#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)));
{
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)
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",
}
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)
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) {
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)
+ops_run_compute5(struct stripe_head *sh, unsigned long ops_request)
{
/* 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--; )
ops_complete_compute5, sh);
/* ack now if postxor is not set to be run */
- if (tx && !test_bit(STRIPE_OP_POSTXOR, &pending))
+ if (tx && !test_bit(STRIPE_OP_POSTXOR, &ops_request))
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--; ) {
}
static struct dma_async_tx_descriptor *
-ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
+ops_run_biodrain(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
+ unsigned long ops_request)
{
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 prexor = test_bit(STRIPE_OP_PREXOR, &ops_request);
- pr_debug("%s: stripe %llu\n", __FUNCTION__,
+ pr_debug("%s: stripe %llu\n", __func__,
(unsigned long long)sh->sector);
for (i = disks; i--; ) {
{
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_POSTXOR, &sh->ops.complete);
+ sh->reconstruct_state = reconstruct_state_result;
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
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);
-
+ sh->reconstruct_state = reconstruct_state_drain_result;
set_bit(STRIPE_HANDLE, &sh->state);
release_stripe(sh);
}
static void
-ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx)
+ops_run_postxor(struct stripe_head *sh, struct dma_async_tx_descriptor *tx,
+ unsigned long ops_request)
{
/* kernel stack size limits the total number of disks */
int disks = sh->disks;
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 = test_bit(STRIPE_OP_PREXOR, &ops_request);
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
}
/* check whether this postxor is part of a write */
- callback = test_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending) ?
+ callback = test_bit(STRIPE_OP_BIODRAIN, &ops_request) ?
ops_complete_write : ops_complete_postxor;
/* 1/ if we prexor'd then the dest is reused as a source
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, ops_request);
- 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)) {
- tx = ops_run_biodrain(sh, tx);
+ if (test_bit(STRIPE_OP_BIODRAIN, &ops_request)) {
+ tx = ops_run_biodrain(sh, tx, ops_request);
overlap_clear++;
}
- if (test_bit(STRIPE_OP_POSTXOR, &pending))
- ops_run_postxor(sh, tx);
+ if (test_bit(STRIPE_OP_POSTXOR, &ops_request))
+ ops_run_postxor(sh, tx, ops_request);
- 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];
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;
/* 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;
raid5_conf_t *conf = sh->raid_conf;
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;
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;
}
/*
* 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",
+ "raid5: Disk failure on %s, disabling device.\n"
+ "raid5: Operation continuing on %d devices.\n",
bdevname(rdev->bdev,b), conf->raid_disks - mddev->degraded);
}
}
} \
} 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;
}
}
-static int
-handle_write_operations5(struct stripe_head *sh, int rcw, int expand)
+static void
+handle_write_operations5(struct stripe_head *sh, struct stripe_head_state *s,
+ int rcw, int expand)
{
int i, pd_idx = sh->pd_idx, disks = sh->disks;
- int locked = 0;
if (rcw) {
/* if we are not expanding this is a proper write request, and
* stripe cache
*/
if (!expand) {
- set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
- sh->ops.count++;
- }
+ 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, &sh->ops.pending);
- sh->ops.count++;
+ set_bit(STRIPE_OP_POSTXOR, &s->ops_request);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
set_bit(R5_LOCKED, &dev->flags);
if (!expand)
clear_bit(R5_UPTODATE, &dev->flags);
- locked++;
+ 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)));
- set_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
- set_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
- set_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
-
- sh->ops.count += 3;
+ sh->reconstruct_state = reconstruct_state_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];
set_bit(R5_Wantprexor, &dev->flags);
set_bit(R5_LOCKED, &dev->flags);
clear_bit(R5_UPTODATE, &dev->flags);
- locked++;
+ s->locked++;
}
}
}
*/
set_bit(R5_LOCKED, &sh->dev[pd_idx].flags);
clear_bit(R5_UPTODATE, &sh->dev[pd_idx].flags);
- locked++;
+ s->locked++;
- pr_debug("%s: stripe %llu locked: %d pending: %lx\n",
- __FUNCTION__, (unsigned long long)sh->sector,
- locked, sh->ops.pending);
-
- return locked;
+ pr_debug("%s: stripe %llu locked: %d ops_request: %lx\n",
+ __func__, (unsigned long long)sh->sector,
+ s->locked, s->ops_request);
}
/*
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))
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);
}
/* __handle_issuing_new_read_requests5 - returns 0 if there are no more disks
struct r5dev *dev = &sh->dev[disk_idx];
struct r5dev *failed_dev = &sh->dev[s->failed_num];
- /* don't schedule compute operations or reads on the parity block while
- * a check is in flight
- */
- if ((disk_idx == sh->pd_idx) &&
- test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
- return ~0;
-
/* 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 ||
(failed_dev->toread || (failed_dev->towrite &&
!test_bit(R5_OVERWRITE, &failed_dev->flags)
))))) {
- /* 1/ We would like to get this block, possibly by computing it,
- * but we might not be able to.
