*/
#define NR_RAID1_BIOS 256
-static mdk_personality_t raid1_personality;
static void unplug_slaves(mddev_t *mddev);
int size = offsetof(r1bio_t, bios[pi->raid_disks]);
/* allocate a r1bio with room for raid_disks entries in the bios array */
- r1_bio = kmalloc(size, gfp_flags);
- if (r1_bio)
- memset(r1_bio, 0, size);
- else
+ r1_bio = kzalloc(size, gfp_flags);
+ if (!r1_bio)
unplug_slaves(pi->mddev);
return r1_bio;
}
/*
* Allocate RESYNC_PAGES data pages and attach them to
- * the first bio;
+ * the first bio.
+ * If this is a user-requested check/repair, allocate
+ * RESYNC_PAGES for each bio.
*/
- bio = r1_bio->bios[0];
- for (i = 0; i < RESYNC_PAGES; i++) {
- page = alloc_page(gfp_flags);
- if (unlikely(!page))
- goto out_free_pages;
-
- bio->bi_io_vec[i].bv_page = page;
+ if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
+ j = pi->raid_disks;
+ else
+ j = 1;
+ while(j--) {
+ bio = r1_bio->bios[j];
+ for (i = 0; i < RESYNC_PAGES; i++) {
+ page = alloc_page(gfp_flags);
+ if (unlikely(!page))
+ goto out_free_pages;
+
+ bio->bi_io_vec[i].bv_page = page;
+ }
+ }
+ /* If not user-requests, copy the page pointers to all bios */
+ if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
+ for (i=0; i<RESYNC_PAGES ; i++)
+ for (j=1; j<pi->raid_disks; j++)
+ r1_bio->bios[j]->bi_io_vec[i].bv_page =
+ r1_bio->bios[0]->bi_io_vec[i].bv_page;
}
r1_bio->master_bio = NULL;
return r1_bio;
out_free_pages:
- for ( ; i > 0 ; i--)
- __free_page(bio->bi_io_vec[i-1].bv_page);
+ for (i=0; i < RESYNC_PAGES ; i++)
+ for (j=0 ; j < pi->raid_disks; j++)
+ safe_put_page(r1_bio->bios[j]->bi_io_vec[i].bv_page);
+ j = -1;
out_free_bio:
while ( ++j < pi->raid_disks )
bio_put(r1_bio->bios[j]);
static void r1buf_pool_free(void *__r1_bio, void *data)
{
struct pool_info *pi = data;
- int i;
+ int i,j;
r1bio_t *r1bio = __r1_bio;
- struct bio *bio = r1bio->bios[0];
- for (i = 0; i < RESYNC_PAGES; i++) {
- __free_page(bio->bi_io_vec[i].bv_page);
- bio->bi_io_vec[i].bv_page = NULL;
- }
+ for (i = 0; i < RESYNC_PAGES; i++)
+ for (j = pi->raid_disks; j-- ;) {
+ if (j == 0 ||
+ r1bio->bios[j]->bi_io_vec[i].bv_page !=
+ r1bio->bios[0]->bi_io_vec[i].bv_page)
+ safe_put_page(r1bio->bios[j]->bi_io_vec[i].bv_page);
+ }
for (i=0 ; i < pi->raid_disks; i++)
bio_put(r1bio->bios[i]);
* user-side. So if something waits for IO, then it will
* wait for the 'master' bio.
