#include <linux/async.h>
#include <linux/seq_file.h>
#include <linux/cpu.h>
+#include <linux/slab.h>
#include "md.h"
#include "raid5.h"
+#include "raid0.h"
#include "bitmap.h"
/*
static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
int *count, int syndrome_disks)
{
- int slot;
+ int slot = *count;
+ if (sh->ddf_layout)
+ (*count)++;
if (idx == sh->pd_idx)
return syndrome_disks;
if (idx == sh->qd_idx)
return syndrome_disks + 1;
- slot = (*count)++;
+ if (!sh->ddf_layout)
+ (*count)++;
return slot;
}
int i;
for (i = 0; i < disks; i++)
- srcs[i] = (void *)raid6_empty_zero_page;
+ srcs[i] = NULL;
count = 0;
i = d0_idx;
srcs[slot] = sh->dev[i].page;
i = raid6_next_disk(i, disks);
} while (i != d0_idx);
- BUG_ON(count != syndrome_disks);
- return count;
+ return syndrome_disks;
}
static struct dma_async_tx_descriptor *
* slot number conversion for 'faila' and 'failb'
*/
for (i = 0; i < disks ; i++)
- blocks[i] = (void *)raid6_empty_zero_page;
+ blocks[i] = NULL;
count = 0;
i = d0_idx;
do {
failb = slot;
i = raid6_next_disk(i, disks);
} while (i != d0_idx);
- BUG_ON(count != syndrome_disks);
BUG_ON(faila == failb);
if (failb < faila)
init_async_submit(&submit, ASYNC_TX_FENCE, NULL,
ops_complete_compute, sh,
to_addr_conv(sh, percpu));
- return async_gen_syndrome(blocks, 0, count+2,
+ return async_gen_syndrome(blocks, 0, syndrome_disks+2,
STRIPE_SIZE, &submit);
} else {
struct page *dest;
&sh->ops.zero_sum_result, percpu->spare_page, &submit);
}
-static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
+static void __raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
{
int overlap_clear = 0, i, disks = sh->disks;
struct dma_async_tx_descriptor *tx = NULL;
put_cpu();
}
+#ifdef CONFIG_MULTICORE_RAID456
+static void async_run_ops(void *param, async_cookie_t cookie)
+{
+ struct stripe_head *sh = param;
+ unsigned long ops_request = sh->ops.request;
+
+ clear_bit_unlock(STRIPE_OPS_REQ_PENDING, &sh->state);
+ wake_up(&sh->ops.wait_for_ops);
+
+ __raid_run_ops(sh, ops_request);
+ release_stripe(sh);
+}
+
+static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
+{
+ /* since handle_stripe can be called outside of raid5d context
+ * we need to ensure sh->ops.request is de-staged before another
+ * request arrives
+ */
+ wait_event(sh->ops.wait_for_ops,
+ !test_and_set_bit_lock(STRIPE_OPS_REQ_PENDING, &sh->state));
+ sh->ops.request = ops_request;
+
+ atomic_inc(&sh->count);
+ async_schedule(async_run_ops, sh);
+}
+#else
+#define raid_run_ops __raid_run_ops
+#endif
+
static int grow_one_stripe(raid5_conf_t *conf)
{
struct stripe_head *sh;
+ int disks = max(conf->raid_disks, conf->previous_raid_disks);
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));
+ memset(sh, 0, sizeof(*sh) + (disks-1)*sizeof(struct r5dev));
sh->raid_conf = conf;
spin_lock_init(&sh->lock);
+ #ifdef CONFIG_MULTICORE_RAID456
+ init_waitqueue_head(&sh->ops.wait_for_ops);
+ #endif
- if (grow_buffers(sh, conf->raid_disks)) {
- shrink_buffers(sh, conf->raid_disks);
+ if (grow_buffers(sh, disks)) {
+ shrink_buffers(sh, 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);
static int grow_stripes(raid5_conf_t *conf, int num)
{
struct kmem_cache *sc;
- int devs = conf->raid_disks;
+ int devs = max(conf->raid_disks, conf->previous_raid_disks);
sprintf(conf->cache_name[0],
"raid%d-%s", conf->level, mdname(conf->mddev));
nsh->raid_conf = conf;
spin_lock_init(&nsh->lock);
+ #ifdef CONFIG_MULTICORE_RAID456
+ init_waitqueue_head(&nsh->ops.wait_for_ops);
+ #endif
list_add(&nsh->lru, &newstripes);
}
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"
+ printk_rl(KERN_INFO "md/raid:%s: read error corrected"
" (%lu sectors at %llu on %s)\n",
mdname(conf->mddev), STRIPE_SECTORS,
(unsigned long long)(sh->sector
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
atomic_inc(&rdev->read_errors);
- if (conf->mddev->degraded)
+ if (conf->mddev->degraded >= conf->max_degraded)
printk_rl(KERN_WARNING
- "raid5:%s: read error not correctable "
+ "md/raid:%s: read error not correctable "
"(sector %llu on %s).\n",
mdname(conf->mddev),
(unsigned long long)(sh->sector
else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
/* Oh, no!!! */
printk_rl(KERN_WARNING
- "raid5:%s: read error NOT corrected!! "
+ "md/raid:%s: read error NOT corrected!! "
"(sector %llu on %s).\n",
mdname(conf->mddev),
(unsigned long long)(sh->sector
else if (atomic_read(&rdev->read_errors)
> conf->max_nr_stripes)
printk(KERN_WARNING
- "raid5:%s: Too many read errors, failing device %s.\n",
