#include <linux/seq_file.h>
#include <linux/cpu.h>
#include <linux/slab.h>
+#include <linux/ratelimit.h>
#include "md.h"
#include "raid5.h"
#include "raid0.h"
#define NR_HASH (PAGE_SIZE / sizeof(struct hlist_head))
#define HASH_MASK (NR_HASH - 1)
-#define stripe_hash(conf, sect) (&((conf)->stripe_hashtbl[((sect) >> STRIPE_SHIFT) & HASH_MASK]))
+static inline struct hlist_head *stripe_hash(struct r5conf *conf, sector_t sect)
+{
+ int hash = (sect >> STRIPE_SHIFT) & HASH_MASK;
+ return &conf->stripe_hashtbl[hash];
+}
/* bio's attached to a stripe+device for I/O are linked together in bi_sector
* order without overlap. There may be several bio's per stripe+device, and
* When walking this list for a particular stripe+device, we must never proceed
* beyond a bio that extends past this device, as the next bio might no longer
* be valid.
- * This macro is used to determine the 'next' bio in the list, given the sector
+ * This function is used to determine the 'next' bio in the list, given the sector
* of the current stripe+device
*/
-#define r5_next_bio(bio, sect) ( ( (bio)->bi_sector + ((bio)->bi_size>>9) < sect + STRIPE_SECTORS) ? (bio)->bi_next : NULL)
-/*
- * The following can be used to debug the driver
- */
-#define RAID5_PARANOIA 1
-#if RAID5_PARANOIA && defined(CONFIG_SMP)
-# define CHECK_DEVLOCK() assert_spin_locked(&conf->device_lock)
-#else
-# define CHECK_DEVLOCK()
-#endif
-
-#ifdef DEBUG
-#define inline
-#define __inline__
-#endif
-
-#define printk_rl(args...) ((void) (printk_ratelimit() && printk(args)))
+static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
+{
+ int sectors = bio->bi_size >> 9;
+ if (bio->bi_sector + sectors < sector + STRIPE_SECTORS)
+ return bio->bi_next;
+ else
+ return NULL;
+}
/*
* We maintain a biased count of active stripes in the bottom 16 bits of
}
}
-static void print_raid5_conf (raid5_conf_t *conf);
+static void print_raid5_conf (struct r5conf *conf);
static int stripe_operations_active(struct stripe_head *sh)
{
test_bit(STRIPE_COMPUTE_RUN, &sh->state);
}
-static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
+static void __release_stripe(struct r5conf *conf, struct stripe_head *sh)
{
if (atomic_dec_and_test(&sh->count)) {
BUG_ON(!list_empty(&sh->lru));
static void release_stripe(struct stripe_head *sh)
{
- raid5_conf_t *conf = sh->raid_conf;
+ struct r5conf *conf = sh->raid_conf;
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
hlist_del_init(&sh->hash);
}
-static inline void insert_hash(raid5_conf_t *conf, struct stripe_head *sh)
+static inline void insert_hash(struct r5conf *conf, struct stripe_head *sh)
{
struct hlist_head *hp = stripe_hash(conf, sh->sector);
pr_debug("insert_hash(), stripe %llu\n",
(unsigned long long)sh->sector);
- CHECK_DEVLOCK();
hlist_add_head(&sh->hash, hp);
}
/* find an idle stripe, make sure it is unhashed, and return it. */
-static struct stripe_head *get_free_stripe(raid5_conf_t *conf)
+static struct stripe_head *get_free_stripe(struct r5conf *conf)
{
struct stripe_head *sh = NULL;
struct list_head *first;
- CHECK_DEVLOCK();
if (list_empty(&conf->inactive_list))
goto out;
first = conf->inactive_list.next;
}
static void raid5_build_block(struct stripe_head *sh, int i, int previous);
-static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
+static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
struct stripe_head *sh);
static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
{
- raid5_conf_t *conf = sh->raid_conf;
+ struct r5conf *conf = sh->raid_conf;
int i;
BUG_ON(atomic_read(&sh->count) != 0);
BUG_ON(test_bit(STRIPE_HANDLE, &sh->state));
BUG_ON(stripe_operations_active(sh));
- CHECK_DEVLOCK();
pr_debug("init_stripe called, stripe %llu\n",
(unsigned long long)sh->sector);
(unsigned long long)sh->sector, i, dev->toread,
dev->read, dev->towrite, dev->written,
test_bit(R5_LOCKED, &dev->flags));
- BUG();
+ WARN_ON(1);
}
dev->flags = 0;
raid5_build_block(sh, i, previous);
insert_hash(conf, sh);
}
-static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector,
+static struct stripe_head *__find_stripe(struct r5conf *conf, sector_t sector,
short generation)
{
struct stripe_head *sh;
struct hlist_node *hn;
- CHECK_DEVLOCK();
pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector);
hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
if (sh->sector == sector && sh->generation == generation)
* of the two sections, and some non-in_sync devices may
* be insync in the section most affected by failed devices.
*/
-static int has_failed(raid5_conf_t *conf)
+static int has_failed(struct r5conf *conf)
{
int degraded;
int i;
rcu_read_lock();
degraded = 0;
for (i = 0; i < conf->previous_raid_disks; i++) {
- mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
+ struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded++;
else if (test_bit(In_sync, &rdev->flags))
rcu_read_lock();
degraded = 0;
for (i = 0; i < conf->raid_disks; i++) {
- mdk_rdev_t *rdev = rcu_dereference(conf->disks[i].rdev);
+ struct md_rdev *rdev = rcu_dereference(conf->disks[i].rdev);
if (!rdev || test_bit(Faulty, &rdev->flags))
degraded++;
else if (test_bit(In_sync, &rdev->flags))
}
static struct stripe_head *
-get_active_stripe(raid5_conf_t *conf, sector_t sector,
+get_active_stripe(struct r5conf *conf, sector_t sector,
int previous, int noblock, int noquiesce)
{
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;
+ struct r5conf *conf = sh->raid_conf;
int i, disks = sh->disks;
might_sleep();
for (i = disks; i--; ) {
int rw;
struct bio *bi;
- mdk_rdev_t *rdev;
+ struct md_rdev *rdev;
if (test_and_clear_bit(R5_Wantwrite, &sh->dev[i].flags)) {
if (test_and_clear_bit(R5_WantFUA, &sh->dev[i].flags))
rw = WRITE_FUA;
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
+ /* We have already checked bad blocks for reads. Now
+ * need to check for writes.
+ */
+ while ((rw & WRITE) && rdev &&
+ test_bit(WriteErrorSeen, &rdev->flags)) {
+ sector_t first_bad;
+ int bad_sectors;
+ int bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
+ &first_bad, &bad_sectors);
+ if (!bad)
+ break;
+
+ if (bad < 0) {
+ set_bit(BlockedBadBlocks, &rdev->flags);
+ if (!conf->mddev->external &&
+ conf->mddev->flags) {
+ /* It is very unlikely, but we might
+ * still need to write out the
+ * bad block log - better give it
+ * a chance*/
+ md_check_recovery(conf->mddev);
+ }
+ md_wait_for_blocked_rdev(rdev, conf->mddev);
+ } else {
+ /* Acknowledged bad block - skip the write */
+ rdev_dec_pending(rdev, conf->mddev);
+ rdev = NULL;
+ }
+ }
+
if (rdev) {
if (s->syncing || s->expanding || s->expanded)
md_sync_acct(rdev->bdev, STRIPE_SECTORS);
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)
{
struct stripe_head *sh = stripe_head_ref;
struct bio *return_bi = NULL;
- raid5_conf_t *conf = sh->raid_conf;
+ struct r5conf *conf = sh->raid_conf;
int i;
pr_debug("%s: stripe %llu\n", __func__,
static void ops_run_biofill(struct stripe_head *sh)
{
struct dma_async_tx_descriptor *tx = NULL;
- raid5_conf_t *conf = sh->raid_conf;
+ struct r5conf *conf = sh->raid_conf;
struct async_submit_ctl submit;
int i;
if (test_and_clear_bit(R5_Wantdrain, &dev->flags)) {
struct bio *wbi;
- spin_lock(&sh->lock);
+ spin_lock_irq(&sh->raid_conf->device_lock);
chosen = dev->towrite;
dev->towrite = NULL;
BUG_ON(dev->written);
wbi = dev->written = chosen;
- spin_unlock(&sh->lock);
+ spin_unlock_irq(&sh->raid_conf->device_lock);
while (wbi && wbi->bi_sector <
dev->sector + STRIPE_SECTORS) {
{
int overlap_clear = 0, i, disks = sh->disks;
struct dma_async_tx_descriptor *tx = NULL;
- raid5_conf_t *conf = sh->raid_conf;
+ struct r5conf *conf = sh->raid_conf;
int level = conf->level;
struct raid5_percpu *percpu;
unsigned long cpu;
#define raid_run_ops __raid_run_ops
#endif
-static int grow_one_stripe(raid5_conf_t *conf)
+static int grow_one_stripe(struct r5conf *conf)
{
struct stripe_head *sh;
- sh = kmem_cache_alloc(conf->slab_cache, GFP_KERNEL);
+ sh = kmem_cache_zalloc(conf->slab_cache, GFP_KERNEL);
if (!sh)
return 0;
- memset(sh, 0, sizeof(*sh) + (conf->pool_size-1)*sizeof(struct r5dev));
+
sh->raid_conf = conf;
- spin_lock_init(&sh->lock);
#ifdef CONFIG_MULTICORE_RAID456
init_waitqueue_head(&sh->ops.wait_for_ops);
#endif
return 1;
}
-static int grow_stripes(raid5_conf_t *conf, int num)
+static int grow_stripes(struct r5conf *conf, int num)
{
struct kmem_cache *sc;
int devs = max(conf->raid_disks, conf->previous_raid_disks);
return len;
}
-static int resize_stripes(raid5_conf_t *conf, int newsize)
+static int resize_stripes(struct r5conf *conf, int newsize)
{
/* Make all the stripes able to hold 'newsize' devices.
