* 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->bm_write is the number of the last batch successfully written.
+ * conf->bm_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 bm_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/module.h>
#include <linux/slab.h>
#include "raid6.h"
#include <linux/raid/bitmap.h>
+#include <linux/async_tx.h>
/*
* Stripe cache
#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)
/*
* The following can be used to debug the driver
*/
-#define RAID5_DEBUG 0
#define RAID5_PARANOIA 1
#if RAID5_PARANOIA && defined(CONFIG_SMP)
# define CHECK_DEVLOCK() assert_spin_locked(&conf->device_lock)
# define CHECK_DEVLOCK()
#endif
-#define PRINTK(x...) ((void)(RAID5_DEBUG && printk(x)))
-#if RAID5_DEBUG
+#ifdef DEBUG
#define inline
#define __inline__
#endif
+#define printk_rl(args...) ((void) (printk_ratelimit() && printk(args)))
+
#if !RAID6_USE_EMPTY_ZERO_PAGE
/* In .bss so it's zeroed */
const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
disk++;
return (disk < raid_disks) ? disk : 0;
}
+
+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 (raid5_conf_t *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 __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
{
if (atomic_dec_and_test(&sh->count)) {
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))
+ if (test_bit(STRIPE_DELAYED, &sh->state)) {
list_add_tail(&sh->lru, &conf->delayed_list);
- else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
- conf->seq_write == sh->bm_seq)
+ blk_plug_device(conf->mddev->queue);
+ } 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 {
+ blk_plug_device(conf->mddev->queue);
+ } else {
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)) {
atomic_dec(&conf->preread_active_stripes);
if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
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 inline void remove_hash(struct stripe_head *sh)
{
- PRINTK("remove_hash(), stripe %llu\n", (unsigned long long)sh->sector);
+ pr_debug("remove_hash(), stripe %llu\n",
+ (unsigned long long)sh->sector);
hlist_del_init(&sh->hash);
}
{
struct hlist_head *hp = stripe_hash(conf, sh->sector);
- PRINTK("insert_hash(), stripe %llu\n", (unsigned long long)sh->sector);
+ pr_debug("insert_hash(), stripe %llu\n",
+ (unsigned long long)sh->sector);
CHECK_DEVLOCK();
hlist_add_head(&sh->hash, hp);
BUG_ON(atomic_read(&sh->count) != 0);
BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
-
+ BUG_ON(stripe_operations_active(sh));
+
CHECK_DEVLOCK();
- PRINTK("init_stripe called, stripe %llu\n",
+ pr_debug("init_stripe called, stripe %llu\n",
(unsigned long long)sh->sector);
remove_hash(sh);
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- if (dev->toread || dev->towrite || dev->written ||
+ if (dev->toread || dev->read || dev->towrite || dev->written ||
test_bit(R5_LOCKED, &dev->flags)) {
- printk("sector=%llx i=%d %p %p %p %d\n",
+ printk(KERN_ERR "sector=%llx i=%d %p %p %p %p %d\n",
(unsigned long long)sh->sector, i, dev->toread,
- dev->towrite, dev->written,
+ dev->read, dev->towrite, dev->written,
test_bit(R5_LOCKED, &dev->flags));
BUG();
}
struct hlist_node *hn;
CHECK_DEVLOCK();
- PRINTK("__find_stripe, sector %llu\n", (unsigned long long)sector);
+ 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->disks == disks)
return sh;
- PRINTK("__stripe %llu not in cache\n", (unsigned long long)sector);
+ pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector);
return NULL;
}
static void unplug_slaves(mddev_t *mddev);
-static void raid5_unplug_device(request_queue_t *q);
+static void raid5_unplug_device(struct request_queue *q);
static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector, int disks,
int pd_idx, int noblock)
{
struct stripe_head *sh;
- PRINTK("get_stripe, sector %llu\n", (unsigned long long)sector);
+ pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
spin_lock_irq(&conf->device_lock);
} else {
if (!test_bit(STRIPE_HANDLE, &sh->state))
atomic_inc(&conf->active_stripes);
- if (list_empty(&sh->lru))
+ if (list_empty(&sh->lru) &&
+ !test_bit(STRIPE_EXPANDING, &sh->state))
BUG();
list_del_init(&sh->lru);
}
return sh;
}
-static int grow_one_stripe(raid5_conf_t *conf)
-{
- struct stripe_head *sh;
- sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
- if (!sh)
- return 0;
- memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev));
- sh->raid_conf = conf;
- spin_lock_init(&sh->lock);
-
- if (grow_buffers(sh, conf->raid_disks)) {
- shrink_buffers(sh, conf->raid_disks);
- kmem_cache_free(conf->slab_cache, sh);
- return 0;
- }
- sh->disks = conf->raid_disks;
- /* 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 void
+raid5_end_read_request(struct bio *bi, int error);
+static void
+raid5_end_write_request(struct bio *bi, int error);
-static int grow_stripes(raid5_conf_t *conf, int num)
+static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
{
- kmem_cache_t *sc;
- int devs = conf->raid_disks;
+ raid5_conf_t *conf = sh->raid_conf;
+ int i, disks = sh->disks;
- sprintf(conf->cache_name[0], "raid5/%s", mdname(conf->mddev));
- sprintf(conf->cache_name[1], "raid5/%s-alt", mdname(conf->mddev));
- 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, NULL);
- if (!sc)
- return 1;
- conf->slab_cache = sc;
- conf->pool_size = devs;
- while (num--)
- if (!grow_one_stripe(conf))
- return 1;
- return 0;
-}
+ might_sleep();
-#ifdef CONFIG_MD_RAID5_RESHAPE
-static int resize_stripes(raid5_conf_t *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;
- int err = 0;
- kmem_cache_t *sc;
- int i;
+ for (i = disks; i--; ) {
+ int rw;
+ struct bio *bi;
+ mdk_rdev_t *rdev;
+ if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
+ rw = WRITE;
+ else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
+ rw = READ;
+ else
+ continue;
- if (newsize <= conf->pool_size)
- return 0; /* never bother to shrink */
+ bi = &sh->dev[i].req;
- /* 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, NULL);
- if (!sc)
- return -ENOMEM;
+ bi->bi_rw = rw;
+ if (rw == WRITE)
+ bi->bi_end_io = raid5_end_write_request;
+ else
+ bi->bi_end_io = raid5_end_read_request;
- for (i = conf->max_nr_stripes; i; i--) {
- nsh = kmem_cache_alloc(sc, GFP_KERNEL);
- if (!nsh)
- break;
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(Faulty, &rdev->flags))
+ rdev = NULL;
+ if (rdev)
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
- memset(nsh, 0, sizeof(*nsh) + (newsize-1)*sizeof(struct r5dev));
+ if (rdev) {
+ if (s->syncing || s->expanding || s->expanded)
+ md_sync_acct(rdev->bdev, STRIPE_SECTORS);
- nsh->raid_conf = conf;
- spin_lock_init(&nsh->lock);
+ set_bit(STRIPE_IO_STARTED, &sh->state);
- 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);
+ 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);
+ bi->bi_sector = sh->sector + rdev->data_offset;
+ bi->bi_flags = 1 << BIO_UPTODATE;
+ bi->bi_vcnt = 1;
+ bi->bi_max_vecs = 1;
+ bi->bi_idx = 0;
+ bi->bi_io_vec = &sh->dev[i].vec;
+ 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 (rw == WRITE &&
+ test_bit(R5_ReWrite, &sh->dev[i].flags))
+ atomic_add(STRIPE_SECTORS,
+ &rdev->corrected_errors);
+ generic_make_request(bi);
+ } else {
+ 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);
}
- 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,
- unplug_slaves(conf->mddev)
- );
- 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.
- */
- 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;
+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;
- /* 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);
+ if (bio->bi_sector >= sector)
+ page_offset = (signed)(bio->bi_sector - sector) * 512;
+ else
+ page_offset = (signed)(sector - bio->bi_sector) * -512;
+ bio_for_each_segment(bvl, bio, i) {
+ int len = bio_iovec_idx(bio, i)->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 += bio_iovec_idx(bio, i)->bv_offset;
+ bio_page = bio_iovec_idx(bio, i)->bv_page;
+ if (frombio)
+ tx = async_memcpy(page, bio_page, page_offset,
+ b_offset, clen,
+ ASYNC_TX_DEP_ACK,
+ tx, NULL, NULL);
+ else
+ tx = async_memcpy(bio_page, page, b_offset,
+ page_offset, clen,
+ ASYNC_TX_DEP_ACK,
+ tx, NULL, NULL);
+ }
+ if (clen < len) /* hit end of page */
+ break;
+ page_offset += len;
}
- /* 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;
+ return tx;
}
-#endif
-static int drop_one_stripe(raid5_conf_t *conf)
+static void ops_complete_biofill(void *stripe_head_ref)
{
- struct stripe_head *sh;
+ struct stripe_head *sh = stripe_head_ref;
+ struct bio *return_bi = NULL;
+ raid5_conf_t *conf = sh->raid_conf;
+ int i;
- 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, conf->pool_size);
- kmem_cache_free(conf->slab_cache, sh);
- atomic_dec(&conf->active_stripes);
- return 1;
-}
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
-static void shrink_stripes(raid5_conf_t *conf)
-{
- while (drop_one_stripe(conf))
- ;
-
- if (conf->slab_cache)
- kmem_cache_destroy(conf->slab_cache);
- conf->slab_cache = NULL;
-}
-
-static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done,
- int error)
-{
- struct stripe_head *sh = bi->bi_private;
- raid5_conf_t *conf = sh->raid_conf;
- int disks = sh->disks, i;
- int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
-
- if (bi->bi_size)
- return 1;
-
- for (i=0 ; i<disks; i++)
- if (bi == &sh->dev[i].req)
- break;
-
- PRINTK("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 0;
- }
+ /* clear completed biofills */
+ spin_lock_irq(&conf->device_lock);
+ for (i = sh->disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
- if (uptodate) {
-#if 0
- struct bio *bio;
- unsigned long flags;
- spin_lock_irqsave(&conf->device_lock, flags);
- /* we can return a buffer if we bypassed the cache or
- * if the top buffer is not in highmem. If there are
- * multiple buffers, leave the extra work to
- * handle_stripe
+ /* 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
*/
- buffer = sh->bh_read[i];
- if (buffer &&
- (!PageHighMem(buffer->b_page)
- || buffer->b_page == bh->b_page )
- ) {
- sh->bh_read[i] = buffer->b_reqnext;
- buffer->b_reqnext = NULL;
- } else
- buffer = NULL;
- spin_unlock_irqrestore(&conf->device_lock, flags);
- if (sh->bh_page[i]==bh->b_page)
- set_buffer_uptodate(bh);
- if (buffer) {
- if (buffer->b_page != bh->b_page)
- memcpy(buffer->b_data, bh->b_data, bh->b_size);
- buffer->b_end_io(buffer, 1);
- }
-#else
- set_bit(R5_UPTODATE, &sh->dev[i].flags);
-#endif
- if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
- printk(KERN_INFO "raid5: read error corrected!!\n");
- clear_bit(R5_ReadError, &sh->dev[i].flags);
- clear_bit(R5_ReWrite, &sh->dev[i].flags);
- }
- if (atomic_read(&conf->disks[i].rdev->read_errors))
- atomic_set(&conf->disks[i].rdev->read_errors, 0);
- } else {
- int retry = 0;
- clear_bit(R5_UPTODATE, &sh->dev[i].flags);
- atomic_inc(&conf->disks[i].rdev->read_errors);
- if (conf->mddev->degraded)
- printk(KERN_WARNING "raid5: read error not correctable.\n");
- else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
- /* Oh, no!!! */
- printk(KERN_WARNING "raid5: read error NOT corrected!!\n");
- else if (atomic_read(&conf->disks[i].rdev->read_errors)
- > conf->max_nr_stripes)
- printk(KERN_WARNING
- "raid5: Too many read errors, failing device.\n");
- else
- retry = 1;
- if (retry)
- set_bit(R5_ReadError, &sh->dev[i].flags);
- else {
- clear_bit(R5_ReadError, &sh->dev[i].flags);
- clear_bit(R5_ReWrite, &sh->dev[i].flags);
- md_error(conf->mddev, conf->disks[i].rdev);
+ 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 (--rbi->bi_phys_segments == 0) {
+ rbi->bi_next = return_bi;
+ return_bi = rbi;
+ }
+ rbi = rbi2;
+ }
}
}
- rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
-#if 0
- /* must restore b_page before unlocking buffer... */
- if (sh->bh_page[i] != bh->b_page) {
- bh->b_page = sh->bh_page[i];
- bh->b_data = page_address(bh->b_page);
- clear_buffer_uptodate(bh);
- }
-#endif
- clear_bit(R5_LOCKED, &sh->dev[i].flags);
+ spin_unlock_irq(&conf->device_lock);
+ clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
+
+ return_io(return_bi);
+
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
- return 0;
}
-static int raid5_end_write_request (struct bio *bi, unsigned int bytes_done,
- int error)
+static void ops_run_biofill(struct stripe_head *sh)
{
- struct stripe_head *sh = bi->bi_private;
+ struct dma_async_tx_descriptor *tx = NULL;
raid5_conf_t *conf = sh->raid_conf;
- int disks = sh->disks, i;
- unsigned long flags;
- int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
-
- if (bi->bi_size)
- return 1;
+ int i;
- for (i=0 ; i<disks; i++)
- if (bi == &sh->dev[i].req)
- break;
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
- PRINTK("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 0;
+ for (i = sh->disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ if (test_bit(R5_Wantfill, &dev->flags)) {
+ struct bio *rbi;
+ spin_lock_irq(&conf->device_lock);
+ dev->read = rbi = dev->toread;
+ dev->toread = NULL;
+ spin_unlock_irq(&conf->device_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);
+ }
+ }
}
- spin_lock_irqsave(&conf->device_lock, flags);
- if (!uptodate)
- md_error(conf->mddev, conf->disks[i].rdev);
+ atomic_inc(&sh->count);
+ async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
+ ops_complete_biofill, sh);
+}
- rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
-
- clear_bit(R5_LOCKED, &sh->dev[i].flags);
+static void ops_complete_compute5(void *stripe_head_ref)
+{
+ struct stripe_head *sh = stripe_head_ref;
+ int target = sh->ops.target;
+ struct r5dev *tgt = &sh->dev[target];
+
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
+
+ set_bit(R5_UPTODATE, &tgt->flags);
+ BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
+ clear_bit(R5_Wantcompute, &tgt->flags);
+ 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(conf, sh);
- spin_unlock_irqrestore(&conf->device_lock, flags);
- return 0;
+ release_stripe(sh);
}
-
-static sector_t compute_blocknr(struct stripe_head *sh, int i);
-
-static void raid5_build_block (struct stripe_head *sh, int i)
+static struct dma_async_tx_descriptor *
+ops_run_compute5(struct stripe_head *sh, unsigned long ops_request)
{
- struct r5dev *dev = &sh->dev[i];
+ /* kernel stack size limits the total number of disks */
+ int disks = sh->disks;
+ struct page *xor_srcs[disks];
+ 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;
+ int i;
- bio_init(&dev->req);
- dev->req.bi_io_vec = &dev->vec;
- dev->req.bi_vcnt++;
- dev->req.bi_max_vecs++;
- dev->vec.bv_page = dev->page;
- dev->vec.bv_len = STRIPE_SIZE;
- dev->vec.bv_offset = 0;
+ pr_debug("%s: stripe %llu block: %d\n",
+ __func__, (unsigned long long)sh->sector, target);
+ BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
- dev->req.bi_sector = sh->sector;
- dev->req.bi_private = sh;
+ for (i = disks; i--; )
+ if (i != target)
+ xor_srcs[count++] = sh->dev[i].page;
- dev->flags = 0;
- dev->sector = compute_blocknr(sh, i);
+ atomic_inc(&sh->count);
+
+ if (unlikely(count == 1))
+ tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
+ 0, NULL, ops_complete_compute5, sh);
+ else
+ tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
+ ASYNC_TX_XOR_ZERO_DST, NULL,
+ ops_complete_compute5, sh);
+
+ /* ack now if postxor is not set to be run */
+ if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request))
+ async_tx_ack(tx);
+
+ return tx;
}
-static void error(mddev_t *mddev, mdk_rdev_t *rdev)
+static void ops_complete_prexor(void *stripe_head_ref)
{
- char b[BDEVNAME_SIZE];
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
- PRINTK("raid5: error called\n");
+ struct stripe_head *sh = stripe_head_ref;
- if (!test_bit(Faulty, &rdev->flags)) {
- mddev->sb_dirty = 1;
- if (test_bit(In_sync, &rdev->flags)) {
- conf->working_disks--;
- mddev->degraded++;
- conf->failed_disks++;
- clear_bit(In_sync, &rdev->flags);
- /*
- * if recovery was running, make sure it aborts.
- */
- set_bit(MD_RECOVERY_ERR, &mddev->recovery);
- }
- set_bit(Faulty, &rdev->flags);
- printk (KERN_ALERT
- "raid5: Disk failure on %s, disabling device."
- " Operation continuing on %d devices\n",
- bdevname(rdev->bdev,b), conf->working_disks);
- }
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
}
-/*
- * Input: a 'big' sector number,
- * Output: index of the data and parity disk, and the sector # in them.
- */
-static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks,
- unsigned int data_disks, unsigned int * dd_idx,
- unsigned int * pd_idx, raid5_conf_t *conf)
+static struct dma_async_tx_descriptor *
+ops_run_prexor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
{
- long stripe;
- unsigned long chunk_number;
- unsigned int chunk_offset;
- sector_t new_sector;
- int sectors_per_chunk = conf->chunk_size >> 9;
+ /* kernel stack size limits the total number of disks */
+ int disks = sh->disks;
+ struct page *xor_srcs[disks];
+ int count = 0, pd_idx = sh->pd_idx, i;
- /* First compute the information on this sector */
+ /* existing parity data subtracted */
+ struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
- /*
- * Compute the chunk number and the sector offset inside the chunk
- */
- chunk_offset = sector_div(r_sector, sectors_per_chunk);
- chunk_number = r_sector;
- BUG_ON(r_sector != chunk_number);
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
- /*
- * Compute the stripe number
- */
- stripe = chunk_number / data_disks;
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ /* Only process blocks that are known to be uptodate */
+ if (dev->towrite && test_bit(R5_Wantprexor, &dev->flags))
+ xor_srcs[count++] = dev->page;
+ }
- /*
- * Compute the data disk and parity disk indexes inside the stripe
- */
- *dd_idx = chunk_number % data_disks;
+ tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
+ ASYNC_TX_DEP_ACK | ASYNC_TX_XOR_DROP_DST, tx,
+ ops_complete_prexor, sh);
- /*
- * Select the parity disk based on the user selected algorithm.
