blk_rq_bytes(rq) on request start and restoring explicit clearing in affected drivers. While at it, take advantage of the fact that rq->resid_len is set to full count where applicable. * ide-cd: rq->resid_len cleared on pc success * mptsas: req->resid_len cleared on success * sas_expander: rsp/req->resid_len cleared on success * mpt2sas_transport: req->resid_len cleared on success * ide-cd, ide-tape, mptsas, sas_host_smp, mpt2sas_transport, ub: take advantage of initial full count to simplify code Boaz Harrosh spotted bug in resid_len initialization. Fixed as suggested. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Borislav Petkov <petkovbb@googlemail.com> Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Darrick J. Wong <djwong@us.ibm.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-19 09:33:05 +00:00
* We are now handing the request to the hardware, initialize
* resid_len to full count and add the timeout handler.
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 02:54:16 +00:00
*/
block: set rq->resid_len to blk_rq_bytes() on issue In commit c3a4d78c580de4edc9ef0f7c59812fb02ceb037f, while introducing rq->resid_len, the default value of residue count was changed from full count to zero. The conversion was done under the assumption that when a request fails residue count wasn't defined. However, Boaz and James pointed out that this wasn't true and the residue count should be preserved for failed requests too. This patchset restores the original behavior by setting rq->resid_len to blk_rq_bytes(rq) on request start and restoring explicit clearing in affected drivers. While at it, take advantage of the fact that rq->resid_len is set to full count where applicable. * ide-cd: rq->resid_len cleared on pc success * mptsas: req->resid_len cleared on success * sas_expander: rsp/req->resid_len cleared on success * mpt2sas_transport: req->resid_len cleared on success * ide-cd, ide-tape, mptsas, sas_host_smp, mpt2sas_transport, ub: take advantage of initial full count to simplify code Boaz Harrosh spotted bug in resid_len initialization. Fixed as suggested. Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Borislav Petkov <petkovbb@googlemail.com> Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Eric Moore <Eric.Moore@lsi.com> Cc: Darrick J. Wong <djwong@us.ibm.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-19 09:33:05 +00:00
req->resid_len = blk_rq_bytes(req);
if (unlikely(blk_bidi_rq(req)))
req->next_rq->resid_len = blk_rq_bytes(req->next_rq);
block: implement and enforce request peek/start/fetch Till now block layer allowed two separate modes of request execution. A request is always acquired from the request queue via elv_next_request(). After that, drivers are free to either dequeue it or process it without dequeueing. Dequeue allows elv_next_request() to return the next request so that multiple requests can be in flight. Executing requests without dequeueing has its merits mostly in allowing drivers for simpler devices which can't do sg to deal with segments only without considering request boundary. However, the benefit this brings is dubious and declining while the cost of the API ambiguity is increasing. Segment based drivers are usually for very old or limited devices and as converting to dequeueing model isn't difficult, it doesn't justify the API overhead it puts on block layer and its more modern users. Previous patches converted all block low level drivers to dequeueing model. This patch completes the API transition by... * renaming elv_next_request() to blk_peek_request() * renaming blkdev_dequeue_request() to blk_start_request() * adding blk_fetch_request() which is combination of peek and start * disallowing completion of queued (not started) requests * applying new API to all LLDs Renamings are for consistency and to break out of tree code so that it's apparent that out of tree drivers need updating. [ Impact: block request issue API cleanup, no functional change ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Miller <mike.miller@hp.com> Cc: unsik Kim <donari75@gmail.com> Cc: Paul Clements <paul.clements@steeleye.com> Cc: Tim Waugh <tim@cyberelk.net> Cc: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Cc: David S. Miller <davem@davemloft.net> Cc: Laurent Vivier <Laurent@lvivier.info> Cc: Jeff Garzik <jgarzik@pobox.com> Cc: Jeremy Fitzhardinge <jeremy@xensource.com> Cc: Grant Likely <grant.likely@secretlab.ca> Cc: Adrian McMenamin <adrian@mcmen.demon.co.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com> Cc: Borislav Petkov <petkovbb@googlemail.com> Cc: Sergei Shtylyov <sshtylyov@ru.mvista.com> Cc: Alex Dubov <oakad@yahoo.com> Cc: Pierre Ossman <drzeus@drzeus.cx> Cc: David Woodhouse <dwmw2@infradead.org> Cc: Markus Lidel <Markus.Lidel@shadowconnect.com> Cc: Stefan Weinhuber <wein@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Pete Zaitcev <zaitcev@redhat.com> Cc: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-08 02:54:16 +00:00
blk_add_timer(req);
}
EXPORT_SYMBOL(blk_start_request);
/**
* blk_fetch_request - fetch a request from a request queue
* @q: request queue to fetch a request from
*
* Description:
* Return the request at the top of @q. The request is started on
* return and LLD can start processing it immediately.
*
* Return:
* Pointer to the request at the top of @q if available. Null
* otherwise.
*
* Context:
* queue_lock must be held.