* New slots in each stripe get 'page' set to a new page.
return -ENOMEM;
for (i = conf->max_nr_stripes; i; i--) {
- nsh = kmem_cache_alloc(sc, GFP_KERNEL);
+ nsh = kmem_cache_zalloc(sc, GFP_KERNEL);
if (!nsh)
break;
- memset(nsh, 0, sizeof(*nsh) + (newsize-1)*sizeof(struct r5dev));
-
nsh->raid_conf = conf;
- spin_lock_init(&nsh->lock);
#ifdef CONFIG_MULTICORE_RAID456
init_waitqueue_head(&nsh->ops.wait_for_ops);
#endif
return err;
}
-static int drop_one_stripe(raid5_conf_t *conf)
+static int drop_one_stripe(struct r5conf *conf)
{
struct stripe_head *sh;
return 1;
}
-static void shrink_stripes(raid5_conf_t *conf)
+static void shrink_stripes(struct r5conf *conf)
{
while (drop_one_stripe(conf))
;
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;
+ struct r5conf *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;
+ struct md_rdev *rdev;
for (i=0 ; i<disks; i++)
set_bit(R5_UPTODATE, &sh->dev[i].flags);
if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
rdev = conf->disks[i].rdev;
- printk_rl(KERN_INFO "md/raid:%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_ratelimited(
+ KERN_INFO
+ "md/raid:%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));
+ atomic_add(STRIPE_SECTORS, &rdev->corrected_errors);
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 >= conf->max_degraded)
- printk_rl(KERN_WARNING
- "md/raid:%s: read error not correctable "
- "(sector %llu on %s).\n",
- mdname(conf->mddev),
- (unsigned long long)(sh->sector
- + rdev->data_offset),
- bdn);
+ printk_ratelimited(
+ KERN_WARNING
+ "md/raid:%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_rl(KERN_WARNING
- "md/raid:%s: read error NOT corrected!! "
- "(sector %llu on %s).\n",
- mdname(conf->mddev),
- (unsigned long long)(sh->sector
- + rdev->data_offset),
- bdn);
+ printk_ratelimited(
+ KERN_WARNING
+ "md/raid:%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
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;
+ struct r5conf *conf = sh->raid_conf;
int disks = sh->disks, i;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
+ sector_t first_bad;
+ int bad_sectors;
for (i=0 ; i<disks; i++)
if (bi == &sh->dev[i].req)
return;
}
- if (!uptodate)
- md_error(conf->mddev, conf->disks[i].rdev);
+ if (!uptodate) {
+ set_bit(WriteErrorSeen, &conf->disks[i].rdev->flags);
+ set_bit(R5_WriteError, &sh->dev[i].flags);
+ } else if (is_badblock(conf->disks[i].rdev, sh->sector, STRIPE_SECTORS,
+ &first_bad, &bad_sectors))
+ set_bit(R5_MadeGood, &sh->dev[i].flags);
rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
dev->sector = compute_blocknr(sh, i, previous);
}
-static void error(mddev_t *mddev, mdk_rdev_t *rdev)
+static void error(struct mddev *mddev, struct md_rdev *rdev)
{
char b[BDEVNAME_SIZE];
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
pr_debug("raid456: error called\n");
if (test_and_clear_bit(In_sync, &rdev->flags)) {
*/
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
}
+ set_bit(Blocked, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT
* Input: a 'big' sector number,
* Output: index of the data and parity disk, and the sector # in them.
*/
-static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
+static sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector,
int previous, int *dd_idx,
struct stripe_head *sh)
{
/*
* Select the parity disk based on the user selected algorithm.
*/
- pd_idx = qd_idx = ~0;
+ pd_idx = qd_idx = -1;
switch(conf->level) {
case 4:
pd_idx = data_disks;
static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
{
- raid5_conf_t *conf = sh->raid_conf;
+ struct r5conf *conf = sh->raid_conf;
int raid_disks = sh->disks;
int data_disks = raid_disks - conf->max_degraded;
sector_t new_sector = sh->sector, check;
int rcw, int expand)
{
int i, pd_idx = sh->pd_idx, disks = sh->disks;
- raid5_conf_t *conf = sh->raid_conf;
+ struct r5conf *conf = sh->raid_conf;
int level = conf->level;
if (rcw) {
static int add_stripe_bio(struct stripe_head *sh, struct bio *bi, int dd_idx, int forwrite)
{
struct bio **bip;
- raid5_conf_t *conf = sh->raid_conf;
+ struct r5conf *conf = sh->raid_conf;
int firstwrite=0;
- pr_debug("adding bh b#%llu to stripe s#%llu\n",
+ pr_debug("adding bi b#%llu to stripe s#%llu\n",
(unsigned long long)bi->bi_sector,
(unsigned long long)sh->sector);
- spin_lock(&sh->lock);
spin_lock_irq(&conf->device_lock);
if (forwrite) {
bip = &sh->dev[dd_idx].towrite;
bi->bi_next = *bip;
*bip = bi;
bi->bi_phys_segments++;
- spin_unlock_irq(&conf->device_lock);
- spin_unlock(&sh->lock);
-
- pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
- (unsigned long long)bi->bi_sector,
- (unsigned long long)sh->sector, dd_idx);
-
- if (conf->mddev->bitmap && firstwrite) {
- bitmap_startwrite(conf->mddev->bitmap, sh->sector,
- STRIPE_SECTORS, 0);
- sh->bm_seq = conf->seq_flush+1;
- set_bit(STRIPE_BIT_DELAY, &sh->state);
- }
if (forwrite) {
/* check if page is covered */
if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
}
+ spin_unlock_irq(&conf->device_lock);
+
+ pr_debug("added bi b#%llu to stripe s#%llu, disk %d.\n",
+ (unsigned long long)(*bip)->bi_sector,
+ (unsigned long long)sh->sector, dd_idx);
+
+ if (conf->mddev->bitmap && firstwrite) {
+ bitmap_startwrite(conf->mddev->bitmap, sh->sector,
+ STRIPE_SECTORS, 0);
+ sh->bm_seq = conf->seq_flush+1;
+ set_bit(STRIPE_BIT_DELAY, &sh->state);
+ }
return 1;
overlap:
set_bit(R5_Overlap, &sh->dev[dd_idx].flags);
spin_unlock_irq(&conf->device_lock);
- spin_unlock(&sh->lock);
return 0;
}
-static void end_reshape(raid5_conf_t *conf);
+static void end_reshape(struct r5conf *conf);
-static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
+static void stripe_set_idx(sector_t stripe, struct r5conf *conf, int previous,
struct stripe_head *sh)
{
int sectors_per_chunk =
}
static void
-handle_failed_stripe(raid5_conf_t *conf, struct stripe_head *sh,
+handle_failed_stripe(struct r5conf *conf, struct stripe_head *sh,
struct stripe_head_state *s, int disks,
struct bio **return_bi)
{
int bitmap_end = 0;
if (test_bit(R5_ReadError, &sh->dev[i].flags)) {
- mdk_rdev_t *rdev;
+ struct md_rdev *rdev;
rcu_read_lock();
rdev = rcu_dereference(conf->disks[i].rdev);
if (rdev && test_bit(In_sync, &rdev->flags))
- /* multiple read failures in one stripe */
- md_error(conf->mddev, rdev);
+ atomic_inc(&rdev->nr_pending);
+ else
+ rdev = NULL;
rcu_read_unlock();
+ if (rdev) {
+ if (!rdev_set_badblocks(
+ rdev,
+ sh->sector,
+ STRIPE_SECTORS, 0))
+ md_error(conf->mddev, rdev);
+ rdev_dec_pending(rdev, conf->mddev);
+ }
}
spin_lock_irq(&conf->device_lock);
/* fail all writes first */
if (bitmap_end)
bitmap_endwrite(conf->mddev->bitmap, sh->sector,
STRIPE_SECTORS, 0, 0);
+ /* If we were in the middle of a write the parity block might
+ * still be locked - so just clear all R5_LOCKED flags
+ */
+ clear_bit(R5_LOCKED, &sh->dev[i].flags);
}
if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
md_wakeup_thread(conf->mddev->thread);
}
-/* 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)
-{
- 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;
- sh->ops.target2 = -1;
- s->req_compute = 1;
- /* Careful: from this point on 'uptodate' is in the eye
- * of raid_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.
