* miss any bits.
*/
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/highmem.h>
-#include <linux/bitops.h>
+#include <linux/blkdev.h>
#include <linux/kthread.h>
-#include <asm/atomic.h>
-#include "raid6.h"
-
-#include <linux/raid/bitmap.h>
#include <linux/async_tx.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "raid5.h"
+#include "raid6.h"
+#include "bitmap.h"
/*
* Stripe cache
const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
#endif
+/*
+ * We maintain a biased count of active stripes in the bottom 16 bits of
+ * bi_phys_segments, and a count of processed stripes in the upper 16 bits
+ */
+static inline int raid5_bi_phys_segments(struct bio *bio)
+{
+ return bio->bi_phys_segments & 0xffff;
+}
+
+static inline int raid5_bi_hw_segments(struct bio *bio)
+{
+ return (bio->bi_phys_segments >> 16) & 0xffff;
+}
+
+static inline int raid5_dec_bi_phys_segments(struct bio *bio)
+{
+ --bio->bi_phys_segments;
+ return raid5_bi_phys_segments(bio);
+}
+
+static inline int raid5_dec_bi_hw_segments(struct bio *bio)
+{
+ unsigned short val = raid5_bi_hw_segments(bio);
+
+ --val;
+ bio->bi_phys_segments = (val << 16) | raid5_bi_phys_segments(bio);
+ return val;
+}
+
+static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt)
+{
+ bio->bi_phys_segments = raid5_bi_phys_segments(bio) || (cnt << 16);
+}
+
+/* Find first data disk in a raid6 stripe */
+static inline int raid6_d0(struct stripe_head *sh)
+{
+ if (sh->ddf_layout)
+ /* ddf always start from first device */
+ return 0;
+ /* md starts just after Q block */
+ if (sh->qd_idx == sh->disks - 1)
+ return 0;
+ else
+ return sh->qd_idx + 1;
+}
static inline int raid6_next_disk(int disk, int raid_disks)
{
disk++;
return (disk < raid_disks) ? disk : 0;
}
+/* When walking through the disks in a raid5, starting at raid6_d0,
+ * We need to map each disk to a 'slot', where the data disks are slot
+ * 0 .. raid_disks-3, the parity disk is raid_disks-2 and the Q disk
+ * is raid_disks-1. This help does that mapping.
+ */
+static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
+ int *count, int syndrome_disks)
+{
+ int slot;
+
+ if (idx == sh->pd_idx)
+ return syndrome_disks;
+ if (idx == sh->qd_idx)
+ return syndrome_disks + 1;
+ slot = (*count)++;
+ return slot;
+}
+
static void return_io(struct bio *return_bi)
{
struct bio *bi = return_bi;
}
}
}
+
static void release_stripe(struct stripe_head *sh)
{
raid5_conf_t *conf = sh->raid_conf;
return 0;
}
-static void raid5_build_block (struct stripe_head *sh, int i);
+static void raid5_build_block(struct stripe_head *sh, int i);
+static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
+ struct stripe_head *sh);
-static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int disks)
+static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
{
raid5_conf_t *conf = sh->raid_conf;
int i;
remove_hash(sh);
+ sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks;
sh->sector = sector;
- sh->pd_idx = pd_idx;
+ stripe_set_idx(sector, conf, previous, sh);
sh->state = 0;
- sh->disks = disks;
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
static void unplug_slaves(mddev_t *mddev);
static void raid5_unplug_device(struct request_queue *q);
-static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector, int disks,
- int pd_idx, int noblock)
+static struct stripe_head *
+get_active_stripe(raid5_conf_t *conf, sector_t sector,
+ int previous, int noblock)
{
struct stripe_head *sh;
+ int disks = previous ? conf->previous_raid_disks : conf->raid_disks;
pr_debug("get_stripe, sector %llu\n", (unsigned long long)sector);
);
conf->inactive_blocked = 0;
} else
- init_stripe(sh, sector, pd_idx, disks);
+ init_stripe(sh, sector, previous);
} else {
if (atomic_read(&sh->count)) {
BUG_ON(!list_empty(&sh->lru));
while (rbi && rbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
rbi2 = r5_next_bio(rbi, dev->sector);
- if (--rbi->bi_phys_segments == 0) {
+ if (!raid5_dec_bi_phys_segments(rbi)) {
rbi->bi_next = return_bi;
return_bi = rbi;
}
struct kmem_cache *sc;
int devs = conf->raid_disks;
- sprintf(conf->cache_name[0], "raid5-%s", mdname(conf->mddev));
- sprintf(conf->cache_name[1], "raid5-%s-alt", mdname(conf->mddev));
+ sprintf(conf->cache_name[0],
+ "raid%d-%s", conf->level, mdname(conf->mddev));
+ sprintf(conf->cache_name[1],
+ "raid%d-%s-alt", conf->level, mdname(conf->mddev));
conf->active_name = 0;
sc = kmem_cache_create(conf->cache_name[conf->active_name],
sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
static void raid5_end_read_request(struct bio * bi, int error)
{
- struct stripe_head *sh = bi->bi_private;
+ struct stripe_head *sh = bi->bi_private;
raid5_conf_t *conf = sh->raid_conf;
int disks = sh->disks, i;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
release_stripe(sh);
}
-static void raid5_end_write_request (struct bio *bi, int error)
+static void raid5_end_write_request(struct bio *bi, int error)
{
- struct stripe_head *sh = bi->bi_private;
+ struct stripe_head *sh = bi->bi_private;
raid5_conf_t *conf = sh->raid_conf;
int disks = sh->disks, i;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
static sector_t compute_blocknr(struct stripe_head *sh, int i);
-static void raid5_build_block (struct stripe_head *sh, int i)
+static void raid5_build_block(struct stripe_head *sh, int i)
{
struct r5dev *dev = &sh->dev[i];
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
}
set_bit(Faulty, &rdev->flags);
- printk (KERN_ALERT
- "raid5: Disk failure on %s, disabling device.\n"
- "raid5: Operation continuing on %d devices.\n",
- bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
+ printk(KERN_ALERT
+ "raid5: Disk failure on %s, disabling device.\n"
+ "raid5: Operation continuing on %d devices.\n",
+ bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
}
}
* Input: a 'big' sector number,
* Output: index of the data and parity disk, and the sector # in them.
*/
-static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks,
- unsigned int data_disks, unsigned int * dd_idx,
- unsigned int * pd_idx, raid5_conf_t *conf)
+static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
+ int previous, int *dd_idx,
+ struct stripe_head *sh)
{
long stripe;
unsigned long chunk_number;
unsigned int chunk_offset;
+ int pd_idx, qd_idx;
+ int ddf_layout = 0;
sector_t new_sector;
int sectors_per_chunk = conf->chunk_size >> 9;
+ int raid_disks = previous ? conf->previous_raid_disks
+ : conf->raid_disks;
+ int data_disks = raid_disks - conf->max_degraded;
/* First compute the information on this sector */
/*
* Select the parity disk based on the user selected algorithm.