*/
struct request *blk_fetch_request(struct request_queue *q)
{
struct request *rq;
rq = blk_peek_request(q);
if (rq)
blk_start_request(rq);
return rq;
}
EXPORT_SYMBOL(blk_fetch_request);
/**
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
* blk_update_request - Special helper function for request stacking drivers
* @req: the request being processed
* @error: %0 for success, < %0 for error
* @nr_bytes: number of bytes to complete @req
*
* Description:
* Ends I/O on a number of bytes attached to @req, but doesn't complete
* the request structure even if @req doesn't have leftover.
* If @req has leftover, sets it up for the next range of segments.
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
*
* This special helper function is only for request stacking drivers
* (e.g. request-based dm) so that they can handle partial completion.
* Actual device drivers should use blk_end_request instead.
*
* Passing the result of blk_rq_bytes() as @nr_bytes guarantees
* %false return from this function.
*
* Return:
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
* %false - this request doesn't have any more data
* %true - this request has more data
**/
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
{
int total_bytes, bio_nbytes, next_idx = 0;
struct bio *bio;
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
if (!req->bio)
return false;
trace_block_rq_complete(req->q, req);
/*
* For fs requests, rq is just carrier of independent bio's
* and each partial completion should be handled separately.
* Reset per-request error on each partial completion.
*
* TODO: tj: This is too subtle. It would be better to let
* low level drivers do what they see fit.
*/
if (req->cmd_type == REQ_TYPE_FS)
req->errors = 0;
if (error && req->cmd_type == REQ_TYPE_FS &&
!(req->cmd_flags & REQ_QUIET)) {
char *error_type;
switch (error) {
case -ENOLINK:
error_type = "recoverable transport";
break;
case -EREMOTEIO:
error_type = "critical target";
break;
case -EBADE:
error_type = "critical nexus";
break;
case -EIO:
default:
error_type = "I/O";
break;
}
printk(KERN_ERR "end_request: %s error, dev %s, sector %llu\n",
error_type, req->rq_disk ? req->rq_disk->disk_name : "?",
(unsigned long long)blk_rq_pos(req));
}
blk_account_io_completion(req, nr_bytes);
total_bytes = bio_nbytes = 0;
while ((bio = req->bio) != NULL) {
int nbytes;
if (nr_bytes >= bio->bi_size) {
req->bio = bio->bi_next;
nbytes = bio->bi_size;
req_bio_endio(req, bio, nbytes, error);
next_idx = 0;
bio_nbytes = 0;
} else {
int idx = bio->bi_idx + next_idx;
if (unlikely(idx >= bio->bi_vcnt)) {
blk_dump_rq_flags(req, "__end_that");
printk(KERN_ERR "%s: bio idx %d >= vcnt %d\n",
__func__, idx, bio->bi_vcnt);
break;
}
nbytes = bio_iovec_idx(bio, idx)->bv_len;
BIO_BUG_ON(nbytes > bio->bi_size);
/*
* not a complete bvec done
*/
if (unlikely(nbytes > nr_bytes)) {
bio_nbytes += nr_bytes;
total_bytes += nr_bytes;
break;
}
/*
* advance to the next vector
*/
next_idx++;
bio_nbytes += nbytes;
}
total_bytes += nbytes;
nr_bytes -= nbytes;
bio = req->bio;
if (bio) {
/*
* end more in this run, or just return 'not-done'
*/
if (unlikely(nr_bytes <= 0))
break;
}
}
/*
* completely done
*/
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
if (!req->bio) {
/*
* Reset counters so that the request stacking driver
* can find how many bytes remain in the request
* later.
*/
req->__data_len = 0;
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
return false;
}
/*
* if the request wasn't completed, update state
*/
if (bio_nbytes) {
req_bio_endio(req, bio, bio_nbytes, error);
bio->bi_idx += next_idx;
bio_iovec(bio)->bv_offset += nr_bytes;
bio_iovec(bio)->bv_len -= nr_bytes;
}
req->__data_len -= total_bytes;
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:41 +00:00
req->buffer = bio_data(req->bio);
/* update sector only for requests with clear definition of sector */
if (req->cmd_type == REQ_TYPE_FS || (req->cmd_flags & REQ_DISCARD))
req->__sector += total_bytes >> 9;
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:41 +00:00
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
/* mixed attributes always follow the first bio */
if (req->cmd_flags & REQ_MIXED_MERGE) {
req->cmd_flags &= ~REQ_FAILFAST_MASK;
req->cmd_flags |= req->bio->bi_rw & REQ_FAILFAST_MASK;
}
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:41 +00:00
/*
* If total number of sectors is less than the first segment
* size, something has gone terribly wrong.
*/
if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
blk_dump_rq_flags(req, "request botched");
req->__data_len = blk_rq_cur_bytes(req);
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:41 +00:00
}
/* recalculate the number of segments */
blk_recalc_rq_segments(req);
block: drop request->hard_* and *nr_sectors struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-05-07 13:24:41 +00:00
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
return true;
}
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
EXPORT_SYMBOL_GPL(blk_update_request);
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
static bool blk_update_bidi_request(struct request *rq, int error,
unsigned int nr_bytes,
unsigned int bidi_bytes)
{
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
if (blk_update_request(rq, error, nr_bytes))
return true;
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
/* Bidi request must be completed as a whole */
if (unlikely(blk_bidi_rq(rq)) &&
blk_update_request(rq->next_rq, error, bidi_bytes))
return true;
if (blk_queue_add_random(rq->q))
add_disk_randomness(rq->rq_disk);
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
return false;
}
/**
* blk_unprep_request - unprepare a request
* @req: the request
*
* This function makes a request ready for complete resubmission (or
* completion). It happens only after all error handling is complete,
* so represents the appropriate moment to deallocate any resources
* that were allocated to the request in the prep_rq_fn. The queue
* lock is held when calling this.