- */
- 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)
+static void
+handle_failed_sync(struct r5conf *conf, struct stripe_head *sh,
+ struct stripe_head_state *s)
{
+ int abort = 0;
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
+ md_done_sync(conf->mddev, STRIPE_SECTORS, 0);
+ clear_bit(STRIPE_SYNCING, &sh->state);
+ s->syncing = 0;
+ /* There is nothing more to do for sync/check/repair.
+ * For recover we need to record a bad block on all
+ * non-sync devices, or abort the recovery
*/
- 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);
+ if (!test_bit(MD_RECOVERY_RECOVER, &conf->mddev->recovery))
+ return;
+ /* During recovery devices cannot be removed, so locking and
+ * refcounting of rdevs is not needed
+ */
+ for (i = 0; i < conf->raid_disks; i++) {
+ struct md_rdev *rdev = conf->disks[i].rdev;
+ if (!rdev
+ || test_bit(Faulty, &rdev->flags)
+ || test_bit(In_sync, &rdev->flags))
+ continue;
+ if (!rdev_set_badblocks(rdev, sh->sector,
+ STRIPE_SECTORS, 0))
+ abort = 1;
+ }
+ if (abort) {
+ conf->recovery_disabled = conf->mddev->recovery_disabled;
+ set_bit(MD_RECOVERY_INTR, &conf->mddev->recovery);
+ }
}
-/* fetch_block6 - checks the given member device to see if its data needs
+/* fetch_block - 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_fill6 to continue
+ * 0 to tell the loop in handle_stripe_fill to continue
*/
-static int fetch_block6(struct stripe_head *sh, struct stripe_head_state *s,
- struct r6_state *r6s, int disk_idx, int disks)
+static int fetch_block(struct stripe_head *sh, struct stripe_head_state *s,
+ int disk_idx, int disks)
{
struct r5dev *dev = &sh->dev[disk_idx];
- struct r5dev *fdev[2] = { &sh->dev[r6s->failed_num[0]],
- &sh->dev[r6s->failed_num[1]] };
+ struct r5dev *fdev[2] = { &sh->dev[s->failed_num[0]],
+ &sh->dev[s->failed_num[1]] };
+ /* 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 >= 1 &&
- (fdev[0]->toread || s->to_write)) ||
- (s->failed >= 2 &&
- (fdev[1]->toread || s->to_write)))) {
+ (s->failed >= 1 && fdev[0]->toread) ||
+ (s->failed >= 2 && fdev[1]->toread) ||
+ (sh->raid_conf->level <= 5 && s->failed && fdev[0]->towrite &&
+ !test_bit(R5_OVERWRITE, &fdev[0]->flags)) ||
+ (sh->raid_conf->level == 6 && s->failed && s->to_write))) {
/* we would like to get this block, possibly by computing it,
* otherwise read it if the backing disk is insync
*/
BUG_ON(test_bit(R5_Wantcompute, &dev->flags));
BUG_ON(test_bit(R5_Wantread, &dev->flags));
if ((s->uptodate == disks - 1) &&
- (s->failed && (disk_idx == r6s->failed_num[0] ||
- disk_idx == r6s->failed_num[1]))) {
+ (s->failed && (disk_idx == s->failed_num[0] ||
+ disk_idx == s->failed_num[1]))) {
/* have disk failed, and we're requested to fetch it;
* do compute it
*/
sh->ops.target = disk_idx;
sh->ops.target2 = -1; /* no 2nd target */
s->req_compute = 1;
+ /* Careful: from this point on 'uptodate' is in the eye
+ * of raid_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.
+ */
s->uptodate++;
return 1;
} else if (s->uptodate == disks-2 && s->failed >= 2) {
}
/**
- * handle_stripe_fill6 - read or compute data to satisfy pending requests.
+ * handle_stripe_fill - read or compute data to satisfy pending requests.
*/
-static void handle_stripe_fill6(struct stripe_head *sh,
- struct stripe_head_state *s, struct r6_state *r6s,
- int disks)
+static void handle_stripe_fill(struct stripe_head *sh,
+ struct stripe_head_state *s,
+ int disks)
{
int i;
if (!test_bit(STRIPE_COMPUTE_RUN, &sh->state) && !sh->check_state &&
!sh->reconstruct_state)
for (i = disks; i--; )
- if (fetch_block6(sh, s, r6s, i, disks))
+ if (fetch_block(sh, s, i, disks))
break;
set_bit(STRIPE_HANDLE, &sh->state);
}
* 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_stripe_clean_event(raid5_conf_t *conf,
+static void handle_stripe_clean_event(struct r5conf *conf,
struct stripe_head *sh, int disks, struct bio **return_bi)
{
int i;
md_wakeup_thread(conf->mddev->thread);
}
-static void handle_stripe_dirtying5(raid5_conf_t *conf,
- struct stripe_head *sh, struct stripe_head_state *s, int disks)
+static void handle_stripe_dirtying(struct r5conf *conf,
+ struct stripe_head *sh,
+ struct stripe_head_state *s,
+ int disks)
{
int rmw = 0, rcw = 0, i;
- for (i = disks; i--; ) {
+ if (conf->max_degraded == 2) {
+ /* RAID6 requires 'rcw' in current implementation
+ * Calculate the real rcw later - for now fake it
+ * look like rcw is cheaper
+ */
+ rcw = 1; rmw = 2;
+ } else for (i = disks; i--; ) {
/* would I have to read this buffer for read_modify_write */
struct r5dev *dev = &sh->dev[i];
if ((dev->towrite || i == sh->pd_idx) &&
}
}
}
- if (rcw <= rmw && rcw > 0)
+ if (rcw <= rmw && rcw > 0) {
/* want reconstruct write, but need to get some data */
+ rcw = 0;
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (!test_bit(R5_OVERWRITE, &dev->flags) &&
- i != sh->pd_idx &&
+ i != sh->pd_idx && i != sh->qd_idx &&
!test_bit(R5_LOCKED, &dev->flags) &&
!(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_Wantcompute, &dev->flags)) &&
- test_bit(R5_Insync, &dev->flags)) {
+ test_bit(R5_Wantcompute, &dev->flags))) {
+ rcw++;
+ if (!test_bit(R5_Insync, &dev->flags))
+ continue; /* it's a failed drive */
if (
test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
pr_debug("Read_old block "
}
}
}
+ }
/* now if nothing is locked, and if we have enough data,
* we can start a write request
*/
schedule_reconstruction(sh, s, rcw == 0, 0);
}
-static void handle_stripe_dirtying6(raid5_conf_t *conf,
- struct stripe_head *sh, struct stripe_head_state *s,
- struct r6_state *r6s, int disks)
-{
- int rcw = 0, pd_idx = sh->pd_idx, i;
- int qd_idx = sh->qd_idx;
-
- set_bit(STRIPE_HANDLE, &sh->state);
- for (i = disks; i--; ) {
- struct r5dev *dev = &sh->dev[i];
- /* check if we haven't enough data */
- if (!test_bit(R5_OVERWRITE, &dev->flags) &&
- i != pd_idx && i != qd_idx &&
- !test_bit(R5_LOCKED, &dev->flags) &&
- !(test_bit(R5_UPTODATE, &dev->flags) ||
- test_bit(R5_Wantcompute, &dev->flags))) {
- rcw++;
- if (!test_bit(R5_Insync, &dev->flags))
- continue; /* it's a failed drive */
-
- if (
- test_bit(STRIPE_PREREAD_ACTIVE, &sh->state)) {
- pr_debug("Read_old stripe %llu "
- "block %d for Reconstruct\n",
- (unsigned long long)sh->sector, i);
- set_bit(R5_LOCKED, &dev->flags);
- set_bit(R5_Wantread, &dev->flags);
- s->locked++;
- } else {
- pr_debug("Request delayed stripe %llu "
- "block %d for Reconstruct\n",
- (unsigned long long)sh->sector, i);
- set_bit(STRIPE_DELAYED, &sh->state);
- set_bit(STRIPE_HANDLE, &sh->state);
- }
- }
- }
- /* now if nothing is locked, and if we have enough data, we can start a
- * write request
- */
- if ((s->req_compute || !test_bit(STRIPE_COMPUTE_RUN, &sh->state)) &&
- s->locked == 0 && rcw == 0 &&
- !test_bit(STRIPE_BIT_DELAY, &sh->state)) {
- schedule_reconstruction(sh, s, 1, 0);
- }
-}
-
-static void handle_parity_checks5(raid5_conf_t *conf, struct stripe_head *sh,
+static void handle_parity_checks5(struct r5conf *conf, struct stripe_head *sh,
struct stripe_head_state *s, int disks)
{
struct r5dev *dev = NULL;
s->uptodate--;
break;
}
- dev = &sh->dev[s->failed_num];
+ dev = &sh->dev[s->failed_num[0]];
/* fall through */
case check_state_compute_result:
sh->check_state = check_state_idle;
}
-static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
+static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh,
struct stripe_head_state *s,
- struct r6_state *r6s, int disks)
+ int disks)
{
int pd_idx = sh->pd_idx;
int qd_idx = sh->qd_idx;
switch (sh->check_state) {
case check_state_idle:
/* start a new check operation if there are < 2 failures */
- if (s->failed == r6s->q_failed) {
+ if (s->failed == s->q_failed) {
/* The only possible failed device holds Q, so it
* makes sense to check P (If anything else were failed,
* we would have used P to recreate it).
