blob: 5d09256d7f81857d4a6861ef192a6f0d385118a8 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* 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!
*/
/*
* 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 <linux/nodemask.h>
#include <trace/events/block.h>
#include <linux/list_sort.h>
#include "md.h"
#include "raid5.h"
#include "raid0.h"
#include "md-bitmap.h"
#include "raid5-log.h"
#define UNSUPPORTED_MDDEV_FLAGS (1L << MD_FAILFAST_SUPPORTED)
#define cpu_to_group(cpu) cpu_to_node(cpu)
#define ANY_GROUP NUMA_NO_NODE
static bool devices_handle_discard_safely = false;
module_param(devices_handle_discard_safely, bool, 0644);
MODULE_PARM_DESC(devices_handle_discard_safely,
"Set to Y if all devices in each array reliably return zeroes on reads from discarded regions");
static struct workqueue_struct *raid5_wq;
static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
{
int hash = (sect >> RAID5_STRIPE_SHIFT(conf)) & HASH_MASK;
return &conf->stripe_hashtbl[hash];
}
static inline int stripe_hash_locks_hash(struct r5conf *conf, sector_t sect)
{
return (sect >> RAID5_STRIPE_SHIFT(conf)) & STRIPE_HASH_LOCKS_MASK;
}
static inline void lock_device_hash_lock(struct r5conf *conf, int hash)
__acquires(&conf->device_lock)
{
spin_lock_irq(conf->hash_locks + hash);
spin_lock(&conf->device_lock);
}
static inline void unlock_device_hash_lock(struct r5conf *conf, int hash)
__releases(&conf->device_lock)
{
spin_unlock(&conf->device_lock);
spin_unlock_irq(conf->hash_locks + hash);
}
static inline void lock_all_device_hash_locks_irq(struct r5conf *conf)
__acquires(&conf->device_lock)
{
int i;
spin_lock_irq(conf->hash_locks);
for (i = 1; i < NR_STRIPE_HASH_LOCKS; i++)
spin_lock_nest_lock(conf->hash_locks + i, conf->hash_locks);
spin_lock(&conf->device_lock);
}
static inline void unlock_all_device_hash_locks_irq(struct r5conf *conf)
__releases(&conf->device_lock)
{
int i;
spin_unlock(&conf->device_lock);
for (i = NR_STRIPE_HASH_LOCKS - 1; i; i--)
spin_unlock(conf->hash_locks + i);
spin_unlock_irq(conf->hash_locks);
}
/* 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 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 bool stripe_is_lowprio(struct stripe_head *sh)
{
return (test_bit(STRIPE_R5C_FULL_STRIPE, &sh->state) ||
test_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state)) &&
!test_bit(STRIPE_R5C_CACHING, &sh->state);
}
static void raid5_wakeup_stripe_thread(struct stripe_head *sh)
__must_hold(&sh->raid_conf->device_lock)
{
struct r5conf *conf = sh->raid_conf;
struct r5worker_group *group;
int thread_cnt;
int i, cpu = sh->cpu;
if (!cpu_online(cpu)) {
cpu = cpumask_any(cpu_online_mask);
sh->cpu = cpu;
}
if (list_empty(&sh->lru)) {
struct r5worker_group *group;
group = conf->worker_groups + cpu_to_group(cpu);
if (stripe_is_lowprio(sh))
list_add_tail(&sh->lru, &group->loprio_list);
else
list_add_tail(&sh->lru, &group->handle_list);
group->stripes_cnt++;
sh->group = group;
}
if (conf->worker_cnt_per_group == 0) {
md_wakeup_thread(conf->mddev->thread);
return;
}
group = conf->worker_groups + cpu_to_group(sh->cpu);
group->workers[0].working = true;
/* at least one worker should run to avoid race */
queue_work_on(sh->cpu, raid5_wq, &group->workers[0].work);
thread_cnt = group->stripes_cnt / MAX_STRIPE_BATCH - 1;
/* wakeup more workers */
for (i = 1; i < conf->worker_cnt_per_group && thread_cnt > 0; i++) {
if (group->workers[i].working == false) {
group->workers[i].working = true;
queue_work_on(sh->cpu, raid5_wq,
&group->workers[i].work);
thread_cnt--;
}
}
}
static void do_release_stripe(struct r5conf *conf, struct stripe_head *sh,
struct list_head *temp_inactive_list)
__must_hold(&conf->device_lock)
{
int i;
int injournal = 0; /* number of date pages with R5_InJournal */
BUG_ON(!list_empty(&sh->lru));
BUG_ON(atomic_read(&conf->active_stripes)==0);
if (r5c_is_writeback(conf->log))
for (i = sh->disks; i--; )
if (test_bit(R5_InJournal, &sh->dev[i].flags))
injournal++;
/*
* In the following cases, the stripe cannot be released to cached
* lists. Therefore, we make the stripe write out and set
* STRIPE_HANDLE:
* 1. when quiesce in r5c write back;
* 2. when resync is requested fot the stripe.
*/
if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state) ||
(conf->quiesce && r5c_is_writeback(conf->log) &&
!test_bit(STRIPE_HANDLE, &sh->state) && injournal != 0)) {
if (test_bit(STRIPE_R5C_CACHING, &sh->state))
r5c_make_stripe_write_out(sh);
set_bit(STRIPE_HANDLE, &sh->state);
}
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);
if (conf->worker_cnt_per_group == 0) {
if (stripe_is_lowprio(sh))
list_add_tail(&sh->lru,
&conf->loprio_list);
else
list_add_tail(&sh->lru,
&conf->handle_list);
} else {
raid5_wakeup_stripe_thread(sh);
return;
}
}
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)) {
if (!r5c_is_writeback(conf->log))
list_add_tail(&sh->lru, temp_inactive_list);
else {
WARN_ON(test_bit(R5_InJournal, &sh->dev[sh->pd_idx].flags));
if (injournal == 0)
list_add_tail(&sh->lru, temp_inactive_list);
else if (injournal == conf->raid_disks - conf->max_degraded) {
/* full stripe */
if (!test_and_set_bit(STRIPE_R5C_FULL_STRIPE, &sh->state))
atomic_inc(&conf->r5c_cached_full_stripes);
if (test_and_clear_bit(STRIPE_R5C_PARTIAL_STRIPE, &sh->state))
atomic_dec(&conf->r5c_cached_partial_stripes);
list_add_tail(&sh->lru, &conf->r5c_full_stripe_list);
r5c_check_cached_full_stripe(conf);
} else
/*
* STRIPE_R5C_PARTIAL_STRIPE is set in
* r5c_try_caching_write(). No need to
* set it again.
*/
list_add_tail(&sh->lru, &conf->r5c_partial_stripe_list);
}
}
}
}
static void __release_stripe(struct r5conf *conf, struct stripe_head *sh,
struct list_head *temp_inactive_list)
__must_hold(&conf->device_lock)
{
if (atomic_dec_and_test(&sh->count))
do_release_stripe(conf, sh, temp_inactive_list);
}
/*
* @hash could be NR_STRIPE_HASH_LOCKS, then we have a list of inactive_list
*
* Be careful: Only one task can add/delete stripes from temp_inactive_list at
* given time. Adding stripes only takes device lock, while deleting stripes
* only takes hash lock.