*/
+ pd_idx = qd_idx = ~0;
switch(conf->level) {
case 4:
- *pd_idx = data_disks;
+ pd_idx = data_disks;
break;
case 5:
switch (conf->algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
- *pd_idx = data_disks - stripe % raid_disks;
- if (*dd_idx >= *pd_idx)
+ pd_idx = data_disks - stripe % raid_disks;
+ if (*dd_idx >= pd_idx)
(*dd_idx)++;
break;
case ALGORITHM_RIGHT_ASYMMETRIC:
- *pd_idx = stripe % raid_disks;
- if (*dd_idx >= *pd_idx)
+ pd_idx = stripe % raid_disks;
+ if (*dd_idx >= pd_idx)
(*dd_idx)++;
break;
case ALGORITHM_LEFT_SYMMETRIC:
- *pd_idx = data_disks - stripe % raid_disks;
- *dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
+ pd_idx = data_disks - stripe % raid_disks;
+ *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
break;
case ALGORITHM_RIGHT_SYMMETRIC:
- *pd_idx = stripe % raid_disks;
- *dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
+ pd_idx = stripe % raid_disks;
+ *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
+ break;
+ case ALGORITHM_PARITY_0:
+ pd_idx = 0;
+ (*dd_idx)++;
+ break;
+ case ALGORITHM_PARITY_N:
+ pd_idx = data_disks;
break;
default:
printk(KERN_ERR "raid5: unsupported algorithm %d\n",
conf->algorithm);
+ BUG();
}
break;
case 6:
- /**** FIX THIS ****/
switch (conf->algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
- *pd_idx = raid_disks - 1 - (stripe % raid_disks);
- if (*pd_idx == raid_disks-1)
- (*dd_idx)++; /* Q D D D P */
- else if (*dd_idx >= *pd_idx)
+ pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ qd_idx = pd_idx + 1;
+ if (pd_idx == raid_disks-1) {
+ (*dd_idx)++; /* Q D D D P */
+ qd_idx = 0;
+ } else if (*dd_idx >= pd_idx)
(*dd_idx) += 2; /* D D P Q D */
break;
case ALGORITHM_RIGHT_ASYMMETRIC:
- *pd_idx = stripe % raid_disks;
- if (*pd_idx == raid_disks-1)
- (*dd_idx)++; /* Q D D D P */
- else if (*dd_idx >= *pd_idx)
+ pd_idx = stripe % raid_disks;
+ qd_idx = pd_idx + 1;
+ if (pd_idx == raid_disks-1) {
+ (*dd_idx)++; /* Q D D D P */
+ qd_idx = 0;
+ } else if (*dd_idx >= pd_idx)
(*dd_idx) += 2; /* D D P Q D */
break;
case ALGORITHM_LEFT_SYMMETRIC:
- *pd_idx = raid_disks - 1 - (stripe % raid_disks);
- *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
+ pd_idx = raid_disks - 1 - (stripe % 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;
- *dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
+ pd_idx = stripe % raid_disks;
+ qd_idx = (pd_idx + 1) % raid_disks;
+ *dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
+ break;
+
+ case ALGORITHM_PARITY_0:
+ pd_idx = 0;
+ qd_idx = 1;
+ (*dd_idx) += 2;
+ break;
+ case ALGORITHM_PARITY_N:
+ pd_idx = data_disks;
+ qd_idx = data_disks + 1;
+ break;
+
+ case ALGORITHM_ROTATING_ZERO_RESTART:
+ /* Exactly the same as RIGHT_ASYMMETRIC, but or
+ * of blocks for computing Q is different.
+ */
+ pd_idx = stripe % raid_disks;
+ qd_idx = pd_idx + 1;
+ if (pd_idx == raid_disks-1) {
+ (*dd_idx)++; /* Q D D D P */
+ qd_idx = 0;
+ } else if (*dd_idx >= pd_idx)
+ (*dd_idx) += 2; /* D D P Q D */
+ ddf_layout = 1;
+ break;
+
+ case ALGORITHM_ROTATING_N_RESTART:
+ /* Same a left_asymmetric, by first stripe is
+ * D D D P Q rather than
+ * Q D D D P
+ */
+ pd_idx = raid_disks - 1 - ((stripe + 1) % raid_disks);
+ qd_idx = pd_idx + 1;
+ if (pd_idx == raid_disks-1) {
+ (*dd_idx)++; /* Q D D D P */
+ qd_idx = 0;
+ } else if (*dd_idx >= pd_idx)
+ (*dd_idx) += 2; /* D D P Q D */
+ ddf_layout = 1;
+ break;
+
+ case ALGORITHM_ROTATING_N_CONTINUE:
+ /* Same as left_symmetric but Q is before P */
+ pd_idx = raid_disks - 1 - (stripe % raid_disks);
+ qd_idx = (pd_idx + raid_disks - 1) % raid_disks;
+ *dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
+ ddf_layout = 1;
+ break;
+
+ case ALGORITHM_LEFT_ASYMMETRIC_6:
+ /* RAID5 left_asymmetric, with Q on last device */
+ pd_idx = data_disks - stripe % (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);
+ 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);
+ *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);
+ *dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
+ qd_idx = raid_disks - 1;
break;
+
+ case ALGORITHM_PARITY_0_6:
+ pd_idx = 0;
+ (*dd_idx)++;
+ qd_idx = raid_disks - 1;
+ break;
+
+
default:
- printk (KERN_CRIT "raid6: unsupported algorithm %d\n",
- conf->algorithm);
+ printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
+ conf->algorithm);
+ BUG();
}
break;
}
+ if (sh) {
+ sh->pd_idx = pd_idx;
+ sh->qd_idx = qd_idx;
+ sh->ddf_layout = ddf_layout;
+ }
/*
* Finally, compute the new sector number
*/
int sectors_per_chunk = conf->chunk_size >> 9;
sector_t stripe;
int chunk_offset;
- int chunk_number, dummy1, dummy2, dd_idx = i;
+ int chunk_number, dummy1, dd_idx = i;
sector_t r_sector;
+ struct stripe_head sh2;
chunk_offset = sector_div(new_sector, sectors_per_chunk);
i += raid_disks;
i -= (sh->pd_idx + 1);
break;
+ case ALGORITHM_PARITY_0:
+ i -= 1;
+ break;
+ case ALGORITHM_PARITY_N:
+ break;
default:
printk(KERN_ERR "raid5: unsupported algorithm %d\n",
conf->algorithm);
+ BUG();
}
break;
case 6:
- if (i == raid6_next_disk(sh->pd_idx, raid_disks))
+ if (i == sh->qd_idx)
return 0; /* It is the Q disk */
switch (conf->algorithm) {
case ALGORITHM_LEFT_ASYMMETRIC:
case ALGORITHM_RIGHT_ASYMMETRIC:
- if (sh->pd_idx == raid_disks-1)
- i--; /* Q D D D P */
+ case ALGORITHM_ROTATING_ZERO_RESTART:
+ case ALGORITHM_ROTATING_N_RESTART:
+ if (sh->pd_idx == raid_disks-1)
