summaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/dm-integrity.c4
-rw-r--r--drivers/md/dm-ioctl.c2
-rw-r--r--drivers/md/dm-rq.c4
-rw-r--r--drivers/md/dm-writecache.c16
-rw-r--r--drivers/md/dm-zoned-metadata.c51
-rw-r--r--drivers/md/dm-zoned-reclaim.c11
-rw-r--r--drivers/md/dm-zoned-target.c12
-rw-r--r--drivers/md/dm.c109
8 files changed, 143 insertions, 66 deletions
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index ae866e469e1b..5da3eb661e50 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -2420,7 +2420,7 @@ static void integrity_writer(struct work_struct *w)
unsigned prev_free_sectors;
/* the following test is not needed, but it tests the replay code */
- if (unlikely(dm_suspended(ic->ti)) && !ic->meta_dev)
+ if (unlikely(dm_post_suspending(ic->ti)) && !ic->meta_dev)
return;
spin_lock_irq(&ic->endio_wait.lock);
@@ -2481,7 +2481,7 @@ static void integrity_recalc(struct work_struct *w)
next_chunk:
- if (unlikely(dm_suspended(ic->ti)))
+ if (unlikely(dm_post_suspending(ic->ti)))
goto unlock_ret;
range.logical_sector = le64_to_cpu(ic->sb->recalc_sector);
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index ac83f5002ce5..489935d5f22d 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -1471,7 +1471,7 @@ static void retrieve_deps(struct dm_table *table,
/*
* Check we have enough space.
*/
- needed = sizeof(*deps) + (sizeof(*deps->dev) * count);
+ needed = struct_size(deps, dev, count);
if (len < needed) {
param->flags |= DM_BUFFER_FULL_FLAG;
return;
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 5aec1cd09348..7ce387a1cc6a 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -146,10 +146,6 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig)
*/
static void rq_completed(struct mapped_device *md)
{
- /* nudge anyone waiting on suspend queue */
- if (unlikely(wq_has_sleeper(&md->wait)))
- wake_up(&md->wait);
-
/*
* dm_put() must be at the end of this function. See the comment above
*/
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 62421554b838..8aa306ebc2ab 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -282,6 +282,8 @@ static int persistent_memory_claim(struct dm_writecache *wc)
while (daa-- && i < p) {
pages[i++] = pfn_t_to_page(pfn);
pfn.val++;
+ if (!(i & 15))
+ cond_resched();
}
} while (i < p);
wc->memory_map = vmap(pages, p, VM_MAP, PAGE_KERNEL);
@@ -849,10 +851,14 @@ static void writecache_discard(struct dm_writecache *wc, sector_t start, sector_
if (likely(!e->write_in_progress)) {
if (!discarded_something) {
- writecache_wait_for_ios(wc, READ);
- writecache_wait_for_ios(wc, WRITE);
+ if (!WC_MODE_PMEM(wc)) {
+ writecache_wait_for_ios(wc, READ);
+ writecache_wait_for_ios(wc, WRITE);
+ }
discarded_something = true;
}
+ if (!writecache_entry_is_committed(wc, e))
+ wc->uncommitted_blocks--;
writecache_free_entry(wc, e);
}
@@ -2260,6 +2266,12 @@ invalid_optional:
}
if (WC_MODE_PMEM(wc)) {
+ if (!dax_synchronous(wc->ssd_dev->dax_dev)) {
+ r = -EOPNOTSUPP;
+ ti->error = "Asynchronous persistent memory not supported as pmem cache";
+ goto bad;
+ }
+
r = persistent_memory_claim(wc);
if (r) {
ti->error = "Unable to map persistent memory for cache";
diff --git a/drivers/md/dm-zoned-metadata.c b/drivers/md/dm-zoned-metadata.c
index 130b5a6d9f12..b298fefb022e 100644
--- a/drivers/md/dm-zoned-metadata.c
+++ b/drivers/md/dm-zoned-metadata.c
@@ -1078,7 +1078,8 @@ static int dmz_check_sb(struct dmz_metadata *zmd, struct dmz_sb *dsb,
nr_meta_zones = (le32_to_cpu(sb->nr_meta_blocks) + zmd->zone_nr_blocks - 1)
>> zmd->zone_nr_blocks_shift;
if (!nr_meta_zones ||
- nr_meta_zones >= zmd->nr_rnd_zones) {
+ (zmd->nr_devs <= 1 && nr_meta_zones >= zmd->nr_rnd_zones) ||
+ (zmd->nr_devs > 1 && nr_meta_zones >= zmd->nr_cache_zones)) {
dmz_dev_err(dev, "Invalid number of metadata blocks");
return -ENXIO;
}
@@ -1949,7 +1950,7 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd,
unsigned int idx, bool idle)
{
struct dm_zone *dzone = NULL;
- struct dm_zone *zone, *last = NULL;
+ struct dm_zone *zone, *maxw_z = NULL;
struct list_head *zone_list;
/* If we have cache zones select from the cache zone list */
@@ -1961,18 +1962,37 @@ static struct dm_zone *dmz_get_rnd_zone_for_reclaim(struct dmz_metadata *zmd,
} else
zone_list = &zmd->dev[idx].map_rnd_list;
+ /*
+ * Find the buffer zone with the heaviest weight or the first (oldest)
+ * data zone that can be reclaimed.
