#include <linux/module.h>
#include <linux/slab.h>
#include <linux/highmem.h>
-#include <asm/bitops.h>
+#include <linux/bitops.h>
#include <asm/atomic.h>
#include "raid6.h"
+#include <linux/raid/bitmap.h>
+
/*
* Stripe cache
*/
#define STRIPE_SHIFT (PAGE_SHIFT - 9)
#define STRIPE_SECTORS (STRIPE_SIZE>>9)
#define IO_THRESHOLD 1
-#define HASH_PAGES 1
-#define HASH_PAGES_ORDER 0
-#define NR_HASH (HASH_PAGES * PAGE_SIZE / sizeof(struct stripe_head *))
+#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
-#define stripe_hash(conf, sect) ((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK])
+#define stripe_hash(conf, sect) (&((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK]))
/* bio's attached to a stripe+device for I/O are linked together in bi_sector
* order without overlap. There may be several bio's per stripe+device, and
* This macro is used to determine the 'next' bio in the list, given the sector
* of the current stripe+device
*/
-#define r5_next_bio(bio, sect) ( ( bio->bi_sector + (bio->bi_size>>9) < sect + STRIPE_SECTORS) ? bio->bi_next : NULL)
+#define r5_next_bio(bio, sect) ( ( (bio)->bi_sector + ((bio)->bi_size>>9) < sect + STRIPE_SECTORS) ? (bio)->bi_next : NULL)
/*
* The following can be used to debug the driver
*/
#define RAID6_PARANOIA 1 /* Check spinlocks */
#define RAID6_DUMPSTATE 0 /* Include stripe cache state in /proc/mdstat */
#if RAID6_PARANOIA && defined(CONFIG_SMP)
-# define CHECK_DEVLOCK() if (!spin_is_locked(&conf->device_lock)) BUG()
+# define CHECK_DEVLOCK() assert_spin_locked(&conf->device_lock)
#else
# define CHECK_DEVLOCK()
#endif
static void print_raid6_conf (raid6_conf_t *conf);
-static inline void __release_stripe(raid6_conf_t *conf, struct stripe_head *sh)
+static void __release_stripe(raid6_conf_t *conf, struct stripe_head *sh)
{
if (atomic_dec_and_test(&sh->count)) {
if (!list_empty(&sh->lru))
if (test_bit(STRIPE_HANDLE, &sh->state)) {
if (test_bit(STRIPE_DELAYED, &sh->state))
list_add_tail(&sh->lru, &conf->delayed_list);
- else
+ else if (test_bit(STRIPE_BIT_DELAY, &sh->state) &&
+ conf->seq_write == sh->bm_seq)
+ list_add_tail(&sh->lru, &conf->bitmap_list);
+ else {
+ clear_bit(STRIPE_BIT_DELAY, &sh->state);
list_add_tail(&sh->lru, &conf->handle_list);
+ }
md_wakeup_thread(conf->mddev->thread);
} else {
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
list_add_tail(&sh->lru, &conf->inactive_list);
atomic_dec(&conf->active_stripes);
if (!conf->inactive_blocked ||
- atomic_read(&conf->active_stripes) < (NR_STRIPES*3/4))
+ atomic_read(&conf->active_stripes) < (conf->max_nr_stripes*3/4))
wake_up(&conf->wait_for_stripe);
}
}
spin_unlock_irqrestore(&conf->device_lock, flags);
}
-static void remove_hash(struct stripe_head *sh)
+static inline void remove_hash(struct stripe_head *sh)
{
PRINTK("remove_hash(), stripe %llu\n", (unsigned long long)sh->sector);
- if (sh->hash_pprev) {
- if (sh->hash_next)
- sh->hash_next->hash_pprev = sh->hash_pprev;
- *sh->hash_pprev = sh->hash_next;
- sh->hash_pprev = NULL;
- }
+ hlist_del_init(&sh->hash);
}
-static __inline__ void insert_hash(raid6_conf_t *conf, struct stripe_head *sh)
+static inline void insert_hash(raid6_conf_t *conf, struct stripe_head *sh)
{
- struct stripe_head **shp = &stripe_hash(conf, sh->sector);
+ struct hlist_head *hp = stripe_hash(conf, sh->sector);
PRINTK("insert_hash(), stripe %llu\n", (unsigned long long)sh->sector);
CHECK_DEVLOCK();
- if ((sh->hash_next = *shp) != NULL)
- (*shp)->hash_pprev = &sh->hash_next;
- *shp = sh;
- sh->hash_pprev = shp;
+ hlist_add_head(&sh->hash, hp);
}
if (!p)
continue;
sh->dev[i].page = NULL;
- page_cache_release(p);
+ put_page(p);
}
}
static void raid6_build_block (struct stripe_head *sh, int i);
-static inline void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
+static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx)
{
raid6_conf_t *conf = sh->raid_conf;
int disks = conf->raid_disks, i;
static struct stripe_head *__find_stripe(raid6_conf_t *conf, sector_t sector)
{
struct stripe_head *sh;
+ struct hlist_node *hn;
CHECK_DEVLOCK();