+ i--; /* Q D D D P */
else if (i > sh->pd_idx)
i -= 2; /* D D P Q D */
break;
i -= (sh->pd_idx + 2);
}
break;
+ case ALGORITHM_PARITY_0:
+ i -= 2;
+ break;
+ case ALGORITHM_PARITY_N:
+ break;
+ case ALGORITHM_ROTATING_N_CONTINUE:
+ if (sh->pd_idx == 0)
+ i--; /* P D D D Q */
+ else if (i > sh->pd_idx)
+ i -= 2; /* D D Q P D */
+ break;
+ case ALGORITHM_LEFT_ASYMMETRIC_6:
+ case ALGORITHM_RIGHT_ASYMMETRIC_6:
+ if (i > sh->pd_idx)
+ i--;
+ break;
+ case ALGORITHM_LEFT_SYMMETRIC_6:
+ case ALGORITHM_RIGHT_SYMMETRIC_6:
+ if (i < sh->pd_idx)
+ i += data_disks + 1;
+ i -= (sh->pd_idx + 1);
+ break;
+ case ALGORITHM_PARITY_0_6:
+ i -= 1;
+ break;
default:
- printk (KERN_CRIT "raid6: unsupported algorithm %d\n",
- conf->algorithm);
+ printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
+ conf->algorithm);
+ BUG();
}
break;
}
chunk_number = stripe * data_disks + i;
r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset;
- check = raid5_compute_sector (r_sector, raid_disks, data_disks, &dummy1, &dummy2, conf);
- if (check != sh->sector || dummy1 != dd_idx || dummy2 != sh->pd_idx) {
+ check = raid5_compute_sector(conf, r_sector,
+ (raid_disks != conf->raid_disks),
+ &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");
return 0;
}
static void compute_parity6(struct stripe_head *sh, int method)
{
- raid6_conf_t *conf = sh->raid_conf;
- int i, pd_idx = sh->pd_idx, qd_idx, d0_idx, disks = sh->disks, count;
+ raid5_conf_t *conf = sh->raid_conf;
+ int i, pd_idx, qd_idx, d0_idx, disks = sh->disks, count;
+ int syndrome_disks = sh->ddf_layout ? disks : (disks - 2);
struct bio *chosen;
/**** FIX THIS: This could be very bad if disks is close to 256 ****/
- void *ptrs[disks];
+ void *ptrs[syndrome_disks+2];
- qd_idx = raid6_next_disk(pd_idx, disks);
- d0_idx = raid6_next_disk(qd_idx, disks);
+ pd_idx = sh->pd_idx;
+ qd_idx = sh->qd_idx;
+ d0_idx = raid6_d0(sh);
pr_debug("compute_parity, stripe %llu, method %d\n",
(unsigned long long)sh->sector, method);
set_bit(R5_UPTODATE, &sh->dev[i].flags);
}
-// switch(method) {
-// case RECONSTRUCT_WRITE:
-// case CHECK_PARITY:
-// case UPDATE_PARITY:
- /* Note that unlike RAID-5, the ordering of the disks matters greatly. */
- /* FIX: Is this ordering of drives even remotely optimal? */
- count = 0;
- i = d0_idx;
- do {
- ptrs[count++] = page_address(sh->dev[i].page);
- if (count <= disks-2 && !test_bit(R5_UPTODATE, &sh->dev[i].flags))
- printk("block %d/%d not uptodate on parity calc\n", i,count);
- i = raid6_next_disk(i, disks);
- } while ( i != d0_idx );
-// break;
-// }
-
- raid6_call.gen_syndrome(disks, STRIPE_SIZE, ptrs);
+ /* Note that unlike RAID-5, the ordering of the disks matters greatly.*/
+
+ for (i = 0; i < disks; i++)
+ ptrs[i] = (void *)raid6_empty_zero_page;
+
+ count = 0;
+ i = d0_idx;
+ do {
+ int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
+
+ ptrs[slot] = page_address(sh->dev[i].page);
+ if (slot < syndrome_disks &&
+ !test_bit(R5_UPTODATE, &sh->dev[i].flags)) {
+ printk(KERN_ERR "block %d/%d not uptodate "
+ "on parity calc\n", i, count);
+ BUG();
+ }
+
+ i = raid6_next_disk(i, disks);
+ } while (i != d0_idx);
+ BUG_ON(count != syndrome_disks);
+
+ raid6_call.gen_syndrome(syndrome_disks+2, STRIPE_SIZE, ptrs);
switch(method) {
case RECONSTRUCT_WRITE:
{
int i, count, disks = sh->disks;
void *ptr[MAX_XOR_BLOCKS], *dest, *p;
- int pd_idx = sh->pd_idx;
- int qd_idx = raid6_next_disk(pd_idx, disks);
+ int qd_idx = sh->qd_idx;
pr_debug("compute_block_1, stripe %llu, idx %d\n",
(unsigned long long)sh->sector, dd_idx);
static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
{
int i, count, disks = sh->disks;
- int pd_idx = sh->pd_idx;
- int qd_idx = raid6_next_disk(pd_idx, disks);
- int d0_idx = raid6_next_disk(qd_idx, disks);
- int faila, failb;
+ int syndrome_disks = sh->ddf_layout ? disks : disks-2;
+ int d0_idx = raid6_d0(sh);
+ int faila = -1, failb = -1;
+ /**** FIX THIS: This could be very bad if disks is close to 256 ****/
+ void *ptrs[syndrome_disks+2];
+
+ for (i = 0; i < disks ; i++)
+ ptrs[i] = (void *)raid6_empty_zero_page;
+ count = 0;
+ i = d0_idx;
+ do {
+ int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
- /* faila and failb are disk numbers relative to d0_idx */
- /* pd_idx become disks-2 and qd_idx become disks-1 */
- faila = (dd_idx1 < d0_idx) ? dd_idx1+(disks-d0_idx) : dd_idx1-d0_idx;
- failb = (dd_idx2 < d0_idx) ? dd_idx2+(disks-d0_idx) : dd_idx2-d0_idx;
+ ptrs[slot] = page_address(sh->dev[i].page);
+
+ if (i == dd_idx1)
+ faila = slot;
+ if (i == dd_idx2)
+ failb = slot;
+ i = raid6_next_disk(i, disks);
+ } while (i != d0_idx);
+ BUG_ON(count != syndrome_disks);
BUG_ON(faila == failb);
if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; }
pr_debug("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n",
- (unsigned long long)sh->sector, dd_idx1, dd_idx2, faila, failb);
+ (unsigned long long)sh->sector, dd_idx1, dd_idx2,
+ faila, failb);
- if ( failb == disks-1 ) {
+ if (failb == syndrome_disks+1) {
/* Q disk is one of the missing disks */
- if ( faila == disks-2 ) {
+ if (faila == syndrome_disks) {
/* Missing P+Q, just recompute */
compute_parity6(sh, UPDATE_PARITY);
return;
} else {
/* We're missing D+Q; recompute D from P */
- compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1, 0);
+ compute_block_1(sh, ((dd_idx1 == sh->qd_idx) ?