*/
static void release_inactive_stripe_list(struct r5conf *conf,
struct list_head *temp_inactive_list,
int hash)
{
int size;
bool do_wakeup = false;
unsigned long flags;
if (hash == NR_STRIPE_HASH_LOCKS) {
size = NR_STRIPE_HASH_LOCKS;
hash = NR_STRIPE_HASH_LOCKS - 1;
} else
size = 1;
while (size) {
struct list_head *list = &temp_inactive_list[size - 1];
/*
* We don't hold any lock here yet, raid5_get_active_stripe() might
* remove stripes from the list
*/
if (!list_empty_careful(list)) {
spin_lock_irqsave(conf->hash_locks + hash, flags);
if (list_empty(conf->inactive_list + hash) &&
!list_empty(list))
atomic_dec(&conf->empty_inactive_list_nr);
list_splice_tail_init(list, conf->inactive_list + hash);
do_wakeup = true;
spin_unlock_irqrestore(conf->hash_locks + hash, flags);
}
size--;
hash--;
}
if (do_wakeup) {
wake_up(&conf->wait_for_stripe);
if (atomic_read(&conf->active_stripes) == 0)
wake_up(&conf->wait_for_quiescent);
if (conf->retry_read_aligned)
md_wakeup_thread(conf->mddev->thread);
}
}
static int release_stripe_list(struct r5conf *conf,
struct list_head *temp_inactive_list)
__must_hold(&conf->device_lock)
{
struct stripe_head *sh, *t;
int count = 0;
struct llist_node *head;
head = llist_del_all(&conf->released_stripes);
head = llist_reverse_order(head);
llist_for_each_entry_safe(sh, t, head, release_list) {
int hash;
/* sh could be readded after STRIPE_ON_RELEASE_LIST is cleard */
smp_mb();
clear_bit(STRIPE_ON_RELEASE_LIST, &sh->state);
/*
* Don't worry the bit is set here, because if the bit is set
* again, the count is always > 1. This is true for
* STRIPE_ON_UNPLUG_LIST bit too.
*/
hash = sh->hash_lock_index;
__release_stripe(conf, sh, &temp_inactive_list[hash]);
count++;
}
return count;
}
void raid5_release_stripe(struct stripe_head *sh)
{
struct r5conf *conf = sh->raid_conf;
unsigned long flags;
struct list_head list;
int hash;
bool wakeup;
/* Avoid release_list until the last reference.
*/
if (atomic_add_unless(&sh->count, -1, 1))
return;
if (unlikely(!conf->mddev->thread) ||
test_and_set_bit(STRIPE_ON_RELEASE_LIST, &sh->state))
goto slow_path;
wakeup = llist_add(&sh->release_list, &conf->released_stripes);
if (wakeup)
md_wakeup_thread(conf->mddev->thread);
return;
slow_path:
/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
if (atomic_dec_and_lock_irqsave(&sh->count, &conf->device_lock, flags)) {
INIT_LIST_HEAD(&list);
hash = sh->hash_lock_index;
do_release_stripe(conf, sh, &list);
spin_unlock_irqrestore(&conf->device_lock, flags);
release_inactive_stripe_list(conf, &list, hash);
}
}
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, int hash)
{
struct stripe_head *sh = NULL;
struct list_head *first;
if (list_empty(conf->inactive_list + hash))
goto out;
first = (conf->inactive_list + hash)->next;
sh = list_entry(first, struct stripe_head, lru);
list_del_init(first);
remove_hash(sh);
atomic_inc(&conf->active_stripes);
BUG_ON(hash != sh->hash_lock_index);
if (list_empty(conf->inactive_list + hash))
atomic_inc(&conf->empty_inactive_list_nr);
out:
return sh;
}
#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
static void free_stripe_pages(struct stripe_head *sh)
{
int i;
struct page *p;
/* Have not allocate page pool */
if (!sh->pages)
return;
for (i = 0; i < sh->nr_pages; i++) {
p = sh->pages[i];
if (p)
put_page(p);
sh->pages[i] = NULL;
}
}
static int alloc_stripe_pages(struct stripe_head *sh, gfp_t gfp)
{
int i;
struct page *p;
for (i = 0; i < sh->nr_pages; i++) {
/* The page have allocated. */
if (sh->pages[i])
continue;
p = alloc_page(gfp);
if (!p) {
free_stripe_pages(sh);
return -ENOMEM;
}
sh->pages[i] = p;
}
return 0;
}
static int
init_stripe_shared_pages(struct stripe_head *sh, struct r5conf *conf, int disks)
{
int nr_pages, cnt;
if (sh->pages)
return 0;
/* Each of the sh->dev[i] need one conf->stripe_size */
cnt = PAGE_SIZE / conf->stripe_size;
nr_pages = (disks + cnt - 1) / cnt;
sh->pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL);
if (!sh->pages)
return -ENOMEM;
sh->nr_pages = nr_pages;
sh->stripes_per_page = cnt;
return 0;
}
#endif
static void shrink_buffers(struct stripe_head *sh)
{
int i;
int num = sh->raid_conf->pool_size;
#if PAGE_SIZE == DEFAULT_STRIPE_SIZE
for (i = 0; i < num ; i++) {
struct page *p;
WARN_ON(sh->dev[i].page != sh->dev[i].orig_page);
p = sh->dev[i].page;
if (!p)
continue;
sh->dev[i].page = NULL;
put_page(p);
}
#else
for (i = 0; i < num; i++)
sh->dev[i].page = NULL;
free_stripe_pages(sh); /* Free pages */
#endif
}
static int grow_buffers(struct stripe_head *sh, gfp_t gfp)
{
int i;
int num = sh->raid_conf->pool_size;
#if PAGE_SIZE == DEFAULT_STRIPE_SIZE
for (i = 0; i < num; i++) {
struct page *page;
if (!(page = alloc_page(gfp))) {
return 1;
}
sh->dev[i].page = page;
sh->dev[i].orig_page = page;
sh->dev[i].offset = 0;
}
#else
if (alloc_stripe_pages(sh, gfp))
return -ENOMEM;
for (i = 0; i < num; i++) {
sh->dev[i].page = raid5_get_dev_page(sh, i);
sh->dev[i].orig_page = sh->dev[i].page;
sh->dev[i].offset = raid5_get_page_offset(sh, i);
}
#endif
return 0;
}
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, seq;
BUG_ON(atomic_read(&sh->count) != 0);
BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
BUG_ON(stripe_operations_active(sh));
BUG_ON(sh->batch_head);
pr_debug("init_stripe called, stripe %llu\n",
(unsigned long long)sector);
retry:
seq = read_seqcount_begin(&conf->gen_lock);
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)) {
pr_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;
dev->sector = raid5_compute_blocknr(sh, i, previous);
}
if (read_seqcount_retry(&conf->gen_lock, seq))
goto retry;
sh->overwrite_disks = 0;
insert_hash(conf, sh);
sh->cpu = smp_processor_id();
set_bit(STRIPE_BATCH_READY, &sh->state);
}
static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector,
short generation)
{
struct stripe_head *sh;
pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector);
hlist_for_each_entry(sh, 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.
*
* Most calls to this function hold &conf->device_lock. Calls
* in raid5_run() do not require the lock as no other threads
* have been started yet.