PRINTK("__find_stripe, sector %llu\n", (unsigned long long)sector);
- for (sh = stripe_hash(conf, sector); sh; sh = sh->hash_next)
+ hlist_for_each_entry (sh, hn, stripe_hash(conf, sector), hash)
if (sh->sector == sector)
return sh;
PRINTK("__stripe %llu not in cache\n", (unsigned long long)sector);
spin_lock_irq(&conf->device_lock);
do {
+ wait_event_lock_irq(conf->wait_for_stripe,
+ conf->quiesce == 0,
+ conf->device_lock, /* nothing */);
sh = __find_stripe(conf, sector);
if (!sh) {
if (!conf->inactive_blocked)
conf->inactive_blocked = 1;
wait_event_lock_irq(conf->wait_for_stripe,
!list_empty(&conf->inactive_list) &&
- (atomic_read(&conf->active_stripes) < (NR_STRIPES *3/4)
+ (atomic_read(&conf->active_stripes)
+ < (conf->max_nr_stripes *3/4)
|| !conf->inactive_blocked),
conf->device_lock,
unplug_slaves(conf->mddev);
return sh;
}
-static int grow_stripes(raid6_conf_t *conf, int num)
+static int grow_one_stripe(raid6_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;
+ }
+ /* 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(raid6_conf_t *conf, int num)
+{
kmem_cache_t *sc;
int devs = conf->raid_disks;
if (!sc)
return 1;
conf->slab_cache = sc;
- while (num--) {
- sh = kmem_cache_alloc(sc, GFP_KERNEL);
- if (!sh)
+ while (num--)
+ if (!grow_one_stripe(conf))
return 1;
- memset(sh, 0, sizeof(*sh) + (devs-1)*sizeof(struct r5dev));
- sh->raid_conf = conf;
- sh->lock = SPIN_LOCK_UNLOCKED;
-
- if (grow_buffers(sh, conf->raid_disks)) {
- shrink_buffers(sh, conf->raid_disks);
- kmem_cache_free(sc, sh);
- return 1;
- }
- /* 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 0;
}
-static void shrink_stripes(raid6_conf_t *conf)
+static int drop_one_stripe(raid6_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;
+ if (atomic_read(&sh->count))
+ BUG();
+ shrink_buffers(sh, conf->raid_disks);
+ kmem_cache_free(conf->slab_cache, sh);
+ atomic_dec(&conf->active_stripes);
+ return 1;
+}
- while (1) {
- spin_lock_irq(&conf->device_lock);
- sh = get_free_stripe(conf);
- spin_unlock_irq(&conf->device_lock);
- if (!sh)
- break;
- if (atomic_read(&sh->count))
- BUG();
- shrink_buffers(sh, conf->raid_disks);
- kmem_cache_free(conf->slab_cache, sh);
- atomic_dec(&conf->active_stripes);
- }
- kmem_cache_destroy(conf->slab_cache);
+static void shrink_stripes(raid6_conf_t *conf)
+{
+ while (drop_one_stripe(conf))
+ ;
+
+ if (conf->slab_cache)
+ kmem_cache_destroy(conf->slab_cache);
conf->slab_cache = NULL;
}
-static int raid6_end_read_request (struct bio * bi, unsigned int bytes_done,
- int error)
+static int raid6_end_read_request(struct bio * bi, unsigned int bytes_done,
+ int error)
{
struct stripe_head *sh = bi->bi_private;
raid6_conf_t *conf = sh->raid_conf;
#else
set_bit(R5_UPTODATE, &sh->dev[i].flags);
#endif
+ if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ printk(KERN_INFO "raid6: 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 {
- md_error(conf->mddev, conf->disks[i].rdev);
+ 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 "raid6: read error not correctable.\n");
+ else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
+ /* Oh, no!!! */
+ printk(KERN_WARNING "raid6: read error NOT corrected!!\n");
+ else if (atomic_read(&conf->disks[i].rdev->read_errors)
+ > conf->max_nr_stripes)
+ printk(KERN_WARNING
+ "raid6: 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);
+ }
}
rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
#if 0
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;
raid6_conf_t *conf = (raid6_conf_t *) mddev->private;
PRINTK("raid6: error called\n");
- if (!rdev->faulty) {
+ if (!test_bit(Faulty, &rdev->flags)) {
mddev->sb_dirty = 1;
- conf->working_disks--;
- if (rdev->in_sync) {
+ if (test_bit(In_sync, &rdev->flags)) {
+ conf->working_disks--;
mddev->degraded++;
conf->failed_disks++;
- rdev->in_sync = 0;
+ clear_bit(In_sync, &rdev->flags);
/*
* if recovery was running, make sure it aborts.
*/
set_bit(MD_RECOVERY_ERR, &mddev->recovery);
}
- rdev->faulty = 1;
+ set_bit(Faulty, &rdev->flags);
printk (KERN_ALERT
"raid6: Disk failure on %s, disabling device."
