* 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
#define STRIPE_SHIFT (PAGE_SHIFT - 9)
#define STRIPE_SECTORS (STRIPE_SIZE>>9)
#define IO_THRESHOLD 1
+#define BYPASS_THRESHOLD 1
#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
#define __inline__
#endif
+#define printk_rl(args...) ((void) (printk_ratelimit() && printk(args)))
+
#if !RAID6_USE_EMPTY_ZERO_PAGE
/* In .bss so it's zeroed */
const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
#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;
while (bi) {
- int bytes = bi->bi_size;
return_bi = bi->bi_next;
bi->bi_next = NULL;
bi->bi_size = 0;
- bi->bi_end_io(bi, bytes,
- test_bit(BIO_UPTODATE, &bi->bi_flags)
- ? 0 : -EIO);
+ bio_endio(bi, 0);
bi = return_bi;
}
}
static void print_raid5_conf (raid5_conf_t *conf);
+static int stripe_operations_active(struct stripe_head *sh)
+{
+ return sh->check_state || sh->reconstruct_state ||
+ test_bit(STRIPE_BIOFILL_RUN, &sh->state) ||
+ test_bit(STRIPE_COMPUTE_RUN, &sh->state);
+}
+
static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
{
if (atomic_dec_and_test(&sh->count)) {
}
md_wakeup_thread(conf->mddev->thread);
} else {
- BUG_ON(sh->ops.pending);
+ BUG_ON(stripe_operations_active(sh));
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
atomic_dec(&conf->preread_active_stripes);
if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD)
}
}
}
+
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;
BUG_ON(atomic_read(&sh->count) != 0);
BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
- BUG_ON(sh->ops.pending || sh->ops.ack || sh->ops.complete);
+ BUG_ON(stripe_operations_active(sh));
CHECK_DEVLOCK();
pr_debug("init_stripe called, stripe %llu\n",
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(request_queue_t *q);
+static void raid5_unplug_device(struct request_queue *q);
-static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector, int disks,
- int pd_idx, int noblock)
+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));
return sh;
}
-/* test_and_ack_op() ensures that we only dequeue an operation once */
-#define test_and_ack_op(op, pend) \
-do { \
- if (test_bit(op, &sh->ops.pending) && \
- !test_bit(op, &sh->ops.complete)) { \
- if (test_and_set_bit(op, &sh->ops.ack)) \
- clear_bit(op, &pend); \
- else \
- ack++; \
- } else \
- clear_bit(op, &pend); \
-} while (0)
-
-/* find new work to run, do not resubmit work that is already
- * in flight
- */
-static unsigned long get_stripe_work(struct stripe_head *sh)
-{
- unsigned long pending;
- int ack = 0;
-
- pending = sh->ops.pending;
-
- test_and_ack_op(STRIPE_OP_BIOFILL, pending);
- test_and_ack_op(STRIPE_OP_COMPUTE_BLK, pending);
- test_and_ack_op(STRIPE_OP_PREXOR, pending);
- test_and_ack_op(STRIPE_OP_BIODRAIN, pending);
- test_and_ack_op(STRIPE_OP_POSTXOR, pending);
- test_and_ack_op(STRIPE_OP_CHECK, pending);
- if (test_and_clear_bit(STRIPE_OP_IO, &sh->ops.pending))
- ack++;
-
- sh->ops.count -= ack;
- BUG_ON(sh->ops.count < 0);
-
- return pending;
-}
-
-static int
-raid5_end_read_request(struct bio *bi, unsigned int bytes_done, int error);
-static int
-raid5_end_write_request (struct bio *bi, unsigned int bytes_done, int error);
+static void
+raid5_end_read_request(struct bio *bi, int error);
+static void
+raid5_end_write_request(struct bio *bi, int error);
-static void ops_run_io(struct stripe_head *sh)
+static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s)
{
raid5_conf_t *conf = sh->raid_conf;
int i, disks = sh->disks;
rcu_read_unlock();
if (rdev) {
- if (test_bit(STRIPE_SYNCING, &sh->state) ||
- test_bit(STRIPE_EXPAND_SOURCE, &sh->state) ||
- test_bit(STRIPE_EXPAND_READY, &sh->state))
+ if (s->syncing || s->expanding || s->expanded)
md_sync_acct(rdev->bdev, STRIPE_SECTORS);
+ set_bit(STRIPE_IO_STARTED, &sh->state);
+
bi->bi_bdev = rdev->bdev;
pr_debug("%s: for %llu schedule op %ld on disc %d\n",
- __FUNCTION__, (unsigned long long)sh->sector,
+ __func__, (unsigned long long)sh->sector,
bi->bi_rw, i);
atomic_inc(&sh->count);
bi->bi_sector = sh->sector + rdev->data_offset;
if (frombio)
tx = async_memcpy(page, bio_page, page_offset,
b_offset, clen,
- ASYNC_TX_DEP_ACK | ASYNC_TX_KMAP_SRC,
+ ASYNC_TX_DEP_ACK,
tx, NULL, NULL);
else
tx = async_memcpy(bio_page, page, b_offset,
page_offset, clen,
- ASYNC_TX_DEP_ACK | ASYNC_TX_KMAP_DST,
+ ASYNC_TX_DEP_ACK,
tx, NULL, NULL);
}
if (clen < len) /* hit end of page */
struct stripe_head *sh = stripe_head_ref;
struct bio *return_bi = NULL;
raid5_conf_t *conf = sh->raid_conf;
- int i, more_to_read = 0;
+ int i;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
/* clear completed biofills */
+ spin_lock_irq(&conf->device_lock);
for (i = sh->disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
- /* check if this stripe has new incoming reads */
- if (dev->toread)
- more_to_read++;
/* acknowledge completion of a biofill operation */
- /* and check if we need to reply to a read request
- */
- if (test_bit(R5_Wantfill, &dev->flags) && !dev->toread) {
+ /* and check if we need to reply to a read request,
+ * new R5_Wantfill requests are held off until
+ * !STRIPE_BIOFILL_RUN
+ */
+ if (test_and_clear_bit(R5_Wantfill, &dev->flags)) {
struct bio *rbi, *rbi2;
- clear_bit(R5_Wantfill, &dev->flags);
- /* The access to dev->read is outside of the
- * spin_lock_irq(&conf->device_lock), but is protected
- * by the STRIPE_OP_BIOFILL pending bit
- */
BUG_ON(!dev->read);
rbi = dev->read;
dev->read = NULL;
while (rbi && rbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
rbi2 = r5_next_bio(rbi, dev->sector);
- 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;
}
- spin_unlock_irq(&conf->device_lock);
rbi = rbi2;
}
}
}
- clear_bit(STRIPE_OP_BIOFILL, &sh->ops.ack);
- clear_bit(STRIPE_OP_BIOFILL, &sh->ops.pending);
+ spin_unlock_irq(&conf->device_lock);
+ clear_bit(STRIPE_BIOFILL_RUN, &sh->state);
return_io(return_bi);
- if (more_to_read)
- set_bit(STRIPE_HANDLE, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
raid5_conf_t *conf = sh->raid_conf;
int i;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = sh->disks; i--; ) {
int target = sh->ops.target;
struct r5dev *tgt = &sh->dev[target];
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
set_bit(R5_UPTODATE, &tgt->flags);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
clear_bit(R5_Wantcompute, &tgt->flags);
- set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
+ clear_bit(STRIPE_COMPUTE_RUN, &sh->state);
+ if (sh->check_state == check_state_compute_run)
+ sh->check_state = check_state_compute_result;
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
-static struct dma_async_tx_descriptor *
-ops_run_compute5(struct stripe_head *sh, unsigned long pending)
+static struct dma_async_tx_descriptor *ops_run_compute5(struct stripe_head *sh)
{
/* kernel stack size limits the total number of disks */
int disks = sh->disks;
int i;
pr_debug("%s: stripe %llu block: %d\n",
- __FUNCTION__, (unsigned long long)sh->sector, target);
+ __func__, (unsigned long long)sh->sector, target);
BUG_ON(!test_bit(R5_Wantcompute, &tgt->flags));
for (i = disks; i--; )
ASYNC_TX_XOR_ZERO_DST, NULL,
ops_complete_compute5, sh);
- /* ack now if postxor is not set to be run */
- if (tx && !test_bit(STRIPE_OP_POSTXOR, &pending))
- async_tx_ack(tx);
-
return tx;
}
{
struct stripe_head *sh = stripe_head_ref;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
-
- set_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
}
static struct dma_async_tx_descriptor *
/* existing parity data subtracted */
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
/* Only process blocks that are known to be uptodate */
- if (dev->towrite && test_bit(R5_Wantprexor, &dev->flags))
+ if (test_bit(R5_Wantdrain, &dev->flags))
xor_srcs[count++] = dev->page;
}
ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
{
int disks = sh->disks;
- int pd_idx = sh->pd_idx, i;
-
- /* check if prexor is active which means only process blocks
- * that are part of a read-modify-write (Wantprexor)
- */
- int prexor = test_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
+ int i;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
struct bio *chosen;
- int towrite;
- towrite = 0;
- if (prexor) { /* rmw */
- if (dev->towrite &&
- test_bit(R5_Wantprexor, &dev->flags))
- towrite = 1;
- } else { /* rcw */
- if (i != pd_idx && dev->towrite &&
- test_bit(R5_LOCKED, &dev->flags))
- towrite = 1;
- }
-
- if (towrite) {
+ if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
struct bio *wbi;
spin_lock(&sh->lock);
static void ops_complete_postxor(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
-
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
- (unsigned long long)sh->sector);
-
- set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
- set_bit(STRIPE_HANDLE, &sh->state);
- release_stripe(sh);
-}
-
-static void ops_complete_write(void *stripe_head_ref)
-{
- struct stripe_head *sh = stripe_head_ref;
int disks = sh->disks, i, pd_idx = sh->pd_idx;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
set_bit(R5_UPTODATE, &dev->flags);
}
- set_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
- set_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
+ if (sh->reconstruct_state == reconstruct_state_drain_run)
+ sh->reconstruct_state = reconstruct_state_drain_result;
+ else if (sh->reconstruct_state == reconstruct_state_prexor_drain_run)
+ sh->reconstruct_state = reconstruct_state_prexor_drain_result;
+ else {
+ BUG_ON(sh->reconstruct_state != reconstruct_state_run);
+ sh->reconstruct_state = reconstruct_state_result;
+ }
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
int count = 0, pd_idx = sh->pd_idx, i;
struct page *xor_dest;
- int prexor = test_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
+ int prexor = 0;
unsigned long flags;
- dma_async_tx_callback callback;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
/* check if prexor is active which means only process blocks
* that are part of a read-modify-write (written)
*/
- if (prexor) {
+ if (sh->reconstruct_state == reconstruct_state_prexor_drain_run) {
+ prexor = 1;
xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
}
}
- /* check whether this postxor is part of a write */
- callback = test_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending) ?
