From f70575805708cabdedea7498aaa3f710fde4d920 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 31 Jan 2024 03:29:01 +0000
Subject: [PATCH] add lvds1024*800
---
kernel/drivers/md/dm-zoned-target.c | 498 +++++++++++++++++++++++++++++++++++++-----------------
1 files changed, 337 insertions(+), 161 deletions(-)
diff --git a/kernel/drivers/md/dm-zoned-target.c b/kernel/drivers/md/dm-zoned-target.c
index 1853972..48fc723 100644
--- a/kernel/drivers/md/dm-zoned-target.c
+++ b/kernel/drivers/md/dm-zoned-target.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017 Western Digital Corporation or its affiliates.
*
@@ -16,10 +17,10 @@
* Zone BIO context.
*/
struct dmz_bioctx {
- struct dmz_target *target;
+ struct dmz_dev *dev;
struct dm_zone *zone;
struct bio *bio;
- atomic_t ref;
+ refcount_t ref;
};
/*
@@ -27,7 +28,7 @@
*/
struct dm_chunk_work {
struct work_struct work;
- atomic_t refcount;
+ refcount_t refcount;
struct dmz_target *target;
unsigned int chunk;
struct bio_list bio_list;
@@ -37,18 +38,16 @@
* Target descriptor.
*/
struct dmz_target {
- struct dm_dev *ddev;
+ struct dm_dev **ddev;
+ unsigned int nr_ddevs;
- unsigned long flags;
+ unsigned int flags;
/* Zoned block device information */
struct dmz_dev *dev;
/* For metadata handling */
struct dmz_metadata *metadata;
-
- /* For reclaim */
- struct dmz_reclaim *reclaim;
/* For chunk work */
struct radix_tree_root chunk_rxtree;
@@ -75,14 +74,15 @@
*/
static inline void dmz_bio_endio(struct bio *bio, blk_status_t status)
{
- struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
+ struct dmz_bioctx *bioctx =
+ dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK)
bio->bi_status = status;
- if (bio->bi_status != BLK_STS_OK)
- bioctx->target->dev->flags |= DMZ_CHECK_BDEV;
+ if (bioctx->dev && bio->bi_status != BLK_STS_OK)
+ bioctx->dev->flags |= DMZ_CHECK_BDEV;
- if (atomic_dec_and_test(&bioctx->ref)) {
+ if (refcount_dec_and_test(&bioctx->ref)) {
struct dm_zone *zone = bioctx->zone;
if (zone) {
@@ -117,14 +117,20 @@
struct bio *bio, sector_t chunk_block,
unsigned int nr_blocks)
{
- struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
+ struct dmz_bioctx *bioctx =
+ dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
+ struct dmz_dev *dev = zone->dev;
struct bio *clone;
+
+ if (dev->flags & DMZ_BDEV_DYING)
+ return -EIO;
clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set);
if (!clone)
return -ENOMEM;
- bio_set_dev(clone, dmz->dev->bdev);
+ bio_set_dev(clone, dev->bdev);
+ bioctx->dev = dev;
clone->bi_iter.bi_sector =
dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT;
@@ -133,8 +139,8 @@
bio_advance(bio, clone->bi_iter.bi_size);
- atomic_inc(&bioctx->ref);
- generic_make_request(clone);
+ refcount_inc(&bioctx->ref);
+ submit_bio_noacct(clone);
if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone))
zone->wp_block += nr_blocks;
@@ -164,7 +170,8 @@
static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone,
struct bio *bio)
{
- sector_t chunk_block = dmz_chunk_block(dmz->dev, dmz_bio_block(bio));
+ struct dmz_metadata *zmd = dmz->metadata;
+ sector_t chunk_block = dmz_chunk_block(zmd, dmz_bio_block(bio));
unsigned int nr_blocks = dmz_bio_blocks(bio);
sector_t end_block = chunk_block + nr_blocks;
struct dm_zone *rzone, *bzone;
@@ -176,19 +183,22 @@
return 0;
}
- dmz_dev_debug(dmz->dev, "READ chunk %llu -> %s zone %u, block %llu, %u blocks",
- (unsigned long long)dmz_bio_chunk(dmz->dev, bio),
- (dmz_is_rnd(zone) ? "RND" : "SEQ"),
- dmz_id(dmz->metadata, zone),
- (unsigned long long)chunk_block, nr_blocks);
+ DMDEBUG("(%s): READ chunk %llu -> %s zone %u, block %llu, %u blocks",
+ dmz_metadata_label(zmd),
+ (unsigned long long)dmz_bio_chunk(zmd, bio),
+ (dmz_is_rnd(zone) ? "RND" :
+ (dmz_is_cache(zone) ? "CACHE" : "SEQ")),
+ zone->id,
+ (unsigned long long)chunk_block, nr_blocks);
/* Check block validity to determine the read location */
bzone = zone->bzone;
while (chunk_block < end_block) {
nr_blocks = 0;
- if (dmz_is_rnd(zone) || chunk_block < zone->wp_block) {
+ if (dmz_is_rnd(zone) || dmz_is_cache(zone) ||
+ chunk_block < zone->wp_block) {
/* Test block validity in the data zone */
- ret = dmz_block_valid(dmz->metadata, zone, chunk_block);
+ ret = dmz_block_valid(zmd, zone, chunk_block);
if (ret < 0)
return ret;
if (ret > 0) {
@@ -203,7 +213,7 @@
* Check the buffer zone, if there is one.