+ dd_idx2 : dd_idx1),
+ 0);
compute_parity6(sh, UPDATE_PARITY); /* Is this necessary? */
return;
}
}
- /* We're missing D+P or D+D; build pointer table */
- {
- /**** FIX THIS: This could be very bad if disks is close to 256 ****/
- void *ptrs[disks];
-
- count = 0;
- i = d0_idx;
- do {
- ptrs[count++] = page_address(sh->dev[i].page);
- i = raid6_next_disk(i, disks);
- if (i != dd_idx1 && i != dd_idx2 &&
- !test_bit(R5_UPTODATE, &sh->dev[i].flags))
- printk("compute_2 with missing block %d/%d\n", count, i);
- } while ( i != d0_idx );
-
- if ( failb == disks-2 ) {
- /* We're missing D+P. */
- raid6_datap_recov(disks, STRIPE_SIZE, faila, ptrs);
- } else {
- /* We're missing D+D. */
- raid6_2data_recov(disks, STRIPE_SIZE, faila, failb, ptrs);
- }
-
- /* Both the above update both missing blocks */
- set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
- set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
+ /* We're missing D+P or D+D; */
+ if (failb == syndrome_disks) {
+ /* We're missing D+P. */
+ raid6_datap_recov(syndrome_disks+2, STRIPE_SIZE, faila, ptrs);
+ } else {
+ /* We're missing D+D. */
+ raid6_2data_recov(syndrome_disks+2, STRIPE_SIZE, faila, failb,
+ ptrs);
}
+
+ /* Both the above update both missing blocks */
+ set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
+ set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
}
static void
if (*bip)
bi->bi_next = *bip;
*bip = bi;
- bi->bi_phys_segments ++;
+ bi->bi_phys_segments++;
spin_unlock_irq(&conf->device_lock);
spin_unlock(&sh->lock);
memcmp(a, a+4, STRIPE_SIZE-4)==0);
}
-static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks)
+static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
+ struct stripe_head *sh)
{
int sectors_per_chunk = conf->chunk_size >> 9;
- int pd_idx, dd_idx;
+ int dd_idx;
int chunk_offset = sector_div(stripe, sectors_per_chunk);
+ int disks = previous ? conf->previous_raid_disks : conf->raid_disks;
- raid5_compute_sector(stripe * (disks - conf->max_degraded)
+ raid5_compute_sector(conf,
+ stripe * (disks - conf->max_degraded)
*sectors_per_chunk + chunk_offset,
- disks, disks - conf->max_degraded,
- &dd_idx, &pd_idx, conf);
- return pd_idx;
+ previous,
+ &dd_idx, sh);
}
static void
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *nextbi = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- if (--bi->bi_phys_segments == 0) {
+ if (!raid5_dec_bi_phys_segments(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
*return_bi = bi;
sh->dev[i].sector + STRIPE_SECTORS) {
struct bio *bi2 = r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- if (--bi->bi_phys_segments == 0) {
+ if (!raid5_dec_bi_phys_segments(bi)) {
md_write_end(conf->mddev);
bi->bi_next = *return_bi;
*return_bi = bi;
struct bio *nextbi =
r5_next_bio(bi, sh->dev[i].sector);
clear_bit(BIO_UPTODATE, &bi->bi_flags);
- if (--bi->bi_phys_segments == 0) {
+ if (!raid5_dec_bi_phys_segments(bi)) {
bi->bi_next = *return_bi;
*return_bi = bi;
}
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
wbi2 = r5_next_bio(wbi, dev->sector);
- if (--wbi->bi_phys_segments == 0) {
+ if (!raid5_dec_bi_phys_segments(wbi)) {
md_write_end(conf->mddev);
wbi->bi_next = *return_bi;
*return_bi = wbi;
clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
for (i = 0; i < sh->disks; i++)
if (i != sh->pd_idx && (!r6s || i != r6s->qd_idx)) {
- int dd_idx, pd_idx, j;
+ int dd_idx, j;
struct stripe_head *sh2;
sector_t bn = compute_blocknr(sh, i);
- sector_t s = raid5_compute_sector(bn, conf->raid_disks,
- conf->raid_disks -
- conf->max_degraded, &dd_idx,
- &pd_idx, conf);
- sh2 = get_active_stripe(conf, s, conf->raid_disks,
- pd_idx, 1);
+ sector_t s = raid5_compute_sector(conf, bn, 0,
+ &dd_idx, NULL);
+ sh2 = get_active_stripe(conf, s, 0, 1);
if (sh2 == NULL)
/* so far only the early blocks of this stripe
* have been requested. When later blocks
set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
for (j = 0; j < conf->raid_disks; j++)
if (j != sh2->pd_idx &&
- (!r6s || j != raid6_next_disk(sh2->pd_idx,
- sh2->disks)) &&
+ (!r6s || j != sh2->qd_idx) &&
!test_bit(R5_Expanded, &sh2->dev[j].flags))
break;
if (j == conf->raid_disks) {
*
*/
-static void handle_stripe5(struct stripe_head *sh)
+static bool handle_stripe5(struct stripe_head *sh)
{
raid5_conf_t *conf = sh->raid_conf;
int disks = sh->disks, i;
if (dev->written)
s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ if (blocked_rdev == NULL &&
+ rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
blocked_rdev = rdev;
atomic_inc(&rdev->nr_pending);
- break;
}
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
rcu_read_unlock();
if (unlikely(blocked_rdev)) {
- set_bit(STRIPE_HANDLE, &sh->state);
- goto unlock;
+ if (s.syncing || s.expanding || s.expanded ||
+ s.to_write || s.written) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
+ }
+ /* There is nothing for the blocked_rdev to block */
+ rdev_dec_pending(blocked_rdev, conf->mddev);
+ blocked_rdev = NULL;
}
if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
!sh->reconstruct_state) {
/* Need to write out all blocks after computing parity */
sh->disks = conf->raid_disks;
- sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
- conf->raid_disks);
+ stripe_set_idx(sh->sector, conf, 0, sh);
schedule_reconstruction5(sh, &s, 1, 1);
} else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
clear_bit(STRIPE_EXPAND_READY, &sh->state);
ops_run_io(sh, &s);
return_io(return_bi);
+
+ return blocked_rdev == NULL;
}
-static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
+static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
{
- raid6_conf_t *conf = sh->raid_conf;
+ raid5_conf_t *conf = sh->raid_conf;
int disks = sh->disks;
struct bio *return_bi = NULL;
int i, pd_idx = sh->pd_idx;
struct r5dev *dev, *pdev, *qdev;
mdk_rdev_t *blocked_rdev = NULL;
- r6s.qd_idx = raid6_next_disk(pd_idx, disks);
+ r6s.qd_idx = sh->qd_idx;
pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
"pd_idx=%d, qd_idx=%d\n",
(unsigned long long)sh->sector, sh->state,
copy_data(0, rbi, dev->page, dev->sector);
rbi2 = r5_next_bio(rbi, dev->sector);
spin_lock_irq(&conf->device_lock);
- if (--rbi->bi_phys_segments == 0) {
+ if (!raid5_dec_bi_phys_segments(rbi)) {
rbi->bi_next = return_bi;
return_bi = rbi;
}
if (dev->written)
s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ if (blocked_rdev == NULL &&
+ rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
blocked_rdev = rdev;
atomic_inc(&rdev->nr_pending);
- break;
}
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
rcu_read_unlock();
if (unlikely(blocked_rdev)) {
- set_bit(STRIPE_HANDLE, &sh->state);
- goto unlock;
+ if (s.syncing || s.expanding || s.expanded ||
+ s.to_write || s.written) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
+ }
+ /* There is nothing for the blocked_rdev to block */
+ rdev_dec_pending(blocked_rdev, conf->mddev);
+ blocked_rdev = NULL;
}
+
pr_debug("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d,%d\n",
s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
/* Need to write out all blocks after computing P&Q */
sh->disks = conf->raid_disks;
- sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
- conf->raid_disks);
+ stripe_set_idx(sh->sector, conf, 0, sh);
compute_parity6(sh, RECONSTRUCT_WRITE);
for (i = conf->raid_disks ; i-- ; ) {
set_bit(R5_LOCKED, &sh->dev[i].flags);
ops_run_io(sh, &s);
return_io(return_bi);
+
+ return blocked_rdev == NULL;
}
-static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
+/* returns true if the stripe was handled */
+static bool handle_stripe(struct stripe_head *sh, struct page *tmp_page)
{
if (sh->raid_conf->level == 6)
- handle_stripe6(sh, tmp_page);
+ return handle_stripe6(sh, tmp_page);
else
- handle_stripe5(sh);
+ return handle_stripe5(sh);
}
/* We want read requests to align with chunks where possible,
* but write requests don't need to.