*/
sh->check_state = check_state_run;
}
- if (!r6s->q_failed && s->failed < 2) {
+ if (!s->q_failed && s->failed < 2) {
/* Q is not failed, and we didn't use it to generate
* anything, so it makes sense to check it
*/
*/
BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */
if (s->failed == 2) {
- dev = &sh->dev[r6s->failed_num[1]];
+ dev = &sh->dev[s->failed_num[1]];
s->locked++;
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
}
if (s->failed >= 1) {
- dev = &sh->dev[r6s->failed_num[0]];
+ dev = &sh->dev[s->failed_num[0]];
s->locked++;
set_bit(R5_LOCKED, &dev->flags);
set_bit(R5_Wantwrite, &dev->flags);
}
}
-static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
- struct r6_state *r6s)
+static void handle_stripe_expansion(struct r5conf *conf, struct stripe_head *sh)
{
int i;
set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
for (j = 0; j < conf->raid_disks; j++)
if (j != sh2->pd_idx &&
- (!r6s || j != sh2->qd_idx) &&
+ j != sh2->qd_idx &&
!test_bit(R5_Expanded, &sh2->dev[j].flags))
break;
if (j == conf->raid_disks) {
*
*/
-static void handle_stripe5(struct stripe_head *sh)
+static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
{
- raid5_conf_t *conf = sh->raid_conf;
- int disks = sh->disks, i;
- struct bio *return_bi = NULL;
- struct stripe_head_state s;
+ struct r5conf *conf = sh->raid_conf;
+ int disks = sh->disks;
struct r5dev *dev;
- mdk_rdev_t *blocked_rdev = NULL;
- int prexor;
- int dec_preread_active = 0;
+ int i;
- memset(&s, 0, sizeof(s));
- 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);
+ memset(s, 0, sizeof(*s));
- spin_lock(&sh->lock);
- clear_bit(STRIPE_HANDLE, &sh->state);
- clear_bit(STRIPE_DELAYED, &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);
+ 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);
+ s->failed_num[0] = -1;
+ s->failed_num[1] = -1;
/* Now to look around and see what can be done */
rcu_read_lock();
+ spin_lock_irq(&conf->device_lock);
for (i=disks; i--; ) {
- mdk_rdev_t *rdev;
+ struct md_rdev *rdev;
+ sector_t first_bad;
+ int bad_sectors;
+ int is_bad = 0;
dev = &sh->dev[i];
- 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
+ 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
*
* new wantfill requests are only permitted while
* ops_complete_biofill is guaranteed to be inactive
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 (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++;
+ BUG_ON(s->compute > 2);
+ }
if (test_bit(R5_Wantfill, &dev->flags))
- s.to_fill++;
+ s->to_fill++;
else if (dev->toread)
- s.to_read++;
+ s->to_read++;
if (dev->towrite) {
- s.to_write++;
+ s->to_write++;
if (!test_bit(R5_OVERWRITE, &dev->flags))
- s.non_overwrite++;
+ s->non_overwrite++;
}
if (dev->written)
- s.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) {
+ is_bad = is_badblock(rdev, sh->sector, STRIPE_SECTORS,
+ &first_bad, &bad_sectors);
+ if (s->blocked_rdev == NULL
+ && (test_bit(Blocked, &rdev->flags)
+ || is_bad < 0)) {
+ if (is_bad < 0)
+ set_bit(BlockedBadBlocks,
+ &rdev->flags);
+ s->blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
+ }
}
clear_bit(R5_Insync, &dev->flags);
if (!rdev)
/* Not in-sync */;
- else if (test_bit(In_sync, &rdev->flags))
+ else if (is_bad) {
+ /* also not in-sync */
+ if (!test_bit(WriteErrorSeen, &rdev->flags)) {
+ /* treat as in-sync, but with a read error
+ * which we can now try to correct
+ */
+ set_bit(R5_Insync, &dev->flags);
+ set_bit(R5_ReadError, &dev->flags);
+ }
+ } else if (test_bit(In_sync, &rdev->flags))
set_bit(R5_Insync, &dev->flags);
- else {
- /* could be in-sync depending on recovery/reshape status */
+ else if (!test_bit(Faulty, &rdev->flags)) {
+ /* in sync if before recovery_offset */
if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
set_bit(R5_Insync, &dev->flags);
}
+ if (test_bit(R5_WriteError, &dev->flags)) {
+ clear_bit(R5_Insync, &dev->flags);
+ if (!test_bit(Faulty, &rdev->flags)) {
+ s->handle_bad_blocks = 1;
+ atomic_inc(&rdev->nr_pending);
+ } else
+ clear_bit(R5_WriteError, &dev->flags);
+ }
+ if (test_bit(R5_MadeGood, &dev->flags)) {
+ if (!test_bit(Faulty, &rdev->flags)) {
+ s->handle_bad_blocks = 1;
+ atomic_inc(&rdev->nr_pending);
+ } else
+ clear_bit(R5_MadeGood, &dev->flags);
+ }
if (!test_bit(R5_Insync, &dev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
if (test_bit(R5_ReadError, &dev->flags))
clear_bit(R5_Insync, &dev->flags);
if (!test_bit(R5_Insync, &dev->flags)) {
- s.failed++;
- s.failed_num = i;
+ if (s->failed < 2)
+ s->failed_num[s->failed] = i;
+ s->failed++;
}
}
+ spin_unlock_irq(&conf->device_lock);
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,
- s.failed, s.failed_num);
- /* check if the array has lost two devices and, if so, some requests might
- * need to be failed
- */
- if (s.failed > 1 && s.to_read+s.to_write+s.written)
- 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);
- s.syncing = 0;
- }
-
- /* might be able to return some write requests if the parity block
- * is safe, or on a failed drive
- */
- dev = &sh->dev[sh->pd_idx];
- if ( s.written &&
- ((test_bit(R5_Insync, &dev->flags) &&
- !test_bit(R5_LOCKED, &dev->flags) &&
- test_bit(R5_UPTODATE, &dev->flags)) ||
- (s.failed == 1 && s.failed_num == sh->pd_idx)))
- 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 + s.compute < disks)) || s.expanding)
- handle_stripe_fill5(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))
- dec_preread_active = 1;
- }
-
- /* 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. The parity check is held off while parity
- * dependent operations are in flight.
- */
- 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 the failed drive is just a ReadError, then we might need to progress
- * the repair/check process
- */
- if (s.failed == 1 && !conf->mddev->ro &&
- test_bit(R5_ReadError, &sh->dev[s.failed_num].flags)
- && !test_bit(R5_LOCKED, &sh->dev[s.failed_num].flags)
- && test_bit(R5_UPTODATE, &sh->dev[s.failed_num].flags)
- ) {
- dev = &sh->dev[s.failed_num];
- if (!test_bit(R5_ReWrite, &dev->flags)) {
- set_bit(R5_Wantwrite, &dev->flags);
- set_bit(R5_ReWrite, &dev->flags);
- set_bit(R5_LOCKED, &dev->flags);
- s.locked++;
- } else {
- /* let's read it back */
- set_bit(R5_Wantread, &dev->flags);
- set_bit(R5_LOCKED, &dev->flags);
- s.locked++;
- }
- }
-
- /* Finish reconstruct operations initiated by the expansion process */
- if (sh->reconstruct_state == reconstruct_state_result) {
- struct stripe_head *sh2
- = get_active_stripe(conf, sh->sector, 1, 1, 1);
- if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
- /* sh cannot be written until sh2 has been read.