*/
if (!nr_blocks && bzone) {
- ret = dmz_block_valid(dmz->metadata, bzone, chunk_block);
+ ret = dmz_block_valid(zmd, bzone, chunk_block);
if (ret < 0)
return ret;
if (ret > 0) {
@@ -215,8 +225,10 @@
if (nr_blocks) {
/* Valid blocks found: read them */
- nr_blocks = min_t(unsigned int, nr_blocks, end_block - chunk_block);
- ret = dmz_submit_bio(dmz, rzone, bio, chunk_block, nr_blocks);
+ nr_blocks = min_t(unsigned int, nr_blocks,
+ end_block - chunk_block);
+ ret = dmz_submit_bio(dmz, rzone, bio,
+ chunk_block, nr_blocks);
if (ret)
return ret;
chunk_block += nr_blocks;
@@ -307,25 +319,30 @@
static int dmz_handle_write(struct dmz_target *dmz, struct dm_zone *zone,
struct bio *bio)
{
- sector_t chunk_block = dmz_chunk_block(dmz->dev, dmz_bio_block(bio));
+ struct dmz_metadata *zmd = dmz->metadata;
+ sector_t chunk_block = dmz_chunk_block(zmd, dmz_bio_block(bio));
unsigned int nr_blocks = dmz_bio_blocks(bio);
if (!zone)
return -ENOSPC;
- dmz_dev_debug(dmz->dev, "WRITE chunk %llu -> %s zone %u, block %llu, %u blocks",
- (unsigned long long)dmz_bio_chunk(dmz->dev, bio),
- (dmz_is_rnd(zone) ? "RND" : "SEQ"),
- dmz_id(dmz->metadata, zone),
- (unsigned long long)chunk_block, nr_blocks);
+ DMDEBUG("(%s): WRITE chunk %llu -> %s zone %u, block %llu, %u blocks",
+ dmz_metadata_label(zmd),
+ (unsigned long long)dmz_bio_chunk(zmd, bio),
+ (dmz_is_rnd(zone) ? "RND" :
+ (dmz_is_cache(zone) ? "CACHE" : "SEQ")),
+ zone->id,
+ (unsigned long long)chunk_block, nr_blocks);
- if (dmz_is_rnd(zone) || chunk_block == zone->wp_block) {
+ if (dmz_is_rnd(zone) || dmz_is_cache(zone) ||
+ chunk_block == zone->wp_block) {
/*
* zone is a random zone or it is a sequential zone
* and the BIO is aligned to the zone write pointer:
* direct write the zone.
*/
- return dmz_handle_direct_write(dmz, zone, bio, chunk_block, nr_blocks);
+ return dmz_handle_direct_write(dmz, zone, bio,
+ chunk_block, nr_blocks);
}
/*
@@ -344,7 +361,7 @@
struct dmz_metadata *zmd = dmz->metadata;
sector_t block = dmz_bio_block(bio);
unsigned int nr_blocks = dmz_bio_blocks(bio);
- sector_t chunk_block = dmz_chunk_block(dmz->dev, block);
+ sector_t chunk_block = dmz_chunk_block(zmd, block);
int ret = 0;
/* For unmapped chunks, there is nothing to do */
@@ -354,16 +371,18 @@
if (dmz_is_readonly(zone))
return -EROFS;
- dmz_dev_debug(dmz->dev, "DISCARD chunk %llu -> zone %u, block %llu, %u blocks",
- (unsigned long long)dmz_bio_chunk(dmz->dev, bio),
- dmz_id(zmd, zone),
- (unsigned long long)chunk_block, nr_blocks);
+ DMDEBUG("(%s): DISCARD chunk %llu -> zone %u, block %llu, %u blocks",
+ dmz_metadata_label(dmz->metadata),
+ (unsigned long long)dmz_bio_chunk(zmd, bio),
+ zone->id,
+ (unsigned long long)chunk_block, nr_blocks);
/*
* Invalidate blocks in the data zone and its
* buffer zone if one is mapped.