*/
int raid5_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))
rdev = rcu_dereference(conf->disks[i].replacement);
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))
rdev = rcu_dereference(conf->disks[i].replacement);
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 bool has_failed(struct r5conf *conf)
{
int degraded = conf->mddev->degraded;
if (test_bit(MD_BROKEN, &conf->mddev->flags))
return true;
if (conf->mddev->reshape_position != MaxSector)
degraded = raid5_calc_degraded(conf);
return degraded > conf->max_degraded;
}
struct stripe_head *
raid5_get_active_stripe(struct r5conf *conf, sector_t sector,
int previous, int noblock, int noquiesce)
{
struct stripe_head *sh;
int hash = stripe_hash_locks_hash(conf, sector);
int inc_empty_inactive_list_flag;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
spin_lock_irq(conf->hash_locks + hash);
do {
wait_event_lock_irq(conf->wait_for_quiescent,
conf->quiesce == 0 || noquiesce,
*(conf->hash_locks + hash));
sh = __find_stripe(conf, sector, conf->generation - previous);
if (!sh) {
if (!test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) {
sh = get_free_stripe(conf, hash);
if (!sh && !test_bit(R5_DID_ALLOC,
&conf->cache_state))
set_bit(R5_ALLOC_MORE,
&conf->cache_state);
}
if (noblock && sh == NULL)
break;
r5c_check_stripe_cache_usage(conf);
if (!sh) {
set_bit(R5_INACTIVE_BLOCKED,
&conf->cache_state);
r5l_wake_reclaim(conf->log, 0);
wait_event_lock_irq(
conf->wait_for_stripe,
!list_empty(conf->inactive_list + hash) &&
(atomic_read(&conf->active_stripes)
< (conf->max_nr_stripes * 3 / 4)
|| !test_bit(R5_INACTIVE_BLOCKED,
&conf->cache_state)),
*(conf->hash_locks + hash));
clear_bit(R5_INACTIVE_BLOCKED,
&conf->cache_state);
} else {
init_stripe(sh, sector, previous);
atomic_inc(&sh->count);
}
} else if (!atomic_inc_not_zero(&sh->count)) {
spin_lock(&conf->device_lock);
if (!atomic_read(&sh->count)) {
if (!test_bit(STRIPE_HANDLE, &sh->state))
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&sh->lru) &&
!test_bit(STRIPE_EXPANDING, &sh->state));
inc_empty_inactive_list_flag = 0;
if (!list_empty(conf->inactive_list + hash))
inc_empty_inactive_list_flag = 1;
list_del_init(&sh->lru);
if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
atomic_inc(&conf->empty_inactive_list_nr);
if (sh->group) {
sh->group->stripes_cnt--;
sh->group = NULL;
}
}
atomic_inc(&sh->count);
spin_unlock(&conf->device_lock);
}
} while (sh == NULL);
spin_unlock_irq(conf->hash_locks + hash);
return sh;
}
static bool is_full_stripe_write(struct stripe_head *sh)
{
BUG_ON(sh->overwrite_disks > (sh->disks - sh->raid_conf->max_degraded));
return sh->overwrite_disks == (sh->disks - sh->raid_conf->max_degraded);
}
static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
__acquires(&sh1->stripe_lock)
__acquires(&sh2->stripe_lock)
{
if (sh1 > sh2) {
spin_lock_irq(&sh2->stripe_lock);
spin_lock_nested(&sh1->stripe_lock, 1);
} else {
spin_lock_irq(&sh1->stripe_lock);
spin_lock_nested(&sh2->stripe_lock, 1);
}
}
static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2)
__releases(&sh1->stripe_lock)
__releases(&sh2->stripe_lock)
{
spin_unlock(&sh1->stripe_lock);
spin_unlock_irq(&sh2->stripe_lock);
}
/* Only freshly new full stripe normal write stripe can be added to a batch list */
static bool stripe_can_batch(struct stripe_head *sh)
{
struct r5conf *conf = sh->raid_conf;
if (raid5_has_log(conf) || raid5_has_ppl(conf))
return false;
return test_bit(STRIPE_BATCH_READY, &sh->state) &&
!test_bit(STRIPE_BITMAP_PENDING, &sh->state) &&
is_full_stripe_write(sh);
}
/* we only do back search */
static void stripe_add_to_batch_list(struct r5conf *conf, struct stripe_head *sh)
{
struct stripe_head *head;
sector_t head_sector, tmp_sec;
int hash;
int dd_idx;
int inc_empty_inactive_list_flag;
/* Don't cross chunks, so stripe pd_idx/qd_idx is the same */
tmp_sec = sh->sector;
if (!sector_div(tmp_sec, conf->chunk_sectors))
return;
head_sector = sh->sector - RAID5_STRIPE_SECTORS(conf);
hash = stripe_hash_locks_hash(conf, head_sector);
spin_lock_irq(conf->hash_locks + hash);
head = __find_stripe(conf, head_sector, conf->generation);
if (head && !atomic_inc_not_zero(&head->count)) {
spin_lock(&conf->device_lock);
if (!atomic_read(&head->count)) {
if (!test_bit(STRIPE_HANDLE, &head->state))
atomic_inc(&conf->active_stripes);
BUG_ON(list_empty(&head->lru) &&
!test_bit(STRIPE_EXPANDING, &head->state));
inc_empty_inactive_list_flag = 0;
if (!list_empty(conf->inactive_list + hash))
inc_empty_inactive_list_flag = 1;
list_del_init(&head->lru);
if (list_empty(conf->inactive_list + hash) && inc_empty_inactive_list_flag)
atomic_inc(&conf->empty_inactive_list_nr);
if (head->group) {
head->group->stripes_cnt--;
head->group = NULL;
}
}
atomic_inc(&head->count);
spin_unlock(&conf->device_lock);
}
spin_unlock_irq(conf->hash_locks + hash);
if (!head)
return;
if (!stripe_can_batch(head))
goto out;
lock_two_stripes(head, sh);
/* clear_batch_ready clear the flag */
if (!stripe_can_batch(head) || !stripe_can_batch(sh))
goto unlock_out;
if (sh->batch_head)
goto unlock_out;
dd_idx = 0;
while (dd_idx == sh->pd_idx || dd_idx == sh->qd_idx)
dd_idx++;
if (head->dev[dd_idx].towrite->bi_opf != sh->dev[dd_idx].towrite->bi_opf ||
bio_op(head->dev[dd_idx].towrite) != bio_op(sh->dev[dd_idx].towrite))
goto unlock_out;
if (head->batch_head) {
spin_lock(&head->batch_head->batch_lock);
/* This batch list is already running */
if (!stripe_can_batch(head)) {
spin_unlock(&head->batch_head->batch_lock);
goto unlock_out;
}
/*
* We must assign batch_head of this stripe within the
* batch_lock, otherwise clear_batch_ready of batch head
* stripe could clear BATCH_READY bit of this stripe and
* this stripe->batch_head doesn't get assigned, which
* could confuse clear_batch_ready for this stripe
*/
sh->batch_head = head->batch_head;
/*
* at this point, head's BATCH_READY could be cleared, but we
* can still add the stripe to batch list
*/
list_add(&sh->batch_list, &head->batch_list);
spin_unlock(&head->batch_head->batch_lock);
} else {
head->batch_head = head;
sh->batch_head = head->batch_head;
spin_lock(&head->batch_lock);
list_add_tail(&sh->batch_list, &head->batch_list);
spin_unlock(&head->batch_lock);
}
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);
if (test_and_clear_bit(STRIPE_BIT_DELAY, &sh->state)) {
int seq = sh->bm_seq;
if (test_bit(STRIPE_BIT_DELAY, &sh->batch_head->state) &&
sh->batch_head->bm_seq > seq)
seq = sh->batch_head->bm_seq;
set_bit(STRIPE_BIT_DELAY, &sh->batch_head->state);
sh->batch_head->bm_seq = seq;
}
atomic_inc(&sh->count);
unlock_out:
unlock_two_stripes(head, sh);
out:
raid5_release_stripe(head);
}
/* 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 dispatch_bio_list(struct bio_list *tmp)
{
struct bio *bio;
while ((bio = bio_list_pop(tmp)))
submit_bio_noacct(bio);
}
static int cmp_stripe(void *priv, const struct list_head *a,
const struct list_head *b)
{
const struct r5pending_data *da = list_entry(a,
struct r5pending_data, sibling);
const struct r5pending_data *db = list_entry(b,
struct r5pending_data, sibling);
if (da->sector > db->sector)
return 1;
if (da->sector < db->sector)
return -1;
return 0;