" Operation continuing on %d devices\n",
char *pa = page_address(page);
struct bio_vec *bvl;
int i;
+ int page_offset;
- for (;bio && bio->bi_sector < sector+STRIPE_SECTORS;
- bio = r5_next_bio(bio, sector) ) {
- 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 (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;
+ 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;
}
}
case READ_MODIFY_WRITE:
BUG(); /* READ_MODIFY_WRITE N/A for RAID-6 */
case RECONSTRUCT_WRITE:
- case UPDATE_PARITY: /* Is this right? */
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);
+
if (sh->dev[i].written) BUG();
sh->dev[i].written = chosen;
}
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;
}
/* Compute one missing block */
-static void compute_block_1(struct stripe_head *sh, int dd_idx)
+static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
{
raid6_conf_t *conf = sh->raid_conf;
int i, count, disks = conf->raid_disks;
compute_parity(sh, UPDATE_PARITY);
} else {
ptr[0] = page_address(sh->dev[dd_idx].page);
- memset(ptr[0], 0, STRIPE_SIZE);
+ if (!nozero) memset(ptr[0], 0, STRIPE_SIZE);
count = 1;
for (i = disks ; i--; ) {
if (i == dd_idx || i == qd_idx)
if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
ptr[count++] = p;
else
- PRINTK("compute_block() %d, stripe %llu, %d"
+ printk("compute_block() %d, stripe %llu, %d"
" not present\n", dd_idx,
(unsigned long long)sh->sector, i);
}
if (count != 1)
xor_block(count, STRIPE_SIZE, ptr);
- set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
+ if (!nozero) set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
+ else clear_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
}
}
return;
} else {
/* We're missing D+Q; recompute D from P */
- compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1);
+ compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1, 0);
compute_parity(sh, UPDATE_PARITY); /* Is this necessary? */
return;
}
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 ) {
* toread/towrite point to the first in a chain.
* The bi_next chain must be in order.
*/
-static void add_stripe_bio (struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite)
+static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite)
{
struct bio **bip;
raid6_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,
spin_lock(&sh->lock);
spin_lock_irq(&conf->device_lock);
- if (forwrite)
+ if (forwrite) {
bip = &sh->dev[dd_idx].towrite;
- else
+ 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) {
- BUG_ON((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector);
- bip = & (*bip)->bi_next;
+ if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector)
+ goto overlap;
+ bip = &(*bip)->bi_next;
}
-/* FIXME do I need to worry about overlapping bion */
+ if (*bip && (*bip)->bi_sector < bi->bi_sector + ((bi->bi_size)>>9))
+ goto overlap;
+
if (*bip && bi->bi_next && (*bip) != bi->bi_next)
BUG();
if (*bip)
(unsigned long long)bi->bi_sector,
(unsigned long long)sh->sector, dd_idx);
+ 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 (forwrite) {
- /* check if page is coverred */
+ /* 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 &&
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 int page_is_zero(struct page *p)
+{
+ char *a = page_address(p);
+ return ((*(u32*)a) == 0 &&
+ memcmp(a, a+4, STRIPE_SIZE-4)==0);
+}
/*
* handle_stripe - do things to a stripe.
*
*
*/
-static void handle_stripe(struct stripe_head *sh)
+static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
{
raid6_conf_t *conf = sh->raid_conf;
int disks = conf->raid_disks;
syncing = test_bit(STRIPE_SYNCING, &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];
clear_bit(R5_Insync, &dev->flags);
- clear_bit(R5_Syncio, &dev->flags);
PRINTK("check %d: state 0x%lx read %p write %p written %p\n",
i, dev->flags, dev->toread, dev->towrite, dev->written);
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);
non_overwrite++;
}
if (dev->written) written++;
- rdev = conf->disks[i].rdev; /* FIXME, should I be looking rdev */
- if (!rdev || !rdev->in_sync) {
+ rdev = rcu_dereference(conf->disks[i].rdev);
+ if (!rdev || !test_bit(In_sync, &rdev->flags)) {
+ /* The ReadError flag will just be confusing now */
+ clear_bit(R5_ReadError, &dev->flags);
+ clear_bit(R5_ReWrite, &dev->flags);
+ }
+ if (!rdev || !test_bit(In_sync, &rdev->flags)
+ || test_bit(R5_ReadError, &dev->flags)) {
if ( failed < 2 )
failed_num[failed] = i;
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,
* need to be failed
*/
if (failed > 2 && to_read+to_write+written) {
- spin_lock_irq(&conf->device_lock);
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--;
+ 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);
/* 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);
}
/* fail any reads if this device is non-operational */
- if (!test_bit(R5_Insync, &sh->dev[i].flags)) {
+ 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);
bi = nextbi;
}
}
+ spin_unlock_irq(&conf->device_lock);
+ if (bitmap_end)
+ bitmap_endwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS, 0, 0);
}
- spin_unlock_irq(&conf->device_lock);
}
if (failed > 2 && syncing) {
md_done_sync(conf->mddev, STRIPE_SECTORS,0);
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);
}
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);
}
}
}
* parity, or to satisfy requests
* or to load a block that is being partially written.