- ops_complete_write : ops_complete_postxor;
-
/* 1/ if we prexor'd then the dest is reused as a source
* 2/ if we did not prexor then we are redoing the parity
* set ASYNC_TX_XOR_DROP_DST and ASYNC_TX_XOR_ZERO_DST
if (unlikely(count == 1)) {
flags &= ~(ASYNC_TX_XOR_DROP_DST | ASYNC_TX_XOR_ZERO_DST);
tx = async_memcpy(xor_dest, xor_srcs[0], 0, 0, STRIPE_SIZE,
- flags, tx, callback, sh);
+ flags, tx, ops_complete_postxor, sh);
} else
tx = async_xor(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
- flags, tx, callback, sh);
+ flags, tx, ops_complete_postxor, sh);
}
static void ops_complete_check(void *stripe_head_ref)
{
struct stripe_head *sh = stripe_head_ref;
- int pd_idx = sh->pd_idx;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
- if (test_and_clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending) &&
- sh->ops.zero_sum_result == 0)
- set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-
- set_bit(STRIPE_OP_CHECK, &sh->ops.complete);
+ sh->check_state = check_state_check_result;
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
int count = 0, pd_idx = sh->pd_idx, i;
struct page *xor_dest = xor_srcs[count++] = sh->dev[pd_idx].page;
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
tx = async_xor_zero_sum(xor_dest, xor_srcs, 0, count, STRIPE_SIZE,
&sh->ops.zero_sum_result, 0, NULL, NULL, NULL);
- if (tx)
- set_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
- else
- clear_bit(STRIPE_OP_MOD_DMA_CHECK, &sh->ops.pending);
-
atomic_inc(&sh->count);
tx = async_trigger_callback(ASYNC_TX_DEP_ACK | ASYNC_TX_ACK, tx,
ops_complete_check, sh);
}
-static void raid5_run_ops(struct stripe_head *sh, unsigned long pending)
+static void raid5_run_ops(struct stripe_head *sh, unsigned long ops_request)
{
int overlap_clear = 0, i, disks = sh->disks;
struct dma_async_tx_descriptor *tx = NULL;
- if (test_bit(STRIPE_OP_BIOFILL, &pending)) {
+ if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
ops_run_biofill(sh);
overlap_clear++;
}
- if (test_bit(STRIPE_OP_COMPUTE_BLK, &pending))
- tx = ops_run_compute5(sh, pending);
+ if (test_bit(STRIPE_OP_COMPUTE_BLK, &ops_request)) {
+ tx = ops_run_compute5(sh);
+ /* terminate the chain if postxor is not set to be run */
+ if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request))
+ async_tx_ack(tx);
+ }
- if (test_bit(STRIPE_OP_PREXOR, &pending))
+ if (test_bit(STRIPE_OP_PREXOR, &ops_request))
tx = ops_run_prexor(sh, tx);
- if (test_bit(STRIPE_OP_BIODRAIN, &pending)) {
+ if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
tx = ops_run_biodrain(sh, tx);
overlap_clear++;
}
- if (test_bit(STRIPE_OP_POSTXOR, &pending))
+ if (test_bit(STRIPE_OP_POSTXOR, &ops_request))
ops_run_postxor(sh, tx);
- if (test_bit(STRIPE_OP_CHECK, &pending))
+ if (test_bit(STRIPE_OP_CHECK, &ops_request))
ops_run_check(sh);
- if (test_bit(STRIPE_OP_IO, &pending))
- ops_run_io(sh);
-
if (overlap_clear)
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
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),
- 0, 0, NULL, NULL);
+ 0, 0, NULL);
if (!sc)
return 1;
conf->slab_cache = sc;
struct stripe_head *osh, *nsh;
LIST_HEAD(newstripes);
struct disk_info *ndisks;
- int err = 0;
+ int err;
struct kmem_cache *sc;
int i;
if (newsize <= conf->pool_size)
return 0; /* never bother to shrink */
- md_allow_write(conf->mddev);
+ err = md_allow_write(conf->mddev);
+ if (err)
+ return err;
/* Step 1 */
sc = kmem_cache_create(conf->cache_name[1-conf->active_name],
sizeof(struct stripe_head)+(newsize-1)*sizeof(struct r5dev),
- 0, 0, NULL, NULL);
+ 0, 0, NULL);
if (!sc)
return -ENOMEM;
conf->slab_cache = NULL;
}
-static int raid5_end_read_request(struct bio * bi, unsigned int bytes_done,
- int error)
+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);
char b[BDEVNAME_SIZE];
mdk_rdev_t *rdev;
- if (bi->bi_size)
- return 1;
for (i=0 ; i<disks; i++)
if (bi == &sh->dev[i].req)
uptodate);
if (i == disks) {
BUG();
- return 0;
+ return;
}
if (uptodate) {
set_bit(R5_UPTODATE, &sh->dev[i].flags);
if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
rdev = conf->disks[i].rdev;
- printk(KERN_INFO "raid5:%s: read error corrected (%lu sectors at %llu on %s)\n",
- mdname(conf->mddev), STRIPE_SECTORS,
- (unsigned long long)sh->sector + rdev->data_offset,
- bdevname(rdev->bdev, b));
+ printk_rl(KERN_INFO "raid5:%s: read error corrected"
+ " (%lu sectors at %llu on %s)\n",
+ mdname(conf->mddev), STRIPE_SECTORS,
+ (unsigned long long)(sh->sector
+ + rdev->data_offset),
+ bdevname(rdev->bdev, b));
clear_bit(R5_ReadError, &sh->dev[i].flags);
clear_bit(R5_ReWrite, &sh->dev[i].flags);
}
clear_bit(R5_UPTODATE, &sh->dev[i].flags);
atomic_inc(&rdev->read_errors);
if (conf->mddev->degraded)
- printk(KERN_WARNING "raid5:%s: read error not correctable (sector %llu on %s).\n",
- mdname(conf->mddev),
- (unsigned long long)sh->sector + rdev->data_offset,
- bdn);
+ printk_rl(KERN_WARNING
+ "raid5:%s: read error not correctable "
+ "(sector %llu on %s).\n",
+ mdname(conf->mddev),
+ (unsigned long long)(sh->sector
+ + rdev->data_offset),
+ bdn);
else if (test_bit(R5_ReWrite, &sh->dev[i].flags))
/* Oh, no!!! */
- printk(KERN_WARNING "raid5:%s: read error NOT corrected!! (sector %llu on %s).\n",
- mdname(conf->mddev),
- (unsigned long long)sh->sector + rdev->data_offset,
- bdn);
+ printk_rl(KERN_WARNING
+ "raid5:%s: read error NOT corrected!! "
+ "(sector %llu on %s).\n",
+ mdname(conf->mddev),
+ (unsigned long long)(sh->sector
+ + rdev->data_offset),
+ bdn);
else if (atomic_read(&rdev->read_errors)
> conf->max_nr_stripes)
printk(KERN_WARNING
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
- return 0;
}
-static int raid5_end_write_request (struct bio *bi, unsigned int bytes_done,
- int error)
+static void 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);
- if (bi->bi_size)
- return 1;
-
for (i=0 ; i<disks; i++)
if (bi == &sh->dev[i].req)
break;
uptodate);
if (i == disks) {
BUG();
- return 0;
+ return;
}
if (!uptodate)
clear_bit(R5_LOCKED, &sh->dev[i].flags);
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
- return 0;
}
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];
/*
* if recovery was running, make sure it aborts.
*/
- set_bit(MD_RECOVERY_ERR, &mddev->recovery);
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
}
set_bit(Faulty, &rdev->flags);
- printk (KERN_ALERT
- "raid5: Disk failure on %s, disabling device."
