blob: adda94df5eb2352775e64fb7fae4e88c6e89a98b [file] [log] [blame]
/*
* raid5.c : Multiple Devices driver for Linux
* Copyright (C) 1996, 1997 Ingo Molnar, Miguel de Icaza, Gadi Oxman
* Copyright (C) 1999, 2000 Ingo Molnar
* Copyright (C) 2002, 2003 H. Peter Anvin
*
* RAID-4/5/6 management functions.
* Thanks to Penguin Computing for making the RAID-6 development possible
* by donating a test server!
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2, or (at your option)
* any later version.
*
* You should have received a copy of the GNU General Public License
* (for example /usr/src/linux/COPYING); if not, write to the Free
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/*
* BITMAP UNPLUGGING:
*
* The sequencing for updating the bitmap reliably is a little
* subtle (and I got it wrong the first time) so it deserves some
* explanation.
*
* We group bitmap updates into batches. Each batch has a number.
* We may write out several batches at once, but that isn't very important.
* conf->seq_write is the number of the last batch successfully written.
* conf->seq_flush is the number of the last batch that was closed to
* new additions.
* When we discover that we will need to write to any block in a stripe
* (in add_stripe_bio) we update the in-memory bitmap and record in sh->bm_seq
* the number of the batch it will be in. This is seq_flush+1.
* When we are ready to do a write, if that batch hasn't been written yet,
* we plug the array and queue the stripe for later.
* When an unplug happens, we increment bm_flush, thus closing the current
* batch.
* When we notice that bm_flush > bm_write, we write out all pending updates
* to the bitmap, and advance bm_write to where bm_flush was.
* This may occasionally write a bit out twice, but is sure never to
* miss any bits.
*/
#include <linux/blkdev.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/async_tx.h>
#include <linux/module.h>
#include <linux/async.h>
#include <linux/seq_file.h>
#include <linux/cpu.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include "md.h"
#include "raid5.h"
#include "raid0.h"
#include "bitmap.h"
/*
* Stripe cache
*/
#define NR_STRIPES 256
#define STRIPE_SIZE PAGE_SIZE
#define STRIPE_SHIFT (PAGE_SHIFT - 9)
#define STRIPE_SECTORS (STRIPE_SIZE>>9)
#define IO_THRESHOLD 1
#define BYPASS_THRESHOLD 1
#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
{
int hash = (sect >> STRIPE_SHIFT) & HASH_MASK;
return &conf->stripe_hashtbl[hash];
}
/* bio's attached to a stripe+device for I/O are linked together in bi_sector
* order without overlap. There may be several bio's per stripe+device, and
* a bio could span several devices.
* When walking this list for a particular stripe+device, we must never proceed
* beyond a bio that extends past this device, as the next bio might no longer
* be valid.
* This function is used to determine the 'next' bio in the list, given the sector
* of the current stripe+device
*/
static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
{
int sectors = bio->bi_size >> 9;
if (bio->bi_sector + sectors < sector + STRIPE_SECTORS)
return bio->bi_next;
else
return NULL;
}
/*
* We maintain a biased count of active stripes in the bottom 16 bits of
* bi_phys_segments, and a count of processed stripes in the upper 16 bits
*/
static inline int raid5_bi_processed_stripes(struct bio *bio)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
return (atomic_read(segments) >> 16) & 0xffff;
}
static inline int raid5_dec_bi_active_stripes(struct bio *bio)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
return atomic_sub_return(1, segments) & 0xffff;
}
static inline void raid5_inc_bi_active_stripes(struct bio *bio)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
atomic_inc(segments);
}
static inline void raid5_set_bi_processed_stripes(struct bio *bio,
unsigned int cnt)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
int old, new;
do {
old = atomic_read(segments);
new = (old & 0xffff) | (cnt << 16);
} while (atomic_cmpxchg(segments, old, new) != old);
}
static inline void raid5_set_bi_stripes(struct bio *bio, unsigned int cnt)
{
atomic_t *segments = (atomic_t *)&bio->bi_phys_segments;
atomic_set(segments, cnt);
}
/* Find first data disk in a raid6 stripe */
static inline int raid6_d0(struct stripe_head *sh)
{
if (sh->ddf_layout)
/* ddf always start from first device */
return 0;
/* md starts just after Q block */
if (sh->qd_idx == sh->disks - 1)
return 0;
else
return sh->qd_idx + 1;
}
static inline int raid6_next_disk(int disk, int raid_disks)
{
disk++;
return (disk < raid_disks) ? disk : 0;
}
/* When walking through the disks in a raid5, starting at raid6_d0,
* We need to map each disk to a 'slot', where the data disks are slot
* 0 .. raid_disks-3, the parity disk is raid_disks-2 and the Q disk
* is raid_disks-1. This help does that mapping.
*/
static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
int *count, int syndrome_disks)
{
int slot = *count;
if (sh->ddf_layout)
(*count)++;
if (idx == sh->pd_idx)
return syndrome_disks;
if (idx == sh->qd_idx)
return syndrome_disks + 1;
if (!sh->ddf_layout)
(*count)++;
return slot;
}
static void return_io(struct bio *return_bi)
{
struct bio *bi = return_bi;
while (bi) {
return_bi = bi->bi_next;
bi->bi_next = NULL;
bi->bi_size = 0;
bio_endio(bi, 0);
bi = return_bi;
}
}
static void print_raid5_conf (struct r5conf *conf);
static int stripe_operations_active(struct stripe_head *sh)
{
return sh->check_state || sh->reconstruct_state ||
test_bit(STRIPE_BIOFILL_RUN, &sh->state) ||
test_bit(STRIPE_COMPUTE_RUN, &sh->state);
}
static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh)
{
BUG_ON(!list_empty(&sh->lru));
BUG_ON(atomic_read(&conf->active_stripes)==0);
if (test_bit(STRIPE_HANDLE, &sh->state)) {
if (test_bit(STRIPE_DELAYED, &sh->state) &&
!test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
list_add_tail(&sh->lru, &conf->delayed_list);
else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
sh->bm_seq - conf->seq_write > 0)
list_add_tail(&sh->lru, &conf->bitmap_list);
else {
clear_bit(STRIPE_DELAYED, &sh->state);
clear_bit(STRIPE_BIT_DELAY, &sh->state);
list_add_tail(&sh->lru, &conf->handle_list);
}
md_wakeup_thread(conf->mddev->thread);
} else {
BUG_ON(stripe_operations_active(sh));
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
if (atomic_dec_return(&conf->preread_active_stripes)
< IO_THRESHOLD)
md_wakeup_thread(conf->mddev->thread);
atomic_dec(&conf->active_stripes);
if (!test_bit(STRIPE_EXPANDING, &sh->state)) {
list_add_tail(&sh->lru, &conf->inactive_list);
wake_up(&conf->wait_for_stripe);
if (conf->retry_read_aligned)
md_wakeup_thread(conf->mddev->thread);
}
}
}
static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
{
if (atomic_dec_and_test(&sh->count))
do_release_stripe(conf, sh);
}
static void release_stripe(struct stripe_head *sh)
{
struct r5conf *conf = sh->raid_conf;
unsigned long flags;
local_irq_save(flags);
if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
do_release_stripe(conf, sh);
spin_unlock(&conf->device_lock);
}
local_irq_restore(flags);
}
static inline void remove_hash(struct stripe_head *sh)
{
pr_debug("remove_hash(), stripe %llu\n",
(unsigned long long)sh->sector);
hlist_del_init(&sh->hash);
}
static inline void insert_hash(struct r5conf *conf, struct stripe_head *sh)
{
struct hlist_head *hp = stripe_hash(conf, sh->sector);
pr_debug("insert_hash(), stripe %llu\n",
(unsigned long long)sh->sector);
hlist_add_head(&sh->hash, hp);
}
/* find an idle stripe, make sure it is unhashed, and return it. */
static struct stripe_head *get_free_stripe(struct r5conf *conf)
{
struct stripe_head *sh = NULL;
struct list_head *first;
if (list_empty(&conf->inactive_list))
goto out;
first = conf->inactive_list.next;
sh = list_entry(first, struct stripe_head, lru);
list_del_init(first);
remove_hash(sh);
atomic_inc(&conf->active_stripes);
out:
return sh;
}
static void shrink_buffers(struct stripe_head *sh)
{
struct page *p;
int i;
int num = sh->raid_conf->pool_size;
for (i = 0; i < num ; i++) {
p = sh->dev[i].page;
if (!p)
continue;
sh->dev[i].page = NULL;
put_page(p);
}
}
static int grow_buffers(struct stripe_head *sh)
{
int i;
int num = sh->raid_conf->pool_size;
for (i = 0; i < num; i++) {
struct page *page;
if (!(page = alloc_page(GFP_KERNEL))) {
return 1;
}
sh->dev[i].page = page;
}
return 0;
}
static void raid5_build_block(struct stripe_head *sh, int i, int previous);
static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
struct stripe_head *sh);
static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
{
struct r5conf *conf = sh->raid_conf;
int i;
BUG_ON(atomic_read(&sh->count) != 0);
BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
BUG_ON(stripe_operations_active(sh));
pr_debug("init_stripe called, stripe %llu\n",
(unsigned long long)sh->sector);
remove_hash(sh);
sh->generation = conf->generation - previous;
sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks;
sh->sector = sector;
stripe_set_idx(sector, conf, previous, sh);
sh->state = 0;
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->toread || dev->read || dev->towrite || dev->written ||
test_bit(R5_LOCKED, &dev->flags)) {
printk(KERN_ERR "sector=%llx i=%d %p %p %p %p %d\n",
(unsigned long long)sh->sector, i, dev->toread,
dev->read, dev->towrite, dev->written,
test_bit(R5_LOCKED, &dev->flags));
WARN_ON(1);
}
dev->flags = 0;
raid5_build_block(sh, i, previous);
}
insert_hash(conf, sh);
}
static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector,
short generation)
{
struct stripe_head *sh;
struct hlist_node *hn;
pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector);
hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
if (sh->sector == sector && sh->generation == generation)
return sh;
pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector);
return NULL;
}
/*
* Need to check if array has failed when deciding whether to:
* - start an array
* - remove non-faulty devices
* - add a spare
* - allow a reshape
* This determination is simple when no reshape is happening.