*/
- if (to_read || non_overwrite || (syncing && (uptodate < disks))) {
+ 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 ||
- (sh->dev[failed_num[0]].towrite && !test_bit(R5_OVERWRITE, &sh->dev[failed_num[0]].flags)))) ||
- (failed >= 2 && (sh->dev[failed_num[1]].toread ||
- (sh->dev[failed_num[1]].towrite && !test_bit(R5_OVERWRITE, &sh->dev[failed_num[1]].flags))))
+ (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
if (uptodate == disks-1) {
PRINTK("Computing stripe %llu block %d\n",
(unsigned long long)sh->sector, i);
- compute_block_1(sh, 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 */
locked++;
PRINTK("Reading block %d (sync=%d)\n",
i, syncing);
- if (syncing)
- md_sync_acct(conf->disks[i].rdev, STRIPE_SECTORS);
}
}
}
}
}
/* now if nothing is locked, and if we have enough data, we can start a write request */
- if (locked == 0 && rcw == 0) {
+ 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]); break;
+ 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? */
}
(unsigned long long)sh->sector, i);
locked++;
set_bit(R5_Wantwrite, &sh->dev[i].flags);
-#if 0 /**** FIX: I don't understand the logic here... ****/
- if (!test_bit(R5_Insync, &sh->dev[i].flags)
- || ((i==pd_idx || i==qd_idx) && failed == 0)) /* FIX? */
- set_bit(STRIPE_INSYNC, &sh->state);
-#endif
}
+ /* 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)
* 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) && failed <= 2) {
- set_bit(STRIPE_HANDLE, &sh->state);
-#if 0 /* RAID-6: Don't support CHECK PARITY yet */
- if (failed == 0) {
- char *pagea;
- if (uptodate != disks)
- BUG();
- compute_parity(sh, CHECK_PARITY);
- uptodate--;
- pagea = page_address(sh->dev[pd_idx].page);
- if ((*(u32*)pagea) == 0 &&
- !memcmp(pagea, pagea+4, STRIPE_SIZE-4)) {
- /* parity is correct (on disc, not in buffer any more) */
- set_bit(STRIPE_INSYNC, &sh->state);
- }
- }
-#endif
- if (!test_bit(STRIPE_INSYNC, &sh->state)) {
- int failed_needupdate[2];
- struct r5dev *adev, *bdev;
+ if (syncing && locked == 0 && !test_bit(STRIPE_INSYNC, &sh->state)) {
+ int update_p = 0, update_q = 0;
+ struct r5dev *dev;
- if ( failed < 1 )
- failed_num[0] = pd_idx;
- if ( failed < 2 )
- failed_num[1] = (failed_num[0] == qd_idx) ? pd_idx : qd_idx;
-
- failed_needupdate[0] = !test_bit(R5_UPTODATE, &sh->dev[failed_num[0]].flags);
- failed_needupdate[1] = !test_bit(R5_UPTODATE, &sh->dev[failed_num[1]].flags);
+ set_bit(STRIPE_HANDLE, &sh->state);
- PRINTK("sync: failed=%d num=%d,%d fnu=%u%u\n",
- failed, failed_num[0], failed_num[1], failed_needupdate[0], failed_needupdate[1]);
+ 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 0 /* RAID-6: This code seems to require that CHECK_PARITY destroys the uptodateness of the parity */
- /* should be able to compute the missing block(s) and write to spare */
- if ( failed_needupdate[0] ^ failed_needupdate[1] ) {
- if (uptodate+1 != disks)
- BUG();
- compute_block_1(sh, failed_needupdate[0] ? failed_num[0] : failed_num[1]);
- uptodate++;
- } else if ( failed_needupdate[0] & failed_needupdate[1] ) {
- if (uptodate+2 != disks)
- BUG();
- compute_block_2(sh, failed_num[0], failed_num[1]);
- uptodate += 2;
+ /* 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_parity(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;
}
-#else
- compute_block_2(sh, failed_num[0], failed_num[1]);
- uptodate += failed_needupdate[0] + failed_needupdate[1];
-#endif
- if (uptodate != disks)
- BUG();
+ /* now write out any block on a failed drive,
+ * or P or Q if they need it
+ */
- PRINTK("Marking for sync stripe %llu blocks %d,%d\n",
- (unsigned long long)sh->sector, failed_num[0], failed_num[1]);
+ 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);
+ }
- /**** FIX: Should we really do both of these unconditionally? ****/
- adev = &sh->dev[failed_num[0]];
- locked += !test_bit(R5_LOCKED, &adev->flags);
- set_bit(R5_LOCKED, &adev->flags);
- set_bit(R5_Wantwrite, &adev->flags);
- bdev = &sh->dev[failed_num[1]];
- locked += !test_bit(R5_LOCKED, &bdev->flags);
- set_bit(R5_LOCKED, &bdev->flags);
- set_bit(R5_Wantwrite, &bdev->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);
- set_bit(R5_Syncio, &adev->flags);
- set_bit(R5_Syncio, &bdev->flags);
}
}
+
if (syncing && 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 (test_bit(R5_ReadError, &dev->flags)
+ && !test_bit(R5_LOCKED, &dev->flags)
+ && test_bit(R5_UPTODATE, &dev->flags)
+ ) {
+ 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);
+ } else {
+ /* let's read it back */
+ set_bit(R5_Wantread, &dev->flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ }
+ }
+ }
spin_unlock(&sh->lock);
while ((bi=return_bi)) {
else
bi->bi_end_io = raid6_end_read_request;
- spin_lock_irq(&conf->device_lock);
- rdev = conf->disks[i].rdev;
- if (rdev && rdev->faulty)
+ 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);
- spin_unlock_irq(&conf->device_lock);
+ rcu_read_unlock();
if (rdev) {
- if (test_bit(R5_Syncio, &sh->dev[i].flags))
- md_sync_acct(rdev, STRIPE_SECTORS);
+ if (syncing)
+ md_sync_acct(rdev->bdev, STRIPE_SECTORS);
bi->bi_bdev = rdev->bdev;
PRINTK("for %llu schedule op %ld on disc %d\n",
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);
}
}