*/
void blk_unprep_request(struct request *req)
{
struct request_queue *q = req->q;
req->cmd_flags &= ~REQ_DONTPREP;
if (q->unprep_rq_fn)
q->unprep_rq_fn(q, req);
}
EXPORT_SYMBOL_GPL(blk_unprep_request);
/*
* queue lock must be held
*/
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
static void blk_finish_request(struct request *req, int error)
{
if (blk_rq_tagged(req))
blk_queue_end_tag(req->q, req);
BUG_ON(blk_queued_rq(req));
if (unlikely(laptop_mode) && req->cmd_type == REQ_TYPE_FS)
laptop_io_completion(&req->q->backing_dev_info);
blk_delete_timer(req);
if (req->cmd_flags & REQ_DONTPREP)
blk_unprep_request(req);
blk_account_io_done(req);
if (req->end_io)
req->end_io(req, error);
else {
if (blk_bidi_rq(req))
__blk_put_request(req->next_rq->q, req->next_rq);
__blk_put_request(req->q, req);
}
}
/**
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
* blk_end_bidi_request - Complete a bidi request
* @rq: the request to complete
* @error: %0 for success, < %0 for error
* @nr_bytes: number of bytes to complete @rq
* @bidi_bytes: number of bytes to complete @rq->next_rq
*
* Description:
* Ends I/O on a number of bytes attached to @rq and @rq->next_rq.
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
* Drivers that supports bidi can safely call this member for any
* type of request, bidi or uni. In the later case @bidi_bytes is
* just ignored.
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
*
* Return:
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
* %false - we are done with this request
* %true - still buffers pending for this request
**/
static bool blk_end_bidi_request(struct request *rq, int error,
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
unsigned int nr_bytes, unsigned int bidi_bytes)
{
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
struct request_queue *q = rq->q;
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
unsigned long flags;
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
return true;
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
spin_lock_irqsave(q->queue_lock, flags);
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
blk_finish_request(rq, error);
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
spin_unlock_irqrestore(q->queue_lock, flags);
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
return false;
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
}
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
/**
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
* __blk_end_bidi_request - Complete a bidi request with queue lock held
* @rq: the request to complete
* @error: %0 for success, < %0 for error
* @nr_bytes: number of bytes to complete @rq
* @bidi_bytes: number of bytes to complete @rq->next_rq
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
*
* Description:
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
* Identical to blk_end_bidi_request() except that queue lock is
* assumed to be locked on entry and remains so on return.
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
*
* Return:
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
* %false - we are done with this request
* %true - still buffers pending for this request
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
**/
block: fix flush machinery for stacking drivers with differring flush flags Commit ae1b1539622fb46e51b4d13b3f9e5f4c713f86ae, block: reimplement FLUSH/FUA to support merge, introduced a performance regression when running any sort of fsyncing workload using dm-multipath and certain storage (in our case, an HP EVA). The test I ran was fs_mark, and it dropped from ~800 files/sec on ext4 to ~100 files/sec. It turns out that dm-multipath always advertised flush+fua support, and passed commands on down the stack, where those flags used to get stripped off. The above commit changed that behavior: static inline struct request *__elv_next_request(struct request_queue *q) { struct request *rq; while (1) { - while (!list_empty(&q->queue_head)) { + if (!list_empty(&q->queue_head)) { rq = list_entry_rq(q->queue_head.next); - if (!(rq->cmd_flags & (REQ_FLUSH | REQ_FUA)) || - (rq->cmd_flags & REQ_FLUSH_SEQ)) - return rq; - rq = blk_do_flush(q, rq); - if (rq) - return rq; + return rq; } Note that previously, a command would come in here, have REQ_FLUSH|REQ_FUA set, and then get handed off to blk_do_flush: struct request *blk_do_flush(struct request_queue *q, struct request *rq) { unsigned int fflags = q->flush_flags; /* may change, cache it */ bool has_flush = fflags & REQ_FLUSH, has_fua = fflags & REQ_FUA; bool do_preflush = has_flush && (rq->cmd_flags & REQ_FLUSH); bool do_postflush = has_flush && !has_fua && (rq->cmd_flags & REQ_FUA); unsigned skip = 0; ... if (blk_rq_sectors(rq) && !do_preflush && !do_postflush) { rq->cmd_flags &= ~REQ_FLUSH; if (!has_fua) rq->cmd_flags &= ~REQ_FUA; return rq; } So, the flush machinery was bypassed in such cases (q->flush_flags == 0 && rq->cmd_flags & (REQ_FLUSH|REQ_FUA)). Now, however, we don't get into the flush machinery at all. Instead, __elv_next_request just hands a request with flush and fua bits set to the scsi_request_fn, even if the underlying request_queue does not support flush or fua. The agreed upon approach is to fix the flush machinery to allow stacking. While this isn't used in practice (since there is only one request-based dm target, and that target will now reflect the flush flags of the underlying device), it does future-proof the solution, and make it function as designed. In order to make this work, I had to add a field to the struct request, inside the flush structure (to store the original req->end_io). Shaohua had suggested overloading the union with rb_node and completion_data, but the completion data is used by device mapper and can also be used by other drivers. So, I didn't see a way around the additional field. I tested this patch on an HP EVA with both ext4 and xfs, and it recovers the lost performance. Comments and other testers, as always, are appreciated. Cheers, Jeff Signed-off-by: Jeff Moyer <jmoyer@redhat.com> Acked-by: Tejun Heo <tj@kernel.org> Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
