linux/drivers/md/md-multipath.c

471 lines
12 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* multipath.c : Multiple Devices driver for Linux
*
* Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat
*
* Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman
*
* MULTIPATH management functions.
*
* derived from raid1.c.
*/
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/raid/md_u.h>
#include <linux/seq_file.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include "md.h"
#include "md-multipath.h"
#define MAX_WORK_PER_DISK 128
#define NR_RESERVED_BUFS 32
static int multipath_map (struct mpconf *conf)
{
int i, disks = conf->raid_disks;
/*
* Later we do read balancing on the read side
* now we use the first available disk.
*/
rcu_read_lock();
for (i = 0; i < disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
if (rdev && test_bit(In_sync, &rdev->flags) &&
!test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
return i;
}
}
rcu_read_unlock();
pr_crit_ratelimited("multipath_map(): no more operational IO paths?\n");
return (-1);
}
static void multipath_reschedule_retry (struct multipath_bh *mp_bh)
{
unsigned long flags;
struct mddev *mddev = mp_bh->mddev;
struct mpconf *conf = mddev->private;
spin_lock_irqsave(&conf->device_lock, flags);
list_add(&mp_bh->retry_list, &conf->retry_list);
spin_unlock_irqrestore(&conf->device_lock, flags);
md_wakeup_thread(mddev->thread);
}
/*
* multipath_end_bh_io() is called when we have finished servicing a multipathed
* operation and are ready to return a success/failure code to the buffer
* cache layer.
*/
static void multipath_end_bh_io(struct multipath_bh *mp_bh, blk_status_t status)
{
struct bio *bio = mp_bh->master_bio;
struct mpconf *conf = mp_bh->mddev->private;
bio->bi_status = status;
bio_endio(bio);
mempool_free(mp_bh, &conf->pool);
}
static void multipath_end_request(struct bio *bio)
{
struct multipath_bh *mp_bh = bio->bi_private;
struct mpconf *conf = mp_bh->mddev->private;
struct md_rdev *rdev = conf->multipaths[mp_bh->path].rdev;
if (!bio->bi_status)
multipath_end_bh_io(mp_bh, 0);
else if (!(bio->bi_opf & REQ_RAHEAD)) {
/*
* oops, IO error:
*/
md_error (mp_bh->mddev, rdev);
pr_info("multipath: %pg: rescheduling sector %llu\n",
rdev->bdev,
(unsigned long long)bio->bi_iter.bi_sector);
multipath_reschedule_retry(mp_bh);
} else
multipath_end_bh_io(mp_bh, bio->bi_status);
rdev_dec_pending(rdev, conf->mddev);
}
static bool multipath_make_request(struct mddev *mddev, struct bio * bio)
{
struct mpconf *conf = mddev->private;
struct multipath_bh * mp_bh;
struct multipath_info *multipath;
if (unlikely(bio->bi_opf & REQ_PREFLUSH)
&& md_flush_request(mddev, bio))
return true;
mp_bh = mempool_alloc(&conf->pool, GFP_NOIO);
mp_bh->master_bio = bio;
mp_bh->mddev = mddev;
mp_bh->path = multipath_map(conf);
if (mp_bh->path < 0) {
bio_io_error(bio);
mempool_free(mp_bh, &conf->pool);
return true;
}
multipath = conf->multipaths + mp_bh->path;
bio_init_clone(multipath->rdev->bdev, &mp_bh->bio, bio, GFP_NOIO);
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
mp_bh->bio.bi_iter.bi_sector += multipath->rdev->data_offset;
mp_bh->bio.bi_opf |= REQ_FAILFAST_TRANSPORT;
mp_bh->bio.bi_end_io = multipath_end_request;
mp_bh->bio.bi_private = mp_bh;
mddev_check_write_zeroes(mddev, &mp_bh->bio);
submit_bio_noacct(&mp_bh->bio);
return true;
}
static void multipath_status(struct seq_file *seq, struct mddev *mddev)
{
struct mpconf *conf = mddev->private;
int i;
seq_printf (seq, " [%d/%d] [", conf->raid_disks,
conf->raid_disks - mddev->degraded);
rcu_read_lock();
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev);
seq_printf (seq, "%s", rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
}
rcu_read_unlock();
seq_putc(seq, ']');
}
/*
* Careful, this can execute in IRQ contexts as well!
*/
static void multipath_error (struct mddev *mddev, struct md_rdev *rdev)
{
struct mpconf *conf = mddev->private;
if (conf->raid_disks - mddev->degraded <= 1) {
/*
* Uh oh, we can do nothing if this is our last path, but
* first check if this is a queued request for a device
* which has just failed.