+ "md/raid:%s: Too many read errors, failing device %s.\n",
mdname(conf->mddev), bdn);
else
retry = 1;
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");
+ raid5_conf_t *conf = mddev->private;
+ pr_debug("raid456: error called\n");
if (!test_bit(Faulty, &rdev->flags)) {
set_bit(MD_CHANGE_DEVS, &mddev->flags);
}
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);
+ "md/raid:%s: Disk failure on %s, disabling device.\n"
+ KERN_ALERT
+ "md/raid:%s: Operation continuing on %d devices.\n",
+ mdname(mddev),
+ bdevname(rdev->bdev, b),
+ mdname(mddev),
+ conf->raid_disks - mddev->degraded);
}
}
int previous, int *dd_idx,
struct stripe_head *sh)
{
- long stripe;
- unsigned long chunk_number;
+ sector_t stripe, stripe2;
+ sector_t chunk_number;
unsigned int chunk_offset;
int pd_idx, qd_idx;
int ddf_layout = 0;
*/
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;
-
+ stripe = chunk_number;
+ *dd_idx = sector_div(stripe, data_disks);
+ stripe2 = stripe;
/*
* Select the parity disk based on the user selected algorithm.
*/
case 5:
switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
- pd_idx = data_disks - stripe % raid_disks;
+ pd_idx = data_disks - sector_div(stripe2, raid_disks);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
break;
case ALGORITHM_RIGHT_ASYMMETRIC:
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
break;
case ALGORITHM_LEFT_SYMMETRIC:
- pd_idx = data_disks - stripe % raid_disks;
+ pd_idx = data_disks - sector_div(stripe2, raid_disks);
*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
break;
case ALGORITHM_RIGHT_SYMMETRIC:
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
break;
case ALGORITHM_PARITY_0:
pd_idx = data_disks;
break;
default:
- printk(KERN_ERR "raid5: unsupported algorithm %d\n",
- algorithm);
BUG();
}
break;
switch (algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
- pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
(*dd_idx) += 2; /* D D P Q D */
break;
case ALGORITHM_RIGHT_ASYMMETRIC:
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
(*dd_idx) += 2; /* D D P Q D */
break;
case ALGORITHM_LEFT_SYMMETRIC:
- pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = (pd_idx + 1) % raid_disks;
*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
break;
case ALGORITHM_RIGHT_SYMMETRIC:
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
qd_idx = (pd_idx + 1) % raid_disks;
*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
break;
/* Exactly the same as RIGHT_ASYMMETRIC, but or
* of blocks for computing Q is different.
*/
- pd_idx = stripe % raid_disks;
+ pd_idx = sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
* D D D P Q rather than
* Q D D D P
*/
- pd_idx = raid_disks - 1 - ((stripe + 1) % raid_disks);
+ stripe2 += 1;
+ pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = pd_idx + 1;
if (pd_idx == raid_disks-1) {
(*dd_idx)++; /* Q D D D P */
case ALGORITHM_ROTATING_N_CONTINUE:
/* Same as left_symmetric but Q is before P */
- pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ pd_idx = raid_disks - 1 - sector_div(stripe2, raid_disks);
qd_idx = (pd_idx + raid_disks - 1) % raid_disks;
*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
ddf_layout = 1;
case ALGORITHM_LEFT_ASYMMETRIC_6:
/* RAID5 left_asymmetric, with Q on last device */
- pd_idx = data_disks - stripe % (raid_disks-1);
+ pd_idx = data_disks - sector_div(stripe2, raid_disks-1);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
qd_idx = raid_disks - 1;
break;
case ALGORITHM_RIGHT_ASYMMETRIC_6:
- pd_idx = stripe % (raid_disks-1);
+ pd_idx = sector_div(stripe2, raid_disks-1);
if (*dd_idx >= pd_idx)
(*dd_idx)++;
qd_idx = raid_disks - 1;
break;
case ALGORITHM_LEFT_SYMMETRIC_6:
- pd_idx = data_disks - stripe % (raid_disks-1);
+ pd_idx = data_disks - sector_div(stripe2, raid_disks-1);
*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
qd_idx = raid_disks - 1;
break;
case ALGORITHM_RIGHT_SYMMETRIC_6:
- pd_idx = stripe % (raid_disks-1);
+ pd_idx = sector_div(stripe2, raid_disks-1);
*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
qd_idx = raid_disks - 1;
break;
qd_idx = raid_disks - 1;
break;
-
default:
- printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
- algorithm);
BUG();
}
break;
: conf->algorithm;
sector_t stripe;
int chunk_offset;
- int chunk_number, dummy1, dd_idx = i;
+ sector_t chunk_number;
+ int dummy1, dd_idx = i;
sector_t r_sector;
struct stripe_head sh2;
chunk_offset = sector_div(new_sector, sectors_per_chunk);