* However if there is a reshape, we need to carefully check
* both the before and after sections.
* This is because some failed devices may only affect one
* of the two sections, and some non-in_sync devices may
* be insync in the section most affected by failed devices.
*/
static int calc_degraded(struct r5conf *conf)
{
int degraded, degraded2;
int i;
rcu_read_lock();
degraded = 0;
for (i = 0; i < conf->previous_raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded++;
else if (test_bit(In_sync, &rdev->flags))
;
else
/* not in-sync or faulty.
* If the reshape increases the number of devices,
* this is being recovered by the reshape, so
* this 'previous' section is not in_sync.
* If the number of devices is being reduced however,
* the device can only be part of the array if
* we are reverting a reshape, so this section will
* be in-sync.
*/
if (conf->raid_disks >= conf->previous_raid_disks)
degraded++;
}
rcu_read_unlock();
if (conf->raid_disks == conf->previous_raid_disks)
return degraded;
rcu_read_lock();
degraded2 = 0;
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded2++;
else if (test_bit(In_sync, &rdev->flags))
;
else
/* not in-sync or faulty.
* If reshape increases the number of devices, this
* section has already been recovered, else it
* almost certainly hasn't.
*/
if (conf->raid_disks <= conf->previous_raid_disks)
degraded2++;
}
rcu_read_unlock();
if (degraded2 > degraded)
return degraded2;
return degraded;
}
static int has_failed(struct r5conf *conf)
{
int degraded;
if (conf->mddev->reshape_position == MaxSector)
return conf->mddev->degraded > conf->max_degraded;
degraded = calc_degraded(conf);
if (degraded > conf->max_degraded)
return 1;
return 0;
}
static struct stripe_head *
get_active_stripe(struct r5conf *conf, sector_t sector,
int previous, int noblock, int noquiesce)
{
struct stripe_head *sh;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
spin_lock_irq(&conf->device_lock);
do {
wait_event_lock_irq(conf->wait_for_stripe,
conf->quiesce == 0 || noquiesce,
conf->device_lock, /* nothing */);
sh = __find_stripe(conf, sector, conf->generation - previous);
if (!sh) {
if (!conf->inactive_blocked)
sh = get_free_stripe(conf);
if (noblock && sh == NULL)
break;
if (!sh) {
conf->inactive_blocked = 1;
wait_event_lock_irq(conf->wait_for_stripe,
!list_empty(&conf->inactive_list) &&
(atomic_read(&conf->active_stripes)
< (conf->max_nr_stripes *3/4)
|| !conf->inactive_blocked),
conf->device_lock,
);
conf->inactive_blocked = 0;
} else
init_stripe(sh, sector, previous);
} else {
if (atomic_read(&sh->count)) {
BUG_ON(!list_empty(&sh->lru)
&& !test_bit(STRIPE_EXPANDING, &sh->state)
&& !test_bit(STRIPE_ON_UNPLUG_LIST, &sh->state));
} else {
if (!test_bit(STRIPE_HANDLE, &sh->state))
atomic_inc(&conf->active_stripes);
if (list_empty(&sh->lru) &&
!test_bit(STRIPE_EXPANDING, &sh->state))
BUG();
list_del_init(&sh->lru);
}
}
} while (sh == NULL);
if (sh)
atomic_inc(&sh->count);
spin_unlock_irq(&conf->device_lock);
return sh;
}
/* Determine if 'data_offset' or 'new_data_offset' should be used
* in this stripe_head.
*/
static int use_new_offset(struct r5conf *conf, struct stripe_head *sh)
{
sector_t progress = conf->reshape_progress;
/* Need a memory barrier to make sure we see the value
* of conf->generation, or ->data_offset that was set before
* reshape_progress was updated.
*/
smp_rmb();
if (progress == MaxSector)
return 0;
if (sh->generation == conf->generation - 1)
return 0;
/* We are in a reshape, and this is a new-generation stripe,
* so use new_data_offset.
*/
return 1;
}
static void
raid5_end_read_request(struct bio *bi, int error);
static void
raid5_end_write_request(struct bio *bi, int error);
static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
{
struct r5conf *conf = sh->raid_conf;
int i, disks = sh->disks;
might_sleep();
for (i = disks; i--; ) {
int rw;
int replace_only = 0;
struct bio *bi, *rbi;
struct md_rdev *rdev, *rrdev = NULL;
if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
rw = WRITE_FUA;
else
rw = WRITE;
} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
rw = READ;
else if (test_and_clear_bit(R5_WantReplace,
&sh->dev[i].flags)) {
rw = WRITE;
replace_only = 1;
} else
continue;
if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags))
rw |= REQ_SYNC;
bi = &sh->dev[i].req;
rbi = &sh->dev[i].rreq; /* For writing to replacement */
bi->bi_rw = rw;
rbi->bi_rw = rw;
if (rw & WRITE) {
bi->bi_end_io = raid5_end_write_request;
rbi->bi_end_io = raid5_end_write_request;
} else
bi->bi_end_io = raid5_end_read_request;
rcu_read_lock();
rrdev = rcu_dereference(conf->disks[i].replacement);
smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */
rdev = rcu_dereference(conf->disks[i].rdev);
if (!rdev) {
rdev = rrdev;
rrdev = NULL;
}
if (rw & WRITE) {
if (replace_only)
rdev = NULL;
if (rdev == rrdev)
/* We raced and saw duplicates */
rrdev = NULL;
} else {
if (test_bit(R5_ReadRepl, &sh->dev[i].flags) && rrdev)
rdev = rrdev;
rrdev = NULL;
}
if (rdev && test_bit(Faulty, &rdev->flags))
rdev = NULL;
if (rdev)
atomic_inc(&rdev->nr_pending);
if (rrdev && test_bit(Faulty, &rrdev->flags))
rrdev = NULL;
if (rrdev)
atomic_inc(&rrdev->nr_pending);
rcu_read_unlock();
/* We have already checked bad blocks for reads. Now
* need to check for writes. We never accept write errors
* on the replacement, so we don't to check rrdev.
*/
while ((rw & WRITE) && rdev &&
test_bit(WriteErrorSeen, &rdev->flags)) {
sector_t first_bad;
int bad_sectors;
int bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
&first_bad, &bad_sectors);
if (!bad)
break;
if (bad < 0) {
set_bit(BlockedBadBlocks, &rdev->flags);
if (!conf->mddev->external &&
conf->mddev->flags) {
/* It is very unlikely, but we might
* still need to write out the
* bad block log - better give it
* a chance*/
md_check_recovery(conf->mddev);
}
/*
* Because md_wait_for_blocked_rdev
* will dec nr_pending, we must
* increment it first.
