/* Find first affected segment... */
resid = offset;
- __bio_for_each_segment(bv, bio_src, idx, 0) {
+ bio_for_each_segment(bv, bio_src, idx) {
if (resid < bv->bv_len)
break;
resid -= bv->bv_len;
return atomic_read(&obj_request->done) != 0;
}
+ static void
+ rbd_img_obj_request_read_callback(struct rbd_obj_request *obj_request)
+ {
+ dout("%s: obj %p img %p result %d %llu/%llu\n", __func__,
+ obj_request, obj_request->img_request, obj_request->result,
+ obj_request->xferred, obj_request->length);
+ /*
+ * ENOENT means a hole in the image. We zero-fill the
+ * entire length of the request. A short read also implies
+ * zero-fill to the end of the request. Either way we
+ * update the xferred count to indicate the whole request
+ * was satisfied.
+ */
+ BUG_ON(obj_request->type != OBJ_REQUEST_BIO);
+ if (obj_request->result == -ENOENT) {
+ zero_bio_chain(obj_request->bio_list, 0);
+ obj_request->result = 0;
+ obj_request->xferred = obj_request->length;
+ } else if (obj_request->xferred < obj_request->length &&
+ !obj_request->result) {
+ zero_bio_chain(obj_request->bio_list, obj_request->xferred);
+ obj_request->xferred = obj_request->length;
+ }
+ obj_request_done_set(obj_request);
+ }
+
static void rbd_obj_request_complete(struct rbd_obj_request *obj_request)
{
dout("%s: obj %p cb %p\n", __func__, obj_request,
{
dout("%s: obj %p result %d %llu/%llu\n", __func__, obj_request,
obj_request->result, obj_request->xferred, obj_request->length);
- /*
- * ENOENT means a hole in the object. We zero-fill the
- * entire length of the request. A short read also implies
- * zero-fill to the end of the request. Either way we
- * update the xferred count to indicate the whole request
- * was satisfied.
- */
- if (obj_request->result == -ENOENT) {
- zero_bio_chain(obj_request->bio_list, 0);
- obj_request->result = 0;
- obj_request->xferred = obj_request->length;
- } else if (obj_request->xferred < obj_request->length &&
- !obj_request->result) {
- zero_bio_chain(obj_request->bio_list, obj_request->xferred);
- obj_request->xferred = obj_request->length;
- }
- obj_request_done_set(obj_request);
+ if (obj_request->img_request)
+ rbd_img_obj_request_read_callback(obj_request);
+ else
+ obj_request_done_set(obj_request);
}
static void rbd_osd_write_callback(struct rbd_obj_request *obj_request)
*/
};
+ struct dm_verity_prefetch_work {
+ struct work_struct work;
+ struct dm_verity *v;
+ sector_t block;
+ unsigned n_blocks;
+ };
+
static struct shash_desc *io_hash_desc(struct dm_verity *v, struct dm_verity_io *io)
{
return (struct shash_desc *)(io + 1);
* The root buffer is not prefetched, it is assumed that it will be cached
* all the time.