-static inline void raid6_activate_delayed(raid6_conf_t *conf)
+static void raid6_activate_delayed(raid6_conf_t *conf)
{
if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
while (!list_empty(&conf->delayed_list)) {
}
}
+static void activate_bit_delay(raid6_conf_t *conf)
+{
+ /* device_lock is held */
+ struct list_head head;
+ list_add(&head, &conf->bitmap_list);
+ list_del_init(&conf->bitmap_list);
+ while (!list_empty(&head)) {
+ struct stripe_head *sh = list_entry(head.next, struct stripe_head, lru);
+ list_del_init(&sh->lru);
+ atomic_inc(&sh->count);
+ __release_stripe(conf, sh);
+ }
+}
+
static void unplug_slaves(mddev_t *mddev)
{
raid6_conf_t *conf = mddev_to_conf(mddev);
int i;
- unsigned long flags;
- spin_lock_irqsave(&conf->device_lock, flags);
+ rcu_read_lock();
for (i=0; i<mddev->raid_disks; i++) {
- mdk_rdev_t *rdev = conf->disks[i].rdev;
- if (rdev && atomic_read(&rdev->nr_pending)) {
+ 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);
atomic_inc(&rdev->nr_pending);
- spin_unlock_irqrestore(&conf->device_lock, flags);
+ rcu_read_unlock();
- if (r_queue && r_queue->unplug_fn)
+ if (r_queue->unplug_fn)
r_queue->unplug_fn(r_queue);
- spin_lock_irqsave(&conf->device_lock, flags);
- atomic_dec(&rdev->nr_pending);
+ rdev_dec_pending(rdev, mddev);
+ rcu_read_lock();
}
}
- spin_unlock_irqrestore(&conf->device_lock, flags);
+ rcu_read_unlock();
}
static void raid6_unplug_device(request_queue_t *q)
spin_lock_irqsave(&conf->device_lock, flags);
- if (blk_remove_plug(q))
+ if (blk_remove_plug(q)) {
+ conf->seq_flush++;
raid6_activate_delayed(conf);
+ }
md_wakeup_thread(mddev->thread);
spin_unlock_irqrestore(&conf->device_lock, flags);
unplug_slaves(mddev);
}
+static int raid6_issue_flush(request_queue_t *q, struct gendisk *disk,
+ sector_t *error_sector)
+{
+ mddev_t *mddev = q->queuedata;
+ raid6_conf_t *conf = mddev_to_conf(mddev);
+ int i, ret = 0;
+
+ 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 (!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_unlock();
+ return ret;
+}
+
static inline void raid6_plug_device(raid6_conf_t *conf)
{
spin_lock_irq(&conf->device_lock);
sector_t new_sector;
sector_t logical_sector, last_sector;
struct stripe_head *sh;
+ const int rw = bio_data_dir(bi);
- if (bio_data_dir(bi)==WRITE) {
- disk_stat_inc(mddev->gendisk, writes);
- disk_stat_add(mddev->gendisk, write_sectors, bio_sectors(bi));
- } else {
- disk_stat_inc(mddev->gendisk, reads);
- disk_stat_add(mddev->gendisk, read_sectors, bio_sectors(bi));
+ if (unlikely(bio_barrier(bi))) {
+ bio_endio(bi, bi->bi_size, -EOPNOTSUPP);
+ return 0;
}
+ md_write_start(mddev, bi);
+
+ disk_stat_inc(mddev->gendisk, ios[rw]);
+ disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(bi));
+
logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
last_sector = bi->bi_sector + (bi->bi_size>>9);
bi->bi_next = NULL;
bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
- if ( bio_data_dir(bi) == WRITE )
- md_write_start(mddev);
+
for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
+ DEFINE_WAIT(w);
new_sector = raid6_compute_sector(logical_sector,
raid_disks, data_disks, &dd_idx, &pd_idx, conf);
- PRINTK("raid6: make_request, sector %Lu logical %Lu\n",
+ PRINTK("raid6: make_request, sector %llu logical %llu\n",
(unsigned long long)new_sector,
(unsigned long long)logical_sector);
+ retry:
+ prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
sh = get_active_stripe(conf, new_sector, pd_idx, (bi->bi_rw&RWA_MASK));
if (sh) {
-
- add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK));
-
+ if (!add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK))) {
+ /* Add failed due to overlap. Flush everything
+ * and wait a while
+ */
+ raid6_unplug_device(mddev->queue);
+ release_stripe(sh);
+ schedule();
+ goto retry;
+ }
+ finish_wait(&conf->wait_for_overlap, &w);
raid6_plug_device(conf);
- handle_stripe(sh);
+ handle_stripe(sh, NULL);
release_stripe(sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
clear_bit(BIO_UPTODATE, &bi->bi_flags);
+ finish_wait(&conf->wait_for_overlap, &w);
break;
}
if (--bi->bi_phys_segments == 0) {
int bytes = bi->bi_size;
- if ( bio_data_dir(bi) == WRITE )
+ if (rw == WRITE )
md_write_end(mddev);
bi->bi_size = 0;
bi->bi_end_io(bi, bytes, 0);
}
/* FIXME go_faster isn't used */
-static int sync_request (mddev_t *mddev, sector_t sector_nr, int go_faster)
+static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
raid6_conf_t *conf = (raid6_conf_t *) mddev->private;
struct stripe_head *sh;
sector_t first_sector;
int raid_disks = conf->raid_disks;
int data_disks = raid_disks - 2;
+ sector_t max_sector = mddev->size << 1;
+ int sync_blocks;
+ int still_degraded = 0;
+ int i;
- if (sector_nr >= mddev->size <<1) {
+ if (sector_nr >= max_sector) {
/* just being told to finish up .. nothing much to do */
unplug_slaves(mddev);
+
+ if (mddev->curr_resync < max_sector) /* aborted */
+ bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
+ &sync_blocks, 1);
+ else /* completed sync */
+ conf->fullsync = 0;
+ bitmap_close_sync(mddev->bitmap);
+
return 0;
}
+ /* if there are 2 or more failed drives and we are trying
+ * to resync, then assert that we are finished, because there is
+ * nothing we can do.