*/
atomic_inc(&rdev->nr_pending);
md_wait_for_blocked_rdev(rdev, conf->mddev);
} else {
/* Acknowledged bad block - skip the write */
rdev_dec_pending(rdev, conf->mddev);
rdev = NULL;
}
}
if (rdev) {
if (s->syncing || s->expanding || s->expanded
|| s->replacing)
md_sync_acct(rdev->bdev, STRIPE_SECTORS);
set_bit(STRIPE_IO_STARTED, &sh->state);
bi->bi_bdev = rdev->bdev;
pr_debug("%s: for %llu schedule op %ld on disc %d\n",
__func__, (unsigned long long)sh->sector,
bi->bi_rw, i);
atomic_inc(&sh->count);
if (use_new_offset(conf, sh))
bi->bi_sector = (sh->sector
+ rdev->new_data_offset);
else
bi->bi_sector = (sh->sector
+ rdev->data_offset);
if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
bi->bi_rw |= REQ_FLUSH;
bi->bi_flags = 1 << BIO_UPTODATE;
bi->bi_idx = 0;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
bi->bi_next = NULL;
if (rrdev)
set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
generic_make_request(bi);
}
if (rrdev) {
if (s->syncing || s->expanding || s->expanded
|| s->replacing)
md_sync_acct(rrdev->bdev, STRIPE_SECTORS);
set_bit(STRIPE_IO_STARTED, &sh->state);
rbi->bi_bdev = rrdev->bdev;
pr_debug("%s: for %llu schedule op %ld on "
"replacement disc %d\n",
__func__, (unsigned long long)sh->sector,
rbi->bi_rw, i);
atomic_inc(&sh->count);
if (use_new_offset(conf, sh))
rbi->bi_sector = (sh->sector
+ rrdev->new_data_offset);
else
rbi->bi_sector = (sh->sector
+ rrdev->data_offset);
rbi->bi_flags = 1 << BIO_UPTODATE;
rbi->bi_idx = 0;
rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
rbi->bi_io_vec[0].bv_offset = 0;
rbi->bi_size = STRIPE_SIZE;
rbi->bi_next = NULL;
generic_make_request(rbi);
}
if (!rdev && !rrdev) {
if (rw & WRITE)
set_bit(STRIPE_DEGRADED, &sh->state);
pr_debug("skip op %ld on disc %d for sector %llu\n",
bi->bi_rw, i, (unsigned long long)sh->sector);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
}
}
}
static struct dma_async_tx_descriptor *
async_copy_data(int frombio, struct bio *bio, struct page *page,
sector_t sector, struct dma_async_tx_descriptor *tx)
{
struct bio_vec *bvl;
struct page *bio_page;
int i;
int page_offset;
struct async_submit_ctl submit;
enum async_tx_flags flags = 0;
if (bio->bi_sector >= sector)
page_offset = (signed)(bio->bi_sector - sector) * 512;
else
page_offset = (signed)(sector - bio->bi_sector) * -512;
if (frombio)
flags |= ASYNC_TX_FENCE;
init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
bio_for_each_segment(bvl, bio, i) {
int len = bvl->bv_len;
int clen;
int b_offset = 0;
if (page_offset < 0) {
b_offset = -page_offset;
page_offset += b_offset;
len -= b_offset;
}
if (len > 0 && page_offset + len > STRIPE_SIZE)
clen = STRIPE_SIZE - page_offset;
else
clen = len;
if (clen > 0) {
b_offset += bvl->bv_offset;
bio_page = bvl->bv_page;
if (frombio)
tx = async_memcpy(page, bio_page, page_offset,
b_offset, clen, &submit);
else
tx = async_memcpy(bio_page, page, b_offset,
page_offset, clen, &submit);
}
/* chain the operations */
submit.depend_tx = tx;
if (clen < len) /* hit end of page */
break;
page_offset += len;
}
return tx;
}
static void ops_complete_biofill(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
struct bio *return_bi = NULL;
int i;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
/* clear completed biofills */
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
/* acknowledge completion of a biofill operation */
/* and check if we need to reply to a read request,
* new R5_Wantfill requests are held off until
* !STRIPE_BIOFILL_RUN
*/
if (test_and_clear_bit(R5_Wantfill, &dev->flags)) {
struct bio *rbi, *rbi2;
BUG_ON(!dev->read);
rbi = dev->read;
dev->read = NULL;
while (rbi && rbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
rbi2 = r5_next_bio(rbi, dev->sector);
if (!raid5_dec_bi_active_stripes(rbi)) {
rbi->bi_next = return_bi;
return_bi = rbi;
}
rbi = rbi2;
}
}
}
clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
return_io(return_bi);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static void ops_run_biofill(struct stripe_head *sh)
{
struct dma_async_tx_descriptor *tx = NULL;
struct async_submit_ctl submit;
int i;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (test_bit(R5_Wantfill, &dev->flags)) {
struct bio *rbi;
spin_lock_irq(&sh->stripe_lock);
dev->read = rbi = dev->toread;
dev->toread = NULL;
spin_unlock_irq(&sh->stripe_lock);
while (rbi && rbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
tx = async_copy_data(0, rbi, dev->page,
dev->sector, tx);
rbi = r5_next_bio(rbi, dev->sector);
}
}
}
atomic_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_biofill, sh, NULL);
async_trigger_callback(&submit);
}
static void mark_target_uptodate(struct stripe_head *sh, int target)
{
struct r5dev *tgt;
if (target < 0)
return;
tgt = &sh->dev[target];
set_bit(R5_UPTODATE, &tgt->flags);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
clear_bit(R5_Wantcompute, &tgt->flags);
}
static void ops_complete_compute(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
/* mark the computed target(s) as uptodate */
mark_target_uptodate(sh, sh->ops.target);
mark_target_uptodate(sh, sh->ops.target2);
clear_bit(STRIPE_COMPUTE_RUN, &sh->state);
if (sh->check_state == check_state_compute_run)
sh->check_state = check_state_compute_result;
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
/* return a pointer to the address conversion region of the scribble buffer */
static addr_conv_t *to_addr_conv(struct stripe_head *sh,
struct raid5_percpu *percpu)
{
return percpu->scribble + sizeof(struct page *) * (sh->disks + 2);
}
static struct dma_async_tx_descriptor *
ops_run_compute5(struct stripe_head *sh, struct raid5_percpu *percpu)
{
int disks = sh->disks;
struct page **xor_srcs = percpu->scribble;
int target = sh->ops.target;
struct r5dev *tgt = &sh->dev[target];
struct page *xor_dest = tgt->page;
int count = 0;
struct dma_async_tx_descriptor *tx;
struct async_submit_ctl submit;
int i;
pr_debug("%s: stripe %llu block: %d\n",
__func__, (unsigned long long)sh->sector, target);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
for (i = disks; i--; )
if (i != target)
xor_srcs[count++] = sh->dev[i].page;
atomic_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST, NULL,
ops_complete_compute, sh, to_addr_conv(sh, percpu));
if (unlikely(count == 1))
tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
else
tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
return tx;
}
/* set_syndrome_sources - populate source buffers for gen_syndrome
* @srcs - (struct page *) array of size sh->disks
* @sh - stripe_head to parse
*
* Populates srcs in proper layout order for the stripe and returns the
* 'count' of sources to be used in a call to async_gen_syndrome. The P
* destination buffer is recorded in srcs[count] and the Q destination
* is recorded in srcs[count+1]].
*/
static int set_syndrome_sources(struct page **srcs, struct stripe_head *sh)
{
int disks = sh->disks;
int syndrome_disks = sh->ddf_layout ? disks : (disks - 2);
int d0_idx = raid6_d0(sh);
int count;
int i;
for (i = 0; i < disks; i++)
srcs[i] = NULL;
count = 0;
i = d0_idx;
do {
int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
srcs[slot] = sh->dev[i].page;
i = raid6_next_disk(i, disks);
} while (i != d0_idx);
return syndrome_disks;
}
static struct dma_async_tx_descriptor *
ops_run_compute6_1(struct stripe_head *sh, struct raid5_percpu *percpu)
{
int disks = sh->disks;
struct page **blocks = percpu->scribble;
int target;
int qd_idx = sh->qd_idx;
struct dma_async_tx_descriptor *tx;
struct async_submit_ctl submit;
struct r5dev *tgt;
struct page *dest;
int i;
int count;
if (sh->ops.target < 0)
target = sh->ops.target2;
else if (sh->ops.target2 < 0)
target = sh->ops.target;
else
/* we should only have one valid target */
BUG();
BUG_ON(target < 0);
pr_debug("%s: stripe %llu block: %d\n",
__func__, (unsigned long long)sh->sector, target);
tgt = &sh->dev[target];
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
dest = tgt->page;
atomic_inc(&sh->count);
if (target == qd_idx) {
count = set_syndrome_sources(blocks, sh);
blocks[count] = NULL; /* regenerating p is not necessary */
BUG_ON(blocks[count+1] != dest); /* q should already be set */
init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
ops_complete_compute, sh,
to_addr_conv(sh, percpu));
tx = async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
} else {
/* Compute any data- or p-drive using XOR */
count = 0;
for (i = disks; i-- ; ) {
if (i == target || i == qd_idx)
continue;
blocks[count++] = sh->dev[i].page;
}
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
NULL, ops_complete_compute, sh,
to_addr_conv(sh, percpu));
tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE, &submit);
}
return tx;
}
static struct dma_async_tx_descriptor *
ops_run_compute6_2(struct stripe_head *sh, struct raid5_percpu *percpu)
{
int i, count, disks = sh->disks;
int syndrome_disks = sh->ddf_layout ? disks : disks-2;
int d0_idx = raid6_d0(sh);
int faila = -1, failb = -1;
int target = sh->ops.target;
int target2 = sh->ops.target2;
struct r5dev *tgt = &sh->dev[target];
struct r5dev *tgt2 = &sh->dev[target2];
struct dma_async_tx_descriptor *tx;
struct page **blocks = percpu->scribble;
struct async_submit_ctl submit;
pr_debug("%s: stripe %llu block1: %d block2: %d\n",
__func__, (unsigned long long)sh->sector, target, target2);
BUG_ON(target < 0 || target2 < 0);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
BUG_ON(!test_bit(R5_Wantcompute, &tgt2->flags));
/* we need to open-code set_syndrome_sources to handle the
* slot number conversion for 'faila' and 'failb'
*/
for (i = 0; i < disks ; i++)
blocks[i] = NULL;
count = 0;
i = d0_idx;
do {
int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
blocks[slot] = sh->dev[i].page;
if (i == target)
faila = slot;
if (i == target2)
failb = slot;
i = raid6_next_disk(i, disks);
} while (i != d0_idx);
BUG_ON(faila == failb);
if (failb < faila)
swap(faila, failb);
pr_debug("%s: stripe: %llu faila: %d failb: %d\n",
__func__, (unsigned long long)sh->sector, faila, failb);
atomic_inc(&sh->count);
if (failb == syndrome_disks+1) {
/* Q disk is one of the missing disks */
if (faila == syndrome_disks) {
/* Missing P+Q, just recompute */
init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
ops_complete_compute, sh,
to_addr_conv(sh, percpu));
return async_gen_syndrome(blocks, 0, syndrome_disks+2,
STRIPE_SIZE, &submit);
} else {
struct page *dest;
int data_target;
int qd_idx = sh->qd_idx;
/* Missing D+Q: recompute D from P, then recompute Q */
if (target == qd_idx)
data_target = target2;
else
data_target = target;
count = 0;
for (i = disks; i-- ; ) {
if (i == data_target || i == qd_idx)
continue;
blocks[count++] = sh->dev[i].page;
}