- " Operation continuing on %d devices\n",
- bdevname(rdev->bdev,b), conf->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;
}
} \
} while(0)
-
-static void compute_block(struct stripe_head *sh, int dd_idx)
-{
- int i, count, disks = sh->disks;
- void *ptr[MAX_XOR_BLOCKS], *dest, *p;
-
- pr_debug("compute_block, stripe %llu, idx %d\n",
- (unsigned long long)sh->sector, dd_idx);
-
- dest = page_address(sh->dev[dd_idx].page);
- memset(dest, 0, STRIPE_SIZE);
- count = 0;
- for (i = disks ; i--; ) {
- if (i == dd_idx)
- continue;
- p = page_address(sh->dev[i].page);
- if (test_bit(R5_UPTODATE, &sh->dev[i].flags))
- ptr[count++] = p;
- else
- printk(KERN_ERR "compute_block() %d, stripe %llu, %d"
- " not present\n", dd_idx,
- (unsigned long long)sh->sector, i);
-
- check_xor();
- }
- if (count)
- xor_blocks(count, STRIPE_SIZE, dest, ptr);
- set_bit(R5_UPTODATE, &sh->dev[dd_idx].flags);
-}
-
-static void compute_parity5(struct stripe_head *sh, int method)
-{
- raid5_conf_t *conf = sh->raid_conf;
- int i, pd_idx = sh->pd_idx, disks = sh->disks, count;
- void *ptr[MAX_XOR_BLOCKS], *dest;
- struct bio *chosen;
-
- pr_debug("compute_parity5, stripe %llu, method %d\n",
- (unsigned long long)sh->sector, method);
-
- count = 0;
- dest = page_address(sh->dev[pd_idx].page);
- switch(method) {
- case READ_MODIFY_WRITE:
- BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags));
- for (i=disks ; i-- ;) {
- if (i==pd_idx)
- continue;
- if (sh->dev[i].towrite &&
- test_bit(R5_UPTODATE, &sh->dev[i].flags)) {
- ptr[count++] = page_address(sh->dev[i].page);
- chosen = sh->dev[i].towrite;
- sh->dev[i].towrite = NULL;
-
- if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
- wake_up(&conf->wait_for_overlap);
-
- BUG_ON(sh->dev[i].written);
- sh->dev[i].written = chosen;
- check_xor();
- }
- }
- break;
- case RECONSTRUCT_WRITE:
- memset(dest, 0, STRIPE_SIZE);
- for (i= disks; i-- ;)
- if (i!=pd_idx && sh->dev[i].towrite) {
- chosen = sh->dev[i].towrite;
- sh->dev[i].towrite = NULL;
-
- if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
- wake_up(&conf->wait_for_overlap);
-
- BUG_ON(sh->dev[i].written);
- sh->dev[i].written = chosen;
- }
- break;
- case CHECK_PARITY:
- break;
- }
- if (count) {
- xor_blocks(count, STRIPE_SIZE, dest, ptr);
- count = 0;
- }
-
- for (i = disks; i--;)
- if (sh->dev[i].written) {
- sector_t sector = sh->dev[i].sector;
- struct bio *wbi = sh->dev[i].written;
- while (wbi && wbi->bi_sector < sector + STRIPE_SECTORS) {
- copy_data(1, wbi, sh->dev[i].page, sector);
- wbi = r5_next_bio(wbi, sector);
- }
-
- set_bit(R5_LOCKED, &sh->dev[i].flags);
- set_bit(R5_UPTODATE, &sh->dev[i].flags);
- }
-
- switch(method) {
- case RECONSTRUCT_WRITE:
- case CHECK_PARITY:
- for (i=disks; i--;)
- if (i != pd_idx) {
- ptr[count++] = page_address(sh->dev[i].page);
- check_xor();
- }
- break;
- case READ_MODIFY_WRITE:
- for (i = disks; i--;)
- if (sh->dev[i].written) {
- ptr[count++] = page_address(sh->dev[i].page);
- check_xor();
- }
- }
- if (count)
- xor_blocks(count, STRIPE_SIZE, dest, ptr);
-
- if (method != CHECK_PARITY) {
- set_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
- set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
- } else
- clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
-}
-
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];
+ /* 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);
+ }
- 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);
+}
- /* 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
+schedule_reconstruction5(struct stripe_head *sh, struct stripe_head_state *s,
+ int rcw, int expand)
+{
+ int i, pd_idx = sh->pd_idx, disks = sh->disks;
+
+ if (rcw) {
+ /* if we are not expanding this is a proper write request, and
+ * there will be bios with new data to be drained into the
+ * stripe cache
+ */
+ if (!expand) {
+ sh->reconstruct_state = reconstruct_state_drain_run;
+ set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+ } else
+ sh->reconstruct_state = reconstruct_state_run;
+
+ set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
+
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+
+ if (dev->towrite) {
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantdrain, &dev->flags);
+ if (!expand)
+ clear_bit(R5_UPTODATE, &dev->flags);
+ s->locked++;
+ }
+ }
+ if (s->locked + 1 == disks)
+ if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
+ atomic_inc(&sh->raid_conf->pending_full_writes);
+ } else {
+ BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
+ test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
+
+ sh->reconstruct_state = reconstruct_state_prexor_drain_run;
+ set_bit(STRIPE_OP_PREXOR, &s->ops_request);
+ set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+ set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
+
+ for (i = disks; i--; ) {
+ struct r5dev *dev = &sh->dev[i];
+ if (i == pd_idx)
+ continue;
+
+ if (dev->towrite &&
+ (test_bit(R5_UPTODATE, &dev->flags) ||
+ test_bit(R5_Wantcompute, &dev->flags))) {
+ set_bit(R5_Wantdrain, &dev->flags);
+ set_bit(R5_LOCKED, &dev->flags);
+ clear_bit(R5_UPTODATE, &dev->flags);
+ s->locked++;
+ }
+ }
}
-}
+ /* keep the parity disk locked while asynchronous operations
+ * are in flight
+ */
+ set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
+ clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
+ s->locked++;
+ pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
+ __func__, (unsigned long long)sh->sector,
+ s->locked, s->ops_request);
+}
/*
* Each stripe/dev can have one or more bion attached.
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
-handle_requests_to_failed_array(raid5_conf_t *conf, struct stripe_head *sh,
+handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh,
struct stripe_head_state *s, int disks,
struct bio **return_bi)
{
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;
bi = bi2;
}
- /* fail any reads if this device is non-operational */
- if (!test_bit(R5_Insync, &sh->dev[i].flags) ||
- test_bit(R5_ReadError, &sh->dev[i].flags)) {
+ /* fail any reads if this device is non-operational and
+ * the data has not reached the cache yet.
+ */
+ if (!test_bit(R5_Wantfill, &sh->dev[i].flags) &&
+ (!test_bit(R5_Insync, &sh->dev[i].flags) ||
+ test_bit(R5_ReadError, &sh->dev[i].flags))) {
bi = sh->dev[i].toread;
sh->dev[i].toread = NULL;
if (test_and_clear_bit(R5_Overlap, &sh->dev[i].flags))
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;
}
STRIPE_SECTORS, 0, 0);
}
+ if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
+ if (atomic_dec_and_test(&conf->pending_full_writes))
+ md_wakeup_thread(conf->mddev->thread);
}
-static void handle_issuing_new_read_requests5(struct stripe_head *sh,
- struct stripe_head_state *s, int disks)
+/* fetch_block5 - checks the given member device to see if its data needs
+ * to be read or computed to satisfy a request.
+ *
+ * Returns 1 when no more member devices need to be checked, otherwise returns
+ * 0 to tell the loop in handle_stripe_fill5 to continue
+ */
+static int fetch_block5(struct stripe_head *sh, struct stripe_head_state *s,
+ int disk_idx, int disks)
{
- int i;
- for (i = disks; i--; ) {
- struct r5dev *dev = &sh->dev[i];
- if (!test_bit(R5_LOCKED, &dev->flags) &&
- !test_bit(R5_UPTODATE, &dev->flags) &&
- (dev->toread ||
- (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
- s->syncing || s->expanding ||
- (s->failed && (sh->dev[s->failed_num].toread ||
- (sh->dev[s->failed_num].towrite &&
- !test_bit(R5_OVERWRITE, &sh->dev[s->failed_num].flags))
- )))) {
- /* we would like to get this block, possibly
- * by computing it, but we might not be able to
+ struct r5dev *dev = &sh->dev[disk_idx];
+ struct r5dev *failed_dev = &sh->dev[s->failed_num];
+
+ /* is the data in this block needed, and can we get it? */
+ if (!test_bit(R5_LOCKED, &dev->flags) &&
+ !test_bit(R5_UPTODATE, &dev->flags) &&
+ (dev->toread ||
+ (dev->towrite && !test_bit(R5_OVERWRITE, &dev->flags)) ||
+ s->syncing || s->expanding ||
+ (s->failed &&
+ (failed_dev->toread ||
+ (failed_dev->towrite &&
+ !test_bit(R5_OVERWRITE, &failed_dev->flags)))))) {
+ /* We would like to get this block, possibly by computing it,
+ * otherwise read it if the backing disk is insync
+ */
+ if ((s->uptodate == disks - 1) &&
+ (s->failed && disk_idx == s->failed_num)) {
+ set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+ set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+ set_bit(R5_Wantcompute, &dev->flags);
+ sh->ops.target = disk_idx;
+ s->req_compute = 1;
+ /* Careful: from this point on 'uptodate' is in the eye
+ * of raid5_run_ops which services 'compute' operations
+ * before writes. R5_Wantcompute flags a block that will
+ * be R5_UPTODATE by the time it is needed for a
+ * subsequent operation.
