summaryrefslogtreecommitdiff
path: root/drivers/md/raid10.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md/raid10.c')
-rw-r--r--drivers/md/raid10.c279
1 files changed, 212 insertions, 67 deletions
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 5026e7ad51d3..b9edbc747a95 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -29,7 +29,7 @@
#include "md.h"
#include "raid10.h"
#include "raid0.h"
-#include "bitmap.h"
+#include "md-bitmap.h"
/*
* RAID10 provides a combination of RAID0 and RAID1 functionality.
@@ -110,14 +110,7 @@ static void end_reshape(struct r10conf *conf);
#define raid10_log(md, fmt, args...) \
do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid10 " fmt, ##args); } while (0)
-/*
- * 'strct resync_pages' stores actual pages used for doing the resync
- * IO, and it is per-bio, so make .bi_private points to it.
- */
-static inline struct resync_pages *get_resync_pages(struct bio *bio)
-{
- return bio->bi_private;
-}
+#include "raid1-10.c"
/*
* for resync bio, r10bio pointer can be retrieved from the per-bio
@@ -143,10 +136,13 @@ static void r10bio_pool_free(void *r10_bio, void *data)
kfree(r10_bio);
}
+#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
/* amount of memory to reserve for resync requests */
#define RESYNC_WINDOW (1024*1024)
/* maximum number of concurrent requests, memory permitting */
#define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE)
+#define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW)
+#define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9)
/*
* When performing a resync, we need to read and compare, so
@@ -221,7 +217,6 @@ static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
resync_get_all_pages(rp);
}
- rp->idx = 0;
rp->raid_bio = r10_bio;
bio->bi_private = rp;
if (rbio) {
@@ -391,12 +386,11 @@ static void raid10_end_read_request(struct bio *bio)
{
int uptodate = !bio->bi_status;
struct r10bio *r10_bio = bio->bi_private;
- int slot, dev;
+ int slot;
struct md_rdev *rdev;
struct r10conf *conf = r10_bio->mddev->private;
slot = r10_bio->read_slot;
- dev = r10_bio->devs[slot].devnum;
rdev = r10_bio->devs[slot].rdev;
/*
* this branch is our 'one mirror IO has finished' event handler:
@@ -756,7 +750,6 @@ static struct md_rdev *read_balance(struct r10conf *conf,
raid10_find_phys(conf, r10_bio);
rcu_read_lock();
- sectors = r10_bio->sectors;
best_slot = -1;
best_rdev = NULL;
best_dist = MaxSector;
@@ -769,8 +762,11 @@ static struct md_rdev *read_balance(struct r10conf *conf,
* the resync window. We take the first readable disk when
* above the resync window.
*/
- if (conf->mddev->recovery_cp < MaxSector
- && (this_sector + sectors >= conf->next_resync))
+ if ((conf->mddev->recovery_cp < MaxSector
+ && (this_sector + sectors >= conf->next_resync)) ||
+ (mddev_is_clustered(conf->mddev) &&
+ md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
+ this_sector + sectors)))
do_balance = 0;
for (slot = 0; slot < conf->copies ; slot++) {
@@ -909,14 +905,13 @@ static void flush_pending_writes(struct r10conf *conf)
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
- struct md_rdev *rdev = (void*)bio->bi_bdev;
+ struct md_rdev *rdev = (void*)bio->bi_disk;
bio->bi_next = NULL;
- bio->bi_bdev = rdev->bdev;
+ bio_set_dev(bio, rdev->bdev);
if (test_bit(Faulty, &rdev->flags)) {
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
+ bio_io_error(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
- !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+ !blk_queue_discard(bio->bi_disk->queue)))
/* Just ignore it */
bio_endio(bio);
else
@@ -1094,14 +1089,13 @@ static void raid10_unplug(struct blk_plug_cb *cb, bool from_schedule)
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
- struct md_rdev *rdev = (void*)bio->bi_bdev;
+ struct md_rdev *rdev = (void*)bio->bi_disk;
bio->bi_next = NULL;
- bio->bi_bdev = rdev->bdev;
+ bio_set_dev(bio, rdev->bdev);