2011-08-15 19:37:25 +00:00
bool __blk_end_bidi_request(struct request *rq, int error,
unsigned int nr_bytes, unsigned int bidi_bytes)
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
{
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes))
return true;
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
blk_finish_request(rq, error);
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
block: clean up request completion API Request completion has gone through several changes and became a bit messy over the time. Clean it up. 1. end_that_request_data() is a thin wrapper around end_that_request_data_first() which checks whether bio is NULL before doing anything and handles bidi completion. blk_update_request() is a thin wrapper around end_that_request_data() which clears nr_sectors on the last iteration but doesn't use the bidi completion. Clean it up by moving the initial bio NULL check and nr_sectors clearing on the last iteration into end_that_request_data() and renaming it to blk_update_request(), which makes blk_end_io() the only user of end_that_request_data(). Collapse end_that_request_data() into blk_end_io(). 2. There are four visible completion variants - blk_end_request(), __blk_end_request(), blk_end_bidi_request() and end_request(). blk_end_request() and blk_end_bidi_request() uses blk_end_request() as the backend but __blk_end_request() and end_request() use separate implementation in __blk_end_request() due to different locking rules. blk_end_bidi_request() is identical to blk_end_io(). Collapse blk_end_io() into blk_end_bidi_request(), separate out request update into internal helper blk_update_bidi_request() and add __blk_end_bidi_request(). Redefine [__]blk_end_request() as thin inline wrappers around [__]blk_end_bidi_request(). 3. As the whole request issue/completion usages are about to be modified and audited, it's a good chance to convert completion functions return bool which better indicates the intended meaning of return values. 4. The function name end_that_request_last() is from the days when it was a public interface and slighly confusing. Give it a proper internal name - blk_finish_request(). 5. Add description explaning that blk_end_bidi_request() can be safely used for uni requests as suggested by Boaz Harrosh. The only visible behavior change is from #1. nr_sectors counts are cleared after the final iteration no matter which function is used to complete the request. I couldn't find any place where the code assumes those nr_sectors counters contain the values for the last segment and this change is good as it makes the API much more consistent as the end result is now same whether a request is completed using [__]blk_end_request() alone or in combination with blk_update_request(). API further cleaned up per Christoph's suggestion. [ Impact: cleanup, rq->*nr_sectors always updated after req completion ] Signed-off-by: Tejun Heo <tj@kernel.org> Reviewed-by: Boaz Harrosh <bharrosh@panasas.com> Cc: Christoph Hellwig <hch@infradead.org>
2009-04-23 02:05:18 +00:00
return false;
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
}
/**
* blk_end_request - Helper function for drivers to complete the request.
* @rq: the request being processed
* @error: %0 for success, < %0 for error
* @nr_bytes: number of bytes to complete
*
* Description:
* Ends I/O on a number of bytes attached to @rq.
* If @rq has leftover, sets it up for the next range of segments.
*
* Return:
* %false - we are done with this request
* %true - still buffers pending for this request
**/
bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
{
return blk_end_bidi_request(rq, error, nr_bytes, 0);
}
EXPORT_SYMBOL(blk_end_request);
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
/**
* blk_end_request_all - Helper function for drives to finish the request.
* @rq: the request to finish
* @error: %0 for success, < %0 for error
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
*
* Description:
* Completely finish @rq.
*/
void blk_end_request_all(struct request *rq, int error)
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
{
bool pending;
unsigned int bidi_bytes = 0;
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
if (unlikely(blk_bidi_rq(rq)))
bidi_bytes = blk_rq_bytes(rq->next_rq);
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
BUG_ON(pending);
}
EXPORT_SYMBOL(blk_end_request_all);
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
/**
* blk_end_request_cur - Helper function to finish the current request chunk.
* @rq: the request to finish the current chunk for
* @error: %0 for success, < %0 for error
*
* Description:
* Complete the current consecutively mapped chunk from @rq.