*/
- static void verity_prefetch_io(struct dm_verity *v, struct dm_verity_io *io)
+ static void verity_prefetch_io(struct work_struct *work)
{
+ struct dm_verity_prefetch_work *pw =
+ container_of(work, struct dm_verity_prefetch_work, work);
+ struct dm_verity *v = pw->v;
int i;
for (i = v->levels - 2; i >= 0; i--) {
sector_t hash_block_start;
sector_t hash_block_end;
- verity_hash_at_level(v, io->block, i, &hash_block_start, NULL);
- verity_hash_at_level(v, io->block + io->n_blocks - 1, i, &hash_block_end, NULL);
+ verity_hash_at_level(v, pw->block, i, &hash_block_start, NULL);
+ verity_hash_at_level(v, pw->block + pw->n_blocks - 1, i, &hash_block_end, NULL);
if (!i) {
unsigned cluster = ACCESS_ONCE(dm_verity_prefetch_cluster);
dm_bufio_prefetch(v->bufio, hash_block_start,
hash_block_end - hash_block_start + 1);
}
+
+ kfree(pw);
+ }
+
+ static void verity_submit_prefetch(struct dm_verity *v, struct dm_verity_io *io)
+ {
+ struct dm_verity_prefetch_work *pw;
+
+ pw = kmalloc(sizeof(struct dm_verity_prefetch_work),
+ GFP_NOIO | __GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN);
+
+ if (!pw)
+ return;
+
+ INIT_WORK(&pw->work, verity_prefetch_io);
+ pw->v = v;
+ pw->block = io->block;
+ pw->n_blocks = io->n_blocks;
+ queue_work(v->verify_wq, &pw->work);
}
/*
return -EIO;
}
- if ((bio->bi_sector + bio_sectors(bio)) >>
+ if (bio_end_sector(bio) >>
(v->data_dev_block_bits - SECTOR_SHIFT) > v->data_blocks) {
DMERR_LIMIT("io out of range");
return -EIO;
bio->bi_end_io = verity_end_io;
bio->bi_private = io;
- io->io_vec_size = bio->bi_vcnt - bio->bi_idx;
+ io->io_vec_size = bio_segments(bio);
if (io->io_vec_size < DM_VERITY_IO_VEC_INLINE)
io->io_vec = io->io_vec_inline;
else
memcpy(io->io_vec, bio_iovec(bio),
io->io_vec_size * sizeof(struct bio_vec));
- verity_prefetch_io(v, io);
+ verity_submit_prefetch(v, io);
generic_make_request(bio);
static struct target_type verity_target = {
.name = "verity",
- .version = {1, 1, 1},
+ .version = {1, 2, 0},
.module = THIS_MODULE,
.ctr = verity_ctr,
.dtr = verity_dtr,
*/
static inline struct bio *r5_next_bio(struct bio *bio, sector_t sector)
{
- int sectors = bio->bi_size >> 9;
+ int sectors = bio_sectors(bio);
if (bio->bi_sector + sectors < sector + STRIPE_SECTORS)
return bio->bi_next;
else
bi = &sh->dev[i].req;
rbi = &sh->dev[i].rreq; /* For writing to replacement */
- bi->bi_rw = rw;
- rbi->bi_rw = rw;
- if (rw & WRITE) {
- bi->bi_end_io = raid5_end_write_request;
- rbi->bi_end_io = raid5_end_write_request;
- } else
- bi->bi_end_io = raid5_end_read_request;
-
rcu_read_lock();
rrdev = rcu_dereference(conf->disks[i].replacement);
smp_mb(); /* Ensure that if rrdev is NULL, rdev won't be */
set_bit(STRIPE_IO_STARTED, &sh->state);
+ bio_reset(bi);
bi->bi_bdev = rdev->bdev;
+ bi->bi_rw = rw;
+ bi->bi_end_io = (rw & WRITE)
+ ? raid5_end_write_request
+ : raid5_end_read_request;
+ bi->bi_private = sh;
+
pr_debug("%s: for %llu schedule op %ld on disc %d\n",
__func__, (unsigned long long)sh->sector,
bi->bi_rw, i);
if (test_bit(R5_ReadNoMerge, &sh->dev[i].flags))
bi->bi_rw |= REQ_FLUSH;
- bi->bi_flags = 1 << BIO_UPTODATE;
- bi->bi_idx = 0;
bi->bi_io_vec[0].bv_len = STRIPE_SIZE;
bi->bi_io_vec[0].bv_offset = 0;
bi->bi_size = STRIPE_SIZE;
- bi->bi_next = NULL;
if (rrdev)
set_bit(R5_DOUBLE_LOCKED, &sh->dev[i].flags);
- trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
- bi, disk_devt(conf->mddev->gendisk),
- sh->dev[i].sector);
+
+ if (conf->mddev->gendisk)
+ trace_block_bio_remap(bdev_get_queue(bi->bi_bdev),
+ bi, disk_devt(conf->mddev->gendisk),
+ sh->dev[i].sector);
generic_make_request(bi);
}
if (rrdev) {
set_bit(STRIPE_IO_STARTED, &sh->state);
+ bio_reset(rbi);