if (test_bit(Faulty, &rdev->flags)) {
- bio->bi_status = BLK_STS_IOERR;
- bio_endio(bio);
+ bio_io_error(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
- !blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
+ !blk_queue_discard(bio->bi_disk->queue)))
/* Just ignore it */
bio_endio(bio);
else
@@ -1210,7 +1204,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr +
choose_data_offset(r10_bio, rdev);
- read_bio->bi_bdev = rdev->bdev;
+ bio_set_dev(read_bio, rdev->bdev);
read_bio->bi_end_io = raid10_end_read_request;
bio_set_op_attrs(read_bio, op, do_sync);
if (test_bit(FailFast, &rdev->flags) &&
@@ -1219,7 +1213,7 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
read_bio->bi_private = r10_bio;
if (mddev->gendisk)
- trace_block_bio_remap(bdev_get_queue(read_bio->bi_bdev),
+ trace_block_bio_remap(read_bio->bi_disk->queue,
read_bio, disk_devt(mddev->gendisk),
r10_bio->sector);
generic_make_request(read_bio);
@@ -1259,7 +1253,7 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
mbio->bi_iter.bi_sector = (r10_bio->devs[n_copy].addr +
choose_data_offset(r10_bio, rdev));
- mbio->bi_bdev = rdev->bdev;
+ bio_set_dev(mbio, rdev->bdev);
mbio->bi_end_io = raid10_end_write_request;
bio_set_op_attrs(mbio, op, do_sync | do_fua);
if (!replacement && test_bit(FailFast,
@@ -1269,11 +1263,11 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio,
mbio->bi_private = r10_bio;
if (conf->mddev->gendisk)
- trace_block_bio_remap(bdev_get_queue(mbio->bi_bdev),
+ trace_block_bio_remap(mbio->bi_disk->queue,
mbio, disk_devt(conf->mddev->gendisk),
r10_bio->sector);
/* flush_pending_writes() needs access to the rdev so...*/
- mbio->bi_bdev = (void *)rdev;
+ mbio->bi_disk = (void *)rdev;
atomic_inc(&r10_bio->remaining);
@@ -1303,6 +1297,22 @@ static void raid10_write_request(struct mddev *mddev, struct bio *bio,
sector_t sectors;
int max_sectors;
+ if ((mddev_is_clustered(mddev) &&
+ md_cluster_ops->area_resyncing(mddev, WRITE,
+ bio->bi_iter.bi_sector,
+ bio_end_sector(bio)))) {
+ DEFINE_WAIT(w);
+ for (;;) {
+ prepare_to_wait(&conf->wait_barrier,
+ &w, TASK_IDLE);
+ if (!md_cluster_ops->area_resyncing(mddev, WRITE,
+ bio->bi_iter.bi_sector, bio_end_sector(bio)))
+ break;
+ schedule();
+ }
+ finish_wait(&conf->wait_barrier, &w);
+ }
+
/*
* Register the new request and wait if the reconstruction
* thread has put up a bar for new requests.
@@ -2087,8 +2097,8 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
rp = get_resync_pages(tbio);
bio_reset(tbio);
- tbio->bi_vcnt = vcnt;
- tbio->bi_iter.bi_size = fbio->bi_iter.bi_size;
+ md_bio_reset_resync_pages(tbio, rp, fbio->bi_iter.bi_size);
+
rp->raid_bio = r10_bio;
tbio->bi_private = rp;
tbio->bi_iter.bi_sector = r10_bio->devs[i].addr;
@@ -2104,7 +2114,7 @@ static void sync_request_write(struct mddev *mddev, struct r10bio *r10_bio)
if (test_bit(FailFast, &conf->mirrors[d].rdev->flags))
tbio->bi_opf |= MD_FAILFAST;
tbio->bi_iter.bi_sector += conf->mirrors[d].rdev->data_offset;
- tbio->bi_bdev = conf->mirrors[d].rdev->bdev;
+ bio_set_dev(tbio, conf->mirrors[d].rdev->bdev);
generic_make_request(tbio);
}
@@ -2562,7 +2572,7 @@ static int narrow_write_error(struct r10bio *r10_bio, int i)
wsector = r10_bio->devs[i].addr + (sector - r10_bio->sector);
wbio->bi_iter.bi_sector = wsector +
choose_data_offset(r10_bio, rdev);
- wbio->bi_bdev = rdev->bdev;
+ bio_set_dev(wbio, rdev->bdev);
bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
if (submit_bio_wait(wbio) < 0)
@@ -2585,8 +2595,6 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
struct bio *bio;
struct r10conf *conf = mddev->private;
struct md_rdev *rdev = r10_bio->devs[slot].rdev;
- dev_t bio_dev;
- sector_t bio_last_sector;
/* we got a read error. Maybe the drive is bad. Maybe just
* the block and we can fix it.
@@ -2597,8 +2605,6 @@ static void handle_read_error(struct mddev *mddev, struct r10bio *r10_bio)
* frozen.
