diff options
| author | Jens Axboe <axboe@kernel.dk> | 2023-12-19 15:49:23 -0700 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2023-12-19 15:49:23 -0700 |
| commit | 0bd7c5d802586e9d86c09f79cbf5ca8fdbec57ec (patch) | |
| tree | 807c626d7453819a1fbc77a43834216a520af517 | |
| parent | 4c434392c4777881d01beada6701eff8c76b43fe (diff) | |
| parent | 415c7451872b0d037760795edd3961eaa63276ea (diff) | |
| download | linux-0bd7c5d802586e9d86c09f79cbf5ca8fdbec57ec.tar.gz linux-0bd7c5d802586e9d86c09f79cbf5ca8fdbec57ec.tar.bz2 linux-0bd7c5d802586e9d86c09f79cbf5ca8fdbec57ec.zip | |
Merge tag 'md-next-20231219' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md into for-6.8/block
Pull MD updates from Song:
"1. Remove deprecated flavors, by Song Liu;
2. raid1 read error check support, by Li Nan;
3. Better handle events off-by-1 case, by Alex Lyakas."
* tag 'md-next-20231219' of https://git.kernel.org/pub/scm/linux/kernel/git/song/md:
md: Remove deprecated CONFIG_MD_FAULTY
md: Remove deprecated CONFIG_MD_MULTIPATH
md: Remove deprecated CONFIG_MD_LINEAR
md/raid1: support read error check
md: factor out a helper exceed_read_errors() to check read_errors
md: Whenassemble the array, consult the superblock of the freshest device
md/raid1: remove unnecessary null checking
| -rw-r--r-- | drivers/md/Kconfig | 34 | ||||
| -rw-r--r-- | drivers/md/Makefile | 10 | ||||
| -rw-r--r-- | drivers/md/md-autodetect.c | 8 | ||||
| -rw-r--r-- | drivers/md/md-faulty.c | 365 | ||||
| -rw-r--r-- | drivers/md/md-linear.c | 318 | ||||
| -rw-r--r-- | drivers/md/md-multipath.c | 463 | ||||
| -rw-r--r-- | drivers/md/md.c | 239 | ||||
| -rw-r--r-- | drivers/md/raid1-10.c | 54 | ||||
| -rw-r--r-- | drivers/md/raid1.c | 20 | ||||
| -rw-r--r-- | drivers/md/raid10.c | 49 | ||||
| -rw-r--r-- | include/uapi/linux/raid/md_p.h | 8 | ||||
| -rw-r--r-- | include/uapi/linux/raid/md_u.h | 11 |
12 files changed, 201 insertions, 1378 deletions
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index 2a8b081bce7d..f6dc2acdf1ed 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -61,19 +61,6 @@ config MD_BITMAP_FILE various kernel APIs and can only work with files on a file system not actually sitting on the MD device. -config MD_LINEAR - tristate "Linear (append) mode (deprecated)" - depends on BLK_DEV_MD - help - If you say Y here, then your multiple devices driver will be able to - use the so-called linear mode, i.e. it will combine the hard disk - partitions by simply appending one to the other. - - To compile this as a module, choose M here: the module - will be called linear. - - If unsure, say Y. - config MD_RAID0 tristate "RAID-0 (striping) mode" depends on BLK_DEV_MD @@ -172,27 +159,6 @@ config MD_RAID456 If unsure, say Y. -config MD_MULTIPATH - tristate "Multipath I/O support (deprecated)" - depends on BLK_DEV_MD - help - MD_MULTIPATH provides a simple multi-path personality for use - the MD framework. It is not under active development. New - projects should consider using DM_MULTIPATH which has more - features and more testing. - - If unsure, say N. - -config MD_FAULTY - tristate "Faulty test module for MD (deprecated)" - depends on BLK_DEV_MD - help - The "faulty" module allows for a block device that occasionally returns - read or write errors. It is useful for testing. - - In unsure, say N. - - config MD_CLUSTER tristate "Cluster Support for MD" depends on BLK_DEV_MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 84291e38dca8..027d7cfeca3f 