dest = sh->dev[data_target].page;
init_async_submit(&submit,
ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
NULL, NULL, NULL,
to_addr_conv(sh, percpu));
tx = async_xor(dest, blocks, 0, count, STRIPE_SIZE,
&submit);
count = set_syndrome_sources(blocks, sh);
init_async_submit(&submit, ASYNC_TX_FENCE, tx,
ops_complete_compute, sh,
to_addr_conv(sh, percpu));
return async_gen_syndrome(blocks, 0, count+2,
STRIPE_SIZE, &submit);
}
} else {
init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
ops_complete_compute, sh,
to_addr_conv(sh, percpu));
if (failb == syndrome_disks) {
/* We're missing D+P. */
return async_raid6_datap_recov(syndrome_disks+2,
STRIPE_SIZE, faila,
blocks, &submit);
} else {
/* We're missing D+D. */
return async_raid6_2data_recov(syndrome_disks+2,
STRIPE_SIZE, faila, failb,
blocks, &submit);
}
}
}
static void ops_complete_prexor(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
}
static struct dma_async_tx_descriptor *
ops_run_prexor(struct stripe_head *sh, struct raid5_percpu *percpu,
struct dma_async_tx_descriptor *tx)
{
int disks = sh->disks;
struct page **xor_srcs = percpu->scribble;
int count = 0, pd_idx = sh->pd_idx, i;
struct async_submit_ctl submit;
/* existing parity data subtracted */
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
/* Only process blocks that are known to be uptodate */
if (test_bit(R5_Wantdrain, &dev->flags))
xor_srcs[count++] = dev->page;
}
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_XOR_DROP_DST, tx,
ops_complete_prexor, sh, to_addr_conv(sh, percpu));
tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
return tx;
}
static struct dma_async_tx_descriptor *
ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
{
int disks = sh->disks;
int i;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
struct bio *chosen;
if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
struct bio *wbi;
spin_lock_irq(&sh->stripe_lock);
chosen = dev->towrite;
dev->towrite = NULL;
BUG_ON(dev->written);
wbi = dev->written = chosen;
spin_unlock_irq(&sh->stripe_lock);
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
if (wbi->bi_rw & REQ_FUA)
set_bit(R5_WantFUA, &dev->flags);
if (wbi->bi_rw & REQ_SYNC)
set_bit(R5_SyncIO, &dev->flags);
tx = async_copy_data(1, wbi, dev->page,
dev->sector, tx);
wbi = r5_next_bio(wbi, dev->sector);
}
}
}
return tx;
}
static void ops_complete_reconstruct(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
int disks = sh->disks;
int pd_idx = sh->pd_idx;
int qd_idx = sh->qd_idx;
int i;
bool fua = false, sync = false;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
fua |= test_bit(R5_WantFUA, &sh->dev[i].flags);
sync |= test_bit(R5_SyncIO, &sh->dev[i].flags);
}
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->written || i == pd_idx || i == qd_idx) {
set_bit(R5_UPTODATE, &dev->flags);
if (fua)
set_bit(R5_WantFUA, &dev->flags);
if (sync)
set_bit(R5_SyncIO, &dev->flags);
}
}
if (sh->reconstruct_state == reconstruct_state_drain_run)
sh->reconstruct_state = reconstruct_state_drain_result;
else if (sh->reconstruct_state == reconstruct_state_prexor_drain_run)
sh->reconstruct_state = reconstruct_state_prexor_drain_result;
else {
BUG_ON(sh->reconstruct_state != reconstruct_state_run);
sh->reconstruct_state = reconstruct_state_result;
}
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static void
ops_run_reconstruct5(struct stripe_head *sh, struct raid5_percpu *percpu,
struct dma_async_tx_descriptor *tx)
{
int disks = sh->disks;
struct page **xor_srcs = percpu->scribble;
struct async_submit_ctl submit;
int count = 0, pd_idx = sh->pd_idx, i;
struct page *xor_dest;
int prexor = 0;
unsigned long flags;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
/* check if prexor is active which means only process blocks
* that are part of a read-modify-write (written)
*/
if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
prexor = 1;
xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->written)
xor_srcs[count++] = dev->page;
}
} else {
xor_dest = sh->dev[pd_idx].page;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (i != pd_idx)
xor_srcs[count++] = dev->page;
}
}
/* 1/ if we prexor'd then the dest is reused as a source
* 2/ if we did not prexor then we are redoing the parity
* set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST
* for the synchronous xor case
*/
flags = ASYNC_TX_ACK |
(prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST);
atomic_inc(&sh->count);
init_async_submit(&submit, flags, tx, ops_complete_reconstruct, sh,
to_addr_conv(sh, percpu));
if (unlikely(count == 1))
tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE, &submit);
else
tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE, &submit);
}
static void
ops_run_reconstruct6(struct stripe_head *sh, struct raid5_percpu *percpu,
struct dma_async_tx_descriptor *tx)
{
struct async_submit_ctl submit;
struct page **blocks = percpu->scribble;
int count;
pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector);
count = set_syndrome_sources(blocks, sh);
atomic_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_reconstruct,
sh, to_addr_conv(sh, percpu));
async_gen_syndrome(blocks, 0, count+2, STRIPE_SIZE, &submit);
}
static void ops_complete_check(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
sh->check_state = check_state_check_result;
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static void ops_run_check_p(struct stripe_head *sh, struct raid5_percpu *percpu)
{
int disks = sh->disks;
int pd_idx = sh->pd_idx;
int qd_idx = sh->qd_idx;
struct page *xor_dest;
struct page **xor_srcs = percpu->scribble;
struct dma_async_tx_descriptor *tx;
struct async_submit_ctl submit;
int count;
int i;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
count = 0;
xor_dest = sh->dev[pd_idx].page;
xor_srcs[count++] = xor_dest;
for (i = disks; i--; ) {
if (i == pd_idx || i == qd_idx)
continue;
xor_srcs[count++] = sh->dev[i].page;
}
init_async_submit(&submit, 0, NULL, NULL, NULL,
to_addr_conv(sh, percpu));
tx = async_xor_val(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
&sh->ops.zero_sum_result, &submit);
atomic_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, tx, ops_complete_check, sh, NULL);
tx = async_trigger_callback(&submit);
}
static void ops_run_check_pq(struct stripe_head *sh, struct raid5_percpu *percpu, int checkp)
{
struct page **srcs = percpu->scribble;
struct async_submit_ctl submit;
int count;
pr_debug("%s: stripe %llu checkp: %d\n", __func__,
(unsigned long long)sh->sector, checkp);
count = set_syndrome_sources(srcs, sh);
if (!checkp)
srcs[count] = NULL;
atomic_inc(&sh->count);
init_async_submit(&submit, ASYNC_TX_ACK, NULL, ops_complete_check,
sh, to_addr_conv(sh, percpu));
async_syndrome_val(srcs, 0, count+2, STRIPE_SIZE,
&sh->ops.zero_sum_result, percpu->spare_page, &submit);
}
static void __raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
{
int overlap_clear = 0, i, disks = sh->disks;
struct dma_async_tx_descriptor *tx = NULL;
struct r5conf *conf = sh->raid_conf;
int level = conf->level;
struct raid5_percpu *percpu;
unsigned long cpu;
cpu = get_cpu();
percpu = per_cpu_ptr(conf->percpu, cpu);
if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
ops_run_biofill(sh);
overlap_clear++;
}
if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) {
if (level < 6)
tx = ops_run_compute5(sh, percpu);
else {
if (sh->ops.target2 < 0 || sh->ops.target < 0)
tx = ops_run_compute6_1(sh, percpu);
else
tx = ops_run_compute6_2(sh, percpu);
}
/* terminate the chain if reconstruct is not set to be run */
if (tx && !test_bit(STRIPE_OP_RECONSTRUCT, &ops_request))
async_tx_ack(tx);
}
if (test_bit(STRIPE_OP_PREXOR, &ops_request))
tx = ops_run_prexor(sh, percpu, tx);
if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
tx = ops_run_biodrain(sh, tx);
overlap_clear++;
}
if (test_bit(STRIPE_OP_RECONSTRUCT, &ops_request)) {
if (level < 6)
ops_run_reconstruct5(sh, percpu, tx);
else
ops_run_reconstruct6(sh, percpu, tx);
}
if (test_bit(STRIPE_OP_CHECK, &ops_request)) {
if (sh->check_state == check_state_run)
ops_run_check_p(sh, percpu);
else if (sh->check_state == check_state_run_q)
ops_run_check_pq(sh, percpu, 0);
else if (sh->check_state == check_state_run_pq)
ops_run_check_pq(sh, percpu, 1);
else
BUG();
}
if (overlap_clear)
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (test_and_clear_bit(R5_Overlap, &dev->flags))
wake_up(&sh->raid_conf->wait_for_overlap);
}
put_cpu();
}
#ifdef CONFIG_MULTICORE_RAID456
static void async_run_ops(void *param, async_cookie_t cookie)
{
struct stripe_head *sh = param;
unsigned long ops_request = sh->ops.request;
clear_bit_unlock(STRIPE_OPS_REQ_PENDING, &sh->state);
wake_up(&sh->ops.wait_for_ops);
__raid_run_ops(sh, ops_request);
release_stripe(sh);
}
static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
{
/* since handle_stripe can be called outside of raid5d context
* we need to ensure sh->ops.request is de-staged before another
* request arrives
*/
wait_event(sh->ops.wait_for_ops,
!test_and_set_bit_lock(STRIPE_OPS_REQ_PENDING, &sh->state));
sh->ops.request = ops_request;
atomic_inc(&sh->count);
async_schedule(async_run_ops, sh);
}
#else
#define raid_run_ops __raid_run_ops
#endif
static int grow_one_stripe(struct r5conf *conf)
{
struct stripe_head *sh;
sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL);
if (!sh)
return 0;
sh->raid_conf = conf;
#ifdef CONFIG_MULTICORE_RAID456
init_waitqueue_head(&sh->ops.wait_for_ops);
#endif
spin_lock_init(&sh->stripe_lock);
if (grow_buffers(sh)) {
shrink_buffers(sh);
kmem_cache_free(conf->slab_cache, sh);
return 0;
}
/* we just created an active stripe so... */
atomic_set(&sh->count, 1);
atomic_inc(&conf->active_stripes);
INIT_LIST_HEAD(&sh->lru);
release_stripe(sh);
return 1;
}
static int grow_stripes(struct r5conf *conf, int num)
{
struct kmem_cache *sc;
int devs = max(conf->raid_disks, conf->previous_raid_disks);
if (conf->mddev->gendisk)
sprintf(conf->cache_name[0],
"raid%d-%s", conf->level, mdname(conf->mddev));
else
sprintf(conf->cache_name[0],
"raid%d-%p", conf->level, conf->mddev);
sprintf(conf->cache_name[1], "%s-alt", conf->cache_name[0]);
conf->active_name = 0;
sc = kmem_cache_create(conf->cache_name[conf->active_name],
sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
0, 0, NULL);
if (!sc)
return 1;
conf->slab_cache = sc;
conf->pool_size = devs;
while (num--)
if (!grow_one_stripe(conf))
return 1;
return 0;
}
/**
* scribble_len - return the required size of the scribble region
* @num - total number of disks in the array
*
* The size must be enough to contain:
* 1/ a struct page pointer for each device in the array +2
* 2/ room to convert each entry in (1) to its corresponding dma
* (dma_map_page()) or page (page_address()) address.