}
static void dispatch_defer_bios(struct r5conf *conf, int target,
struct bio_list *list)
{
struct r5pending_data *data;
struct list_head *first, *next = NULL;
int cnt = 0;
if (conf->pending_data_cnt == 0)
return;
list_sort(NULL, &conf->pending_list, cmp_stripe);
first = conf->pending_list.next;
/* temporarily move the head */
if (conf->next_pending_data)
list_move_tail(&conf->pending_list,
&conf->next_pending_data->sibling);
while (!list_empty(&conf->pending_list)) {
data = list_first_entry(&conf->pending_list,
struct r5pending_data, sibling);
if (&data->sibling == first)
first = data->sibling.next;
next = data->sibling.next;
bio_list_merge(list, &data->bios);
list_move(&data->sibling, &conf->free_list);
cnt++;
if (cnt >= target)
break;
}
conf->pending_data_cnt -= cnt;
BUG_ON(conf->pending_data_cnt < 0 || cnt < target);
if (next != &conf->pending_list)
conf->next_pending_data = list_entry(next,
struct r5pending_data, sibling);
else
conf->next_pending_data = NULL;
/* list isn't empty */
if (first != &conf->pending_list)
list_move_tail(&conf->pending_list, first);
}
static void flush_deferred_bios(struct r5conf *conf)
{
struct bio_list tmp = BIO_EMPTY_LIST;
if (conf->pending_data_cnt == 0)
return;
spin_lock(&conf->pending_bios_lock);
dispatch_defer_bios(conf, conf->pending_data_cnt, &tmp);
BUG_ON(conf->pending_data_cnt != 0);
spin_unlock(&conf->pending_bios_lock);
dispatch_bio_list(&tmp);
}
static void defer_issue_bios(struct r5conf *conf, sector_t sector,
struct bio_list *bios)
{
struct bio_list tmp = BIO_EMPTY_LIST;
struct r5pending_data *ent;
spin_lock(&conf->pending_bios_lock);
ent = list_first_entry(&conf->free_list, struct r5pending_data,
sibling);
list_move_tail(&ent->sibling, &conf->pending_list);
ent->sector = sector;
bio_list_init(&ent->bios);
bio_list_merge(&ent->bios, bios);
conf->pending_data_cnt++;
if (conf->pending_data_cnt >= PENDING_IO_MAX)
dispatch_defer_bios(conf, PENDING_IO_ONE_FLUSH, &tmp);
spin_unlock(&conf->pending_bios_lock);
dispatch_bio_list(&tmp);
}
static void
raid5_end_read_request(struct bio *bi);
static void
raid5_end_write_request(struct bio *bi);
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;
struct stripe_head *head_sh = sh;
struct bio_list pending_bios = BIO_EMPTY_LIST;
struct r5dev *dev;
bool should_defer;
might_sleep();
if (log_stripe(sh, s) == 0)
return;
should_defer = conf->batch_bio_dispatch && conf->group_cnt;
for (i = disks; i--; ) {
int op, op_flags = 0;
int replace_only = 0;
struct bio *bi, *rbi;
struct md_rdev *rdev, *rrdev = NULL;
sh = head_sh;
if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
op = REQ_OP_WRITE;
if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
op_flags = REQ_FUA;
if (test_bit(R5_Discard, &sh->dev[i].flags))
op = REQ_OP_DISCARD;
} else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
op = REQ_OP_READ;
else if (test_and_clear_bit(R5_WantReplace,
&sh->dev[i].flags)) {
op = REQ_OP_WRITE;
replace_only = 1;
} else
continue;
if (test_and_clear_bit(R5_SyncIO, &sh->dev[i].flags))
op_flags |= REQ_SYNC;
again:
dev = &sh->dev[i];
bi = &dev->req;
rbi = &dev->rreq; /* For writing to replacement */
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 (op_is_write(op)) {
if (replace_only)
rdev = NULL;
if (rdev == rrdev)
/* We raced and saw duplicates */
rrdev = NULL;
} else {
if (test_bit(R5_ReadRepl, &head_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 (op_is_write(op) && rdev &&
test_bit(WriteErrorSeen, &rdev->flags)) {
sector_t first_bad;
int bad_sectors;
int bad = is_badblock(rdev, sh->sector, RAID5_STRIPE_SECTORS(conf),
&first_bad, &bad_sectors);
if (!bad)
break;
if (bad < 0) {
set_bit(BlockedBadBlocks, &rdev->flags);
if (!conf->mddev->external &&
conf->mddev->sb_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, RAID5_STRIPE_SECTORS(conf));
set_bit(STRIPE_IO_STARTED, &sh->state);
bio_init(bi, rdev->bdev, &dev->vec, 1, op | op_flags);
bi->bi_end_io = op_is_write(op)
? raid5_end_write_request
: raid5_end_read_request;
bi->bi_private = sh;
pr_debug("%s: for %llu schedule op %d on disc %d\n",
__func__, (unsigned long long)sh->sector,
bi->bi_opf, i);
atomic_inc(&sh->count);
if (sh != head_sh)
atomic_inc(&head_sh->count);
if (use_new_offset(conf, sh))
bi->bi_iter.bi_sector = (sh->sector
+ rdev->new_data_offset);
else
bi->bi_iter.bi_sector = (sh->sector
+ rdev->data_offset);
if (test_bit(R5_ReadNoMerge, &head_sh->dev[i].flags))
bi->bi_opf |= REQ_NOMERGE;
if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
if (!op_is_write(op) &&
test_bit(R5_InJournal, &sh->dev[i].flags))
/*
* issuing read for a page in journal, this
* must be preparing for prexor in rmw; read
* the data into orig_page
*/
sh->dev[i].vec.bv_page = sh->dev[i].orig_page;
else
sh->dev[i].vec.bv_page = sh->dev[i].page;
bi->bi_vcnt = 1;
bi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf);
bi->bi_io_vec[0].bv_offset = sh->dev[i].offset;
bi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf);
/*
* If this is discard request, set bi_vcnt 0. We don't
* want to confuse SCSI because SCSI will replace payload
*/
if (op == REQ_OP_DISCARD)
bi->bi_vcnt = 0;
if (rrdev)
set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
if (conf->mddev->gendisk)
trace_block_bio_remap(bi,
disk_devt(conf->mddev->gendisk),
sh->dev[i].sector);
if (should_defer && op_is_write(op))
bio_list_add(&pending_bios, bi);
else
submit_bio_noacct(bi);
}
if (rrdev) {
if (s->syncing || s->expanding || s->expanded
|| s->replacing)
md_sync_acct(rrdev->bdev, RAID5_STRIPE_SECTORS(conf));
set_bit(STRIPE_IO_STARTED, &sh->state);
bio_init(rbi, rrdev->bdev, &dev->rvec, 1, op | op_flags);
BUG_ON(!op_is_write(op));
rbi->bi_end_io = raid5_end_write_request;
rbi->bi_private = sh;
pr_debug("%s: for %llu schedule op %d on "
"replacement disc %d\n",
__func__, (unsigned long long)sh->sector,
rbi->bi_opf, i);
atomic_inc(&sh->count);
if (sh != head_sh)
atomic_inc(&head_sh->count);
if (use_new_offset(conf, sh))
rbi->bi_iter.bi_sector = (sh->sector
+ rrdev->new_data_offset);
else
rbi->bi_iter.bi_sector = (sh->sector
+ rrdev->data_offset);
if (test_bit(R5_SkipCopy, &sh->dev[i].flags))
WARN_ON(test_bit(R5_UPTODATE, &sh->dev[i].flags));
sh->dev[i].rvec.bv_page = sh->dev[i].page;
rbi->bi_vcnt = 1;
rbi->bi_io_vec[0].bv_len = RAID5_STRIPE_SIZE(conf);
rbi->bi_io_vec[0].bv_offset = sh->dev[i].offset;
rbi->bi_iter.bi_size = RAID5_STRIPE_SIZE(conf);
/*
* If this is discard request, set bi_vcnt 0. We don't
* want to confuse SCSI because SCSI will replace payload
*/
if (op == REQ_OP_DISCARD)
rbi->bi_vcnt = 0;
if (conf->mddev->gendisk)
trace_block_bio_remap(rbi,
disk_devt(conf->mddev->gendisk),
sh->dev[i].sector);
if (should_defer && op_is_write(op))
bio_list_add(&pending_bios, rbi);
else
submit_bio_noacct(rbi);
}
if (!rdev && !rrdev) {
if (op_is_write(op))
set_bit(STRIPE_DEGRADED, &sh->state);
pr_debug("skip op %d on disc %d for sector %llu\n",
bi->bi_opf, i, (unsigned long long)sh->sector);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
}
if (!head_sh->batch_head)
continue;
sh = list_first_entry(&sh->batch_list, struct stripe_head,
batch_list);
if (sh != head_sh)
goto again;
}
if (should_defer && !bio_list_empty(&pending_bios))