*/
- if (s->uptodate == disks-1) {
- pr_debug("Computing block %d\n", i);
- compute_block(sh, i);
- s->uptodate++;
- } else if (test_bit(R5_Insync, &dev->flags)) {
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantread, &dev->flags);
- s->locked++;
- pr_debug("Reading block %d (sync=%d)\n",
- i, s->syncing);
- }
+ s->uptodate++;
+ return 1; /* uptodate + compute == disks */
+ } else if (test_bit(R5_Insync, &dev->flags)) {
+ set_bit(R5_LOCKED, &dev->flags);
+ set_bit(R5_Wantread, &dev->flags);
+ s->locked++;
+ pr_debug("Reading block %d (sync=%d)\n", disk_idx,
+ s->syncing);
}
}
+
+ return 0;
+}
+
+/**
+ * handle_stripe_fill5 - read or compute data to satisfy pending requests.
+ */
+static void handle_stripe_fill5(struct stripe_head *sh,
+ struct stripe_head_state *s, int disks)
+{
+ int i;
+
+ /* look for blocks to read/compute, skip this if a compute
+ * is already in flight, or if the stripe contents are in the
+ * midst of changing due to a write
+ */
+ if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
+ !sh->reconstruct_state)
+ for (i = disks; i--; )
+ if (fetch_block5(sh, s, i, disks))
+ break;
set_bit(STRIPE_HANDLE, &sh->state);
}
-static void handle_issuing_new_read_requests6(struct stripe_head *sh,
+static void handle_stripe_fill6(struct stripe_head *sh,
struct stripe_head_state *s, struct r6_state *r6s,
int disks)
{
/* we would like to get this block, possibly
* by computing it, but we might not be able to
*/
- if (s->uptodate == disks-1) {
+ if ((s->uptodate == disks - 1) &&
+ (s->failed && (i == r6s->failed_num[0] ||
+ i == r6s->failed_num[1]))) {
pr_debug("Computing stripe %llu block %d\n",
(unsigned long long)sh->sector, i);
compute_block_1(sh, i, 0);
}
-/* handle_completed_write_requests
+/* handle_stripe_clean_event
* any written block on an uptodate or failed drive can be returned.
* Note that if we 'wrote' to a failed drive, it will be UPTODATE, but
* never LOCKED, so we don't need to test 'failed' directly.
*/
-static void handle_completed_write_requests(raid5_conf_t *conf,
+static void handle_stripe_clean_event(raid5_conf_t *conf,
struct stripe_head *sh, int disks, struct bio **return_bi)
{
int i;
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;
0);
}
}
+
+ if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
+ if (atomic_dec_and_test(&conf->pending_full_writes))
+ md_wakeup_thread(conf->mddev->thread);
}
-static void handle_issuing_new_write_requests5(raid5_conf_t *conf,
+static void handle_stripe_dirtying5(raid5_conf_t *conf,
struct stripe_head *sh, struct stripe_head_state *s, int disks)
{
int rmw = 0, rcw = 0, i;
struct r5dev *dev = &sh->dev[i];
if ((dev->towrite || i == sh->pd_idx) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !test_bit(R5_UPTODATE, &dev->flags)) {
+ !(test_bit(R5_UPTODATE, &dev->flags) ||
+ test_bit(R5_Wantcompute, &dev->flags))) {
if (test_bit(R5_Insync, &dev->flags))
rmw++;
else
/* Would I have to read this buffer for reconstruct_write */
if (!test_bit(R5_OVERWRITE, &dev->flags) && i != sh->pd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !test_bit(R5_UPTODATE, &dev->flags)) {
- if (test_bit(R5_Insync, &dev->flags))
- rcw++;
+ !(test_bit(R5_UPTODATE, &dev->flags) ||
+ test_bit(R5_Wantcompute, &dev->flags))) {
+ if (test_bit(R5_Insync, &dev->flags)) rcw++;
else
rcw += 2*disks;
}
struct r5dev *dev = &sh->dev[i];
if ((dev->towrite || i == sh->pd_idx) &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !test_bit(R5_UPTODATE, &dev->flags) &&
+ !(test_bit(R5_UPTODATE, &dev->flags) ||
+ test_bit(R5_Wantcompute, &dev->flags)) &&
test_bit(R5_Insync, &dev->flags)) {
if (
test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
if (!test_bit(R5_OVERWRITE, &dev->flags) &&
i != sh->pd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
- !test_bit(R5_UPTODATE, &dev->flags) &&
+ !(test_bit(R5_UPTODATE, &dev->flags) ||
+ test_bit(R5_Wantcompute, &dev->flags)) &&
test_bit(R5_Insync, &dev->flags)) {
if (
test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
/* now if nothing is locked, and if we have enough data,
* we can start a write request
*/
- if (s->locked == 0 && (rcw == 0 || rmw == 0) &&
- !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
- pr_debug("Computing parity...\n");
- compute_parity5(sh, rcw == 0 ?
- RECONSTRUCT_WRITE : READ_MODIFY_WRITE);
- /* now every locked buffer is ready to be written */
- for (i = disks; i--; )
- if (test_bit(R5_LOCKED, &sh->dev[i].flags)) {
- pr_debug("Writing block %d\n", i);
- s->locked++;
- set_bit(R5_Wantwrite, &sh->dev[i].flags);
- if (!test_bit(R5_Insync, &sh->dev[i].flags)
- || (i == sh->pd_idx && s->failed == 0))
- set_bit(STRIPE_INSYNC, &sh->state);
- }
- if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
- atomic_dec(&conf->preread_active_stripes);
- if (atomic_read(&conf->preread_active_stripes) <
- IO_THRESHOLD)
- md_wakeup_thread(conf->mddev->thread);
- }
- }
+ /* since handle_stripe can be called at any time we need to handle the
+ * case where a compute block operation has been submitted and then a
+ * subsequent call wants to start a write request. raid5_run_ops only
+ * handles the case where compute block and postxor are requested
+ * simultaneously. If this is not the case then new writes need to be
+ * held off until the compute completes.
+ */
+ if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
+ (s->locked == 0 && (rcw == 0 || rmw == 0) &&
+ !test_bit(STRIPE_BIT_DELAY, &sh->state)))
+ schedule_reconstruction5(sh, s, rcw == 0, 0);
}
-static void handle_issuing_new_write_requests6(raid5_conf_t *conf,
+static void handle_stripe_dirtying6(raid5_conf_t *conf,
struct stripe_head *sh, struct stripe_head_state *s,
struct r6_state *r6s, int disks)
{
s->locked++;
set_bit(R5_Wantwrite, &sh->dev[i].flags);
}
+ if (s->locked == disks)
+ if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
+ atomic_inc(&conf->pending_full_writes);
/* after a RECONSTRUCT_WRITE, the stripe MUST be in-sync */
set_bit(STRIPE_INSYNC, &sh->state);
static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
struct stripe_head_state *s, int disks)
{
+ struct r5dev *dev = NULL;
+
set_bit(STRIPE_HANDLE, &sh->state);
- if (s->failed == 0) {
+
+ switch (sh->check_state) {
+ case check_state_idle:
+ /* start a new check operation if there are no failures */
+ if (s->failed == 0) {
+ BUG_ON(s->uptodate != disks);
+ sh->check_state = check_state_run;
+ set_bit(STRIPE_OP_CHECK, &s->ops_request);
+ clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
+ s->uptodate--;
+ break;
+ }
+ dev = &sh->dev[s->failed_num];
+ /* fall through */
+ case check_state_compute_result:
+ sh->check_state = check_state_idle;
+ if (!dev)
+ dev = &sh->dev[sh->pd_idx];
+
+ /* check that a write has not made the stripe insync */
+ if (test_bit(STRIPE_INSYNC, &sh->state))
+ break;
+
+ /* either failed parity check, or recovery is happening */
+ BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
BUG_ON(s->uptodate != disks);
- compute_parity5(sh, CHECK_PARITY);
- s->uptodate--;
- if (page_is_zero(sh->dev[sh->pd_idx].page)) {
- /* parity is correct (on disc, not in buffer any more)
+
+ set_bit(R5_LOCKED, &dev->flags);
+ s->locked++;
+ set_bit(R5_Wantwrite, &dev->flags);
+
+ clear_bit(STRIPE_DEGRADED, &sh->state);
+ set_bit(STRIPE_INSYNC, &sh->state);
+ break;
+ case check_state_run:
+ break; /* we will be called again upon completion */
+ case check_state_check_result:
+ sh->check_state = check_state_idle;
+
+ /* if a failure occurred during the check operation, leave
+ * STRIPE_INSYNC not set and let the stripe be handled again
+ */
+ if (s->failed)
+ break;
+
+ /* handle a successful check operation, if parity is correct
+ * we are done. Otherwise update the mismatch count and repair
+ * parity if !MD_RECOVERY_CHECK
+ */
+ if (sh->ops.zero_sum_result == 0)
+ /* parity is correct (on disc,
+ * not in buffer any more)
*/
set_bit(STRIPE_INSYNC, &sh->state);
- } else {
+ else {
conf->mddev->resync_mismatches += STRIPE_SECTORS;
if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery))
/* don't try to repair!! */
set_bit(STRIPE_INSYNC, &sh->state);
else {
- compute_block(sh, sh->pd_idx);
+ sh->check_state = check_state_compute_run;
+ set_bit(STRIPE_COMPUTE_RUN, &sh->state);
+ set_bit(STRIPE_OP_COMPUTE_BLK, &s->ops_request);
+ set_bit(R5_Wantcompute,
+ &sh->dev[sh->pd_idx].flags);
+ sh->ops.target = sh->pd_idx;
s->uptodate++;
}
}
- }
- if (!test_bit(STRIPE_INSYNC, &sh->state)) {
- struct r5dev *dev;
- /* either failed parity check, or recovery is happening */
- if (s->failed == 0)
- s->failed_num = sh->pd_idx;
- dev = &sh->dev[s->failed_num];
- BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
- BUG_ON(s->uptodate != disks);
-
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantwrite, &dev->flags);
- clear_bit(STRIPE_DEGRADED, &sh->state);
- s->locked++;
- set_bit(STRIPE_INSYNC, &sh->state);
+ break;
+ case check_state_compute_run:
+ break;
+ default:
+ printk(KERN_ERR "%s: unknown check_state: %d sector: %llu\n",
+ __func__, sh->check_state,
+ (unsigned long long) sh->sector);
+ BUG();
}
}
/* We have read all the blocks in this stripe and now we need to
* copy some of them into a target stripe for expand.