*/
-static int raid5_mergeable_bvec(struct request_queue *q, struct bio *bio, struct bio_vec *biovec)
+static int raid5_mergeable_bvec(struct request_queue *q,
+ struct bvec_merge_data *bvm,
+ struct bio_vec *biovec)
{
mddev_t *mddev = q->queuedata;
- sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
+ sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max;
unsigned int chunk_sectors = mddev->chunk_size >> 9;
- unsigned int bio_sectors = bio->bi_size >> 9;
+ unsigned int bio_sectors = bvm->bi_size >> 9;
- if (bio_data_dir(bio) == WRITE)
+ if ((bvm->bi_rw & 1) == WRITE)
return biovec->bv_len; /* always allow writes to be mergeable */
max = (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
if(bi) {
conf->retry_read_aligned_list = bi->bi_next;
bi->bi_next = NULL;
+ /*
+ * this sets the active strip count to 1 and the processed
+ * strip count to zero (upper 8 bits)
+ */
bi->bi_phys_segments = 1; /* biased count of active stripes */
- bi->bi_hw_segments = 0; /* count of processed stripes */
}
return bi;
if ((bi->bi_size>>9) > q->max_sectors)
return 0;
blk_recount_segments(q, bi);
- if (bi->bi_phys_segments > q->max_phys_segments ||
- bi->bi_hw_segments > q->max_hw_segments)
+ if (bi->bi_phys_segments > q->max_phys_segments)
return 0;
if (q->merge_bvec_fn)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev_to_conf(mddev);
- const unsigned int raid_disks = conf->raid_disks;
- const unsigned int data_disks = raid_disks - conf->max_degraded;
- unsigned int dd_idx, pd_idx;
+ unsigned int dd_idx;
struct bio* align_bi;
mdk_rdev_t *rdev;
return 0;
}
/*
- * use bio_clone to make a copy of the bio
+ * use bio_clone to make a copy of the bio
*/
align_bi = bio_clone(raid_bio, GFP_NOIO);
if (!align_bi)
/*
* compute position
*/
- align_bi->bi_sector = raid5_compute_sector(raid_bio->bi_sector,
- raid_disks,
- data_disks,
- &dd_idx,
- &pd_idx,
- conf);
+ align_bi->bi_sector = raid5_compute_sector(conf, raid_bio->bi_sector,
+ 0,
+ &dd_idx, NULL);
rcu_read_lock();
rdev = rcu_dereference(conf->disks[dd_idx].rdev);
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev_to_conf(mddev);
- unsigned int dd_idx, pd_idx;
+ 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 remaining;
+ int cpu, remaining;
if (unlikely(bio_barrier(bi))) {
bio_endio(bi, -EOPNOTSUPP);
md_write_start(mddev, bi);
- disk_stat_inc(mddev->gendisk, ios[rw]);
- disk_stat_add(mddev->gendisk, sectors[rw], bio_sectors(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))
- return 0;
+ return 0;
logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
last_sector = bi->bi_sector + (bi->bi_size>>9);
for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
DEFINE_WAIT(w);
int disks, data_disks;
+ int previous;
retry:
+ previous = 0;
prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
if (likely(conf->expand_progress == MaxSector))
disks = conf->raid_disks;
*/
spin_lock_irq(&conf->device_lock);
disks = conf->raid_disks;
- if (logical_sector >= conf->expand_progress)
+ if (logical_sector >= conf->expand_progress) {
disks = conf->previous_raid_disks;
- else {
+ previous = 1;
+ } else {
if (logical_sector >= conf->expand_lo) {
spin_unlock_irq(&conf->device_lock);
schedule();
}
data_disks = disks - conf->max_degraded;
- new_sector = raid5_compute_sector(logical_sector, disks, data_disks,
- &dd_idx, &pd_idx, conf);
+ new_sector = raid5_compute_sector(conf, logical_sector,
+ previous,
+ &dd_idx, NULL);
pr_debug("raid5: make_request, sector %llu logical %llu\n",
(unsigned long long)new_sector,
(unsigned long long)logical_sector);
- sh = get_active_stripe(conf, new_sector, disks, pd_idx, (bi->bi_rw&RWA_MASK));
+ sh = get_active_stripe(conf, new_sector, previous,
+ (bi->bi_rw&RWA_MASK));
if (sh) {
if (unlikely(conf->expand_progress != MaxSector)) {
/* expansion might have moved on while waiting for a
}
spin_lock_irq(&conf->device_lock);
- remaining = --bi->bi_phys_segments;
+ remaining = raid5_dec_bi_phys_segments(bi);
spin_unlock_irq(&conf->device_lock);
if (remaining == 0) {
*/
raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
struct stripe_head *sh;
- int pd_idx;
sector_t first_sector, last_sector;
int raid_disks = conf->previous_raid_disks;
int data_disks = raid_disks - conf->max_degraded;
for (i=0; i < conf->chunk_size/512; i+= STRIPE_SECTORS) {
int j;
int skipped = 0;
- pd_idx = stripe_to_pdidx(sector_nr+i, conf, conf->raid_disks);
- sh = get_active_stripe(conf, sector_nr+i,
- conf->raid_disks, pd_idx, 0);
+ sh = get_active_stripe(conf, sector_nr+i, 0, 0);
set_bit(STRIPE_EXPANDING, &sh->state);
atomic_inc(&conf->reshape_stripes);
/* If any of this stripe is beyond the end of the old
if (j == sh->pd_idx)
continue;
if (conf->level == 6 &&
- j == raid6_next_disk(sh->pd_idx, sh->disks))
+ j == sh->qd_idx)
continue;
s = compute_blocknr(sh, j);
if (s < mddev->array_sectors) {
* block on the destination stripes.