+ */
+ if (mddev->degraded >= 2 && test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ sector_t rv = (mddev->size << 1) - sector_nr;
+ *skipped = 1;
+ return rv;
+ }
+ if (!bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
+ !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
+ !conf->fullsync && sync_blocks >= STRIPE_SECTORS) {
+ /* we can skip this block, and probably more */
+ sync_blocks /= STRIPE_SECTORS;
+ *skipped = 1;
+ return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
+ }
x = sector_nr;
chunk_offset = sector_div(x, sectors_per_chunk);
/* make sure we don't swamp the stripe cache if someone else
* is trying to get access
*/
- set_current_state(TASK_UNINTERRUPTIBLE);
- schedule_timeout(1);
+ schedule_timeout_uninterruptible(1);
}
+ /* Need to check if array will still be degraded after recovery/resync
+ * We don't need to check the 'failed' flag as when that gets set,
+ * recovery aborts.
+ */
+ for (i=0; i<mddev->raid_disks; i++)
+ if (conf->disks[i].rdev == NULL)
+ still_degraded = 1;
+
+ bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
+
spin_lock(&sh->lock);
set_bit(STRIPE_SYNCING, &sh->state);
clear_bit(STRIPE_INSYNC, &sh->state);
spin_unlock(&sh->lock);
- handle_stripe(sh);
+ handle_stripe(sh, NULL);
release_stripe(sh);
return STRIPE_SECTORS;
PRINTK("+++ raid6d active\n");
md_check_recovery(mddev);
- md_handle_safemode(mddev);
handled = 0;
spin_lock_irq(&conf->device_lock);
while (1) {
struct list_head *first;
+ if (conf->seq_flush - conf->seq_write > 0) {
+ int seq = conf->seq_flush;
+ spin_unlock_irq(&conf->device_lock);
+ bitmap_unplug(mddev->bitmap);
+ spin_lock_irq(&conf->device_lock);
+ conf->seq_write = seq;
+ activate_bit_delay(conf);
+ }
+
if (list_empty(&conf->handle_list) &&
atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD &&
!blk_queue_plugged(mddev->queue) &&
spin_unlock_irq(&conf->device_lock);
handled++;
- handle_stripe(sh);
+ handle_stripe(sh, conf->spare_page);
release_stripe(sh);
spin_lock_irq(&conf->device_lock);
PRINTK("--- raid6d inactive\n");
}
-static int run (mddev_t *mddev)
+static ssize_t
+raid6_show_stripe_cache_size(mddev_t *mddev, char *page)
+{
+ raid6_conf_t *conf = mddev_to_conf(mddev);
+ if (conf)
+ return sprintf(page, "%d\n", conf->max_nr_stripes);
+ else
+ return 0;
+}
+
+static ssize_t
+raid6_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
+{
+ raid6_conf_t *conf = mddev_to_conf(mddev);
+ char *end;
+ int new;
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (!conf)
+ return -ENODEV;
+
+ new = simple_strtoul(page, &end, 10);
+ if (!*page || (*end && *end != '\n') )
+ return -EINVAL;
+ if (new <= 16 || new > 32768)
+ return -EINVAL;
+ while (new < conf->max_nr_stripes) {
+ if (drop_one_stripe(conf))
+ conf->max_nr_stripes--;
+ else
+ break;
+ }
+ while (new > conf->max_nr_stripes) {
+ if (grow_one_stripe(conf))
+ conf->max_nr_stripes++;
+ else break;
+ }
+ return len;
+}
+
+static struct md_sysfs_entry
+raid6_stripecache_size = __ATTR(stripe_cache_size, S_IRUGO | S_IWUSR,
+ raid6_show_stripe_cache_size,
+ raid6_store_stripe_cache_size);
+
+static ssize_t
+stripe_cache_active_show(mddev_t *mddev, char *page)
+{
+ raid6_conf_t *conf = mddev_to_conf(mddev);
+ if (conf)
+ return sprintf(page, "%d\n", atomic_read(&conf->active_stripes));
+ else
+ return 0;
+}
+
+static struct md_sysfs_entry
+raid6_stripecache_active = __ATTR_RO(stripe_cache_active);
+
+static struct attribute *raid6_attrs[] = {
+ &raid6_stripecache_size.attr,
+ &raid6_stripecache_active.attr,
+ NULL,
+};
+static struct attribute_group raid6_attrs_group = {
+ .name = NULL,
+ .attrs = raid6_attrs,
+};
+
+static int run(mddev_t *mddev)
{
raid6_conf_t *conf;
int raid_disk, memory;