defer_issue_bios(conf, head_sh->sector, &pending_bios);
}
static struct dma_async_tx_descriptor *
async_copy_data(int frombio, struct bio *bio, struct page **page,
unsigned int poff, sector_t sector, struct dma_async_tx_descriptor *tx,
struct stripe_head *sh, int no_skipcopy)
{
struct bio_vec bvl;
struct bvec_iter iter;
struct page *bio_page;
int page_offset;
struct async_submit_ctl submit;
enum async_tx_flags flags = 0;
struct r5conf *conf = sh->raid_conf;
if (bio->bi_iter.bi_sector >= sector)
page_offset = (signed)(bio->bi_iter.bi_sector - sector) * 512;
else
page_offset = (signed)(sector - bio->bi_iter.bi_sector) * -512;
if (frombio)
flags |= ASYNC_TX_FENCE;
init_async_submit(&submit, flags, tx, NULL, NULL, NULL);
bio_for_each_segment(bvl, bio, iter) {
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 > RAID5_STRIPE_SIZE(conf))
clen = RAID5_STRIPE_SIZE(conf) - page_offset;
else
clen = len;
if (clen > 0) {
b_offset += bvl.bv_offset;
bio_page = bvl.bv_page;
if (frombio) {
if (conf->skip_copy &&
b_offset == 0 && page_offset == 0 &&
clen == RAID5_STRIPE_SIZE(conf) &&
!no_skipcopy)
*page = bio_page;
else
tx = async_memcpy(*page, bio_page, page_offset + poff,
b_offset, clen, &submit);
} else
tx = async_memcpy(bio_page, *page, b_offset,
page_offset + poff, 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;
int i;
struct r5conf *conf = sh->raid_conf;
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_iter.bi_sector <
dev->sector + RAID5_STRIPE_SECTORS(conf)) {
rbi2 = r5_next_bio(conf, rbi, dev->sector);
bio_endio(rbi);
rbi = rbi2;
}
}
}
clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_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;
struct r5conf *conf = sh->raid_conf;
BUG_ON(sh->batch_head);
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_iter.bi_sector <
dev->sector + RAID5_STRIPE_SECTORS(conf)) {
tx = async_copy_data(0, rbi, &dev->page,
dev->offset,
dev->sector, tx, sh, 0);
rbi = r5_next_bio(conf, 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);
raid5_release_stripe(sh);
}
/* return a pointer to the address conversion region of the scribble buffer */
static struct page **to_addr_page(struct raid5_percpu *percpu, int i)
{
return percpu->scribble + i * percpu->scribble_obj_size;
}
/* 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, int i)
{
return (void *) (to_addr_page(percpu, i) + sh->disks + 2);
}
/*
* Return a pointer to record offset address.
*/
static unsigned int *
to_addr_offs(struct stripe_head *sh, struct raid5_percpu *percpu)
{
return (unsigned int *) (to_addr_conv(sh, percpu, 0) + 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 = to_addr_page(percpu, 0);
unsigned int *off_srcs = to_addr_offs(sh, percpu);
int target = sh->ops.target;
struct r5dev *tgt = &sh->dev[target];
struct page *xor_dest = tgt->page;
unsigned int off_dest = tgt->offset;
int count = 0;
struct dma_async_tx_descriptor *tx;
struct async_submit_ctl submit;
int i;
BUG_ON(sh->batch_head);
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) {
off_srcs[count] = sh->dev[i].offset;
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, 0));
if (unlikely(count == 1))
tx = async_memcpy(xor_dest, xor_srcs[0], off_dest, off_srcs[0],
RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
else
tx = async_xor_offs(xor_dest, off_dest, xor_srcs, off_srcs, count,
RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
return tx;
}
/* set_syndrome_sources - populate source buffers for gen_syndrome
* @srcs - (struct page *) array of size sh->disks
* @offs - (unsigned int) array of offset for each page
* @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,
unsigned int *offs,
struct stripe_head *sh,
int srctype)
{
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);
struct r5dev *dev = &sh->dev[i];
if (i == sh->qd_idx || i == sh->pd_idx ||
(srctype == SYNDROME_SRC_ALL) ||
(srctype == SYNDROME_SRC_WANT_DRAIN &&
(test_bit(R5_Wantdrain, &dev->flags) ||
test_bit(R5_InJournal, &dev->flags))) ||
(srctype == SYNDROME_SRC_WRITTEN &&
(dev->written ||
test_bit(R5_InJournal, &dev->flags)))) {
if (test_bit(R5_InJournal, &dev->flags))
srcs[slot] = sh->dev[i].orig_page;
else
srcs[slot] = sh->dev[i].page;
/*
* For R5_InJournal, PAGE_SIZE must be 4KB and will
* not shared page. In that case, dev[i].offset
* is 0.
*/
offs[slot] = sh->dev[i].offset;
}
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 = to_addr_page(percpu, 0);
unsigned int *offs = to_addr_offs(sh, percpu);
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;
unsigned int dest_off;
int i;
int count;
BUG_ON(sh->batch_head);
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;
dest_off = tgt->offset;
atomic_inc(&sh->count);
if (target == qd_idx) {
count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_ALL);
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, 0));
tx = async_gen_syndrome(blocks, offs, count+2,
RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
} else {
/* Compute any data- or p-drive using XOR */
count = 0;
for (i = disks; i-- ; ) {
if (i == target || i == qd_idx)
continue;
offs[count] = sh->dev[i].offset;
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, 0));
tx = async_xor_offs(dest, dest_off, blocks, offs, count,
RAID5_STRIPE_SIZE(sh->raid_conf), &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 = to_addr_page(percpu, 0);
unsigned int *offs = to_addr_offs(sh, percpu);
struct async_submit_ctl submit;
BUG_ON(sh->batch_head);
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++) {
offs[i] = 0;
blocks[i] = NULL;
}
count = 0;
i = d0_idx;
do {
int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
offs[slot] = sh->dev[i].offset;
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, 0));
return async_gen_syndrome(blocks, offs, syndrome_disks+2,
RAID5_STRIPE_SIZE(sh->raid_conf),
&submit);
} else {
struct page *dest;
unsigned int dest_off;
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;
offs[count] = sh->dev[i].offset;
blocks[count++] = sh->dev[i].page;
}
dest = sh->dev[data_target].page;
dest_off = sh->dev[data_target].offset;
init_async_submit(&submit,
ASYNC_TX_FENCE|ASYNC_TX_XOR_ZERO_DST,
NULL, NULL, NULL,
to_addr_conv(sh, percpu, 0));
tx = async_xor_offs(dest, dest_off, blocks, offs, count,
RAID5_STRIPE_SIZE(sh->raid_conf),
&submit);
count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_ALL);
init_async_submit(&submit, ASYNC_TX_FENCE, tx,
ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
return async_gen_syndrome(blocks, offs, count+2,
RAID5_STRIPE_SIZE(sh->raid_conf),
&submit);
}
} else {
init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
ops_complete_compute, sh,
to_addr_conv(sh, percpu, 0));
if (failb == syndrome_disks) {
/* We're missing D+P. */
return async_raid6_datap_recov(syndrome_disks+2,
RAID5_STRIPE_SIZE(sh->raid_conf),
faila,
blocks, offs, &submit);
} else {
/* We're missing D+D. */
return async_raid6_2data_recov(syndrome_disks+2,
RAID5_STRIPE_SIZE(sh->raid_conf),
faila, failb,
blocks, offs, &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);
if (r5c_is_writeback(sh->raid_conf->log))
/*
* raid5-cache write back uses orig_page during prexor.