rbi->bi_bdev = rrdev->bdev;
+ rbi->bi_rw = rw;
+ BUG_ON(!(rw & WRITE));
+ rbi->bi_end_io = raid5_end_write_request;
+ rbi->bi_private = sh;
+
pr_debug("%s: for %llu schedule op %ld on "
"replacement disc %d\n",
__func__, (unsigned long long)sh->sector,
else
rbi->bi_sector = (sh->sector
+ rrdev->data_offset);
- rbi->bi_flags = 1 << BIO_UPTODATE;
- rbi->bi_idx = 0;
rbi->bi_io_vec[0].bv_len = STRIPE_SIZE;
rbi->bi_io_vec[0].bv_offset = 0;
rbi->bi_size = STRIPE_SIZE;
- trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
- rbi, disk_devt(conf->mddev->gendisk),
- sh->dev[i].sector);
- rbi->bi_next = NULL;
+ if (conf->mddev->gendisk)
+ trace_block_bio_remap(bdev_get_queue(rbi->bi_bdev),
+ rbi, disk_devt(conf->mddev->gendisk),
+ sh->dev[i].sector);
generic_make_request(rbi);
}
if (!rdev && !rrdev) {
int level = conf->level;
if (rcw) {
- /* if we are not expanding this is a proper write request, and
- * there will be bios with new data to be drained into the
- * stripe cache
- */
- if (!expand) {
- sh->reconstruct_state = reconstruct_state_drain_run;
- set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
- } else
- sh->reconstruct_state = reconstruct_state_run;
-
- set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
s->locked++;
}
}
+ /* if we are not expanding this is a proper write request, and
+ * there will be bios with new data to be drained into the
+ * stripe cache
+ */
+ if (!expand) {
+ if (!s->locked)
+ /* False alarm, nothing to do */
+ return;
+ sh->reconstruct_state = reconstruct_state_drain_run;
+ set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+ } else
+ sh->reconstruct_state = reconstruct_state_run;
+
+ set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
+
if (s->locked + conf->max_degraded == disks)
if (!test_and_set_bit(STRIPE_FULL_WRITE, &sh->state))
atomic_inc(&conf->pending_full_writes);
BUG_ON(!(test_bit(R5_UPTODATE, &sh->dev[pd_idx].flags) ||
test_bit(R5_Wantcompute, &sh->dev[pd_idx].flags)));
- sh->reconstruct_state = reconstruct_state_prexor_drain_run;
- set_bit(STRIPE_OP_PREXOR, &s->ops_request);
- set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
- set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
-
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if (i == pd_idx)
s->locked++;
}
}
+ if (!s->locked)
+ /* False alarm - nothing to do */
+ return;
+ sh->reconstruct_state = reconstruct_state_prexor_drain_run;
+ set_bit(STRIPE_OP_PREXOR, &s->ops_request);
+ set_bit(STRIPE_OP_BIODRAIN, &s->ops_request);
+ set_bit(STRIPE_OP_RECONSTRUCT, &s->ops_request);
}
/* keep the parity disk(s) locked while asynchronous operations
} else
bip = &sh->dev[dd_idx].toread;
while (*bip && (*bip)->bi_sector < bi->bi_sector) {
- if ((*bip)->bi_sector + ((*bip)->bi_size >> 9) > bi->bi_sector)
+ if (bio_end_sector(*bip) > bi->bi_sector)
goto overlap;
bip = & (*bip)->bi_next;
}
- if (*bip && (*bip)->bi_sector < bi->bi_sector + ((bi->bi_size)>>9))
+ if (*bip && (*bip)->bi_sector < bio_end_sector(bi))
goto overlap;
BUG_ON(*bip && bi->bi_next && (*bip) != bi->bi_next);
sector < sh->dev[dd_idx].sector + STRIPE_SECTORS &&
bi && bi->bi_sector <= sector;
bi = r5_next_bio(bi, sh->dev[dd_idx].sector)) {
- if (bi->bi_sector + (bi->bi_size>>9) >= sector)
- sector = bi->bi_sector + (bi->bi_size>>9);
+ if (bio_end_sector(bi) >= sector)
+ sector = bio_end_sector(bi);
}
if (sector >= sh->dev[dd_idx].sector + STRIPE_SECTORS)
set_bit(R5_OVERWRITE, &sh->dev[dd_idx].flags);
int i;
clear_bit(STRIPE_SYNCING, &sh->state);
+ if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
+ wake_up(&conf->wait_for_overlap);
s->syncing = 0;
s->replacing = 0;
/* There is nothing more to do for sync/check/repair.