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -29,22 +29,16 @@ dm-zoned-y += dm-zoned-target.o dm-zoned-metadata.o dm-zoned-reclaim.o md-mod-y += md.o md-bitmap.o raid456-y += raid5.o raid5-cache.o raid5-ppl.o -linear-y += md-linear.o -multipath-y += md-multipath.o -faulty-y += md-faulty.o # Note: link order is important. All raid personalities -# and must come before md.o, as they each initialise -# themselves, and md.o may use the personalities when it +# and must come before md.o, as they each initialise +# themselves, and md.o may use the personalities when it # auto-initialised. -obj-$(CONFIG_MD_LINEAR) += linear.o obj-$(CONFIG_MD_RAID0) += raid0.o obj-$(CONFIG_MD_RAID1) += raid1.o obj-$(CONFIG_MD_RAID10) += raid10.o obj-$(CONFIG_MD_RAID456) += raid456.o -obj-$(CONFIG_MD_MULTIPATH) += multipath.o -obj-$(CONFIG_MD_FAULTY) += faulty.o obj-$(CONFIG_MD_CLUSTER) += md-cluster.o obj-$(CONFIG_BCACHE) += bcache/ obj-$(CONFIG_BLK_DEV_MD) += md-mod.o diff --git a/drivers/md/md-autodetect.c b/drivers/md/md-autodetect.c index 4b80165afd23..b2a00f213c2c 100644 --- a/drivers/md/md-autodetect.c +++ b/drivers/md/md-autodetect.c @@ -49,7 +49,6 @@ static int md_setup_ents __initdata; * instead of just one. -- KTK * 18May2000: Added support for persistent-superblock arrays: * md=n,0,factor,fault,device-list uses RAID0 for device n - * md=n,-1,factor,fault,device-list uses LINEAR for device n * md=n,device-list reads a RAID superblock from the devices * elements in device-list are read by name_to_kdev_t so can be * a hex number or something like /dev/hda1 /dev/sdb @@ -88,7 +87,7 @@ static int __init md_setup(char *str) md_setup_ents++; switch (get_option(&str, &level)) { /* RAID level */ case 2: /* could be 0 or -1.. */ - if (level == 0 || level == LEVEL_LINEAR) { + if (level == 0) { if (get_option(&str, &factor) != 2 || /* Chunk Size */ get_option(&str, &fault) != 2) { printk(KERN_WARNING "md: Too few arguments supplied to md=.\n"); @@ -96,10 +95,7 @@ static int __init md_setup(char *str) } md_setup_args[ent].level = level; md_setup_args[ent].chunk = 1 << (factor+12); - if (level == LEVEL_LINEAR) - pername = "linear"; - else - pername = "raid0"; + pername = "raid0"; break; } fallthrough; diff --git a/drivers/md/md-faulty.c b/drivers/md/md-faulty.c deleted file mode 100644 index a039e8e20f55..000000000000 --- a/drivers/md/md-faulty.c +++ /dev/null @@ -1,365 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * faulty.c : Multiple Devices driver for Linux - * - * Copyright (C) 2004 Neil Brown - * - * fautly-device-simulator personality for md - */ - - -/* - * The "faulty" personality causes some requests to fail. - * - * Possible failure modes are: - * reads fail "randomly" but succeed on retry - * writes fail "randomly" but succeed on retry - * reads for some address fail and then persist until a write - * reads for some address fail and then persist irrespective of write - * writes for some address fail and persist - * all writes fail - * - * Different modes can be active at a time, but only - * one can be set at array creation. Others can be added later. - * A mode can be one-shot or recurrent with the recurrence being - * once in every N requests. - * The bottom 5 bits of the "layout" indicate the mode. The - * remainder indicate a period, or 0 for one-shot. - * - * There is an implementation limit on the number of concurrently - * persisting-faulty blocks. When a new fault is requested that would - * exceed the limit, it