*/
+ struct dma_async_tx_descriptor *tx = NULL;
clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
for (i = 0; i < sh->disks; i++)
- if (i != sh->pd_idx && (r6s && i != r6s->qd_idx)) {
- int dd_idx, pd_idx, j;
+ if (i != sh->pd_idx && (!r6s || i != r6s->qd_idx)) {
+ 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
release_stripe(sh2);
continue;
}
- memcpy(page_address(sh2->dev[dd_idx].page),
- page_address(sh->dev[i].page),
- STRIPE_SIZE);
+
+ /* place all the copies on one channel */
+ tx = async_memcpy(sh2->dev[dd_idx].page,
+ sh->dev[i].page, 0, 0, STRIPE_SIZE,
+ ASYNC_TX_DEP_ACK, tx, NULL, NULL);
+
set_bit(R5_Expanded, &sh2->dev[dd_idx].flags);
set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
for (j = 0; j < conf->raid_disks; j++)
if (j != sh2->pd_idx &&
- (r6s && j != r6s->qd_idx) &&
+ (!r6s || j != sh2->qd_idx) &&
!test_bit(R5_Expanded, &sh2->dev[j].flags))
break;
if (j == conf->raid_disks) {
set_bit(STRIPE_HANDLE, &sh2->state);
}
release_stripe(sh2);
+
}
+ /* done submitting copies, wait for them to complete */
+ if (tx) {
+ async_tx_ack(tx);
+ dma_wait_for_async_tx(tx);
+ }
}
+
/*
* handle_stripe - do things to a stripe.
*
*
*/
-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;
struct bio *return_bi = NULL;
struct stripe_head_state s;
struct r5dev *dev;
- unsigned long pending = 0;
+ mdk_rdev_t *blocked_rdev = NULL;
+ int prexor;
memset(&s, 0, sizeof(s));
- pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
- "ops=%lx:%lx:%lx\n", (unsigned long long)sh->sector, sh->state,
- atomic_read(&sh->count), sh->pd_idx,
- sh->ops.pending, sh->ops.ack, sh->ops.complete);
+ pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d check:%d "
+ "reconstruct:%d\n", (unsigned long long)sh->sector, sh->state,
+ atomic_read(&sh->count), sh->pd_idx, sh->check_state,
+ sh->reconstruct_state);
spin_lock(&sh->lock);
clear_bit(STRIPE_HANDLE, &sh->state);
s.syncing = test_bit(STRIPE_SYNCING, &sh->state);
s.expanding = test_bit(STRIPE_EXPAND_SOURCE, &sh->state);
s.expanded = test_bit(STRIPE_EXPAND_READY, &sh->state);
- /* Now to look around and see what can be done */
+ /* Now to look around and see what can be done */
rcu_read_lock();
for (i=disks; i--; ) {
mdk_rdev_t *rdev;
struct r5dev *dev = &sh->dev[i];
clear_bit(R5_Insync, &dev->flags);
- pr_debug("check %d: state 0x%lx read %p write %p written %p\n",
- i, dev->flags, dev->toread, dev->towrite, dev->written);
- /* maybe we can reply to a read */
- if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread) {
- struct bio *rbi, *rbi2;
- pr_debug("Return read for disc %d\n", i);
- spin_lock_irq(&conf->device_lock);
- rbi = dev->toread;
- dev->toread = NULL;
- if (test_and_clear_bit(R5_Overlap, &dev->flags))
- wake_up(&conf->wait_for_overlap);
- spin_unlock_irq(&conf->device_lock);
- while (rbi && rbi->bi_sector < dev->sector + STRIPE_SECTORS) {
- copy_data(0, rbi, dev->page, dev->sector);
- rbi2 = r5_next_bio(rbi, dev->sector);
- spin_lock_irq(&conf->device_lock);
- if (--rbi->bi_phys_segments == 0) {
- rbi->bi_next = return_bi;
- return_bi = rbi;
- }
- spin_unlock_irq(&conf->device_lock);
- rbi = rbi2;
- }
- }
+ pr_debug("check %d: state 0x%lx toread %p read %p write %p "
+ "written %p\n", i, dev->flags, dev->toread, dev->read,
+ dev->towrite, dev->written);
+
+ /* maybe we can request a biofill operation
+ *
+ * new wantfill requests are only permitted while
+ * ops_complete_biofill is guaranteed to be inactive
+ */
+ if (test_bit(R5_UPTODATE, &dev->flags) && dev->toread &&
+ !test_bit(STRIPE_BIOFILL_RUN, &sh->state))
+ set_bit(R5_Wantfill, &dev->flags);
/* now count some things */
if (test_bit(R5_LOCKED, &dev->flags)) s.locked++;
if (test_bit(R5_UPTODATE, &dev->flags)) s.uptodate++;
+ if (test_bit(R5_Wantcompute, &dev->flags)) s.compute++;
- if (dev->toread)
+ if (test_bit(R5_Wantfill, &dev->flags))
+ s.to_fill++;
+ else if (dev->toread)
s.to_read++;
if (dev->towrite) {
s.to_write++;
if (dev->written)
s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
+ if (blocked_rdev == NULL &&
+ rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
+ }
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
set_bit(R5_Insync, &dev->flags);
}
rcu_read_unlock();
+
+ if (unlikely(blocked_rdev)) {
+ 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)) {
+ set_bit(STRIPE_OP_BIOFILL, &s.ops_request);
+ set_bit(STRIPE_BIOFILL_RUN, &sh->state);
+ }
+
pr_debug("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d\n",
s.locked, s.uptodate, s.to_read, s.to_write,
* need to be failed
*/
if (s.failed > 1 && s.to_read+s.to_write+s.written)
- handle_requests_to_failed_array(conf, sh, &s, disks,
- &return_bi);
+ handle_failed_stripe(conf, sh, &s, disks, &return_bi);
if (s.failed > 1 && s.syncing) {
md_done_sync(conf->mddev, STRIPE_SECTORS,0);
clear_bit(STRIPE_SYNCING, &sh->state);
!test_bit(R5_LOCKED, &dev->flags) &&
test_bit(R5_UPTODATE, &dev->flags)) ||
(s.failed == 1 && s.failed_num == sh->pd_idx)))
- handle_completed_write_requests(conf, sh, disks, &return_bi);
+ handle_stripe_clean_event(conf, sh, disks, &return_bi);
/* Now we might consider reading some blocks, either to check/generate
* parity, or to satisfy requests
* or to load a block that is being partially written.
*/
if (s.to_read || s.non_overwrite ||
- (s.syncing && (s.uptodate < disks)) || s.expanding)
- handle_issuing_new_read_requests5(sh, &s, disks);
+ (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
+ handle_stripe_fill5(sh, &s, disks);
- /* now to consider writing and what else, if anything should be read */
- if (s.to_write)
- handle_issuing_new_write_requests5(conf, sh, &s, disks);
+ /* Now we check to see if any write operations have recently
+ * completed
+ */
+ prexor = 0;
+ if (sh->reconstruct_state == reconstruct_state_prexor_drain_result)
+ prexor = 1;
+ if (sh->reconstruct_state == reconstruct_state_drain_result ||
+ sh->reconstruct_state == reconstruct_state_prexor_drain_result) {
+ sh->reconstruct_state = reconstruct_state_idle;
+
+ /* All the 'written' buffers and the parity block are ready to
+ * be written back to disk
+ */
+ BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags));
+ for (i = disks; i--; ) {
+ dev = &sh->dev[i];
+ if (test_bit(R5_LOCKED, &dev->flags) &&
+ (i == sh->pd_idx || dev->written)) {
+ pr_debug("Writing block %d\n", i);
+ set_bit(R5_Wantwrite, &dev->flags);
+ if (prexor)
+ continue;
+ if (!test_bit(R5_Insync, &dev->flags) ||
+ (i == sh->pd_idx && s.failed == 0))
+ set_bit(STRIPE_INSYNC, &sh->state);
+ }
+ }
+ if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
+ atomic_dec(&conf->preread_active_stripes);
+ if (atomic_read(&conf->preread_active_stripes) <
+ IO_THRESHOLD)
+ md_wakeup_thread(conf->mddev->thread);
+ }
+ }
+
+ /* Now to consider new write requests and what else, if anything
+ * should be read. We do not handle new writes when:
+ * 1/ A 'write' operation (copy+xor) is already in flight.
+ * 2/ A 'check' operation is in flight, as it may clobber the parity
+ * block.
+ */
+ if (s.to_write && !sh->reconstruct_state && !sh->check_state)
+ handle_stripe_dirtying5(conf, sh, &s, disks);
/* maybe we need to check and possibly fix the parity for this stripe
- * Any reads will already have been scheduled, so we just see if enough data
- * is available
+ * Any reads will already have been scheduled, so we just see if enough
+ * data is available. The parity check is held off while parity
+ * dependent operations are in flight.