- * so arrange for sh to be delayed a little
- */
- set_bit(STRIPE_DELAYED, &sh->state);
- set_bit(STRIPE_HANDLE, &sh->state);
- if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
- &sh2->state))
- atomic_inc(&conf->preread_active_stripes);
- release_stripe(sh2);
- goto unlock;
- }
- if (sh2)
- release_stripe(sh2);
-
- 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++;
- }
- }
+static void handle_stripe(struct stripe_head *sh)
+{
+ struct stripe_head_state s;
+ struct r5conf *conf = sh->raid_conf;
+ int i;
+ int prexor;
+ int disks = sh->disks;
+ struct r5dev *pdev, *qdev;
- 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_reconstruction(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);
+ clear_bit(STRIPE_HANDLE, &sh->state);
+ if (test_and_set_bit(STRIPE_ACTIVE, &sh->state)) {
+ /* already being handled, ensure it gets handled
+ * again when current action finishes */
+ set_bit(STRIPE_HANDLE, &sh->state);
+ return;
}
- if (s.expanding && s.locked == 0 &&
- !test_bit(STRIPE_COMPUTE_RUN, &sh->state))
- handle_stripe_expansion(conf, sh, NULL);
-
- unlock:
- spin_unlock(&sh->lock);
-
- /* wait for this device to become unblocked */
- if (unlikely(blocked_rdev))
- md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
-
- if (s.ops_request)
- raid_run_ops(sh, s.ops_request);
-
- ops_run_io(sh, &s);
-
- if (dec_preread_active) {
- /* We delay this until after ops_run_io so that if make_request
- * is waiting on a flush, it won't continue until the writes
- * have actually been submitted.
- */
- atomic_dec(&conf->preread_active_stripes);
- if (atomic_read(&conf->preread_active_stripes) <
- IO_THRESHOLD)
- md_wakeup_thread(conf->mddev->thread);
+ if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
+ set_bit(STRIPE_SYNCING, &sh->state);
+ clear_bit(STRIPE_INSYNC, &sh->state);
}
- return_io(return_bi);
-}
-
-static void handle_stripe6(struct stripe_head *sh)
-{
- raid5_conf_t *conf = sh->raid_conf;
- int disks = sh->disks;
- struct bio *return_bi = NULL;
- int i, pd_idx = sh->pd_idx, qd_idx = sh->qd_idx;
- struct stripe_head_state s;
- struct r6_state r6s;
- struct r5dev *dev, *pdev, *qdev;
- mdk_rdev_t *blocked_rdev = NULL;
- int dec_preread_active = 0;
+ clear_bit(STRIPE_DELAYED, &sh->state);
pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
"pd_idx=%d, qd_idx=%d\n, check:%d, reconstruct:%d\n",
(unsigned long long)sh->sector, sh->state,
- atomic_read(&sh->count), pd_idx, qd_idx,
+ atomic_read(&sh->count), sh->pd_idx, sh->qd_idx,
sh->check_state, sh->reconstruct_state);
- memset(&s, 0, sizeof(s));
-
- spin_lock(&sh->lock);
- clear_bit(STRIPE_HANDLE, &sh->state);
- clear_bit(STRIPE_DELAYED, &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 */
-
- rcu_read_lock();
- for (i=disks; i--; ) {
- mdk_rdev_t *rdev;
- dev = &sh->dev[i];
- 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
- *
- * 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);
+ analyse_stripe(sh, &s);
- /* 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++;
- BUG_ON(s.compute > 2);
- }
-
- if (test_bit(R5_Wantfill, &dev->flags)) {
- s.to_fill++;
- } else if (dev->toread)
- s.to_read++;
- if (dev->towrite) {
- s.to_write++;
- if (!test_bit(R5_OVERWRITE, &dev->flags))
- s.non_overwrite++;
- }
- 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);
- }
- clear_bit(R5_Insync, &dev->flags);
- if (!rdev)
- /* Not in-sync */;
- else if (test_bit(In_sync, &rdev->flags))
- set_bit(R5_Insync, &dev->flags);
- else {
- /* in sync if before recovery_offset */
- if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
- set_bit(R5_Insync, &dev->flags);
- }
- if (!test_bit(R5_Insync, &dev->flags)) {
- /* The ReadError flag will just be confusing now */
- clear_bit(R5_ReadError, &dev->flags);
- clear_bit(R5_ReWrite, &dev->flags);
- }
- if (test_bit(R5_ReadError, &dev->flags))
- clear_bit(R5_Insync, &dev->flags);
- if (!test_bit(R5_Insync, &dev->flags)) {
- if (s.failed < 2)
- r6s.failed_num[s.failed] = i;
- s.failed++;
- }
+ if (s.handle_bad_blocks) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto finish;
}
- rcu_read_unlock();
- if (unlikely(blocked_rdev)) {
+ if (unlikely(s.blocked_rdev)) {
if (s.syncing || s.expanding || s.expanded ||
s.to_write || s.written) {
set_bit(STRIPE_HANDLE, &sh->state);
- goto unlock;
+ goto finish;
}
/* There is nothing for the blocked_rdev to block */
- rdev_dec_pending(blocked_rdev, conf->mddev);
- blocked_rdev = NULL;
+ rdev_dec_pending(s.blocked_rdev, conf->mddev);
+ s.blocked_rdev = NULL;
}
if (s.to_fill && !test_bit(STRIPE_BIOFILL_RUN, &sh->state)) {
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,
- r6s.failed_num[0], r6s.failed_num[1]);
- /* check if the array has lost >2 devices and, if so, some requests
- * might need to be failed
+ s.failed_num[0], s.failed_num[1]);
+ /* check if the array has lost more than max_degraded devices and,
+ * if so, some requests might need to be failed.
*/
- if (s.failed > 2 && s.to_read+s.to_write+s.written)
- 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);
- s.syncing = 0;
- }
+ if (s.failed > conf->max_degraded && s.to_read+s.to_write+s.written)
+ handle_failed_stripe(conf, sh, &s, disks, &s.return_bi);
+ if (s.failed > conf->max_degraded && s.syncing)
+ handle_failed_sync(conf, sh, &s);
/*
* might be able to return some write requests if the parity blocks
* are safe, or on a failed drive
*/
- pdev = &sh->dev[pd_idx];
- r6s.p_failed = (s.failed >= 1 && r6s.failed_num[0] == pd_idx)
- || (s.failed >= 2 && r6s.failed_num[1] == pd_idx);
- qdev = &sh->dev[qd_idx];
- r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == qd_idx)
- || (s.failed >= 2 && r6s.failed_num[1] == qd_idx);
-
- if ( s.written &&
- ( r6s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
+ pdev = &sh->dev[sh->pd_idx];
+ s.p_failed = (s.failed >= 1 && s.failed_num[0] == sh->pd_idx)
+ || (s.failed >= 2 && s.failed_num[1] == sh->pd_idx);
+ qdev = &sh->dev[sh->qd_idx];
+ s.q_failed = (s.failed >= 1 && s.failed_num[0] == sh->qd_idx)
+ || (s.failed >= 2 && s.failed_num[1] == sh->qd_idx)
+ || conf->level < 6;
+
+ if (s.written &&
+ (s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
&& !test_bit(R5_LOCKED, &pdev->flags)
&& test_bit(R5_UPTODATE, &pdev->flags)))) &&
- ( r6s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
+ (s.q_failed || ((test_bit(R5_Insync, &qdev->flags)
&& !test_bit(R5_LOCKED, &qdev->flags)
&& test_bit(R5_UPTODATE, &qdev->flags)))))
- handle_stripe_clean_event(conf, sh, disks, &return_bi);
+ handle_stripe_clean_event(conf, sh, disks, &s.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.to_write && s.failed) ||
- (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
- handle_stripe_fill6(sh, &s, &r6s, disks);
+ if (s.to_read || s.non_overwrite
+ || (conf->level == 6 && s.to_write && s.failed)
+ || (s.syncing && (s.uptodate + s.compute < disks)) || s.expanding)
+ handle_stripe_fill(sh, &s, disks);
/* Now we check to see if any write operations have recently
* completed
*/
- if (sh->reconstruct_state == reconstruct_state_drain_result) {
-
+ 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 blocks are ready to
+
+ /* 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));
- BUG_ON(!test_bit(R5_UPTODATE, &sh->dev[qd_idx].flags));
+ BUG_ON(sh->qd_idx >= 0 &&
+ !test_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags));
for (i = disks; i--; ) {
- dev = &sh->dev[i];
+ struct r5dev *dev = &sh->dev[i];
if (test_bit(R5_LOCKED, &dev->flags) &&
- (i == sh->pd_idx || i == qd_idx ||
- dev->written)) {
+ (i == sh->pd_idx || i == sh->qd_idx ||
+ dev->written)) {
pr_debug("Writing block %d\n", i);
- BUG_ON(!test_bit(R5_UPTODATE, &dev->flags));
set_bit(R5_Wantwrite, &dev->flags);
+ if (prexor)
+ continue;
if (!test_bit(R5_Insync, &dev->flags) ||
- ((i == sh->pd_idx || i == qd_idx) &&
- s.failed == 0))
+ ((i == sh->pd_idx || i == sh->qd_idx) &&
+ s.failed == 0))
set_bit(STRIPE_INSYNC, &sh->state);
}
}
if (test_and_clear_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
- dec_preread_active = 1;
+ s.dec_preread_active = 1;
}
/* 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+gen_syndrome) is already in flight.