*
* Note: the +2 is for the destination buffers of the ddf/raid6 case where we
* calculate over all devices (not just the data blocks), using zeros in place
* of the P and Q blocks.
*/
static size_t scribble_len(int num)
{
size_t len;
len = sizeof(struct page *) * (num+2) + sizeof(addr_conv_t) * (num+2);
return len;
}
static int resize_stripes(struct r5conf *conf, int newsize)
{
/* Make all the stripes able to hold 'newsize' devices.
* New slots in each stripe get 'page' set to a new page.
*
* This happens in stages:
* 1/ create a new kmem_cache and allocate the required number of
* stripe_heads.
* 2/ gather all the old stripe_heads and tranfer the pages across
* to the new stripe_heads. This will have the side effect of
* freezing the array as once all stripe_heads have been collected,
* no IO will be possible. Old stripe heads are freed once their
* pages have been transferred over, and the old kmem_cache is
* freed when all stripes are done.
* 3/ reallocate conf->disks to be suitable bigger. If this fails,
* we simple return a failre status - no need to clean anything up.
* 4/ allocate new pages for the new slots in the new stripe_heads.
* If this fails, we don't bother trying the shrink the
* stripe_heads down again, we just leave them as they are.
* As each stripe_head is processed the new one is released into
* active service.
*
* Once step2 is started, we cannot afford to wait for a write,
* so we use GFP_NOIO allocations.
*/
struct stripe_head *osh, *nsh;
LIST_HEAD(newstripes);
struct disk_info *ndisks;
unsigned long cpu;
int err;
struct kmem_cache *sc;
int i;
if (newsize <= conf->pool_size)
return 0; /* never bother to shrink */
err = md_allow_write(conf->mddev);
if (err)
return err;
/* Step 1 */
sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
sizeof(struct stripe_head)+(newsize-1)*sizeof(struct r5dev),
0, 0, NULL);
if (!sc)
return -ENOMEM;
for (i = conf->max_nr_stripes; i; i--) {
nsh = kmem_cache_zalloc(sc, GFP_KERNEL);
if (!nsh)
break;
nsh->raid_conf = conf;
#ifdef CONFIG_MULTICORE_RAID456
init_waitqueue_head(&nsh->ops.wait_for_ops);
#endif
list_add(&nsh->lru, &newstripes);
}
if (i) {
/* didn't get enough, give up */
while (!list_empty(&newstripes)) {
nsh = list_entry(newstripes.next, struct stripe_head, lru);
list_del(&nsh->lru);
kmem_cache_free(sc, nsh);
}
kmem_cache_destroy(sc);
return -ENOMEM;
}
/* Step 2 - Must use GFP_NOIO now.
* OK, we have enough stripes, start collecting inactive
* stripes and copying them over
*/
list_for_each_entry(nsh, &newstripes, lru) {
spin_lock_irq(&conf->device_lock);
wait_event_lock_irq(conf->wait_for_stripe,
!list_empty(&conf->inactive_list),
conf->device_lock,
);
osh = get_free_stripe(conf);
spin_unlock_irq(&conf->device_lock);
atomic_set(&nsh->count, 1);
for(i=0; i<conf->pool_size; i++)
nsh->dev[i].page = osh->dev[i].page;
for( ; i<newsize; i++)
nsh->dev[i].page = NULL;
kmem_cache_free(conf->slab_cache, osh);
}
kmem_cache_destroy(conf->slab_cache);
/* Step 3.
* At this point, we are holding all the stripes so the array
* is completely stalled, so now is a good time to resize
* conf->disks and the scribble region
*/
ndisks = kzalloc(newsize * sizeof(struct disk_info), GFP_NOIO);
if (ndisks) {
for (i=0; i<conf->raid_disks; i++)
ndisks[i] = conf->disks[i];
kfree(conf->disks);
conf->disks = ndisks;
} else
err = -ENOMEM;
get_online_cpus();
conf->scribble_len = scribble_len(newsize);
for_each_present_cpu(cpu) {
struct raid5_percpu *percpu;
void *scribble;
percpu = per_cpu_ptr(conf->percpu, cpu);
scribble = kmalloc(conf->scribble_len, GFP_NOIO);
if (scribble) {
kfree(percpu->scribble);
percpu->scribble = scribble;
} else {
err = -ENOMEM;
break;
}
}
put_online_cpus();
/* Step 4, return new stripes to service */
while(!list_empty(&newstripes)) {
nsh = list_entry(newstripes.next, struct stripe_head, lru);
list_del_init(&nsh->lru);
for (i=conf->raid_disks; i < newsize; i++)
if (nsh->dev[i].page == NULL) {
struct page *p = alloc_page(GFP_NOIO);
nsh->dev[i].page = p;
if (!p)
err = -ENOMEM;
}
release_stripe(nsh);
}
/* critical section pass, GFP_NOIO no longer needed */
conf->slab_cache = sc;
conf->active_name = 1-conf->active_name;
conf->pool_size = newsize;
return err;
}
static int drop_one_stripe(struct r5conf *conf)
{
struct stripe_head *sh;
spin_lock_irq(&conf->device_lock);
sh = get_free_stripe(conf);
spin_unlock_irq(&conf->device_lock);
if (!sh)
return 0;
BUG_ON(atomic_read(&sh->count));
shrink_buffers(sh);
kmem_cache_free(conf->slab_cache, sh);
atomic_dec(&conf->active_stripes);
return 1;
}
static void shrink_stripes(struct r5conf *conf)
{
while (drop_one_stripe(conf))
;
if (conf->slab_cache)
kmem_cache_destroy(conf->slab_cache);
conf->slab_cache = NULL;
}
static void raid5_end_read_request(struct bio * bi, int error)
{
struct stripe_head *sh = bi->bi_private;
struct r5conf *conf = sh->raid_conf;
int disks = sh->disks, i;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
char b[BDEVNAME_SIZE];
struct md_rdev *rdev = NULL;
sector_t s;
for (i=0 ; i<disks; i++)
if (bi == &sh->dev[i].req)
break;
pr_debug("end_read_request %llu/%d, count: %d, uptodate %d.\n",
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
uptodate);
if (i == disks) {
BUG();
return;
}
if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
/* If replacement finished while this request was outstanding,
* 'replacement' might be NULL already.
* In that case it moved down to 'rdev'.
* rdev is not removed until all requests are finished.