stripe = new_sector;
- BUG_ON(new_sector != stripe);
if (i == sh->pd_idx)
return 0;
case ALGORITHM_PARITY_N:
break;
default:
- printk(KERN_ERR "raid5: unsupported algorithm %d\n",
- algorithm);
BUG();
}
break;
case ALGORITHM_PARITY_N:
break;
case ALGORITHM_ROTATING_N_CONTINUE:
+ /* Like left_symmetric, but P is before Q */
if (sh->pd_idx == 0)
i--; /* P D D D Q */
- else if (i > sh->pd_idx)
- i -= 2; /* D D Q P D */
+ else {
+ /* D D Q P D */
+ if (i < sh->pd_idx)
+ i += raid_disks;
+ i -= (sh->pd_idx + 1);
+ }
break;
case ALGORITHM_LEFT_ASYMMETRIC_6:
case ALGORITHM_RIGHT_ASYMMETRIC_6:
i -= 1;
break;
default:
- printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
- algorithm);
BUG();
}
break;
}
chunk_number = stripe * data_disks + i;
- r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset;
+ r_sector = chunk_number * sectors_per_chunk + chunk_offset;
check = raid5_compute_sector(conf, r_sector,
previous, &dummy1, &sh2);
if (check != sh->sector || dummy1 != dd_idx || sh2.pd_idx != sh->pd_idx
|| sh2.qd_idx != sh->qd_idx) {
- printk(KERN_ERR "compute_blocknr: map not correct\n");
+ printk(KERN_ERR "md/raid:%s: compute_blocknr: map not correct\n",
+ mdname(conf->mddev));
return 0;
}
return r_sector;
struct r5dev *dev;
mdk_rdev_t *blocked_rdev = NULL;
int prexor;
+ int dec_preread_active = 0;
memset(&s, 0, sizeof(s));
pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d "
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))
+ dec_preread_active = 1;
}
/* Now to consider new write requests and what else, if anything
ops_run_io(sh, &s);
+ if (dec_preread_active) {
+ /* We delay this until after ops_run_io so that if make_request
+ * is waiting on a barrier, it won't continue until the writes
+ * have actually been submitted.
+ */
+ atomic_dec(&conf->preread_active_stripes);
+ if (atomic_read(&conf->preread_active_stripes) <
+ IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
+ }
return_io(return_bi);
}
struct r6_state r6s;
struct r5dev *dev, *pdev, *qdev;
mdk_rdev_t *blocked_rdev = NULL;
+ int dec_preread_active = 0;
pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
"pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
* completed
*/
if (sh->reconstruct_state == reconstruct_state_drain_result) {
- int qd_idx = sh->qd_idx;
sh->reconstruct_state = reconstruct_state_idle;
/* All the 'written' buffers and the parity blocks are ready to
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))
+ dec_preread_active = 1;
}
/* Now to consider new write requests and what else, if anything
ops_run_io(sh, &s);
+
+ if (dec_preread_active) {
+ /* We delay this until after ops_run_io so that if make_request
+ * is waiting on a barrier, it won't continue until the writes
+ * have actually been submitted.
+ */
+ atomic_dec(&conf->preread_active_stripes);
+ if (atomic_read(&conf->preread_active_stripes) <
+ IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
+ }
+
return_io(return_bi);
}
{
raid5_conf_t *conf = mddev->private;
int i;
+ int devs = max(conf->raid_disks, conf->previous_raid_disks);
rcu_read_lock();
- for (i = 0; i < conf->raid_disks; i++) {
+ for (i = 0; i < devs; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
bio_put(bi);
- mddev = raid_bi->bi_bdev->bd_disk->queue->queuedata;
- conf = mddev->private;
rdev = (void*)raid_bi->bi_next;
raid_bi->bi_next = NULL;
+ mddev = rdev->mddev;
+ conf = mddev->private;
rdev_dec_pending(rdev, conf->mddev);
if ((bi->bi_size>>9) > queue_max_sectors(q))
return 0;
blk_recount_segments(q, bi);
- if (bi->bi_phys_segments > queue_max_phys_segments(q))
+ if (bi->bi_phys_segments > queue_max_segments(q))
return 0;
if (q->merge_bvec_fn)
}
-static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
+static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio)
{
- mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev->private;
- unsigned int dd_idx;
+ int dd_idx;
struct bio* align_bi;
mdk_rdev_t *rdev;
return sh;
}
-static int make_request(struct request_queue *q, struct bio * bi)
+static int make_request(mddev_t *mddev, struct bio * bi)
{
- mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev->private;
int dd_idx;
sector_t new_sector;
sector_t logical_sector, last_sector;
struct stripe_head *sh;
const int rw = bio_data_dir(bi);
- int cpu, remaining;
+ int remaining;
if (unlikely(bio_rw_flagged(bi, BIO_RW_BARRIER))) {
- bio_endio(bi, -EOPNOTSUPP);
+ /* Drain all pending writes. We only really need
+ * to ensure they have been submitted, but this is
+ * easier.