{
int i;
struct r5dev *dev;
+ int discard_pending = 0;
for (i = disks; i--; )
if (sh->dev[i].written) {
STRIPE_SECTORS,
!test_bit(STRIPE_DEGRADED, &sh->state),
0);
- }
- } else if (test_bit(R5_Discard, &sh->dev[i].flags))
- clear_bit(R5_Discard, &sh->dev[i].flags);
+ } else if (test_bit(R5_Discard, &dev->flags))
+ discard_pending = 1;
+ }
+ if (!discard_pending &&
+ test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) {
+ clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags);
+ clear_bit(R5_UPTODATE, &sh->dev[sh->pd_idx].flags);
+ if (sh->qd_idx >= 0) {
+ clear_bit(R5_Discard, &sh->dev[sh->qd_idx].flags);
+ clear_bit(R5_UPTODATE, &sh->dev[sh->qd_idx].flags);
+ }
+ /* now that discard is done we can proceed with any sync */
+ clear_bit(STRIPE_DISCARD, &sh->state);
+ if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state))
+ set_bit(STRIPE_HANDLE, &sh->state);
+
+ }
if (test_and_clear_bit(STRIPE_FULL_WRITE, &sh->state))
if (atomic_dec_and_test(&conf->pending_full_writes))
set_bit(STRIPE_HANDLE, &sh->state);
if (rmw < rcw && rmw > 0) {
/* prefer read-modify-write, but need to get some data */
- blk_add_trace_msg(conf->mddev->queue, "raid5 rmw %llu %d",
- (unsigned long long)sh->sector, rmw);
+ if (conf->mddev->queue)
+ blk_add_trace_msg(conf->mddev->queue,
+ "raid5 rmw %llu %d",
+ (unsigned long long)sh->sector, rmw);
for (i = disks; i--; ) {
struct r5dev *dev = &sh->dev[i];
if ((dev->towrite || i == sh->pd_idx) &&
}
}
}
- if (rcw)
+ if (rcw && conf->mddev->queue)
blk_add_trace_msg(conf->mddev->queue, "raid5 rcw %llu %d %d %d",
(unsigned long long)sh->sector,
rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
return;
}
- if (test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
- set_bit(STRIPE_SYNCING, &sh->state);
- clear_bit(STRIPE_INSYNC, &sh->state);
+ if (test_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
+ spin_lock(&sh->stripe_lock);
+ /* Cannot process 'sync' concurrently with 'discard' */
+ if (!test_bit(STRIPE_DISCARD, &sh->state) &&
+ test_and_clear_bit(STRIPE_SYNC_REQUESTED, &sh->state)) {
+ set_bit(STRIPE_SYNCING, &sh->state);
+ clear_bit(STRIPE_INSYNC, &sh->state);
+ }
+ spin_unlock(&sh->stripe_lock);
}
clear_bit(STRIPE_DELAYED, &sh->state);
test_bit(STRIPE_INSYNC, &sh->state)) {
md_done_sync(conf->mddev, STRIPE_SECTORS, 1);
clear_bit(STRIPE_SYNCING, &sh->state);
+ if (test_and_clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags))
+ wake_up(&conf->wait_for_overlap);
}
/* If the failed drives are just a ReadError, then we might need
{
sector_t sector = bio->bi_sector + get_start_sect(bio->bi_bdev);
unsigned int chunk_sectors = mddev->chunk_sectors;
- unsigned int bio_sectors = bio->bi_size >> 9;
+ unsigned int bio_sectors = bio_sectors(bio);