+ return tx;
+}
+
+static struct dma_async_tx_descriptor *
+ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
+ unsigned long ops_request)
+{
+ int disks = sh->disks;
+ int pd_idx = sh->pd_idx, i;
+
+ /* check if prexor is active which means only process blocks
+ * that are part of a read-modify-write (Wantprexor)
*/
- switch(conf->level) {
- case 4:
- *pd_idx = data_disks;
- break;
- case 5:
- switch (conf->algorithm) {
- case ALGORITHM_LEFT_ASYMMETRIC:
- *pd_idx = data_disks - stripe % raid_disks;
- if (*dd_idx >= *pd_idx)
- (*dd_idx)++;
- break;
- case ALGORITHM_RIGHT_ASYMMETRIC:
- *pd_idx = stripe % raid_disks;
- if (*dd_idx >= *pd_idx)
- (*dd_idx)++;
- break;
- case ALGORITHM_LEFT_SYMMETRIC:
- *pd_idx = data_disks - stripe % raid_disks;
- *dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
- break;
- case ALGORITHM_RIGHT_SYMMETRIC:
- *pd_idx = stripe % raid_disks;
- *dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
- break;
- default:
- printk(KERN_ERR "raid5: unsupported algorithm %d\n",
- conf->algorithm);
+ int prexor = test_bit(STRIPE_OP_PREXOR, &ops_request);
+
+ 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;
+ int towrite;
+
+ towrite = 0;
+ if (prexor) { /* rmw */
+ if (dev->towrite &&
+ test_bit(R5_Wantprexor, &dev->flags))
+ towrite = 1;
+ } else { /* rcw */
+ if (i != pd_idx && dev->towrite &&
+ test_bit(R5_LOCKED, &dev->flags))
+ towrite = 1;
}
- break;
- case 6:
- /**** FIX THIS ****/
- switch (conf->algorithm) {
- case ALGORITHM_LEFT_ASYMMETRIC:
- *pd_idx = raid_disks - 1 - (stripe % raid_disks);
- if (*pd_idx == raid_disks-1)
- (*dd_idx)++; /* Q D D D P */
- else if (*dd_idx >= *pd_idx)
- (*dd_idx) += 2; /* D D P Q D */
- break;
- case ALGORITHM_RIGHT_ASYMMETRIC:
- *pd_idx = stripe % raid_disks;
- if (*pd_idx == raid_disks-1)
- (*dd_idx)++; /* Q D D D P */
- else if (*dd_idx >= *pd_idx)
- (*dd_idx) += 2; /* D D P Q D */
- break;
- case ALGORITHM_LEFT_SYMMETRIC:
- *pd_idx = raid_disks - 1 - (stripe % raid_disks);
- *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
- break;
- case ALGORITHM_RIGHT_SYMMETRIC:
- *pd_idx = stripe % raid_disks;
- *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
- break;
- default:
- printk (KERN_CRIT "raid6: unsupported algorithm %d\n",
- conf->algorithm);
+ if (towrite) {
+ struct bio *wbi;
+
+ spin_lock(&sh->lock);
+ chosen = dev->towrite;
+ dev->towrite = NULL;
+ BUG_ON(dev->written);
+ wbi = dev->written = chosen;
+ spin_unlock(&sh->lock);
+
+ while (wbi && wbi->bi_sector <
+ dev->sector + STRIPE_SECTORS) {
+ tx = async_copy_data(1, wbi, dev->page,
+ dev->sector, tx);
+ wbi = r5_next_bio(wbi, dev->sector);
+ }
}
- break;
}
- /*
- * Finally, compute the new sector number
- */
- new_sector = (sector_t)stripe * sectors_per_chunk + chunk_offset;
- return new_sector;
+ return tx;
}
+static void ops_complete_postxor(void *stripe_head_ref)
+{
+ struct stripe_head *sh = stripe_head_ref;
-static sector_t compute_blocknr(struct stripe_head *sh, int i)
-{
- raid5_conf_t *conf = sh->raid_conf;
- int raid_disks = sh->disks, data_disks = raid_disks - 1;
- sector_t new_sector = sh->sector, check;
- int sectors_per_chunk = conf->chunk_size >> 9;
- sector_t stripe;
- int chunk_offset;
- int chunk_number, dummy1, dummy2, dd_idx = i;
- sector_t r_sector;
-
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
- chunk_offset = sector_div(new_sector, sectors_per_chunk);
- stripe = new_sector;
- BUG_ON(new_sector != stripe);
+ sh->reconstruct_state = reconstruct_state_result;
+ set_bit(STRIPE_HANDLE, &sh->state);
+ release_stripe(sh);
+}
- if (i == sh->pd_idx)
- return 0;
- switch(conf->level) {
- case 4: break;
- case 5:
- switch (conf->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;
- default:
- printk(KERN_ERR "raid5: unsupported algorithm %d\n",
- conf->algorithm);
- }
- break;
- case 6:
- data_disks = raid_disks - 2;
- if (i == raid6_next_disk(sh->pd_idx, raid_disks))
- return 0; /* It is the Q disk */
- switch (conf->algorithm) {
- case ALGORITHM_LEFT_ASYMMETRIC:
- case ALGORITHM_RIGHT_ASYMMETRIC:
- 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;
- default:
- printk (KERN_CRIT "raid6: unsupported algorithm %d\n",
- conf->algorithm);
- }
- break;
- }
+static void ops_complete_write(void *stripe_head_ref)
+{
+ struct stripe_head *sh = stripe_head_ref;
+ int disks = sh->disks, i, pd_idx = sh->pd_idx;
- chunk_number = stripe * data_disks + i;
- r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset;
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
- check = raid5_compute_sector (r_sector, raid_disks, data_disks, &dummy1, &dummy2, conf);
- if (check != sh->sector || dummy1 != dd_idx || dummy2 != sh->pd_idx) {
- printk(KERN_ERR "compute_blocknr: map not correct\n");
- return 0;
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ if (dev->written || i == pd_idx)
+ set_bit(R5_UPTODATE, &dev->flags);
}
- return r_sector;
-}
-
+ sh->reconstruct_state = reconstruct_state_drain_result;
+ set_bit(STRIPE_HANDLE, &sh->state);
+ release_stripe(sh);
+}
-/*
- * Copy data between a page in the stripe cache, and one or more bion
- * The page could align with the middle of the bio, or there could be
- * several bion, each with several bio_vecs, which cover part of the page
- * Multiple bion are linked together on bi_next. There may be extras
- * at the end of this list. We ignore them.
- */
-static void copy_data(int frombio, struct bio *bio,
- struct page *page,
- sector_t sector)
+static void
+ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
+ unsigned long ops_request)
{
- char *pa = page_address(page);
- struct bio_vec *bvl;
- int i;
- int page_offset;
-
- if (bio->bi_sector >= sector)
- page_offset = (signed)(bio->bi_sector - sector) * 512;
- else
- page_offset = (signed)(sector - bio->bi_sector) * -512;
- bio_for_each_segment(bvl, bio, i) {
- int len = bio_iovec_idx(bio,i)->bv_len;
- int clen;
- int b_offset = 0;
+ /* kernel stack size limits the total number of disks */
+ int disks = sh->disks;
+ struct page *xor_srcs[disks];
- if (page_offset < 0) {
- b_offset = -page_offset;
- page_offset += b_offset;
- len -= b_offset;
- }
+ int count = 0, pd_idx = sh->pd_idx, i;
+ struct page *xor_dest;
+ int prexor = test_bit(STRIPE_OP_PREXOR, &ops_request);
+ unsigned long flags;
+ dma_async_tx_callback callback;
- if (len > 0 && page_offset + len > STRIPE_SIZE)
- clen = STRIPE_SIZE - page_offset;
- else clen = len;
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
- if (clen > 0) {
- char *ba = __bio_kmap_atomic(bio, i, KM_USER0);
- if (frombio)
- memcpy(pa+page_offset, ba+b_offset, clen);
- else
- memcpy(ba+b_offset, pa+page_offset, clen);
- __bio_kunmap_atomic(ba, KM_USER0);
+ /* check if prexor is active which means only process blocks
+ * that are part of a read-modify-write (written)
+ */
+ if (prexor) {
+ 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;
}
- if (clen < len) /* hit end of page */
- break;
- page_offset += len;
}
-}
-
-#define check_xor() do { \
- if (count == MAX_XOR_BLOCKS) { \
- xor_block(count, STRIPE_SIZE, ptr); \
- count = 1; \
- } \
- } while(0)
+ /* check whether this postxor is part of a write */
+ callback = test_bit(STRIPE_OP_BIODRAIN, &ops_request) ?
+ ops_complete_write : ops_complete_postxor;
-static void compute_block(struct stripe_head *sh, int dd_idx)
-{
- int i, count, disks = sh->disks;
- void *ptr[MAX_XOR_BLOCKS], *p;
-
- PRINTK("compute_block, stripe %llu, idx %d\n",
- (unsigned long long)sh->sector, dd_idx);
+ /* 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_DEP_ACK | ASYNC_TX_ACK |
+ (prexor ? ASYNC_TX_XOR_DROP_DST : ASYNC_TX_XOR_ZERO_DST);
- ptr[0] = page_address(sh->dev[dd_idx].page);
- memset(ptr[0], 0, STRIPE_SIZE);
- count = 1;
- for (i = disks ; i--; ) {
- if (i == dd_idx)
- continue;
- p = page_address(sh->dev[i].page);
- if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
- ptr[count++] = p;
- else
- printk(KERN_ERR "compute_block() %d, stripe %llu, %d"
- " not present\n", dd_idx,
- (unsigned long long)sh->sector, i);
+ atomic_inc(&sh->count);
- check_xor();
- }
- if (count != 1)
- xor_block(count, STRIPE_SIZE, ptr);
- set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
+ if (unlikely(count == 1)) {
+ flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST);
+ tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
+ flags, tx, callback, sh);
+ } else
+ tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
+ flags, tx, callback, sh);
}
-static void compute_parity5(struct stripe_head *sh, int method)
+static void ops_complete_check(void *stripe_head_ref)
{
- raid5_conf_t *conf = sh->raid_conf;
- int i, pd_idx = sh->pd_idx, disks = sh->disks, count;
- void *ptr[MAX_XOR_BLOCKS];
- struct bio *chosen;
+ struct stripe_head *sh = stripe_head_ref;
- PRINTK("compute_parity5, stripe %llu, method %d\n",
- (unsigned long long)sh->sector, method);
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
- count = 1;
- ptr[0] = page_address(sh->dev[pd_idx].page);
- switch(method) {
- case READ_MODIFY_WRITE:
- BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags));
- for (i=disks ; i-- ;) {
- if (i==pd_idx)
- continue;
- if (sh->dev[i].towrite &&
- test_bit(R5_UPTODATE, &sh->dev[i].flags)) {
- ptr[count++] = page_address(sh->dev[i].page);
- chosen = sh->dev[i].towrite;
- sh->dev[i].towrite = NULL;
+ sh->check_state = check_state_check_result;
+ set_bit(STRIPE_HANDLE, &sh->state);
+ release_stripe(sh);
+}
- if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
- wake_up(&conf->wait_for_overlap);
+static void ops_run_check(struct stripe_head *sh)
+{
+ /* kernel stack size limits the total number of disks */
+ int disks = sh->disks;
+ struct page *xor_srcs[disks];
+ struct dma_async_tx_descriptor *tx;
- BUG_ON(sh->dev[i].written);
- sh->dev[i].written = chosen;
- check_xor();
- }
- }
- break;
- case RECONSTRUCT_WRITE:
- memset(ptr[0], 0, STRIPE_SIZE);
- for (i= disks; i-- ;)
- if (i!=pd_idx && sh->dev[i].towrite) {
- chosen = sh->dev[i].towrite;
- sh->dev[i].towrite = NULL;
+ int count = 0, pd_idx = sh->pd_idx, i;
+ struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
- if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
- wake_up(&conf->wait_for_overlap);
+ pr_debug("%s: stripe %llu\n", __func__,
+ (unsigned long long)sh->sector);
- BUG_ON(sh->dev[i].written);
- sh->dev[i].written = chosen;
- }
- break;
- case CHECK_PARITY:
- break;
- }
- if (count>1) {
- xor_block(count, STRIPE_SIZE, ptr);
- count = 1;
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ if (i != pd_idx)
+ xor_srcs[count++] = dev->page;
}
-
- for (i = disks; i--;)
- if (sh->dev[i].written) {
- sector_t sector = sh->dev[i].sector;
- struct bio *wbi = sh->dev[i].written;
- while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) {
- copy_data(1, wbi, sh->dev[i].page, sector);
- wbi = r5_next_bio(wbi, sector);
- }
- set_bit(R5_LOCKED, &sh->dev[i].flags);
- set_bit(R5_UPTODATE, &sh->dev[i].flags);
- }
+ tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
+ &sh->ops.zero_sum_result, 0, NULL, NULL, NULL);
- switch(method) {
- case RECONSTRUCT_WRITE:
- case CHECK_PARITY:
- for (i=disks; i--;)
- if (i != pd_idx) {
- ptr[count++] = page_address(sh->dev[i].page);
- check_xor();
- }
- break;
- case READ_MODIFY_WRITE:
- for (i = disks; i--;)
- if (sh->dev[i].written) {
- ptr[count++] = page_address(sh->dev[i].page);
- check_xor();
- }
- }
- if (count != 1)
- xor_block(count, STRIPE_SIZE, ptr);
-
- if (method != CHECK_PARITY) {
- set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
- set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
- } else
- clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
+ atomic_inc(&sh->count);
+ tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
+ ops_complete_check, sh);
}
-static void compute_parity6(struct stripe_head *sh, int method)
+static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request)
{
- raid6_conf_t *conf = sh->raid_conf;
- int i, pd_idx = sh->pd_idx, qd_idx, d0_idx, disks = conf->raid_disks, count;
- struct bio *chosen;
- /**** FIX THIS: This could be very bad if disks is close to 256 ****/
- void *ptrs[disks];
-
- qd_idx = raid6_next_disk(pd_idx, disks);
- d0_idx = raid6_next_disk(qd_idx, disks);
+ int overlap_clear = 0, i, disks = sh->disks;
+ struct dma_async_tx_descriptor *tx = NULL;
- PRINTK("compute_parity, stripe %llu, method %d\n",
- (unsigned long long)sh->sector, method);
+ if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
+ ops_run_biofill(sh);
+ overlap_clear++;
+ }
- switch(method) {
- case READ_MODIFY_WRITE:
- BUG(); /* READ_MODIFY_WRITE N/A for RAID-6 */
- case RECONSTRUCT_WRITE:
- for (i= disks; i-- ;)
- if ( i != pd_idx && i != qd_idx && sh->dev[i].towrite ) {
- chosen = sh->dev[i].towrite;
- sh->dev[i].towrite = NULL;
+ if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request))
+ tx = ops_run_compute5(sh, ops_request);
- if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
- wake_up(&conf->wait_for_overlap);
+ if (test_bit(STRIPE_OP_PREXOR, &ops_request))
+ tx = ops_run_prexor(sh, tx);
- if (sh->dev[i].written) BUG();
- sh->dev[i].written = chosen;
- }
- break;
- case CHECK_PARITY:
- BUG(); /* Not implemented yet */
+ if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
+ tx = ops_run_biodrain(sh, tx, ops_request);
+ overlap_clear++;
}
- for (i = disks; i--;)
- if (sh->dev[i].written) {
- sector_t sector = sh->dev[i].sector;
- struct bio *wbi = sh->dev[i].written;
- while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) {
- copy_data(1, wbi, sh->dev[i].page, sector);
- wbi = r5_next_bio(wbi, sector);
- }
+ if (test_bit(STRIPE_OP_POSTXOR, &ops_request))
+ ops_run_postxor(sh, tx, ops_request);
- set_bit(R5_LOCKED, &sh->dev[i].flags);
- set_bit(R5_UPTODATE, &sh->dev[i].flags);
- }
+ if (test_bit(STRIPE_OP_CHECK, &ops_request))
+ ops_run_check(sh);
-// switch(method) {
-// case RECONSTRUCT_WRITE:
-// case CHECK_PARITY:
-// case UPDATE_PARITY:
- /* Note that unlike RAID-5, the ordering of the disks matters greatly. */
- /* FIX: Is this ordering of drives even remotely optimal? */
- count = 0;
- i = d0_idx;
- do {
- ptrs[count++] = page_address(sh->dev[i].page);
- if (count <= disks-2 && !test_bit(R5_UPTODATE, &sh->dev[i].flags))
- printk("block %d/%d not uptodate on parity calc\n", i,count);
- i = raid6_next_disk(i, disks);
- } while ( i != d0_idx );
-// break;
-// }
+ 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);
+ }
+}
+
+static int grow_one_stripe(raid5_conf_t *conf)
+{
+ struct stripe_head *sh;
+ sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
+ if (!sh)
+ return 0;
+ memset(sh, 0, sizeof(*sh) + (conf->raid_disks-1)*sizeof(struct r5dev));
+ sh->raid_conf = conf;
+ spin_lock_init(&sh->lock);
+
+ if (grow_buffers(sh, conf->raid_disks)) {
+ shrink_buffers(sh, conf->raid_disks);
+ kmem_cache_free(conf->slab_cache, sh);
+ return 0;
+ }
+ sh->disks = conf->raid_disks;
+ /* 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(raid5_conf_t *conf, int num)
+{
+ struct kmem_cache *sc;
+ int devs = conf->raid_disks;
+
+ sprintf(conf->cache_name[0], "raid5-%s", mdname(conf->mddev));
+ sprintf(conf->cache_name[1], "raid5-%s-alt", mdname(conf->mddev));
+ 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;
+}
+
+#ifdef CONFIG_MD_RAID5_RESHAPE
+static int resize_stripes(raid5_conf_t *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;
+ int err = 0;
+ struct kmem_cache *sc;
+ int i;
+
+ if (newsize <= conf->pool_size)
+ return 0; /* never bother to shrink */
+
+ 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;
+
+ for (i = conf->max_nr_stripes; i; i--) {
+ nsh = kmem_cache_alloc(sc, GFP_KERNEL);
+ if (!nsh)
+ break;
+
+ memset(nsh, 0, sizeof(*nsh) + (newsize-1)*sizeof(struct r5dev));
+
+ nsh->raid_conf = conf;
+ spin_lock_init(&nsh->lock);
+
+ 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,
+ unplug_slaves(conf->mddev)
+ );
+ 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.