+ */
+ mddev->pers->quiesce(mddev, 1);
+ mddev->pers->quiesce(mddev, 0);
+ md_barrier_request(mddev, bi);
return 0;
}
md_write_start(mddev, bi);
- cpu = part_stat_lock();
- part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
- part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw],
- bio_sectors(bi));
- part_stat_unlock();
-
if (rw == READ &&
mddev->reshape_position == MaxSector &&
- chunk_aligned_read(q,bi))
+ chunk_aligned_read(mddev,bi))
return 0;
logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
new_sector = raid5_compute_sector(conf, logical_sector,
previous,
&dd_idx, NULL);
- pr_debug("raid5: make_request, sector %llu logical %llu\n",
+ pr_debug("raid456: make_request, sector %llu logical %llu\n",
(unsigned long long)new_sector,
(unsigned long long)logical_sector);
finish_wait(&conf->wait_for_overlap, &w);
set_bit(STRIPE_HANDLE, &sh->state);
clear_bit(STRIPE_DELAYED, &sh->state);
+ if (mddev->barrier &&
+ !test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+ atomic_inc(&conf->preread_active_stripes);
release_stripe(sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
bio_endio(bi, 0);
}
+
+ if (mddev->barrier) {
+ /* We need to wait for the stripes to all be handled.
+ * So: wait for preread_active_stripes to drop to 0.
+ */
+ wait_event(mddev->thread->wqueue,
+ atomic_read(&conf->preread_active_stripes) == 0);
+ }
return 0;
}
* As the reads complete, handle_stripe will copy the data
* into the destination stripe and release that stripe.
*/
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ raid5_conf_t *conf = mddev->private;
struct stripe_head *sh;
sector_t first_sector, last_sector;
int raid_disks = conf->previous_raid_disks;
sector_nr = conf->reshape_progress;
sector_div(sector_nr, new_data_disks);
if (sector_nr) {
+ mddev->curr_resync_completed = sector_nr;
+ sysfs_notify(&mddev->kobj, NULL, "sync_completed");
*skipped = 1;
return sector_nr;
}
/* FIXME go_faster isn't used */
static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ raid5_conf_t *conf = mddev->private;
struct stripe_head *sh;
sector_t max_sector = mddev->dev_sectors;
int sync_blocks;
return handled;
}
-#ifdef CONFIG_MULTICORE_RAID456
-static void __process_stripe(void *param, async_cookie_t cookie)
-{
- struct stripe_head *sh = param;
-
- handle_stripe(sh);
- release_stripe(sh);
-}
-
-static void process_stripe(struct stripe_head *sh, struct list_head *domain)
-{
- async_schedule_domain(__process_stripe, sh, domain);
-}
-
-static void synchronize_stripe_processing(struct list_head *domain)
-{
- async_synchronize_full_domain(domain);
-}
-#else
-static void process_stripe(struct stripe_head *sh, struct list_head *domain)
-{
- handle_stripe(sh);
- release_stripe(sh);
- cond_resched();
-}
-
-static void synchronize_stripe_processing(struct list_head *domain)
-{
-}
-#endif
-
/*
* This is our raid5 kernel thread.