*/
rdev = conf->disks[i].replacement;
if (!rdev)
rdev = conf->disks[i].rdev;
if (use_new_offset(conf, sh))
s = sh->sector + rdev->new_data_offset;
else
s = sh->sector + rdev->data_offset;
if (uptodate) {
set_bit(R5_UPTODATE, &sh->dev[i].flags);
if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
/* Note that this cannot happen on a
* replacement device. We just fail those on
* any error
*/
printk_ratelimited(
KERN_INFO
"md/raid:%s: read error corrected"
" (%lu sectors at %llu on %s)\n",
mdname(conf->mddev), STRIPE_SECTORS,
(unsigned long long)s,
bdevname(rdev->bdev, b));
atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
} else if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
if (atomic_read(&rdev->read_errors))
atomic_set(&rdev->read_errors, 0);
} else {
const char *bdn = bdevname(rdev->bdev, b);
int retry = 0;
int set_bad = 0;
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
atomic_inc(&rdev->read_errors);
if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
printk_ratelimited(
KERN_WARNING
"md/raid:%s: read error on replacement device "
"(sector %llu on %s).\n",
mdname(conf->mddev),
(unsigned long long)s,
bdn);
else if (conf->mddev->degraded >= conf->max_degraded) {
set_bad = 1;
printk_ratelimited(
KERN_WARNING
"md/raid:%s: read error not correctable "
"(sector %llu on %s).\n",
mdname(conf->mddev),
(unsigned long long)s,
bdn);
} else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) {
/* Oh, no!!! */
set_bad = 1;
printk_ratelimited(
KERN_WARNING
"md/raid:%s: read error NOT corrected!! "
"(sector %llu on %s).\n",
mdname(conf->mddev),
(unsigned long long)s,
bdn);
} else if (atomic_read(&rdev->read_errors)
> conf->max_nr_stripes)
printk(KERN_WARNING
"md/raid:%s: Too many read errors, failing device %s.\n",
mdname(conf->mddev), bdn);
else
retry = 1;
if (retry)
if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags)) {
set_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReadNoMerge, &sh->dev[i].flags);
} else
set_bit(R5_ReadNoMerge, &sh->dev[i].flags);
else {
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
if (!(set_bad
&& test_bit(In_sync, &rdev->flags)
&& rdev_set_badblocks(
rdev, sh->sector, STRIPE_SECTORS, 0)))
md_error(conf->mddev, rdev);
}
}
rdev_dec_pending(rdev, conf->mddev);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static void raid5_end_write_request(struct bio *bi, int error)
{
struct stripe_head *sh = bi->bi_private;
struct r5conf *conf = sh->raid_conf;
int disks = sh->disks, i;
struct md_rdev *uninitialized_var(rdev);
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
sector_t first_bad;
int bad_sectors;
int replacement = 0;
for (i = 0 ; i < disks; i++) {
if (bi == &sh->dev[i].req) {
rdev = conf->disks[i].rdev;
break;
}
if (bi == &sh->dev[i].rreq) {
rdev = conf->disks[i].replacement;
if (rdev)
replacement = 1;
else
/* rdev was removed and 'replacement'
* replaced it. rdev is not removed
* until all requests are finished.
*/
rdev = conf->disks[i].rdev;
break;
}
}
pr_debug("end_write_request %llu/%d, count %d, uptodate: %d.\n",
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
uptodate);
if (i == disks) {
BUG();
return;
}
if (replacement) {
if (!uptodate)
md_error(conf->mddev, rdev);
else if (is_badblock(rdev, sh->sector,
STRIPE_SECTORS,
&first_bad, &bad_sectors))
set_bit(R5_MadeGoodRepl, &sh->dev[i].flags);
} else {
if (!uptodate) {
set_bit(WriteErrorSeen, &rdev->flags);
set_bit(R5_WriteError, &sh->dev[i].flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED,
&rdev->mddev->recovery);
} else if (is_badblock(rdev, sh->sector,
STRIPE_SECTORS,
&first_bad, &bad_sectors))
set_bit(R5_MadeGood, &sh->dev[i].flags);
}
rdev_dec_pending(rdev, conf->mddev);
if (!test_and_clear_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags))
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous);
static void raid5_build_block(struct stripe_head *sh, int i, int previous)
{
struct r5dev *dev = &sh->dev[i];
bio_init(&dev->req);
dev->req.bi_io_vec = &dev->vec;
dev->req.bi_vcnt++;
dev->req.bi_max_vecs++;
dev->req.bi_private = sh;
dev->vec.bv_page = dev->page;
bio_init(&dev->rreq);
dev->rreq.bi_io_vec = &dev->rvec;
dev->rreq.bi_vcnt++;
dev->rreq.bi_max_vecs++;
dev->rreq.bi_private = sh;
dev->rvec.bv_page = dev->page;
dev->flags = 0;
dev->sector = compute_blocknr(sh, i, previous);
}
static void error(struct mddev *mddev, struct md_rdev *rdev)
{
char b[BDEVNAME_SIZE];
struct r5conf *conf = mddev->private;
unsigned long flags;
pr_debug("raid456: error called\n");
spin_lock_irqsave(&conf->device_lock, flags);
clear_bit(In_sync, &rdev->flags);
mddev->degraded = calc_degraded(conf);
spin_unlock_irqrestore(&conf->device_lock, flags);
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(Blocked, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT
"md/raid:%s: Disk failure on %s, disabling device.\n"
"md/raid:%s: Operation continuing on %d devices.\n",
mdname(mddev),
bdevname(rdev->bdev, b),
mdname(mddev),
conf->raid_disks - mddev->degraded);
}
/*
* Input: a 'big' sector number,
* Output: index of the data and parity disk, and the sector # in them.
*/
static sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
int previous, int *dd_idx,
struct stripe_head *sh)
{
sector_t stripe, stripe2;
sector_t chunk_number;
unsigned int chunk_offset;
int pd_idx, qd_idx;
int ddf_layout = 0;
sector_t new_sector;
int algorithm = previous ? conf->prev_algo
: conf->algorithm;
int sectors_per_chunk = previous ? conf->prev_chunk_sectors
: conf->chunk_sectors;
int raid_disks = previous ? conf->previous_raid_disks
: conf->raid_disks;
int data_disks = raid_disks - conf->max_degraded;
/* First compute the information on this sector */
/*
* Compute the chunk number and the sector offset inside the chunk
*/
chunk_offset = sector_div(r_sector, sectors_per_chunk);
chunk_number = r_sector;
/*
* Compute the stripe number
*/
stripe = chunk_number;
*dd_idx = sector_div(stripe, data_disks);
stripe2 = stripe;
/*
* Select the parity disk based on the user selected algorithm.
*/
pd_idx = qd_idx = -1;
switch(conf->level) {
case 4:
pd_idx = data_disks;
break;
case 5:
switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
pd_idx = data_disks - sector_div(stripe2, raid_disks);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
break;
case ALGORITHM_RIGHT_ASYMMETRIC:
pd_idx = sector_div(stripe2, raid_disks);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
break;
case ALGORITHM_LEFT_SYMMETRIC:
pd_idx = data_disks - sector_div(stripe2, raid_disks);
*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
break;
case ALGORITHM_RIGHT_SYMMETRIC:
pd_idx = sector_div(stripe2, raid_disks);
*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
break;
case ALGORITHM_PARITY_0:
pd_idx = 0;
(*dd_idx)++;
break;
case ALGORITHM_PARITY_N:
pd_idx = data_disks;
break;
default:
BUG();
}
break;
case 6:
switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
qd_idx = 0;
} else if (*dd_idx >= pd_idx)
(*dd_idx) += 2; /* D D P Q D */
break;
case ALGORITHM_RIGHT_ASYMMETRIC:
pd_idx = sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
qd_idx = 0;
} else if (*dd_idx >= pd_idx)
(*dd_idx) += 2; /* D D P Q D */
break;
case ALGORITHM_LEFT_SYMMETRIC:
pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = (pd_idx + 1) % raid_disks;
*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
break;
case ALGORITHM_RIGHT_SYMMETRIC:
pd_idx = sector_div(stripe2, raid_disks);
qd_idx = (pd_idx + 1) % raid_disks;
*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
break;
case ALGORITHM_PARITY_0:
pd_idx = 0;
qd_idx = 1;
(*dd_idx) += 2;
break;
case ALGORITHM_PARITY_N:
pd_idx = data_disks;
qd_idx = data_disks + 1;
break;
case ALGORITHM_ROTATING_ZERO_RESTART:
/* Exactly the same as RIGHT_ASYMMETRIC, but or
* of blocks for computing Q is different.