+ */
+ 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;
+
+ /* 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;
+}
+#endif
+
+static int drop_one_stripe(raid5_conf_t *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, conf->pool_size);
+ kmem_cache_free(conf->slab_cache, sh);
+ atomic_dec(&conf->active_stripes);
+ return 1;
+}
+
+static void shrink_stripes(raid5_conf_t *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;
+ raid5_conf_t *conf = sh->raid_conf;
+ int disks = sh->disks, i;
+ int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
+ char b[BDEVNAME_SIZE];
+ mdk_rdev_t *rdev;
+
+
+ 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 (uptodate) {
+ set_bit(R5_UPTODATE, &sh->dev[i].flags);
+ if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ rdev = conf->disks[i].rdev;
+ printk_rl(KERN_INFO "raid5:%s: read error corrected"
+ " (%lu sectors at %llu on %s)\n",
+ mdname(conf->mddev), STRIPE_SECTORS,
+ (unsigned long long)(sh->sector
+ + rdev->data_offset),
+ bdevname(rdev->bdev, b));
+ clear_bit(R5_ReadError, &sh->dev[i].flags);
+ clear_bit(R5_ReWrite, &sh->dev[i].flags);
+ }
+ if (atomic_read(&conf->disks[i].rdev->read_errors))
+ atomic_set(&conf->disks[i].rdev->read_errors, 0);
+ } else {
+ const char *bdn = bdevname(conf->disks[i].rdev->bdev, b);
+ int retry = 0;
+ rdev = conf->disks[i].rdev;
+
+ clear_bit(R5_UPTODATE, &sh->dev[i].flags);
+ atomic_inc(&rdev->read_errors);
+ if (conf->mddev->degraded)
+ printk_rl(KERN_WARNING
+ "raid5:%s: read error not correctable "
+ "(sector %llu on %s).\n",
+ mdname(conf->mddev),
+ (unsigned long long)(sh->sector
+ + rdev->data_offset),
+ bdn);
+ else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
+ /* Oh, no!!! */
+ printk_rl(KERN_WARNING
+ "raid5:%s: read error NOT corrected!! "
+ "(sector %llu on %s).\n",
+ mdname(conf->mddev),
+ (unsigned long long)(sh->sector
+ + rdev->data_offset),
+ bdn);
+ else if (atomic_read(&rdev->read_errors)
+ > conf->max_nr_stripes)
+ printk(KERN_WARNING
+ "raid5:%s: Too many read errors, failing device %s.\n",
+ mdname(conf->mddev), bdn);
+ else
+ retry = 1;
+ if (retry)
+ set_bit(R5_ReadError, &sh->dev[i].flags);
+ else {
+ clear_bit(R5_ReadError, &sh->dev[i].flags);
+ clear_bit(R5_ReWrite, &sh->dev[i].flags);
+ md_error(conf->mddev, rdev);
+ }
+ }
+ rdev_dec_pending(conf->disks[i].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;
+ raid5_conf_t *conf = sh->raid_conf;
+ int disks = sh->disks, i;
+ int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
+
+ for (i=0 ; i<disks; i++)
+ if (bi == &sh->dev[i].req)
+ 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 (!uptodate)
+ md_error(conf->mddev, conf->disks[i].rdev);
+
+ rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
+
+ 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);
+
+static void raid5_build_block (struct stripe_head *sh, int i)
+{
+ 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->vec.bv_page = dev->page;
+ dev->vec.bv_len = STRIPE_SIZE;
+ dev->vec.bv_offset = 0;
+
+ dev->req.bi_sector = sh->sector;
+ dev->req.bi_private = sh;
+
+ dev->flags = 0;
+ dev->sector = compute_blocknr(sh, i);
+}
+
+static void error(mddev_t *mddev, mdk_rdev_t *rdev)
+{
+ char b[BDEVNAME_SIZE];
+ raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ pr_debug("raid5: error called\n");
+
+ if (!test_bit(Faulty, &rdev->flags)) {
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ if (test_and_clear_bit(In_sync, &rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
+ mddev->degraded++;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ /*
+ * if recovery was running, make sure it aborts.
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ }
+ set_bit(Faulty, &rdev->flags);
+ printk (KERN_ALERT
+ "raid5: Disk failure on %s, disabling device.\n"
+ "raid5: Operation continuing on %d devices.\n",
+ bdevname(rdev->bdev,b), 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(sector_t r_sector, unsigned int raid_disks,
+ unsigned int data_disks, unsigned int * dd_idx,
+ unsigned int * pd_idx, raid5_conf_t *conf)
+{
+ long stripe;
+ unsigned long chunk_number;
+ unsigned int chunk_offset;
+ sector_t new_sector;
+ int sectors_per_chunk = conf->chunk_size >> 9;
+
+ /* 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;
+ BUG_ON(r_sector != chunk_number);
+
+ /*
+ * Compute the stripe number
+ */
+ stripe = chunk_number / data_disks;
+
+ /*
+ * Compute the data disk and parity disk indexes inside the stripe
+ */
+ *dd_idx = chunk_number % data_disks;
+
+ /*
+ * Select the parity disk based on the user selected algorithm.
+ */
+ switch(conf->level) {
+ case 4:
+ *pd_idx = data_disks;
+ break;
+ case 5:
+ switch (conf->algorithm) {
+ case ALGORITHM_LEFT_ASYMMETRIC:
+ *pd_idx = data_disks - stripe % raid_disks;
+ if (*dd_idx >= *pd_idx)
+ (*dd_idx)++;
+ break;
+ case ALGORITHM_RIGHT_ASYMMETRIC:
+ *pd_idx = stripe % raid_disks;
+ if (*dd_idx >= *pd_idx)
+ (*dd_idx)++;
+ break;
+ case ALGORITHM_LEFT_SYMMETRIC:
+ *pd_idx = data_disks - stripe % raid_disks;
+ *dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
+ break;
+ case ALGORITHM_RIGHT_SYMMETRIC:
+ *pd_idx = stripe % raid_disks;
+ *dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
+ break;
+ default:
+ printk(KERN_ERR "raid5: unsupported algorithm %d\n",
+ conf->algorithm);
+ }
+ break;
+ case 6:
+
+ /**** FIX THIS ****/
+ switch (conf->algorithm) {
+ case ALGORITHM_LEFT_ASYMMETRIC:
+ *pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ if (*pd_idx == raid_disks-1)
+ (*dd_idx)++; /* Q D D D P */
+ else if (*dd_idx >= *pd_idx)
+ (*dd_idx) += 2; /* D D P Q D */
+ break;
+ case ALGORITHM_RIGHT_ASYMMETRIC:
+ *pd_idx = stripe % raid_disks;
+ if (*pd_idx == raid_disks-1)
+ (*dd_idx)++; /* Q D D D P */
+ else if (*dd_idx >= *pd_idx)
+ (*dd_idx) += 2; /* D D P Q D */
+ break;
+ case ALGORITHM_LEFT_SYMMETRIC:
+ *pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
+ break;
+ case ALGORITHM_RIGHT_SYMMETRIC:
+ *pd_idx = stripe % raid_disks;
+ *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
+ break;
+ default:
+ printk (KERN_CRIT "raid6: unsupported algorithm %d\n",
+ conf->algorithm);
+ }
+ break;
+ }
+
+ /*
+ * 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)
+{
+ raid5_conf_t *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 = conf->chunk_size >> 9;
+ sector_t stripe;
+ int chunk_offset;
+ int chunk_number, dummy1, dummy2, dd_idx = i;
+ sector_t r_sector;
+
+
+ chunk_offset = sector_div(new_sector, sectors_per_chunk);
+ stripe = new_sector;
+ BUG_ON(new_sector != stripe);
+
+ if (i == sh->pd_idx)
+ return 0;
+ switch(conf->level) {
+ case 4: break;
+ case 5:
+ switch (conf->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;
+ default:
+ printk(KERN_ERR "raid5: unsupported algorithm %d\n",
+ conf->algorithm);
+ }
+ break;
+ case 6:
+ if (i == raid6_next_disk(sh->pd_idx, raid_disks))
+ return 0; /* It is the Q disk */
+ switch (conf->algorithm) {
+ case ALGORITHM_LEFT_ASYMMETRIC:
+ case ALGORITHM_RIGHT_ASYMMETRIC:
+ 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;
+ default:
+ printk (KERN_CRIT "raid6: unsupported algorithm %d\n",
+ conf->algorithm);
+ }
+ break;
+ }
+
+ chunk_number = stripe * data_disks + i;
+ r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset;
+
+ check = raid5_compute_sector (r_sector, raid_disks, data_disks, &dummy1, &dummy2, conf);
+ if (check != sh->sector || dummy1 != dd_idx || dummy2 != sh->pd_idx) {
+ printk(KERN_ERR "compute_blocknr: map not correct\n");
+ return 0;
+ }
+ return r_sector;
+}
+
+
+
+/*
+ * Copy data between a page in the stripe cache, and one or more bion
+ * The page could align with the middle of the bio, or there could be
+ * several bion, each with several bio_vecs, which cover part of the page
+ * Multiple bion are linked together on bi_next. There may be extras
+ * at the end of this list. We ignore them.
+ */
+static void copy_data(int frombio, struct bio *bio,
+ struct page *page,
+ sector_t sector)
+{
+ char *pa = page_address(page);
+ struct bio_vec *bvl;
+ int i;
+ int page_offset;
+
+ if (bio->bi_sector >= sector)
+ page_offset = (signed)(bio->bi_sector - sector) * 512;
+ else
+ page_offset = (signed)(sector - bio->bi_sector) * -512;
+ bio_for_each_segment(bvl, bio, i) {
+ int len = bio_iovec_idx(bio,i)->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) {
+ char *ba = __bio_kmap_atomic(bio, i, KM_USER0);
+ if (frombio)
+ memcpy(pa+page_offset, ba+b_offset, clen);
+ else
+ memcpy(ba+b_offset, pa+page_offset, clen);
+ __bio_kunmap_atomic(ba, KM_USER0);
+ }
+ if (clen < len) /* hit end of page */
+ break;
+ page_offset += len;
+ }
+}
+
+#define check_xor() do { \
+ if (count == MAX_XOR_BLOCKS) { \
+ xor_blocks(count, STRIPE_SIZE, dest, ptr);\
+ count = 0; \
+ } \
+ } while(0)
+
+static void compute_parity6(struct stripe_head *sh, int method)
+{
+ raid6_conf_t *conf = sh->raid_conf;
+ int i, pd_idx = sh->pd_idx, qd_idx, d0_idx, disks = sh->disks, count;
+ struct bio *chosen;
+ /**** FIX THIS: This could be very bad if disks is close to 256 ****/
+ void *ptrs[disks];
+
+ qd_idx = raid6_next_disk(pd_idx, disks);
+ d0_idx = raid6_next_disk(qd_idx, disks);
+
+ pr_debug("compute_parity, stripe %llu, method %d\n",
+ (unsigned long long)sh->sector, method);
+
+ switch(method) {
+ case READ_MODIFY_WRITE:
+ BUG(); /* READ_MODIFY_WRITE N/A for RAID-6 */
+ case RECONSTRUCT_WRITE:
+ for (i= disks; i-- ;)
+ if ( i != pd_idx && i != qd_idx && sh->dev[i].towrite ) {
+ chosen = sh->dev[i].towrite;
+ sh->dev[i].towrite = NULL;
+
+ if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
+ wake_up(&conf->wait_for_overlap);
+
+ BUG_ON(sh->dev[i].written);
+ sh->dev[i].written = chosen;
+ }
+ break;
+ case CHECK_PARITY:
+ BUG(); /* Not implemented yet */
+ }
+
+ for (i = disks; i--;)
+ if (sh->dev[i].written) {
+ sector_t sector = sh->dev[i].sector;
+ struct bio *wbi = sh->dev[i].written;
+ while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) {
+ copy_data(1, wbi, sh->dev[i].page, sector);
+ wbi = r5_next_bio(wbi, sector);
+ }
+
+ set_bit(R5_LOCKED, &sh->dev[i].flags);
+ set_bit(R5_UPTODATE, &sh->dev[i].flags);
+ }
+
+// switch(method) {
+// case RECONSTRUCT_WRITE:
+// case CHECK_PARITY:
+// case UPDATE_PARITY:
+ /* Note that unlike RAID-5, the ordering of the disks matters greatly. */
+ /* FIX: Is this ordering of drives even remotely optimal? */
+ count = 0;
+ i = d0_idx;
+ do {
+ ptrs[count++] = page_address(sh->dev[i].page);
+ if (count <= disks-2 && !test_bit(R5_UPTODATE, &sh->dev[i].flags))
+ printk("block %d/%d not uptodate on parity calc\n", i,count);
+ i = raid6_next_disk(i, disks);
+ } while ( i != d0_idx );
+// break;
+// }
raid6_call.gen_syndrome(disks, STRIPE_SIZE, ptrs);
}
}
-
-/* Compute one missing block */
-static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
+
+/* Compute one missing block */
+static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
+{
+ int i, count, disks = sh->disks;
+ void *ptr[MAX_XOR_BLOCKS], *dest, *p;
+ int pd_idx = sh->pd_idx;
+ int qd_idx = raid6_next_disk(pd_idx, disks);
+
+ pr_debug("compute_block_1, stripe %llu, idx %d\n",
+ (unsigned long long)sh->sector, dd_idx);
+
+ if ( dd_idx == qd_idx ) {
+ /* We're actually computing the Q drive */
+ compute_parity6(sh, UPDATE_PARITY);
+ } else {
+ dest = page_address(sh->dev[dd_idx].page);
+ if (!nozero) memset(dest, 0, STRIPE_SIZE);
+ count = 0;
+ for (i = disks ; i--; ) {
+ if (i == dd_idx || i == qd_idx)
+ continue;
+ p = page_address(sh->dev[i].page);
+ if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
+ ptr[count++] = p;
+ else
+ printk("compute_block() %d, stripe %llu, %d"
+ " not present\n", dd_idx,
+ (unsigned long long)sh->sector, i);
+
+ check_xor();
+ }
+ if (count)
+ xor_blocks(count, STRIPE_SIZE, dest, ptr);
+ if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
+ else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
+ }
+}
+
+/* Compute two missing blocks */
+static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
+{
+ int i, count, disks = sh->disks;
+ int pd_idx = sh->pd_idx;
+ int qd_idx = raid6_next_disk(pd_idx, disks);
+ int d0_idx = raid6_next_disk(qd_idx, disks);
+ int faila, failb;
+
+ /* faila and failb are disk numbers relative to d0_idx */
+ /* pd_idx become disks-2 and qd_idx become disks-1 */
+ faila = (dd_idx1 < d0_idx) ? dd_idx1+(disks-d0_idx) : dd_idx1-d0_idx;
+ failb = (dd_idx2 < d0_idx) ? dd_idx2+(disks-d0_idx) : dd_idx2-d0_idx;
+
+ BUG_ON(faila == failb);
+ if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; }
+
+ pr_debug("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n",
+ (unsigned long long)sh->sector, dd_idx1, dd_idx2, faila, failb);
+
+ if ( failb == disks-1 ) {
+ /* Q disk is one of the missing disks */
+ if ( faila == disks-2 ) {
+ /* Missing P+Q, just recompute */
+ compute_parity6(sh, UPDATE_PARITY);
+ return;
+ } else {
+ /* We're missing D+Q; recompute D from P */
+ compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1, 0);
+ compute_parity6(sh, UPDATE_PARITY); /* Is this necessary? */
+ return;
+ }
+ }
+
+ /* We're missing D+P or D+D; build pointer table */
+ {
+ /**** FIX THIS: This could be very bad if disks is close to 256 ****/
+ void *ptrs[disks];
+
+ count = 0;
+ i = d0_idx;
+ do {
+ ptrs[count++] = page_address(sh->dev[i].page);
+ i = raid6_next_disk(i, disks);
+ if (i != dd_idx1 && i != dd_idx2 &&
+ !test_bit(R5_UPTODATE, &sh->dev[i].flags))
+ printk("compute_2 with missing block %d/%d\n", count, i);
+ } while ( i != d0_idx );
+
+ if ( failb == disks-2 ) {
+ /* We're missing D+P. */
+ raid6_datap_recov(disks, STRIPE_SIZE, faila, ptrs);
+ } else {
+ /* We're missing D+D. */
+ raid6_2data_recov(disks, STRIPE_SIZE, faila, failb, ptrs);
+ }
+
+ /* Both the above update both missing blocks */
+ set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
+ set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
+ }
+}
+
+static void
+handle_write_operations5(struct stripe_head *sh, struct stripe_head_state *s,
+ int rcw, int expand)
{
- raid6_conf_t *conf = sh->raid_conf;
- int i, count, disks = conf->raid_disks;
- void *ptr[MAX_XOR_BLOCKS], *p;
- int pd_idx = sh->pd_idx;
- int qd_idx = raid6_next_disk(pd_idx, disks);
+ int i, pd_idx = sh->pd_idx, disks = sh->disks;
- PRINTK("compute_block_1, stripe %llu, idx %d\n",
- (unsigned long long)sh->sector, dd_idx);
+ 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;
- if ( dd_idx == qd_idx ) {
- /* We're actually computing the Q drive */
- compute_parity6(sh, UPDATE_PARITY);
+ set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
+
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+
+ if (dev->towrite) {
+ set_bit(R5_LOCKED, &dev->flags);
+ if (!expand)
+ clear_bit(R5_UPTODATE, &dev->flags);
+ s->locked++;
+ }
+ }
+ if (s->locked + 1 == disks)
+ if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
+ atomic_inc(&sh->raid_conf->pending_full_writes);
} else {
- ptr[0] = page_address(sh->dev[dd_idx].page);
- if (!nozero) memset(ptr[0], 0, STRIPE_SIZE);
- count = 1;
- for (i = disks ; i--; ) {
- if (i == dd_idx || i == qd_idx)
+ 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_drain_run;
+ set_bit(STRIPE_OP_PREXOR, &s->ops_request);
+ set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+ set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
+
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ if (i == pd_idx)
continue;
- p = page_address(sh->dev[i].page);
- if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
- ptr[count++] = p;
- else
- printk("compute_block() %d, stripe %llu, %d"
- " not present\n", dd_idx,
+
+ /* For a read-modify write there may be blocks that are
+ * locked for reading while others are ready to be
+ * written so we distinguish these blocks by the
+ * R5_Wantprexor bit
+ */
+ if (dev->towrite &&
+ (test_bit(R5_UPTODATE, &dev->flags) ||
+ test_bit(R5_Wantcompute, &dev->flags))) {
+ set_bit(R5_Wantprexor, &dev->flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ clear_bit(R5_UPTODATE, &dev->flags);
+ s->locked++;
+ }
+ }
+ }
+
+ /* keep the parity disk 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++;
+
+ 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;
+ raid5_conf_t *conf = sh->raid_conf;
+ int firstwrite=0;
+
+ pr_debug("adding bh b#%llu to stripe s#%llu\n",
+ (unsigned long long)bi->bi_sector,
+ (unsigned long long)sh->sector);
+
+
+ spin_lock(&sh->lock);
+ spin_lock_irq(&conf->device_lock);
+ if (forwrite) {
+ bip = &sh->dev[dd_idx].towrite;
+ if (*bip == NULL && sh->dev[dd_idx].written == 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;
+ bi->bi_phys_segments ++;
+ spin_unlock_irq(&conf->device_lock);
+ spin_unlock(&sh->lock);
+
+ pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
+ (unsigned long long)bi->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);
+ }
+
+ 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);
+ }
+ return 1;
+
+ overlap:
+ set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
+ spin_unlock_irq(&conf->device_lock);
+ spin_unlock(&sh->lock);
+ return 0;
+}
+
+static void end_reshape(raid5_conf_t *conf);
+
+static int page_is_zero(struct page *p)
+{
+ char *a = page_address(p);
+ return ((*(u32*)a) == 0 &&
+ memcmp(a, a+4, STRIPE_SIZE-4)==0);
+}
+
+static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks)
+{
+ int sectors_per_chunk = conf->chunk_size >> 9;
+ int pd_idx, dd_idx;
+ int chunk_offset = sector_div(stripe, sectors_per_chunk);
+
+ raid5_compute_sector(stripe * (disks - conf->max_degraded)
+ *sectors_per_chunk + chunk_offset,
+ disks, disks - conf->max_degraded,
+ &dd_idx, &pd_idx, conf);
+ return pd_idx;
+}
+
+static void
+handle_requests_to_failed_array(raid5_conf_t *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)) {
+ mdk_rdev_t *rdev;
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && test_bit(In_sync, &rdev->flags))
+ /* multiple read failures in one stripe */
+ md_error(conf->mddev, rdev);
+ rcu_read_unlock();
+ }
+ spin_lock_irq(&conf->device_lock);
+ /* fail all writes first */
+ bi = sh->dev[i].towrite;
+ sh->dev[i].towrite = NULL;
+ 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 (--bi->bi_phys_segments == 0) {
+ md_write_end(conf->mddev);
+ bi->bi_next = *return_bi;
+ *return_bi = bi;
+ }
+ bi = nextbi;
+ }
+ /* 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 (--bi->bi_phys_segments == 0) {
+ 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 (--bi->bi_phys_segments == 0) {
+ bi->bi_next = *return_bi;
+ *return_bi = bi;
+ }
+ bi = nextbi;
+ }
+ }
+ spin_unlock_irq(&conf->device_lock);
+ if (bitmap_end)
+ bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS, 0, 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);
+}
+
+/* __handle_issuing_new_read_requests5 - returns 0 if there are no more disks
+ * to process
+ */
+static int __handle_issuing_new_read_requests5(struct stripe_head *sh,
+ struct stripe_head_state *s, int disk_idx, int disks)
+{
+ struct r5dev *dev = &sh->dev[disk_idx];
+ struct r5dev *failed_dev = &sh->dev[s->failed_num];
+
+ /* 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->failed &&
+ (failed_dev->toread || (failed_dev->towrite &&
+ !test_bit(R5_OVERWRITE, &failed_dev->flags)
+ ))))) {
+ /* We would like to get this block, possibly by computing it,
+ * otherwise read it if the backing disk is insync
+ */
+ if ((s->uptodate == disks - 1) &&
+ (s->failed && disk_idx == s->failed_num)) {
+ 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;
+ s->req_compute = 1;
+ /* Careful: from this point on 'uptodate' is in the eye
+ * of raid5_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 0; /* uptodate + compute == disks */
+ } 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;
+}
+
+static void handle_issuing_new_read_requests5(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 (__handle_issuing_new_read_requests5(
+ sh, s, i, disks) == 0)
+ break;
+ }
+ set_bit(STRIPE_HANDLE, &sh->state);
+}
+
+static void handle_issuing_new_read_requests6(struct stripe_head *sh,
+ struct stripe_head_state *s, struct r6_state *r6s,
+ int disks)
+{
+ int i;
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ 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->failed >= 1 &&
+ (sh->dev[r6s->failed_num[0]].toread ||
+ s->to_write)) ||
+ (s->failed >= 2 &&
+ (sh->dev[r6s->failed_num[1]].toread ||
+ s->to_write)))) {
+ /* we would like to get this block, possibly
+ * by computing it, but we might not be able to
+ */
+ if ((s->uptodate == disks - 1) &&
+ (s->failed && (i == r6s->failed_num[0] ||
+ i == r6s->failed_num[1]))) {
+ pr_debug("Computing stripe %llu block %d\n",
(unsigned long long)sh->sector, i);
+ compute_block_1(sh, i, 0);
+ s->uptodate++;
+ } 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 == i)
+ 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,
+ i, other);
+ compute_block_2(sh, i, other);
+ s->uptodate += 2;
+ } 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",
+ i, s->syncing);
+ }
+ }
+ }
+ set_bit(STRIPE_HANDLE, &sh->state);
+}
+
+
+/* handle_completed_write_requests
+ * 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_completed_write_requests(raid5_conf_t *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;
+ int bitmap_end = 0;
+ pr_debug("Return write for disc %d\n", i);
+ spin_lock_irq(&conf->device_lock);
+ wbi = dev->written;
+ dev->written = NULL;
+ while (wbi && wbi->bi_sector <
+ dev->sector + STRIPE_SECTORS) {
+ wbi2 = r5_next_bio(wbi, dev->sector);
+ if (--wbi->bi_phys_segments == 0) {
+ md_write_end(conf->mddev);
+ wbi->bi_next = *return_bi;
+ *return_bi = wbi;
+ }
+ wbi = wbi2;
+ }
+ if (dev->towrite == NULL)
+ bitmap_end = 1;
+ spin_unlock_irq(&conf->device_lock);
+ if (bitmap_end)
+ 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_issuing_new_write_requests5(raid5_conf_t *conf,
+ struct stripe_head *sh, struct stripe_head_state *s, int disks)
+{
+ int rmw = 0, rcw = 0, i;
+ 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 */
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ 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)) &&
+ test_bit(R5_Insync, &dev->flags)) {
+ if (
+ test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+ pr_debug("Read_old block "
+ "%d for Reconstruct\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);
+ }
+ }
+ }
+ /* now if nothing is locked, and if we have enough data,
+ * we can start a write request
+ */
+ /* since handle_stripe can be called at any time we need to handle the
+ * case where a compute block operation has been submitted and then a
+ * subsequent call wants to start a write request. raid5_run_ops only
+ * handles the case where compute block and postxor are requested
+ * simultaneously. If this is not the case then new writes need to be
+ * held off until the compute completes.