*/
- if (dmz_is_rnd(zone) || chunk_block < zone->wp_block)
+ if (dmz_is_rnd(zone) || dmz_is_cache(zone) ||
+ chunk_block < zone->wp_block)
ret = dmz_invalidate_blocks(zmd, zone, chunk_block, nr_blocks);
if (ret == 0 && zone->bzone)
ret = dmz_invalidate_blocks(zmd, zone->bzone,
@@ -377,31 +396,20 @@
static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw,
struct bio *bio)
{
- struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
+ struct dmz_bioctx *bioctx =
+ dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
struct dmz_metadata *zmd = dmz->metadata;
struct dm_zone *zone;
int ret;
- /*
- * Write may trigger a zone allocation. So make sure the
- * allocation can succeed.
- */
- if (bio_op(bio) == REQ_OP_WRITE)
- dmz_schedule_reclaim(dmz->reclaim);
-
dmz_lock_metadata(zmd);
-
- if (dmz->dev->flags & DMZ_BDEV_DYING) {
- ret = -EIO;
- goto out;
- }
/*
* Get the data zone mapping the chunk. There may be no
* mapping for read and discard. If a mapping is obtained,
+ the zone returned will be set to active state.
*/
- zone = dmz_get_chunk_mapping(zmd, dmz_bio_chunk(dmz->dev, bio),
+ zone = dmz_get_chunk_mapping(zmd, dmz_bio_chunk(zmd, bio),
bio_op(bio));
if (IS_ERR(zone)) {
ret = PTR_ERR(zone);
@@ -412,6 +420,7 @@
if (zone) {
dmz_activate_zone(zone);
bioctx->zone = zone;
+ dmz_reclaim_bio_acc(zone->dev->reclaim);
}
switch (bio_op(bio)) {
@@ -426,8 +435,8 @@
ret = dmz_handle_discard(dmz, zone, bio);
break;
default:
- dmz_dev_err(dmz->dev, "Unsupported BIO operation 0x%x",
- bio_op(bio));
+ DMERR("(%s): Unsupported BIO operation 0x%x",
+ dmz_metadata_label(dmz->metadata), bio_op(bio));
ret = -EIO;
}
@@ -448,7 +457,7 @@
*/
static inline void dmz_get_chunk_work(struct dm_chunk_work *cw)
{
- atomic_inc(&cw->refcount);
+ refcount_inc(&cw->refcount);
}
/*
@@ -457,7 +466,7 @@
*/
static void dmz_put_chunk_work(struct dm_chunk_work *cw)
{
- if (atomic_dec_and_test(&cw->refcount)) {
+ if (refcount_dec_and_test(&cw->refcount)) {
WARN_ON(!bio_list_empty(&cw->bio_list));
radix_tree_delete(&cw->target->chunk_rxtree, cw->chunk);
kfree(cw);
@@ -501,7 +510,8 @@
/* Flush dirty metadata blocks */
ret = dmz_flush_metadata(dmz->metadata);
if (ret)
- dmz_dev_debug(dmz->dev, "Metadata flush failed, rc=%d\n", ret);
+ DMDEBUG("(%s): Metadata flush failed, rc=%d",
+ dmz_metadata_label(dmz->metadata), ret);
/* Process queued flush requests */
while (1) {
@@ -524,7 +534,7 @@
*/
static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio)
{
- unsigned int chunk = dmz_bio_chunk(dmz->dev, bio);
+ unsigned int chunk = dmz_bio_chunk(dmz->metadata, bio);
struct dm_chunk_work *cw;
int ret = 0;
@@ -532,8 +542,9 @@
/* Get the BIO chunk work. If one is not active yet, create one */
cw = radix_tree_lookup(&dmz->chunk_rxtree, chunk);
- if (!cw) {
-
+ if (cw) {
+ dmz_get_chunk_work(cw);
+ } else {
/* Create a new chunk work */