*/
- set_bit(R1BIO_Uptodate, &r1_bio->state);
+ if (uptodate)
+ set_bit(R1BIO_Uptodate, &r1_bio->state);
raid_end_bio_io(r1_bio);
} else {
/* free extra copy of the data pages */
int i = bio->bi_vcnt;
while (i--)
- __free_page(bio->bi_io_vec[i].bv_page);
+ safe_put_page(bio->bi_io_vec[i].bv_page);
}
/* clear the bitmap if all writes complete successfully */
bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
/* cannot risk returning a device that failed
* before we inc'ed nr_pending
*/
- atomic_dec(&rdev->nr_pending);
+ rdev_dec_pending(rdev, conf->mddev);
goto retry;
}
conf->next_seq_sect = this_sector + sectors;
{
int i;
struct bio_vec *bvec;
- struct page **pages = kmalloc(bio->bi_vcnt * sizeof(struct page *),
+ struct page **pages = kzalloc(bio->bi_vcnt * sizeof(struct page *),
GFP_NOIO);
if (unlikely(!pages))
goto do_sync_io;
- memset(pages, 0, bio->bi_vcnt * sizeof(struct page *));
-
bio_for_each_segment(bvec, bio, i) {
pages[i] = alloc_page(GFP_NOIO);
if (unlikely(!pages[i]))
do_sync_io:
if (pages)
for (i = 0; i < bio->bi_vcnt && pages[i]; i++)
- __free_page(pages[i]);
+ put_page(pages[i]);
kfree(pages);
PRINTK("%dB behind alloc failed, doing sync I/O\n", bio->bi_size);
return NULL;
!test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
if (test_bit(Faulty, &rdev->flags)) {
- atomic_dec(&rdev->nr_pending);
+ rdev_dec_pending(rdev, mddev);
r1_bio->bios[i] = NULL;
} else
r1_bio->bios[i] = bio;
static int end_sync_read(struct bio *bio, unsigned int bytes_done, int error)
{
r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+ int i;
if (bio->bi_size)
return 1;
- if (r1_bio->bios[r1_bio->read_disk] != bio)
- BUG();
- update_head_pos(r1_bio->read_disk, r1_bio);
+ for (i=r1_bio->mddev->raid_disks; i--; )
+ if (r1_bio->bios[i] == bio)
+ break;
+ BUG_ON(i < 0);
+ update_head_pos(i, r1_bio);
/*
* we have read a block, now it needs to be re-written,
* or re-read if the read failed.
*/
if (test_bit(BIO_UPTODATE, &bio->bi_flags))
set_bit(R1BIO_Uptodate, &r1_bio->state);
- reschedule_retry(r1_bio);
+
+ if (atomic_dec_and_test(&r1_bio->remaining))
+ reschedule_retry(r1_bio);
return 0;
}
bio = r1_bio->bios[r1_bio->read_disk];
- /*
- * schedule writes
- */
+ if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+ /* We have read all readable devices. If we haven't
+ * got the block, then there is no hope left.
+ * If we have, then we want to do a comparison
+ * and skip the write if everything is the same.
+ * If any blocks failed to read, then we need to
+ * attempt an over-write
+ */
+ int primary;
+ if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
+ for (i=0; i<mddev->raid_disks; i++)
+ if (r1_bio->bios[i]->bi_end_io == end_sync_read)
+ md_error(mddev, conf->mirrors[i].rdev);
+
+ md_done_sync(mddev, r1_bio->sectors, 1);
+ put_buf(r1_bio);
+ return;
+ }
+ for (primary=0; primary<mddev->raid_disks; primary++)
+ if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
+ test_bit(BIO_UPTODATE, &r1_bio->bios[primary]->bi_flags)) {
+ r1_bio->bios[primary]->bi_end_io = NULL;
+ rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
+ break;
+ }
+ r1_bio->read_disk = primary;
+ for (i=0; i<mddev->raid_disks; i++)
+ if (r1_bio->bios[i]->bi_end_io == end_sync_read &&
+ test_bit(BIO_UPTODATE, &r1_bio->bios[i]->bi_flags)) {
+ int j;
+ int vcnt = r1_bio->sectors >> (PAGE_SHIFT- 9);
+ struct bio *pbio = r1_bio->bios[primary];
+ struct bio *sbio = r1_bio->bios[i];
+ for (j = vcnt; j-- ; )
+ if (memcmp(page_address(pbio->bi_io_vec[j].bv_page),
+ page_address(sbio->bi_io_vec[j].bv_page),
+ PAGE_SIZE))
+ break;
+ if (j >= 0)
+ mddev->resync_mismatches += r1_bio->sectors;
+ if (j < 0 || test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
+ sbio->bi_end_io = NULL;
+ rdev_dec_pending(conf->mirrors[i].rdev, mddev);
+ } else {
+ /* fixup the bio for reuse */
+ sbio->bi_vcnt = vcnt;
+ sbio->bi_size = r1_bio->sectors << 9;
+ sbio->bi_idx = 0;
+ sbio->bi_phys_segments = 0;
+ sbio->bi_hw_segments = 0;
+ sbio->bi_hw_front_size = 0;
+ sbio->bi_hw_back_size = 0;
+ sbio->bi_flags &= ~(BIO_POOL_MASK - 1);
+ sbio->bi_flags |= 1 << BIO_UPTODATE;
+ sbio->bi_next = NULL;
+ sbio->bi_sector = r1_bio->sector +
+ conf->mirrors[i].rdev->data_offset;
+ sbio->bi_bdev = conf->mirrors[i].rdev->bdev;
+ }
+ }
+ }
if (!test_bit(R1BIO_Uptodate, &r1_bio->state)) {
/* ouch - failed to read all of that.