*/
first_sector =
- raid5_compute_sector(sector_nr*(new_data_disks),
- raid_disks, data_disks,
- &dd_idx, &pd_idx, conf);
+ raid5_compute_sector(conf, sector_nr*(new_data_disks),
+ 1, &dd_idx, NULL);
last_sector =
- raid5_compute_sector((sector_nr+conf->chunk_size/512)
- *(new_data_disks) -1,
- raid_disks, data_disks,
- &dd_idx, &pd_idx, conf);
- if (last_sector >= (mddev->size<<1))
- last_sector = (mddev->size<<1)-1;
+ raid5_compute_sector(conf, ((sector_nr+conf->chunk_size/512)
+ *(new_data_disks) - 1),
+ 1, &dd_idx, NULL);
+ if (last_sector >= mddev->dev_sectors)
+ last_sector = mddev->dev_sectors - 1;
while (first_sector <= last_sector) {
- pd_idx = stripe_to_pdidx(first_sector, conf,
- conf->previous_raid_disks);
- sh = get_active_stripe(conf, first_sector,
- conf->previous_raid_disks, pd_idx, 0);
+ sh = get_active_stripe(conf, first_sector, 1, 0);
set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
{
raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
struct stripe_head *sh;
- int pd_idx;
- int raid_disks = conf->raid_disks;
- sector_t max_sector = mddev->size << 1;
+ sector_t max_sector = mddev->dev_sectors;
int sync_blocks;
int still_degraded = 0;
int i;
*/
if (mddev->degraded >= conf->max_degraded &&
test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
- sector_t rv = (mddev->size << 1) - sector_nr;
+ sector_t rv = mddev->dev_sectors - sector_nr;
*skipped = 1;
return rv;
}
bitmap_cond_end_sync(mddev->bitmap, sector_nr);
- pd_idx = stripe_to_pdidx(sector_nr, conf, raid_disks);
- sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 1);
+ sh = get_active_stripe(conf, sector_nr, 0, 1);
if (sh == NULL) {
- sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 0);
+ sh = get_active_stripe(conf, sector_nr, 0, 0);
/* make sure we don't swamp the stripe cache if someone else
* is trying to get access
*/
clear_bit(STRIPE_INSYNC, &sh->state);
spin_unlock(&sh->lock);
- handle_stripe(sh, NULL);
+ /* wait for any blocked device to be handled */
+ while(unlikely(!handle_stripe(sh, NULL)))
+ ;
release_stripe(sh);
return STRIPE_SECTORS;
* it will be only one 'dd_idx' and only need one call to raid5_compute_sector.
*/
struct stripe_head *sh;
- int dd_idx, pd_idx;
+ int dd_idx;
sector_t sector, logical_sector, last_sector;
int scnt = 0;
int remaining;
int handled = 0;
logical_sector = raid_bio->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
- sector = raid5_compute_sector( logical_sector,
- conf->raid_disks,
- conf->raid_disks - conf->max_degraded,
- &dd_idx,
- &pd_idx,
- conf);
+ sector = raid5_compute_sector(conf, logical_sector,
+ 0, &dd_idx, NULL);
last_sector = raid_bio->bi_sector + (raid_bio->bi_size>>9);
for (; logical_sector < last_sector;
sector += STRIPE_SECTORS,
scnt++) {
- if (scnt < raid_bio->bi_hw_segments)
+ if (scnt < raid5_bi_hw_segments(raid_bio))
/* already done this stripe */
continue;
- sh = get_active_stripe(conf, sector, conf->raid_disks, pd_idx, 1);
+ sh = get_active_stripe(conf, sector, 0, 1);
if (!sh) {
/* failed to get a stripe - must wait */
- raid_bio->bi_hw_segments = scnt;
+ raid5_set_bi_hw_segments(raid_bio, scnt);
conf->retry_read_aligned = raid_bio;
return handled;
}
set_bit(R5_ReadError, &sh->dev[dd_idx].flags);
if (!add_stripe_bio(sh, raid_bio, dd_idx, 0)) {
release_stripe(sh);
- raid_bio->bi_hw_segments = scnt;
+ raid5_set_bi_hw_segments(raid_bio, scnt);
conf->retry_read_aligned = raid_bio;
return handled;
}
handled++;
}
spin_lock_irq(&conf->device_lock);
- remaining = --raid_bio->bi_phys_segments;
+ remaining = raid5_dec_bi_phys_segments(raid_bio);
spin_unlock_irq(&conf->device_lock);
if (remaining == 0)
bio_endio(raid_bio, 0);
.attrs = raid5_attrs,
};
-static int run(mddev_t *mddev)
+static raid5_conf_t *setup_conf(mddev_t *mddev)
{
raid5_conf_t *conf;
int raid_disk, memory;
mdk_rdev_t *rdev;
struct disk_info *disk;
- struct list_head *tmp;
- int working_disks = 0;
- if (mddev->level != 5 && mddev->level != 4 && mddev->level != 6) {
+ 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",
- mdname(mddev), mddev->level);
- return -EIO;
+ mdname(mddev), mddev->new_level);
+ return ERR_PTR(-EIO);
}
-
- if (mddev->reshape_position != MaxSector) {
- /* Check that we can continue the reshape.
- * Currently only disks can change, it must
- * increase, and we must be past the point where
- * a stripe over-writes itself
- */
- sector_t here_new, here_old;
- int old_disks;
- int max_degraded = (mddev->level == 5 ? 1 : 2);
-
- if (mddev->new_level != mddev->level ||
- mddev->new_layout != mddev->layout ||
- mddev->new_chunk != mddev->chunk_size) {
- printk(KERN_ERR "raid5: %s: unsupported reshape "
- "required - aborting.\n",
- mdname(mddev));
- return -EINVAL;
- }
- if (mddev->delta_disks <= 0) {
- printk(KERN_ERR "raid5: %s: unsupported reshape "
- "(reduce disks) required - aborting.\n",
- mdname(mddev));
- return -EINVAL;
- }
- old_disks = mddev->raid_disks - mddev->delta_disks;
- /* reshape_position must be on a new-stripe boundary, and one
- * further up in new geometry must map after here in old
- * geometry.