+ */
list_for_each_entry(zone, zone_list, link) {
if (dmz_is_buf(zone)) {
dzone = zone->bzone;
- if (dzone->dev->dev_idx != idx)
- continue;
- if (!last) {
- last = dzone;
+ if (dmz_is_rnd(dzone) && dzone->dev->dev_idx != idx)
continue;
- }
- if (last->weight < dzone->weight)
+ if (!maxw_z || maxw_z->weight < dzone->weight)
+ maxw_z = dzone;
+ } else {
+ dzone = zone;
+ if (dmz_lock_zone_reclaim(dzone))
+ return dzone;
+ }
+ }
+
+ if (maxw_z && dmz_lock_zone_reclaim(maxw_z))
+ return maxw_z;
+
+ /*
+ * If we come here, none of the zones inspected could be locked for
+ * reclaim. Try again, being more aggressive, that is, find the
+ * first zone that can be reclaimed regardless of its weitght.
+ */
+ list_for_each_entry(zone, zone_list, link) {
+ if (dmz_is_buf(zone)) {
+ dzone = zone->bzone;
+ if (dmz_is_rnd(dzone) && dzone->dev->dev_idx != idx)
continue;
- dzone = last;
} else
dzone = zone;
if (dmz_lock_zone_reclaim(dzone))
@@ -2006,7 +2026,7 @@ static struct dm_zone *dmz_get_seq_zone_for_reclaim(struct dmz_metadata *zmd,
struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd,
unsigned int dev_idx, bool idle)
{
- struct dm_zone *zone;
+ struct dm_zone *zone = NULL;
/*
* Search for a zone candidate to reclaim: 2 cases are possible.
@@ -2019,7 +2039,7 @@ struct dm_zone *dmz_get_zone_for_reclaim(struct dmz_metadata *zmd,
dmz_lock_map(zmd);
if (list_empty(&zmd->reserved_seq_zones_list))
zone = dmz_get_seq_zone_for_reclaim(zmd, dev_idx);
- else
+ if (!zone)
zone = dmz_get_rnd_zone_for_reclaim(zmd, dev_idx, idle);
dmz_unlock_map(zmd);
@@ -2197,8 +2217,15 @@ struct dm_zone *dmz_alloc_zone(struct dmz_metadata *zmd, unsigned int dev_idx,
{
struct list_head *list;
struct dm_zone *zone;
- int i = 0;
+ int i;
+
+ /* Schedule reclaim to ensure free zones are available */
+ if (!(flags & DMZ_ALLOC_RECLAIM)) {
+ for (i = 0; i < zmd->nr_devs; i++)
+ dmz_schedule_reclaim(zmd->dev[i].reclaim);
+ }
+ i = 0;
again:
if (flags & DMZ_ALLOC_CACHE)
list = &zmd->unmap_cache_list;
diff --git a/drivers/md/dm-zoned-reclaim.c b/drivers/md/dm-zoned-reclaim.c
index 2261b4dd60b7..9c0ecc9568a4 100644
--- a/drivers/md/dm-zoned-reclaim.c
+++ b/drivers/md/dm-zoned-reclaim.c
@@ -377,6 +377,7 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
dmz_metadata_label(zmd), zrc->dev_idx);
return -EBUSY;
}
+ rzone = dzone;
start = jiffies;
if (dmz_is_cache(dzone) || dmz_is_rnd(dzone)) {
@@ -391,8 +392,6 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
*/
ret = dmz_reclaim_rnd_data(zrc, dzone);
}
- rzone = dzone;
-
} else {
struct dm_zone *bzone = dzone->bzone;
sector_t chunk_block = 0;
@@ -415,7 +414,6 @@ static int dmz_do_reclaim(struct dmz_reclaim *zrc)
* be later reclaimed.