*/
bio = r10_bio->devs[slot].bio;
- bio_dev = bio->bi_bdev->bd_dev;
- bio_last_sector = r10_bio->devs[slot].addr + rdev->data_offset + r10_bio->sectors;
bio_put(bio);
r10_bio->devs[slot].bio = NULL;
@@ -2808,6 +2814,72 @@ static int init_resync(struct r10conf *conf)
return 0;
}
+static struct r10bio *raid10_alloc_init_r10buf(struct r10conf *conf)
+{
+ struct r10bio *r10bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+ struct rsync_pages *rp;
+ struct bio *bio;
+ int nalloc;
+ int i;
+
+ if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery) ||
+ test_bit(MD_RECOVERY_RESHAPE, &conf->mddev->recovery))
+ nalloc = conf->copies; /* resync */
+ else
+ nalloc = 2; /* recovery */
+
+ for (i = 0; i < nalloc; i++) {
+ bio = r10bio->devs[i].bio;
+ rp = bio->bi_private;
+ bio_reset(bio);
+ bio->bi_private = rp;
+ bio = r10bio->devs[i].repl_bio;
+ if (bio) {
+ rp = bio->bi_private;
+ bio_reset(bio);
+ bio->bi_private = rp;
+ }
+ }
+ return r10bio;
+}
+
+/*
+ * Set cluster_sync_high since we need other nodes to add the
+ * range [cluster_sync_low, cluster_sync_high] to suspend list.
+ */
+static void raid10_set_cluster_sync_high(struct r10conf *conf)
+{
+ sector_t window_size;
+ int extra_chunk, chunks;
+
+ /*
+ * First, here we define "stripe" as a unit which across
+ * all member devices one time, so we get chunks by use
+ * raid_disks / near_copies. Otherwise, if near_copies is
+ * close to raid_disks, then resync window could increases
+ * linearly with the increase of raid_disks, which means
+ * we will suspend a really large IO window while it is not
+ * necessary. If raid_disks is not divisible by near_copies,
+ * an extra chunk is needed to ensure the whole "stripe" is
+ * covered.
+ */
+
+ chunks = conf->geo.raid_disks / conf->geo.near_copies;
+ if (conf->geo.raid_disks % conf->geo.near_copies == 0)
+ extra_chunk = 0;
+ else
+ extra_chunk = 1;
+ window_size = (chunks + extra_chunk) * conf->mddev->chunk_sectors;
+
+ /*
+ * At least use a 32M window to align with raid1's resync window
+ */
+ window_size = (CLUSTER_RESYNC_WINDOW_SECTORS > window_size) ?
+ CLUSTER_RESYNC_WINDOW_SECTORS : window_size;
+
+ conf->cluster_sync_high = conf->cluster_sync_low + window_size;
+}
+
/*
* perform a "sync" on one "block"
*
@@ -2853,6 +2925,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
sector_t sectors_skipped = 0;
int chunks_skipped = 0;
sector_t chunk_mask = conf->geo.chunk_mask;
+ int page_idx = 0;
if (!conf->r10buf_pool)
if (init_resync(conf))
@@ -2879,6 +2952,9 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
max_sector = mddev->resync_max_sectors;
if (sector_nr >= max_sector) {
+ conf->cluster_sync_low = 0;
+ conf->cluster_sync_high = 0;
+
/* If we aborted, we need to abort the
* sync on the 'current' bitmap chucks (there can
* be several when recovering multiple devices).
@@ -2959,7 +3035,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
/* Again, very different code for resync and recovery.
* Both must result in an r10bio with a list of bios that
- * have bi_end_io, bi_sector, bi_bdev set,
+ * have bi_end_io, bi_sector, bi_disk set,
* and bi_private set to the r10bio.
* For recovery, we may actually create several r10bios
* with 2 bios in each, that correspond to the bios in the main one.
@@ -3036,7 +3112,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
atomic_inc(&mreplace->nr_pending);
rcu_read_unlock();
- r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+ r10_bio = raid10_alloc_init_r10buf(conf);
r10_bio->state = 0;
raise_barrier(conf, rb2 != NULL);
atomic_set(&r10_bio->remaining, 0);
@@ -3104,7 +3180,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
from_addr = r10_bio->devs[j].addr;
bio->bi_iter.bi_sector = from_addr +
rdev->data_offset;
- bio->bi_bdev = rdev->bdev;
+ bio_set_dev(bio, rdev->bdev);
atomic_inc(&rdev->nr_pending);
/* and we write to 'i' (if not in_sync) */
@@ -3126,7 +3202,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_iter.bi_sector = to_addr
+ mrdev->data_offset;
- bio->bi_bdev = mrdev->bdev;
+ bio_set_dev(bio, mrdev->bdev);
atomic_inc(&r10_bio->remaining);
} else
r10_bio->devs[1].bio->bi_end_io = NULL;
@@ -3152,7 +3228,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_iter.bi_sector = to_addr +
mreplace->data_offset;
- bio->bi_bdev = mreplace->bdev;
+ bio_set_dev(bio, mreplace->bdev);
atomic_inc(&r10_bio->remaining);
break;
}
@@ -3233,7 +3309,17 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
/* resync. Schedule a read for every block at this virt offset */
int count = 0;
- bitmap_cond_end_sync(mddev->bitmap, sector_nr, 0);
+ /*
+ * Since curr_resync_completed could probably not update in
+ * time, and we will set cluster_sync_low based on it.