+ */
+ if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
+ (s->locked == 0 && (rcw == 0 || rmw == 0) &&
+ !test_bit(STRIPE_BIT_DELAY, &sh->state)))
+ handle_write_operations5(sh, s, rcw == 0, 0);
+}
+
+static void handle_issuing_new_write_requests6(raid5_conf_t *conf,
+ struct stripe_head *sh, struct stripe_head_state *s,
+ struct r6_state *r6s, int disks)
+{
+ int rcw = 0, must_compute = 0, pd_idx = sh->pd_idx, i;
+ int qd_idx = r6s->qd_idx;
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ /* Would I have to read this buffer for reconstruct_write */
+ if (!test_bit(R5_OVERWRITE, &dev->flags)
+ && i != pd_idx && i != qd_idx
+ && (!test_bit(R5_LOCKED, &dev->flags)
+ ) &&
+ !test_bit(R5_UPTODATE, &dev->flags)) {
+ if (test_bit(R5_Insync, &dev->flags)) rcw++;
+ else {
+ pr_debug("raid6: must_compute: "
+ "disk %d flags=%#lx\n", i, dev->flags);
+ must_compute++;
+ }
+ }
+ }
+ pr_debug("for sector %llu, rcw=%d, must_compute=%d\n",
+ (unsigned long long)sh->sector, rcw, must_compute);
+ set_bit(STRIPE_HANDLE, &sh->state);
+
+ if (rcw > 0)
+ /* want reconstruct write, but need to get some data */
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ if (!test_bit(R5_OVERWRITE, &dev->flags)
+ && !(s->failed == 0 && (i == pd_idx || i == qd_idx))
+ && !test_bit(R5_LOCKED, &dev->flags) &&
+ !test_bit(R5_UPTODATE, &dev->flags) &&
+ test_bit(R5_Insync, &dev->flags)) {
+ if (
+ test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+ pr_debug("Read_old stripe %llu "
+ "block %d for Reconstruct\n",
+ (unsigned long long)sh->sector, i);
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantread, &dev->flags);
+ s->locked++;
+ } else {
+ pr_debug("Request delayed stripe %llu "
+ "block %d for Reconstruct\n",
+ (unsigned long long)sh->sector, i);
+ set_bit(STRIPE_DELAYED, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ }
+ }
+ }
+ /* now if nothing is locked, and if we have enough data, we can start a
+ * write request
+ */
+ if (s->locked == 0 && rcw == 0 &&
+ !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
+ if (must_compute > 0) {
+ /* We have failed blocks and need to compute them */
+ switch (s->failed) {
+ case 0:
+ BUG();
+ case 1:
+ compute_block_1(sh, r6s->failed_num[0], 0);
+ break;
+ case 2:
+ compute_block_2(sh, r6s->failed_num[0],
+ r6s->failed_num[1]);
+ break;
+ default: /* This request should have been failed? */
+ BUG();
+ }
+ }
- check_xor();
+ pr_debug("Computing parity for stripe %llu\n",
+ (unsigned long long)sh->sector);
+ compute_parity6(sh, RECONSTRUCT_WRITE);
+ /* now every locked buffer is ready to be written */
+ for (i = disks; i--; )
+ if (test_bit(R5_LOCKED, &sh->dev[i].flags)) {
+ pr_debug("Writing stripe %llu block %d\n",
+ (unsigned long long)sh->sector, i);
+ s->locked++;
+ set_bit(R5_Wantwrite, &sh->dev[i].flags);
+ }
+ if (s->locked == disks)
+ if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
+ atomic_inc(&conf->pending_full_writes);
+ /* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */
+ set_bit(STRIPE_INSYNC, &sh->state);
+
+ if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+ atomic_dec(&conf->preread_active_stripes);
+ if (atomic_read(&conf->preread_active_stripes) <
+ IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
}
- if (count != 1)
- xor_block(count, STRIPE_SIZE, ptr);
- if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
- else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
}
}
-/* Compute two missing blocks */
-static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
+static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
+ struct stripe_head_state *s, int disks)
{
- raid6_conf_t *conf = sh->raid_conf;
- int i, count, disks = conf->raid_disks;
- int pd_idx = sh->pd_idx;
- int qd_idx = raid6_next_disk(pd_idx, disks);
- int d0_idx = raid6_next_disk(qd_idx, disks);
- int faila, failb;
+ struct r5dev *dev = NULL;
- /* faila and failb are disk numbers relative to d0_idx */
- /* pd_idx become disks-2 and qd_idx become disks-1 */
- faila = (dd_idx1 < d0_idx) ? dd_idx1+(disks-d0_idx) : dd_idx1-d0_idx;
- failb = (dd_idx2 < d0_idx) ? dd_idx2+(disks-d0_idx) : dd_idx2-d0_idx;
+ set_bit(STRIPE_HANDLE, &sh->state);
- BUG_ON(faila == failb);
- if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; }
+ switch (sh->check_state) {
+ case check_state_idle:
+ /* start a new check operation if there are no failures */
+ if (s->failed == 0) {
+ BUG_ON(s->uptodate != disks);
+ sh->check_state = check_state_run;
+ set_bit(STRIPE_OP_CHECK, &s->ops_request);
+ clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
+ s->uptodate--;
+ break;
+ }
+ dev = &sh->dev[s->failed_num];
+ /* fall through */
+ case check_state_compute_result:
+ sh->check_state = check_state_idle;
+ if (!dev)
+ dev = &sh->dev[sh->pd_idx];
+
+ /* check that a write has not made the stripe insync */
+ if (test_bit(STRIPE_INSYNC, &sh->state))
+ break;
- PRINTK("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n",
- (unsigned long long)sh->sector, dd_idx1, dd_idx2, faila, failb);
+ /* either failed parity check, or recovery is happening */
+ BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
+ BUG_ON(s->uptodate != disks);
- if ( failb == disks-1 ) {
- /* Q disk is one of the missing disks */
- if ( faila == disks-2 ) {
- /* Missing P+Q, just recompute */
- compute_parity6(sh, UPDATE_PARITY);
- return;
- } else {
- /* We're missing D+Q; recompute D from P */
- compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1, 0);
- compute_parity6(sh, UPDATE_PARITY); /* Is this necessary? */
- return;
- }
- }
+ set_bit(R5_LOCKED, &dev->flags);
+ s->locked++;
+ set_bit(R5_Wantwrite, &dev->flags);
- /* We're missing D+P or D+D; build pointer table */
- {
- /**** FIX THIS: This could be very bad if disks is close to 256 ****/
- void *ptrs[disks];
+ clear_bit(STRIPE_DEGRADED, &sh->state);
+ set_bit(STRIPE_INSYNC, &sh->state);
+ break;
+ case check_state_run:
+ break; /* we will be called again upon completion */
+ case check_state_check_result:
+ sh->check_state = check_state_idle;
- count = 0;
- i = d0_idx;
- do {
- ptrs[count++] = page_address(sh->dev[i].page);
- i = raid6_next_disk(i, disks);
- if (i != dd_idx1 && i != dd_idx2 &&
- !test_bit(R5_UPTODATE, &sh->dev[i].flags))
- printk("compute_2 with missing block %d/%d\n", count, i);
- } while ( i != d0_idx );
+ /* if a failure occurred during the check operation, leave
+ * STRIPE_INSYNC not set and let the stripe be handled again
+ */
+ if (s->failed)
+ break;
- if ( failb == disks-2 ) {
- /* We're missing D+P. */
- raid6_datap_recov(disks, STRIPE_SIZE, faila, ptrs);
- } else {
- /* We're missing D+D. */
- raid6_2data_recov(disks, STRIPE_SIZE, faila, failb, ptrs);
+ /* handle a successful check operation, if parity is correct
+ * we are done. Otherwise update the mismatch count and repair
+ * parity if !MD_RECOVERY_CHECK
+ */
+ if (sh->ops.zero_sum_result == 0)
+ /* parity is correct (on disc,
+ * not in buffer any more)
+ */
+ set_bit(STRIPE_INSYNC, &sh->state);
+ else {
+ conf->mddev->resync_mismatches += STRIPE_SECTORS;
+ if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+ /* don't try to repair!! */
+ set_bit(STRIPE_INSYNC, &sh->state);
+ else {
+ sh->check_state = check_state_compute_run;
+ set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+ set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+ set_bit(R5_Wantcompute,
+ &sh->dev[sh->pd_idx].flags);
+ sh->ops.target = sh->pd_idx;
+ s->uptodate++;
+ }
}
-
- /* Both the above update both missing blocks */
- set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
- set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
+ break;
+ case check_state_compute_run:
+ break;
+ default:
+ printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n",
+ __func__, sh->check_state,
+ (unsigned long long) sh->sector);
+ BUG();
}
}
-
-/*
- * 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)
+static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
+ struct stripe_head_state *s,
+ struct r6_state *r6s, struct page *tmp_page,
+ int disks)
{
- struct bio **bip;
- raid5_conf_t *conf = sh->raid_conf;
- int firstwrite=0;
-
- PRINTK("adding bh b#%llu to stripe s#%llu\n",
- (unsigned long long)bi->bi_sector,
- (unsigned long long)sh->sector);
+ int update_p = 0, update_q = 0;
+ struct r5dev *dev;
+ int pd_idx = sh->pd_idx;
+ int qd_idx = r6s->qd_idx;
+ set_bit(STRIPE_HANDLE, &sh->state);
- spin_lock(&sh->lock);
- spin_lock_irq(&conf->device_lock);
- if (forwrite) {
- bip = &sh->dev[dd_idx].towrite;
- if (*bip == NULL && sh->dev[dd_idx].written == 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(s->failed > 2);
+ BUG_ON(s->uptodate < disks);
+ /* Want to check and possibly repair P and Q.
+ * However there could be one 'failed' device, in which
+ * case we can only check one of them, possibly using the
+ * other to generate missing data
+ */
- BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
- if (*bip)
- bi->bi_next = *bip;
- *bip = bi;
- bi->bi_phys_segments ++;
- spin_unlock_irq(&conf->device_lock);
- spin_unlock(&sh->lock);
+ /* If !tmp_page, we cannot do the calculations,
+ * but as we have set STRIPE_HANDLE, we will soon be called
+ * by stripe_handle with a tmp_page - just wait until then.
+ */
+ if (tmp_page) {
+ if (s->failed == r6s->q_failed) {
+ /* The only possible failed device holds 'Q', so it
+ * makes sense to check P (If anything else were failed,
+ * we would have used P to recreate it).
+ */
+ compute_block_1(sh, pd_idx, 1);
+ if (!page_is_zero(sh->dev[pd_idx].page)) {
+ compute_block_1(sh, pd_idx, 0);
+ update_p = 1;
+ }
+ }
+ if (!r6s->q_failed && s->failed < 2) {
+ /* q is not failed, and we didn't use it to generate
+ * anything, so it makes sense to check it
+ */
+ memcpy(page_address(tmp_page),
+ page_address(sh->dev[qd_idx].page),
+ STRIPE_SIZE);
+ compute_parity6(sh, UPDATE_PARITY);
+ if (memcmp(page_address(tmp_page),
+ page_address(sh->dev[qd_idx].page),
+ STRIPE_SIZE) != 0) {
+ clear_bit(STRIPE_INSYNC, &sh->state);
+ update_q = 1;
+ }
+ }
+ if (update_p || update_q) {
+ conf->mddev->resync_mismatches += STRIPE_SECTORS;
+ if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
+ /* don't try to repair!! */
+ update_p = update_q = 0;
+ }
- PRINTK("added bi b#%llu to stripe s#%llu, disk %d.\n",
- (unsigned long long)bi->bi_sector,
- (unsigned long long)sh->sector, dd_idx);
+ /* now write out any block on a failed drive,
+ * or P or Q if they need it
+ */
- if (conf->mddev->bitmap && firstwrite) {
- sh->bm_seq = conf->seq_write;
- bitmap_startwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS, 0);
- set_bit(STRIPE_BIT_DELAY, &sh->state);
- }
+ if (s->failed == 2) {
+ dev = &sh->dev[r6s->failed_num[1]];
+ s->locked++;
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantwrite, &dev->flags);
+ }
+ if (s->failed >= 1) {
+ dev = &sh->dev[r6s->failed_num[0]];
+ s->locked++;
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantwrite, &dev->flags);
+ }
- 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 (update_p) {
+ dev = &sh->dev[pd_idx];
+ s->locked++;
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantwrite, &dev->flags);
}
- if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
- set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
- }
- return 1;
+ if (update_q) {
+ dev = &sh->dev[qd_idx];
+ s->locked++;
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantwrite, &dev->flags);
+ }
+ clear_bit(STRIPE_DEGRADED, &sh->state);
- overlap:
- set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
- spin_unlock_irq(&conf->device_lock);
- spin_unlock(&sh->lock);
- return 0;
+ set_bit(STRIPE_INSYNC, &sh->state);
+ }
}
-static void end_reshape(raid5_conf_t *conf);
-
-static int page_is_zero(struct page *p)
+static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
+ struct r6_state *r6s)
{
- char *a = page_address(p);
- return ((*(u32*)a) == 0 &&
- memcmp(a, a+4, STRIPE_SIZE-4)==0);
-}
+ int i;
-static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks)
-{
- int sectors_per_chunk = conf->chunk_size >> 9;
- sector_t x = stripe;
- int pd_idx, dd_idx;
- int chunk_offset = sector_div(x, sectors_per_chunk);
- stripe = x;
- raid5_compute_sector(stripe*(disks-1)*sectors_per_chunk
- + chunk_offset, disks, disks-1, &dd_idx, &pd_idx, conf);
- return pd_idx;
+ /* We have read all the blocks in this stripe and now we need to
+ * copy some of them into a target stripe for expand.
+ */
+ struct dma_async_tx_descriptor *tx = NULL;
+ clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
+ for (i = 0; i < sh->disks; i++)
+ if (i != sh->pd_idx && (!r6s || i != r6s->qd_idx)) {
+ int dd_idx, pd_idx, j;
+ struct stripe_head *sh2;
+
+ sector_t bn = compute_blocknr(sh, i);
+ sector_t s = raid5_compute_sector(bn, conf->raid_disks,
+ conf->raid_disks -
+ conf->max_degraded, &dd_idx,
+ &pd_idx, conf);
+ sh2 = get_active_stripe(conf, s, conf->raid_disks,
+ pd_idx, 1);
+ if (sh2 == NULL)
+ /* so far only the early blocks of this stripe
+ * have been requested. When later blocks
+ * get requested, we will try again
+ */
+ continue;
+ if (!test_bit(STRIPE_EXPANDING, &sh2->state) ||
+ test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) {
+ /* must have already done this block */
+ release_stripe(sh2);
+ continue;
+ }
+
+ /* place all the copies on one channel */
+ tx = async_memcpy(sh2->dev[dd_idx].page,
+ sh->dev[i].page, 0, 0, STRIPE_SIZE,
+ ASYNC_TX_DEP_ACK, tx, NULL, NULL);
+
+ set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
+ set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
+ for (j = 0; j < conf->raid_disks; j++)
+ if (j != sh2->pd_idx &&
+ (!r6s || j != raid6_next_disk(sh2->pd_idx,
+ sh2->disks)) &&
+ !test_bit(R5_Expanded, &sh2->dev[j].flags))
+ break;
+ if (j == conf->raid_disks) {
+ set_bit(STRIPE_EXPAND_READY, &sh2->state);
+ set_bit(STRIPE_HANDLE, &sh2->state);
+ }
+ release_stripe(sh2);
+
+ }
+ /* done submitting copies, wait for them to complete */
+ if (tx) {
+ async_tx_ack(tx);
+ dma_wait_for_async_tx(tx);
+ }
}
* schedule a write of some buffers
* return confirmation of parity correctness
*
- * Parity calculations are done inside the stripe lock
* buffers are taken off read_list or write_list, and bh_cache buffers
* get BH_Lock set before the stripe lock is released.