*/
pd_idx = sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
qd_idx = 0;
} else if (*dd_idx >= pd_idx)
(*dd_idx) += 2; /* D D P Q D */
ddf_layout = 1;
break;
case ALGORITHM_ROTATING_N_RESTART:
/* Same a left_asymmetric, by first stripe is
* D D D P Q rather than
* Q D D D P
*/
stripe2 += 1;
pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
qd_idx = 0;
} else if (*dd_idx >= pd_idx)
(*dd_idx) += 2; /* D D P Q D */
ddf_layout = 1;
break;
case ALGORITHM_ROTATING_N_CONTINUE:
/* Same as left_symmetric but Q is before P */
pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = (pd_idx + raid_disks - 1) % raid_disks;
*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
ddf_layout = 1;
break;
case ALGORITHM_LEFT_ASYMMETRIC_6:
/* RAID5 left_asymmetric, with Q on last device */
pd_idx = data_disks - sector_div(stripe2, raid_disks-1);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
qd_idx = raid_disks - 1;
break;
case ALGORITHM_RIGHT_ASYMMETRIC_6:
pd_idx = sector_div(stripe2, raid_disks-1);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
qd_idx = raid_disks - 1;
break;
case ALGORITHM_LEFT_SYMMETRIC_6:
pd_idx = data_disks - sector_div(stripe2, raid_disks-1);
*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
qd_idx = raid_disks - 1;
break;
case ALGORITHM_RIGHT_SYMMETRIC_6:
pd_idx = sector_div(stripe2, raid_disks-1);
*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
qd_idx = raid_disks - 1;
break;
case ALGORITHM_PARITY_0_6:
pd_idx = 0;
(*dd_idx)++;
qd_idx = raid_disks - 1;
break;
default:
BUG();
}
break;
}
if (sh) {
sh->pd_idx = pd_idx;
sh->qd_idx = qd_idx;
sh->ddf_layout = ddf_layout;
}
/*
* Finally, compute the new sector number
*/
new_sector = (sector_t)stripe * sectors_per_chunk + chunk_offset;
return new_sector;
}
static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
{
struct r5conf *conf = sh->raid_conf;
int raid_disks = sh->disks;
int data_disks = raid_disks - conf->max_degraded;
sector_t new_sector = sh->sector, check;
int sectors_per_chunk = previous ? conf->prev_chunk_sectors
: conf->chunk_sectors;
int algorithm = previous ? conf->prev_algo
: conf->algorithm;
sector_t stripe;
int chunk_offset;
sector_t chunk_number;
int dummy1, dd_idx = i;
sector_t r_sector;
struct stripe_head sh2;
chunk_offset = sector_div(new_sector, sectors_per_chunk);
stripe = new_sector;
if (i == sh->pd_idx)
return 0;
switch(conf->level) {
case 4: break;
case 5:
switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
case ALGORITHM_RIGHT_ASYMMETRIC:
if (i > sh->pd_idx)
i--;
break;
case ALGORITHM_LEFT_SYMMETRIC:
case ALGORITHM_RIGHT_SYMMETRIC:
if (i < sh->pd_idx)
i += raid_disks;
i -= (sh->pd_idx + 1);
break;
case ALGORITHM_PARITY_0:
i -= 1;
break;
case ALGORITHM_PARITY_N:
break;
default:
BUG();
}
break;
case 6:
if (i == sh->qd_idx)
return 0; /* It is the Q disk */
switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
case ALGORITHM_RIGHT_ASYMMETRIC:
case ALGORITHM_ROTATING_ZERO_RESTART:
case ALGORITHM_ROTATING_N_RESTART:
if (sh->pd_idx == raid_disks-1)
i--; /* Q D D D P */
else if (i > sh->pd_idx)
i -= 2; /* D D P Q D */
break;
case ALGORITHM_LEFT_SYMMETRIC:
case ALGORITHM_RIGHT_SYMMETRIC:
if (sh->pd_idx == raid_disks-1)
i--; /* Q D D D P */
else {
/* D D P Q D */
if (i < sh->pd_idx)
i += raid_disks;
i -= (sh->pd_idx + 2);
}
break;
case ALGORITHM_PARITY_0:
i -= 2;
break;
case ALGORITHM_PARITY_N:
break;
case ALGORITHM_ROTATING_N_CONTINUE:
/* Like left_symmetric, but P is before Q */
if (sh->pd_idx == 0)
i--; /* P D D D Q */
else {
/* D D Q P D */
if (i < sh->pd_idx)
i += raid_disks;
i -= (sh->pd_idx + 1);
}
break;
case ALGORITHM_LEFT_ASYMMETRIC_6:
case ALGORITHM_RIGHT_ASYMMETRIC_6:
if (i > sh->pd_idx)
i--;
break;
case ALGORITHM_LEFT_SYMMETRIC_6:
case ALGORITHM_RIGHT_SYMMETRIC_6:
if (i < sh->pd_idx)
i += data_disks + 1;
i -= (sh->pd_idx + 1);
break;
case ALGORITHM_PARITY_0_6:
i -= 1;
break;
default:
BUG();
}
break;
}
chunk_number = stripe * data_disks + i;
r_sector = chunk_number * sectors_per_chunk + chunk_offset;
check = raid5_compute_sector(conf, r_sector,
previous, &dummy1, &sh2);
if (check != sh->sector || dummy1 != dd_idx || sh2.pd_idx != sh->pd_idx
|| sh2.qd_idx != sh->qd_idx) {
printk(KERN_ERR "md/raid:%s: compute_blocknr: map not correct\n",
mdname(conf->mddev));
return 0;
}
return r_sector;
}
static void
schedule_reconstruction(struct stripe_head *sh, struct stripe_head_state *s,
int rcw, int expand)
{
int i, pd_idx = sh->pd_idx, disks = sh->disks;
struct r5conf *conf = sh->raid_conf;
int level = conf->level;
if (rcw) {
/* if we are not expanding this is a proper write request, and
* there will be bios with new data to be drained into the
* stripe cache
*/
if (!expand) {
sh->reconstruct_state = reconstruct_state_drain_run;
set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
} else
sh->reconstruct_state = reconstruct_state_run;
set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->towrite) {
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantdrain, &dev->flags);
if (!expand)
clear_bit(R5_UPTODATE, &dev->flags);
s->locked++;
}
}
if (s->locked + conf->max_degraded == disks)
if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
atomic_inc(&conf->pending_full_writes);
} else {
BUG_ON(level == 6);
BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
sh->reconstruct_state = reconstruct_state_prexor_drain_run;
set_bit(STRIPE_OP_PREXOR, &s->ops_request);
set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (i == pd_idx)
continue;
if (dev->towrite &&
(test_bit(R5_UPTODATE, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
set_bit(R5_Wantdrain, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
clear_bit(R5_UPTODATE, &dev->flags);
s->locked++;
}
}
}
/* keep the parity disk(s) locked while asynchronous operations
* are in flight
*/
set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
s->locked++;
if (level == 6) {
int qd_idx = sh->qd_idx;
struct r5dev *dev = &sh->dev[qd_idx];
set_bit(R5_LOCKED, &dev->flags);
clear_bit(R5_UPTODATE, &dev->flags);
s->locked++;
}
pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
__func__, (unsigned long long)sh->sector,
s->locked, s->ops_request);
}
/*
* Each stripe/dev can have one or more bion attached.
* toread/towrite point to the first in a chain.
* The bi_next chain must be in order.
*/
static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite)
{
struct bio **bip;
struct r5conf *conf = sh->raid_conf;
int firstwrite=0;
pr_debug("adding bi b#%llu to stripe s#%llu\n",
(unsigned long long)bi->bi_sector,
(unsigned long long)sh->sector);
/*
* If several bio share a stripe. The bio bi_phys_segments acts as a
* reference count to avoid race. The reference count should already be
* increased before this function is called (for example, in
* make_request()), so other bio sharing this stripe will not free the
* stripe. If a stripe is owned by one stripe, the stripe lock will
* protect it.
*/
spin_lock_irq(&sh->stripe_lock);
if (forwrite) {
bip = &sh->dev[dd_idx].towrite;
if (*bip == NULL)
firstwrite = 1;
} else
bip = &sh->dev[dd_idx].toread;
while (*bip && (*bip)->bi_sector < bi->bi_sector) {
if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector)
goto overlap;
bip = & (*bip)->bi_next;
}
if (*bip && (*bip)->bi_sector < bi->bi_sector + ((bi->bi_size)>>9))
goto overlap;
BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
if (*bip)
bi->bi_next = *bip;
*bip = bi;
raid5_inc_bi_active_stripes(bi);
if (forwrite) {
/* check if page is covered */
sector_t sector = sh->dev[dd_idx].sector;
for (bi=sh->dev[dd_idx].towrite;
sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
bi && bi->bi_sector <= sector;
bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
if (bi->bi_sector + (bi->bi_size>>9) >= sector)
sector = bi->bi_sector + (bi->bi_size>>9);
}
if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
}
spin_unlock_irq(&sh->stripe_lock);
pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
(unsigned long long)(*bip)->bi_sector,
(unsigned long long)sh->sector, dd_idx);
if (conf->mddev->bitmap && firstwrite) {
bitmap_startwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS, 0);
sh->bm_seq = conf->seq_flush+1;
set_bit(STRIPE_BIT_DELAY, &sh->state);
}
return 1;
overlap:
set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
spin_unlock_irq(&sh->stripe_lock);
return 0;
}
static void end_reshape(struct r5conf *conf);
static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
struct stripe_head *sh)
{
int sectors_per_chunk =
previous ? conf->prev_chunk_sectors : conf->chunk_sectors;
int dd_idx;
int chunk_offset = sector_div(stripe, sectors_per_chunk);
int disks = previous ? conf->previous_raid_disks : conf->raid_disks;
raid5_compute_sector(conf,
stripe * (disks - conf->max_degraded)
*sectors_per_chunk + chunk_offset,
previous,
&dd_idx, sh);
}
static void
handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
struct stripe_head_state *s, int disks,
struct bio **return_bi)
{
int i;
for (i = disks; i--; ) {
struct bio *bi;
int bitmap_end = 0;
if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
struct md_rdev *rdev;
rcu_read_lock();
rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && test_bit(In_sync, &rdev->flags))
atomic_inc(&rdev->nr_pending);
else
rdev = NULL;
rcu_read_unlock();
if (rdev) {
if (!rdev_set_badblocks(
rdev,
sh->sector,
STRIPE_SECTORS, 0))
md_error(conf->mddev, rdev);
rdev_dec_pending(rdev, conf->mddev);
}
}
spin_lock_irq(&sh->stripe_lock);
/* fail all writes first */
bi = sh->dev[i].towrite;
sh->dev[i].towrite = NULL;
spin_unlock_irq(&sh->stripe_lock);
if (bi) {
s->to_write--;
bitmap_end = 1;
}
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
while (bi && bi->bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
*return_bi = bi;
}
bi = nextbi;
}
if (bitmap_end)
bitmap_endwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS, 0, 0);
bitmap_end = 0;
/* and fail all 'written' */
bi = sh->dev[i].written;
sh->dev[i].written = NULL;
if (bi) bitmap_end = 1;
while (bi && bi->bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
if (!raid5_dec_bi_active_stripes(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
*return_bi = bi;
}
bi = bi2;
}
/* fail any reads if this device is non-operational and
* the data has not reached the cache yet.