return -EIO;
}
- mddev->private = kmalloc (sizeof (raid6_conf_t)
- + mddev->raid_disks * sizeof(struct disk_info),
- GFP_KERNEL);
+ mddev->private = kzalloc(sizeof (raid6_conf_t)
+ + mddev->raid_disks * sizeof(struct disk_info),
+ GFP_KERNEL);
if ((conf = mddev->private) == NULL)
goto abort;
- memset (conf, 0, sizeof (*conf) + mddev->raid_disks * sizeof(struct disk_info) );
conf->mddev = mddev;
- if ((conf->stripe_hashtbl = (struct stripe_head **) __get_free_pages(GFP_ATOMIC, HASH_PAGES_ORDER)) == NULL)
+ if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
+ goto abort;
+
+ conf->spare_page = alloc_page(GFP_KERNEL);
+ if (!conf->spare_page)
goto abort;
- memset(conf->stripe_hashtbl, 0, HASH_PAGES * PAGE_SIZE);
- conf->device_lock = SPIN_LOCK_UNLOCKED;
+ spin_lock_init(&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->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);
- mddev->queue->unplug_fn = raid6_unplug_device;
-
PRINTK("raid6: run(%s) called.\n", mdname(mddev));
ITERATE_RDEV(mddev,rdev,tmp) {
disk->rdev = rdev;
- if (rdev->in_sync) {
+ if (test_bit(In_sync, &rdev->flags)) {
char b[BDEVNAME_SIZE];
printk(KERN_INFO "raid6: device %s operational as raid"
" disk %d\n", bdevname(rdev->bdev,b),
/* device size must be a multiple of chunk size */
mddev->size &= ~(mddev->chunk_size/1024 -1);
+ mddev->resync_max_sectors = mddev->size << 1;
if (conf->raid_disks < 4) {
printk(KERN_ERR "raid6: not enough configured devices for %s (%d, minimum 4)\n",
goto abort;
}
-#if 0 /* FIX: For now */
if (mddev->degraded > 0 &&
mddev->recovery_cp != MaxSector) {
- printk(KERN_ERR "raid6: cannot start dirty degraded array for %s\n", mdname(mddev));
- goto abort;
+ if (mddev->ok_start_degraded)
+ printk(KERN_WARNING "raid6: starting dirty degraded array:%s"
+ "- data corruption possible.\n",
+ mdname(mddev));
+ else {
+ printk(KERN_ERR "raid6: cannot start dirty degraded array"
+ " for %s\n", mdname(mddev));
+ goto abort;
+ }
}
-#endif
{
mddev->thread = md_register_thread(raid6d, mddev, "%s_raid6");
*/
{
int stripe = (mddev->raid_disks-2) * mddev->chunk_size
- / PAGE_CACHE_SIZE;
+ / PAGE_SIZE;
if (mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
}
/* Ok, everything is just fine now */
mddev->array_size = mddev->size * (mddev->raid_disks - 2);
+
+ mddev->queue->unplug_fn = raid6_unplug_device;
+ mddev->queue->issue_flush_fn = raid6_issue_flush;
return 0;
abort:
if (conf) {
print_raid6_conf(conf);
- if (conf->stripe_hashtbl)
- free_pages((unsigned long) conf->stripe_hashtbl,
- HASH_PAGES_ORDER);
+ safe_put_page(conf->spare_page);
+ kfree(conf->stripe_hashtbl);
kfree(conf);
}
mddev->private = NULL;
md_unregister_thread(mddev->thread);
mddev->thread = NULL;
shrink_stripes(conf);
- free_pages((unsigned long) conf->stripe_hashtbl, HASH_PAGES_ORDER);
+ kfree(conf->stripe_hashtbl);
+ blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
+ sysfs_remove_group(&mddev->kobj, &raid6_attrs_group);
kfree(conf);
mddev->private = NULL;
return 0;
static void printall (struct seq_file *seq, raid6_conf_t *conf)
{
struct stripe_head *sh;
+ struct hlist_node *hn;
int i;
spin_lock_irq(&conf->device_lock);
for (i = 0; i < NR_HASH; i++) {
sh = conf->stripe_hashtbl[i];
- for (; sh; sh = sh->hash_next) {
+ hlist_for_each_entry(sh, hn, &conf->stripe_hashtbl[i], hash) {
if (sh->raid_conf != conf)
continue;
print_sh(seq, sh);
for (i = 0; i < conf->raid_disks; i++)
seq_printf (seq, "%s",
conf->disks[i].rdev &&
- conf->disks[i].rdev->in_sync ? "U" : "_");
+ test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_");
seq_printf (seq, "]");
#if RAID6_DUMPSTATE
seq_printf (seq, "\n");
tmp = conf->disks + i;
if (tmp->rdev)
printk(" disk %d, o:%d, dev:%s\n",