* After prexor, it is time to free orig_page
*/
r5c_release_extra_page(sh);
}
static struct dma_async_tx_descriptor *
ops_run_prexor5(struct stripe_head *sh, struct raid5_percpu *percpu,
struct dma_async_tx_descriptor *tx)
{
int disks = sh->disks;
struct page **xor_srcs = to_addr_page(percpu, 0);
unsigned int *off_srcs = to_addr_offs(sh, percpu);
int count = 0, pd_idx = sh->pd_idx, i;
struct async_submit_ctl submit;
/* existing parity data subtracted */
unsigned int off_dest = off_srcs[count] = sh->dev[pd_idx].offset;
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
BUG_ON(sh->batch_head);
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_InJournal, &dev->flags)) {
/*
* For this case, PAGE_SIZE must be equal to 4KB and
* page offset is zero.
*/
off_srcs[count] = dev->offset;
xor_srcs[count++] = dev->orig_page;
} else if (test_bit(R5_Wantdrain, &dev->flags)) {
off_srcs[count] = dev->offset;
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, 0));
tx = async_xor_offs(xor_dest, off_dest, xor_srcs, off_srcs, count,
RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
return tx;
}
static struct dma_async_tx_descriptor *
ops_run_prexor6(struct stripe_head *sh, struct raid5_percpu *percpu,
struct dma_async_tx_descriptor *tx)
{
struct page **blocks = to_addr_page(percpu, 0);
unsigned int *offs = to_addr_offs(sh, percpu);
int count;
struct async_submit_ctl submit;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
count = set_syndrome_sources(blocks, offs, sh, SYNDROME_SRC_WANT_DRAIN);
init_async_submit(&submit, ASYNC_TX_FENCE|ASYNC_TX_PQ_XOR_DST, tx,
ops_complete_prexor, sh, to_addr_conv(sh, percpu, 0));
tx = async_gen_syndrome(blocks, offs, count+2,
RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
return tx;
}
static struct dma_async_tx_descriptor *
ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
{
struct r5conf *conf = sh->raid_conf;
int disks = sh->disks;
int i;
struct stripe_head *head_sh = sh;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev;
struct bio *chosen;
sh = head_sh;
if (test_and_clear_bit(R5_Wantdrain, &head_sh->dev[i].flags)) {
struct bio *wbi;
again:
dev = &sh->dev[i];
/*
* clear R5_InJournal, so when rewriting a page in
* journal, it is not skipped by r5l_log_stripe()
*/
clear_bit(R5_InJournal, &dev->flags);
spin_lock_irq(&sh->stripe_lock);
chosen = dev->towrite;
dev->towrite = NULL;
sh->overwrite_disks = 0;
BUG_ON(dev->written);
wbi = dev->written = chosen;
spin_unlock_irq(&sh->stripe_lock);
WARN_ON(dev->page != dev->orig_page);
while (wbi && wbi->bi_iter.bi_sector <
dev->sector + RAID5_STRIPE_SECTORS(conf)) {
if (wbi->bi_opf & REQ_FUA)
set_bit(R5_WantFUA, &dev->flags);
if (wbi->bi_opf & REQ_SYNC)
set_bit(R5_SyncIO, &dev->flags);
if (bio_op(wbi) == REQ_OP_DISCARD)
set_bit(R5_Discard, &dev->flags);
else {
tx = async_copy_data(1, wbi, &dev->page,
dev->offset,
dev->sector, tx, sh,
r5c_is_writeback(conf->log));
if (dev->page != dev->orig_page &&
!r5c_is_writeback(conf->log)) {
set_bit(R5_SkipCopy, &dev->flags);
clear_bit(R5_UPTODATE, &dev->flags);
clear_bit(R5_OVERWRITE, &dev->flags);
}
}
wbi = r5_next_bio(conf, wbi, dev->sector);
}
if (head_sh->batch_head) {
sh = list_first_entry(&sh->batch_list,
struct stripe_head,
batch_list);
if (sh == head_sh)
continue;
goto again;
}
}
}
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, discard = 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);
discard |= test_bit(R5_Discard, &sh->dev[i].flags);
}
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (dev->written || i == pd_idx || i == qd_idx) {
if (!discard && !test_bit(R5_SkipCopy, &dev->flags)) {
set_bit(R5_UPTODATE, &dev->flags);
if (test_bit(STRIPE_EXPAND_READY, &sh->state))
set_bit(R5_Expanded, &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);
raid5_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;
unsigned int *off_srcs;
struct async_submit_ctl submit;
int count, pd_idx = sh->pd_idx, i;
struct page *xor_dest;
unsigned int off_dest;
int prexor = 0;
unsigned long flags;
int j = 0;
struct stripe_head *head_sh = sh;
int last_stripe;
pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = 0; i < sh->disks; i++) {
if (pd_idx == i)
continue;
if (!test_bit(R5_Discard, &sh->dev[i].flags))
break;
}
if (i >= sh->disks) {
atomic_inc(&sh->count);
set_bit(R5_Discard, &sh->dev[pd_idx].flags);
ops_complete_reconstruct(sh);
return;
}
again:
count = 0;
xor_srcs = to_addr_page(percpu, j);
off_srcs = to_addr_offs(sh, percpu);
/* check if prexor is active which means only process blocks
* that are part of a read-modify-write (written)
*/
if (head_sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
prexor = 1;
off_dest = off_srcs[count] = sh->dev[pd_idx].offset;
xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (head_sh->dev[i].written ||
test_bit(R5_InJournal, &head_sh->dev[i].flags)) {
off_srcs[count] = dev->offset;
xor_srcs[count++] = dev->page;
}
}
} else {
xor_dest = sh->dev[pd_idx].page;
off_dest = sh->dev[pd_idx].offset;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (i != pd_idx) {
off_srcs[count] = dev->offset;
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
*/
last_stripe = !head_sh->batch_head ||
list_first_entry(&sh->batch_list,
struct stripe_head, batch_list) == head_sh;
if (last_stripe) {
flags = ASYNC_TX_ACK |
(prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST);
atomic_inc(&head_sh->count);
init_async_submit(&submit, flags, tx, ops_complete_reconstruct, head_sh,
to_addr_conv(sh, percpu, j));
} else {
flags = prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST;
init_async_submit(&submit, flags, tx, NULL, NULL,
to_addr_conv(sh, percpu, j));
}
if (unlikely(count == 1))
tx = async_memcpy(xor_dest, xor_srcs[0], off_dest, off_srcs[0],
RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
else
tx = async_xor_offs(xor_dest, off_dest, xor_srcs, off_srcs, count,
RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
if (!last_stripe) {
j++;
sh = list_first_entry(&sh->batch_list, struct stripe_head,
batch_list);
goto again;
}
}
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;
unsigned int *offs;
int count, i, j = 0;
struct stripe_head *head_sh = sh;
int last_stripe;
int synflags;
unsigned long txflags;
pr_debug("%s: stripe %llu\n", __func__, (unsigned long long)sh->sector);
for (i = 0; i < sh->disks; i++) {
if (sh->pd_idx == i || sh->qd_idx == i)
continue;
if (!test_bit(R5_Discard, &sh->dev[i].flags))
break;
}
if (i >= sh->disks) {
atomic_inc(&sh->count);
set_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
set_bit(R5_Discard, &sh->dev[sh->qd_idx].flags);
ops_complete_reconstruct(sh);
return;
}
again:
blocks = to_addr_page(percpu, j);
offs = to_addr_offs(sh, percpu);
if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
synflags = SYNDROME_SRC_WRITTEN;
txflags = ASYNC_TX_ACK | ASYNC_TX_PQ_XOR_DST;
} else {
synflags = SYNDROME_SRC_ALL;