cw = kmalloc(sizeof(struct dm_chunk_work), GFP_NOIO);
if (unlikely(!cw)) {
@@ -542,7 +553,7 @@
}
INIT_WORK(&cw->work, dmz_chunk_work);
- atomic_set(&cw->refcount, 0);
+ refcount_set(&cw->refcount, 1);
cw->target = dmz;
cw->chunk = chunk;
bio_list_init(&cw->bio_list);
@@ -555,9 +566,7 @@
}
bio_list_add(&cw->bio_list, bio);
- dmz_get_chunk_work(cw);
- dmz_reclaim_bio_acc(dmz->reclaim);
if (queue_work(dmz->chunk_wq, &cw->work))
dmz_get_chunk_work(cw);
out:
@@ -617,23 +626,22 @@
static int dmz_map(struct dm_target *ti, struct bio *bio)
{
struct dmz_target *dmz = ti->private;
- struct dmz_dev *dev = dmz->dev;
+ struct dmz_metadata *zmd = dmz->metadata;
struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
sector_t sector = bio->bi_iter.bi_sector;
unsigned int nr_sectors = bio_sectors(bio);
sector_t chunk_sector;
int ret;
- if (dmz_bdev_is_dying(dmz->dev))
+ if (dmz_dev_is_dying(zmd))
return DM_MAPIO_KILL;
- dmz_dev_debug(dev, "BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks",
- bio_op(bio), (unsigned long long)sector, nr_sectors,
- (unsigned long long)dmz_bio_chunk(dmz->dev, bio),
- (unsigned long long)dmz_chunk_block(dmz->dev, dmz_bio_block(bio)),
- (unsigned int)dmz_bio_blocks(bio));
-
- bio_set_dev(bio, dev->bdev);
+ DMDEBUG("(%s): BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks",
+ dmz_metadata_label(zmd),
+ bio_op(bio), (unsigned long long)sector, nr_sectors,
+ (unsigned long long)dmz_bio_chunk(zmd, bio),
+ (unsigned long long)dmz_chunk_block(zmd, dmz_bio_block(bio)),
+ (unsigned int)dmz_bio_blocks(bio));
if (!nr_sectors && bio_op(bio) != REQ_OP_WRITE)
return DM_MAPIO_REMAPPED;
@@ -643,10 +651,10 @@
return DM_MAPIO_KILL;
/* Initialize the BIO context */
- bioctx->target = dmz;
+ bioctx->dev = NULL;
bioctx->zone = NULL;
bioctx->bio = bio;
- atomic_set(&bioctx->ref, 1);
+ refcount_set(&bioctx->ref, 1);
/* Set the BIO pending in the flush list */
if (!nr_sectors && bio_op(bio) == REQ_OP_WRITE) {
@@ -658,17 +666,17 @@
}
/* Split zone BIOs to fit entirely into a zone */
- chunk_sector = sector & (dev->zone_nr_sectors - 1);
- if (chunk_sector + nr_sectors > dev->zone_nr_sectors)
- dm_accept_partial_bio(bio, dev->zone_nr_sectors - chunk_sector);
+ chunk_sector = sector & (dmz_zone_nr_sectors(zmd) - 1);
+ if (chunk_sector + nr_sectors > dmz_zone_nr_sectors(zmd))
+ dm_accept_partial_bio(bio, dmz_zone_nr_sectors(zmd) - chunk_sector);
/* Now ready to handle this BIO */
ret = dmz_queue_chunk_work(dmz, bio);
if (ret) {
- dmz_dev_debug(dmz->dev,
- "BIO op %d, can't process chunk %llu, err %i\n",
- bio_op(bio), (u64)dmz_bio_chunk(dmz->dev, bio),
- ret);
+ DMDEBUG("(%s): BIO op %d, can't process chunk %llu, err %i",
+ dmz_metadata_label(zmd),
+ bio_op(bio), (u64)dmz_bio_chunk(zmd, bio),
+ ret);
return DM_MAPIO_REQUEUE;
}
@@ -678,76 +686,144 @@
/*
* Get zoned device information.
*/
-static int dmz_get_zoned_device(struct dm_target *ti, char *path)
+static int dmz_get_zoned_device(struct dm_target *ti, char *path,
+ int idx, int nr_devs)
{
struct dmz_target *dmz = ti->private;
- struct request_queue *q;
+ struct dm_dev *ddev;
struct dmz_dev *dev;
- sector_t aligned_capacity;
int ret;
+ struct block_device *bdev;
/* Get the target device */
- ret = dm_get_device(ti, path, dm_table_get_mode(ti->table), &dmz->ddev);
+ ret = dm_get_device(ti, path, dm_table_get_mode(ti->table), &ddev);
if (ret) {
ti->error = "Get target device failed";
- dmz->ddev = NULL;
return ret;
}
- dev = kzalloc(sizeof(struct dmz_dev), GFP_KERNEL);
- if (!dev) {
- ret = -ENOMEM;
- goto err;
+ bdev = ddev->bdev;
+ if (bdev_zoned_model(bdev) == BLK_ZONED_NONE) {
+ if (nr_devs == 1) {
+ ti->error = "Invalid regular device";
+ goto err;
+ }
+ if (idx != 0) {
+ ti->error = "First device must be a regular device";
+ goto err;
+ }
+ if (dmz->ddev[0]) {
+ ti->error = "Too many regular devices";
+ goto err;
+ }
+ dev = &dmz->dev[idx];
+ dev->flags = DMZ_BDEV_REGULAR;
+ } else {
+ if (dmz->ddev[idx]) {
+ ti->error = "Too many zoned devices";
+ goto err;
+ }
+ if (nr_devs > 1 && idx == 0) {
+ ti->error = "First device must be a regular device";
+ goto err;
+ }
+ dev = &dmz->dev[idx];
}
-
- dev->bdev = dmz->ddev->bdev;
+ dev->bdev = bdev;
+ dev->dev_idx = idx;
(void)bdevname(dev->bdev, dev->name);
- if (bdev_zoned_model(dev->bdev) == BLK_ZONED_NONE) {
- ti->error = "Not a zoned block device";
- ret = -EINVAL;
+ dev->capacity = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
+ if (ti->begin) {
+ ti->error = "Partial mapping is not supported";
goto err;
}
- q = bdev_get_queue(dev->bdev);
- dev->capacity = i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT;
- aligned_capacity = dev->capacity & ~(blk_queue_zone_sectors(q) - 1);
- if (ti->begin ||
- ((ti->len != dev->capacity) && (ti->len != aligned_capacity))) {
- ti->error = "Partial mapping not supported";
- ret = -EINVAL;
- goto err;
- }
-
- dev->zone_nr_sectors = blk_queue_zone_sectors(q);
- dev->zone_nr_sectors_shift = ilog2(dev->zone_nr_sectors);
-
- dev->zone_nr_blocks = dmz_sect2blk(dev->zone_nr_sectors);
- dev->zone_nr_blocks_shift = ilog2(dev->zone_nr_blocks);
-
- dev->nr_zones = (dev->capacity + dev->zone_nr_sectors - 1)
- >> dev->zone_nr_sectors_shift;
-
- dmz->dev = dev;
+ dmz->ddev[idx] = ddev;
return 0;
err:
- dm_put_device(ti, dmz->ddev);
- kfree(dev);
-
- return ret;
+ dm_put_device(ti, ddev);
+ return -EINVAL;
}
/*
* Cleanup zoned device information.
*/
-static void dmz_put_zoned_device(struct dm_target *ti)
+static void dmz_put_zoned_devices(struct dm_target *ti)
{
struct dmz_target *dmz = ti->private;
+ int i;
- dm_put_device(ti, dmz->ddev);
- kfree(dmz->dev);
- dmz->dev = NULL;
+ for (i = 0; i < dmz->nr_ddevs; i++)
+ if (dmz->ddev[i])
+ dm_put_device(ti, dmz->ddev[i]);
+
+ kfree(dmz->ddev);
+}
+
+static int dmz_fixup_devices(struct dm_target *ti)
+{
+ struct dmz_target *dmz = ti->private;
+ struct dmz_dev *reg_dev, *zoned_dev;
+ struct request_queue *q;
+ sector_t zone_nr_sectors = 0;
+ int i;
+
+ /*
+ * When we have more than on devices, the first one must be a
+ * regular block device and the others zoned block devices.
+ */
+ if (dmz->nr_ddevs > 1) {
+ reg_dev = &dmz->dev[0];
+ if (!(reg_dev->flags & DMZ_BDEV_REGULAR)) {
+ ti->error = "Primary disk is not a regular device";
+ return -EINVAL;
+ }
+ for (i = 1; i < dmz->nr_ddevs; i++) {
+ zoned_dev = &dmz->dev[i];
+ if (zoned_dev->flags & DMZ_BDEV_REGULAR) {
+ ti->error = "Secondary disk is not a zoned device";
+ return -EINVAL;
+ }
+ q = bdev_get_queue(zoned_dev->bdev);
+ if (zone_nr_sectors &&
+ zone_nr_sectors != blk_queue_zone_sectors(q)) {
+ ti->error = "Zone nr sectors mismatch";
+ return -EINVAL;
+ }
+ zone_nr_sectors = blk_queue_zone_sectors(q);
+ zoned_dev->zone_nr_sectors = zone_nr_sectors;
+ zoned_dev->nr_zones =
+ blkdev_nr_zones(zoned_dev->bdev->bd_disk);
+ }
+ } else {
+ reg_dev = NULL;
+ zoned_dev = &dmz->dev[0];
+ if (zoned_dev->flags & DMZ_BDEV_REGULAR) {
+ ti->error = "Disk is not a zoned device";
+ return -EINVAL;
+ }
+ q = bdev_get_queue(zoned_dev->bdev);
+ zoned_dev->zone_nr_sectors = blk_queue_zone_sectors(q);
+ zoned_dev->nr_zones = blkdev_nr_zones(zoned_dev->bdev->bd_disk);
+ }
+
+ if (reg_dev) {
+ sector_t zone_offset;
+
+ reg_dev->zone_nr_sectors = zone_nr_sectors;
+ reg_dev->nr_zones =
+ DIV_ROUND_UP_SECTOR_T(reg_dev->capacity,
+ reg_dev->zone_nr_sectors);
+ reg_dev->zone_offset = 0;
+ zone_offset = reg_dev->nr_zones;
+ for (i = 1; i < dmz->nr_ddevs; i++) {
+ dmz->dev[i].zone_offset = zone_offset;
+ zone_offset += dmz->dev[i].nr_zones;
+ }
+ }
+ return 0;
}
/*
@@ -756,11 +832,10 @@
static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
struct dmz_target *dmz;
- struct dmz_dev *dev;
- int ret;
+ int ret, i;
/* Check arguments */
- if (argc != 1) {
+ if (argc < 1) {
ti->error = "Invalid argument count";
return -EINVAL;
}
@@ -771,35 +846,52 @@
ti->error = "Unable to allocate the zoned target descriptor";
return -ENOMEM;
}
+ dmz->dev = kcalloc(argc, sizeof(struct dmz_dev), GFP_KERNEL);
+ if (!dmz->dev) {
+ ti->error = "Unable to allocate the zoned device descriptors";
+ kfree(dmz);
+ return -ENOMEM;
+ }
+ dmz->ddev = kcalloc(argc, sizeof(struct dm_dev *), GFP_KERNEL);
+ if (!dmz->ddev) {
+ ti->error = "Unable to allocate the dm device descriptors";
+ ret = -ENOMEM;
+ goto err;
+ }
+ dmz->nr_ddevs = argc;
+
ti->private = dmz;
/* Get the target zoned block device */
- ret = dmz_get_zoned_device(ti, argv[0]);
- if (ret) {
- dmz->ddev = NULL;
- goto err;
+ for (i = 0; i < argc; i++) {
+ ret = dmz_get_zoned_device(ti, argv[i], i, argc);
+ if (ret)
+ goto err_dev;
}
+ ret = dmz_fixup_devices(ti);
+ if (ret)
+ goto err_dev;
/* Initialize metadata */
- dev = dmz->dev;
- ret = dmz_ctr_metadata(dev, &dmz->metadata);
+ ret = dmz_ctr_metadata(dmz->dev, argc, &dmz->metadata,
+ dm_table_device_name(ti->table));
if (ret) {
ti->error = "Metadata initialization failed";
goto err_dev;
}
/* Set target (no write same support) */
- ti->max_io_len = dev->zone_nr_sectors;
+ ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata);
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->num_write_zeroes_bios = 1;
ti->per_io_data_size = sizeof(struct dmz_bioctx);
ti->flush_supported = true;
ti->discards_supported = true;
- ti->split_discard_bios = true;
/* The exposed capacity is the number of chunks that can be mapped */
- ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) << dev->zone_nr_sectors_shift;
+ ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) <<
+ dmz_zone_nr_sectors_shift(dmz->metadata);
/* Zone BIO */
ret = bioset_init(&dmz->bio_set, DMZ_MIN_BIOS, 0, 0);
@@ -811,8 +903,9 @@
/* Chunk BIO work */
mutex_init(&dmz->chunk_lock);
INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOIO);
- dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s", WQ_MEM_RECLAIM | WQ_UNBOUND,
- 0, dev->name);
+ dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, 0,
+ dmz_metadata_label(dmz->metadata));
if (!dmz->chunk_wq) {
ti->error = "Create chunk workqueue failed";
ret = -ENOMEM;
@@ -824,7 +917,7 @@
bio_list_init(&dmz->flush_list);
INIT_DELAYED_WORK(&dmz->flush_work, dmz_flush_work);
dmz->flush_wq = alloc_ordered_workqueue("dmz_fwq_%s", WQ_MEM_RECLAIM,
- dev->name);
+ dmz_metadata_label(dmz->metadata));
if (!dmz->flush_wq) {
ti->error = "Create flush workqueue failed";
ret = -ENOMEM;
@@ -833,15 +926,18 @@
mod_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD);
/* Initialize reclaim */
- ret = dmz_ctr_reclaim(dev, dmz->metadata, &dmz->reclaim);
- if (ret) {
- ti->error = "Zone reclaim initialization failed";
- goto err_fwq;
+ for (i = 0; i < dmz->nr_ddevs; i++) {
+ ret = dmz_ctr_reclaim(dmz->metadata, &dmz->dev[i].reclaim, i);
+ if (ret) {
+ ti->error = "Zone reclaim initialization failed";
+ goto err_fwq;
+ }
}
- dmz_dev_info(dev, "Target device: %llu 512-byte logical sectors (%llu blocks)",
- (unsigned long long)ti->len,
- (unsigned long long)dmz_sect2blk(ti->len));
+ DMINFO("(%s): Target device: %llu 512-byte logical sectors (%llu blocks)",
+ dmz_metadata_label(dmz->metadata),
+ (unsigned long long)ti->len,
+ (unsigned long long)dmz_sect2blk(ti->len));
return 0;
err_fwq:
@@ -854,8 +950,9 @@
err_meta:
dmz_dtr_metadata(dmz->metadata);
err_dev:
- dmz_put_zoned_device(ti);
+ dmz_put_zoned_devices(ti);
err:
+ kfree(dmz->dev);
kfree(dmz);
return ret;
@@ -867,11 +964,13 @@
static void dmz_dtr(struct dm_target *ti)
{
struct dmz_target *dmz = ti->private;
+ int i;
flush_workqueue(dmz->chunk_wq);
destroy_workqueue(dmz->chunk_wq);
- dmz_dtr_reclaim(dmz->reclaim);
+ for (i = 0; i < dmz->nr_ddevs; i++)
+ dmz_dtr_reclaim(dmz->dev[i].reclaim);
cancel_delayed_work_sync(&dmz->flush_work);
destroy_workqueue(dmz->flush_wq);
@@ -882,10 +981,11 @@
bioset_exit(&dmz->bio_set);
- dmz_put_zoned_device(ti);
+ dmz_put_zoned_devices(ti);
mutex_destroy(&dmz->chunk_lock);
+ kfree(dmz->dev);
kfree(dmz);
}
@@ -895,7 +995,7 @@
static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
struct dmz_target *dmz = ti->private;
- unsigned int chunk_sectors = dmz->dev->zone_nr_sectors;
+ unsigned int chunk_sectors = dmz_zone_nr_sectors(dmz->metadata);
limits->logical_block_size = DMZ_BLOCK_SIZE;
limits->physical_block_size = DMZ_BLOCK_SIZE;
@@ -923,11 +1023,12 @@
static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
{
struct dmz_target *dmz = ti->private;
+ struct dmz_dev *dev = &dmz->dev[0];
- if (!dmz_check_bdev(dmz->dev))
+ if (!dmz_check_bdev(dev))
return -EIO;
- *bdev = dmz->dev->bdev;
+ *bdev = dev->bdev;
return 0;
}
@@ -938,9 +1039,11 @@
static void dmz_suspend(struct dm_target *ti)
{
struct dmz_target *dmz = ti->private;
+ int i;
flush_workqueue(dmz->chunk_wq);
- dmz_suspend_reclaim(dmz->reclaim);
+ for (i = 0; i < dmz->nr_ddevs; i++)
+ dmz_suspend_reclaim(dmz->dev[i].reclaim);
cancel_delayed_work_sync(&dmz->flush_work);
}
@@ -950,25 +1053,96 @@
static void dmz_resume(struct dm_target *ti)
{
struct dmz_target *dmz = ti->private;
+ int i;
queue_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD);
- dmz_resume_reclaim(dmz->reclaim);
+ for (i = 0; i < dmz->nr_ddevs; i++)
+ dmz_resume_reclaim(dmz->dev[i].reclaim);
}
static int dmz_iterate_devices(struct dm_target *ti,
iterate_devices_callout_fn fn, void *data)
{
struct dmz_target *dmz = ti->private;
- struct dmz_dev *dev = dmz->dev;
- sector_t capacity = dev->capacity & ~(dev->zone_nr_sectors - 1);
+ unsigned int zone_nr_sectors = dmz_zone_nr_sectors(dmz->metadata);
+ sector_t capacity;
+ int i, r;
- return fn(ti, dmz->ddev, 0, capacity, data);
+ for (i = 0; i < dmz->nr_ddevs; i++) {
+ capacity = dmz->dev[i].capacity & ~(zone_nr_sectors - 1);
+ r = fn(ti, dmz->ddev[i], 0, capacity, data);
+ if (r)
+ break;
+ }
+ return r;
+}
+
+static void dmz_status(struct dm_target *ti, status_type_t type,
+ unsigned int status_flags, char *result,
+ unsigned int maxlen)
+{
+ struct dmz_target *dmz = ti->private;
+ ssize_t sz = 0;
+ char buf[BDEVNAME_SIZE];
+ struct dmz_dev *dev;
+ int i;
+
+ switch (type) {
+ case STATUSTYPE_INFO:
+ DMEMIT("%u zones %u/%u cache",
+ dmz_nr_zones(dmz->metadata),
+ dmz_nr_unmap_cache_zones(dmz->metadata),
+ dmz_nr_cache_zones(dmz->metadata));
+ for (i = 0; i < dmz->nr_ddevs; i++) {
+ /*
+ * For a multi-device setup the first device
+ * contains only cache zones.
+ */
+ if ((i == 0) &&
+ (dmz_nr_cache_zones(dmz->metadata) > 0))
+ continue;
+ DMEMIT(" %u/%u random %u/%u sequential",
+ dmz_nr_unmap_rnd_zones(dmz->metadata, i),
+ dmz_nr_rnd_zones(dmz->metadata, i),
+ dmz_nr_unmap_seq_zones(dmz->metadata, i),
+ dmz_nr_seq_zones(dmz->metadata, i));
+ }
+ break;
+ case STATUSTYPE_TABLE:
+ dev = &dmz->dev[0];
+ format_dev_t(buf, dev->bdev->bd_dev);
+ DMEMIT("%s", buf);
+ for (i = 1; i < dmz->nr_ddevs; i++) {
+ dev = &dmz->dev[i];
+ format_dev_t(buf, dev->bdev->bd_dev);
+ DMEMIT(" %s", buf);
+ }
+ break;
+ }
+ return;
+}
+
+static int dmz_message(struct dm_target *ti, unsigned int argc, char **argv,
+ char *result, unsigned int maxlen)
+{
+ struct dmz_target *dmz = ti->private;
+ int r = -EINVAL;
+
+ if (!strcasecmp(argv[0], "reclaim")) {
+ int i;
+
+ for (i = 0; i < dmz->nr_ddevs; i++)
+ dmz_schedule_reclaim(dmz->dev[i].reclaim);
+ r = 0;
+ } else
+ DMERR("unrecognized message %s", argv[0]);
+ return r;
}
static struct target_type dmz_type = {
.name = "zoned",
- .version = {1, 0, 0},
- .features = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM,
+ .version = {2, 0, 0},
+ .features = DM_TARGET_SINGLETON | DM_TARGET_MIXED_ZONED_MODEL,
.module = THIS_MODULE,
.ctr = dmz_ctr,
.dtr = dmz_dtr,
@@ -978,6 +1152,8 @@
.postsuspend = dmz_suspend,
.resume = dmz_resume,
.iterate_devices = dmz_iterate_devices,
+ .status = dmz_status,
+ .message = dmz_message,
};
static int __init dmz_init(void)
--
Gitblit v1.6.2