+ * 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_dirtying6(conf, sh, &s, &r6s, disks);
+ handle_stripe_dirtying(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
if (sh->check_state ||
(s.syncing && s.locked == 0 &&
!test_bit(STRIPE_COMPUTE_RUN, &sh->state) &&
- !test_bit(STRIPE_INSYNC, &sh->state)))
- handle_parity_checks6(conf, sh, &s, &r6s, disks);
+ !test_bit(STRIPE_INSYNC, &sh->state))) {
+ if (conf->level == 6)
+ handle_parity_checks6(conf, sh, &s, disks);
+ else
+ 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);
+ md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
clear_bit(STRIPE_SYNCING, &sh->state);
}
/* If the failed drives are just a ReadError, then we might need
* to progress the repair/check process
*/
- if (s.failed <= 2 && !conf->mddev->ro)
+ if (s.failed <= conf->max_degraded && !conf->mddev->ro)
for (i = 0; i < s.failed; i++) {
- dev = &sh->dev[r6s.failed_num[i]];
+ struct r5dev *dev = &sh->dev[s.failed_num[i]];
if (test_bit(R5_ReadError, &dev->flags)
&& !test_bit(R5_LOCKED, &dev->flags)
&& test_bit(R5_UPTODATE, &dev->flags)
}
}
+
/* Finish reconstruct operations initiated by the expansion process */
if (sh->reconstruct_state == reconstruct_state_result) {
+ struct stripe_head *sh_src
+ = get_active_stripe(conf, sh->sector, 1, 1, 1);
+ if (sh_src && test_bit(STRIPE_EXPAND_SOURCE, &sh_src->state)) {
+ /* sh cannot be written until sh_src has been read.
+ * so arrange for sh to be delayed a little
+ */
+ set_bit(STRIPE_DELAYED, &sh->state);
+ set_bit(STRIPE_HANDLE, &sh->state);
+ if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
+ &sh_src->state))
+ atomic_inc(&conf->preread_active_stripes);
+ release_stripe(sh_src);
+ goto finish;
+ }
+ if (sh_src)
+ release_stripe(sh_src);
+
sh->reconstruct_state = reconstruct_state_idle;
clear_bit(STRIPE_EXPANDING, &sh->state);
for (i = conf->raid_disks; i--; ) {
if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state) &&
!sh->reconstruct_state) {
- struct stripe_head *sh2
- = get_active_stripe(conf, sh->sector, 1, 1, 1);
- if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
- /* sh cannot be written until sh2 has been read.
- * so arrange for sh to be delayed a little
- */
- set_bit(STRIPE_DELAYED, &sh->state);
- set_bit(STRIPE_HANDLE, &sh->state);
- if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
- &sh2->state))
- atomic_inc(&conf->preread_active_stripes);
- release_stripe(sh2);
- goto unlock;
- }
- if (sh2)
- release_stripe(sh2);
-
- /* Need to write out all blocks after computing P&Q */
+ /* Need to write out all blocks after computing parity */
sh->disks = conf->raid_disks;
stripe_set_idx(sh->sector, conf, 0, sh);
schedule_reconstruction(sh, &s, 1, 1);
if (s.expanding && s.locked == 0 &&
!test_bit(STRIPE_COMPUTE_RUN, &sh->state))
- handle_stripe_expansion(conf, sh, &r6s);
-
- unlock:
- spin_unlock(&sh->lock);
+ handle_stripe_expansion(conf, sh);
+finish:
/* wait for this device to become unblocked */
- if (unlikely(blocked_rdev))
- md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+ if (conf->mddev->external && unlikely(s.blocked_rdev))
+ md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev);
+
+ if (s.handle_bad_blocks)
+ for (i = disks; i--; ) {
+ struct md_rdev *rdev;
+ struct r5dev *dev = &sh->dev[i];
+ if (test_and_clear_bit(R5_WriteError, &dev->flags)) {
+ /* We own a safe reference to the rdev */
+ rdev = conf->disks[i].rdev;
+ if (!rdev_set_badblocks(rdev, sh->sector,
+ STRIPE_SECTORS, 0))
+ md_error(conf->mddev, rdev);
+ rdev_dec_pending(rdev, conf->mddev);
+ }
+ if (test_and_clear_bit(R5_MadeGood, &dev->flags)) {
+ rdev = conf->disks[i].rdev;
+ rdev_clear_badblocks(rdev, sh->sector,
+ STRIPE_SECTORS);
+ rdev_dec_pending(rdev, conf->mddev);
+ }
+ }
if (s.ops_request)
raid_run_ops(sh, s.ops_request);
ops_run_io(sh, &s);
-
- if (dec_preread_active) {
+ if (s.dec_preread_active) {
/* We delay this until after ops_run_io so that if make_request
* is waiting on a flush, it won't continue until the writes
* have actually been submitted.
md_wakeup_thread(conf->mddev->thread);
}
- return_io(return_bi);
-}
+ return_io(s.return_bi);
-static void handle_stripe(struct stripe_head *sh)
-{
- if (sh->raid_conf->level == 6)
- handle_stripe6(sh);
- else
- handle_stripe5(sh);
+ clear_bit(STRIPE_ACTIVE, &sh->state);
}
-static void raid5_activate_delayed(raid5_conf_t *conf)
+static void raid5_activate_delayed(struct r5conf *conf)
{
if (atomic_read(&conf->preread_active_stripes) < IO_THRESHOLD) {
while (!list_empty(&conf->delayed_list)) {
}
}
-static void activate_bit_delay(raid5_conf_t *conf)
+static void activate_bit_delay(struct r5conf *conf)
{
/* device_lock is held */
struct list_head head;
}
}
-int md_raid5_congested(mddev_t *mddev, int bits)
+int md_raid5_congested(struct mddev *mddev, int bits)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
/* No difference between reads and writes. Just check
* how busy the stripe_cache is
static int raid5_congested(void *data, int bits)
{
- mddev_t *mddev = data;
+ struct mddev *mddev = data;
return mddev_congested(mddev, bits) ||
md_raid5_congested(mddev, bits);
struct bvec_merge_data *bvm,
struct bio_vec *biovec)
{
- mddev_t *mddev = q->queuedata;
+ struct mddev *mddev = q->queuedata;
sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
int max;
unsigned int chunk_sectors = mddev->chunk_sectors;
}
-static int in_chunk_boundary(mddev_t *mddev, struct bio *bio)
+static int in_chunk_boundary(struct mddev *mddev, struct bio *bio)
{
sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
unsigned int chunk_sectors = mddev->chunk_sectors;
* add bio to the retry LIFO ( in O(1) ... we are in interrupt )
* later sampled by raid5d.
*/
-static void add_bio_to_retry(struct bio *bi,raid5_conf_t *conf)
+static void add_bio_to_retry(struct bio *bi,struct r5conf *conf)
{
unsigned long flags;
}
-static struct bio *remove_bio_from_retry(raid5_conf_t *conf)
+static struct bio *remove_bio_from_retry(struct r5conf *conf)
{
struct bio *bi;
static void raid5_align_endio(struct bio *bi, int error)
{
struct bio* raid_bi = bi->bi_private;
- mddev_t *mddev;
- raid5_conf_t *conf;
+ struct mddev *mddev;
+ struct r5conf *conf;
int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
- mdk_rdev_t *rdev;
+ struct md_rdev *rdev;
bio_put(bi);
}
-static int chunk_aligned_read(mddev_t *mddev, struct bio * raid_bio)
+static int chunk_aligned_read(struct mddev *mddev, struct bio * raid_bio)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
int dd_idx;
struct bio* align_bi;
- mdk_rdev_t *rdev;
+ struct md_rdev *rdev;
if (!in_chunk_boundary(mddev, raid_bio)) {
pr_debug("chunk_aligned_read : non aligned\n");
rcu_read_lock();
rdev = rcu_dereference(conf->disks[dd_idx].rdev);
if (rdev && test_bit(In_sync, &rdev->flags)) {
+ sector_t first_bad;
+ int bad_sectors;
+
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
raid_bio->bi_next = (void*)rdev;
align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
align_bi->bi_sector += rdev->data_offset;
- if (!bio_fits_rdev(align_bi)) {
- /* too big in some way */
+ if (!bio_fits_rdev(align_bi) ||
+ is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9,
+ &first_bad, &bad_sectors)) {
+ /* too big in some way, or has a known bad block */
bio_put(align_bi);
rdev_dec_pending(rdev, mddev);
return 0;
* 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)
+static struct stripe_head *__get_priority_stripe(struct r5conf *conf)
{
struct stripe_head *sh;
return sh;
}
-static int make_request(mddev_t *mddev, struct bio * bi)
+static int make_request(struct mddev *mddev, struct bio * bi)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
int dd_idx;
sector_t new_sector;
sector_t logical_sector, last_sector;
}
}
- if (bio_data_dir(bi) == WRITE &&
+ if (rw == WRITE &&
logical_sector >= mddev->suspend_lo &&
logical_sector < mddev->suspend_hi) {
release_stripe(sh);
}
if (test_bit(STRIPE_EXPANDING, &sh->state) ||
- !add_stripe_bio(sh, bi, dd_idx, (bi->bi_rw&RW_MASK))) {
+ !add_stripe_bio(sh, bi, dd_idx, rw)) {
/* Stripe is busy expanding or
* add failed due to overlap. Flush everything
* and wait a while
return 0;
}
-static sector_t raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks);
+static sector_t raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks);
-static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped)
+static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *skipped)
{
/* reshaping is quite different to recovery/resync so it is
* handled quite separately ... here.