*
* Return:
* %false - we are done with this request
* %true - still buffers pending for this request
*/
bool blk_end_request_cur(struct request *rq, int error)
{
return blk_end_request(rq, error, blk_rq_cur_bytes(rq));
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
}
EXPORT_SYMBOL(blk_end_request_cur);
blk_end_request: add new request completion interface (take 4) This patch adds 2 new interfaces for request completion: o blk_end_request() : called without queue lock o __blk_end_request() : called with queue lock held blk_end_request takes 'error' as an argument instead of 'uptodate', which current end_that_request_* take. The meanings of values are below and the value is used when bio is completed. 0 : success < 0 : error Some device drivers call some generic functions below between end_that_request_{first/chunk} and end_that_request_last(). o add_disk_randomness() o blk_queue_end_tag() o blkdev_dequeue_request() These are called in the blk_end_request interfaces as a part of generic request completion. So all device drivers become to call above functions. To decide whether to call blkdev_dequeue_request(), blk_end_request uses list_empty(&rq->queuelist) (blk_queued_rq() macro is added for it). So drivers must re-initialize it using list_init() or so before calling blk_end_request if drivers use it for its specific purpose. (Currently, there is no driver which completes request without re-initializing the queuelist after used it. So rq->queuelist can be used for the purpose above.) "Normal" drivers can be converted to use blk_end_request() in a standard way shown below. a) end_that_request_{chunk/first} spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() b) spin_lock_irqsave() end_that_request_{chunk/first} (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => spin_lock_irqsave() __blk_end_request() spin_unlock_irqsave() c) spin_lock_irqsave() (add_disk_randomness(), blk_queue_end_tag(), blkdev_dequeue_request()) end_that_request_last() spin_unlock_irqrestore() => blk_end_request() or spin_lock_irqsave() __blk_end_request() spin_unlock_irqrestore() Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2007-12-11 22:40:30 +00:00
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_end_request_err - Finish a request till the next failure boundary.
* @rq: the request to finish till the next failure boundary for
* @error: must be negative errno
*
* Description:
* Complete @rq till the next failure boundary.
*
* Return:
* %false - we are done with this request
* %true - still buffers pending for this request
*/
bool blk_end_request_err(struct request *rq, int error)
{
WARN_ON(error >= 0);
return blk_end_request(rq, error, blk_rq_err_bytes(rq));
}
EXPORT_SYMBOL_GPL(blk_end_request_err);
/**
* __blk_end_request - Helper function for drivers to complete the request.
* @rq: the request being processed
* @error: %0 for success, < %0 for error
* @nr_bytes: number of bytes to complete
*
* Description:
* Must be called with queue lock held unlike blk_end_request().
*
* Return:
* %false - we are done with this request
* %true - still buffers pending for this request
**/
bool __blk_end_request(struct request *rq, int error, unsigned int nr_bytes)
{
return __blk_end_bidi_request(rq, error, nr_bytes, 0);
}
EXPORT_SYMBOL(__blk_end_request);
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
/**
* __blk_end_request_all - Helper function for drives to finish the request.
* @rq: the request to finish
* @error: %0 for success, < %0 for error
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
*
* Description:
* Completely finish @rq. Must be called with queue lock held.
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
*/
void __blk_end_request_all(struct request *rq, int error)
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
{
bool pending;
unsigned int bidi_bytes = 0;
if (unlikely(blk_bidi_rq(rq)))
bidi_bytes = blk_rq_bytes(rq->next_rq);
pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes);
BUG_ON(pending);
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
}
EXPORT_SYMBOL(__blk_end_request_all);
block: add request update interface This patch adds blk_update_request(), which updates struct request with completing its data part, but doesn't complete the struct request itself. Though it looks like end_that_request_first() of older kernels, blk_update_request() should be used only by request stacking drivers. Request-based dm will use it in bio->bi_end_io callback to update the original request when a data part of a cloned request completes. Followings are additional background information of why request-based dm needs this interface. - Request stacking drivers can't use blk_end_request() directly from the lower driver's completion context (bio->bi_end_io or rq->end_io), because some device drivers (e.g. ide) may try to complete their request with queue lock held, and it may cause deadlock. See below for detailed description of possible deadlock: <http://marc.info/?l=linux-kernel&m=120311479108569&w=2> - To solve that, request-based dm offloads the completion of cloned struct request to softirq context (i.e. using blk_complete_request() from rq->end_io). - Though it is possible to use the same solution from bio->bi_end_io, it will delay the notification of bio completion to the original submitter. Also, it will cause inefficient partial completion, because the lower driver can't perform the cloned request anymore and request-based dm needs to requeue and redispatch it to the lower driver again later. That's not good. - So request-based dm needs blk_update_request() to perform the bio completion in the lower driver's completion context, which is more efficient. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-09-18 14:45:09 +00:00
/**
* __blk_end_request_cur - Helper function to finish the current request chunk.
* @rq: the request to finish the current chunk for
* @error: %0 for success, < %0 for error
*
* Description:
* Complete the current consecutively mapped chunk from @rq. Must
* be called with queue lock held.
*
* Return:
* %false - we are done with this request
* %true - still buffers pending for this request
*/
bool __blk_end_request_cur(struct request *rq, int error)
{
return __blk_end_request(rq, error, blk_rq_cur_bytes(rq));
}
EXPORT_SYMBOL(__blk_end_request_cur);
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_end_request_err - Finish a request till the next failure boundary.
* @rq: the request to finish till the next failure boundary for
* @error: must be negative errno
*
* Description:
* Complete @rq till the next failure boundary. Must be called
* with queue lock held.
