The existing block debugfs hierarchy exposes request queues and hardware contexts, but has no directory for the tag set they share. This makes it difficult to inspect tag set configuration and CPU mappings or identify which request queues share a tag set. Add a tagset/ directory under the debugfs root for each allocated tag set. Expose its configuration, flags and attached queues, along with CPU-to-hardware-queue mappings in map//cpu files. Expose tag information in tags/ and shared_tags, using symlinks to shared_tags for entries that reference the shared tags. Tie the directory lifetime to tag set allocation and release. Recreate the tags directory when the number of hardware queues changes so that its entries reflect the updated tag array. Use a NOIO allocation scope when creating debugfs entries to prevent reclaim from issuing I/O to frozen queues. Serialize reads with hardware queue updates using update_nr_hwq_lock. Tag reads must use down_read_trylock(): blk_mq_update_nr_hw_queues() removes the tags directory while holding the write lock, and debugfs removal waits for active reads to finish. Using down_read() would allow the following deadlock. Both lock operations refer to set->update_nr_hwq_lock, and time flows downward: blk_mq_update_nr_hw_queues() Debugfs reader ----------------------------- -------------- down_write() | | Acquire active reference | blk_mq_tagset_tags_show() | down_read() | | debugfs_remove() Wait for writer to unlock | | Wait for active read to finish | | | +---------- DEADLOCK -------------+ Return -EAGAIN when the read lock cannot be acquired, allowing the read to finish and debugfs removal to proceed. Signed-off-by: Lei Chen --- block/blk-mq-debugfs.c | 316 +++++++++++++++++++++++++++++++++++++++++ block/blk-mq-debugfs.h | 22 +++ block/blk-mq.c | 8 ++ include/linux/blk-mq.h | 8 ++ 4 files changed, 354 insertions(+) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 6754d8f9449c..fd9eb17e97b9 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "blk.h" #include "blk-mq.h" @@ -827,3 +828,318 @@ void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx) debugfs_remove_recursive(hctx->sched_debugfs_dir); hctx->sched_debugfs_dir = NULL; } + +/* Tag set debugfs --------------------------------------------------------- */ + +static DEFINE_IDA(blk_mq_tagset_debugfs_ida); +static DEFINE_MUTEX(blk_mq_tagset_debugfs_mutex); +static struct dentry *blk_mq_tagset_debugfs_root; + +/* Prevent debugfs allocation reclaim from issuing I/O to frozen queues. */ +static unsigned int __must_check blk_mq_tagset_debugfs_lock(void) + __acquires(&blk_mq_tagset_debugfs_mutex) +{ + unsigned int memflags = memalloc_noio_save(); + + mutex_lock(&blk_mq_tagset_debugfs_mutex); + return memflags; +} + +static void blk_mq_tagset_debugfs_unlock(unsigned int memflags) + __releases(&blk_mq_tagset_debugfs_mutex) +{ + mutex_unlock(&blk_mq_tagset_debugfs_mutex); + memalloc_noio_restore(memflags); +} + +#define BLK_MQ_F_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name +static const char *const tagset_flag_name[] = { + BLK_MQ_F_NAME(TAG_QUEUE_SHARED), + BLK_MQ_F_NAME(STACKING), + BLK_MQ_F_NAME(TAG_HCTX_SHARED), + BLK_MQ_F_NAME(BLOCKING), + BLK_MQ_F_NAME(TAG_RR), + BLK_MQ_F_NAME(NO_SCHED_BY_DEFAULT), +}; +#undef BLK_MQ_F_NAME + +static int blk_mq_tagset_flags_show(struct seq_file *m, void *v) +{ + struct blk_mq_tag_set *set = m->private; + + BUILD_BUG_ON(ARRAY_SIZE(tagset_flag_name) != ilog2(BLK_MQ_F_MAX)); + + down_read(&set->update_nr_hwq_lock); + + blk_flags_show(m, set->flags, tagset_flag_name, + ARRAY_SIZE(tagset_flag_name)); + seq_putc(m, '\n'); + + up_read(&set->update_nr_hwq_lock); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(blk_mq_tagset_flags); + +#define BLK_MQ_TAGSET_VALUE_SHOW(_name, _type, _member, _format) \ +static int blk_mq_tagset_##_name##_show(struct seq_file *m, void *v) \ +{ \ + struct blk_mq_tag_set *set = m->private; \ + _type value; \ + \ + down_read(&set->update_nr_hwq_lock); \ + value = set->_member; \ + up_read(&set->update_nr_hwq_lock); \ + \ + seq_printf(m, _format, value); \ + return 0; \ +} \ +DEFINE_SHOW_ATTRIBUTE(blk_mq_tagset_##_name) + +BLK_MQ_TAGSET_VALUE_SHOW(nr_maps, unsigned int, nr_maps, "%u\n"); +BLK_MQ_TAGSET_VALUE_SHOW(nr_hw_queues, unsigned int, nr_hw_queues, "%u\n"); +BLK_MQ_TAGSET_VALUE_SHOW(queue_depth, unsigned int, queue_depth, "%u\n"); +BLK_MQ_TAGSET_VALUE_SHOW(reserved_tags, unsigned int, reserved_tags, "%u\n"); +BLK_MQ_TAGSET_VALUE_SHOW(cmd_size, unsigned int, cmd_size, "%u\n"); +BLK_MQ_TAGSET_VALUE_SHOW(numa_node, int, numa_node, "%d\n"); +BLK_MQ_TAGSET_VALUE_SHOW(timeout, unsigned int, timeout, "%u\n"); + +#undef BLK_MQ_TAGSET_VALUE_SHOW + +static int blk_mq_tagset_hctx_tags_shared_show(struct seq_file *m, void *v) +{ + struct blk_mq_tag_set *set = m->private; + bool shared; + + down_read(&set->update_nr_hwq_lock); + shared = blk_mq_is_shared_tags(set->flags); + up_read(&set->update_nr_hwq_lock); + + seq_printf(m, "%d\n", shared); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(blk_mq_tagset_hctx_tags_shared); + +static int blk_mq_tagset_queues_show(struct seq_file *m, void *v) +{ + struct blk_mq_tag_set *set = m->private; + struct request_queue *q; + int ret; + + ret = down_read_interruptible(&set->update_nr_hwq_lock); + if (ret) + return ret; + + ret = mutex_lock_interruptible(&set->tag_list_lock); + if (ret) { + up_read(&set->update_nr_hwq_lock); + return ret; + } + + if (list_empty(&set->tag_list)) + seq_puts(m, "(none)\n"); + + list_for_each_entry(q, &set->tag_list, tag_set_list) + seq_printf(m, "%s\n", q->disk ? q->disk->disk_name : "(no-disk)"); + + mutex_unlock(&set->tag_list_lock); + up_read(&set->update_nr_hwq_lock); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(blk_mq_tagset_queues); + +static int blk_mq_tagset_map_show(struct seq_file *m, void *v) +{ + struct blk_mq_tag_set *set = m->private; + unsigned long index = debugfs_get_aux_num(m->file); + unsigned int map = index / nr_cpu_ids; + unsigned int cpu = index % nr_cpu_ids; + + down_read(&set->update_nr_hwq_lock); + + seq_printf(m, "%u\n", set->map[map].mq_map[cpu]); + + up_read(&set->update_nr_hwq_lock); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(blk_mq_tagset_map); + +static void blk_mq_tagset_debugfs_create_maps(struct blk_mq_tag_set *set) +{ + struct dentry *dir, *map_dir; + unsigned int cpu, i; + char name[20]; + + dir = debugfs_create_dir("map", set->debugfs_dir); + if (IS_ERR_OR_NULL(dir)) + return; + + for (i = 0; i < set->nr_maps; i++) { + snprintf(name, sizeof(name), "%u", i); + map_dir = debugfs_create_dir(name, dir); + if (IS_ERR_OR_NULL(map_dir)) + continue; + + for_each_possible_cpu(cpu) { + /* Encode the map and CPU indices in the auxiliary data. */ + unsigned long index = (unsigned long)i * nr_cpu_ids + cpu; + + snprintf(name, sizeof(name), "cpu%u", cpu); + debugfs_create_file_aux_num(name, 0444, map_dir, set, + index, &blk_mq_tagset_map_fops); + } + } +} + +static int blk_mq_tagset_tags_show(struct seq_file *m, void *v) +{ + struct blk_mq_tag_set *set = m->private; + long index = (long)debugfs_get_aux_num(m->file); + struct blk_mq_tags *tags = NULL; + + /* + * use trylock here to avoid deadlock + * + * blk_mq_update_nr_hw_queues + * down_write(update_nr_hwq_lock) + * blk_mq_tagset_debugfs_remove_tags + * wait active reads + * + * blk_mq_tagset_tags_show (active reads) + * down_read(udpate_nr_hwq_lock) + * + */ + if (!down_read_trylock(&set->update_nr_hwq_lock)) + return -EAGAIN; + + if (index == -1L) + tags = set->shared_tags; + else if (index >= 0 && index < set->nr_hw_queues) + tags = set->tags[index]; + + if (!tags) { + up_read(&set->update_nr_hwq_lock); + return -ENODEV; + } + + seq_printf(m, ".nr_tags=%u\n.nr_reserved_tags=%u\n.active_queues=%u\n", + tags->nr_tags, + tags->nr_reserved_tags, + READ_ONCE(tags->active_queues)); + + up_read(&set->update_nr_hwq_lock); + return 0; +} +DEFINE_SHOW_ATTRIBUTE(blk_mq_tagset_tags); + +void blk_mq_tagset_debugfs_remove_tags(struct blk_mq_tag_set *set) +{ + if (IS_ERR_OR_NULL(set->debugfs_dir)) + return; + + debugfs_lookup_and_remove("tags", set->debugfs_dir); +} + +void blk_mq_tagset_debugfs_create_tags(struct blk_mq_tag_set *set) +{ + struct dentry *dir; + unsigned int i; + char name[20]; + + if (IS_ERR_OR_NULL(set->debugfs_dir)) + return; + + dir = debugfs_create_dir("tags", set->debugfs_dir); + if (IS_ERR_OR_NULL(dir)) + return; + + for (i = 0; i < set->nr_hw_queues; i++) { + struct blk_mq_tags *tags = set->tags[i]; + + snprintf(name, sizeof(name), "%u", i); + if (tags && tags == set->shared_tags) + debugfs_create_symlink(name, dir, "../shared_tags"); + else + debugfs_create_file_aux_num(name, 0444, dir, set, i, + &blk_mq_tagset_tags_fops); + } +} + +static void blk_mq_tagset_debugfs_create_files(struct blk_mq_tag_set *set) +{ + debugfs_create_file("nr_maps", 0444, set->debugfs_dir, set, + &blk_mq_tagset_nr_maps_fops); + debugfs_create_file("nr_hw_queues", 0444, set->debugfs_dir, set, + &blk_mq_tagset_nr_hw_queues_fops); + debugfs_create_file("queue_depth", 0444, set->debugfs_dir, set, + &blk_mq_tagset_queue_depth_fops); + debugfs_create_file("reserved_tags", 0444, set->debugfs_dir, set, + &blk_mq_tagset_reserved_tags_fops); + debugfs_create_file("cmd_size", 0444, set->debugfs_dir, set, + &blk_mq_tagset_cmd_size_fops); + debugfs_create_file("numa_node", 0444, set->debugfs_dir, set, + &blk_mq_tagset_numa_node_fops); + debugfs_create_file("timeout", 0444, set->debugfs_dir, set, + &blk_mq_tagset_timeout_fops); + debugfs_create_file("hctx_tags_shared", 0444, set->debugfs_dir, set, + &blk_mq_tagset_hctx_tags_shared_fops); + debugfs_create_file("flags", 0444, set->debugfs_dir, set, + &blk_mq_tagset_flags_fops); + debugfs_create_file("queues", 0444, set->debugfs_dir, set, + &blk_mq_tagset_queues_fops); + blk_mq_tagset_debugfs_create_maps(set); + debugfs_create_file_aux_num("shared_tags", 0444, set->debugfs_dir, set, + -1, &blk_mq_tagset_tags_fops); + blk_mq_tagset_debugfs_create_tags(set); +} + +void blk_mq_tagset_debugfs_register(struct blk_mq_tag_set *set) +{ + struct dentry *dir; + unsigned int memflags; + char name[24]; + int id; + + memflags = blk_mq_tagset_debugfs_lock(); + + if (!blk_mq_tagset_debugfs_root) + blk_mq_tagset_debugfs_root = debugfs_create_dir("tagset", NULL); + + if (set->debugfs_dir || IS_ERR_OR_NULL(blk_mq_tagset_debugfs_root)) + goto out_unlock; + + id = ida_alloc(&blk_mq_tagset_debugfs_ida, GFP_KERNEL); + if (id < 0) + goto out_unlock; + + snprintf(name, sizeof(name), "%d", id); + dir = debugfs_create_dir(name, blk_mq_tagset_debugfs_root); + if (IS_ERR_OR_NULL(dir)) { + ida_free(&blk_mq_tagset_debugfs_ida, id); + goto out_unlock; + } + + set->debugfs_id = id; + set->debugfs_dir = dir; + blk_mq_tagset_debugfs_create_files(set); + +out_unlock: + blk_mq_tagset_debugfs_unlock(memflags); +} + +void blk_mq_tagset_debugfs_unregister(struct blk_mq_tag_set *set) +{ + mutex_lock(&blk_mq_tagset_debugfs_mutex); + + if (set->debugfs_dir) { + debugfs_remove_recursive(set->debugfs_dir); + set->debugfs_dir = NULL; + } + + if (set->debugfs_id >= 0) { + ida_free(&blk_mq_tagset_debugfs_ida, set->debugfs_id); + set->debugfs_id = -1; + } + + mutex_unlock(&blk_mq_tagset_debugfs_mutex); +} diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h index 49bb1aaa83dc..aea278bdc4e7 100644 --- a/block/blk-mq-debugfs.h +++ b/block/blk-mq-debugfs.h @@ -7,6 +7,7 @@ #include struct blk_mq_hw_ctx; +struct blk_mq_tag_set; struct blk_mq_debugfs_attr { const char *name; @@ -34,6 +35,11 @@ void blk_mq_debugfs_register_sched_hctx(struct request_queue *q, void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx); void blk_mq_debugfs_register_rq_qos(struct request_queue *q); + +void blk_mq_tagset_debugfs_register(struct blk_mq_tag_set *set); +void blk_mq_tagset_debugfs_unregister(struct blk_mq_tag_set *set); +void blk_mq_tagset_debugfs_create_tags(struct blk_mq_tag_set *set); +void blk_mq_tagset_debugfs_remove_tags(struct blk_mq_tag_set *set); #else static inline void blk_mq_debugfs_register(struct request_queue *q) { @@ -77,6 +83,22 @@ static inline void blk_mq_debugfs_register_rq_qos(struct request_queue *q) { } +static inline void blk_mq_tagset_debugfs_register(struct blk_mq_tag_set *set) +{ +} + +static inline void blk_mq_tagset_debugfs_unregister(struct blk_mq_tag_set *set) +{ +} + +static inline void blk_mq_tagset_debugfs_create_tags(struct blk_mq_tag_set *set) +{ +} + +static inline void blk_mq_tagset_debugfs_remove_tags(struct blk_mq_tag_set *set) +{ +} + #endif #if defined(CONFIG_BLK_DEV_ZONED) && defined(CONFIG_BLK_DEBUG_FS) diff --git a/block/blk-mq.c b/block/blk-mq.c index a26a11c73ee3..e3e6d87f21a7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -4914,6 +4914,10 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); +#ifdef CONFIG_BLK_DEBUG_FS + set->debugfs_id = -1; +#endif + blk_mq_tagset_debugfs_register(set); return 0; @@ -4956,6 +4960,8 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set) { int i, j; + blk_mq_tagset_debugfs_unregister(set); + for (i = 0; i < set->nr_hw_queues; i++) __blk_mq_free_map_and_rqs(set, i); @@ -5137,6 +5143,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, blk_mq_debugfs_unregister_hctxs(q); blk_mq_sysfs_unregister_hctxs(q); } + blk_mq_tagset_debugfs_remove_tags(set); /* * Switch IO scheduler to 'none', cleaning up the data associated @@ -5194,6 +5201,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, blk_mq_remove_hw_queues_cpuhp(q); blk_mq_add_hw_queues_cpuhp(q); } + blk_mq_tagset_debugfs_create_tags(set); out_free_ctx: blk_mq_free_sched_ctx_batch(&elv_tbl); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index af878597afb8..882ed11e7c2b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -14,6 +14,7 @@ struct blk_mq_tags; struct blk_flush_queue; struct io_comp_batch; +struct dentry; #define BLKDEV_MIN_RQ 4 #define BLKDEV_DEFAULT_RQ 128 @@ -530,6 +531,8 @@ enum hctx_type { * @update_nr_hwq_lock: * Synchronize updating nr_hw_queues with add/del disk & * switching elevator. + * @debugfs_dir: Debugfs directory for this tag set. + * @debugfs_id: ID used as part of the debugfs directory name. */ struct blk_mq_tag_set { const struct blk_mq_ops *ops; @@ -554,6 +557,11 @@ struct blk_mq_tag_set { struct srcu_struct tags_srcu; struct rw_semaphore update_nr_hwq_lock; + +#ifdef CONFIG_BLK_DEBUG_FS + struct dentry *debugfs_dir; + int debugfs_id; +#endif }; /** -- 2.43.0