*/
- if (s.syncing && s.locked == 0 &&
- !test_bit(STRIPE_INSYNC, &sh->state))
+ if (sh->check_state ||
+ (s.syncing && s.locked == 0 &&
+ !test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
+ !test_bit(STRIPE_INSYNC, &sh->state)))
handle_parity_checks5(conf, sh, &s, disks);
+
if (s.syncing && s.locked == 0 && test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS,1);
clear_bit(STRIPE_SYNCING, &sh->state);
}
}
- if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
- /* Need to write out all blocks after computing parity */
- sh->disks = conf->raid_disks;
- sh->pd_idx = stripe_to_pdidx(sh->sector, conf, conf->raid_disks);
- compute_parity5(sh, RECONSTRUCT_WRITE);
+ /* Finish reconstruct operations initiated by the expansion process */
+ if (sh->reconstruct_state == reconstruct_state_result) {
+ sh->reconstruct_state = reconstruct_state_idle;
+ clear_bit(STRIPE_EXPANDING, &sh->state);
for (i = conf->raid_disks; i--; ) {
+ set_bit(R5_Wantwrite, &sh->dev[i].flags);
set_bit(R5_LOCKED, &sh->dev[i].flags);
s.locked++;
- set_bit(R5_Wantwrite, &sh->dev[i].flags);
}
- clear_bit(STRIPE_EXPANDING, &sh->state);
- } else if (s.expanded) {
+ }
+
+ if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
+ !sh->reconstruct_state) {
+ /* Need to write out all blocks after computing parity */
+ sh->disks = conf->raid_disks;
+ 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);
atomic_dec(&conf->reshape_stripes);
wake_up(&conf->wait_for_overlap);
md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
}
- if (s.expanding && s.locked == 0)
+ if (s.expanding && s.locked == 0 &&
+ !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
handle_stripe_expansion(conf, sh, NULL);
- if (sh->ops.count)
- pending = get_stripe_work(sh);
-
+ unlock:
spin_unlock(&sh->lock);
- if (pending)
- raid5_run_ops(sh, pending);
+ /* wait for this device to become unblocked */
+ if (unlikely(blocked_rdev))
+ md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+
+ if (s.ops_request)
+ raid5_run_ops(sh, s.ops_request);
+
+ ops_run_io(sh, &s);
return_io(return_bi);
- for (i=disks; i-- ;) {
- int rw;
- struct bio *bi;
- mdk_rdev_t *rdev;
- if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
- rw = WRITE;
- else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
- rw = READ;
- else
- continue;
-
- bi = &sh->dev[i].req;
-
- bi->bi_rw = rw;
- if (rw == WRITE)
- bi->bi_end_io = raid5_end_write_request;
- else
- bi->bi_end_io = raid5_end_read_request;
-
- rcu_read_lock();
- rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && test_bit(Faulty, &rdev->flags))
- rdev = NULL;
- if (rdev)
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
-
- if (rdev) {
- if (s.syncing || s.expanding || s.expanded)
- md_sync_acct(rdev->bdev, STRIPE_SECTORS);
+ return blocked_rdev == NULL;
+}
- bi->bi_bdev = rdev->bdev;
- pr_debug("for %llu schedule op %ld on disc %d\n",
- (unsigned long long)sh->sector, bi->bi_rw, i);
- atomic_inc(&sh->count);
- bi->bi_sector = sh->sector + rdev->data_offset;
- bi->bi_flags = 1 << BIO_UPTODATE;
- bi->bi_vcnt = 1;
- bi->bi_max_vecs = 1;
- bi->bi_idx = 0;
- bi->bi_io_vec = &sh->dev[i].vec;
- bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
- bi->bi_io_vec[0].bv_offset = 0;
- bi->bi_size = STRIPE_SIZE;
- bi->bi_next = NULL;
- if (rw == WRITE &&
- test_bit(R5_ReWrite, &sh->dev[i].flags))
- atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
- generic_make_request(bi);
- } else {
- if (rw == WRITE)
- set_bit(STRIPE_DEGRADED, &sh->state);
- pr_debug("skip op %ld on disc %d for sector %llu\n",
- bi->bi_rw, i, (unsigned long long)sh->sector);
- clear_bit(R5_LOCKED, &sh->dev[i].flags);
- set_bit(STRIPE_HANDLE, &sh->state);
- }
- }
-}
-
-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 stripe_head_state s;
struct r6_state r6s;
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 (blocked_rdev == NULL &&
+ rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
+ }
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
set_bit(R5_Insync, &dev->flags);
}
rcu_read_unlock();
+
+ if (unlikely(blocked_rdev)) {
+ 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,
* might need to be failed
*/
if (s.failed > 2 && s.to_read+s.to_write+s.written)
- handle_requests_to_failed_array(conf, sh, &s, disks,
- &return_bi);
+ handle_failed_stripe(conf, sh, &s, disks, &return_bi);
if (s.failed > 2 && s.syncing) {
md_done_sync(conf->mddev, STRIPE_SECTORS,0);
clear_bit(STRIPE_SYNCING, &sh->state);
( r6s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
&& !test_bit(R5_LOCKED, &qdev->flags)
&& test_bit(R5_UPTODATE, &qdev->flags)))))
- handle_completed_write_requests(conf, sh, disks, &return_bi);
+ handle_stripe_clean_event(conf, sh, disks, &return_bi);
/* Now we might consider reading some blocks, either to check/generate
* parity, or to satisfy requests
*/
if (s.to_read || s.non_overwrite || (s.to_write && s.failed) ||
(s.syncing && (s.uptodate < disks)) || s.expanding)
- handle_issuing_new_read_requests6(sh, &s, &r6s, disks);
+ handle_stripe_fill6(sh, &s, &r6s, disks);
/* now to consider writing and what else, if anything should be read */
if (s.to_write)
- handle_issuing_new_write_requests6(conf, sh, &s, &r6s, disks);
+ handle_stripe_dirtying6(conf, sh, &s, &r6s, disks);
/* maybe we need to check and possibly fix the parity for this stripe
* Any reads will already have been scheduled, so we just see if enough
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);
md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
}
- if (s.expanding && s.locked == 0)
+ if (s.expanding && s.locked == 0 &&
+ !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
handle_stripe_expansion(conf, sh, &r6s);
+ unlock:
spin_unlock(&sh->lock);
- return_io(return_bi);
+ /* wait for this device to become unblocked */
+ if (unlikely(blocked_rdev))
+ md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
- for (i=disks; i-- ;) {
- int rw;
- struct bio *bi;
- mdk_rdev_t *rdev;
- if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags))
- rw = WRITE;
- else if (test_and_clear_bit(R5_Wantread, &sh->dev[i].flags))
- rw = READ;
- else
- continue;
+ ops_run_io(sh, &s);
- bi = &sh->dev[i].req;
-
- bi->bi_rw = rw;
- if (rw == WRITE)
- bi->bi_end_io = raid5_end_write_request;
- else
- bi->bi_end_io = raid5_end_read_request;
-
- rcu_read_lock();
- rdev = rcu_dereference(conf->disks[i].rdev);
- if (rdev && test_bit(Faulty, &rdev->flags))
- rdev = NULL;
- if (rdev)
- atomic_inc(&rdev->nr_pending);
- rcu_read_unlock();
-
- if (rdev) {
- if (s.syncing || s.expanding || s.expanded)
- md_sync_acct(rdev->bdev, STRIPE_SECTORS);
+ return_io(return_bi);
- bi->bi_bdev = rdev->bdev;
- pr_debug("for %llu schedule op %ld on disc %d\n",
- (unsigned long long)sh->sector, bi->bi_rw, i);
- atomic_inc(&sh->count);
- bi->bi_sector = sh->sector + rdev->data_offset;
- bi->bi_flags = 1 << BIO_UPTODATE;
- bi->bi_vcnt = 1;
- bi->bi_max_vecs = 1;
- bi->bi_idx = 0;
- bi->bi_io_vec = &sh->dev[i].vec;
- bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
- bi->bi_io_vec[0].bv_offset = 0;
- bi->bi_size = STRIPE_SIZE;
- bi->bi_next = NULL;
- if (rw == WRITE &&
- test_bit(R5_ReWrite, &sh->dev[i].flags))
- atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
- generic_make_request(bi);
- } else {
- if (rw == WRITE)
- set_bit(STRIPE_DEGRADED, &sh->state);
- pr_debug("skip op %ld on disc %d for sector %llu\n",
- bi->bi_rw, i, (unsigned long long)sh->sector);
- clear_bit(R5_LOCKED, &sh->dev[i].flags);
- set_bit(STRIPE_HANDLE, &sh->state);
- }
- }
+ 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);
}
clear_bit(STRIPE_DELAYED, &sh->state);
if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
atomic_inc(&conf->preread_active_stripes);
- list_add_tail(&sh->lru, &conf->handle_list);
+ list_add_tail(&sh->lru, &conf->hold_list);
}
- }
+ } else
+ blk_plug_device(conf->mddev->queue);
}
static void activate_bit_delay(raid5_conf_t *conf)
for (i=0; i<mddev->raid_disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags) && atomic_read(&rdev->nr_pending)) {
- request_queue_t *r_queue = bdev_get_queue(rdev->bdev);
+ struct request_queue *r_queue = bdev_get_queue(rdev->bdev);
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
- if (r_queue->unplug_fn)
- r_queue->unplug_fn(r_queue);
+ blk_unplug(r_queue);
rdev_dec_pending(rdev, mddev);
rcu_read_lock();
rcu_read_unlock();
}
-static void raid5_unplug_device(request_queue_t *q)
+static void raid5_unplug_device(struct request_queue *q)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev_to_conf(mddev);
unplug_slaves(mddev);
}
-static int raid5_issue_flush(request_queue_t *q, struct gendisk *disk,
- sector_t *error_sector)
-{
- mddev_t *mddev = q->queuedata;
- raid5_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 int raid5_congested(void *data, int bits)
{
mddev_t *mddev = data;
/* We want read requests to align with chunks where possible,
* but write requests don't need to.