* Try some synchronous reads of other devices to get
} while (!success && d != r1_bio->read_disk);
if (success) {
+ int start = d;
/* write it back and re-read */
set_bit(R1BIO_Uptodate, &r1_bio->state);
while (d != r1_bio->read_disk) {
if (r1_bio->bios[d]->bi_end_io != end_sync_read)
continue;
rdev = conf->mirrors[d].rdev;
+ atomic_add(s, &rdev->corrected_errors);
if (sync_page_io(rdev->bdev,
sect + rdev->data_offset,
s<<9,
bio->bi_io_vec[idx].bv_page,
- WRITE) == 0 ||
- sync_page_io(rdev->bdev,
+ WRITE) == 0)
+ md_error(mddev, rdev);
+ }
+ d = start;
+ while (d != r1_bio->read_disk) {
+ if (d == 0)
+ d = conf->raid_disks;
+ d--;
+ if (r1_bio->bios[d]->bi_end_io != end_sync_read)
+ continue;
+ rdev = conf->mirrors[d].rdev;
+ if (sync_page_io(rdev->bdev,
sect + rdev->data_offset,
s<<9,
bio->bi_io_vec[idx].bv_page,
- READ) == 0) {
+ READ) == 0)
md_error(mddev, rdev);
- }
}
} else {
char b[BDEVNAME_SIZE];
idx ++;
}
}
+
+ /*
+ * schedule writes
+ */
atomic_set(&r1_bio->remaining, 1);
for (i = 0; i < disks ; i++) {
wbio = r1_bio->bios[i];
if (success) {
/* write it back and re-read */
+ int start = d;
while (d != r1_bio->read_disk) {
if (d==0)
d = conf->raid_disks;
d--;
rdev = conf->mirrors[d].rdev;
+ atomic_add(s, &rdev->corrected_errors);
if (rdev &&
test_bit(In_sync, &rdev->flags)) {
if (sync_page_io(rdev->bdev,
sect + rdev->data_offset,
- s<<9, conf->tmppage, WRITE) == 0 ||
- sync_page_io(rdev->bdev,
+ s<<9, conf->tmppage, WRITE) == 0)
+ /* Well, this device is dead */
+ md_error(mddev, rdev);
+ }
+ }
+ d = start;
+ while (d != r1_bio->read_disk) {
+ if (d==0)
+ d = conf->raid_disks;
+ d--;
+ rdev = conf->mirrors[d].rdev;
+ if (rdev &&
+ test_bit(In_sync, &rdev->flags)) {
+ if (sync_page_io(rdev->bdev,
sect + rdev->data_offset,
- s<<9, conf->tmppage, READ) == 0) {
+ s<<9, conf->tmppage, READ) == 0)
/* Well, this device is dead */
md_error(mddev, rdev);
- }
}
}
} else {
for (i=0 ; i < conf->raid_disks; i++) {
bio = r1_bio->bios[i];
if (bio->bi_end_io) {
- page = r1_bio->bios[0]->bi_io_vec[bio->bi_vcnt].bv_page;
+ page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
if (bio_add_page(bio, page, len, 0) == 0) {
/* stop here */
- r1_bio->bios[0]->bi_io_vec[bio->bi_vcnt].bv_page = page;
+ bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
while (i > 0) {
i--;
bio = r1_bio->bios[i];
sync_blocks -= (len>>9);
} while (r1_bio->bios[disk]->bi_vcnt < RESYNC_PAGES);
bio_full:
- bio = r1_bio->bios[r1_bio->read_disk];
r1_bio->sectors = nr_sectors;
- md_sync_acct(conf->mirrors[r1_bio->read_disk].rdev->bdev, nr_sectors);