*/
pr_warn("multipath: only one IO path left and IO error.\n");
/* leave it active... it's all we have */
return;
}
/*
* Mark disk as unusable
*/
if (test_and_clear_bit(In_sync, &rdev->flags)) {
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded++;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
set_bit(Faulty, &rdev->flags);
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
pr_err("multipath: IO failure on %pg, disabling IO path.\n"
"multipath: Operation continuing on %d IO paths.\n",
rdev->bdev,
conf->raid_disks - mddev->degraded);
}
static void print_multipath_conf (struct mpconf *conf)
{
int i;
struct multipath_info *tmp;
pr_debug("MULTIPATH conf printout:\n");
if (!conf) {
pr_debug("(conf==NULL)\n");
return;
}
pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
conf->raid_disks);
for (i = 0; i < conf->raid_disks; i++) {
tmp = conf->multipaths + i;
if (tmp->rdev)
pr_debug(" disk%d, o:%d, dev:%pg\n",
i,!test_bit(Faulty, &tmp->rdev->flags),
tmp->rdev->bdev);
}
}
static int multipath_add_disk(struct mddev *mddev, struct md_rdev *rdev)
{
struct mpconf *conf = mddev->private;
int err = -EEXIST;
int path;
struct multipath_info *p;
int first = 0;
int last = mddev->raid_disks - 1;
if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
print_multipath_conf(conf);
for (path = first; path <= last; path++)
if ((p=conf->multipaths+path)->rdev == NULL) {
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
md/raid: only permit hot-add of compatible integrity profiles It is not safe for an integrity profile to be changed while i/o is in-flight in the queue. Prevent adding new disks or otherwise online spares to an array if the device has an incompatible integrity profile. The original change to the blk_integrity_unregister implementation in md, commmit c7bfced9a671 "md: suspend i/o during runtime blk_integrity_unregister" introduced an immediate hang regression. This policy of disallowing changes the integrity profile once one has been established is shared with DM. Here is an abbreviated log from a test run that: 1/ Creates a degraded raid1 with an integrity-enabled device (pmem0s) [ 59.076127] 2/ Tries to add an integrity-disabled device (pmem1m) [ 90.489209] 3/ Retries with an integrity-enabled device (pmem1s) [ 205.671277] [ 59.076127] md/raid1:md0: active with 1 out of 2 mirrors [ 59.078302] md: data integrity enabled on md0 [..] [ 90.489209] md0: incompatible integrity profile for pmem1m [..] [ 205.671277] md: super_written gets error=-5 [ 205.677386] md/raid1:md0: Disk failure on pmem1m, disabling device. [ 205.677386] md/raid1:md0: Operation continuing on 1 devices. [ 205.683037] RAID1 conf printout: [ 205.684699] --- wd:1 rd:2 [ 205.685972] disk 0, wo:0, o:1, dev:pmem0s [ 205.687562] disk 1, wo:1, o:1, dev:pmem1s [ 205.691717] md: recovery of RAID array md0 Fixes: c7bfced9a671 ("md: suspend i/o during runtime blk_integrity_unregister") Cc: <stable@vger.kernel.org> Cc: Mike Snitzer <snitzer@redhat.com> Reported-by: NeilBrown <neilb@suse.com> Signed-off-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: NeilBrown <neilb@suse.com>
2016-01-14 00:00:07 +00:00
err = md_integrity_add_rdev(rdev, mddev);
if (err)
break;
spin_lock_irq(&conf->device_lock);
mddev->degraded--;
rdev->raid_disk = path;
set_bit(In_sync, &rdev->flags);
spin_unlock_irq(&conf->device_lock);
rcu_assign_pointer(p->rdev, rdev);
err = 0;
break;
}
print_multipath_conf(conf);
return err;
}
static int multipath_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
{
struct mpconf *conf = mddev->private;
int err = 0;
int number = rdev->raid_disk;
struct multipath_info *p = conf->multipaths + number;
print_multipath_conf(conf);
if (rdev == p->rdev) {
if (test_bit(In_sync, &rdev->flags) ||
atomic_read(&rdev->nr_pending)) {
pr_warn("hot-remove-disk, slot %d is identified but is still operational!\n", number);
err = -EBUSY;
goto abort;
}
p->rdev = NULL;
if (!test_bit(RemoveSynchronized, &rdev->flags)) {
synchronize_rcu();
if (atomic_read(&rdev->nr_pending)) {
/* lost the race, try later */
err = -EBUSY;
p->rdev = rdev;
goto abort;
}
}
err = md_integrity_register(mddev);
}
abort:
print_multipath_conf(conf);
return err;
}
/*
* This is a kernel thread which:
*
* 1. Retries failed read operations on working multipaths.