struct stripe_head *sh;
raid5_conf_t *conf = mddev->private;
int handled;
- LIST_HEAD(raid_domain);
pr_debug("+++ raid5d active\n");
spin_unlock_irq(&conf->device_lock);
handled++;
- process_stripe(sh, &raid_domain);
+ handle_stripe(sh);
+ release_stripe(sh);
+ cond_resched();
spin_lock_irq(&conf->device_lock);
}
spin_unlock_irq(&conf->device_lock);
- synchronize_stripe_processing(&raid_domain);
async_tx_issue_pending_all();
unplug_slaves(mddev);
if (!sectors)
sectors = mddev->dev_sectors;
- if (!raid_disks) {
+ if (!raid_disks)
/* size is defined by the smallest of previous and new size */
- if (conf->raid_disks < conf->previous_raid_disks)
- raid_disks = conf->raid_disks;
- else
- raid_disks = conf->previous_raid_disks;
- }
+ raid_disks = min(conf->raid_disks, conf->previous_raid_disks);
sectors &= ~((sector_t)mddev->chunk_sectors - 1);
sectors &= ~((sector_t)mddev->new_chunk_sectors - 1);
kfree(percpu->scribble);
pr_err("%s: failed memory allocation for cpu%ld\n",
__func__, cpu);
- return NOTIFY_BAD;
+ return notifier_from_errno(-ENOMEM);
}
break;
case CPU_DEAD:
{
unsigned long cpu;
struct page *spare_page;
- struct raid5_percpu *allcpus;
+ struct raid5_percpu __percpu *allcpus;
void *scribble;
int err;
}
per_cpu_ptr(conf->percpu, cpu)->spare_page = spare_page;
}
- scribble = kmalloc(scribble_len(conf->raid_disks), GFP_KERNEL);
+ scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
if (!scribble) {
err = -ENOMEM;
break;
static raid5_conf_t *setup_conf(mddev_t *mddev)
{
raid5_conf_t *conf;
- int raid_disk, memory;
+ int raid_disk, memory, max_disks;
mdk_rdev_t *rdev;
struct disk_info *disk;
if (mddev->new_level != 5
&& mddev->new_level != 4
&& mddev->new_level != 6) {
- printk(KERN_ERR "raid5: %s: raid level not set to 4/5/6 (%d)\n",
+ printk(KERN_ERR "md/raid:%s: raid level not set to 4/5/6 (%d)\n",
mdname(mddev), mddev->new_level);
return ERR_PTR(-EIO);
}
&& !algorithm_valid_raid5(mddev->new_layout)) ||
(mddev->new_level == 6
&& !algorithm_valid_raid6(mddev->new_layout))) {
- printk(KERN_ERR "raid5: %s: layout %d not supported\n",
+ printk(KERN_ERR "md/raid:%s: layout %d not supported\n",
mdname(mddev), mddev->new_layout);
return ERR_PTR(-EIO);
}
if (mddev->new_level == 6 && mddev->raid_disks < 4) {
- printk(KERN_ERR "raid6: not enough configured devices for %s (%d, minimum 4)\n",
+ printk(KERN_ERR "md/raid:%s: not enough configured devices (%d, minimum 4)\n",
mdname(mddev), mddev->raid_disks);
return ERR_PTR(-EINVAL);
}
if (!mddev->new_chunk_sectors ||
(mddev->new_chunk_sectors << 9) % PAGE_SIZE ||
!is_power_of_2(mddev->new_chunk_sectors)) {
- printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
- mddev->new_chunk_sectors << 9, mdname(mddev));
+ printk(KERN_ERR "md/raid:%s: invalid chunk size %d\n",
+ mdname(mddev), mddev->new_chunk_sectors << 9);
return ERR_PTR(-EINVAL);
}
conf->bypass_threshold = BYPASS_THRESHOLD;
conf->raid_disks = mddev->raid_disks;
- conf->scribble_len = scribble_len(conf->raid_disks);
if (mddev->reshape_position == MaxSector)
conf->previous_raid_disks = mddev->raid_disks;
else
conf->previous_raid_disks = mddev->raid_disks - mddev->delta_disks;
+ max_disks = max(conf->raid_disks, conf->previous_raid_disks);
+ conf->scribble_len = scribble_len(max_disks);
- conf->disks = kzalloc(conf->raid_disks * sizeof(struct disk_info),
+ conf->disks = kzalloc(max_disks * sizeof(struct disk_info),
GFP_KERNEL);
if (!conf->disks)
goto abort;
if (raid5_alloc_percpu(conf) != 0)
goto abort;
- pr_debug("raid5: run(%s) called.\n", mdname(mddev));
+ pr_debug("raid456: run(%s) called.\n", mdname(mddev));
list_for_each_entry(rdev, &mddev->disks, same_set) {
raid_disk = rdev->raid_disk;
- if (raid_disk >= conf->raid_disks
+ if (raid_disk >= max_disks
|| raid_disk < 0)
continue;
disk = conf->disks + raid_disk;
if (test_bit(In_sync, &rdev->flags)) {
char b[BDEVNAME_SIZE];
- printk(KERN_INFO "raid5: device %s operational as raid"
- " disk %d\n", bdevname(rdev->bdev,b),
- raid_disk);
+ printk(KERN_INFO "md/raid:%s: device %s operational as raid"
+ " disk %d\n",
+ mdname(mddev), bdevname(rdev->bdev, b), raid_disk);
} else