*
*/
-
+
static void handle_stripe5(struct stripe_head *sh)
{
raid5_conf_t *conf = sh->raid_conf;
- int disks = sh->disks;
- struct bio *return_bi= NULL;
- struct bio *bi;
- int i;
- int syncing, expanding, expanded;
- int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0;
- int non_overwrite = 0;
- int failed_num=0;
+ int disks = sh->disks, i;
+ struct bio *return_bi = NULL;
+ struct stripe_head_state s;
struct r5dev *dev;
+ mdk_rdev_t *blocked_rdev = NULL;
+ int prexor;
- PRINTK("handling stripe %llu, cnt=%d, pd_idx=%d\n",
- (unsigned long long)sh->sector, atomic_read(&sh->count),
- sh->pd_idx);
+ memset(&s, 0, sizeof(s));
+ pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d "
+ "reconstruct:%d\n", (unsigned long long)sh->sector, sh->state,
+ atomic_read(&sh->count), sh->pd_idx, sh->check_state,
+ sh->reconstruct_state);
spin_lock(&sh->lock);
clear_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
- syncing = test_bit(STRIPE_SYNCING, &sh->state);
- expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
- expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
- /* Now to look around and see what can be done */
+ s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
+ s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
+ s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
+ /* Now to look around and see what can be done */
rcu_read_lock();
for (i=disks; i--; ) {
mdk_rdev_t *rdev;
- dev = &sh->dev[i];
+ struct r5dev *dev = &sh->dev[i];
clear_bit(R5_Insync, &dev->flags);
- PRINTK("check %d: state 0x%lx read %p write %p written %p\n",
- i, dev->flags, dev->toread, dev->towrite, dev->written);
- /* maybe we can reply to a read */
- if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
- struct bio *rbi, *rbi2;
- PRINTK("Return read for disc %d\n", i);
- spin_lock_irq(&conf->device_lock);
- rbi = dev->toread;
- dev->toread = NULL;
- if (test_and_clear_bit(R5_Overlap, &dev->flags))
- wake_up(&conf->wait_for_overlap);
- spin_unlock_irq(&conf->device_lock);
- while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
- copy_data(0, rbi, dev->page, dev->sector);
- rbi2 = r5_next_bio(rbi, dev->sector);
- spin_lock_irq(&conf->device_lock);
- if (--rbi->bi_phys_segments == 0) {
- rbi->bi_next = return_bi;
- return_bi = rbi;
- }
- spin_unlock_irq(&conf->device_lock);
- rbi = rbi2;
- }
- }
+ pr_debug("check %d: state 0x%lx toread %p read %p write %p "
+ "written %p\n", i, dev->flags, dev->toread, dev->read,
+ dev->towrite, dev->written);
- /* now count some things */
- if (test_bit(R5_LOCKED, &dev->flags)) locked++;
- if (test_bit(R5_UPTODATE, &dev->flags)) uptodate++;
+ /* maybe we can request a biofill operation
+ *
+ * new wantfill requests are only permitted while
+ * ops_complete_biofill is guaranteed to be inactive
+ */
+ if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
+ !test_bit(STRIPE_BIOFILL_RUN, &sh->state))
+ set_bit(R5_Wantfill, &dev->flags);
-
- if (dev->toread) to_read++;
+ /* now count some things */
+ if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
+ if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
+ if (test_bit(R5_Wantcompute, &dev->flags)) s.compute++;
+
+ if (test_bit(R5_Wantfill, &dev->flags))
+ s.to_fill++;
+ else if (dev->toread)
+ s.to_read++;
if (dev->towrite) {
- to_write++;
+ s.to_write++;
if (!test_bit(R5_OVERWRITE, &dev->flags))
- non_overwrite++;
+ s.non_overwrite++;
}
- if (dev->written) written++;
+ if (dev->written)
+ s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
+ break;
+ }
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
}
if (!rdev || !test_bit(In_sync, &rdev->flags)
|| test_bit(R5_ReadError, &dev->flags)) {
- failed++;
- failed_num = i;
+ s.failed++;
+ s.failed_num = i;
} else
set_bit(R5_Insync, &dev->flags);
}
rcu_read_unlock();
- PRINTK("locked=%d uptodate=%d to_read=%d"
+
+ if (unlikely(blocked_rdev)) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
+ }
+
+ if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
+ set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
+ set_bit(STRIPE_BIOFILL_RUN, &sh->state);
+ }
+
+ pr_debug("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d\n",
- locked, uptodate, to_read, to_write, failed, failed_num);
+ s.locked, s.uptodate, s.to_read, s.to_write,
+ s.failed, s.failed_num);
/* check if the array has lost two devices and, if so, some requests might
* need to be failed
*/
- if (failed > 1 && to_read+to_write+written) {
- for (i=disks; i--; ) {
- int bitmap_end = 0;
-
- if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
- mdk_rdev_t *rdev;
- rcu_read_lock();
- rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && test_bit(In_sync, &rdev->flags))
- /* multiple read failures in one stripe */
- md_error(conf->mddev, rdev);
- rcu_read_unlock();
- }
-
- spin_lock_irq(&conf->device_lock);
- /* fail all writes first */
- bi = sh->dev[i].towrite;
- sh->dev[i].towrite = NULL;
- if (bi) { 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 (--bi->bi_phys_segments == 0) {
- md_write_end(conf->mddev);
- bi->bi_next = return_bi;
- return_bi = bi;
- }
- bi = nextbi;
- }
- /* 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 (--bi->bi_phys_segments == 0) {
- md_write_end(conf->mddev);
- bi->bi_next = return_bi;
- return_bi = bi;
- }
- bi = bi2;
- }
-
- /* fail any reads if this device is non-operational */
- if (!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) 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 (--bi->bi_phys_segments == 0) {
- bi->bi_next = return_bi;
- return_bi = bi;
- }
- bi = nextbi;
- }
- }
- spin_unlock_irq(&conf->device_lock);
- if (bitmap_end)
- bitmap_endwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS, 0, 0);
- }
- }
- if (failed > 1 && syncing) {
+ if (s.failed > 1 && s.to_read+s.to_write+s.written)
+ handle_requests_to_failed_array(conf, sh, &s, disks,
+ &return_bi);
+ if (s.failed > 1 && s.syncing) {
md_done_sync(conf->mddev, STRIPE_SECTORS,0);
clear_bit(STRIPE_SYNCING, &sh->state);
- syncing = 0;
+ s.syncing = 0;
}
/* might be able to return some write requests if the parity block
* is safe, or on a failed drive
*/
dev = &sh->dev[sh->pd_idx];
- if ( written &&
- ( (test_bit(R5_Insync, &dev->flags) && !test_bit(R5_LOCKED, &dev->flags) &&
- test_bit(R5_UPTODATE, &dev->flags))
- || (failed == 1 && failed_num == sh->pd_idx))
- ) {
- /* 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.
- */
- 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;
- int bitmap_end = 0;
- PRINTK("Return write for disc %d\n", i);
- spin_lock_irq(&conf->device_lock);
- wbi = dev->written;
- dev->written = NULL;
- while (wbi && wbi->bi_sector < dev->sector + STRIPE_SECTORS) {
- wbi2 = r5_next_bio(wbi, dev->sector);
- if (--wbi->bi_phys_segments == 0) {
- md_write_end(conf->mddev);
- wbi->bi_next = return_bi;
- return_bi = wbi;
- }
- wbi = wbi2;
- }
- if (dev->towrite == NULL)
- bitmap_end = 1;
- spin_unlock_irq(&conf->device_lock);
- if (bitmap_end)
- bitmap_endwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS,
- !test_bit(STRIPE_DEGRADED, &sh->state), 0);
- }
- }
- }
+ if ( s.written &&
+ ((test_bit(R5_Insync, &dev->flags) &&
+ !test_bit(R5_LOCKED, &dev->flags) &&
+ test_bit(R5_UPTODATE, &dev->flags)) ||
+ (s.failed == 1 && s.failed_num == sh->pd_idx)))
+ handle_completed_write_requests(conf, sh, disks, &return_bi);
/* Now we might consider reading some blocks, either to check/generate
* parity, or to satisfy requests
* or to load a block that is being partially written.
*/
- if (to_read || non_overwrite || (syncing && (uptodate < disks)) || expanding) {
- for (i=disks; i--;) {
- dev = &sh->dev[i];
- if (!test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) &&
- (dev->toread ||
- (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
- syncing ||
- expanding ||
- (failed && (sh->dev[failed_num].toread ||
- (sh->dev[failed_num].towrite && !test_bit(R5_OVERWRITE, &sh->dev[failed_num].flags))))
- )
- ) {
- /* we would like to get this block, possibly
- * by computing it, but we might not be able to
- */
- if (uptodate == disks-1) {
- PRINTK("Computing block %d\n", i);
- compute_block(sh, i);
- uptodate++;
- } else if (test_bit(R5_Insync, &dev->flags)) {
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantread, &dev->flags);
-#if 0
- /* if I am just reading this block and we don't have
- a failed drive, or any pending writes then sidestep the cache */
- if (sh->bh_read[i] && !sh->bh_read[i]->b_reqnext &&
- ! syncing && !failed && !to_write) {
- sh->bh_cache[i]->b_page = sh->bh_read[i]->b_page;
- sh->bh_cache[i]->b_data = sh->bh_read[i]->b_data;
- }
-#endif
- locked++;
- PRINTK("Reading block %d (sync=%d)\n",
- i, syncing);
- }
- }
- }
- set_bit(STRIPE_HANDLE, &sh->state);
- }
+ if (s.to_read || s.non_overwrite ||
+ (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
+ handle_issuing_new_read_requests5(sh, &s, disks);
- /* now to consider writing and what else, if anything should be read */
- if (to_write) {
- int rmw=0, rcw=0;
- for (i=disks ; i--;) {
- /* would I have to read this buffer for read_modify_write */
+ /* Now we check to see if any write operations have recently
+ * completed
+ */
+ prexor = 0;
+ if (sh->reconstruct_state == reconstruct_state_drain_result) {
+ sh->reconstruct_state = reconstruct_state_idle;
+ for (i = disks; i--; )
+ prexor += test_and_clear_bit(R5_Wantprexor,
+ &sh->dev[i].flags);
+
+ /* All the 'written' buffers and the parity block are ready to
+ * be written back to disk
+ */
+ BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
+ for (i = disks; i--; ) {
dev = &sh->dev[i];
- if ((dev->towrite || i == sh->pd_idx) &&
- (!test_bit(R5_LOCKED, &dev->flags)
-#if 0
-|| sh->bh_page[i]!=bh->b_page
-#endif
- ) &&
- !test_bit(R5_UPTODATE, &dev->flags)) {
- if (test_bit(R5_Insync, &dev->flags)
-/* && !(!mddev->insync && i == sh->pd_idx) */
- )
- 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)
-#if 0
-|| sh->bh_page[i] != bh->b_page
-#endif
- ) &&
- !test_bit(R5_UPTODATE, &dev->flags)) {
- if (test_bit(R5_Insync, &dev->flags)) rcw++;
- else rcw += 2*disks;
+ if (test_bit(R5_LOCKED, &dev->flags) &&
+ (i == sh->pd_idx || dev->written)) {
+ pr_debug("Writing block %d\n", i);
+ set_bit(R5_Wantwrite, &dev->flags);
+ if (prexor)
+ continue;
+ if (!test_bit(R5_Insync, &dev->flags) ||
+ (i == sh->pd_idx && s.failed == 0))
+ set_bit(STRIPE_INSYNC, &sh->state);
}
}
- PRINTK("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--;) {
- 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_Insync, &dev->flags)) {
- if (test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- {
- PRINTK("Read_old block %d for r-m-w\n", i);
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantread, &dev->flags);
- 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 */
- for (i=disks; i--;) {
- dev = &sh->dev[i];
- 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_Insync, &dev->flags)) {
- if (test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- {
- PRINTK("Read_old block %d for Reconstruct\n", i);
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantread, &dev->flags);
- locked++;
- } else {
- set_bit(STRIPE_DELAYED, &sh->state);
- set_bit(STRIPE_HANDLE, &sh->state);
- }
- }
- }
- /* now if nothing is locked, and if we have enough data, we can start a write request */
- if (locked == 0 && (rcw == 0 ||rmw == 0) &&
- !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
- PRINTK("Computing parity...\n");
- compute_parity5(sh, rcw==0 ? RECONSTRUCT_WRITE : READ_MODIFY_WRITE);
- /* now every locked buffer is ready to be written */
- for (i=disks; i--;)
- if (test_bit(R5_LOCKED, &sh->dev[i].flags)) {
- PRINTK("Writing block %d\n", i);
- locked++;
- set_bit(R5_Wantwrite, &sh->dev[i].flags);
- if (!test_bit(R5_Insync, &sh->dev[i].flags)
- || (i==sh->pd_idx && failed == 0))
- set_bit(STRIPE_INSYNC, &sh->state);
- }
- if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
- atomic_dec(&conf->preread_active_stripes);
- if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
- md_wakeup_thread(conf->mddev->thread);
- }
+ if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+ atomic_dec(&conf->preread_active_stripes);
+ if (atomic_read(&conf->preread_active_stripes) <
+ IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
}
}
+ /* Now to consider new write requests and what else, if anything
+ * should be read. We do not handle new writes when:
+ * 1/ A 'write' operation (copy+xor) is already in flight.
+ * 2/ A 'check' operation is in flight, as it may clobber the parity
+ * block.
+ */
+ if (s.to_write && !sh->reconstruct_state && !sh->check_state)
+ handle_issuing_new_write_requests5(conf, sh, &s, disks);
+
/* maybe we need to check and possibly fix the parity for this stripe
- * Any reads will already have been scheduled, so we just see if enough data
- * is available
+ * Any reads will already have been scheduled, so we just see if enough
+ * data is available. The parity check is held off while parity
+ * dependent operations are in flight.
*/
- if (syncing && locked == 0 &&
- !test_bit(STRIPE_INSYNC, &sh->state)) {
- set_bit(STRIPE_HANDLE, &sh->state);
- if (failed == 0) {
- BUG_ON(uptodate != disks);
- compute_parity5(sh, CHECK_PARITY);
- uptodate--;
- if (page_is_zero(sh->dev[sh->pd_idx].page)) {
- /* parity is correct (on disc, not in buffer any more) */
- set_bit(STRIPE_INSYNC, &sh->state);
- } else {
- conf->mddev->resync_mismatches += STRIPE_SECTORS;
- if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
- /* don't try to repair!! */
- set_bit(STRIPE_INSYNC, &sh->state);
- else {
- compute_block(sh, sh->pd_idx);
- uptodate++;
- }
- }
- }
- if (!test_bit(STRIPE_INSYNC, &sh->state)) {
- /* either failed parity check, or recovery is happening */
- if (failed==0)
- failed_num = sh->pd_idx;
- dev = &sh->dev[failed_num];
- BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
- BUG_ON(uptodate != disks);
+ if (sh->check_state ||
+ (s.syncing && s.locked == 0 &&
+ !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
+ !test_bit(STRIPE_INSYNC, &sh->state)))
+ handle_parity_checks5(conf, sh, &s, disks);
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantwrite, &dev->flags);
- clear_bit(STRIPE_DEGRADED, &sh->state);
- locked++;
- set_bit(STRIPE_INSYNC, &sh->state);
- }
- }
- if (syncing && locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
+ if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS,1);
clear_bit(STRIPE_SYNCING, &sh->state);
}
/* If the failed drive is just a ReadError, then we might need to progress
* the repair/check process
*/
- if (failed == 1 && ! conf->mddev->ro &&
- test_bit(R5_ReadError, &sh->dev[failed_num].flags)
- && !test_bit(R5_LOCKED, &sh->dev[failed_num].flags)
- && test_bit(R5_UPTODATE, &sh->dev[failed_num].flags)
+ if (s.failed == 1 && !conf->mddev->ro &&
+ test_bit(R5_ReadError, &sh->dev[s.failed_num].flags)
+ && !test_bit(R5_LOCKED, &sh->dev[s.failed_num].flags)
+ && test_bit(R5_UPTODATE, &sh->dev[s.failed_num].flags)
) {
- dev = &sh->dev[failed_num];
+ dev = &sh->dev[s.failed_num];
if (!test_bit(R5_ReWrite, &dev->flags)) {
set_bit(R5_Wantwrite, &dev->flags);
set_bit(R5_ReWrite, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
- locked++;
+ s.locked++;
} else {
/* let's read it back */
set_bit(R5_Wantread, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
- locked++;
+ s.locked++;
}
}
- if (expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
+ /* Finish reconstruct operations initiated by the expansion process */
+ if (sh->reconstruct_state == reconstruct_state_result) {
+ sh->reconstruct_state = reconstruct_state_idle;
+ clear_bit(STRIPE_EXPANDING, &sh->state);
+ for (i = conf->raid_disks; i--; )
+ set_bit(R5_Wantwrite, &sh->dev[i].flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ s.locked++;
+ }
+
+ if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
+ !sh->reconstruct_state) {
/* Need to write out all blocks after computing parity */
sh->disks = conf->raid_disks;
- sh->pd_idx = stripe_to_pdidx(sh->sector, conf, conf->raid_disks);
- compute_parity5(sh, RECONSTRUCT_WRITE);
- for (i= conf->raid_disks; i--;) {
- set_bit(R5_LOCKED, &sh->dev[i].flags);
- locked++;
- set_bit(R5_Wantwrite, &sh->dev[i].flags);
- }
- clear_bit(STRIPE_EXPANDING, &sh->state);
- } else if (expanded) {
+ sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
+ conf->raid_disks);
+ handle_write_operations5(sh, &s, 1, 1);
+ } else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
clear_bit(STRIPE_EXPAND_READY, &sh->state);
atomic_dec(&conf->reshape_stripes);
wake_up(&conf->wait_for_overlap);
md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
}
- if (expanding && locked == 0) {
- /* We have read all the blocks in this stripe and now we need to
- * copy some of them into a target stripe for expand.