* As the reads complete, handle_stripe will copy the data
* into the destination stripe and release that stripe.
*/
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
struct stripe_head *sh;
sector_t first_sector, last_sector;
int raid_disks = conf->previous_raid_disks;
}
/* FIXME go_faster isn't used */
-static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
+static inline sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
struct stripe_head *sh;
sector_t max_sector = mddev->dev_sectors;
sector_t sync_blocks;
bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, still_degraded);
- spin_lock(&sh->lock);
- set_bit(STRIPE_SYNCING, &sh->state);
- clear_bit(STRIPE_INSYNC, &sh->state);
- spin_unlock(&sh->lock);
+ set_bit(STRIPE_SYNC_REQUESTED, &sh->state);
handle_stripe(sh);
release_stripe(sh);
return STRIPE_SECTORS;
}
-static int retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
+static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio)
{
/* We may not be able to submit a whole bio at once as there
* may not be enough stripe_heads available.
* 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(struct mddev *mddev)
{
struct stripe_head *sh;
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
int handled;
struct blk_plug plug;
release_stripe(sh);
cond_resched();
+ if (mddev->flags & ~(1<<MD_CHANGE_PENDING))
+ md_check_recovery(mddev);
+
spin_lock_irq(&conf->device_lock);
}
pr_debug("%d stripes handled\n", handled);
}
static ssize_t
-raid5_show_stripe_cache_size(mddev_t *mddev, char *page)
+raid5_show_stripe_cache_size(struct mddev *mddev, char *page)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
if (conf)
return sprintf(page, "%d\n", conf->max_nr_stripes);
else
}
int
-raid5_set_cache_size(mddev_t *mddev, int size)
+raid5_set_cache_size(struct mddev *mddev, int size)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
int err;
if (size <= 16 || size > 32768)
EXPORT_SYMBOL(raid5_set_cache_size);
static ssize_t
-raid5_store_stripe_cache_size(mddev_t *mddev, const char *page, size_t len)
+raid5_store_stripe_cache_size(struct mddev *mddev, const char *page, size_t len)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
unsigned long new;
int err;
raid5_store_stripe_cache_size);
static ssize_t
-raid5_show_preread_threshold(mddev_t *mddev, char *page)
+raid5_show_preread_threshold(struct mddev *mddev, char *page)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
if (conf)
return sprintf(page, "%d\n", conf->bypass_threshold);
else
}
static ssize_t
-raid5_store_preread_threshold(mddev_t *mddev, const char *page, size_t len)
+raid5_store_preread_threshold(struct mddev *mddev, const char *page, size_t len)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
unsigned long new;
if (len >= PAGE_SIZE)
return -EINVAL;
raid5_store_preread_threshold);
static ssize_t
-stripe_cache_active_show(mddev_t *mddev, char *page)
+stripe_cache_active_show(struct mddev *mddev, char *page)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
if (conf)
return sprintf(page, "%d\n", atomic_read(&conf->active_stripes));
else
};
static sector_t
-raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+raid5_size(struct mddev *mddev, sector_t sectors, int raid_disks)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
if (!sectors)
sectors = mddev->dev_sectors;
return sectors * (raid_disks - conf->max_degraded);
}
-static void raid5_free_percpu(raid5_conf_t *conf)
+static void raid5_free_percpu(struct r5conf *conf)
{
struct raid5_percpu *percpu;
unsigned long cpu;
free_percpu(conf->percpu);
}
-static void free_conf(raid5_conf_t *conf)
+static void free_conf(struct r5conf *conf)
{
shrink_stripes(conf);
raid5_free_percpu(conf);
static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
void *hcpu)
{
- raid5_conf_t *conf = container_of(nfb, raid5_conf_t, cpu_notify);
+ struct r5conf *conf = container_of(nfb, struct r5conf, cpu_notify);
long cpu = (long)hcpu;
struct raid5_percpu *percpu = per_cpu_ptr(conf->percpu, cpu);
}
#endif
-static int raid5_alloc_percpu(raid5_conf_t *conf)
+static int raid5_alloc_percpu(struct r5conf *conf)
{
unsigned long cpu;
struct page *spare_page;
return err;
}
-static raid5_conf_t *setup_conf(mddev_t *mddev)
+static struct r5conf *setup_conf(struct mddev *mddev)
{
- raid5_conf_t *conf;
+ struct r5conf *conf;
int raid_disk, memory, max_disks;
- mdk_rdev_t *rdev;
+ struct md_rdev *rdev;
struct disk_info *disk;
if (mddev->new_level != 5
return ERR_PTR(-EINVAL);
}
- conf = kzalloc(sizeof(raid5_conf_t), GFP_KERNEL);
+ conf = kzalloc(sizeof(struct r5conf), GFP_KERNEL);
if (conf == NULL)
goto abort;
spin_lock_init(&conf->device_lock);
atomic_set(&conf->preread_active_stripes, 0);
atomic_set(&conf->active_aligned_reads, 0);
conf->bypass_threshold = BYPASS_THRESHOLD;
+ conf->recovery_disabled = mddev->recovery_disabled - 1;
conf->raid_disks = mddev->raid_disks;
if (mddev->reshape_position == MaxSector)
return 0;
}
-static int run(mddev_t *mddev)
+static int run(struct mddev *mddev)
{
- raid5_conf_t *conf;
+ struct r5conf *conf;
int working_disks = 0;
int dirty_parity_disks = 0;
- mdk_rdev_t *rdev;
+ struct md_rdev *rdev;
sector_t reshape_offset = 0;
if (mddev->recovery_cp != MaxSector)
return 0;
abort:
- md_unregister_thread(mddev->thread);
- mddev->thread = NULL;
- if (conf) {
- print_raid5_conf(conf);
- free_conf(conf);
- }
+ md_unregister_thread(&mddev->thread);
+ print_raid5_conf(conf);
+ free_conf(conf);
mddev->private = NULL;
printk(KERN_ALERT "md/raid:%s: failed to run raid set.\n", mdname(mddev));
return -EIO;
}
-static int stop(mddev_t *mddev)
+static int stop(struct mddev *mddev)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
- md_unregister_thread(mddev->thread);
- mddev->thread = NULL;
+ md_unregister_thread(&mddev->thread);
if (mddev->queue)
mddev->queue->backing_dev_info.congested_fn = NULL;
free_conf(conf);
return 0;
}
-#ifdef DEBUG
-static void print_sh(struct seq_file *seq, struct stripe_head *sh)
-{
- int i;
-
- seq_printf(seq, "sh %llu, pd_idx %d, state %ld.\n",
- (unsigned long long)sh->sector, sh->pd_idx, sh->state);
- seq_printf(seq, "sh %llu, count %d.\n",
- (unsigned long long)sh->sector, atomic_read(&sh->count));
- seq_printf(seq, "sh %llu, ", (unsigned long long)sh->sector);
- for (i = 0; i < sh->disks; i++) {
- seq_printf(seq, "(cache%d: %p %ld) ",
- i, sh->dev[i].page, sh->dev[i].flags);
- }
- seq_printf(seq, "\n");
-}
-
-static void printall(struct seq_file *seq, raid5_conf_t *conf)
-{
- struct stripe_head *sh;
- struct hlist_node *hn;
- int i;
-
- spin_lock_irq(&conf->device_lock);
- for (i = 0; i < NR_HASH; i++) {
- hlist_for_each_entry(sh, hn, &conf->stripe_hashtbl[i], hash) {
- if (sh->raid_conf != conf)
- continue;
- print_sh(seq, sh);
- }
- }
- spin_unlock_irq(&conf->device_lock);
-}
-#endif
-
-static void status(struct seq_file *seq, mddev_t *mddev)
+static void status(struct seq_file *seq, struct mddev *mddev)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
int i;
seq_printf(seq, " level %d, %dk chunk, algorithm %d", mddev->level,
conf->disks[i].rdev &&
test_bit(In_sync, &conf->disks[i].rdev->flags) ? "U" : "_");
seq_printf (seq, "]");
-#ifdef DEBUG
- seq_printf (seq, "\n");
- printall(seq, conf);
-#endif
}
-static void print_raid5_conf (raid5_conf_t *conf)
+static void print_raid5_conf (struct r5conf *conf)
{
int i;
struct disk_info *tmp;
}
}
-static int raid5_spare_active(mddev_t *mddev)
+static int raid5_spare_active(struct mddev *mddev)
{
int i;
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
struct disk_info *tmp;
int count = 0;
unsigned long flags;
return count;
}
-static int raid5_remove_disk(mddev_t *mddev, int number)
+static int raid5_remove_disk(struct mddev *mddev, int number)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
int err = 0;
- mdk_rdev_t *rdev;
+ struct md_rdev *rdev;
struct disk_info *p = conf->disks + number;
print_raid5_conf(conf);
* isn't possible.