*
* Return:
* %false - we are done with this request
* %true - still buffers pending for this request
*/
bool __blk_end_request_err(struct request *rq, int error)
{
WARN_ON(error >= 0);
return __blk_end_request(rq, error, blk_rq_err_bytes(rq));
}
EXPORT_SYMBOL_GPL(__blk_end_request_err);
void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
struct bio *bio)
{
/* Bit 0 (R/W) is identical in rq->cmd_flags and bio->bi_rw */
rq->cmd_flags |= bio->bi_rw & REQ_WRITE;
if (bio_has_data(bio)) {
rq->nr_phys_segments = bio_phys_segments(q, bio);
rq->buffer = bio_data(bio);
}
rq->__data_len = bio->bi_size;
rq->bio = rq->biotail = bio;
if (bio->bi_bdev)
rq->rq_disk = bio->bi_bdev->bd_disk;
}
#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
/**
* rq_flush_dcache_pages - Helper function to flush all pages in a request
* @rq: the request to be flushed
*
* Description:
* Flush all pages in @rq.
*/
void rq_flush_dcache_pages(struct request *rq)
{
struct req_iterator iter;
struct bio_vec *bvec;
rq_for_each_segment(bvec, rq, iter)
flush_dcache_page(bvec->bv_page);
}
EXPORT_SYMBOL_GPL(rq_flush_dcache_pages);
#endif
block: add lld busy state exporting interface This patch adds an new interface, blk_lld_busy(), to check lld's busy state from the block layer. blk_lld_busy() calls down into low-level drivers for the checking if the drivers set q->lld_busy_fn() using blk_queue_lld_busy(). This resolves a performance problem on request stacking devices below. Some drivers like scsi mid layer stop dispatching request when they detect busy state on its low-level device like host/target/device. It allows other requests to stay in the I/O scheduler's queue for a chance of merging. Request stacking drivers like request-based dm should follow the same logic. However, there is no generic interface for the stacked device to check if the underlying device(s) are busy. If the request stacking driver dispatches and submits requests to the busy underlying device, the requests will stay in the underlying device's queue without a chance of merging. This causes performance problem on burst I/O load. With this patch, busy state of the underlying device is exported via q->lld_busy_fn(). So the request stacking driver can check it and stop dispatching requests if busy. The underlying device driver must return the busy state appropriately: 1: when the device driver can't process requests immediately. 0: when the device driver can process requests immediately, including abnormal situations where the device driver needs to kill all requests. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2008-10-01 14:12:15 +00:00
/**
* blk_lld_busy - Check if underlying low-level drivers of a device are busy
* @q : the queue of the device being checked
*
* Description:
* Check if underlying low-level drivers of a device are busy.
* If the drivers want to export their busy state, they must set own
* exporting function using blk_queue_lld_busy() first.
*
* Basically, this function is used only by request stacking drivers
* to stop dispatching requests to underlying devices when underlying
* devices are busy. This behavior helps more I/O merging on the queue
* of the request stacking driver and prevents I/O throughput regression
* on burst I/O load.
*
* Return:
* 0 - Not busy (The request stacking driver should dispatch request)
* 1 - Busy (The request stacking driver should stop dispatching request)
*/
int blk_lld_busy(struct request_queue *q)
{
if (q->lld_busy_fn)
return q->lld_busy_fn(q);
return 0;
}
EXPORT_SYMBOL_GPL(blk_lld_busy);
block: add request clone interface (v2) This patch adds the following 2 interfaces for request-stacking drivers: - blk_rq_prep_clone(struct request *clone, struct request *orig, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio*, void *), void *data) * Clones bios in the original request to the clone request (bio_ctr is called for each cloned bios.) * Copies attributes of the original request to the clone request. The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied. - blk_rq_unprep_clone(struct request *clone) * Frees cloned bios from the clone request. Request stacking drivers (e.g. request-based dm) need to make a clone request for a submitted request and dispatch it to other devices. To allocate request for the clone, request stacking drivers may not be able to use blk_get_request() because the allocation may be done in an irq-disabled context. So blk_rq_prep_clone() takes a request allocated by the caller as an argument. For each clone bio in the clone request, request stacking drivers should be able to set up their own completion handler. So blk_rq_prep_clone() takes a callback function which is called for each clone bio, and a pointer for private data which is passed to the callback. NOTE: blk_rq_prep_clone() doesn't copy any actual data of the original request. Pages are shared between original bios and cloned bios. So caller must not complete the original request before the clone request. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-06-11 11:10:16 +00:00
/**
* blk_rq_unprep_clone - Helper function to free all bios in a cloned request
* @rq: the clone request to be cleaned up
*
* Description:
* Free all bios in @rq for a cloned request.
*/
void blk_rq_unprep_clone(struct request *rq)
{
struct bio *bio;
while ((bio = rq->bio) != NULL) {
rq->bio = bio->bi_next;
bio_put(bio);
}
}
EXPORT_SYMBOL_GPL(blk_rq_unprep_clone);
/*
* Copy attributes of the original request to the clone request.
* The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied.