- */
- clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
- for (i=0; i< sh->disks; i++)
- if (i != sh->pd_idx) {
- int dd_idx, pd_idx, j;
- struct stripe_head *sh2;
-
- sector_t bn = compute_blocknr(sh, i);
- sector_t s = raid5_compute_sector(bn, conf->raid_disks,
- conf->raid_disks-1,
- &dd_idx, &pd_idx, conf);
- sh2 = get_active_stripe(conf, s, conf->raid_disks, pd_idx, 1);
- if (sh2 == NULL)
- /* so far only the early blocks of this stripe
- * have been requested. When later blocks
- * get requested, we will try again
- */
- continue;
- if(!test_bit(STRIPE_EXPANDING, &sh2->state) ||
- test_bit(R5_Expanded, &sh2->dev[dd_idx].flags)) {
- /* must have already done this block */
- release_stripe(sh2);
- continue;
- }
- memcpy(page_address(sh2->dev[dd_idx].page),
- page_address(sh->dev[i].page),
- STRIPE_SIZE);
- set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
- set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
- for (j=0; j<conf->raid_disks; j++)
- if (j != sh2->pd_idx &&
- !test_bit(R5_Expanded, &sh2->dev[j].flags))
- break;
- if (j == conf->raid_disks) {
- set_bit(STRIPE_EXPAND_READY, &sh2->state);
- set_bit(STRIPE_HANDLE, &sh2->state);
- }
- release_stripe(sh2);
- }
- }
+ if (s.expanding && s.locked == 0 &&
+ !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
+ handle_stripe_expansion(conf, sh, NULL);
+ unlock:
spin_unlock(&sh->lock);
- while ((bi=return_bi)) {
- int bytes = bi->bi_size;
+ /* wait for this device to become unblocked */
+ if (unlikely(blocked_rdev))
+ md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
- return_bi = bi->bi_next;
- bi->bi_next = NULL;
- bi->bi_size = 0;
- bi->bi_end_io(bi, bytes, 0);
- }
- for (i=disks; i-- ;) {
- int rw;
- struct bio *bi;
- mdk_rdev_t *rdev;
- if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
- rw = 1;
- else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
- rw = 0;
- else
- continue;
-
- bi = &sh->dev[i].req;
-
- bi->bi_rw = rw;
- if (rw)
- bi->bi_end_io = raid5_end_write_request;
- else
- bi->bi_end_io = raid5_end_read_request;
-
- rcu_read_lock();
- rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && test_bit(Faulty, &rdev->flags))
- rdev = NULL;
- if (rdev)
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
-
- if (rdev) {
- if (syncing || expanding || expanded)
- md_sync_acct(rdev->bdev, STRIPE_SECTORS);
+ if (s.ops_request)
+ raid5_run_ops(sh, s.ops_request);
- bi->bi_bdev = rdev->bdev;
- PRINTK("for %llu schedule op %ld on disc %d\n",
- (unsigned long long)sh->sector, bi->bi_rw, i);
- atomic_inc(&sh->count);
- bi->bi_sector = sh->sector + rdev->data_offset;
- bi->bi_flags = 1 << BIO_UPTODATE;
- bi->bi_vcnt = 1;
- bi->bi_max_vecs = 1;
- bi->bi_idx = 0;
- bi->bi_io_vec = &sh->dev[i].vec;
- 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 (rw == WRITE &&
- test_bit(R5_ReWrite, &sh->dev[i].flags))
- atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
- generic_make_request(bi);
- } else {
- if (rw == 1)
- set_bit(STRIPE_DEGRADED, &sh->state);
- PRINTK("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);
- }
- }
+ ops_run_io(sh, &s);
+
+ return_io(return_bi);
}
static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
{
raid6_conf_t *conf = sh->raid_conf;
- int disks = conf->raid_disks;
- struct bio *return_bi= NULL;
- struct bio *bi;
- int i;
- int syncing;
- int locked=0, uptodate=0, to_read=0, to_write=0, failed=0, written=0;
- int non_overwrite = 0;
- int failed_num[2] = {0, 0};
+ int disks = sh->disks;
+ struct bio *return_bi = NULL;
+ int i, pd_idx = sh->pd_idx;
+ struct stripe_head_state s;
+ struct r6_state r6s;
struct r5dev *dev, *pdev, *qdev;
- int pd_idx = sh->pd_idx;
- int qd_idx = raid6_next_disk(pd_idx, disks);
- int p_failed, q_failed;
+ mdk_rdev_t *blocked_rdev = NULL;
- PRINTK("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d, qd_idx=%d\n",
- (unsigned long long)sh->sector, sh->state, atomic_read(&sh->count),
- pd_idx, qd_idx);
+ r6s.qd_idx = raid6_next_disk(pd_idx, disks);
+ pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
+ "pd_idx=%d, qd_idx=%d\n",
+ (unsigned long long)sh->sector, sh->state,
+ atomic_read(&sh->count), pd_idx, r6s.qd_idx);
+ memset(&s, 0, sizeof(s));
spin_lock(&sh->lock);
clear_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
- syncing = test_bit(STRIPE_SYNCING, &sh->state);
+ s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
+ s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
+ s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
/* Now to look around and see what can be done */
rcu_read_lock();
dev = &sh->dev[i];
clear_bit(R5_Insync, &dev->flags);
- PRINTK("check %d: state 0x%lx read %p write %p written %p\n",
+ pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
i, dev->flags, dev->toread, dev->towrite, dev->written);
/* maybe we can reply to a read */
if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
struct bio *rbi, *rbi2;
- PRINTK("Return read for disc %d\n", i);
+ pr_debug("Return read for disc %d\n", i);
spin_lock_irq(&conf->device_lock);
rbi = dev->toread;
dev->toread = NULL;
}
/* now count some things */
- if (test_bit(R5_LOCKED, &dev->flags)) locked++;
- if (test_bit(R5_UPTODATE, &dev->flags)) uptodate++;
+ if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
+ if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
- if (dev->toread) to_read++;
+ if (dev->toread)
+ s.to_read++;
if (dev->towrite) {
- to_write++;
+ s.to_write++;
if (!test_bit(R5_OVERWRITE, &dev->flags))
- non_overwrite++;
+ s.non_overwrite++;
}
- if (dev->written) written++;
+ if (dev->written)
+ s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
+ break;
+ }
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
}
if (!rdev || !test_bit(In_sync, &rdev->flags)
|| test_bit(R5_ReadError, &dev->flags)) {
- if ( failed < 2 )
- failed_num[failed] = i;
- failed++;
+ if (s.failed < 2)
+ r6s.failed_num[s.failed] = i;
+ s.failed++;
} else
set_bit(R5_Insync, &dev->flags);
}
rcu_read_unlock();
- PRINTK("locked=%d uptodate=%d to_read=%d"
- " to_write=%d failed=%d failed_num=%d,%d\n",
- locked, uptodate, to_read, to_write, failed,
- failed_num[0], failed_num[1]);
- /* check if the array has lost >2 devices and, if so, some requests might
- * need to be failed
- */
- if (failed > 2 && to_read+to_write+written) {
- for (i=disks; i--; ) {
- int bitmap_end = 0;
-
- if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
- mdk_rdev_t *rdev;
- rcu_read_lock();
- rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && test_bit(In_sync, &rdev->flags))
- /* multiple read failures in one stripe */
- md_error(conf->mddev, rdev);
- rcu_read_unlock();
- }
-
- spin_lock_irq(&conf->device_lock);
- /* fail all writes first */
- bi = sh->dev[i].towrite;
- sh->dev[i].towrite = NULL;
- if (bi) { 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 (--bi->bi_phys_segments == 0) {
- md_write_end(conf->mddev);
- bi->bi_next = return_bi;
- return_bi = bi;
- }
- bi = nextbi;
- }
- /* 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 (--bi->bi_phys_segments == 0) {
- md_write_end(conf->mddev);
- bi->bi_next = return_bi;
- return_bi = bi;
- }
- bi = bi2;
- }
- /* fail any reads if this device is non-operational */
- if (!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) 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 (--bi->bi_phys_segments == 0) {
- bi->bi_next = return_bi;
- return_bi = bi;
- }
- bi = nextbi;
- }
- }
- spin_unlock_irq(&conf->device_lock);
- if (bitmap_end)
- bitmap_endwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS, 0, 0);
- }
+ if (unlikely(blocked_rdev)) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
}
- if (failed > 2 && syncing) {
+ pr_debug("locked=%d uptodate=%d to_read=%d"
+ " to_write=%d failed=%d failed_num=%d,%d\n",
+ s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
+ r6s.failed_num[0], r6s.failed_num[1]);
+ /* check if the array has lost >2 devices and, if so, some requests
+ * might need to be failed
+ */
+ if (s.failed > 2 && s.to_read+s.to_write+s.written)
+ handle_requests_to_failed_array(conf, sh, &s, disks,
+ &return_bi);
+ if (s.failed > 2 && s.syncing) {
md_done_sync(conf->mddev, STRIPE_SECTORS,0);
clear_bit(STRIPE_SYNCING, &sh->state);
- syncing = 0;
+ s.syncing = 0;
}
/*
* are safe, or on a failed drive
*/
pdev = &sh->dev[pd_idx];
- p_failed = (failed >= 1 && failed_num[0] == pd_idx)
- || (failed >= 2 && failed_num[1] == pd_idx);
- qdev = &sh->dev[qd_idx];
- q_failed = (failed >= 1 && failed_num[0] == qd_idx)
- || (failed >= 2 && failed_num[1] == qd_idx);
-
- if ( written &&
- ( p_failed || ((test_bit(R5_Insync, &pdev->flags)
+ r6s.p_failed = (s.failed >= 1 && r6s.failed_num[0] == pd_idx)
+ || (s.failed >= 2 && r6s.failed_num[1] == pd_idx);
+ qdev = &sh->dev[r6s.qd_idx];
+ r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == r6s.qd_idx)
+ || (s.failed >= 2 && r6s.failed_num[1] == r6s.qd_idx);
+
+ if ( s.written &&
+ ( r6s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
&& !test_bit(R5_LOCKED, &pdev->flags)
- && test_bit(R5_UPTODATE, &pdev->flags))) ) &&
- ( q_failed || ((test_bit(R5_Insync, &qdev->flags)
+ && test_bit(R5_UPTODATE, &pdev->flags)))) &&
+ ( r6s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
&& !test_bit(R5_LOCKED, &qdev->flags)
- && test_bit(R5_UPTODATE, &qdev->flags))) ) ) {
- /* 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.
- */
- 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 */
- int bitmap_end = 0;
- struct bio *wbi, *wbi2;
- PRINTK("Return write for stripe %llu disc %d\n",
- (unsigned long long)sh->sector, i);
- spin_lock_irq(&conf->device_lock);
- wbi = dev->written;
- dev->written = NULL;
- while (wbi && wbi->bi_sector < dev->sector + STRIPE_SECTORS) {
- wbi2 = r5_next_bio(wbi, dev->sector);
- if (--wbi->bi_phys_segments == 0) {
- md_write_end(conf->mddev);
- wbi->bi_next = return_bi;
- return_bi = wbi;
- }
- wbi = wbi2;
- }
- if (dev->towrite == NULL)
- bitmap_end = 1;
- spin_unlock_irq(&conf->device_lock);
- if (bitmap_end)
- bitmap_endwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS,
- !test_bit(STRIPE_DEGRADED, &sh->state), 0);
- }
- }
- }
+ && test_bit(R5_UPTODATE, &qdev->flags)))))
+ handle_completed_write_requests(conf, sh, disks, &return_bi);
/* Now we might consider reading some blocks, either to check/generate
* parity, or to satisfy requests
* or to load a block that is being partially written.
*/
- if (to_read || non_overwrite || (to_write && failed) || (syncing && (uptodate < disks))) {
- for (i=disks; i--;) {
- dev = &sh->dev[i];
- if (!test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) &&
- (dev->toread ||
- (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
- syncing ||
- (failed >= 1 && (sh->dev[failed_num[0]].toread || to_write)) ||
- (failed >= 2 && (sh->dev[failed_num[1]].toread || to_write))
- )
- ) {
- /* we would like to get this block, possibly
- * by computing it, but we might not be able to
- */
- if (uptodate == disks-1) {
- PRINTK("Computing stripe %llu block %d\n",
- (unsigned long long)sh->sector, i);
- compute_block_1(sh, i, 0);
- uptodate++;
- } else if ( uptodate == disks-2 && failed >= 2 ) {
- /* Computing 2-failure is *very* expensive; only do it if failed >= 2 */
- int other;
- for (other=disks; other--;) {
- if ( other == i )
- continue;
- if ( !test_bit(R5_UPTODATE, &sh->dev[other].flags) )
- break;
- }
- BUG_ON(other < 0);
- PRINTK("Computing stripe %llu blocks %d,%d\n",
- (unsigned long long)sh->sector, i, other);
- compute_block_2(sh, i, other);
- uptodate += 2;
- } else if (test_bit(R5_Insync, &dev->flags)) {
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantread, &dev->flags);
-#if 0
- /* if I am just reading this block and we don't have
- a failed drive, or any pending writes then sidestep the cache */
- if (sh->bh_read[i] && !sh->bh_read[i]->b_reqnext &&
- ! syncing && !failed && !to_write) {
- sh->bh_cache[i]->b_page = sh->bh_read[i]->b_page;
- sh->bh_cache[i]->b_data = sh->bh_read[i]->b_data;
- }
-#endif
- locked++;
- PRINTK("Reading block %d (sync=%d)\n",
- i, syncing);
- }
- }
- }
- set_bit(STRIPE_HANDLE, &sh->state);
- }
+ if (s.to_read || s.non_overwrite || (s.to_write && s.failed) ||
+ (s.syncing && (s.uptodate < disks)) || s.expanding)
+ handle_issuing_new_read_requests6(sh, &s, &r6s, disks);
/* now to consider writing and what else, if anything should be read */
- if (to_write) {
- int rcw=0, must_compute=0;
- for (i=disks ; i--;) {
- dev = &sh->dev[i];
- /* Would I have to read this buffer for reconstruct_write */
- if (!test_bit(R5_OVERWRITE, &dev->flags)
- && i != pd_idx && i != qd_idx
- && (!test_bit(R5_LOCKED, &dev->flags)
-#if 0
- || sh->bh_page[i] != bh->b_page
-#endif
- ) &&
- !test_bit(R5_UPTODATE, &dev->flags)) {
- if (test_bit(R5_Insync, &dev->flags)) rcw++;
- else {
- PRINTK("raid6: must_compute: disk %d flags=%#lx\n", i, dev->flags);
- must_compute++;
- }
- }
- }
- PRINTK("for sector %llu, rcw=%d, must_compute=%d\n",
- (unsigned long long)sh->sector, rcw, must_compute);
- set_bit(STRIPE_HANDLE, &sh->state);
-
- if (rcw > 0)
- /* want reconstruct write, but need to get some data */
- for (i=disks; i--;) {
- dev = &sh->dev[i];
- if (!test_bit(R5_OVERWRITE, &dev->flags)
- && !(failed == 0 && (i == pd_idx || i == qd_idx))
- && !test_bit(R5_LOCKED, &dev->flags) && !test_bit(R5_UPTODATE, &dev->flags) &&
- test_bit(R5_Insync, &dev->flags)) {
- if (test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- {
- PRINTK("Read_old stripe %llu block %d for Reconstruct\n",
- (unsigned long long)sh->sector, i);
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantread, &dev->flags);
- locked++;
- } else {
- PRINTK("Request delayed stripe %llu block %d for Reconstruct\n",
- (unsigned long long)sh->sector, i);
- set_bit(STRIPE_DELAYED, &sh->state);
- set_bit(STRIPE_HANDLE, &sh->state);
- }
- }
- }
- /* now if nothing is locked, and if we have enough data, we can start a write request */
- if (locked == 0 && rcw == 0 &&
- !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
- if ( must_compute > 0 ) {
- /* We have failed blocks and need to compute them */
- switch ( failed ) {
- case 0: BUG();
- case 1: compute_block_1(sh, failed_num[0], 0); break;
- case 2: compute_block_2(sh, failed_num[0], failed_num[1]); break;
- default: BUG(); /* This request should have been failed? */
- }
- }
-
- PRINTK("Computing parity for stripe %llu\n", (unsigned long long)sh->sector);
- compute_parity6(sh, RECONSTRUCT_WRITE);
- /* now every locked buffer is ready to be written */
- for (i=disks; i--;)
- if (test_bit(R5_LOCKED, &sh->dev[i].flags)) {
- PRINTK("Writing stripe %llu block %d\n",
- (unsigned long long)sh->sector, i);
- locked++;
- set_bit(R5_Wantwrite, &sh->dev[i].flags);
- }
- /* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */
- set_bit(STRIPE_INSYNC, &sh->state);
-
- if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
- atomic_dec(&conf->preread_active_stripes);
- if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
- md_wakeup_thread(conf->mddev->thread);
- }
- }
- }
+ if (s.to_write)
+ handle_issuing_new_write_requests6(conf, sh, &s, &r6s, disks);
/* maybe we need to check and possibly fix the parity for this stripe
- * Any reads will already have been scheduled, so we just see if enough data
- * is available
+ * Any reads will already have been scheduled, so we just see if enough
+ * data is available
*/
- if (syncing && locked == 0 && !test_bit(STRIPE_INSYNC, &sh->state)) {
- int update_p = 0, update_q = 0;
- struct r5dev *dev;
-
- set_bit(STRIPE_HANDLE, &sh->state);
-
- BUG_ON(failed>2);
- BUG_ON(uptodate < disks);
- /* Want to check and possibly repair P and Q.
- * However there could be one 'failed' device, in which
- * case we can only check one of them, possibly using the
- * other to generate missing data
- */
-
- /* If !tmp_page, we cannot do the calculations,
- * but as we have set STRIPE_HANDLE, we will soon be called
- * by stripe_handle with a tmp_page - just wait until then.
- */
- if (tmp_page) {
- if (failed == q_failed) {
- /* The only possible failed device holds 'Q', so it makes
- * sense to check P (If anything else were failed, we would
- * have used P to recreate it).