+ * Let's check against "sector_nr + 2 * RESYNC_SECTORS" for
+ * safety reason, which ensures curr_resync_completed is
+ * updated in bitmap_cond_end_sync.
+ */
+ bitmap_cond_end_sync(mddev->bitmap, sector_nr,
+ mddev_is_clustered(mddev) &&
+ (sector_nr + 2 * RESYNC_SECTORS >
+ conf->cluster_sync_high));
if (!bitmap_start_sync(mddev->bitmap, sector_nr,
&sync_blocks, mddev->degraded) &&
@@ -3245,7 +3331,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
}
if (sync_blocks < max_sync)
max_sync = sync_blocks;
- r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+ r10_bio = raid10_alloc_init_r10buf(conf);
r10_bio->state = 0;
r10_bio->mddev = mddev;
@@ -3298,7 +3384,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
if (test_bit(FailFast, &rdev->flags))
bio->bi_opf |= MD_FAILFAST;
bio->bi_iter.bi_sector = sector + rdev->data_offset;
- bio->bi_bdev = rdev->bdev;
+ bio_set_dev(bio, rdev->bdev);
count++;
rdev = rcu_dereference(conf->mirrors[d].replacement);
@@ -3320,7 +3406,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
if (test_bit(FailFast, &rdev->flags))
bio->bi_opf |= MD_FAILFAST;
bio->bi_iter.bi_sector = sector + rdev->data_offset;
- bio->bi_bdev = rdev->bdev;
+ bio_set_dev(bio, rdev->bdev);
count++;
rcu_read_unlock();
}
@@ -3355,7 +3441,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
break;
for (bio= biolist ; bio ; bio=bio->bi_next) {
struct resync_pages *rp = get_resync_pages(bio);
- page = resync_fetch_page(rp, rp->idx++);
+ page = resync_fetch_page(rp, page_idx);
/*
* won't fail because the vec table is big enough
* to hold all these pages
@@ -3364,9 +3450,55 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
}
nr_sectors += len>>9;
sector_nr += len>>9;
- } while (get_resync_pages(biolist)->idx < RESYNC_PAGES);
+ } while (++page_idx < RESYNC_PAGES);
r10_bio->sectors = nr_sectors;
+ if (mddev_is_clustered(mddev) &&
+ test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ /* It is resync not recovery */
+ if (conf->cluster_sync_high < sector_nr + nr_sectors) {
+ conf->cluster_sync_low = mddev->curr_resync_completed;
+ raid10_set_cluster_sync_high(conf);
+ /* Send resync message */
+ md_cluster_ops->resync_info_update(mddev,
+ conf->cluster_sync_low,
+ conf->cluster_sync_high);
+ }
+ } else if (mddev_is_clustered(mddev)) {
+ /* This is recovery not resync */
+ sector_t sect_va1, sect_va2;
+ bool broadcast_msg = false;
+
+ for (i = 0; i < conf->geo.raid_disks; i++) {
+ /*
+ * sector_nr is a device address for recovery, so we
+ * need translate it to array address before compare
+ * with cluster_sync_high.
+ */
+ sect_va1 = raid10_find_virt(conf, sector_nr, i);
+
+ if (conf->cluster_sync_high < sect_va1 + nr_sectors) {
+ broadcast_msg = true;
+ /*
+ * curr_resync_completed is similar as
+ * sector_nr, so make the translation too.