- */
- here_new = mddev->reshape_position;
- if (sector_div(here_new, (mddev->chunk_size>>9)*
- (mddev->raid_disks - max_degraded))) {
- printk(KERN_ERR "raid5: reshape_position not "
- "on a stripe boundary\n");
- return -EINVAL;
- }
- /* here_new is the stripe we will write to */
- here_old = mddev->reshape_position;
- sector_div(here_old, (mddev->chunk_size>>9)*
- (old_disks-max_degraded));
- /* here_old is the first stripe that we might need to read
- * from */
- if (here_new >= here_old) {
- /* Reading from the same stripe as writing to - bad */
- printk(KERN_ERR "raid5: reshape_position too early for "
- "auto-recovery - aborting.\n");
- return -EINVAL;
- }
- printk(KERN_INFO "raid5: reshape will continue\n");
- /* OK, we should be able to continue; */
+ if ((mddev->new_level == 5
+ && !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",
+ 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",
+ mdname(mddev), mddev->raid_disks);
+ return ERR_PTR(-EINVAL);
}
+ if (!mddev->new_chunk || mddev->new_chunk % PAGE_SIZE) {
+ printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
+ mddev->new_chunk, mdname(mddev));
+ return ERR_PTR(-EINVAL);
+ }
- mddev->private = kzalloc(sizeof (raid5_conf_t), GFP_KERNEL);
- if ((conf = mddev->private) == NULL)
+ conf = kzalloc(sizeof(raid5_conf_t), GFP_KERNEL);
+ if (conf == NULL)
goto abort;
- if (mddev->reshape_position == MaxSector) {
- conf->previous_raid_disks = conf->raid_disks = mddev->raid_disks;
- } else {
- conf->raid_disks = mddev->raid_disks;
+
+ conf->raid_disks = mddev->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;
- }
conf->disks = kzalloc(conf->raid_disks * sizeof(struct disk_info),
GFP_KERNEL);
if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
goto abort;
- if (mddev->level == 6) {
+ if (mddev->new_level == 6) {
conf->spare_page = alloc_page(GFP_KERNEL);
if (!conf->spare_page)
goto abort;
}
spin_lock_init(&conf->device_lock);
- mddev->queue->queue_lock = &conf->device_lock;
init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
INIT_LIST_HEAD(&conf->handle_list);
pr_debug("raid5: run(%s) called.\n", mdname(mddev));
- rdev_for_each(rdev, tmp, mddev) {
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
raid_disk = rdev->raid_disk;
if (raid_disk >= conf->raid_disks
|| raid_disk < 0)
printk(KERN_INFO "raid5: device %s operational as raid"
" disk %d\n", bdevname(rdev->bdev,b),
raid_disk);
- working_disks++;
} else
/* Cannot rely on bitmap to complete recovery */
conf->fullsync = 1;
}
- /*
- * 0 for a fully functional array, 1 or 2 for a degraded array.
- */
- mddev->degraded = conf->raid_disks - working_disks;
- conf->mddev = mddev;
- conf->chunk_size = mddev->chunk_size;
- conf->level = mddev->level;
+ conf->chunk_size = mddev->new_chunk;
+ conf->level = mddev->new_level;
if (conf->level == 6)
conf->max_degraded = 2;
else
conf->max_degraded = 1;
- conf->algorithm = mddev->layout;
+ conf->algorithm = mddev->new_layout;
conf->max_nr_stripes = NR_STRIPES;
conf->expand_progress = mddev->reshape_position;
- /* 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->level == 6 && conf->raid_disks < 4) {
- printk(KERN_ERR "raid6: not enough configured devices for %s (%d, minimum 4)\n",
- mdname(mddev), conf->raid_disks);
+ memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
+ conf->raid_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);
goto abort;
- }
- if (!conf->chunk_size || conf->chunk_size % 4) {
- printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
- conf->chunk_size, mdname(mddev));
+ } else
+ printk(KERN_INFO "raid5: allocated %dkB for %s\n",
+ memory, mdname(mddev));
+
+ conf->thread = md_register_thread(raid5d, mddev, "%s_raid5");
+ if (!conf->thread) {
+ printk(KERN_ERR
+ "raid5: couldn't allocate thread for %s\n",
+ mdname(mddev));
goto abort;
}
- if (conf->algorithm > ALGORITHM_RIGHT_SYMMETRIC) {
- printk(KERN_ERR
- "raid5: unsupported parity algorithm %d for %s\n",
- conf->algorithm, mdname(mddev));
- goto abort;
+
+ return conf;
+
+ abort:
+ if (conf) {
+ shrink_stripes(conf);
+ safe_put_page(conf->spare_page);
+ kfree(conf->disks);
+ kfree(conf->stripe_hashtbl);
+ kfree(conf);
+ return ERR_PTR(-EIO);
+ } else
+ return ERR_PTR(-ENOMEM);
+}
+
+static int run(mddev_t *mddev)
+{
+ raid5_conf_t *conf;
+ int working_disks = 0;
+ mdk_rdev_t *rdev;
+
+ if (mddev->reshape_position != MaxSector) {
+ /* Check that we can continue the reshape.
+ * Currently only disks can change, it must
+ * increase, and we must be past the point where
+ * a stripe over-writes itself
+ */
+ sector_t here_new, here_old;
+ int old_disks;
+ int max_degraded = (mddev->level == 5 ? 1 : 2);
+
+ if (mddev->new_level != mddev->level ||
+ mddev->new_layout != mddev->layout ||
+ mddev->new_chunk != mddev->chunk_size) {
+ printk(KERN_ERR "raid5: %s: unsupported reshape "
+ "required - aborting.\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ if (mddev->delta_disks <= 0) {
+ printk(KERN_ERR "raid5: %s: unsupported reshape "
+ "(reduce disks) required - aborting.\n",
+ mdname(mddev));
+ return -EINVAL;
+ }
+ old_disks = mddev->raid_disks - mddev->delta_disks;
+ /* reshape_position must be on a new-stripe boundary, and one
+ * further up in new geometry must map after here in old
+ * geometry.
+ */
+ here_new = mddev->reshape_position;
+ if (sector_div(here_new, (mddev->chunk_size>>9)*
+ (mddev->raid_disks - max_degraded))) {
+ printk(KERN_ERR "raid5: reshape_position not "
+ "on a stripe boundary\n");
+ return -EINVAL;
+ }
+ /* here_new is the stripe we will write to */
+ here_old = mddev->reshape_position;
+ sector_div(here_old, (mddev->chunk_size>>9)*
+ (old_disks-max_degraded));
+ /* here_old is the first stripe that we might need to read
+ * from */
+ if (here_new >= here_old) {
+ /* Reading from the same stripe as writing to - bad */
+ printk(KERN_ERR "raid5: reshape_position too early for "
+ "auto-recovery - aborting.\n");
+ return -EINVAL;
+ }
+ printk(KERN_INFO "raid5: reshape will continue\n");
+ /* OK, we should be able to continue; */
+ } else {
+ BUG_ON(mddev->level != mddev->new_level);
+ BUG_ON(mddev->layout != mddev->new_layout);
+ BUG_ON(mddev->chunk_size != mddev->new_chunk);
+ BUG_ON(mddev->delta_disks != 0);
}
+
+ if (mddev->private == NULL)
+ conf = setup_conf(mddev);
+ else
+ conf = mddev->private;
+
+ if (IS_ERR(conf))
+ return PTR_ERR(conf);
+
+ mddev->thread = conf->thread;
+ conf->thread = NULL;
+ mddev->private = conf;
+
+ /*
+ * 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))
+ working_disks++;
+
+ mddev->degraded = conf->raid_disks - working_disks;
+
if (mddev->degraded > conf->max_degraded) {