if (mddev->new_chunk_sectors < mddev->chunk_sectors)
chunk_sectors = mddev->new_chunk_sectors;
{
struct request_queue *q = bdev_get_queue(bi->bi_bdev);
- if ((bi->bi_size>>9) > queue_max_sectors(q))
+ if (bio_sectors(bi) > queue_max_sectors(q))
return 0;
blk_recount_segments(q, bi);
if (bi->bi_phys_segments > queue_max_segments(q))
0,
&dd_idx, NULL);
- end_sector = align_bi->bi_sector + (align_bi->bi_size >> 9);
+ end_sector = bio_end_sector(align_bi);
rcu_read_lock();
rdev = rcu_dereference(conf->disks[dd_idx].replacement);
if (!rdev || test_bit(Faulty, &rdev->flags) ||
align_bi->bi_flags &= ~(1 << BIO_SEG_VALID);
if (!bio_fits_rdev(align_bi) ||
- is_badblock(rdev, align_bi->bi_sector, align_bi->bi_size>>9,
+ is_badblock(rdev, align_bi->bi_sector, bio_sectors(align_bi),
&first_bad, &bad_sectors)) {
/* too big in some way, or has a known bad block */
bio_put(align_bi);
atomic_inc(&conf->active_aligned_reads);
spin_unlock_irq(&conf->device_lock);
- trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev),
- align_bi, disk_devt(mddev->gendisk),
- raid_bio->bi_sector);
+ if (mddev->gendisk)
+ trace_block_bio_remap(bdev_get_queue(align_bi->bi_bdev),
+ align_bi, disk_devt(mddev->gendisk),
+ raid_bio->bi_sector);
generic_make_request(align_bi);
return 1;
} else {
}
spin_unlock_irq(&conf->device_lock);
}
- trace_block_unplug(mddev->queue, cnt, !from_schedule);
+ if (mddev->queue)
+ trace_block_unplug(mddev->queue, cnt, !from_schedule);
kfree(cb);
}
sh = get_active_stripe(conf, logical_sector, 0, 0, 0);
prepare_to_wait(&conf->wait_for_overlap, &w,
TASK_UNINTERRUPTIBLE);
+ set_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags);
+ if (test_bit(STRIPE_SYNCING, &sh->state)) {
+ release_stripe(sh);
+ schedule();
+ goto again;
+ }
+ clear_bit(R5_Overlap, &sh->dev[sh->pd_idx].flags);
spin_lock_irq(&sh->stripe_lock);
for (d = 0; d < conf->raid_disks; d++) {
if (d == sh->pd_idx || d == sh->qd_idx)
goto again;
}
}
+ set_bit(STRIPE_DISCARD, &sh->state);
finish_wait(&conf->wait_for_overlap, &w);
for (d = 0; d < conf->raid_disks; d++) {
if (d == sh->pd_idx || d == sh->qd_idx)
}
logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
- last_sector = bi->bi_sector + (bi->bi_size>>9);
+ last_sector = bio_end_sector(bi);
bi->bi_next = NULL;
bi->bi_phys_segments = 1; /* over-loaded to count active stripes */
logical_sector = raid_bio->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
sector = raid5_compute_sector(conf, logical_sector,
0, &dd_idx, NULL);
- last_sector = raid_bio->bi_sector + (raid_bio->bi_size>>9);
+ last_sector = bio_end_sector(raid_bio);
for (; logical_sector < last_sector;
logical_sector += STRIPE_SECTORS,
projects / firefly-linux-kernel-4.4.55.git / commitdiff