is ignored. - * All current faults can be clear using a layout of "0". - * - * Requests are always sent to the device. If they are to fail, - * we clone the bio and insert a new b_end_io into the chain. - */ - -#define WriteTransient 0 -#define ReadTransient 1 -#define WritePersistent 2 -#define ReadPersistent 3 -#define WriteAll 4 /* doesn't go to device */ -#define ReadFixable 5 -#define Modes 6 - -#define ClearErrors 31 -#define ClearFaults 30 - -#define AllPersist 100 /* internal use only */ -#define NoPersist 101 - -#define ModeMask 0x1f -#define ModeShift 5 - -#define MaxFault 50 -#include <linux/blkdev.h> -#include <linux/module.h> -#include <linux/raid/md_u.h> -#include <linux/slab.h> -#include "md.h" -#include <linux/seq_file.h> - - -static void faulty_fail(struct bio *bio) -{ - struct bio *b = bio->bi_private; - - b->bi_iter.bi_size = bio->bi_iter.bi_size; - b->bi_iter.bi_sector = bio->bi_iter.bi_sector; - - bio_put(bio); - - bio_io_error(b); -} - -struct faulty_conf { - int period[Modes]; - atomic_t counters[Modes]; - sector_t faults[MaxFault]; - int modes[MaxFault]; - int nfaults; - struct md_rdev *rdev; -}; - -static int check_mode(struct faulty_conf *conf, int mode) -{ - if (conf->period[mode] == 0 && - atomic_read(&conf->counters[mode]) <= 0) - return 0; /* no failure, no decrement */ - - - if (atomic_dec_and_test(&conf->counters[mode])) { - if (conf->period[mode]) - atomic_set(&conf->counters[mode], conf->period[mode]); - return 1; - } - return 0; -} - -static int check_sector(struct faulty_conf *conf, sector_t start, sector_t end, int dir) -{ - /* If we find a ReadFixable sector, we fix it ... */ - int i; - for (i=0; i<conf->nfaults; i++) - if (conf->faults[i] >= start && - conf->faults[i] < end) { - /* found it ... */ - switch (conf->modes[i] * 2 + dir) { - case WritePersistent*2+WRITE: return 1; - case ReadPersistent*2+READ: return 1; - case ReadFixable*2+READ: return 1; - case ReadFixable*2+WRITE: - conf->modes[i] = NoPersist; - return 0; - case AllPersist*2+READ: - case AllPersist*2+WRITE: return 1; - default: - return 0; - } - } - return 0; -} - -static void add_sector(struct faulty_conf *conf, sector_t start, int mode) -{ - int i; - int n = conf->nfaults; - for (i=0; i<conf->nfaults; i++) - if (conf->faults[i] == start) { - switch(mode) { - case NoPersist: conf->modes[i] = mode; return; - case WritePersistent: - if (conf->modes[i] == ReadPersistent || - conf->modes[i] == ReadFixable) - conf->modes[i] = AllPersist; - else - conf->modes[i] = WritePersistent; - return; - case ReadPersistent: - if (conf->modes[i] == WritePersistent) - conf->modes[i] = AllPersist; - else - conf->modes[i] = ReadPersistent; - return; - case ReadFixable: - if (conf->modes[i] == WritePersistent || - conf->modes[i] == ReadPersistent) - conf->modes[i] = AllPersist; - else - conf->modes[i] = ReadFixable; - return; - } - } else if (conf->modes[i] == NoPersist) - n = i; - - if (n >= MaxFault) - return; - conf->faults[n] = start; - conf->modes[n] = mode; - if (conf->nfaults == n) - conf->nfaults = n+1; -} - -static bool faulty_make_request(struct mddev *mddev, struct bio *bio) -{ - struct faulty_conf *conf = mddev->private; - int failit = 0; - - if (bio_data_dir(bio) == WRITE) { - /* write request */ - if (atomic_read(&conf->counters[WriteAll])) { - /* special case - don't decrement, don't submit_bio_noacct, - * just fail immediately - */ - bio_io_error(bio); - return true; - } - - if (check_sector(conf, bio->bi_iter.bi_sector, - bio_end_sector(bio), WRITE)) - failit = 1; - if (check_mode(conf, WritePersistent)) { - add_sector(conf, bio->bi_iter.bi_sector, - WritePersistent); - failit = 1; - } - if (check_mode(conf, WriteTransient)) - failit = 1; - } else { - /* read request */ - if (check_sector(conf, bio->bi_iter.bi_sector, - bio_end_sector(bio), READ)) - failit = 1; - if (check_mode(conf, ReadTransient)) - failit = 1; - if (check_mode(conf, ReadPersistent)) { - add_sector(conf, bio->bi_iter.bi_sector, - ReadPersistent); - failit = 1; - } - if (check_mode(conf, ReadFixable)) { - add_sector(conf, bio->bi_iter.bi_sector, - ReadFixable); - failit = 1; - } - } - - md_account_bio(mddev, &bio); - if (failit) { - struct bio *b = bio_alloc_clone(conf->rdev->bdev, bio, GFP_NOIO, - &mddev->bio_set); - - b->bi_private = bio; - b->bi_end_io = faulty_fail; - bio = b; - } else - bio_set_dev(bio, conf->rdev->bdev); - - submit_bio_noacct(bio); - return true; -} - -static void faulty_status(struct seq_file *seq, struct mddev *mddev) -{ - struct faulty_conf *conf = mddev->private; - int n; - - if ((n=atomic_read(&conf->counters[WriteTransient])) != 0) - seq_printf(seq, " WriteTransient=%d(%d)", - n, conf->period[WriteTransient]); - - if ((n=atomic_read(&conf->counters[ReadTransient])) != 0) - seq_printf(seq, " ReadTransient=%d(%d)", - n, conf->period[ReadTransient]); - - if ((n=atomic_read(&conf->counters[WritePersistent])) != 0) - seq_printf(seq, " WritePersistent=%d(%d)", - n, conf->period[WritePersistent]); - - if ((n=atomic_read(&conf->counters[ReadPersistent])) != 0) - seq_printf(seq, " ReadPersistent=%d(%d)", - n, conf->period[ReadPersistent]); - - - if ((n=atomic_read(&conf->counters[ReadFixable])) != 0) - seq_printf(seq, " ReadFixable=%d(%d)", - n, conf->period[ReadFixable]); - - if ((n=atomic_read(&conf->counters[WriteAll])) != 0) - seq_printf(seq, " WriteAll"); - - seq_printf(seq, " nfaults=%d", conf->nfaults); -} - - -static int faulty_reshape(struct mddev *mddev) -{ - int mode = mddev->new_layout & ModeMask; - int count = mddev->new_layout >> ModeShift; - struct faulty_conf *conf = mddev->private; - - if (mddev->new_layout < 0) - return 0; - - /* new layout */ - if (mode == ClearFaults) - conf->nfaults = 0; - else if (mode == ClearErrors) { - int i; - for (i=0 ; i < Modes ; i++) { - conf->period[i] = 0; - atomic_set(&conf->counters[i], 0); - } - } else if (mode < Modes) { - conf->period[mode] = count; - if (!count) count++; - atomic_set(&conf->counters[mode], count); - } else - return -EINVAL; - mddev->new_layout = -1; - mddev->layout = -1; /* makes sure further changes come through */ - return 0; -} - -static sector_t faulty_size(struct mddev *mddev, sector_t sectors, int raid_disks) -{ - WARN_ONCE(raid_disks, - "%s does not support generic reshape\n", __func__); - - if (sectors == 0) - return mddev->dev_sectors; - - return sectors; -} - -static int faulty_run(struct mddev *mddev) -{ - struct md_rdev *rdev; - int i; - struct faulty_conf *conf; - - if (md_check_no_bitmap(mddev)) - return -EINVAL; - - conf = kmalloc(sizeof(*conf), GFP_KERNEL); - if (!conf) - return -ENOMEM; - - for (i=0; i<Modes; i++) { - atomic_set(&conf->counters[i], 0); - conf->period[i] = 0; - } - conf->nfaults = 0; - - rdev_for_each(rdev, mddev) { - conf->rdev = rdev; - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - } - - md_set_array_sectors(mddev, faulty_size(mddev, 0, 0)); - mddev->private = conf; - - faulty_reshape(mddev); - - return 0; -} - -static void faulty_free(struct mddev *mddev, void *priv) -{ - struct faulty_conf *conf = priv; - - kfree(conf); -} - -static struct md_personality faulty_personality = -{ - .name = "faulty", - .level = LEVEL_FAULTY, - .owner = THIS_MODULE, - .make_request = faulty_make_request, - .run = faulty_run, - .free = faulty_free, - .status = faulty_status, - .check_reshape = faulty_reshape, - .size = faulty_size, -}; - -static int __init raid_init(void) -{ - return register_md_personality(&faulty_personality); -} - -static void raid_exit(void) -{ - unregister_md_personality(&faulty_personality); -} - -module_init(raid_init); -module_exit(raid_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Fault injection personality for MD (deprecated)"); -MODULE_ALIAS("md-personality-10"); /* faulty */ -MODULE_ALIAS("md-faulty"); -MODULE_ALIAS("md-level--5"); diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c deleted file mode 100644 index 8eca7693b793..000000000000 --- a/drivers/md/md-linear.c +++ /dev/null @@ -1,318 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - linear.c : Multiple Devices driver for Linux - Copyright (C) 1994-96 Marc ZYNGIER - <zyngier@ufr-info-p7.ibp.fr> or - <maz@gloups.fdn.fr> - - Linear mode management functions. - -*/ - -#include <linux/blkdev.h> -#include <linux/raid/md_u.h> -#include <linux/seq_file.h> -#include <linux/module.h> -#include <linux/slab.h> -#include <trace/events/block.h> -#include "md.h" -#include "md-linear.h" - -/* - * find which device holds a particular offset - */ -static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) -{ - int lo, mid, hi; - struct linear_conf *conf; - - lo = 0; - hi = mddev->raid_disks - 1; - conf = mddev->private; - - /* - * Binary Search - */ - - while (hi > lo) { - - mid = (hi + lo) / 2; - if (sector < conf->disks[mid].end_sector) - hi = mid; - else - lo = mid + 1; - } - - return conf->disks + lo; -} - -static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks) -{ - struct linear_conf *conf; - sector_t array_sectors; - - conf = mddev->private; - WARN_ONCE(sectors || raid_disks, - "%s does not support generic reshape\n", __func__); - array_sectors = conf->array_sectors; - - return array_sectors; -} - -static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) -{ - struct linear_conf *conf; - struct md_rdev *rdev; - int i, cnt; - - conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL); - if (!conf) - return NULL; - - /* - * conf->raid_disks is copy of mddev->raid_disks. The reason to - * keep a copy of mddev->raid_disks in struct linear_conf is, - * mddev->raid_disks may not be consistent with pointers number of - * conf->disks[] when it is updated in linear_add() and used to - * iterate old conf->disks[] earray in linear_congested(). - * Here conf->raid_disks is always consitent with number of - * pointers in conf->disks[] array, and mddev->private is updated - * with rcu_assign_pointer() in linear_addr(), such race can be - * avoided. - */ - conf->raid_disks = raid_disks; - - cnt = 0; - conf->array_sectors = 0; - - rdev_for_each(rdev, mddev) { - int j = rdev->raid_disk; - struct dev_info *disk = conf->disks + j; - sector_t sectors; - - if (j < 0 || j >= raid_disks || disk->rdev) { - pr_warn("md/linear:%s: disk numbering problem. Aborting!\n", - mdname(mddev)); - goto out; - } - - disk->rdev = rdev; - if (mddev->chunk_sectors) { - sectors = rdev->sectors; - sector_div(sectors, mddev->chunk_sectors); - rdev->sectors = sectors * mddev->chunk_sectors; - } - - disk_stack_limits(mddev->gendisk, rdev->bdev, - rdev->data_offset << 9); - - conf->array_sectors += rdev->sectors; - cnt++; - } - if (cnt != raid_disks) { - pr_warn("md/linear:%s: not enough drives present. Aborting!\n", - mdname(mddev)); - goto out; - } - - /* - * Here we calculate the device offsets. - */ - conf->disks[0].end_sector = conf->disks[0].rdev->sectors; - - for (i = 1; i < raid_disks; i++) - conf->disks[i].end_sector = - conf->disks[i-1].end_sector + - conf->disks[i].rdev->sectors; - - return conf; - -out: - kfree(conf); - return NULL; -} - -static int linear_run (struct mddev *mddev) -{ - struct linear_conf *conf; - int ret; - - if (md_check_no_bitmap(mddev)) - return -EINVAL; - conf = linear_conf(mddev, mddev->raid_disks); - - if (!conf) - return 1; - mddev->private = conf; - md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); - - ret = md_integrity_register(mddev); - if (ret) { - kfree(conf); - mddev->private = NULL; - } - return ret; -} - -static int linear_add(struct mddev *mddev, struct md_rdev *rdev) -{ - /* Adding a drive to a linear array allows the array to grow. - * It is permitted if the new drive has a matching superblock - * already on it, with raid_disk equal to raid_disks. - * It is achieved by creating a new linear_private_data structure - * and swapping it in in-place of the current one. - * The current one is never freed until the array is stopped. - * This avoids races. - */ - struct linear_conf *newconf, *oldconf; - - if (rdev->saved_raid_disk != mddev->raid_disks) - return -EINVAL; - - rdev->raid_disk = rdev->saved_raid_disk; - rdev->saved_raid_disk = -1; - - newconf = linear_conf(mddev,mddev->raid_disks+1); - - if (!newconf) - return -ENOMEM; - - /* newconf->raid_disks already keeps a copy of * the increased - * value of mddev->raid_disks, WARN_ONCE() is just used to make - * sure of this. It is possible that oldconf is still referenced - * in linear_congested(), therefore kfree_rcu() is used to free - * oldconf until no one uses it anymore. - */ - oldconf = rcu_dereference_protected(mddev->private, - lockdep_is_held(&mddev->reconfig_mutex)); - mddev->raid_disks++; - WARN_ONCE(mddev->raid_disks != newconf->raid_disks, - "copied raid_disks doesn't match mddev->raid_disks"); - rcu_assign_pointer(mddev->private, newconf); - md_set_array_sectors(mddev, linear_size(mddev, 0, 0)); - set_capacity_and_notify(mddev->gendisk, mddev->array_sectors); - kfree_rcu(oldconf, rcu); - return 0; -} - -static void linear_free(struct mddev *mddev, void *priv) -{ - struct linear_conf *conf = priv; - - kfree(conf); -} - -static bool linear_make_request(struct mddev *mddev, struct bio *bio) -{ - struct dev_info *tmp_dev; - sector_t start_sector, end_sector, data_offset; - sector_t bio_sector = bio->bi_iter.bi_sector; - - if (unlikely(bio->bi_opf & REQ_PREFLUSH) - && md_flush_request(mddev, bio)) - return true; - - tmp_dev = which_dev(mddev, bio_sector); - start_sector = tmp_dev->end_sector - tmp_dev->rdev->sectors; - end_sector = tmp_dev->end_sector; - data_offset = tmp_dev->rdev->data_offset; - - if (unlikely(bio_sector >= end_sector || - bio_sector < start_sector)) - goto out_of_bounds; - - if (unlikely(is_rdev_broken(tmp_dev->rdev))) { - md_error(mddev, tmp_dev->rdev); - bio_io_error(bio); - return true; - } - - if (unlikely(bio_end_sector(bio) > end_sector)) { - /* This bio crosses a device boundary, so we have to split it */ - struct bio *split = bio_split(bio, end_sector - bio_sector, - GFP_NOIO, &mddev->bio_set); - bio_chain(split, bio); - submit_bio_noacct(bio); - bio = split; - } - - md_account_bio(mddev, &bio); - bio_set_dev(bio, tmp_dev->rdev->bdev); - bio->bi_iter.bi_sector = bio->bi_iter.bi_sector - - start_sector + data_offset; - - if (unlikely((bio_op(bio) == REQ_OP_DISCARD) && - !bdev_max_discard_sectors(bio->bi_bdev))) { - /* Just ignore it */ - bio_endio(bio); - } else { - if (mddev->gendisk) - trace_block_bio_remap(bio, disk_devt(mddev->gendisk), - bio_sector); - mddev_check_write_zeroes(mddev, bio); - submit_bio_noacct(bio); - } - return true; - -out_of_bounds: - pr_err("md/linear:%s: make_request: Sector %llu out of bounds on dev %pg: %llu sectors, offset %llu\n", - mdname(mddev), - (unsigned long long)bio->bi_iter.bi_sector, - tmp_dev->rdev->bdev, - (unsigned long long)tmp_dev->rdev->sectors, - (unsigned long long)start_sector); - bio_io_error(bio); - return true; -} - -static void linear_status (struct seq_file *seq, struct mddev *mddev) -{ - seq_printf(seq, " %dk rounding", mddev->chunk_sectors / 2); -} - -static void linear_error(struct mddev *mddev, struct md_rdev *rdev) -{ - if (!test_and_set_bit(MD_BROKEN, &mddev->flags)) { - char *md_name = mdname(mddev); - - pr_crit("md/linear%s: Disk failure on %pg detected, failing array.\n", - md_name, rdev->bdev); - } -} - -static void linear_quiesce(struct mddev *mddev, int state) -{ -} - -static struct md_personality linear_personality = -{ - .name = "linear", - .level = LEVEL_LINEAR, - .owner = THIS_MODULE, - .make_request = linear_make_request, - .run = linear_run, - .free = linear_free, - .status = linear_status, - .hot_add_disk = linear_add, - .size = linear_size, - .quiesce = linear_quiesce, - .error_handler = linear_error, -}; - -static int __init linear_init (void) -{ - return register_md_personality (&linear_personality); -} - -static void linear_exit (void) -{ - unregister_md_personality (&linear_personality); -} - -module_init(linear_init); -module_exit(linear_exit); -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("Linear device concatenation personality for MD (deprecated)"); -MODULE_ALIAS("md-personality-1"); /* LINEAR - deprecated*/ -MODULE_ALIAS("md-linear"); -MODULE_ALIAS("md-level--1"); diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c deleted file mode 100644 index 19c8625ea642..000000000000 --- a/drivers/md/md-multipath.c +++ /dev/null @@ -1,463 +0,0 @@ -// 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 <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. - */ - - for (i = 0; i < disks; i++) { - struct md_rdev *rdev = conf->multipaths[i].rdev; - - if (rdev && test_bit(In_sync, &rdev->flags) && - !test_bit(Faulty, &rdev->flags)) { - atomic_inc(&rdev->nr_pending); - return i; - } - } - - 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; - - md_account_bio(mddev, &bio); - 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); - - 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; - - lockdep_assert_held(&mddev->lock); - - seq_printf (seq, " [%d/%d] [", conf->raid_disks, - conf->raid_disks - mddev->degraded); - for (i = 0; i < conf->raid_disks; i++) { - struct md_rdev *rdev = READ_ONCE(conf->multipaths[i].rdev); - - seq_printf(seq, "%s", - rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_"); - } - 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); - - lockdep_assert_held(&conf->mddev->reconfig_mutex); - 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-& |