- *
- * 2/ Since parity check operations potentially make the parity
- * block !uptodate it will need to be refreshed before any
- * compute operations on data disks are scheduled.
- *
- * 3/ We hold off parity block re-reads until check operations
- * have quiesced.
+ /* 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) &&
- !test_bit(STRIPE_OP_CHECK, &sh->ops.pending)) {
- set_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
+ (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;
- sh->ops.count++;
/* 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
*/
s->uptodate++;
return 0; /* uptodate + compute == disks */
- } else if ((s->uptodate < disks - 1) &&
- test_bit(R5_Insync, &dev->flags)) {
- /* Note: we hold off compute operations while checks are
- * in flight, but we still prefer 'compute' over 'read'
- * hence we only read if (uptodate < * disks-1)
- */
+ } else if (test_bit(R5_Insync, &dev->flags)) {
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantread, &dev->flags);
- if (!test_and_set_bit(STRIPE_OP_IO, &sh->ops.pending))
- sh->ops.count++;
s->locked++;
pr_debug("Reading block %d (sync=%d)\n", disk_idx,
s->syncing);
{
int i;
- /* Clear completed compute operations. Parity recovery
- * (STRIPE_OP_MOD_REPAIR_PD) implies a write-back which is handled
- * later on in this routine
- */
- if (test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete) &&
- !test_bit(STRIPE_OP_MOD_REPAIR_PD, &sh->ops.pending)) {
- clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.complete);
- clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.ack);
- clear_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending);
- }
-
/* 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_OP_COMPUTE_BLK, &sh->ops.pending) &&
- !test_bit(STRIPE_OP_PREXOR, &sh->ops.pending) &&
- !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending)) {
+ if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
+ !sh->reconstruct_state) {
for (i = disks; i--; )
if (__handle_issuing_new_read_requests5(
sh, s, i, disks) == 0)
/* 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);
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,
* 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_OP_COMPUTE_BLK, &sh->ops.pending)) &&
- (s->locked == 0 && (rcw == 0 || rmw == 0) &&
- !test_bit(STRIPE_BIT_DELAY, &sh->state)))
- s->locked += handle_write_operations5(sh, rcw == 0, 0);
+ 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)))
+ handle_write_operations5(sh, s, rcw == 0, 0);
}
static void handle_issuing_new_write_requests6(raid5_conf_t *conf,
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)) {
+ if (i != sh->pd_idx && (!r6s || i != r6s->qd_idx)) {
int dd_idx, pd_idx, j;
struct stripe_head *sh2;
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 != raid6_next_disk(sh2->pd_idx,
+ sh2->disks)) &&
!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.
*
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 (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
+ break;
+ }
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
set_bit(R5_Insync, &dev->flags);
}
rcu_read_unlock();
+
+ if (unlikely(blocked_rdev)) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
+ }
+
+ 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,
* or to load a block that is being partially written.
*/
if (s.to_read || s.non_overwrite ||
- (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding ||
- test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
+ (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
handle_issuing_new_read_requests5(sh, &s, disks);
/* Now we check to see if any write operations have recently
* completed
*/
-
- /* leave prexor set until postxor is done, allows us to distinguish
- * a rmw from a rcw during biodrain
- */
- if (test_bit(STRIPE_OP_PREXOR, &sh->ops.complete) &&
- test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
-
- clear_bit(STRIPE_OP_PREXOR, &sh->ops.complete);
- clear_bit(STRIPE_OP_PREXOR, &sh->ops.ack);
- clear_bit(STRIPE_OP_PREXOR, &sh->ops.pending);
-
+ prexor = 0;
+ if (sh->reconstruct_state == reconstruct_state_drain_result) {
+ sh->reconstruct_state = reconstruct_state_idle;
for (i = disks; i--; )
- clear_bit(R5_Wantprexor, &sh->dev[i].flags);
- }
-
- /* if only POSTXOR is set then this is an 'expand' postxor */
- if (test_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete) &&
- test_bit(STRIPE_OP_POSTXOR, &sh->ops.complete)) {
-
- clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.complete);
- clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.ack);
- clear_bit(STRIPE_OP_BIODRAIN, &sh->ops.pending);
-
- clear_bit(STRIPE_OP_POSTXOR, &sh->ops.complete);
- clear_bit(STRIPE_OP_POSTXOR, &sh->ops.ack);
- clear_bit(STRIPE_OP_POSTXOR, &sh->ops.pending);
+ prexor += test_and_clear_bit(R5_Wantprexor,
+ &sh->dev[i].flags);
/* All the 'written' buffers and the parity block are ready to
* be written back to disk
(i == sh->pd_idx || dev->written)) {
pr_debug("Writing block %d\n", i);
set_bit(R5_Wantwrite, &dev->flags);
- if (!test_and_set_bit(
- STRIPE_OP_IO, &sh->ops.pending))
- sh->ops.count++;
+ if (prexor)
+ continue;
if (!test_bit(R5_Insync, &dev->flags) ||
(i == sh->pd_idx && s.failed == 0))
set_bit(STRIPE_INSYNC, &sh->state);
* 2/ A 'check' operation is in flight, as it may clobber the parity
* block.