- i, !tmp->rdev->faulty,
+ i, !test_bit(Faulty, &tmp->rdev->flags),
bdevname(tmp->rdev->bdev,b));
}
}
raid6_conf_t *conf = mddev->private;
struct disk_info *tmp;
- spin_lock_irq(&conf->device_lock);
for (i = 0; i < conf->raid_disks; i++) {
tmp = conf->disks + i;
if (tmp->rdev
- && !tmp->rdev->faulty
- && !tmp->rdev->in_sync) {
+ && !test_bit(Faulty, &tmp->rdev->flags)
+ && !test_bit(In_sync, &tmp->rdev->flags)) {
mddev->degraded--;
conf->failed_disks--;
conf->working_disks++;
- tmp->rdev->in_sync = 1;
+ set_bit(In_sync, &tmp->rdev->flags);
}
}
- spin_unlock_irq(&conf->device_lock);
print_raid6_conf(conf);
return 0;
}
static int raid6_remove_disk(mddev_t *mddev, int number)
{
raid6_conf_t *conf = mddev->private;
- int err = 1;
+ int err = 0;
+ mdk_rdev_t *rdev;
struct disk_info *p = conf->disks + number;
print_raid6_conf(conf);
- spin_lock_irq(&conf->device_lock);
-
- if (p->rdev) {
- if (p->rdev->in_sync ||
- atomic_read(&p->rdev->nr_pending)) {
+ rdev = p->rdev;
+ if (rdev) {
+ if (test_bit(In_sync, &rdev->flags) ||
+ atomic_read(&rdev->nr_pending)) {
err = -EBUSY;
goto abort;
}
p->rdev = NULL;
- err = 0;
+ synchronize_rcu();
+ if (atomic_read(&rdev->nr_pending)) {
+ /* lost the race, try later */
+ err = -EBUSY;
+ p->rdev = rdev;
+ }
}
- if (err)
- MD_BUG();
+
abort:
- spin_unlock_irq(&conf->device_lock);
+
print_raid6_conf(conf);
return err;
}
int disk;
struct disk_info *p;
- spin_lock_irq(&conf->device_lock);
+ if (mddev->degraded > 2)
+ /* no point adding a device */
+ return 0;
/*
- * find the disk ...
+ * find the disk ... but prefer rdev->saved_raid_disk
+ * if possible.
*/
- for (disk=0; disk < mddev->raid_disks; disk++)
+ if (rdev->saved_raid_disk >= 0 &&
+ conf->disks[rdev->saved_raid_disk].rdev == NULL)
+ disk = rdev->saved_raid_disk;
+ else
+ disk = 0;
+ for ( ; disk < mddev->raid_disks; disk++)
if ((p=conf->disks + disk)->rdev == NULL) {
- p->rdev = rdev;
- rdev->in_sync = 0;
+ clear_bit(In_sync, &rdev->flags);
rdev->raid_disk = disk;
found = 1;
+ if (rdev->saved_raid_disk != disk)
+ conf->fullsync = 1;
+ rcu_assign_pointer(p->rdev, rdev);
break;
}
- spin_unlock_irq(&conf->device_lock);
print_raid6_conf(conf);
return found;
}
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
}
mddev->size = sectors /2;
+ mddev->resync_max_sectors = sectors;
return 0;
}
-static mdk_personality_t raid6_personality=
+static void raid6_quiesce(mddev_t *mddev, int state)
+{
+ raid6_conf_t *conf = mddev_to_conf(mddev);
+
+ switch(state) {
+ case 1: /* stop all writes */
+ spin_lock_irq(&conf->device_lock);
+ conf->quiesce = 1;
+ wait_event_lock_irq(conf->wait_for_stripe,
+ atomic_read(&conf->active_stripes) == 0,
+ conf->device_lock, /* nothing */);
+ spin_unlock_irq(&conf->device_lock);
+ break;
+
+ case 0: /* re-enable writes */
+ spin_lock_irq(&conf->device_lock);
+ conf->quiesce = 0;
+ wake_up(&conf->wait_for_stripe);
+ spin_unlock_irq(&conf->device_lock);
+ break;
+ }
+}
+
+static struct mdk_personality raid6_personality =
{
.name = "raid6",
+ .level = 6,
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
.spare_active = raid6_spare_active,
.sync_request = sync_request,
.resize = raid6_resize,
+ .quiesce = raid6_quiesce,
};
-static int __init raid6_init (void)
+static int __init raid6_init(void)
{
int e;
if ( e )
return e;
- return register_md_personality (RAID6, &raid6_personality);
+ return register_md_personality(&raid6_personality);
}
static void raid6_exit (void)
{
- unregister_md_personality (RAID6);
+ unregister_md_personality(&raid6_personality);
}
module_init(raid6_init);
module_exit(raid6_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md-personality-8"); /* RAID6 */
+MODULE_ALIAS("md-raid6");
+MODULE_ALIAS("md-level-6");