+ /* For a user-requested sync, we read all readable devices and do a
+ * compare
+ */
+ if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
+ atomic_set(&r1_bio->remaining, read_targets);
+ for (i=0; i<conf->raid_disks; i++) {
+ bio = r1_bio->bios[i];
+ if (bio->bi_end_io == end_sync_read) {
+ md_sync_acct(conf->mirrors[i].rdev->bdev, nr_sectors);
+ generic_make_request(bio);
+ }
+ }
+ } else {
+ atomic_set(&r1_bio->remaining, 1);
+ bio = r1_bio->bios[r1_bio->read_disk];
+ md_sync_acct(conf->mirrors[r1_bio->read_disk].rdev->bdev,
+ nr_sectors);
+ generic_make_request(bio);
- generic_make_request(bio);
+ }
return nr_sectors;
}
* bookkeeping area. [whatever we allocate in run(),
* should be freed in stop()]
*/
- conf = kmalloc(sizeof(conf_t), GFP_KERNEL);
+ conf = kzalloc(sizeof(conf_t), GFP_KERNEL);
mddev->private = conf;
if (!conf)
goto out_no_mem;
- memset(conf, 0, sizeof(*conf));
- conf->mirrors = kmalloc(sizeof(struct mirror_info)*mddev->raid_disks,
+ conf->mirrors = kzalloc(sizeof(struct mirror_info)*mddev->raid_disks,
GFP_KERNEL);
if (!conf->mirrors)
goto out_no_mem;
- memset(conf->mirrors, 0, sizeof(struct mirror_info)*mddev->raid_disks);
-
conf->tmppage = alloc_page(GFP_KERNEL);
if (!conf->tmppage)
goto out_no_mem;
if (conf->r1bio_pool)
mempool_destroy(conf->r1bio_pool);
kfree(conf->mirrors);
- __free_page(conf->tmppage);
+ safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
kfree(conf);
mddev->private = NULL;
kfree(newpoolinfo);
return -ENOMEM;
}
- newmirrors = kmalloc(sizeof(struct mirror_info) * raid_disks, GFP_KERNEL);
+ newmirrors = kzalloc(sizeof(struct mirror_info) * raid_disks, GFP_KERNEL);
if (!newmirrors) {
kfree(newpoolinfo);
mempool_destroy(newpool);
return -ENOMEM;
}
- memset(newmirrors, 0, sizeof(struct mirror_info)*raid_disks);
raise_barrier(conf);
}
-static mdk_personality_t raid1_personality =
+static struct mdk_personality raid1_personality =
{
.name = "raid1",
+ .level = 1,
.owner = THIS_MODULE,
.make_request = make_request,
.run = run,
static int __init raid_init(void)
{
- return register_md_personality(RAID1, &raid1_personality);
+ return register_md_personality(&raid1_personality);
}
static void raid_exit(void)
{
- unregister_md_personality(RAID1);
+ unregister_md_personality(&raid1_personality);
}
module_init(raid_init);
module_exit(raid_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS("md-personality-3"); /* RAID1 */
+MODULE_ALIAS("md-raid1");
+MODULE_ALIAS("md-level-1");
projects / linux-2.6-omap-h63xx.git / blobdiff