txflags = ASYNC_TX_ACK;
}
count = set_syndrome_sources(blocks, offs, sh, synflags);
last_stripe = !head_sh->batch_head ||
list_first_entry(&sh->batch_list,
struct stripe_head, batch_list) == head_sh;
if (last_stripe) {
atomic_inc(&head_sh->count);
init_async_submit(&submit, txflags, tx, ops_complete_reconstruct,
head_sh, to_addr_conv(sh, percpu, j));
} else
init_async_submit(&submit, 0, tx, NULL, NULL,
to_addr_conv(sh, percpu, j));
tx = async_gen_syndrome(blocks, offs, count+2,
RAID5_STRIPE_SIZE(sh->raid_conf), &submit);
if (!last_stripe) {
j++;
sh = list_first_entry(&sh->batch_list, struct stripe_head,
batch_list);
goto again;
}
}
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);
raid5_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;
unsigned int off_dest;
struct page **xor_srcs = to_addr_page(percpu, 0);
unsigned int *off_srcs = to_addr_offs(sh, percpu);
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);
BUG_ON(sh->batch_head);
count = 0;
xor_dest = sh->dev[pd_idx].page;
off_dest = sh->dev[pd_idx].offset;
off_srcs[count] = off_dest;
xor_srcs[count++] = xor_dest;
for (i = disks; i--; ) {
if (i == pd_idx || i == qd_idx)
continue;
off_srcs[count] = sh->dev[i].offset;
xor_srcs[count++] = sh->dev[i].page;
}
init_async_submit(&submit, 0, NULL, NULL, NULL,
to_addr_conv(sh, percpu, 0));
tx = async_xor_val_offs(xor_dest, off_dest, xor_srcs, off_srcs, count,
RAID5_STRIPE_SIZE(sh->raid_conf),
&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 = to_addr_page(percpu, 0);
unsigned int *offs = to_addr_offs(sh, percpu);
struct async_submit_ctl submit;
int count;
pr_debug("%s: stripe %llu checkp: %d\n", __func__,
(unsigned long long)sh->sector, checkp);
BUG_ON(sh->batch_head);
count = set_syndrome_sources(srcs, offs, sh, SYNDROME_SRC_ALL);
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, 0));
async_syndrome_val(srcs, offs, count+2,
RAID5_STRIPE_SIZE(sh->raid_conf),
&sh->ops.zero_sum_result, percpu->spare_page, 0, &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;
local_lock(&conf->percpu->lock);
percpu = this_cpu_ptr(conf->percpu);
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)) {
if (level < 6)
tx = ops_run_prexor5(sh, percpu, tx);
else
tx = ops_run_prexor6(sh, percpu, tx);
}
if (test_bit(STRIPE_OP_PARTIAL_PARITY, &ops_request))
tx = ops_run_partial_parity(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 && !sh->batch_head) {
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);
}
}
local_unlock(&conf->percpu->lock);
}
static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
{
#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
kfree(sh->pages);
#endif
if (sh->ppl_page)
__free_page(sh->ppl_page);
kmem_cache_free(sc, sh);
}
static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
int disks, struct r5conf *conf)
{
struct stripe_head *sh;
sh = kmem_cache_zalloc(sc, gfp);
if (sh) {
spin_lock_init(&sh->stripe_lock);
spin_lock_init(&sh->batch_lock);
INIT_LIST_HEAD(&sh->batch_list);
INIT_LIST_HEAD(&sh->lru);
INIT_LIST_HEAD(&sh->r5c);
INIT_LIST_HEAD(&sh->log_list);
atomic_set(&sh->count, 1);
sh->raid_conf = conf;
sh->log_start = MaxSector;
if (raid5_has_ppl(conf)) {
sh->ppl_page = alloc_page(gfp);
if (!sh->ppl_page) {
free_stripe(sc, sh);
return NULL;
}
}
#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
if (init_stripe_shared_pages(sh, conf, disks)) {
free_stripe(sc, sh);
return NULL;
}
#endif
}
return sh;
}
static int grow_one_stripe(struct r5conf *conf, gfp_t gfp)
{
struct stripe_head *sh;
sh = alloc_stripe(conf->slab_cache, gfp, conf->pool_size, conf);
if (!sh)
return 0;
if (grow_buffers(sh, gfp)) {
shrink_buffers(sh);
free_stripe(conf->slab_cache, sh);
return 0;
}
sh->hash_lock_index =
conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS;
/* we just created an active stripe so... */
atomic_inc(&conf->active_stripes);
raid5_release_stripe(sh);
conf->max_nr_stripes++;
return 1;
}
static int grow_stripes(struct r5conf *conf, int num)
{
struct kmem_cache *sc;
size_t namelen = sizeof(conf->cache_name[0]);
int devs = max(conf->raid_disks, conf->previous_raid_disks);
if (conf->mddev->gendisk)
snprintf(conf->cache_name[0], namelen,
"raid%d-%s", conf->level, mdname(conf->mddev));
else
snprintf(conf->cache_name[0], namelen,
"raid%d-%p", conf->level, conf->mddev);
snprintf(conf->cache_name[1], namelen, "%.27s-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, GFP_KERNEL))
return 1;
return 0;
}
/**
* scribble_alloc - allocate percpu scribble buffer for required size
* of the scribble region
* @percpu: from for_each_present_cpu() of the caller
* @num: total number of disks in the array
* @cnt: scribble objs count for required size of the scribble region
*
* The scribble buffer 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 int scribble_alloc(struct raid5_percpu *percpu,
int num, int cnt)
{
size_t obj_size =
sizeof(struct page *) * (num + 2) +
sizeof(addr_conv_t) * (num + 2) +
sizeof(unsigned int) * (num + 2);
void *scribble;
/*
* If here is in raid array suspend context, it is in memalloc noio
* context as well, there is no potential recursive memory reclaim
* I/Os with the GFP_KERNEL flag.
*/
scribble = kvmalloc_array(cnt, obj_size, GFP_KERNEL);
if (!scribble)
return -ENOMEM;
kvfree(percpu->scribble);
percpu->scribble = scribble;
percpu->scribble_obj_size = obj_size;
return 0;
}
static int resize_chunks(struct r5conf *conf, int new_disks, int new_sectors)
{
unsigned long cpu;
int err = 0;
/*
* Never shrink. And mddev_suspend() could deadlock if this is called
* from raid5d. In that case, scribble_disks and scribble_sectors
* should equal to new_disks and new_sectors
*/
if (conf->scribble_disks >= new_disks &&
conf->scribble_sectors >= new_sectors)
return 0;
mddev_suspend(conf->mddev);
cpus_read_lock();
for_each_present_cpu(cpu) {
struct raid5_percpu *percpu;
percpu = per_cpu_ptr(conf->percpu, cpu);
err = scribble_alloc(percpu, new_disks,
new_sectors / RAID5_STRIPE_SECTORS(conf));
if (err)
break;
}
cpus_read_unlock();
mddev_resume(conf->mddev);
if (!err) {
conf->scribble_disks = new_disks;
conf->scribble_sectors = new_sectors;
}
return err;
}
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 transfer 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 failure 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;
int err = 0;
struct kmem_cache *sc;
int i;
int hash, cnt;
md_allow_write(conf->mddev);
/* 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;
/* Need to ensure auto-resizing doesn't interfere */
mutex_lock(&conf->cache_size_mutex);
for (i = conf->max_nr_stripes; i; i--) {
nsh = alloc_stripe(sc, GFP_KERNEL, newsize, conf);
if (!nsh)
break;
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);
free_stripe(sc, nsh);
}
kmem_cache_destroy(sc);
mutex_unlock(&conf->cache_size_mutex);
return -ENOMEM;
}
/* Step 2 - Must use GFP_NOIO now.