*/
static void __blk_rq_prep_clone(struct request *dst, struct request *src)
{
dst->cpu = src->cpu;
dst->cmd_flags = (src->cmd_flags & REQ_CLONE_MASK) | REQ_NOMERGE;
block: add request clone interface (v2) This patch adds the following 2 interfaces for request-stacking drivers: - blk_rq_prep_clone(struct request *clone, struct request *orig, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio*, void *), void *data) * Clones bios in the original request to the clone request (bio_ctr is called for each cloned bios.) * Copies attributes of the original request to the clone request. The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied. - blk_rq_unprep_clone(struct request *clone) * Frees cloned bios from the clone request. Request stacking drivers (e.g. request-based dm) need to make a clone request for a submitted request and dispatch it to other devices. To allocate request for the clone, request stacking drivers may not be able to use blk_get_request() because the allocation may be done in an irq-disabled context. So blk_rq_prep_clone() takes a request allocated by the caller as an argument. For each clone bio in the clone request, request stacking drivers should be able to set up their own completion handler. So blk_rq_prep_clone() takes a callback function which is called for each clone bio, and a pointer for private data which is passed to the callback. NOTE: blk_rq_prep_clone() doesn't copy any actual data of the original request. Pages are shared between original bios and cloned bios. So caller must not complete the original request before the clone request. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-06-11 11:10:16 +00:00
dst->cmd_type = src->cmd_type;
dst->__sector = blk_rq_pos(src);
dst->__data_len = blk_rq_bytes(src);
dst->nr_phys_segments = src->nr_phys_segments;
dst->ioprio = src->ioprio;
dst->extra_len = src->extra_len;
}
/**
* blk_rq_prep_clone - Helper function to setup clone request
* @rq: the request to be setup
* @rq_src: original request to be cloned
* @bs: bio_set that bios for clone are allocated from
* @gfp_mask: memory allocation mask for bio
* @bio_ctr: setup function to be called for each clone bio.
* Returns %0 for success, non %0 for failure.
* @data: private data to be passed to @bio_ctr
*
* Description:
* Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq.
* The actual data parts of @rq_src (e.g. ->cmd, ->buffer, ->sense)
* are not copied, and copying such parts is the caller's responsibility.
* Also, pages which the original bios are pointing to are not copied
* and the cloned bios just point same pages.
* So cloned bios must be completed before original bios, which means
* the caller must complete @rq before @rq_src.
*/
int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
struct bio_set *bs, gfp_t gfp_mask,
int (*bio_ctr)(struct bio *, struct bio *, void *),
void *data)
{
struct bio *bio, *bio_src;
if (!bs)
bs = fs_bio_set;
blk_rq_init(NULL, rq);
__rq_for_each_bio(bio_src, rq_src) {
bio = bio_alloc_bioset(gfp_mask, bio_src->bi_max_vecs, bs);
if (!bio)
goto free_and_out;
__bio_clone(bio, bio_src);
if (bio_integrity(bio_src) &&
bio_integrity_clone(bio, bio_src, gfp_mask, bs))
block: add request clone interface (v2) This patch adds the following 2 interfaces for request-stacking drivers: - blk_rq_prep_clone(struct request *clone, struct request *orig, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio*, void *), void *data) * Clones bios in the original request to the clone request (bio_ctr is called for each cloned bios.) * Copies attributes of the original request to the clone request. The actual data parts (e.g. ->cmd, ->buffer, ->sense) are not copied. - blk_rq_unprep_clone(struct request *clone) * Frees cloned bios from the clone request. Request stacking drivers (e.g. request-based dm) need to make a clone request for a submitted request and dispatch it to other devices. To allocate request for the clone, request stacking drivers may not be able to use blk_get_request() because the allocation may be done in an irq-disabled context. So blk_rq_prep_clone() takes a request allocated by the caller as an argument. For each clone bio in the clone request, request stacking drivers should be able to set up their own completion handler. So blk_rq_prep_clone() takes a callback function which is called for each clone bio, and a pointer for private data which is passed to the callback. NOTE: blk_rq_prep_clone() doesn't copy any actual data of the original request. Pages are shared between original bios and cloned bios. So caller must not complete the original request before the clone request. Signed-off-by: Kiyoshi Ueda <k-ueda@ct.jp.nec.com> Signed-off-by: Jun'ichi Nomura <j-nomura@ce.jp.nec.com> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
2009-06-11 11:10:16 +00:00
goto free_and_out;
if (bio_ctr && bio_ctr(bio, bio_src, data))
goto free_and_out;
if (rq->bio) {
rq->biotail->bi_next = bio;
rq->biotail = bio;
} else
rq->bio = rq->biotail = bio;
}
__blk_rq_prep_clone(rq, rq_src);
return 0;
free_and_out:
if (bio)
bio_free(bio, bs);
blk_rq_unprep_clone(rq);
return -ENOMEM;
}
EXPORT_SYMBOL_GPL(blk_rq_prep_clone);
int kblockd_schedule_work(struct request_queue *q, struct work_struct *work)
{
return queue_work(kblockd_workqueue, work);
}
EXPORT_SYMBOL(kblockd_schedule_work);
int kblockd_schedule_delayed_work(struct request_queue *q,
struct delayed_work *dwork, unsigned long delay)
{
return queue_delayed_work(kblockd_workqueue, dwork, delay);
}
EXPORT_SYMBOL(kblockd_schedule_delayed_work);
#define PLUG_MAGIC 0x91827364
/**
* blk_start_plug - initialize blk_plug and track it inside the task_struct
* @plug: The &struct blk_plug that needs to be initialized
*
* Description:
* Tracking blk_plug inside the task_struct will help with auto-flushing the
* pending I/O should the task end up blocking between blk_start_plug() and
* blk_finish_plug(). This is important from a performance perspective, but
* also ensures that we don't deadlock. For instance, if the task is blocking
* for a memory allocation, memory reclaim could end up wanting to free a
* page belonging to that request that is currently residing in our private
* plug. By flushing the pending I/O when the process goes to sleep, we avoid
* this kind of deadlock.