printk(KERN_ERR "raid5: not enough operational devices for %s"
" (%d/%d failed)\n",
goto abort;
}
+ /* device size must be a multiple of chunk size */
+ mddev->dev_sectors &= ~(mddev->chunk_size / 512 - 1);
+ mddev->resync_max_sectors = mddev->dev_sectors;
+
if (mddev->degraded > 0 &&
mddev->recovery_cp != MaxSector) {
if (mddev->ok_start_degraded)
}
}
- {
- mddev->thread = md_register_thread(raid5d, mddev, "%s_raid5");
- if (!mddev->thread) {
- printk(KERN_ERR
- "raid5: couldn't allocate thread for %s\n",
- mdname(mddev));
- goto abort;
- }
- }
- memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
- conf->raid_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);
- shrink_stripes(conf);
- md_unregister_thread(mddev->thread);
- goto abort;
- } else
- printk(KERN_INFO "raid5: allocated %dkB for %s\n",
- memory, mdname(mddev));
-
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),
"raid5: failed to create sysfs attributes for %s\n",
mdname(mddev));
+ mddev->queue->queue_lock = &conf->device_lock;
+
mddev->queue->unplug_fn = raid5_unplug_device;
mddev->queue->backing_dev_info.congested_data = mddev;
mddev->queue->backing_dev_info.congested_fn = raid5_congested;
- mddev->array_sectors = 2 * mddev->size * (conf->previous_raid_disks -
- conf->max_degraded);
+ mddev->array_sectors = mddev->dev_sectors *
+ (conf->previous_raid_disks - conf->max_degraded);
blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
return 0;
abort:
+ md_unregister_thread(mddev->thread);
+ mddev->thread = NULL;
if (conf) {
+ shrink_stripes(conf);
print_raid5_conf(conf);
safe_put_page(conf->spare_page);
kfree(conf->disks);
}
#ifdef DEBUG
-static void print_sh (struct seq_file *seq, struct stripe_head *sh)
+static void print_sh(struct seq_file *seq, struct stripe_head *sh)
{
int i;
seq_printf(seq, "\n");
}
-static void printall (struct seq_file *seq, raid5_conf_t *conf)
+static void printall(struct seq_file *seq, raid5_conf_t *conf)
{
struct stripe_head *sh;
struct hlist_node *hn;
}
#endif
-static void status (struct seq_file *seq, mddev_t *mddev)
+static void status(struct seq_file *seq, mddev_t *mddev)
{
raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
int i;
- conf->max_degraded);
set_capacity(mddev->gendisk, mddev->array_sectors);
mddev->changed = 1;
- if (sectors/2 > mddev->size && mddev->recovery_cp == MaxSector) {
- mddev->recovery_cp = mddev->size << 1;
+ if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) {
+ mddev->recovery_cp = mddev->dev_sectors;
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
}
- mddev->size = sectors /2;
+ mddev->dev_sectors = sectors;
mddev->resync_max_sectors = sectors;
return 0;
}
return -EINVAL; /* Cannot shrink array or change level yet */
if (mddev->delta_disks == 0)
return 0; /* nothing to do */
+ if (mddev->bitmap)
+ /* Cannot grow a bitmap yet */
+ return -EBUSY;
/* Can only proceed if there are plenty of stripe_heads.
* We need a minimum of one full stripe,, and for sensible progress
{
raid5_conf_t *conf = mddev_to_conf(mddev);
mdk_rdev_t *rdev;
- struct list_head *rtmp;
int spares = 0;
int added_devices = 0;
unsigned long flags;
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return -EBUSY;
- rdev_for_each(rdev, rtmp, mddev)
+ list_for_each_entry(rdev, &mddev->disks, same_set)
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags))
spares++;
/* Add some new drives, as many as will fit.
* We know there are enough to make the newly sized array work.
*/
- rdev_for_each(rdev, rtmp, mddev)
+ list_for_each_entry(rdev, &mddev->disks, same_set)
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags)) {
if (raid5_add_disk(mddev, rdev) == 0) {
struct block_device *bdev;
if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
- conf->mddev->array_sectors = 2 * conf->mddev->size *
+ conf->mddev->array_sectors = conf->mddev->dev_sectors *
(conf->raid_disks - conf->max_degraded);
set_capacity(conf->mddev->gendisk, conf->mddev->array_sectors);
conf->mddev->changed = 1;
}
}
+
+static void *raid5_takeover_raid1(mddev_t *mddev)
+{
+ int chunksect;
+
+ if (mddev->raid_disks != 2 ||
+ mddev->degraded > 1)
+ return ERR_PTR(-EINVAL);
+
+ /* Should check if there are write-behind devices? */
+
+ chunksect = 64*2; /* 64K by default */
+
+ /* The array must be an exact multiple of chunksize */
+ while (chunksect && (mddev->array_sectors & (chunksect-1)))
+ chunksect >>= 1;
+
+ if ((chunksect<<9) < STRIPE_SIZE)
+ /* array size does not allow a suitable chunk size */
+ return ERR_PTR(-EINVAL);
+
+ mddev->new_level = 5;
+ mddev->new_layout = ALGORITHM_LEFT_SYMMETRIC;
+ mddev->new_chunk = chunksect << 9;
+
+ return setup_conf(mddev);
+}
+
+
+static void *raid5_takeover(mddev_t *mddev)
+{
+ /* raid5 can take over:
+ * raid0 - if all devices are the same - 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
+ *
+ * For now, just do raid1
+ */
+
+ if (mddev->level == 1)
+ return raid5_takeover_raid1(mddev);
+
+ return ERR_PTR(-EINVAL);
+}
+
+
+static struct mdk_personality raid5_personality;
+
+static void *raid6_takeover(mddev_t *mddev)
+{
+ /* Currently can only take over a raid5. We map the
+ * personality to an equivalent raid6 personality
+ * with the Q block at the end.
+ */
+ int new_layout;
+
+ if (mddev->pers != &raid5_personality)
+ return ERR_PTR(-EINVAL);
+ if (mddev->degraded > 1)
+ return ERR_PTR(-EINVAL);
+ if (mddev->raid_disks > 253)
+ return ERR_PTR(-EINVAL);
+ if (mddev->raid_disks < 3)
+ return ERR_PTR(-EINVAL);
+
+ switch (mddev->layout) {
+ case ALGORITHM_LEFT_ASYMMETRIC:
+ new_layout = ALGORITHM_LEFT_ASYMMETRIC_6;
+ break;
+ case ALGORITHM_RIGHT_ASYMMETRIC:
+ new_layout = ALGORITHM_RIGHT_ASYMMETRIC_6;
+ break;
+ case ALGORITHM_LEFT_SYMMETRIC:
+ new_layout = ALGORITHM_LEFT_SYMMETRIC_6;
+ break;
+ case ALGORITHM_RIGHT_SYMMETRIC:
+ new_layout = ALGORITHM_RIGHT_SYMMETRIC_6;
+ break;
+ case ALGORITHM_PARITY_0:
+ new_layout = ALGORITHM_PARITY_0_6;
+ break;
+ case ALGORITHM_PARITY_N:
+ new_layout = ALGORITHM_PARITY_N;
+ break;
+ default:
+ return ERR_PTR(-EINVAL);
+ }
+ mddev->new_level = 6;
+ mddev->new_layout = new_layout;
+ mddev->delta_disks = 1;
+ mddev->raid_disks += 1;
+ return setup_conf(mddev);
+}
+
+
static struct mdk_personality raid6_personality =
{
.name = "raid6",
.start_reshape = raid5_start_reshape,
#endif
.quiesce = raid5_quiesce,
+ .takeover = raid6_takeover,
};
static struct mdk_personality raid5_personality =
{
.start_reshape = raid5_start_reshape,
#endif
.quiesce = raid5_quiesce,
+ .takeover = raid5_takeover,
};
static struct mdk_personality raid4_personality =
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff