From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Tue, 20 Feb 2024 01:20:52 +0000 Subject: [PATCH] add new system file --- kernel/drivers/md/dm-cache-target.c | 248 ++++++++++++++++++++++++++++--------------------- 1 files changed, 141 insertions(+), 107 deletions(-) diff --git a/kernel/drivers/md/dm-cache-target.c b/kernel/drivers/md/dm-cache-target.c index 2ddd575..f98ad43 100644 --- a/kernel/drivers/md/dm-cache-target.c +++ b/kernel/drivers/md/dm-cache-target.c @@ -74,22 +74,19 @@ static bool iot_idle_for(struct io_tracker *iot, unsigned long jifs) { bool r; - unsigned long flags; - spin_lock_irqsave(&iot->lock, flags); + spin_lock_irq(&iot->lock); r = __iot_idle_for(iot, jifs); - spin_unlock_irqrestore(&iot->lock, flags); + spin_unlock_irq(&iot->lock); return r; } static void iot_io_begin(struct io_tracker *iot, sector_t len) { - unsigned long flags; - - spin_lock_irqsave(&iot->lock, flags); + spin_lock_irq(&iot->lock); iot->in_flight += len; - spin_unlock_irqrestore(&iot->lock, flags); + spin_unlock_irq(&iot->lock); } static void __iot_io_end(struct io_tracker *iot, sector_t len) @@ -172,7 +169,6 @@ { struct batcher *b = container_of(_ws, struct batcher, commit_work); blk_status_t r; - unsigned long flags; struct list_head work_items; struct work_struct *ws, *tmp; struct continuation *k; @@ -186,12 +182,12 @@ * We have to grab these before the commit_op to avoid a race * condition. */ - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); list_splice_init(&b->work_items, &work_items); bio_list_merge(&bios, &b->bios); bio_list_init(&b->bios); b->commit_scheduled = false; - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); r = b->commit_op(b->commit_context); @@ -238,13 +234,12 @@ static void continue_after_commit(struct batcher *b, struct continuation *k) { - unsigned long flags; bool commit_scheduled; - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); commit_scheduled = b->commit_scheduled; list_add_tail(&k->ws.entry, &b->work_items); - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); if (commit_scheduled) async_commit(b); @@ -255,13 +250,12 @@ */ static void issue_after_commit(struct batcher *b, struct bio *bio) { - unsigned long flags; bool commit_scheduled; - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); commit_scheduled = b->commit_scheduled; bio_list_add(&b->bios, bio); - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); if (commit_scheduled) async_commit(b); @@ -273,12 +267,11 @@ static void schedule_commit(struct batcher *b) { bool immediate; - unsigned long flags; - spin_lock_irqsave(&b->lock, flags); + spin_lock_irq(&b->lock); immediate = !list_empty(&b->work_items) || !bio_list_empty(&b->bios); b->commit_scheduled = true; - spin_unlock_irqrestore(&b->lock, flags); + spin_unlock_irq(&b->lock); if (immediate) async_commit(b); @@ -353,6 +346,7 @@ enum cache_metadata_mode mode; enum cache_io_mode io_mode; unsigned metadata_version; + bool discard_passdown:1; }; struct cache_stats { @@ -426,8 +420,6 @@ struct bio_list deferred_bios; struct rw_semaphore quiesce_lock; - - struct dm_target_callbacks callbacks; /* * origin_blocks entries, discarded if set. @@ -629,23 +621,19 @@ static void defer_bio(struct cache *cache, struct bio *bio) { - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); bio_list_add(&cache->deferred_bios, bio); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); wake_deferred_bio_worker(cache); } static void defer_bios(struct cache *cache, struct bio_list *bios) { - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); bio_list_merge(&cache->deferred_bios, bios); bio_list_init(bios); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); wake_deferred_bio_worker(cache); } @@ -724,10 +712,6 @@ return cache->sectors_per_block_shift >= 0; } -/* gcc on ARM generates spurious references to __udivdi3 and __umoddi3 */ -#if defined(CONFIG_ARM) && __GNUC__ == 4 && __GNUC_MINOR__ <= 6 -__always_inline -#endif static dm_block_t block_div(dm_block_t b, uint32_t n) { do_div(b, n); @@ -755,33 +739,27 @@ static void set_discard(struct cache *cache, dm_dblock_t b) { - unsigned long flags; - BUG_ON(from_dblock(b) >= from_dblock(cache->discard_nr_blocks)); atomic_inc(&cache->stats.discard_count); - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); set_bit(from_dblock(b), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); } static void clear_discard(struct cache *cache, dm_dblock_t b) { - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); clear_bit(from_dblock(b), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); } static bool is_discarded(struct cache *cache, dm_dblock_t b) { int r; - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); r = test_bit(from_dblock(b), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); return r; } @@ -789,12 +767,10 @@ static bool is_discarded_oblock(struct cache *cache, dm_oblock_t b) { int r; - unsigned long flags; - - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); r = test_bit(from_dblock(oblock_to_dblock(cache, b)), cache->discard_bitset); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); return r; } @@ -826,17 +802,16 @@ static void check_if_tick_bio_needed(struct cache *cache, struct bio *bio) { - unsigned long flags; struct per_bio_data *pb; - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); if (cache->need_tick_bio && !op_is_flush(bio->bi_opf) && bio_op(bio) != REQ_OP_DISCARD) { pb = get_per_bio_data(bio); pb->tick = true; cache->need_tick_bio = false; } - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); } static void __remap_to_origin_clear_discard(struct cache *cache, struct bio *bio, @@ -905,7 +880,7 @@ static void accounted_request(struct cache *cache, struct bio *bio) { accounted_begin(cache, bio); - generic_make_request(bio); + submit_bio_noacct(bio); } static void issue_op(struct bio *bio, void *context) @@ -946,7 +921,7 @@ static const char *cache_device_name(struct cache *cache) { - return dm_device_name(dm_table_get_md(cache->ti->table)); + return dm_table_device_name(cache->ti->table); } static void notify_mode_switch(struct cache *cache, enum cache_metadata_mode mode) @@ -1010,14 +985,14 @@ if (get_cache_mode(cache) >= CM_READ_ONLY) return; - if (dm_cache_metadata_set_needs_check(cache->cmd)) { - DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name); - set_cache_mode(cache, CM_FAIL); - } - DMERR_LIMIT("%s: aborting current metadata transaction", dev_name); if (dm_cache_metadata_abort(cache->cmd)) { DMERR("%s: failed to abort metadata transaction", dev_name); + set_cache_mode(cache, CM_FAIL); + } + + if (dm_cache_metadata_set_needs_check(cache->cmd)) { + DMERR("%s: failed to set 'needs_check' flag in metadata", dev_name); set_cache_mode(cache, CM_FAIL); } } @@ -1811,7 +1786,7 @@ bool commit_needed; if (map_bio(cache, bio, get_bio_block(cache, bio), &commit_needed) == DM_MAPIO_REMAPPED) - generic_make_request(bio); + submit_bio_noacct(bio); return commit_needed; } @@ -1875,7 +1850,11 @@ b = to_dblock(from_dblock(b) + 1); } - bio_endio(bio); + if (cache->features.discard_passdown) { + remap_to_origin(cache, bio); + submit_bio_noacct(bio); + } else + bio_endio(bio); return false; } @@ -1884,17 +1863,16 @@ { struct cache *cache = container_of(ws, struct cache, deferred_bio_worker); - unsigned long flags; bool commit_needed = false; struct bio_list bios; struct bio *bio; bio_list_init(&bios); - spin_lock_irqsave(&cache->lock, flags); + spin_lock_irq(&cache->lock); bio_list_merge(&bios, &cache->deferred_bios); bio_list_init(&cache->deferred_bios); - spin_unlock_irqrestore(&cache->lock, flags); + spin_unlock_irq(&cache->lock); while ((bio = bio_list_pop(&bios))) { if (bio->bi_opf & REQ_PREFLUSH) @@ -1905,6 +1883,7 @@ else commit_needed = process_bio(cache, bio) || commit_needed; + cond_resched(); } if (commit_needed) @@ -1927,6 +1906,7 @@ while ((bio = bio_list_pop(&bios))) { bio->bi_status = BLK_STS_DM_REQUEUE; bio_endio(bio); + cond_resched(); } } @@ -1967,6 +1947,8 @@ r = mg_start(cache, op, NULL); if (r) break; + + cond_resched(); } } @@ -1987,6 +1969,7 @@ if (cache->prison) dm_bio_prison_destroy_v2(cache->prison); + cancel_delayed_work_sync(&cache->waker); if (cache->wq) destroy_workqueue(cache->wq); @@ -2209,13 +2192,14 @@ cf->mode = CM_WRITE; cf->io_mode = CM_IO_WRITEBACK; cf->metadata_version = 1; + cf->discard_passdown = true; } static int parse_features(struct cache_args *ca, struct dm_arg_set *as, char **error) { static const struct dm_arg _args[] = { - {0, 2, "Invalid number of cache feature arguments"}, + {0, 3, "Invalid number of cache feature arguments"}, }; int r, mode_ctr = 0; @@ -2249,6 +2233,9 @@ else if (!strcasecmp(arg, "metadata2")) cf->metadata_version = 2; + + else if (!strcasecmp(arg, "no_discard_passdown")) + cf->discard_passdown = false; else { *error = "Unrecognised cache feature requested"; @@ -2435,20 +2422,6 @@ cache->cache_size = size; } -static int is_congested(struct dm_dev *dev, int bdi_bits) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - return bdi_congested(q->backing_dev_info, bdi_bits); -} - -static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits) -{ - struct cache *cache = container_of(cb, struct cache, callbacks); - - return is_congested(cache->origin_dev, bdi_bits) || - is_congested(cache->cache_dev, bdi_bits); -} - #define DEFAULT_MIGRATION_THRESHOLD 2048 static int cache_create(struct cache_args *ca, struct cache **result) @@ -2472,7 +2445,6 @@ ti->num_discard_bios = 1; ti->discards_supported = true; - ti->split_discard_bios = false; ti->per_io_data_size = sizeof(struct per_bio_data); @@ -2483,9 +2455,6 @@ if (r) goto bad; } - - cache->callbacks.congested_fn = cache_is_congested; - dm_table_add_target_callbacks(ti->table, &cache->callbacks); cache->metadata_dev = ca->metadata_dev; cache->origin_dev = ca->origin_dev; @@ -3096,6 +3065,39 @@ do_waker(&cache->waker.work); } +static void emit_flags(struct cache *cache, char *result, + unsigned maxlen, ssize_t *sz_ptr) +{ + ssize_t sz = *sz_ptr; + struct cache_features *cf = &cache->features; + unsigned count = (cf->metadata_version == 2) + !cf->discard_passdown + 1; + + DMEMIT("%u ", count); + + if (cf->metadata_version == 2) + DMEMIT("metadata2 "); + + if (writethrough_mode(cache)) + DMEMIT("writethrough "); + + else if (passthrough_mode(cache)) + DMEMIT("passthrough "); + + else if (writeback_mode(cache)) + DMEMIT("writeback "); + + else { + DMEMIT("unknown "); + DMERR("%s: internal error: unknown io mode: %d", + cache_device_name(cache), (int) cf->io_mode); + } + + if (!cf->discard_passdown) + DMEMIT("no_discard_passdown "); + + *sz_ptr = sz; +} + /* * Status format: * @@ -3162,25 +3164,7 @@ (unsigned) atomic_read(&cache->stats.promotion), (unsigned long) atomic_read(&cache->nr_dirty)); - if (cache->features.metadata_version == 2) - DMEMIT("2 metadata2 "); - else - DMEMIT("1 "); - - if (writethrough_mode(cache)) - DMEMIT("writethrough "); - - else if (passthrough_mode(cache)) - DMEMIT("passthrough "); - - else if (writeback_mode(cache)) - DMEMIT("writeback "); - - else { - DMERR("%s: internal error: unknown io mode: %d", - cache_device_name(cache), (int) cache->features.io_mode); - goto err; - } + emit_flags(cache, result, maxlen, &sz); DMEMIT("2 migration_threshold %llu ", (unsigned long long) cache->migration_threshold); @@ -3409,14 +3393,62 @@ return r; } +static bool origin_dev_supports_discard(struct block_device *origin_bdev) +{ + struct request_queue *q = bdev_get_queue(origin_bdev); + + return q && blk_queue_discard(q); +} + +/* + * If discard_passdown was enabled verify that the origin device + * supports discards. Disable discard_passdown if not. + */ +static void disable_passdown_if_not_supported(struct cache *cache) +{ + struct block_device *origin_bdev = cache->origin_dev->bdev; + struct queue_limits *origin_limits = &bdev_get_queue(origin_bdev)->limits; + const char *reason = NULL; + char buf[BDEVNAME_SIZE]; + + if (!cache->features.discard_passdown) + return; + + if (!origin_dev_supports_discard(origin_bdev)) + reason = "discard unsupported"; + + else if (origin_limits->max_discard_sectors < cache->sectors_per_block) + reason = "max discard sectors smaller than a block"; + + if (reason) { + DMWARN("Origin device (%s) %s: Disabling discard passdown.", + bdevname(origin_bdev, buf), reason); + cache->features.discard_passdown = false; + } +} + static void set_discard_limits(struct cache *cache, struct queue_limits *limits) { + struct block_device *origin_bdev = cache->origin_dev->bdev; + struct queue_limits *origin_limits = &bdev_get_queue(origin_bdev)->limits; + + if (!cache->features.discard_passdown) { + /* No passdown is done so setting own virtual limits */ + limits->max_discard_sectors = min_t(sector_t, cache->discard_block_size * 1024, + cache->origin_sectors); + limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT; + return; + } + /* - * FIXME: these limits may be incompatible with the cache device + * cache_iterate_devices() is stacking both origin and fast device limits + * but discards aren't passed to fast device, so inherit origin's limits. */ - limits->max_discard_sectors = min_t(sector_t, cache->discard_block_size * 1024, - cache->origin_sectors); - limits->discard_granularity = cache->discard_block_size << SECTOR_SHIFT; + limits->max_discard_sectors = origin_limits->max_discard_sectors; + limits->max_hw_discard_sectors = origin_limits->max_hw_discard_sectors; + limits->discard_granularity = origin_limits->discard_granularity; + limits->discard_alignment = origin_limits->discard_alignment; + limits->discard_misaligned = origin_limits->discard_misaligned; } static void cache_io_hints(struct dm_target *ti, struct queue_limits *limits) @@ -3433,6 +3465,8 @@ blk_limits_io_min(limits, cache->sectors_per_block << SECTOR_SHIFT); blk_limits_io_opt(limits, cache->sectors_per_block << SECTOR_SHIFT); } + + disable_passdown_if_not_supported(cache); set_discard_limits(cache, limits); } @@ -3440,7 +3474,7 @@ static struct target_type cache_target = { .name = "cache", - .version = {2, 0, 0}, + .version = {2, 2, 0}, .module = THIS_MODULE, .ctr = cache_ctr, .dtr = cache_dtr, -- Gitblit v1.6.2