*/
ret = dmz_reclaim_seq_data(zrc, dzone);
- rzone = dzone;
}
}
out:
@@ -458,6 +456,8 @@ static unsigned int dmz_reclaim_percentage(struct dmz_reclaim *zrc)
nr_zones = dmz_nr_rnd_zones(zmd, zrc->dev_idx);
nr_unmap = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx);
}
+ if (nr_unmap <= 1)
+ return 0;
return nr_unmap * 100 / nr_zones;
}
@@ -503,7 +503,7 @@ static void dmz_reclaim_work(struct work_struct *work)
{
struct dmz_reclaim *zrc = container_of(work, struct dmz_reclaim, work.work);
struct dmz_metadata *zmd = zrc->metadata;
- unsigned int p_unmap, nr_unmap_rnd = 0, nr_rnd = 0;
+ unsigned int p_unmap;
int ret;
if (dmz_dev_is_dying(zmd))
@@ -529,9 +529,6 @@ static void dmz_reclaim_work(struct work_struct *work)
zrc->kc_throttle.throttle = min(75U, 100U - p_unmap / 2);
}
- nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd, zrc->dev_idx);
- nr_rnd = dmz_nr_rnd_zones(zmd, zrc->dev_idx);
-
DMDEBUG("(%s/%u): Reclaim (%u): %s, %u%% free zones (%u/%u cache %u/%u random)",
dmz_metadata_label(zmd), zrc->dev_idx,
zrc->kc_throttle.throttle,
diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c
index 05a3cfefe937..697f9de37355 100644
--- a/drivers/md/dm-zoned-target.c
+++ b/drivers/md/dm-zoned-target.c
@@ -400,15 +400,7 @@ static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw,
dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
struct dmz_metadata *zmd = dmz->metadata;
struct dm_zone *zone;
- int i, ret;
-
- /*
- * Write may trigger a zone allocation. So make sure the
- * allocation can succeed.
- */
- if (bio_op(bio) == REQ_OP_WRITE)
- for (i = 0; i < dmz->nr_ddevs; i++)
- dmz_schedule_reclaim(dmz->dev[i].reclaim);
+ int ret;
dmz_lock_metadata(zmd);
@@ -890,7 +882,7 @@ static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
}
/* Set target (no write same support) */
- ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata) << 9;
+ 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;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index e2148fcb88bb..87cf45f619fd 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -12,6 +12,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/mutex.h>
+#include <linux/sched/mm.h>
#include <linux/sched/signal.h>
#include <linux/blkpg.h>
#include <linux/bio.h>
@@ -142,6 +143,7 @@ EXPORT_SYMBOL_GPL(dm_bio_get_target_bio_nr);
#define DMF_NOFLUSH_SUSPENDING 5
#define DMF_DEFERRED_REMOVE 6
#define DMF_SUSPENDED_INTERNALLY 7
+#define DMF_POST_SUSPENDING 8
#define DM_NUMA_NODE NUMA_NO_NODE
static int dm_numa_node = DM_NUMA_NODE;
@@ -654,28 +656,6 @@ static void free_tio(struct dm_target_io *tio)
bio_put(&tio->clone);
}
-static bool md_in_flight_bios(struct mapped_device *md)
-{
- int cpu;
- struct hd_struct *part = &dm_disk(md)->part0;
- long sum = 0;
-
- for_each_possible_cpu(cpu) {
- sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
- sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
- }
-
- return sum != 0;
-}
-
-static bool md_in_flight(struct mapped_device *md)
-{
- if (queue_is_mq(md->queue))
- return blk_mq_queue_inflight(md->queue);
- else
- return md_in_flight_bios(md);
-}
-
u64 dm_start_time_ns_from_clone(struct bio *bio)
{
struct dm_target_io *tio = container_of(bio, struct dm_target_io, clone);
@@ -1009,6 +989,7 @@ static void clone_endio(struct bio *bio)
struct dm_io *io = tio->io;
struct mapped_device *md = tio->io->md;
dm_endio_fn endio = tio->ti->type->end_io;
+ struct bio *orig_bio = io->orig_bio;
if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) {
if (bio_op(bio) == REQ_OP_DISCARD &&
@@ -1022,6 +1003,18 @@ static void clone_endio(struct bio *bio)
disable_write_zeroes(md);
}
+ /*
+ * For zone-append bios get offset in zone of the written
+ * sector and add that to the original bio sector pos.