*/
- if (s.to_write && !test_bit(STRIPE_OP_POSTXOR, &sh->ops.pending) &&
- !test_bit(STRIPE_OP_CHECK, &sh->ops.pending))
+ if (s.to_write && !sh->reconstruct_state && !sh->check_state)
handle_issuing_new_write_requests5(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)) {
+ /* 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, &dev->flags);
+ s.locked++;
+ }
+
+ 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;
- sh->pd_idx = stripe_to_pdidx(sh->sector, conf, conf->raid_disks);
- compute_parity5(sh, RECONSTRUCT_WRITE);
- for (i = conf->raid_disks; i--; ) {
- 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) {
+ sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
+ conf->raid_disks);
+ handle_write_operations5(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);
- return_io(return_bi);
+ if (s.ops_request)
+ raid5_run_ops(sh, s.ops_request);
- 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);
+ ops_run_io(sh, &s);
- 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_io(return_bi);
}
static void handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
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);
pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
if (dev->written)
s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
+ break;
+ }
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
set_bit(R5_Insync, &dev->flags);
}
rcu_read_unlock();
+
+ if (unlikely(blocked_rdev)) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
+ }
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,
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;
-
- 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();
+ ops_run_io(sh, &s);
- if (rdev) {
- if (s.syncing || s.expanding || s.expanded)
- md_sync_acct(rdev->bdev, STRIPE_SECTORS);
-
- 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_io(return_bi);
}
static void handle_stripe(struct stripe_head *sh, struct page *tmp_page)
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 bio *bio, struct bio_vec *biovec)
{
mddev_t *mddev = q->queuedata;
sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
* 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;
}
-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);
}
}
+/* __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);
int remaining;
if (unlikely(bio_barrier(bi))) {
- bio_endio(bi, bi->bi_size, -EOPNOTSUPP);
+ bio_endio(bi, -EOPNOTSUPP);
return 0;
}
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 */
remaining = --bi->bi_phys_segments;
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;
}
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;
}
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.
return sync_blocks * STRIPE_SECTORS; /* keep things rounded to whole stripes */
}
+
+ bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+
pd_idx = stripe_to_pdidx(sector_nr, conf, raid_disks);
sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 1);
if (sh == NULL) {
spin_lock_irq(&conf->device_lock);
remaining = --raid_bio->bi_phys_segments;
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)) {
+ sh = __get_priority_stripe(conf);
+
+ if (!sh) {
async_tx_issue_pending_all();
break;
}
-
- first = conf->handle_list.next;
- sh = list_entry(first, struct stripe_head, lru);
-
- list_del_init(first);
- atomic_inc(&sh->count);
- BUG_ON(atomic_read(&sh->count)!= 1);
spin_unlock_irq(&conf->device_lock);
handled++;
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;
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;
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 = {
goto abort;
}
spin_lock_init(&conf->device_lock);
+ mddev->queue->queue_lock = &conf->device_lock;
init_waitqueue_head(&conf->wait_for_stripe);
init_waitqueue_head(&conf->wait_for_overlap);
INIT_LIST_HEAD(&conf->handle_list);
+ 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));
- ITERATE_RDEV(mddev,rdev,tmp) {
+ rdev_for_each(rdev, tmp, mddev) {
raid_disk = rdev->raid_disk;
if (raid_disk >= conf->raid_disks
|| raid_disk < 0)
" disk %d\n", bdevname(rdev->bdev,b),
raid_disk);
working_disks++;
- }
+ } else
+ /* Cannot rely on bitmap to complete recovery */
+ conf->fullsync = 1;
}
/*
mdname(mddev));
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;
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)
if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery))
return -EBUSY;
- ITERATE_RDEV(mddev, rdev, rtmp)
+ rdev_for_each(rdev, rtmp, mddev)
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)
+ rdev_for_each(rdev, rtmp, mddev)
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++;