/* Cannot rely on bitmap to complete recovery */
conf->fullsync = 1;
}
memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
- conf->raid_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
+ max_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
if (grow_stripes(conf, conf->max_nr_stripes)) {
printk(KERN_ERR
- "raid5: couldn't allocate %dkB for buffers\n", memory);
+ "md/raid:%s: couldn't allocate %dkB for buffers\n",
+ mdname(mddev), memory);
goto abort;
} else
- printk(KERN_INFO "raid5: allocated %dkB for %s\n",
- memory, mdname(mddev));
+ printk(KERN_INFO "md/raid:%s: allocated %dkB\n",
+ mdname(mddev), memory);
conf->thread = md_register_thread(raid5d, mddev, NULL);
if (!conf->thread) {
printk(KERN_ERR
- "raid5: couldn't allocate thread for %s\n",
+ "md/raid:%s: couldn't allocate thread.\n",
mdname(mddev));
goto abort;
}
return ERR_PTR(-ENOMEM);
}
+
+static int only_parity(int raid_disk, int algo, int raid_disks, int max_degraded)
+{
+ switch (algo) {
+ case ALGORITHM_PARITY_0:
+ if (raid_disk < max_degraded)
+ return 1;
+ break;
+ case ALGORITHM_PARITY_N:
+ if (raid_disk >= raid_disks - max_degraded)
+ return 1;
+ break;
+ case ALGORITHM_PARITY_0_6:
+ if (raid_disk == 0 ||
+ raid_disk == raid_disks - 1)
+ return 1;
+ break;
+ case ALGORITHM_LEFT_ASYMMETRIC_6:
+ case ALGORITHM_RIGHT_ASYMMETRIC_6:
+ case ALGORITHM_LEFT_SYMMETRIC_6:
+ case ALGORITHM_RIGHT_SYMMETRIC_6:
+ if (raid_disk == raid_disks - 1)
+ return 1;
+ }
+ return 0;
+}
+
static int run(mddev_t *mddev)
{
raid5_conf_t *conf;
int working_disks = 0, chunk_size;
+ int dirty_parity_disks = 0;
mdk_rdev_t *rdev;
+ sector_t reshape_offset = 0;
if (mddev->recovery_cp != MaxSector)
- printk(KERN_NOTICE "raid5: %s is not clean"
+ printk(KERN_NOTICE "md/raid:%s: not clean"
" -- starting background reconstruction\n",
mdname(mddev));
if (mddev->reshape_position != MaxSector) {
int max_degraded = (mddev->level == 6 ? 2 : 1);
if (mddev->new_level != mddev->level) {
- printk(KERN_ERR "raid5: %s: unsupported reshape "
+ printk(KERN_ERR "md/raid:%s: unsupported reshape "
"required - aborting.\n",
mdname(mddev));
return -EINVAL;
here_new = mddev->reshape_position;
if (sector_div(here_new, mddev->new_chunk_sectors *
(mddev->raid_disks - max_degraded))) {
- printk(KERN_ERR "raid5: reshape_position not "
- "on a stripe boundary\n");
+ printk(KERN_ERR "md/raid:%s: reshape_position not "
+ "on a stripe boundary\n", mdname(mddev));
return -EINVAL;
}
+ reshape_offset = here_new * mddev->new_chunk_sectors;
/* here_new is the stripe we will write to */
here_old = mddev->reshape_position;
sector_div(here_old, mddev->chunk_sectors *
if ((here_new * mddev->new_chunk_sectors !=
here_old * mddev->chunk_sectors) ||
mddev->ro == 0) {
- printk(KERN_ERR "raid5: in-place reshape must be started"
- " in read-only mode - aborting\n");
+ printk(KERN_ERR "md/raid:%s: in-place reshape must be started"
+ " in read-only mode - aborting\n",
+ mdname(mddev));
return -EINVAL;
}
} else if (mddev->delta_disks < 0
: (here_new * mddev->new_chunk_sectors >=
here_old * mddev->chunk_sectors)) {
/* 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 "md/raid:%s: reshape_position too early for "
+ "auto-recovery - aborting.\n",
+ mdname(mddev));
return -EINVAL;
}
- printk(KERN_INFO "raid5: reshape will continue\n");
+ printk(KERN_INFO "md/raid:%s: reshape will continue\n",
+ mdname(mddev));
/* OK, we should be able to continue; */
} else {
BUG_ON(mddev->level != mddev->new_level);
/*
* 0 for a fully functional array, 1 or 2 for a degraded array.
*/
- list_for_each_entry(rdev, &mddev->disks, same_set)
- if (rdev->raid_disk >= 0 &&
- test_bit(In_sync, &rdev->flags))
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ if (rdev->raid_disk < 0)
+ continue;
+ if (test_bit(In_sync, &rdev->flags))
working_disks++;
+ /* This disc is not fully in-sync. However if it
+ * just stored parity (beyond the recovery_offset),
+ * when we don't need to be concerned about the
+ * array being dirty.
+ * When reshape goes 'backwards', we never have
+ * partially completed devices, so we only need
+ * to worry about reshape going forwards.