* OK, we have enough stripes, start collecting inactive
* stripes and copying them over
*/
hash = 0;
cnt = 0;
list_for_each_entry(nsh, &newstripes, lru) {
lock_device_hash_lock(conf, hash);
wait_event_cmd(conf->wait_for_stripe,
!list_empty(conf->inactive_list + hash),
unlock_device_hash_lock(conf, hash),
lock_device_hash_lock(conf, hash));
osh = get_free_stripe(conf, hash);
unlock_device_hash_lock(conf, hash);
#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
for (i = 0; i < osh->nr_pages; i++) {
nsh->pages[i] = osh->pages[i];
osh->pages[i] = NULL;
}
#endif
for(i=0; i<conf->pool_size; i++) {
nsh->dev[i].page = osh->dev[i].page;
nsh->dev[i].orig_page = osh->dev[i].page;
nsh->dev[i].offset = osh->dev[i].offset;
}
nsh->hash_lock_index = hash;
free_stripe(conf->slab_cache, osh);
cnt++;
if (cnt >= conf->max_nr_stripes / NR_STRIPE_HASH_LOCKS +
!!((conf->max_nr_stripes % NR_STRIPE_HASH_LOCKS) > hash)) {
hash++;
cnt = 0;
}
}
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 = kcalloc(newsize, sizeof(struct disk_info), GFP_NOIO);
if (ndisks) {
for (i = 0; i < conf->pool_size; i++)
ndisks[i] = conf->disks[i];
for (i = conf->pool_size; i < newsize; i++) {
ndisks[i].extra_page = alloc_page(GFP_NOIO);
if (!ndisks[i].extra_page)
err = -ENOMEM;
}
if (err) {
for (i = conf->pool_size; i < newsize; i++)
if (ndisks[i].extra_page)
put_page(ndisks[i].extra_page);
kfree(ndisks);
} else {
kfree(conf->disks);
conf->disks = ndisks;
}
} else
err = -ENOMEM;
conf->slab_cache = sc;
conf->active_name = 1-conf->active_name;
/* 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);
#if PAGE_SIZE != DEFAULT_STRIPE_SIZE
for (i = 0; i < nsh->nr_pages; i++) {
if (nsh->pages[i])
continue;
nsh->pages[i] = alloc_page(GFP_NOIO);
if (!nsh->pages[i])
err = -ENOMEM;
}
for (i = conf->raid_disks; i < newsize; i++) {
if (nsh->dev[i].page)
continue;
nsh->dev[i].page = raid5_get_dev_page(nsh, i);
nsh->dev[i].orig_page = nsh->dev[i].page;
nsh->dev[i].offset = raid5_get_page_offset(nsh, i);
}
#else
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;
nsh->dev[i].orig_page = p;
nsh->dev[i].offset = 0;
if (!p)
err = -ENOMEM;
}
#endif
raid5_release_stripe(nsh);
}
/* critical section pass, GFP_NOIO no longer needed */
if (!err)
conf->pool_size = newsize;
mutex_unlock(&conf->cache_size_mutex);
return err;
}
static int drop_one_stripe(struct r5conf *conf)
{
struct stripe_head *sh;
int hash = (conf->max_nr_stripes - 1) & STRIPE_HASH_LOCKS_MASK;
spin_lock_irq(conf->hash_locks + hash);
sh = get_free_stripe(conf, hash);
spin_unlock_irq(conf->hash_locks + hash);
if (!sh)
return 0;
BUG_ON(atomic_read(&sh->count));
shrink_buffers(sh);
free_stripe(conf->slab_cache, sh);
atomic_dec(&conf->active_stripes);
conf->max_nr_stripes--;
return 1;
}
static void shrink_stripes(struct r5conf *conf)
{
while (conf->max_nr_stripes &&
drop_one_stripe(conf))
;
kmem_cache_destroy(conf->slab_cache);
conf->slab_cache = NULL;
}
/*
* This helper wraps rcu_dereference_protected() and can be used when
* it is known that the nr_pending of the rdev is elevated.
*/
static struct md_rdev *rdev_pend_deref(struct md_rdev __rcu *rdev)
{
return rcu_dereference_protected(rdev,
atomic_read(&rcu_access_pointer(rdev)->nr_pending));
}
/*
* This helper wraps rcu_dereference_protected() and should be used
* when it is known that the mddev_lock() is held. This is safe
* seeing raid5_remove_disk() has the same lock held.
*/
static struct md_rdev *rdev_mdlock_deref(struct mddev *mddev,
struct md_rdev __rcu *rdev)
{
return rcu_dereference_protected(rdev,
lockdep_is_held(&mddev->reconfig_mutex));
}
static void raid5_end_read_request(struct bio * bi)
{
struct stripe_head *sh = bi->bi_private;
struct r5conf *conf = sh->raid_conf;
int disks = sh->disks, i;
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, error %d.\n",
(unsigned long long)sh->sector, i, atomic_read(&sh->count),
bi->bi_status);
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 = rdev_pend_deref(conf->disks[i].replacement);
if (!rdev)
rdev = rdev_pend_deref(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 (!bi->bi_status) {
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
*/
pr_info_ratelimited(
"md/raid:%s: read error corrected (%lu sectors at %llu on %pg)\n",
mdname(conf->mddev), RAID5_STRIPE_SECTORS(conf),
(unsigned long long)s,
rdev->bdev);
atomic_add(RAID5_STRIPE_SECTORS(conf), &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 (test_bit(R5_InJournal, &sh->dev[i].flags))
/*
* end read for a page in journal, this
* must be preparing for prexor in rmw
*/
set_bit(R5_OrigPageUPTDODATE, &sh->dev[i].flags);
if (atomic_read(&rdev->read_errors))
atomic_set(&rdev->read_errors, 0);
} else {
int retry = 0;
int set_bad = 0;
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
if (!(bi->bi_status == BLK_STS_PROTECTION))
atomic_inc(&rdev->read_errors);
if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
pr_warn_ratelimited(
"md/raid:%s: read error on replacement device (sector %llu on %pg).\n",
mdname(conf->mddev),
(unsigned long long)s,
rdev->bdev);
else if (conf->mddev->degraded >= conf->max_degraded) {
set_bad = 1;
pr_warn_ratelimited(
"md/raid:%s: read error not correctable (sector %llu on %pg).\n",
mdname(conf->mddev),
(unsigned long long)s,
rdev->bdev);
} else if (test_bit(R5_ReWrite, &sh->dev[i].flags)) {
/* Oh, no!!! */
set_bad = 1;
pr_warn_ratelimited(
"md/raid:%s: read error NOT corrected!! (sector %llu on %pg).\n",
mdname(conf->mddev),
(unsigned long long)s,
rdev->bdev);
} else if (atomic_read(&rdev->read_errors)
> conf->max_nr_stripes) {
if (!test_bit(Faulty, &rdev->flags)) {
pr_warn("md/raid:%s: %d read_errors > %d stripes\n",
mdname(conf->mddev),
atomic_read(&rdev->read_errors),
conf->max_nr_stripes);
pr_warn("md/raid:%s: Too many read errors, failing device %pg.\n",
mdname(conf->mddev), rdev->bdev);
}
} else
retry = 1;
if (set_bad && test_bit(In_sync, &rdev->flags)
&& !test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
retry = 1;
if (retry)
if (sh->qd_idx >= 0 && sh->pd_idx == i)
set_bit(R5_ReadError, &sh->dev[i].flags);
else 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, RAID5_STRIPE_SECTORS(conf), 0)))
md_error(conf->mddev, rdev);
}
}
rdev_dec_pending(rdev, conf->mddev);
bio_uninit(bi);
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
raid5_release_stripe(sh);
}
static void raid5_end_write_request(struct bio *bi)
{
struct stripe_head *sh = bi->bi_private;
struct r5conf *conf = sh->raid_conf;
int disks = sh->disks, i;
struct md_rdev *rdev;
sector_t first_bad;
int bad_sectors;
int replacement = 0;
for (i = 0 ; i < disks; i++) {
if (bi == &sh->dev[i].req) {
rdev = rdev_pend_deref(