- */
- compute_block_1(sh, pd_idx, 1);
- if (!page_is_zero(sh->dev[pd_idx].page)) {
- compute_block_1(sh,pd_idx,0);
- update_p = 1;
- }
- }
- if (!q_failed && failed < 2) {
- /* q is not failed, and we didn't use it to generate
- * anything, so it makes sense to check it
- */
- memcpy(page_address(tmp_page),
- page_address(sh->dev[qd_idx].page),
- STRIPE_SIZE);
- compute_parity6(sh, UPDATE_PARITY);
- if (memcmp(page_address(tmp_page),
- page_address(sh->dev[qd_idx].page),
- STRIPE_SIZE)!= 0) {
- clear_bit(STRIPE_INSYNC, &sh->state);
- update_q = 1;
- }
- }
- if (update_p || update_q) {
- conf->mddev->resync_mismatches += STRIPE_SECTORS;
- if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
- /* don't try to repair!! */
- update_p = update_q = 0;
- }
-
- /* now write out any block on a failed drive,
- * or P or Q if they need it
- */
-
- if (failed == 2) {
- dev = &sh->dev[failed_num[1]];
- locked++;
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantwrite, &dev->flags);
- }
- if (failed >= 1) {
- dev = &sh->dev[failed_num[0]];
- locked++;
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantwrite, &dev->flags);
- }
-
- if (update_p) {
- dev = &sh->dev[pd_idx];
- locked ++;
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantwrite, &dev->flags);
- }
- if (update_q) {
- dev = &sh->dev[qd_idx];
- locked++;
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantwrite, &dev->flags);
- }
- clear_bit(STRIPE_DEGRADED, &sh->state);
-
- set_bit(STRIPE_INSYNC, &sh->state);
- }
- }
+ if (s.syncing && s.locked == 0 && !test_bit(STRIPE_INSYNC, &sh->state))
+ handle_parity_checks6(conf, sh, &s, &r6s, tmp_page, disks);
- if (syncing && locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
+ if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS,1);
clear_bit(STRIPE_SYNCING, &sh->state);
}
/* If the failed drives are just a ReadError, then we might need
* to progress the repair/check process
*/
- if (failed <= 2 && ! conf->mddev->ro)
- for (i=0; i<failed;i++) {
- dev = &sh->dev[failed_num[i]];
+ if (s.failed <= 2 && !conf->mddev->ro)
+ for (i = 0; i < s.failed; i++) {
+ dev = &sh->dev[r6s.failed_num[i]];
if (test_bit(R5_ReadError, &dev->flags)
&& !test_bit(R5_LOCKED, &dev->flags)
&& test_bit(R5_UPTODATE, &dev->flags)
}
}
}
- spin_unlock(&sh->lock);
-
- while ((bi=return_bi)) {
- int bytes = bi->bi_size;
- return_bi = bi->bi_next;
- bi->bi_next = NULL;
- bi->bi_size = 0;
- bi->bi_end_io(bi, bytes, 0);
+ if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
+ /* Need to write out all blocks after computing P&Q */
+ sh->disks = conf->raid_disks;
+ sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
+ conf->raid_disks);
+ compute_parity6(sh, RECONSTRUCT_WRITE);
+ for (i = conf->raid_disks ; i-- ; ) {
+ set_bit(R5_LOCKED, &sh->dev[i].flags);
+ s.locked++;
+ set_bit(R5_Wantwrite, &sh->dev[i].flags);
+ }
+ clear_bit(STRIPE_EXPANDING, &sh->state);
+ } else if (s.expanded) {
+ clear_bit(STRIPE_EXPAND_READY, &sh->state);
+ atomic_dec(&conf->reshape_stripes);
+ wake_up(&conf->wait_for_overlap);
+ md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
}
- for (i=disks; i-- ;) {
- int rw;
- struct bio *bi;
- mdk_rdev_t *rdev;
- if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
- rw = 1;
- else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
- rw = 0;
- else
- continue;
- bi = &sh->dev[i].req;
+ if (s.expanding && s.locked == 0 &&
+ !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
+ handle_stripe_expansion(conf, sh, &r6s);
- bi->bi_rw = rw;
- if (rw)
- bi->bi_end_io = raid5_end_write_request;
- else
- bi->bi_end_io = raid5_end_read_request;
+ unlock:
+ spin_unlock(&sh->lock);
- rcu_read_lock();
- rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && test_bit(Faulty, &rdev->flags))
- rdev = NULL;
- if (rdev)
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
+ /* wait for this device to become unblocked */
+ if (unlikely(blocked_rdev))
+ md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
- if (rdev) {
- if (syncing)
- md_sync_acct(rdev->bdev, STRIPE_SECTORS);
+ ops_run_io(sh, &s);
- bi->bi_bdev = rdev->bdev;
- PRINTK("for %llu schedule op %ld on disc %d\n",
- (unsigned long long)sh->sector, bi->bi_rw, i);
- atomic_inc(&sh->count);
- bi->bi_sector = sh->sector + rdev->data_offset;
- bi->bi_flags = 1 << BIO_UPTODATE;
- bi->bi_vcnt = 1;
- bi->bi_max_vecs = 1;
- bi->bi_idx = 0;
- bi->bi_io_vec = &sh->dev[i].vec;
- 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 (rw == WRITE &&
- test_bit(R5_ReWrite, &sh->dev[i].flags))
- atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
- generic_make_request(bi);
- } else {
- if (rw == 1)
- set_bit(STRIPE_DEGRADED, &sh->state);
- PRINTK("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);
- }
- }
+ return_io(return_bi);
}
static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
clear_bit(STRIPE_DELAYED, &sh->state);
if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
atomic_inc(&conf->preread_active_stripes);
- list_add_tail(&sh->lru, &conf->handle_list);
+ list_add_tail(&sh->lru, &conf->hold_list);
}
- }
+ } else
+ blk_plug_device(conf->mddev->queue);
}
static void activate_bit_delay(raid5_conf_t *conf)
for (i=0; i<mddev->raid_disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
- request_queue_t *r_queue = bdev_get_queue(rdev->bdev);
+ struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
- if (r_queue->unplug_fn)
- r_queue->unplug_fn(r_queue);
+ blk_unplug(r_queue);
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
rcu_read_unlock();
}
-static void raid5_unplug_device(request_queue_t *q)
+static void raid5_unplug_device(struct request_queue *q)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev_to_conf(mddev);
unplug_slaves(mddev);
}
-static int raid5_issue_flush(request_queue_t *q, struct gendisk *disk,
- sector_t *error_sector)
+static int raid5_congested(void *data, int bits)
+{
+ mddev_t *mddev = data;
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+
+ /* No difference between reads and writes. Just check
+ * how busy the stripe_cache is
+ */
+ if (conf->inactive_blocked)
+ return 1;
+ if (conf->quiesce)
+ return 1;
+ if (list_empty_careful(&conf->inactive_list))
+ return 1;
+
+ return 0;
+}
+
+/* We want read requests to align with chunks where possible,
+ * but write requests don't need to.
+ */
+static int raid5_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec)
+{
+ mddev_t *mddev = q->queuedata;
+ sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+ int max;
+ unsigned int chunk_sectors = mddev->chunk_size >> 9;
+ unsigned int bio_sectors = bio->bi_size >> 9;
+
+ if (bio_data_dir(bio) == WRITE)
+ return biovec->bv_len; /* always allow writes to be mergeable */
+
+ max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
+ if (max < 0) max = 0;
+ if (max <= biovec->bv_len && bio_sectors == 0)
+ return biovec->bv_len;
+ else
+ return max;
+}
+
+
+static int in_chunk_boundary(mddev_t *mddev, struct bio *bio)
+{
+ sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+ unsigned int chunk_sectors = mddev->chunk_size >> 9;
+ unsigned int bio_sectors = bio->bi_size >> 9;
+
+ return chunk_sectors >=
+ ((sector & (chunk_sectors - 1)) + bio_sectors);
+}
+
+/*
+ * add bio to the retry LIFO ( in O(1) ... we are in interrupt )
+ * later sampled by raid5d.
+ */
+static void add_bio_to_retry(struct bio *bi,raid5_conf_t *conf)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&conf->device_lock, flags);
+
+ bi->bi_next = conf->retry_read_aligned_list;
+ conf->retry_read_aligned_list = bi;
+
+ spin_unlock_irqrestore(&conf->device_lock, flags);
+ md_wakeup_thread(conf->mddev->thread);
+}
+
+
+static struct bio *remove_bio_from_retry(raid5_conf_t *conf)
+{
+ struct bio *bi;
+
+ bi = conf->retry_read_aligned;
+ if (bi) {
+ conf->retry_read_aligned = NULL;
+ return bi;
+ }
+ bi = conf->retry_read_aligned_list;
+ if(bi) {
+ conf->retry_read_aligned_list = bi->bi_next;
+ bi->bi_next = NULL;
+ bi->bi_phys_segments = 1; /* biased count of active stripes */
+ bi->bi_hw_segments = 0; /* count of processed stripes */
+ }
+
+ return bi;
+}
+
+
+/*
+ * The "raid5_align_endio" should check if the read succeeded and if it
+ * did, call bio_endio on the original bio (having bio_put the new bio
+ * first).
+ * If the read failed..
+ */
+static void raid5_align_endio(struct bio *bi, int error)
+{
+ struct bio* raid_bi = bi->bi_private;
+ mddev_t *mddev;
+ raid5_conf_t *conf;
+ int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
+ mdk_rdev_t *rdev;
+
+ bio_put(bi);
+
+ mddev = raid_bi->bi_bdev->bd_disk->queue->queuedata;
+ conf = mddev_to_conf(mddev);
+ rdev = (void*)raid_bi->bi_next;
+ raid_bi->bi_next = NULL;
+
+ rdev_dec_pending(rdev, conf->mddev);
+
+ if (!error && uptodate) {
+ bio_endio(raid_bi, 0);
+ if (atomic_dec_and_test(&conf->active_aligned_reads))
+ wake_up(&conf->wait_for_stripe);
+ return;
+ }
+
+
+ pr_debug("raid5_align_endio : io error...handing IO for a retry\n");
+
+ add_bio_to_retry(raid_bi, conf);
+}
+
+static int bio_fits_rdev(struct bio *bi)
+{
+ struct request_queue *q = bdev_get_queue(bi->bi_bdev);
+
+ if ((bi->bi_size>>9) > q->max_sectors)
+ return 0;
+ blk_recount_segments(q, bi);
+ if (bi->bi_phys_segments > q->max_phys_segments ||
+ bi->bi_hw_segments > q->max_hw_segments)
+ return 0;
+
+ if (q->merge_bvec_fn)
+ /* it's too hard to apply the merge_bvec_fn at this stage,
+ * just just give up
+ */
+ return 0;
+
+ return 1;
+}
+
+
+static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev_to_conf(mddev);
- int i, ret = 0;
+ const unsigned int raid_disks = conf->raid_disks;
+ const unsigned int data_disks = raid_disks - conf->max_degraded;
+ unsigned int dd_idx, pd_idx;
+ struct bio* align_bi;
+ mdk_rdev_t *rdev;
- rcu_read_lock();
- for (i=0; i<mddev->raid_disks && ret == 0; i++) {
- mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && !test_bit(Faulty, &rdev->flags)) {
- struct block_device *bdev = rdev->bdev;
- request_queue_t *r_queue = bdev_get_queue(bdev);
+ if (!in_chunk_boundary(mddev, raid_bio)) {
+ pr_debug("chunk_aligned_read : non aligned\n");
+ return 0;
+ }
+ /*
+ * use bio_clone to make a copy of the bio
+ */
+ align_bi = bio_clone(raid_bio, GFP_NOIO);
+ if (!align_bi)
+ return 0;
+ /*
+ * set bi_end_io to a new function, and set bi_private to the
+ * original bio.
+ */
+ align_bi->bi_end_io = raid5_align_endio;
+ align_bi->bi_private = raid_bio;
+ /*
+ * compute position
+ */
+ align_bi->bi_sector = raid5_compute_sector(raid_bio->bi_sector,
+ raid_disks,
+ data_disks,
+ &dd_idx,
+ &pd_idx,
+ conf);
- if (!r_queue->issue_flush_fn)
- ret = -EOPNOTSUPP;
- else {
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
- ret = r_queue->issue_flush_fn(r_queue, bdev->bd_disk,
- error_sector);
- rdev_dec_pending(rdev, mddev);
- rcu_read_lock();
- }
+ rcu_read_lock();
+ rdev = rcu_dereference(conf->disks[dd_idx].rdev);
+ if (rdev && test_bit(In_sync, &rdev->flags)) {
+ atomic_inc(&rdev->nr_pending);
+ rcu_read_unlock();
+ raid_bio->bi_next = (void*)rdev;
+ align_bi->bi_bdev = rdev->bdev;
+ align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
+ align_bi->bi_sector += rdev->data_offset;
+
+ if (!bio_fits_rdev(align_bi)) {
+ /* too big in some way */
+ bio_put(align_bi);
+ rdev_dec_pending(rdev, mddev);
+ return 0;
}
+
+ spin_lock_irq(&conf->device_lock);
+ wait_event_lock_irq(conf->wait_for_stripe,
+ conf->quiesce == 0,
+ conf->device_lock, /* nothing */);
+ atomic_inc(&conf->active_aligned_reads);
+ spin_unlock_irq(&conf->device_lock);
+
+ generic_make_request(align_bi);
+ return 1;
+ } else {
+ rcu_read_unlock();
+ bio_put(align_bi);
+ return 0;
}
- rcu_read_unlock();
- return ret;
}
-static inline void raid5_plug_device(raid5_conf_t *conf)
+/* __get_priority_stripe - get the next stripe to process
+ *
+ * Full stripe writes are allowed to pass preread active stripes up until
+ * the bypass_threshold is exceeded. In general the bypass_count
+ * increments when the handle_list is handled before the hold_list; however, it
+ * will not be incremented when STRIPE_IO_STARTED is sampled set signifying a
+ * stripe with in flight i/o. The bypass_count will be reset when the
+ * head of the hold_list has changed, i.e. the head was promoted to the
+ * handle_list.
+ */
+static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf)
{
- spin_lock_irq(&conf->device_lock);
- blk_plug_device(conf->mddev->queue);
- spin_unlock_irq(&conf->device_lock);
+ struct stripe_head *sh;
+
+ pr_debug("%s: handle: %s hold: %s full_writes: %d bypass_count: %d\n",
+ __func__,
+ list_empty(&conf->handle_list) ? "empty" : "busy",
+ list_empty(&conf->hold_list) ? "empty" : "busy",
+ atomic_read(&conf->pending_full_writes), conf->bypass_count);
+
+ if (!list_empty(&conf->handle_list)) {
+ sh = list_entry(conf->handle_list.next, typeof(*sh), lru);
+
+ if (list_empty(&conf->hold_list))
+ conf->bypass_count = 0;
+ else if (!test_bit(STRIPE_IO_STARTED, &sh->state)) {
+ if (conf->hold_list.next == conf->last_hold)
+ conf->bypass_count++;
+ else {
+ conf->last_hold = conf->hold_list.next;
+ conf->bypass_count -= conf->bypass_threshold;
+ if (conf->bypass_count < 0)
+ conf->bypass_count = 0;
+ }
+ }
+ } else if (!list_empty(&conf->hold_list) &&
+ ((conf->bypass_threshold &&
+ conf->bypass_count > conf->bypass_threshold) ||
+ atomic_read(&conf->pending_full_writes) == 0)) {
+ sh = list_entry(conf->hold_list.next,
+ typeof(*sh), lru);
+ conf->bypass_count -= conf->bypass_threshold;
+ if (conf->bypass_count < 0)
+ conf->bypass_count = 0;
+ } else
+ return NULL;
+
+ list_del_init(&sh->lru);
+ atomic_inc(&sh->count);
+ BUG_ON(atomic_read(&sh->count) != 1);
+ return sh;
}
-static int make_request(request_queue_t *q, struct bio * bi)
+static int make_request(struct request_queue *q, struct bio * bi)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev_to_conf(mddev);
int remaining;
if (unlikely(bio_barrier(bi))) {
- bio_endio(bi, bi->bi_size, -EOPNOTSUPP);
+ bio_endio(bi, -EOPNOTSUPP);
return 0;
}
disk_stat_inc(mddev->gendisk, ios[rw]);
disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bi));
+ if (rw == READ &&
+ mddev->reshape_position == MaxSector &&
+ chunk_aligned_read(q,bi))
+ return 0;
+
logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
last_sector = bi->bi_sector + (bi->bi_size>>9);
bi->bi_next = NULL;
new_sector = raid5_compute_sector(logical_sector, disks, data_disks,
&dd_idx, &pd_idx, conf);
- PRINTK("raid5: make_request, sector %llu logical %llu\n",
+ pr_debug("raid5: make_request, sector %llu logical %llu\n",
(unsigned long long)new_sector,
(unsigned long long)logical_sector);
goto retry;
}
finish_wait(&conf->wait_for_overlap, &w);
- raid5_plug_device(conf);
- handle_stripe(sh, NULL);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ clear_bit(STRIPE_DELAYED, &sh->state);
release_stripe(sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
remaining = --bi->bi_phys_segments;
spin_unlock_irq(&conf->device_lock);
if (remaining == 0) {
- int bytes = bi->bi_size;
if ( rw == WRITE )
md_write_end(mddev);
- bi->bi_size = 0;
- bi->bi_end_io(bi, bytes, 0);
+
+ bio_endio(bi, 0);
}
return 0;
}
struct stripe_head *sh;
int pd_idx;
sector_t first_sector, last_sector;
- int raid_disks;
- int data_disks;
+ int raid_disks = conf->previous_raid_disks;
+ int data_disks = raid_disks - conf->max_degraded;
+ int new_data_disks = conf->raid_disks - conf->max_degraded;
int i;
int dd_idx;
sector_t writepos, safepos, gap;
conf->expand_progress != 0) {
/* restarting in the middle, skip the initial sectors */
sector_nr = conf->expand_progress;
- sector_div(sector_nr, conf->raid_disks-1);
+ sector_div(sector_nr, new_data_disks);
*skipped = 1;
return sector_nr;
}
* to after where expand_lo old_maps to
*/
writepos = conf->expand_progress +
- conf->chunk_size/512*(conf->raid_disks-1);
- sector_div(writepos, conf->raid_disks-1);
+ conf->chunk_size/512*(new_data_disks);
+ sector_div(writepos, new_data_disks);
safepos = conf->expand_lo;
- sector_div(safepos, conf->previous_raid_disks-1);
+ sector_div(safepos, data_disks);
gap = conf->expand_progress - conf->expand_lo;
if (writepos >= safepos ||
- gap > (conf->raid_disks-1)*3000*2 /*3Meg*/) {
+ gap > (new_data_disks)*3000*2 /*3Meg*/) {
/* Cannot proceed until we've updated the superblock... */
wait_event(conf->wait_for_overlap,
atomic_read(&conf->reshape_stripes)==0);
mddev->reshape_position = conf->expand_progress;
- mddev->sb_dirty = 1;
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
md_wakeup_thread(mddev->thread);
- wait_event(mddev->sb_wait, mddev->sb_dirty == 0 ||
+ wait_event(mddev->sb_wait, mddev->flags == 0 ||
kthread_should_stop());
spin_lock_irq(&conf->device_lock);
conf->expand_lo = mddev->reshape_position;
sector_t s;
if (j == sh->pd_idx)
continue;
+ if (conf->level == 6 &&
+ j == raid6_next_disk(sh->pd_idx, sh->disks))
+ continue;
s = compute_blocknr(sh, j);
if (s < (mddev->array_size<<1)) {
skipped = 1;
release_stripe(sh);
}
spin_lock_irq(&conf->device_lock);
- conf->expand_progress = (sector_nr + i)*(conf->raid_disks-1);
+ conf->expand_progress = (sector_nr + i) * new_data_disks;
spin_unlock_irq(&conf->device_lock);
/* Ok, those stripe are ready. We can start scheduling
* reads on the source stripes.
* The source stripes are determined by mapping the first and last
* block on the destination stripes.
*/
- raid_disks = conf->previous_raid_disks;
- data_disks = raid_disks - 1;
first_sector =
- raid5_compute_sector(sector_nr*(conf->raid_disks-1),
+ raid5_compute_sector(sector_nr*(new_data_disks),
raid_disks, data_disks,
&dd_idx, &pd_idx, conf);
last_sector =
raid5_compute_sector((sector_nr+conf->chunk_size/512)
- *(conf->raid_disks-1) -1,
+ *(new_data_disks) -1,
raid_disks, data_disks,
&dd_idx, &pd_idx, conf);
if (last_sector >= (mddev->size<<1))
last_sector = (mddev->size<<1)-1;
while (first_sector <= last_sector) {
- pd_idx = stripe_to_pdidx(first_sector, conf, conf->previous_raid_disks);
+ pd_idx = stripe_to_pdidx(first_sector, conf,
+ conf->previous_raid_disks);
sh = get_active_stripe(conf, first_sector,
conf->previous_raid_disks, pd_idx, 0);
set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
release_stripe(sh);
first_sector += STRIPE_SECTORS;
}
+ /* If this takes us to the resync_max point where we have to pause,
+ * then we need to write out the superblock.
+ */
+ sector_nr += conf->chunk_size>>9;
+ if (sector_nr >= mddev->resync_max) {
+ /* Cannot proceed until we've updated the superblock... */
+ wait_event(conf->wait_for_overlap,
+ atomic_read(&conf->reshape_stripes) == 0);
+ mddev->reshape_position = conf->expand_progress;
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ md_wakeup_thread(mddev->thread);
+ wait_event(mddev->sb_wait,
+ !test_bit(MD_CHANGE_DEVS, &mddev->flags)
+ || kthread_should_stop());
+ spin_lock_irq(&conf->device_lock);
+ conf->expand_lo = mddev->reshape_position;
+ spin_unlock_irq(&conf->device_lock);
+ wake_up(&conf->wait_for_overlap);
+ }
return conf->chunk_size>>9;
}
if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
return reshape_request(mddev, sector_nr, skipped);
+ /* No need to check resync_max as we never do more than one
+ * stripe, and as resync_max will always be on a chunk boundary,
+ * if the check in md_do_sync didn't fire, there is no chance
+ * of overstepping resync_max here
+ */
+
/* if there is too many failed drives and we are trying
* to resync, then assert that we are finished, because there is
* nothing we can do.
return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
}
+
+ bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+
pd_idx = stripe_to_pdidx(sector_nr, conf, raid_disks);
sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 1);
if (sh == NULL) {
return STRIPE_SECTORS;
}
+static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
+{
+ /* We may not be able to submit a whole bio at once as there
+ * may not be enough stripe_heads available.