+ */
+ if (bio_op(orig_bio) == REQ_OP_ZONE_APPEND) {
+ sector_t written_sector = bio->bi_iter.bi_sector;
+ struct request_queue *q = orig_bio->bi_disk->queue;
+ u64 mask = (u64)blk_queue_zone_sectors(q) - 1;
+
+ orig_bio->bi_iter.bi_sector += written_sector & mask;
+ }
+
if (endio) {
int r = endio(tio->ti, bio, &error);
switch (r) {
@@ -2378,6 +2371,7 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
if (!dm_suspended_md(md)) {
dm_table_presuspend_targets(map);
set_bit(DMF_SUSPENDED, &md->flags);
+ set_bit(DMF_POST_SUSPENDING, &md->flags);
dm_table_postsuspend_targets(map);
}
/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
@@ -2418,15 +2412,29 @@ void dm_put(struct mapped_device *md)
}
EXPORT_SYMBOL_GPL(dm_put);
-static int dm_wait_for_completion(struct mapped_device *md, long task_state)
+static bool md_in_flight_bios(struct mapped_device *md)
+{
+ int cpu;
+ struct hd_struct *part = &dm_disk(md)->part0;
+ long sum = 0;
+
+ for_each_possible_cpu(cpu) {
+ sum += part_stat_local_read_cpu(part, in_flight[0], cpu);
+ sum += part_stat_local_read_cpu(part, in_flight[1], cpu);
+ }
+
+ return sum != 0;
+}
+
+static int dm_wait_for_bios_completion(struct mapped_device *md, long task_state)
{
int r = 0;
DEFINE_WAIT(wait);
- while (1) {
+ while (true) {
prepare_to_wait(&md->wait, &wait, task_state);
- if (!md_in_flight(md))
+ if (!md_in_flight_bios(md))
break;
if (signal_pending_state(task_state, current)) {
@@ -2441,6 +2449,28 @@ static int dm_wait_for_completion(struct mapped_device *md, long task_state)
return r;
}
+static int dm_wait_for_completion(struct mapped_device *md, long task_state)
+{
+ int r = 0;
+
+ if (!queue_is_mq(md->queue))
+ return dm_wait_for_bios_completion(md, task_state);
+
+ while (true) {
+ if (!blk_mq_queue_inflight(md->queue))
+ break;
+
+ if (signal_pending_state(task_state, current)) {
+ r = -EINTR;
+ break;
+ }
+
+ msleep(5);
+ }
+
+ return r;
+}
+
/*
* Process the deferred bios
*/
@@ -2700,7 +2730,9 @@ retry:
if (r)
goto out_unlock;
+ set_bit(DMF_POST_SUSPENDING, &md->flags);
dm_table_postsuspend_targets(map);
+ clear_bit(DMF_POST_SUSPENDING, &md->flags);
out_unlock:
mutex_unlock(&md->suspend_lock);
@@ -2797,7 +2829,9 @@ static void __dm_internal_suspend(struct mapped_device *md, unsigned suspend_fla
(void) __dm_suspend(md, map, suspend_flags, TASK_UNINTERRUPTIBLE,
DMF_SUSPENDED_INTERNALLY);
+ set_bit(DMF_POST_SUSPENDING, &md->flags);
dm_table_postsuspend_targets(map);
+ clear_bit(DMF_POST_SUSPENDING, &md->flags);
}
static void __dm_internal_resume(struct mapped_device *md)
@@ -2874,17 +2908,25 @@ EXPORT_SYMBOL_GPL(dm_internal_resume_fast);
int dm_kobject_uevent(struct mapped_device *md, enum kobject_action action,
unsigned cookie)
{
+ int r;
+ unsigned noio_flag;
char udev_cookie[DM_COOKIE_LENGTH];
char *envp[] = { udev_cookie, NULL };
+ noio_flag = memalloc_noio_save();
+
if (!cookie)
- return kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
+ r = kobject_uevent(&disk_to_dev(md->disk)->kobj, action);
else {
snprintf(udev_cookie, DM_COOKIE_LENGTH, "%s=%u",
DM_COOKIE_ENV_VAR_NAME, cookie);
- return kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
- action, envp);
+ r = kobject_uevent_env(&disk_to_dev(md->disk)->kobj,
+ action, envp);
}
+
+ memalloc_noio_restore(noio_flag);
+
+ return r;
}
uint32_t dm_next_uevent_seq(struct mapped_device *md)
@@ -2950,6 +2992,11 @@ int dm_suspended_md(struct mapped_device *md)
return test_bit(DMF_SUSPENDED, &md->flags);
}
+static int dm_post_suspending_md(struct mapped_device *md)
+{
+ return test_bit(DMF_POST_SUSPENDING, &md->flags);
+}
+
int dm_suspended_internally_md(struct mapped_device *md)
{
return test_bit(DMF_SUSPENDED_INTERNALLY, &md->flags);
@@ -2966,6 +3013,12 @@ int dm_suspended(struct dm_target *ti)
}
EXPORT_SYMBOL_GPL(dm_suspended);
+int dm_post_suspending(struct dm_target *ti)
+{
+ return dm_post_suspending_md(dm_table_get_md(ti->table));
+}
+EXPORT_SYMBOL_GPL(dm_post_suspending);
+
int dm_noflush_suspending(struct dm_target *ti)
{
return __noflush_suspending(dm_table_get_md(ti->table));
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-20 06:04:16 +0300