+ */
+ /* Hack because v0.91 doesn't store recovery_offset properly. */
+ if (mddev->major_version == 0 &&
+ mddev->minor_version > 90)
+ rdev->recovery_offset = reshape_offset;
+
+ if (rdev->recovery_offset < reshape_offset) {
+ /* We need to check old and new layout */
+ if (!only_parity(rdev->raid_disk,
+ conf->algorithm,
+ conf->raid_disks,
+ conf->max_degraded))
+ continue;
+ }
+ if (!only_parity(rdev->raid_disk,
+ conf->prev_algo,
+ conf->previous_raid_disks,
+ conf->max_degraded))
+ continue;
+ dirty_parity_disks++;
+ }
- mddev->degraded = conf->raid_disks - working_disks;
+ mddev->degraded = (max(conf->raid_disks, conf->previous_raid_disks)
+ - working_disks);
if (mddev->degraded > conf->max_degraded) {
- printk(KERN_ERR "raid5: not enough operational devices for %s"
+ printk(KERN_ERR "md/raid:%s: not enough operational devices"
" (%d/%d failed)\n",
mdname(mddev), mddev->degraded, conf->raid_disks);
goto abort;
mddev->dev_sectors &= ~(mddev->chunk_sectors - 1);
mddev->resync_max_sectors = mddev->dev_sectors;
- if (mddev->degraded > 0 &&
+ if (mddev->degraded > dirty_parity_disks &&
mddev->recovery_cp != MaxSector) {
if (mddev->ok_start_degraded)
printk(KERN_WARNING
- "raid5: starting dirty degraded array: %s"
- "- data corruption possible.\n",
+ "md/raid:%s: starting dirty degraded array"
+ " - data corruption possible.\n",
mdname(mddev));
else {
printk(KERN_ERR
- "raid5: cannot start dirty degraded array for %s\n",
+ "md/raid:%s: cannot start dirty degraded array.\n",
mdname(mddev));
goto abort;
}
}
if (mddev->degraded == 0)
- printk("raid5: raid level %d set %s active with %d out of %d"
- " devices, algorithm %d\n", conf->level, mdname(mddev),
+ printk(KERN_INFO "md/raid:%s: raid level %d active with %d out of %d"
+ " devices, algorithm %d\n", mdname(mddev), conf->level,
mddev->raid_disks-mddev->degraded, mddev->raid_disks,
mddev->new_layout);
else
- printk(KERN_ALERT "raid5: raid level %d set %s active with %d"
- " out of %d devices, algorithm %d\n", conf->level,
- mdname(mddev), mddev->raid_disks - mddev->degraded,
- mddev->raid_disks, mddev->new_layout);
+ printk(KERN_ALERT "md/raid:%s: raid level %d active with %d"
+ " out of %d devices, algorithm %d\n",
+ mdname(mddev), conf->level,
+ mddev->raid_disks - mddev->degraded,
+ mddev->raid_disks, mddev->new_layout);
print_raid5_conf(conf);
if (conf->reshape_progress != MaxSector) {
- printk("...ok start reshape thread\n");
conf->reshape_safe = conf->reshape_progress;
atomic_set(&conf->reshape_stripes, 0);
clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
}
/* Ok, everything is just fine now */
- if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
+ if (mddev->to_remove == &raid5_attrs_group)
+ mddev->to_remove = NULL;
+ else if (sysfs_create_group(&mddev->kobj, &raid5_attrs_group))
printk(KERN_WARNING
- "raid5: failed to create sysfs attributes for %s\n",
+ "md/raid:%s: failed to create sysfs attributes.\n",
mdname(mddev));
mddev->queue->queue_lock = &conf->device_lock;
free_conf(conf);
}
mddev->private = NULL;
- printk(KERN_ALERT "raid5: failed to run raid set %s\n", mdname(mddev));
+ printk(KERN_ALERT "md/raid:%s: failed to run raid set.\n", mdname(mddev));
return -EIO;
}
-
-
static int stop(mddev_t *mddev)
{
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ raid5_conf_t *conf = mddev->private;
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
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);
free_conf(conf);
mddev->private = NULL;
+ mddev->to_remove = &raid5_attrs_group;
return 0;
}
static void status(struct seq_file *seq, mddev_t *mddev)
{
- raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
+ raid5_conf_t *conf = mddev->private;
int i;
seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
int i;
struct disk_info *tmp;
- printk("RAID5 conf printout:\n");
+ printk(KERN_DEBUG "RAID conf printout:\n");
if (!conf) {
printk("(conf==NULL)\n");
return;
}
- printk(" --- rd:%d wd:%d\n", conf->raid_disks,
- conf->raid_disks - conf->mddev->degraded);
+ printk(KERN_DEBUG " --- level:%d rd:%d wd:%d\n", conf->level,
+ 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)
- printk(" disk %d, o:%d, dev:%s\n",
- i, !test_bit(Faulty, &tmp->rdev->flags),
- bdevname(tmp->rdev->bdev,b));
+ printk(KERN_DEBUG " disk %d, o:%d, dev:%s\n",
+ i, !test_bit(Faulty, &tmp->rdev->flags),