*/
if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
(!test_bit(R5_Insync, &sh->dev[i].flags) ||
test_bit(R5_ReadError, &sh->dev[i].flags))) {
bi = sh->dev[i].toread;
sh->dev[i].toread = NULL;
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
wake_up(&conf->wait_for_overlap);
if (bi) s->to_read--;
while (bi && bi->bi_sector <
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi =
r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
if (!raid5_dec_bi_active_stripes(bi)) {
bi->bi_next = *return_bi;
*return_bi = bi;
}
bi = nextbi;
}
}
if (bitmap_end)
bitmap_endwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS, 0, 0);
/* If we were in the middle of a write the parity block might
* still be locked - so just clear all R5_LOCKED flags
*/
clear_bit(R5_LOCKED, &sh->dev[i].flags);
}
if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
if (atomic_dec_and_test(&conf->pending_full_writes))
md_wakeup_thread(conf->mddev->thread);
}
static void
handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
struct stripe_head_state *s)
{
int abort = 0;
int i;
clear_bit(STRIPE_SYNCING, &sh->state);
s->syncing = 0;
s->replacing = 0;
/* There is nothing more to do for sync/check/repair.
* Don't even need to abort as that is handled elsewhere
* if needed, and not always wanted e.g. if there is a known
* bad block here.
* For recover/replace we need to record a bad block on all
* non-sync devices, or abort the recovery
*/
if (test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery)) {
/* During recovery devices cannot be removed, so
* locking and refcounting of rdevs is not needed
*/
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = conf->disks[i].rdev;
if (rdev
&& !test_bit(Faulty, &rdev->flags)
&& !test_bit(In_sync, &rdev->flags)
&& !rdev_set_badblocks(rdev, sh->sector,
STRIPE_SECTORS, 0))
abort = 1;
rdev = conf->disks[i].replacement;
if (rdev
&& !test_bit(Faulty, &rdev->flags)
&& !test_bit(In_sync, &rdev->flags)
&& !rdev_set_badblocks(rdev, sh->sector,
STRIPE_SECTORS, 0))
abort = 1;
}
if (abort)
conf->recovery_disabled =
conf->mddev->recovery_disabled;
}
md_done_sync(conf->mddev, STRIPE_SECTORS, !abort);
}
static int want_replace(struct stripe_head *sh, int disk_idx)
{
struct md_rdev *rdev;
int rv = 0;
/* Doing recovery so rcu locking not required */
rdev = sh->raid_conf->disks[disk_idx].replacement;
if (rdev
&& !test_bit(Faulty, &rdev->flags)
&& !test_bit(In_sync, &rdev->flags)
&& (rdev->recovery_offset <= sh->sector
|| rdev->mddev->recovery_cp <= sh->sector))
rv = 1;
return rv;
}
/* fetch_block - checks the given member device to see if its data needs
* to be read or computed to satisfy a request.
*
* Returns 1 when no more member devices need to be checked, otherwise returns
* 0 to tell the loop in handle_stripe_fill to continue
*/
static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
int disk_idx, int disks)
{
struct r5dev *dev = &sh->dev[disk_idx];
struct r5dev *fdev[2] = { &sh->dev[s->failed_num[0]],
&sh->dev[s->failed_num[1]] };
/* is the data in this block needed, and can we get it? */
if (!test_bit(R5_LOCKED, &dev->flags) &&
!test_bit(R5_UPTODATE, &dev->flags) &&
(dev->toread ||
(dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
s->syncing || s->expanding ||
(s->replacing && want_replace(sh, disk_idx)) ||
(s->failed >= 1 && fdev[0]->toread) ||
(s->failed >= 2 && fdev[1]->toread) ||
(sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
!test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
(sh->raid_conf->level == 6 && s->failed && s->to_write))) {
/* we would like to get this block, possibly by computing it,
* otherwise read it if the backing disk is insync
*/
BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
BUG_ON(test_bit(R5_Wantread, &dev->flags));
if ((s->uptodate == disks - 1) &&
(s->failed && (disk_idx == s->failed_num[0] ||
disk_idx == s->failed_num[1]))) {
/* have disk failed, and we're requested to fetch it;
* do compute it
*/
pr_debug("Computing stripe %llu block %d\n",
(unsigned long long)sh->sector, disk_idx);
set_bit(STRIPE_COMPUTE_RUN, &sh->state);
set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
set_bit(R5_Wantcompute, &dev->flags);
sh->ops.target = disk_idx;
sh->ops.target2 = -1; /* no 2nd target */
s->req_compute = 1;
/* Careful: from this point on 'uptodate' is in the eye
* of raid_run_ops which services 'compute' operations
* before writes. R5_Wantcompute flags a block that will
* be R5_UPTODATE by the time it is needed for a
* subsequent operation.
*/
s->uptodate++;
return 1;
} else if (s->uptodate == disks-2 && s->failed >= 2) {
/* Computing 2-failure is *very* expensive; only
* do it if failed >= 2
*/
int other;
for (other = disks; other--; ) {
if (other == disk_idx)
continue;
if (!test_bit(R5_UPTODATE,
&sh->dev[other].flags))
break;
}
BUG_ON(other < 0);
pr_debug("Computing stripe %llu blocks %d,%d\n",
(unsigned long long)sh->sector,
disk_idx, other);
set_bit(STRIPE_COMPUTE_RUN, &sh->state);
set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
set_bit(R5_Wantcompute, &sh->dev[disk_idx].flags);
set_bit(R5_Wantcompute, &sh->dev[other].flags);
sh->ops.target = disk_idx;
sh->ops.target2 = other;
s->uptodate += 2;
s->req_compute = 1;
return 1;
} else if (test_bit(R5_Insync, &dev->flags)) {
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
pr_debug("Reading block %d (sync=%d)\n",
disk_idx, s->syncing);
}
}
return 0;
}
/**
* handle_stripe_fill - read or compute data to satisfy pending requests.
*/
static void handle_stripe_fill(struct stripe_head *sh,
struct stripe_head_state *s,
int disks)
{
int i;
/* look for blocks to read/compute, skip this if a compute
* is already in flight, or if the stripe contents are in the
* midst of changing due to a write
*/
if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
!sh->reconstruct_state)
for (i = disks; i--; )
if (fetch_block(sh, s, i, disks))
break;
set_bit(STRIPE_HANDLE, &sh->state);
}
/* handle_stripe_clean_event
* any written block on an uptodate or failed drive can be returned.
* Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
* never LOCKED, so we don't need to test 'failed' directly.
*/
static void handle_stripe_clean_event(struct r5conf *conf,
struct stripe_head *sh, int disks, struct bio **return_bi)
{
int i;
struct r5dev *dev;
for (i = disks; i--; )
if (sh->dev[i].written) {
dev = &sh->dev[i];
if (!test_bit(R5_LOCKED, &dev->flags) &&
test_bit(R5_UPTODATE, &dev->flags)) {
/* We can return any write requests */
struct bio *wbi, *wbi2;
pr_debug("Return write for disc %d\n", i);
wbi = dev->written;
dev->written = NULL;
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
wbi2 = r5_next_bio(wbi, dev->sector);
if (!raid5_dec_bi_active_stripes(wbi)) {
md_write_end(conf->mddev);
wbi->bi_next = *return_bi;
*return_bi = wbi;
}
wbi = wbi2;
}
bitmap_endwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS,
!test_bit(STRIPE_DEGRADED, &sh->state),
0);
}
}
if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
if (atomic_dec_and_test(&conf->pending_full_writes))
md_wakeup_thread(conf->mddev->thread);
}
static void handle_stripe_dirtying(struct r5conf *conf,
struct stripe_head *sh,
struct stripe_head_state *s,
int disks)
{
int rmw = 0, rcw = 0, i;
if (conf->max_degraded == 2) {
/* RAID6 requires 'rcw' in current implementation
* Calculate the real rcw later - for now fake it
* look like rcw is cheaper
*/
rcw = 1; rmw = 2;
} else for (i = disks; i--; ) {
/* would I have to read this buffer for read_modify_write */
struct r5dev *dev = &sh->dev[i];
if ((dev->towrite || i == sh->pd_idx) &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rmw++;
else
rmw += 2*disks; /* cannot read it */
}
/* Would I have to read this buffer for reconstruct_write */
if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags)) rcw++;
else
rcw += 2*disks;
}
}
pr_debug("for sector %llu, rmw=%d rcw=%d\n",
(unsigned long long)sh->sector, rmw, rcw);
set_bit(STRIPE_HANDLE, &sh->state);
if (rmw < rcw && rmw > 0)
/* prefer read-modify-write, but need to get some data */
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if ((dev->towrite || i == sh->pd_idx) &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
test_bit(R5_Wantcompute, &dev->flags)) &&
test_bit(R5_Insync, &dev->flags)) {
if (
test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
pr_debug("Read_old block "
"%d for r-m-w\n", i);
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
s->locked++;
} else {
set_bit(STRIPE_DELAYED, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
}
}
}
if (rcw <= rmw && rcw > 0) {
/* want reconstruct write, but need to get some data */
rcw = 0;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (!test_bit(R5_OVERWRITE, &dev->flags) &&
i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
test_bit