*/
if (!test_bit(Faulty, &rdev->flags) &&
+ mddev->recovery_disabled != conf->recovery_disabled &&
!has_failed(conf) &&
number < conf->raid_disks) {
err = -EBUSY;
return err;
}
-static int raid5_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
+static int raid5_add_disk(struct mddev *mddev, struct md_rdev *rdev)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
int err = -EEXIST;
int disk;
struct disk_info *p;
int first = 0;
int last = conf->raid_disks - 1;
+ if (mddev->recovery_disabled == conf->recovery_disabled)
+ return -EBUSY;
+
if (has_failed(conf))
/* no point adding a device */
return -EINVAL;
return err;
}
-static int raid5_resize(mddev_t *mddev, sector_t sectors)
+static int raid5_resize(struct mddev *mddev, sector_t sectors)
{
/* no resync is happening, and there is enough space
* on all devices, so we can resize.
return 0;
}
-static int check_stripe_cache(mddev_t *mddev)
+static int check_stripe_cache(struct mddev *mddev)
{
/* Can only proceed if there are plenty of stripe_heads.
* We need a minimum of one full stripe,, and for sensible progress
* If the chunk size is greater, user-space should request more
* stripe_heads first.
*/
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
if (((mddev->chunk_sectors << 9) / STRIPE_SIZE) * 4
> conf->max_nr_stripes ||
((mddev->new_chunk_sectors << 9) / STRIPE_SIZE) * 4
return 1;
}
-static int check_reshape(mddev_t *mddev)
+static int check_reshape(struct mddev *mddev)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
if (mddev->delta_disks == 0 &&
mddev->new_layout == mddev->layout &&
return resize_stripes(conf, conf->raid_disks + mddev->delta_disks);
}
-static int raid5_start_reshape(mddev_t *mddev)
+static int raid5_start_reshape(struct mddev *mddev)
{
- raid5_conf_t *conf = mddev->private;
- mdk_rdev_t *rdev;
+ struct r5conf *conf = mddev->private;
+ struct md_rdev *rdev;
int spares = 0;
unsigned long flags;
if (rdev->raid_disk < 0 &&
!test_bit(Faulty, &rdev->flags)) {
if (raid5_add_disk(mddev, rdev) == 0) {
- char nm[20];
if (rdev->raid_disk
>= conf->previous_raid_disks) {
set_bit(In_sync, &rdev->flags);
added_devices++;
} else
rdev->recovery_offset = 0;
- sprintf(nm, "rd%d", rdev->raid_disk);
- if (sysfs_create_link(&mddev->kobj,
- &rdev->kobj, nm))
+
+ if (sysfs_link_rdev(mddev, rdev))
/* Failure here is OK */;
}
} else if (rdev->raid_disk >= conf->previous_raid_disks
/* This is called from the reshape thread and should make any
* changes needed in 'conf'
*/
-static void end_reshape(raid5_conf_t *conf)
+static void end_reshape(struct r5conf *conf)
{
if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
/* This is called from the raid5d thread with mddev_lock held.
* It makes config changes to the device.
*/
-static void raid5_finish_reshape(mddev_t *mddev)
+static void raid5_finish_reshape(struct mddev *mddev)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
for (d = conf->raid_disks ;
d < conf->raid_disks - mddev->delta_disks;
d++) {
- mdk_rdev_t *rdev = conf->disks[d].rdev;
+ struct md_rdev *rdev = conf->disks[d].rdev;
if (rdev && raid5_remove_disk(mddev, d) == 0) {
- char nm[20];
- sprintf(nm, "rd%d", rdev->raid_disk);
- sysfs_remove_link(&mddev->kobj, nm);
+ sysfs_unlink_rdev(mddev, rdev);
rdev->raid_disk = -1;
}
}
}
}
-static void raid5_quiesce(mddev_t *mddev, int state)
+static void raid5_quiesce(struct mddev *mddev, int state)
{
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
switch(state) {
case 2: /* resume for a suspend */
}
-static void *raid45_takeover_raid0(mddev_t *mddev, int level)
+static void *raid45_takeover_raid0(struct mddev *mddev, int level)
{
- struct raid0_private_data *raid0_priv = mddev->private;
+ struct r0conf *raid0_conf = mddev->private;
sector_t sectors;
/* for raid0 takeover only one zone is supported */
- if (raid0_priv->nr_strip_zones > 1) {
+ if (raid0_conf->nr_strip_zones > 1) {
printk(KERN_ERR "md/raid:%s: cannot takeover raid0 with more than one zone.\n",
mdname(mddev));
return ERR_PTR(-EINVAL);
}
- sectors = raid0_priv->strip_zone[0].zone_end;
- sector_div(sectors, raid0_priv->strip_zone[0].nb_dev);
+ sectors = raid0_conf->strip_zone[0].zone_end;
+ sector_div(sectors, raid0_conf->strip_zone[0].nb_dev);
mddev->dev_sectors = sectors;
mddev->new_level = level;
mddev->new_layout = ALGORITHM_PARITY_N;
}
-static void *raid5_takeover_raid1(mddev_t *mddev)
+static void *raid5_takeover_raid1(struct mddev *mddev)
{
int chunksect;
return setup_conf(mddev);
}
-static void *raid5_takeover_raid6(mddev_t *mddev)
+static void *raid5_takeover_raid6(struct mddev *mddev)
{
int new_layout;
}
-static int raid5_check_reshape(mddev_t *mddev)
+static int raid5_check_reshape(struct mddev *mddev)
{
/* For a 2-drive array, the layout and chunk size can be changed
* immediately as not restriping is needed.
* For larger arrays we record the new value - after validation
* to be used by a reshape pass.
*/
- raid5_conf_t *conf = mddev->private;
+ struct r5conf *conf = mddev->private;
int new_chunk = mddev->new_chunk_sectors;
if (mddev->new_layout >= 0 && !algorithm_valid_raid5(mddev->new_layout))
return check_reshape(mddev);
}
-static int raid6_check_reshape(mddev_t *mddev)
+static int raid6_check_reshape(struct mddev *mddev)
{
int new_chunk = mddev->new_chunk_sectors;
return check_reshape(mddev);
}
-static void *raid5_takeover(mddev_t *mddev)
+static void *raid5_takeover(struct mddev *mddev)
{
/* raid5 can take over:
* raid0 - if there is only one strip zone - make it a raid4 layout
return ERR_PTR(-EINVAL);
}
-static void *raid4_takeover(mddev_t *mddev)
+static void *raid4_takeover(struct mddev *mddev)
{
/* raid4 can take over:
* raid0 - if there is only one strip zone
return ERR_PTR(-EINVAL);
}
-static struct mdk_personality raid5_personality;
+static struct md_personality raid5_personality;
-static void *raid6_takeover(mddev_t *mddev)
+static void *raid6_takeover(struct mddev *mddev)
{
/* Currently can only take over a raid5. We map the
* personality to an equivalent raid6 personality
}
-static struct mdk_personality raid6_personality =
+static struct md_personality raid6_personality =
{
.name = "raid6",
.level = 6,
.quiesce = raid5_quiesce,
.takeover = raid6_takeover,
};
-static struct mdk_personality raid5_personality =
+static struct md_personality raid5_personality =
{
.name = "raid5",
.level = 5,
.takeover = raid5_takeover,
};
-static struct mdk_personality raid4_personality =
+static struct md_personality raid4_personality =
{
.name = "raid4",
.level = 4,