*/
-static int raid5_mergeable_bvec(request_queue_t *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;
* first).
* If the read failed..
*/
-static int raid5_align_endio(struct bio *bi, unsigned int bytes, int error)
+static void raid5_align_endio(struct bio *bi, int error)
{
struct bio* raid_bi = bi->bi_private;
mddev_t *mddev;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
mdk_rdev_t *rdev;
- if (bi->bi_size)
- return 1;
bio_put(bi);
mddev = raid_bi->bi_bdev->bd_disk->queue->queuedata;
rdev_dec_pending(rdev, conf->mddev);
if (!error && uptodate) {
- bio_endio(raid_bi, bytes, 0);
+ bio_endio(raid_bi, 0);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_stripe);
- return 0;
+ return;
}
pr_debug("raid5_align_endio : io error...handing IO for a retry\n");
add_bio_to_retry(raid_bi, conf);
- return 0;
}
static int bio_fits_rdev(struct bio *bi)
{
- request_queue_t *q = bdev_get_queue(bi->bi_bdev);
+ struct request_queue *q = bdev_get_queue(bi->bi_bdev);
if ((bi->bi_size>>9) > q->max_sectors)
return 0;
blk_recount_segments(q, bi);
- if (bi->bi_phys_segments > q->max_phys_segments ||
- bi->bi_hw_segments > q->max_hw_segments)
+ if (bi->bi_phys_segments > q->max_phys_segments)
return 0;
if (q->merge_bvec_fn)
}
-static int chunk_aligned_read(request_queue_t *q, struct bio * raid_bio)
+static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
{
mddev_t *mddev = q->queuedata;
raid5_conf_t *conf = mddev_to_conf(mddev);
- 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);
}
}
+/* __get_priority_stripe - get the next stripe to process
+ *
+ * Full stripe writes are allowed to pass preread active stripes up until
+ * the bypass_threshold is exceeded. In general the bypass_count
+ * increments when the handle_list is handled before the hold_list; however, it
+ * will not be incremented when STRIPE_IO_STARTED is sampled set signifying a
+ * stripe with in flight i/o. The bypass_count will be reset when the
+ * head of the hold_list has changed, i.e. the head was promoted to the
+ * handle_list.
+ */
+static struct stripe_head *__get_priority_stripe(raid5_conf_t *conf)
+{
+ struct stripe_head *sh;
+
+ pr_debug("%s: handle: %s hold: %s full_writes: %d bypass_count: %d\n",
+ __func__,
+ list_empty(&conf->handle_list) ? "empty" : "busy",
+ list_empty(&conf->hold_list) ? "empty" : "busy",
+ atomic_read(&conf->pending_full_writes), conf->bypass_count);
+
+ if (!list_empty(&conf->handle_list)) {
+ sh = list_entry(conf->handle_list.next, typeof(*sh), lru);
-static int make_request(request_queue_t *q, struct bio * bi)
+ if (list_empty(&conf->hold_list))
+ conf->bypass_count = 0;
+ else if (!test_bit(STRIPE_IO_STARTED, &sh->state)) {
+ if (conf->hold_list.next == conf->last_hold)
+ conf->bypass_count++;
+ else {
+ conf->last_hold = conf->hold_list.next;
+ conf->bypass_count -= conf->bypass_threshold;
+ if (conf->bypass_count < 0)
+ conf->bypass_count = 0;
+ }
+ }
+ } else if (!list_empty(&conf->hold_list) &&
+ ((conf->bypass_threshold &&
+ conf->bypass_count > conf->bypass_threshold) ||
+ atomic_read(&conf->pending_full_writes) == 0)) {
+ sh = list_entry(conf->hold_list.next,
+ typeof(*sh), lru);
+ conf->bypass_count -= conf->bypass_threshold;
+ if (conf->bypass_count < 0)
+ conf->bypass_count = 0;
+ } else
+ return NULL;
+
+ list_del_init(&sh->lru);
+ atomic_inc(&sh->count);
+ BUG_ON(atomic_read(&sh->count) != 1);
+ return sh;
+}
+
+static int make_request(struct request_queue *q, struct bio * bi)
{
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, bi->bi_size, -EOPNOTSUPP);
+ bio_endio(bi, -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));
+ 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
goto retry;
}
finish_wait(&conf->wait_for_overlap, &w);
- handle_stripe(sh, NULL);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ clear_bit(STRIPE_DELAYED, &sh->state);
release_stripe(sh);
} else {
/* cannot get stripe for read-ahead, just give-up */
}
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) {
- int bytes = bi->bi_size;
if ( rw == WRITE )
md_write_end(mddev);
- bi->bi_size = 0;
- bi->bi_end_io(bi, bytes,
- test_bit(BIO_UPTODATE, &bi->bi_flags)
- ? 0 : -EIO);
+
+ bio_endio(bi, 0);
}
return 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_size<<1)) {
+ if (s < mddev->array_sectors) {
skipped = 1;
continue;
}
* 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);
first_sector += STRIPE_SECTORS;
}
+ /* If this takes us to the resync_max point where we have to pause,
+ * then we need to write out the superblock.
+ */
+ sector_nr += conf->chunk_size>>9;
+ if (sector_nr >= mddev->resync_max) {
+ /* Cannot proceed until we've updated the superblock... */
+ wait_event(conf->wait_for_overlap,
+ atomic_read(&conf->reshape_stripes) == 0);
+ mddev->reshape_position = conf->expand_progress;
+ set_bit(MD_CHANGE_DEVS, &mddev->flags);
+ md_wakeup_thread(mddev->thread);
+ wait_event(mddev->sb_wait,
+ !test_bit(MD_CHANGE_DEVS, &mddev->flags)
+ || kthread_should_stop());
+ spin_lock_irq(&conf->device_lock);
+ conf->expand_lo = mddev->reshape_position;
+ spin_unlock_irq(&conf->device_lock);
+ wake_up(&conf->wait_for_overlap);
+ }
return conf->chunk_size>>9;
}
{
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 (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
return reshape_request(mddev, sector_nr, skipped);
+ /* No need to check resync_max as we never do more than one
+ * stripe, and as resync_max will always be on a chunk boundary,
+ * if the check in md_do_sync didn't fire, there is no chance
+ * of overstepping resync_max here
+ */
+
/* if there is too many failed drives and we are trying
* to resync, then assert that we are finished, because there is
* nothing we can do.
*/
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;
}
return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
}
- pd_idx = stripe_to_pdidx(sector_nr, conf, raid_disks);
- sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 1);
+
+ bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+
+ 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) {
- int bytes = raid_bio->bi_size;
-
- raid_bio->bi_size = 0;
- raid_bio->bi_end_io(raid_bio, bytes,
- test_bit(BIO_UPTODATE, &raid_bio->bi_flags)
- ? 0 : -EIO);
- }
+ if (remaining == 0)
+ bio_endio(raid_bio, 0);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_stripe);
return handled;
* During the scan, completed stripes are saved for us by the interrupt
* handler, so that they will not have to wait for our next wakeup.