*/
void blk_start_plug(struct blk_plug *plug)
{
struct task_struct *tsk = current;
plug->magic = PLUG_MAGIC;
INIT_LIST_HEAD(&plug->list);
INIT_LIST_HEAD(&plug->cb_list);
plug->should_sort = 0;
/*
* If this is a nested plug, don't actually assign it. It will be
* flushed on its own.
*/
if (!tsk->plug) {
/*
* Store ordering should not be needed here, since a potential
* preempt will imply a full memory barrier
*/
tsk->plug = plug;
}
}
EXPORT_SYMBOL(blk_start_plug);
static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b)
{
struct request *rqa = container_of(a, struct request, queuelist);
struct request *rqb = container_of(b, struct request, queuelist);
return !(rqa->q <= rqb->q);
}
/*
* If 'from_schedule' is true, then postpone the dispatch of requests
* until a safe kblockd context. We due this to avoid accidental big
* additional stack usage in driver dispatch, in places where the originally
* plugger did not intend it.
*/
static void queue_unplugged(struct request_queue *q, unsigned int depth,
bool from_schedule)
__releases(q->queue_lock)
{
trace_block_unplug(q, depth, !from_schedule);
/*
* Don't mess with dead queue.
*/
if (unlikely(blk_queue_dead(q))) {
spin_unlock(q->queue_lock);
return;
}
/*
* If we are punting this to kblockd, then we can safely drop
* the queue_lock before waking kblockd (which needs to take
* this lock).
*/
if (from_schedule) {
spin_unlock(q->queue_lock);
blk_run_queue_async(q);
} else {
__blk_run_queue(q);
spin_unlock(q->queue_lock);
}
}
static void flush_plug_callbacks(struct blk_plug *plug)
{
LIST_HEAD(callbacks);
if (list_empty(&plug->cb_list))
return;
list_splice_init(&plug->cb_list, &callbacks);
while (!list_empty(&callbacks)) {
struct blk_plug_cb *cb = list_first_entry(&callbacks,
struct blk_plug_cb,
list);
list_del(&cb->list);
cb->callback(cb);
}
}
void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
struct request_queue *q;
unsigned long flags;
struct request *rq;
LIST_HEAD(list);
unsigned int depth;
BUG_ON(plug->magic != PLUG_MAGIC);
flush_plug_callbacks(plug);
if (list_empty(&plug->list))
return;
list_splice_init(&plug->list, &list);
if (plug->should_sort) {
list_sort(NULL, &list, plug_rq_cmp);
plug->should_sort = 0;
}
q = NULL;
depth = 0;
/*
* Save and disable interrupts here, to avoid doing it for every
* queue lock we have to take.
*/
local_irq_save(flags);
while (!list_empty(&list)) {
rq = list_entry_rq(list.next);
list_del_init(&rq->queuelist);
BUG_ON(!rq->q);
if (rq->q != q) {
/*
* This drops the queue lock
*/
if (q)
queue_unplugged(q, depth, from_schedule);
q = rq->q;
depth = 0;
spin_lock(q->queue_lock);
}
/*
* Short-circuit if @q is dead
*/
if (unlikely(blk_queue_dead(q))) {
__blk_end_request_all(rq, -ENODEV);
continue;
}
/*
* rq is already accounted, so use raw insert
*/
if (rq->cmd_flags & (REQ_FLUSH | REQ_FUA))
__elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH);
else
__elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE);
depth++;
}
/*
* This drops the queue lock
*/
if (q)
queue_unplugged(q, depth, from_schedule);
local_irq_restore(flags);
}
void blk_finish_plug(struct blk_plug *plug)
{
blk_flush_plug_list(plug, false);
if (plug == current->plug)
current->plug = NULL;
}
EXPORT_SYMBOL(blk_finish_plug);
int __init blk_dev_init(void)
{
BUILD_BUG_ON(__REQ_NR_BITS > 8 *
sizeof(((struct request *)0)->cmd_flags));
/* used for unplugging and affects IO latency/throughput - HIGHPRI */
kblockd_workqueue = alloc_workqueue("kblockd",
WQ_MEM_RECLAIM | WQ_HIGHPRI, 0);
if (!kblockd_workqueue)
panic("Failed to create kblockd\n");
request_cachep = kmem_cache_create("blkdev_requests",
sizeof(struct request), 0, SLAB_PANIC, NULL);
blk_requestq_cachep = kmem_cache_create("blkdev_queue",
sizeof(struct request_queue), 0, SLAB_PANIC, NULL);
return 0;
}