+ */
+ sect_va2 = raid10_find_virt(conf,
+ mddev->curr_resync_completed, i);
+
+ if (conf->cluster_sync_low == 0 ||
+ conf->cluster_sync_low > sect_va2)
+ conf->cluster_sync_low = sect_va2;
+ }
+ }
+ if (broadcast_msg) {
+ raid10_set_cluster_sync_high(conf);
+ md_cluster_ops->resync_info_update(mddev,
+ conf->cluster_sync_low,
+ conf->cluster_sync_high);
+ }
+ }
+
while (biolist) {
bio = biolist;
biolist = biolist->bi_next;
@@ -3376,7 +3508,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr,
r10_bio->sectors = nr_sectors;
if (bio->bi_end_io == end_sync_read) {
- md_sync_acct(bio->bi_bdev, nr_sectors);
+ md_sync_acct_bio(bio, nr_sectors);
bio->bi_status = 0;
generic_make_request(bio);
}
@@ -3626,6 +3758,18 @@ static int raid10_run(struct mddev *mddev)
if (!conf)
goto out;
+ if (mddev_is_clustered(conf->mddev)) {
+ int fc, fo;
+
+ fc = (mddev->layout >> 8) & 255;
+ fo = mddev->layout & (1<<16);
+ if (fc > 1 || fo > 0) {
+ pr_err("only near layout is supported by clustered"
+ " raid10\n");
+ goto out;
+ }
+ }
+
mddev->thread = conf->thread;
conf->thread = NULL;
@@ -3814,18 +3958,14 @@ static void raid10_free(struct mddev *mddev, void *priv)
kfree(conf);
}
-static void raid10_quiesce(struct mddev *mddev, int state)
+static void raid10_quiesce(struct mddev *mddev, int quiesce)
{
struct r10conf *conf = mddev->private;
- switch(state) {
- case 1:
+ if (quiesce)
raise_barrier(conf, 0);
- break;
- case 0:
+ else
lower_barrier(conf);
- break;
- }
}
static int raid10_resize(struct mddev *mddev, sector_t sectors)
@@ -4369,7 +4509,7 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
read_more:
/* Now schedule reads for blocks from sector_nr to last */
- r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
+ r10_bio = raid10_alloc_init_r10buf(conf);
r10_bio->state = 0;
raise_barrier(conf, sectors_done != 0);
atomic_set(&r10_bio->remaining, 0);
@@ -4392,7 +4532,7 @@ read_more:
read_bio = bio_alloc_mddev(GFP_KERNEL, RESYNC_PAGES, mddev);
- read_bio->bi_bdev = rdev->bdev;
+ bio_set_dev(read_bio, rdev->bdev);
read_bio->bi_iter.bi_sector = (r10_bio->devs[r10_bio->read_slot].addr
+ rdev->data_offset);
read_bio->bi_private = r10_bio;
@@ -4426,7 +4566,7 @@ read_more:
if (!rdev2 || test_bit(Faulty, &rdev2->flags))
continue;
- b->bi_bdev = rdev2->bdev;
+ bio_set_dev(b, rdev2->bdev);
b->bi_iter.bi_sector = r10_bio->devs[s/2].addr +
rdev2->new_data_offset;
b->bi_end_io = end_reshape_write;
@@ -4458,7 +4598,7 @@ read_more:
r10_bio->sectors = nr_sectors;
/* Now submit the read */
- md_sync_acct(read_bio->bi_bdev, r10_bio->sectors);
+ md_sync_acct_bio(read_bio, r10_bio->sectors);
atomic_inc(&r10_bio->remaining);
read_bio->bi_next = NULL;
generic_make_request(read_bio);
@@ -4520,7 +4660,7 @@ static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio)
}
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
- md_sync_acct(b->bi_bdev, r10_bio->sectors);
+ md_sync_acct_bio(b, r10_bio->sectors);
atomic_inc(&r10_bio->remaining);
b->bi_next = NULL;
generic_make_request(b);
@@ -4560,15 +4700,18 @@ static int handle_reshape_read_error(struct mddev *mddev,
/* Use sync reads to get the blocks from somewhere else */
int sectors = r10_bio->sectors;
struct r10conf *conf = mddev->private;
- struct {
- struct r10bio r10_bio;
- struct r10dev devs[conf->copies];
- } on_stack;
- struct r10bio *r10b = &on_stack.r10_bio;
+ struct r10bio *r10b;
int slot = 0;
int idx = 0;
struct page **pages;
+ r10b = kmalloc(sizeof(*r10b) +
+ sizeof(struct r10dev) * conf->copies, GFP_NOIO);
+ if (!r10b) {
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
+ return -ENOMEM;
+ }
+
/* reshape IOs share pages from .devs[0].bio */
pages = get_resync_pages(r10_bio->devs[0].bio)->pages;
@@ -4617,11 +4760,13 @@ static int handle_reshape_read_error(struct mddev *mddev,
/* couldn't read this block, must give up */
set_bit(MD_RECOVERY_INTR,
&mddev->recovery);
+ kfree(r10b);
return -EIO;
}
sectors -= s;
idx++;
}
+ kfree(r10b);
return 0;
}
generated by cgit v1.2.3 (git 2.46.0) at 2025-09-08 09:49:42 +0000