+ * We cannot pre-allocate enough stripe_heads as we may need
+ * more than exist in the cache (if we allow ever large chunks).
+ * So we do one stripe head at a time and record in
+ * ->bi_hw_segments how many have been done.
+ *
+ * We *know* that this entire raid_bio is in one chunk, so
+ * it will be only one 'dd_idx' and only need one call to raid5_compute_sector.
+ */
+ struct stripe_head *sh;
+ int dd_idx, pd_idx;
+ sector_t sector, logical_sector, last_sector;
+ int scnt = 0;
+ int remaining;
+ int handled = 0;
+
+ logical_sector = raid_bio->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
+ sector = raid5_compute_sector( logical_sector,
+ conf->raid_disks,
+ conf->raid_disks - conf->max_degraded,
+ &dd_idx,
+ &pd_idx,
+ conf);
+ last_sector = raid_bio->bi_sector + (raid_bio->bi_size>>9);
+
+ for (; logical_sector < last_sector;
+ logical_sector += STRIPE_SECTORS,
+ sector += STRIPE_SECTORS,
+ scnt++) {
+
+ if (scnt < raid_bio->bi_hw_segments)
+ /* already done this stripe */
+ continue;
+
+ sh = get_active_stripe(conf, sector, conf->raid_disks, pd_idx, 1);
+
+ if (!sh) {
+ /* failed to get a stripe - must wait */
+ raid_bio->bi_hw_segments = scnt;
+ conf->retry_read_aligned = raid_bio;
+ return handled;
+ }
+
+ set_bit(R5_ReadError, &sh->dev[dd_idx].flags);
+ if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) {
+ release_stripe(sh);
+ raid_bio->bi_hw_segments = scnt;
+ conf->retry_read_aligned = raid_bio;
+ return handled;
+ }
+
+ handle_stripe(sh, NULL);
+ release_stripe(sh);
+ handled++;
+ }
+ spin_lock_irq(&conf->device_lock);
+ remaining = --raid_bio->bi_phys_segments;
+ spin_unlock_irq(&conf->device_lock);
+ if (remaining == 0)
+ bio_endio(raid_bio, 0);
+ if (atomic_dec_and_test(&conf->active_aligned_reads))
+ wake_up(&conf->wait_for_stripe);
+ return handled;
+}
+
+
+
/*
* This is our raid5 kernel thread.
*
* During the scan, completed stripes are saved for us by the interrupt
* handler, so that they will not have to wait for our next wakeup.
*/
-static void raid5d (mddev_t *mddev)
+static void raid5d(mddev_t *mddev)
{
struct stripe_head *sh;
raid5_conf_t *conf = mddev_to_conf(mddev);
int handled;
- PRINTK("+++ raid5d active\n");
+ pr_debug("+++ raid5d active\n");
md_check_recovery(mddev);
handled = 0;
spin_lock_irq(&conf->device_lock);
while (1) {
- struct list_head *first;
+ struct bio *bio;
- if (conf->seq_flush - conf->seq_write > 0) {
+ if (conf->seq_flush != conf->seq_write) {
int seq = conf->seq_flush;
spin_unlock_irq(&conf->device_lock);
bitmap_unplug(mddev->bitmap);
activate_bit_delay(conf);
}
- if (list_empty(&conf->handle_list) &&
- atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD &&
- !blk_queue_plugged(mddev->queue) &&
- !list_empty(&conf->delayed_list))
- raid5_activate_delayed(conf);
-
- if (list_empty(&conf->handle_list))
- break;
+ while ((bio = remove_bio_from_retry(conf))) {
+ int ok;
+ spin_unlock_irq(&conf->device_lock);
+ ok = retry_aligned_read(conf, bio);
+ spin_lock_irq(&conf->device_lock);
+ if (!ok)
+ break;
+ handled++;
+ }
- first = conf->handle_list.next;
- sh = list_entry(first, struct stripe_head, lru);
+ sh = __get_priority_stripe(conf);
- list_del_init(first);
- atomic_inc(&sh->count);
- BUG_ON(atomic_read(&sh->count)!= 1);
+ if (!sh) {
+ async_tx_issue_pending_all();
+ break;
+ }
spin_unlock_irq(&conf->device_lock);
handled++;
spin_lock_irq(&conf->device_lock);
}
- PRINTK("%d stripes handled\n", handled);
+ pr_debug("%d stripes handled\n", handled);
spin_unlock_irq(&conf->device_lock);
unplug_slaves(mddev);
- PRINTK("--- raid5d inactive\n");
+ pr_debug("--- raid5d inactive\n");
}
static ssize_t
raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
{
raid5_conf_t *conf = mddev_to_conf(mddev);
- char *end;
- int new;
+ unsigned long new;
if (len >= PAGE_SIZE)
return -EINVAL;
if (!conf)
return -ENODEV;
- new = simple_strtoul(page, &end, 10);
- if (!*page || (*end && *end != '\n') )
+ if (strict_strtoul(page, 10, &new))
return -EINVAL;
if (new <= 16 || new > 32768)
return -EINVAL;
else
break;
}
+ md_allow_write(mddev);
while (new > conf->max_nr_stripes) {
if (grow_one_stripe(conf))
conf->max_nr_stripes++;
raid5_store_stripe_cache_size);
static ssize_t
+raid5_show_preread_threshold(mddev_t *mddev, char *page)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ if (conf)
+ return sprintf(page, "%d\n", conf->bypass_threshold);
+ else
+ return 0;
+}
+
+static ssize_t
+raid5_store_preread_threshold(mddev_t *mddev, const char *page, size_t len)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ unsigned long new;
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (!conf)
+ return -ENODEV;
+
+ if (strict_strtoul(page, 10, &new))
+ return -EINVAL;
+ if (new > conf->max_nr_stripes)
+ return -EINVAL;
+ conf->bypass_threshold = new;
+ return len;
+}
+
+static struct md_sysfs_entry
+raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
+ S_IRUGO | S_IWUSR,
+ raid5_show_preread_threshold,
+ raid5_store_preread_threshold);
+
+static ssize_t
stripe_cache_active_show(mddev_t *mddev, char *page)
{
raid5_conf_t *conf = mddev_to_conf(mddev);
static struct attribute *raid5_attrs[] = {
&raid5_stripecache_size.attr,
&raid5_stripecache_active.attr,
+ &raid5_preread_bypass_threshold.attr,
NULL,
};
static struct attribute_group raid5_attrs_group = {
mdk_rdev_t *rdev;
struct disk_info *disk;
struct list_head *tmp;
+ int working_disks = 0;
if (mddev->level != 5 && mddev->level != 4 && mddev->level != 6) {
printk(KERN_ERR "raid5: %s: raid level not set to 4/5/6 (%d)\n",
*/
sector_t here_new, here_old;
int old_disks;
+ int max_degraded = (mddev->level == 5 ? 1 : 2);
if (mddev->new_level != mddev->level ||
mddev->new_layout != mddev->layout ||
mddev->new_chunk != mddev->chunk_size) {
- printk(KERN_ERR "raid5: %s: unsupported reshape required - aborting.\n",
+ printk(KERN_ERR "raid5: %s: unsupported reshape "
+ "required - aborting.\n",
mdname(mddev));
return -EINVAL;
}
if (mddev->delta_disks <= 0) {
- printk(KERN_ERR "raid5: %s: unsupported reshape (reduce disks) required - aborting.\n",
+ printk(KERN_ERR "raid5: %s: unsupported reshape "
+ "(reduce disks) required - aborting.\n",
mdname(mddev));
return -EINVAL;
}
old_disks = mddev->raid_disks - mddev->delta_disks;
/* reshape_position must be on a new-stripe boundary, and one
- * further up in new geometry must map after here in old geometry.
+ * further up in new geometry must map after here in old
+ * geometry.
*/
here_new = mddev->reshape_position;
- if (sector_div(here_new, (mddev->chunk_size>>9)*(mddev->raid_disks-1))) {
- printk(KERN_ERR "raid5: reshape_position not on a stripe boundary\n");
+ if (sector_div(here_new, (mddev->chunk_size>>9)*
+ (mddev->raid_disks - max_degraded))) {
+ printk(KERN_ERR "raid5: reshape_position not "
+ "on a stripe boundary\n");
return -EINVAL;
}
/* here_new is the stripe we will write to */
here_old = mddev->reshape_position;
- sector_div(here_old, (mddev->chunk_size>>9)*(old_disks-1));
- /* here_old is the first stripe that we might need to read from */
+ sector_div(here_old, (mddev->chunk_size>>9)*
+ (old_disks-max_degraded));
+ /* here_old is the first stripe that we might need to read
+ * from */
if (here_new >= here_old) {
/* Reading from the same stripe as writing to - bad */
- printk(KERN_ERR "raid5: reshape_position too early for auto-recovery - aborting.\n");
+ printk(KERN_ERR "raid5: reshape_position too early for "
+ "auto-recovery - aborting.\n");
return -EINVAL;
}
printk(KERN_INFO "raid5: reshape will continue\n");
goto abort;
}
spin_lock_init(&conf->device_lock);
+ mddev->queue->queue_lock = &conf->device_lock;
init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
INIT_LIST_HEAD(&conf->handle_list);
+ INIT_LIST_HEAD(&conf->hold_list);
INIT_LIST_HEAD(&conf->delayed_list);
INIT_LIST_HEAD(&conf->bitmap_list);
INIT_LIST_HEAD(&conf->inactive_list);
atomic_set(&conf->active_stripes, 0);
atomic_set(&conf->preread_active_stripes, 0);
+ atomic_set(&conf->active_aligned_reads, 0);
+ conf->bypass_threshold = BYPASS_THRESHOLD;
- PRINTK("raid5: run(%s) called.\n", mdname(mddev));
+ pr_debug("raid5: run(%s) called.\n", mdname(mddev));
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
raid_disk = rdev->raid_disk;
if (raid_disk >= conf->raid_disks
|| raid_disk < 0)
printk(KERN_INFO "raid5: device %s operational as raid"
" disk %d\n", bdevname(rdev->bdev,b),
raid_disk);
- conf->working_disks++;
- }
+ working_disks++;
+ } else
+ /* Cannot rely on bitmap to complete recovery */
+ conf->fullsync = 1;
}
/*
* 0 for a fully functional array, 1 or 2 for a degraded array.
*/
- mddev->degraded = conf->failed_disks = conf->raid_disks - conf->working_disks;
+ mddev->degraded = conf->raid_disks - working_disks;
conf->mddev = mddev;
conf->chunk_size = mddev->chunk_size;
conf->level = mddev->level;
if (mddev->degraded > conf->max_degraded) {
printk(KERN_ERR "raid5: not enough operational devices for %s"
" (%d/%d failed)\n",
- mdname(mddev), conf->failed_disks, conf->raid_disks);
+ mdname(mddev), mddev->degraded, conf->raid_disks);
goto abort;
}
set_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
mddev->sync_thread = md_register_thread(md_do_sync, mddev,
"%s_reshape");
- /* FIXME if md_register_thread fails?? */
- md_wakeup_thread(mddev->sync_thread);
-
}
/* read-ahead size must cover two whole stripes, which is
}
/* Ok, everything is just fine now */
- sysfs_create_group(&mddev->kobj, &raid5_attrs_group);
+ if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
+ printk(KERN_WARNING
+ "raid5: failed to create sysfs attributes for %s\n",
+ mdname(mddev));
mddev->queue->unplug_fn = raid5_unplug_device;
- mddev->queue->issue_flush_fn = raid5_issue_flush;
+ mddev->queue->backing_dev_info.congested_data = mddev;
+ mddev->queue->backing_dev_info.congested_fn = raid5_congested;
+
mddev->array_size = mddev->size * (conf->previous_raid_disks -
conf->max_degraded);
+ blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
+
return 0;
abort:
if (conf) {
mddev->thread = NULL;
shrink_stripes(conf);
kfree(conf->stripe_hashtbl);
+ mddev->queue->backing_dev_info.congested_fn = NULL;
blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
sysfs_remove_group(&mddev->kobj, &raid5_attrs_group);
kfree(conf->disks);
return 0;
}
-#if RAID5_DEBUG
+#ifdef DEBUG
static void print_sh (struct seq_file *seq, struct stripe_head *sh)
{
int i;
int i;
seq_printf (seq, " level %d, %dk chunk, algorithm %d", mddev->level, mddev->chunk_size >> 10, mddev->layout);
- seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->working_disks);
+ seq_printf (seq, " [%d/%d] [", conf->raid_disks, conf->raid_disks - mddev->degraded);
for (i = 0; i < conf->raid_disks; i++)
seq_printf (seq, "%s",
conf->disks[i].rdev &&
test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_");
seq_printf (seq, "]");
-#if RAID5_DEBUG
+#ifdef DEBUG
seq_printf (seq, "\n");
printall(seq, conf);
#endif
printk("(conf==NULL)\n");
return;
}
- printk(" --- rd:%d wd:%d fd:%d\n", conf->raid_disks,
- conf->working_disks, conf->failed_disks);
+ printk(" --- rd:%d wd:%d\n", conf->raid_disks,
+ conf->raid_disks - conf->mddev->degraded);
for (i = 0; i < conf->raid_disks; i++) {
char b[BDEVNAME_SIZE];
tmp = conf->disks + i;
if (tmp->rdev
&& !test_bit(Faulty, &tmp->rdev->flags)
- && !test_bit(In_sync, &tmp->rdev->flags)) {
+ && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
+ unsigned long flags;
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded--;
- conf->failed_disks--;
- conf->working_disks++;
- set_bit(In_sync, &tmp->rdev->flags);
+ spin_unlock_irqrestore(&conf->device_lock, flags);
}
}
print_raid5_conf(conf);
err = -EBUSY;
goto abort;
}
+ /* Only remove non-faulty devices if recovery
+ * isn't possible.
+ */
+ if (!test_bit(Faulty, &rdev->flags) &&
+ mddev->degraded <= conf->max_degraded) {
+ err = -EBUSY;
+ goto abort;
+ }
p->rdev = NULL;
synchronize_rcu();
if (atomic_read(&rdev->nr_pending)) {
static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
{
raid5_conf_t *conf = mddev->private;
- int found = 0;
+ int err = -EEXIST;
int disk;
struct disk_info *p;
+ int first = 0;
+ int last = conf->raid_disks - 1;
if (mddev->degraded > conf->max_degraded)
/* no point adding a device */
- return 0;
+ return -EINVAL;
+
+ if (rdev->raid_disk >= 0)
+ first = last = rdev->raid_disk;
/*
* find the disk ... but prefer rdev->saved_raid_disk
* if possible.
*/
if (rdev->saved_raid_disk >= 0 &&
+ rdev->saved_raid_disk >= first &&
conf->disks[rdev->saved_raid_disk].rdev == NULL)
disk = rdev->saved_raid_disk;
else
- disk = 0;
- for ( ; disk < conf->raid_disks; disk++)
+ disk = first;
+ for ( ; disk <= last ; disk++)
if ((p=conf->disks + disk)->rdev == NULL) {
clear_bit(In_sync, &rdev->flags);
rdev->raid_disk = disk;
- found = 1;
+ err = 0;
if (rdev->saved_raid_disk != disk)
conf->fullsync = 1;
rcu_assign_pointer(p->rdev, rdev);
break;
}
print_raid5_conf(conf);
- return found;
+ return err;
}
static int raid5_resize(mddev_t *mddev, sector_t sectors)
if (err)
return err;
+ if (mddev->degraded > conf->max_degraded)
+ return -EINVAL;
/* looks like we might be able to manage this */
return 0;
}
struct list_head *rtmp;
int spares = 0;
int added_devices = 0;
+ unsigned long flags;
- if (mddev->degraded ||
- test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
+ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return -EBUSY;
- ITERATE_RDEV(mddev, rdev, rtmp)
+ rdev_for_each(rdev, rtmp, mddev)
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags))
spares++;
- if (spares < mddev->delta_disks-1)
+ if (spares - mddev->degraded < mddev->delta_disks - conf->max_degraded)
/* Not enough devices even to make a degraded array
* of that size
*/
/* Add some new drives, as many as will fit.
* We know there are enough to make the newly sized array work.
*/
- ITERATE_RDEV(mddev, rdev, rtmp)
+ rdev_for_each(rdev, rtmp, mddev)
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags)) {
- if (raid5_add_disk(mddev, rdev)) {
+ if (raid5_add_disk(mddev, rdev) == 0) {
char nm[20];
set_bit(In_sync, &rdev->flags);
- conf->working_disks++;
added_devices++;
rdev->recovery_offset = 0;
sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_create_link(&mddev->kobj, &rdev->kobj, nm);
+ if (sysfs_create_link(&mddev->kobj,
+ &rdev->kobj, nm))
+ printk(KERN_WARNING
+ "raid5: failed to create "
+ " link %s for %s\n",
+ nm, mdname(mddev));
} else
break;
}
+ spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded = (conf->raid_disks - conf->previous_raid_disks) - added_devices;
+ spin_unlock_irqrestore(&conf->device_lock, flags);
mddev->raid_disks = conf->raid_disks;
mddev->reshape_position = 0;
- mddev->sb_dirty = 1;
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
struct block_device *bdev;
if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
- conf->mddev->array_size = conf->mddev->size * (conf->raid_disks-1);
+ conf->mddev->array_size = conf->mddev->size *
+ (conf->raid_disks - conf->max_degraded);
set_capacity(conf->mddev->gendisk, conf->mddev->array_size << 1);
conf->mddev->changed = 1;
bdev = bdget_disk(conf->mddev->gendisk, 0);
if (bdev) {
mutex_lock(&bdev->bd_inode->i_mutex);
- i_size_write(bdev->bd_inode, conf->mddev->array_size << 10);
+ i_size_write(bdev->bd_inode, (loff_t)conf->mddev->array_size << 10);
mutex_unlock(&bdev->bd_inode->i_mutex);
bdput(bdev);
}
spin_lock_irq(&conf->device_lock);
conf->quiesce = 1;
wait_event_lock_irq(conf->wait_for_stripe,
- atomic_read(&conf->active_stripes) == 0,
+ atomic_read(&conf->active_stripes) == 0 &&
+ atomic_read(&conf->active_aligned_reads) == 0,
conf->device_lock, /* nothing */);
spin_unlock_irq(&conf->device_lock);
break;
.spare_active = raid5_spare_active,
.sync_request = sync_request,
.resize = raid5_resize,
+#ifdef CONFIG_MD_RAID5_RESHAPE
+ .check_reshape = raid5_check_reshape,
+ .start_reshape = raid5_start_reshape,
+#endif
.quiesce = raid5_quiesce,
};
static struct mdk_personality raid5_personality =
.spare_active = raid5_spare_active,
.sync_request = sync_request,
.resize = raid5_resize,
+#ifdef CONFIG_MD_RAID5_RESHAPE
+ .check_reshape = raid5_check_reshape,
+ .start_reshape = raid5_start_reshape,
+#endif
.quiesce = raid5_quiesce,
};