*/
-static void raid5d (mddev_t *mddev)
+static void raid5d(mddev_t *mddev)
{
struct stripe_head *sh;
raid5_conf_t *conf = mddev_to_conf(mddev);
handled = 0;
spin_lock_irq(&conf->device_lock);
while (1) {
- struct list_head *first;
struct bio *bio;
if (conf->seq_flush != conf->seq_write) {
activate_bit_delay(conf);
}
- if (list_empty(&conf->handle_list) &&
- atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD &&
- !blk_queue_plugged(mddev->queue) &&
- !list_empty(&conf->delayed_list))
- raid5_activate_delayed(conf);
-
while ((bio = remove_bio_from_retry(conf))) {
int ok;
spin_unlock_irq(&conf->device_lock);
handled++;
}
- if (list_empty(&conf->handle_list)) {
- async_tx_issue_pending_all();
- break;
- }
-
- first = conf->handle_list.next;
- sh = list_entry(first, struct stripe_head, lru);
+ sh = __get_priority_stripe(conf);
- list_del_init(first);
- atomic_inc(&sh->count);
- BUG_ON(atomic_read(&sh->count)!= 1);
+ if (!sh)
+ break;
spin_unlock_irq(&conf->device_lock);
handled++;
spin_unlock_irq(&conf->device_lock);
+ async_tx_issue_pending_all();
unplug_slaves(mddev);
pr_debug("--- raid5d inactive\n");
raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
{
raid5_conf_t *conf = mddev_to_conf(mddev);
- char *end;
- int new;
+ unsigned long new;
+ int err;
+
if (len >= PAGE_SIZE)
return -EINVAL;
if (!conf)
return -ENODEV;
- new = simple_strtoul(page, &end, 10);
- if (!*page || (*end && *end != '\n') )
+ if (strict_strtoul(page, 10, &new))
return -EINVAL;
if (new <= 16 || new > 32768)
return -EINVAL;
else
break;
}
- md_allow_write(mddev);
+ err = md_allow_write(mddev);
+ if (err)
+ return err;
while (new > conf->max_nr_stripes) {
if (grow_one_stripe(conf))
conf->max_nr_stripes++;
raid5_store_stripe_cache_size);
static ssize_t
+raid5_show_preread_threshold(mddev_t *mddev, char *page)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ if (conf)
+ return sprintf(page, "%d\n", conf->bypass_threshold);
+ else
+ return 0;
+}
+
+static ssize_t
+raid5_store_preread_threshold(mddev_t *mddev, const char *page, size_t len)
+{
+ raid5_conf_t *conf = mddev_to_conf(mddev);
+ unsigned long new;
+ if (len >= PAGE_SIZE)
+ return -EINVAL;
+ if (!conf)
+ return -ENODEV;
+
+ if (strict_strtoul(page, 10, &new))
+ return -EINVAL;
+ if (new > conf->max_nr_stripes)
+ return -EINVAL;
+ conf->bypass_threshold = new;
+ return len;
+}
+
+static struct md_sysfs_entry
+raid5_preread_bypass_threshold = __ATTR(preread_bypass_threshold,
+ S_IRUGO | S_IWUSR,
+ raid5_show_preread_threshold,
+ raid5_store_preread_threshold);
+
+static ssize_t
stripe_cache_active_show(mddev_t *mddev, char *page)
{
raid5_conf_t *conf = mddev_to_conf(mddev);
static struct attribute *raid5_attrs[] = {
&raid5_stripecache_size.attr,
&raid5_stripecache_active.attr,
+ &raid5_preread_bypass_threshold.attr,
NULL,
};
static struct attribute_group raid5_attrs_group = {
.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->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);
}
+ conf = kzalloc(sizeof(raid5_conf_t), GFP_KERNEL);
+ if (conf == NULL)
+ goto abort;
+
+ 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->disks)
+ goto abort;
+
+ conf->mddev = mddev;
+
+ if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
+ goto abort;
+
+ if (mddev->new_level == 6) {
+ conf->spare_page = alloc_page(GFP_KERNEL);
+ if (!conf->spare_page)
+ goto abort;
+ }
+ 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->hold_list);
+ INIT_LIST_HEAD(&conf->delayed_list);
+ INIT_LIST_HEAD(&conf->bitmap_list);
+ INIT_LIST_HEAD(&conf->inactive_list);
+ atomic_set(&conf->active_stripes, 0);
+ atomic_set(&conf->preread_active_stripes, 0);
+ atomic_set(&conf->active_aligned_reads, 0);
+ conf->bypass_threshold = BYPASS_THRESHOLD;
+
+ pr_debug("raid5: run(%s) called.\n", mdname(mddev));
+
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ raid_disk = rdev->raid_disk;
+ if (raid_disk >= conf->raid_disks
+ || raid_disk < 0)
+ continue;
+ disk = conf->disks + raid_disk;
+
+ disk->rdev = rdev;
+
+ if (test_bit(In_sync, &rdev->flags)) {
+ char b[BDEVNAME_SIZE];
+ printk(KERN_INFO "raid5: device %s operational as raid"
+ " disk %d\n", bdevname(rdev->bdev,b),
+ raid_disk);
+ } else
+ /* Cannot rely on bitmap to complete recovery */
+ conf->fullsync = 1;
+ }
+
+ 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->new_layout;
+ conf->max_nr_stripes = NR_STRIPES;
+ conf->expand_progress = mddev->reshape_position;
+
+ 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;
+ } 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;
+ }
+
+ 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
}
printk(KERN_INFO "raid5: reshape will continue\n");
/* OK, we should be able to continue; */
- }
-
-
- mddev->private = kzalloc(sizeof (raid5_conf_t), GFP_KERNEL);
- if ((conf = mddev->private) == 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->previous_raid_disks = mddev->raid_disks - mddev->delta_disks;
- }
-
- conf->disks = kzalloc(conf->raid_disks * sizeof(struct disk_info),
- GFP_KERNEL);
- if (!conf->disks)
- goto abort;
-
- conf->mddev = mddev;
-
- if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
- goto abort;
-
- if (mddev->level == 6) {
- conf->spare_page = alloc_page(GFP_KERNEL);
- if (!conf->spare_page)
- goto abort;
+ 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);
}
- 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);
- atomic_set(&conf->active_aligned_reads, 0);
-
- pr_debug("raid5: run(%s) called.\n", mdname(mddev));
- ITERATE_RDEV(mddev,rdev,tmp) {
- raid_disk = rdev->raid_disk;
- if (raid_disk >= conf->raid_disks
- || raid_disk < 0)
- continue;
- disk = conf->disks + raid_disk;
+ if (mddev->private == NULL)
+ conf = setup_conf(mddev);
+ else
+ conf = mddev->private;
- disk->rdev = rdev;
+ if (IS_ERR(conf))
+ return PTR_ERR(conf);
- if (test_bit(In_sync, &rdev->flags)) {
- char b[BDEVNAME_SIZE];
- printk(KERN_INFO "raid5: device %s operational as raid"
- " disk %d\n", bdevname(rdev->bdev,b),
- raid_disk);
- working_disks++;
- }
- }
+ mddev->thread = conf->thread;
+ conf->thread = NULL;
+ mddev->private = conf;
/*
* 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;
- if (conf->level == 6)
- conf->max_degraded = 2;
- else
- conf->max_degraded = 1;
- conf->algorithm = mddev->layout;
- conf->max_nr_stripes = NR_STRIPES;
- conf->expand_progress = mddev->reshape_position;
+ list_for_each_entry(rdev, &mddev->disks, same_set)
+ if (rdev->raid_disk >= 0 &&
+ test_bit(In_sync, &rdev->flags))
+ working_disks++;
- /* device size must be a multiple of chunk size */
- mddev->size &= ~(mddev->chunk_size/1024 -1);
- mddev->resync_max_sectors = mddev->size << 1;
+ mddev->degraded = conf->raid_disks - working_disks;
- 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);
- 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));
- 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;
- }
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->issue_flush_fn = raid5_issue_flush;
mddev->queue->backing_dev_info.congested_data = mddev;
mddev->queue->backing_dev_info.congested_fn = raid5_congested;
- mddev->array_size = mddev->size * (conf->previous_raid_disks -
- conf->max_degraded);
+ 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;
err = -EBUSY;
goto abort;
}
+ /* Only remove non-faulty devices if recovery
+ * isn't possible.
+ */
+ if (!test_bit(Faulty, &rdev->flags) &&
+ mddev->degraded <= conf->max_degraded) {
+ err = -EBUSY;
+ goto abort;
+ }
p->rdev = NULL;
synchronize_rcu();
if (atomic_read(&rdev->nr_pending)) {
static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
{
raid5_conf_t *conf = mddev->private;
- int found = 0;
+ int err = -EEXIST;
int disk;
struct disk_info *p;
+ int first = 0;
+ int last = conf->raid_disks - 1;
if (mddev->degraded > conf->max_degraded)
/* no point adding a device */
- return 0;
+ return -EINVAL;
+
+ if (rdev->raid_disk >= 0)
+ first = last = rdev->raid_disk;
/*
* find the disk ... but prefer rdev->saved_raid_disk
* if possible.
*/
if (rdev->saved_raid_disk >= 0 &&
+ rdev->saved_raid_disk >= first &&
conf->disks[rdev->saved_raid_disk].rdev == NULL)
disk = rdev->saved_raid_disk;
else
- disk = 0;
- for ( ; disk < conf->raid_disks; disk++)
+ disk = first;
+ for ( ; disk <= last ; disk++)
if ((p=conf->disks + disk)->rdev == NULL) {
clear_bit(In_sync, &rdev->flags);
rdev->raid_disk = disk;
- found = 1;
+ err = 0;
if (rdev->saved_raid_disk != disk)
conf->fullsync = 1;
rcu_assign_pointer(p->rdev, rdev);
break;
}
print_raid5_conf(conf);
- return found;
+ return err;
}
static int raid5_resize(mddev_t *mddev, sector_t sectors)
raid5_conf_t *conf = mddev_to_conf(mddev);
sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
- mddev->array_size = (sectors * (mddev->raid_disks-conf->max_degraded))>>1;
- set_capacity(mddev->gendisk, mddev->array_size << 1);
+ mddev->array_sectors = sectors * (mddev->raid_disks
+ - 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;
- ITERATE_RDEV(mddev, rdev, rtmp)
+ 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.
*/
- ITERATE_RDEV(mddev, rdev, rtmp)
+ 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)) {
+ if (raid5_add_disk(mddev, rdev) == 0) {
char nm[20];
set_bit(In_sync, &rdev->flags);
added_devices++;
struct block_device *bdev;
if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
- conf->mddev->array_size = 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_size << 1);
+ set_capacity(conf->mddev->gendisk, conf->mddev->array_sectors);
conf->mddev->changed = 1;
bdev = bdget_disk(conf->mddev->gendisk, 0);
if (bdev) {
mutex_lock(&bdev->bd_inode->i_mutex);
- i_size_write(bdev->bd_inode, (loff_t)conf->mddev->array_size << 10);
+ i_size_write(bdev->bd_inode,
+ (loff_t)conf->mddev->array_sectors << 9);
mutex_unlock(&bdev->bd_inode->i_mutex);
bdput(bdev);
}
}
}
+
+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 =