* 2. Updates the raid superblock when problems encounter.
* 3. Performs writes following reads for array syncronising.
*/
static void multipathd(struct md_thread *thread)
{
struct mddev *mddev = thread->mddev;
struct multipath_bh *mp_bh;
struct bio *bio;
unsigned long flags;
struct mpconf *conf = mddev->private;
struct list_head *head = &conf->retry_list;
md_check_recovery(mddev);
for (;;) {
spin_lock_irqsave(&conf->device_lock, flags);
if (list_empty(head))
break;
mp_bh = list_entry(head->prev, struct multipath_bh, retry_list);
list_del(head->prev);
spin_unlock_irqrestore(&conf->device_lock, flags);
bio = &mp_bh->bio;
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
bio->bi_iter.bi_sector = mp_bh->master_bio->bi_iter.bi_sector;
if ((mp_bh->path = multipath_map (conf))<0) {
pr_err("multipath: %pg: unrecoverable IO read error for block %llu\n",
bio->bi_bdev,
(unsigned long long)bio->bi_iter.bi_sector);
multipath_end_bh_io(mp_bh, BLK_STS_IOERR);
} else {
pr_err("multipath: %pg: redirecting sector %llu to another IO path\n",
bio->bi_bdev,
(unsigned long long)bio->bi_iter.bi_sector);
*bio = *(mp_bh->master_bio);
block: Abstract out bvec iterator Immutable biovecs are going to require an explicit iterator. To implement immutable bvecs, a later patch is going to add a bi_bvec_done member to this struct; for now, this patch effectively just renames things. Signed-off-by: Kent Overstreet <kmo@daterainc.com> Cc: Jens Axboe <axboe@kernel.dk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: "Ed L. Cashin" <ecashin@coraid.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Lars Ellenberg <drbd-dev@lists.linbit.com> Cc: Jiri Kosina <jkosina@suse.cz> Cc: Matthew Wilcox <willy@linux.intel.com> Cc: Geoff Levand <geoff@infradead.org> Cc: Yehuda Sadeh <yehuda@inktank.com> Cc: Sage Weil <sage@inktank.com> Cc: Alex Elder <elder@inktank.com> Cc: ceph-devel@vger.kernel.org Cc: Joshua Morris <josh.h.morris@us.ibm.com> Cc: Philip Kelleher <pjk1939@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Neil Brown <neilb@suse.de> Cc: Alasdair Kergon <agk@redhat.com> Cc: Mike Snitzer <snitzer@redhat.com> Cc: dm-devel@redhat.com Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: linux390@de.ibm.com Cc: Boaz Harrosh <bharrosh@panasas.com> Cc: Benny Halevy <bhalevy@tonian.com> Cc: "James E.J. Bottomley" <JBottomley@parallels.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: "Nicholas A. Bellinger" <nab@linux-iscsi.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Chris Mason <chris.mason@fusionio.com> Cc: "Theodore Ts'o" <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Jaegeuk Kim <jaegeuk.kim@samsung.com> Cc: Steven Whitehouse <swhiteho@redhat.com> Cc: Dave Kleikamp <shaggy@kernel.org> Cc: Joern Engel <joern@logfs.org> Cc: Prasad Joshi <prasadjoshi.linux@gmail.com> Cc: Trond Myklebust <Trond.Myklebust@netapp.com> Cc: KONISHI Ryusuke <konishi.ryusuke@lab.ntt.co.jp> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <jlbec@evilplan.org> Cc: Ben Myers <bpm@sgi.com> Cc: xfs@oss.sgi.com Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Len Brown <len.brown@intel.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Herton Ronaldo Krzesinski <herton.krzesinski@canonical.com> Cc: Ben Hutchings <ben@decadent.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Guo Chao <yan@linux.vnet.ibm.com> Cc: Tejun Heo <tj@kernel.org> Cc: Asai Thambi S P <asamymuthupa@micron.com> Cc: Selvan Mani <smani@micron.com> Cc: Sam Bradshaw <sbradshaw@micron.com> Cc: Wei Yongjun <yongjun_wei@trendmicro.com.cn> Cc: "Roger Pau Monné" <roger.pau@citrix.com> Cc: Jan Beulich <jbeulich@suse.com> Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com> Cc: Ian Campbell <Ian.Campbell@citrix.com> Cc: Sebastian Ott <sebott@linux.vnet.ibm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Nitin Gupta <ngupta@vflare.org> Cc: Jerome Marchand <jmarchand@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Peng Tao <tao.peng@emc.com> Cc: Andy Adamson <andros@netapp.com> Cc: fanchaoting <fanchaoting@cn.fujitsu.com> Cc: Jie Liu <jeff.liu@oracle.com> Cc: Sunil Mushran <sunil.mushran@gmail.com> Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Namjae Jeon <namjae.jeon@samsung.com> Cc: Pankaj Kumar <pankaj.km@samsung.com> Cc: Dan Magenheimer <dan.magenheimer@oracle.com> Cc: Mel Gorman <mgorman@suse.de>6
2013-10-11 22:44:27 +00:00
bio->bi_iter.bi_sector +=
conf->multipaths[mp_bh->path].rdev->data_offset;
bio_set_dev(bio, conf->multipaths[mp_bh->path].rdev->bdev);
bio->bi_opf |= REQ_FAILFAST_TRANSPORT;
bio->bi_end_io = multipath_end_request;
bio->bi_private = mp_bh;
submit_bio_noacct(bio);
}
}
spin_unlock_irqrestore(&conf->device_lock, flags);
}
static sector_t multipath_size(struct mddev *mddev, sector_t sectors, int raid_disks)
{
WARN_ONCE(sectors || raid_disks,
"%s does not support generic reshape\n", __func__);
return mddev->dev_sectors;
}
static int multipath_run (struct mddev *mddev)
{
struct mpconf *conf;
int disk_idx;
struct multipath_info *disk;
struct md_rdev *rdev;
int working_disks;
int ret;
if (md_check_no_bitmap(mddev))
return -EINVAL;
if (mddev->level != LEVEL_MULTIPATH) {
pr_warn("multipath: %s: raid level not set to multipath IO (%d)\n",
mdname(mddev), mddev->level);
goto out;
}
/*
* copy the already verified devices into our private MULTIPATH
* bookkeeping area. [whatever we allocate in multipath_run(),
* should be freed in multipath_free()]
*/
conf = kzalloc(sizeof(struct mpconf), GFP_KERNEL);
mddev->private = conf;
if (!conf)
goto out;
treewide: kzalloc() -> kcalloc() The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 21:03:40 +00:00
conf->multipaths = kcalloc(mddev->raid_disks,
sizeof(struct multipath_info),
GFP_KERNEL);
if (!conf->multipaths)
goto out_free_conf;
working_disks = 0;
rdev_for_each(rdev, mddev) {
disk_idx = rdev->raid_disk;
if (disk_idx < 0 ||
disk_idx >= mddev->raid_disks)
continue;
disk = conf->multipaths + disk_idx;
disk->rdev = rdev;
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
if (!test_bit(Faulty, &rdev->flags))
working_disks++;
}
conf->raid_disks = mddev->raid_disks;
conf->mddev = mddev;
spin_lock_init(&conf->device_lock);
INIT_LIST_HEAD(&conf->retry_list);
if (!working_disks) {
pr_warn("multipath: no operational IO paths for %s\n",
mdname(mddev));
goto out_free_conf;
}
mddev->degraded = conf->raid_disks - working_disks;
ret = mempool_init_kmalloc_pool(&conf->pool, NR_RESERVED_BUFS,
sizeof(struct multipath_bh));
if (ret)
goto out_free_conf;
mddev->thread = md_register_thread(multipathd, mddev,
"multipath");
if (!mddev->thread)
goto out_free_conf;
pr_info("multipath: array %s active with %d out of %d IO paths\n",
mdname(mddev), conf->raid_disks - mddev->degraded,
mddev->raid_disks);
/*
* Ok, everything is just fine now
*/
md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
if (md_integrity_register(mddev))
goto out_free_conf;
return 0;
out_free_conf:
mempool_exit(&conf->pool);
kfree(conf->multipaths);
kfree(conf);
mddev->private = NULL;
out:
return -EIO;
}
static void multipath_free(struct mddev *mddev, void *priv)
{
struct mpconf *conf = priv;
mempool_exit(&conf->pool);
kfree(conf->multipaths);
kfree(conf);
}
static struct md_personality multipath_personality =
{
.name = "multipath",
.level = LEVEL_MULTIPATH,
.owner = THIS_MODULE,
.make_request = multipath_make_request,
.run = multipath_run,
.free = multipath_free,
.status = multipath_status,
.error_handler = multipath_error,
.hot_add_disk = multipath_add_disk,
.hot_remove_disk= multipath_remove_disk,
.size = multipath_size,
};
static int __init multipath_init (void)
{
return register_md_personality (&multipath_personality);
}
static void __exit multipath_exit (void)
{
unregister_md_personality (&multipath_personality);
}
module_init(multipath_init);
module_exit(multipath_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("simple multi-path personality for MD (deprecated)");
MODULE_ALIAS("md-personality-7"); /* MULTIPATH */
MODULE_ALIAS("md-multipath");
MODULE_ALIAS("md-level--4");