+ bdevname(tmp->rdev->bdev, b));
}
}
raid5_size(mddev, sectors, mddev->raid_disks))
return -EINVAL;
set_capacity(mddev->gendisk, mddev->array_sectors);
- mddev->changed = 1;
revalidate_disk(mddev->gendisk);
if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) {
mddev->recovery_cp = mddev->dev_sectors;
> conf->max_nr_stripes ||
((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4
> conf->max_nr_stripes) {
- printk(KERN_WARNING "raid5: reshape: not enough stripes. Needed %lu\n",
+ printk(KERN_WARNING "md/raid:%s: reshape: not enough stripes. Needed %lu\n",
+ mdname(mddev),
((max(mddev->chunk_sectors, mddev->new_chunk_sectors) << 9)
/ STRIPE_SIZE)*4);
return 0;
*/
if (raid5_size(mddev, 0, conf->raid_disks + mddev->delta_disks)
< mddev->array_sectors) {
- printk(KERN_ERR "md: %s: array size must be reduced "
+ printk(KERN_ERR "md/raid:%s: array size must be reduced "
"before number of disks\n", mdname(mddev));
return -EINVAL;
}
!test_bit(Faulty, &rdev->flags)) {
if (raid5_add_disk(mddev, rdev) == 0) {
char nm[20];
- set_bit(In_sync, &rdev->flags);
- added_devices++;
- rdev->recovery_offset = 0;
+ if (rdev->raid_disk >= conf->previous_raid_disks) {
+ set_bit(In_sync, &rdev->flags);
+ added_devices++;
+ } else
+ rdev->recovery_offset = 0;
sprintf(nm, "rd%d", rdev->raid_disk);
if (sysfs_create_link(&mddev->kobj,
&rdev->kobj, nm))
printk(KERN_WARNING
- "raid5: failed to create "
- " link %s for %s\n",
- nm, mdname(mddev));
+ "md/raid:%s: failed to create "
+ " link %s\n",
+ mdname(mddev), nm);
} else
break;
}
+ /* When a reshape changes the number of devices, ->degraded
+ * is measured against the large of the pre and post number of
+ * devices.*/
if (mddev->delta_disks > 0) {
spin_lock_irqsave(&conf->device_lock, flags);
- mddev->degraded = (conf->raid_disks - conf->previous_raid_disks)
+ mddev->degraded += (conf->raid_disks - conf->previous_raid_disks)
- added_devices;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
if (mddev->delta_disks > 0) {
md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
set_capacity(mddev->gendisk, mddev->array_sectors);
- mddev->changed = 1;
revalidate_disk(mddev->gendisk);
} else {
int d;
}
+static void *raid45_takeover_raid0(mddev_t *mddev, int level)
+{
+ struct raid0_private_data *raid0_priv = mddev->private;
+
+ /* for raid0 takeover only one zone is supported */
+ if (raid0_priv->nr_strip_zones > 1) {
+ printk(KERN_ERR "md/raid:%s: cannot takeover raid0 with more than one zone.\n",
+ mdname(mddev));
+ return ERR_PTR(-EINVAL);
+ }
+
+ mddev->new_level = level;
+ mddev->new_layout = ALGORITHM_PARITY_N;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
+ mddev->raid_disks += 1;
+ mddev->delta_disks = 1;
+ /* make sure it will be not marked as dirty */
+ mddev->recovery_cp = MaxSector;
+
+ return setup_conf(mddev);
+}
+
+
static void *raid5_takeover_raid1(mddev_t *mddev)
{
int chunksect;
static void *raid5_takeover(mddev_t *mddev)
{
/* raid5 can take over:
- * raid0 - if all devices are the same - make it a raid4 layout
+ * raid0 - if there is only one strip zone - make it a raid4 layout
* raid1 - if there are two drives. We need to know the chunk size
* raid4 - trivial - just use a raid4 layout.
* raid6 - Providing it is a *_6 layout
*/
-
+ if (mddev->level == 0)
+ return raid45_takeover_raid0(mddev, 5);
if (mddev->level == 1)
return raid5_takeover_raid1(mddev);
if (mddev->level == 4) {
return ERR_PTR(-EINVAL);
}
+static void *raid4_takeover(mddev_t *mddev)
+{
+ /* raid4 can take over:
+ * raid0 - if there is only one strip zone
+ * raid5 - if layout is right
+ */
+ if (mddev->level == 0)
+ return raid45_takeover_raid0(mddev, 4);
+ if (mddev->level == 5 &&
+ mddev->layout == ALGORITHM_PARITY_N) {
+ mddev->new_layout = 0;
+ mddev->new_level = 4;
+ return setup_conf(mddev);
+ }
+ return ERR_PTR(-EINVAL);
+}
static struct mdk_personality raid5_personality;
.start_reshape = raid5_start_reshape,
.finish_reshape = raid5_finish_reshape,
.quiesce = raid5_quiesce,
+ .takeover = raid4_takeover,
};
static int __init raid5_init(void)
module_init(raid5_init);
module_exit(raid5_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAID4/5/6 (striping with parity) personality for MD");
MODULE_ALIAS("md-personality-4"); /* RAID5 */
MODULE_ALIAS("md-raid5");
MODULE_ALIAS("md-raid4");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff