diff options
Diffstat (limited to 'drivers/md/dm-table.c')
| -rw-r--r-- | drivers/md/dm-table.c | 1145 |
1 files changed, 589 insertions, 556 deletions
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 0a2cc197f62b..078da18bb86d 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -6,10 +6,12 @@ */ #include "dm-core.h" +#include "dm-rq.h" #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/blkdev.h> +#include <linux/blk-integrity.h> #include <linux/namei.h> #include <linux/ctype.h> #include <linux/string.h> @@ -24,50 +26,10 @@ #define DM_MSG_PREFIX "table" -#define MAX_DEPTH 16 #define NODE_SIZE L1_CACHE_BYTES #define KEYS_PER_NODE (NODE_SIZE / sizeof(sector_t)) #define CHILDREN_PER_NODE (KEYS_PER_NODE + 1) -struct dm_table { - struct mapped_device *md; - enum dm_queue_mode type; - - /* btree table */ - unsigned int depth; - unsigned int counts[MAX_DEPTH]; /* in nodes */ - sector_t *index[MAX_DEPTH]; - - unsigned int num_targets; - unsigned int num_allocated; - sector_t *highs; - struct dm_target *targets; - - struct target_type *immutable_target_type; - - bool integrity_supported:1; - bool singleton:1; - unsigned integrity_added:1; - - /* - * Indicates the rw permissions for the new logical - * device. This should be a combination of FMODE_READ - * and FMODE_WRITE. - */ - fmode_t mode; - - /* a list of devices used by this table */ - struct list_head devices; - - /* events get handed up using this callback */ - void (*event_fn)(void *); - void *event_context; - - struct dm_md_mempools *mempools; - - struct list_head target_callbacks; -}; - /* * Similar to ceiling(log_size(n)) */ @@ -134,24 +96,6 @@ static int setup_btree_index(unsigned int l, struct dm_table *t) return 0; } -void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size) -{ - unsigned long size; - void *addr; - - /* - * Check that we're not going to overflow. - */ - if (nmemb > (ULONG_MAX / elem_size)) - return NULL; - - size = nmemb * elem_size; - addr = vzalloc(size); - - return addr; -} -EXPORT_SYMBOL(dm_vcalloc); - /* * highs, and targets are managed as dynamic arrays during a * table load. @@ -164,15 +108,15 @@ static int alloc_targets(struct dm_table *t, unsigned int num) /* * Allocate both the target array and offset array at once. */ - n_highs = (sector_t *) dm_vcalloc(num, sizeof(struct dm_target) + - sizeof(sector_t)); + n_highs = kvcalloc(num, sizeof(struct dm_target) + sizeof(sector_t), + GFP_KERNEL); if (!n_highs) return -ENOMEM; n_targets = (struct dm_target *) (n_highs + num); memset(n_highs, -1, sizeof(*n_highs) * num); - vfree(t->highs); + kvfree(t->highs); t->num_allocated = num; t->highs = n_highs; @@ -190,7 +134,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode, return -ENOMEM; INIT_LIST_HEAD(&t->devices); - INIT_LIST_HEAD(&t->target_callbacks); if (!num_targets) num_targets = KEYS_PER_NODE; @@ -228,34 +171,36 @@ static void free_devices(struct list_head *devices, struct mapped_device *md) } } +static void dm_table_destroy_crypto_profile(struct dm_table *t); + void dm_table_destroy(struct dm_table *t) { - unsigned int i; - if (!t) return; /* free the indexes */ if (t->depth >= 2) - vfree(t->index[t->depth - 2]); + kvfree(t->index[t->depth - 2]); /* free the targets */ - for (i = 0; i < t->num_targets; i++) { - struct dm_target *tgt = t->targets + i; + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - if (tgt->type->dtr) - tgt->type->dtr(tgt); + if (ti->type->dtr) + ti->type->dtr(ti); - dm_put_target_type(tgt->type); + dm_put_target_type(ti->type); } - vfree(t->highs); + kvfree(t->highs); /* free the device list */ free_devices(&t->devices, t->md); dm_free_md_mempools(t->mempools); + dm_table_destroy_crypto_profile(t); + kfree(t); } @@ -279,41 +224,22 @@ static struct dm_dev_internal *find_device(struct list_head *l, dev_t dev) static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q; struct queue_limits *limits = data; struct block_device *bdev = dev->bdev; - sector_t dev_size = - i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + sector_t dev_size = bdev_nr_sectors(bdev); unsigned short logical_block_size_sectors = limits->logical_block_size >> SECTOR_SHIFT; - char b[BDEVNAME_SIZE]; - - /* - * Some devices exist without request functions, - * such as loop devices not yet bound to backing files. - * Forbid the use of such devices. - */ - q = bdev_get_queue(bdev); - if (!q || !q->make_request_fn) { - DMWARN("%s: %s is not yet initialised: " - "start=%llu, len=%llu, dev_size=%llu", - dm_device_name(ti->table->md), bdevname(bdev, b), - (unsigned long long)start, - (unsigned long long)len, - (unsigned long long)dev_size); - return 1; - } if (!dev_size) return 0; if ((start >= dev_size) || (start + len > dev_size)) { - DMWARN("%s: %s too small for target: " - "start=%llu, len=%llu, dev_size=%llu", - dm_device_name(ti->table->md), bdevname(bdev, b), - (unsigned long long)start, - (unsigned long long)len, - (unsigned long long)dev_size); + DMERR("%s: %pg too small for target: " + "start=%llu, len=%llu, dev_size=%llu", + dm_device_name(ti->table->md), bdev, + (unsigned long long)start, + (unsigned long long)len, + (unsigned long long)dev_size); return 1; } @@ -321,14 +247,14 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * If the target is mapped to zoned block device(s), check * that the zones are not partially mapped. */ - if (bdev_zoned_model(bdev) != BLK_ZONED_NONE) { + if (bdev_is_zoned(bdev)) { unsigned int zone_sectors = bdev_zone_sectors(bdev); if (start & (zone_sectors - 1)) { - DMWARN("%s: start=%llu not aligned to h/w zone size %u of %s", - dm_device_name(ti->table->md), - (unsigned long long)start, - zone_sectors, bdevname(bdev, b)); + DMERR("%s: start=%llu not aligned to h/w zone size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)start, + zone_sectors, bdev); return 1; } @@ -342,10 +268,10 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * the sector range. */ if (len & (zone_sectors - 1)) { - DMWARN("%s: len=%llu not aligned to h/w zone size %u of %s", - dm_device_name(ti->table->md), - (unsigned long long)len, - zone_sectors, bdevname(bdev, b)); + DMERR("%s: len=%llu not aligned to h/w zone size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)len, + zone_sectors, bdev); return 1; } } @@ -354,20 +280,20 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, return 0; if (start & (logical_block_size_sectors - 1)) { - DMWARN("%s: start=%llu not aligned to h/w " - "logical block size %u of %s", - dm_device_name(ti->table->md), - (unsigned long long)start, - limits->logical_block_size, bdevname(bdev, b)); + DMERR("%s: start=%llu not aligned to h/w " + "logical block size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)start, + limits->logical_block_size, bdev); return 1; } if (len & (logical_block_size_sectors - 1)) { - DMWARN("%s: len=%llu not aligned to h/w " - "logical block size %u of %s", - dm_device_name(ti->table->md), - (unsigned long long)len, - limits->logical_block_size, bdevname(bdev, b)); + DMERR("%s: len=%llu not aligned to h/w " + "logical block size %u of %pg", + dm_device_name(ti->table->md), + (unsigned long long)len, + limits->logical_block_size, bdev); return 1; } @@ -378,7 +304,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * This upgrades the mode on an already open dm_dev, being * careful to leave things as they were if we fail to reopen the * device and not to touch the existing bdev field in case - * it is accessed concurrently inside dm_table_any_congested(). + * it is accessed concurrently. */ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, struct mapped_device *md) @@ -405,16 +331,9 @@ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, dev_t dm_get_dev_t(const char *path) { dev_t dev; - struct block_device *bdev; - bdev = lookup_bdev(path); - if (IS_ERR(bdev)) + if (lookup_bdev(path, &dev)) dev = name_to_dev_t(path); - else { - dev = bdev->bd_dev; - bdput(bdev); - } - return dev; } EXPORT_SYMBOL_GPL(dm_get_dev_t); @@ -428,14 +347,23 @@ int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, { int r; dev_t dev; + unsigned int major, minor; + char dummy; struct dm_dev_internal *dd; struct dm_table *t = ti->table; BUG_ON(!t); - dev = dm_get_dev_t(path); - if (!dev) - return -ENODEV; + if (sscanf(path, "%u:%u%c", &major, &minor, &dummy) == 2) { + /* Extract the major/minor numbers */ + dev = MKDEV(major, minor); + if (MAJOR(dev) != major || MINOR(dev) != minor) + return -EOVERFLOW; + } else { + dev = dm_get_dev_t(path); + if (!dev) + return -ENODEV; + } dd = find_device(&t->devices, dev); if (!dd) { @@ -470,26 +398,23 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, struct queue_limits *limits = data; struct block_device *bdev = dev->bdev; struct request_queue *q = bdev_get_queue(bdev); - char b[BDEVNAME_SIZE]; if (unlikely(!q)) { - DMWARN("%s: Cannot set limits for nonexistent device %s", - dm_device_name(ti->table->md), bdevname(bdev, b)); + DMWARN("%s: Cannot set limits for nonexistent device %pg", + dm_device_name(ti->table->md), bdev); return 0; } - if (bdev_stack_limits(limits, bdev, start) < 0) - DMWARN("%s: adding target device %s caused an alignment inconsistency: " + if (blk_stack_limits(limits, &q->limits, + get_start_sect(bdev) + start) < 0) + DMWARN("%s: adding target device %pg caused an alignment inconsistency: " "physical_block_size=%u, logical_block_size=%u, " "alignment_offset=%u, start=%llu", - dm_device_name(ti->table->md), bdevname(bdev, b), + dm_device_name(ti->table->md), bdev, q->limits.physical_block_size, q->limits.logical_block_size, q->limits.alignment_offset, (unsigned long long) start << SECTOR_SHIFT); - - limits->zoned = blk_queue_zoned_model(q); - return 0; } @@ -509,8 +434,8 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d) } } if (!found) { - DMWARN("%s: device %s not in table devices list", - dm_device_name(ti->table->md), d->name); + DMERR("%s: device %s not in table devices list", + dm_device_name(ti->table->md), d->name); return; } if (refcount_dec_and_test(&dd->count)) { @@ -524,14 +449,14 @@ EXPORT_SYMBOL(dm_put_device); /* * Checks to see if the target joins onto the end of the table. */ -static int adjoin(struct dm_table *table, struct dm_target *ti) +static int adjoin(struct dm_table *t, struct dm_target *ti) { struct dm_target *prev; - if (!table->num_targets) + if (!t->num_targets) return !ti->begin; - prev = &table->targets[table->num_targets - 1]; + prev = &t->targets[t->num_targets - 1]; return (ti->begin == (prev->begin + prev->len)); } @@ -638,8 +563,8 @@ int dm_split_args(int *argc, char ***argvp, char *input) * two or more targets, the size of each piece it gets split into must * be compatible with the logical_block_size of the target processing it. */ -static int validate_hardware_logical_block_alignment(struct dm_table *table, - struct queue_limits *limits) +static int validate_hardware_logical_block_alignment(struct dm_table *t, + struct queue_limits *limits) { /* * This function uses arithmetic modulo the logical_block_size @@ -659,15 +584,15 @@ static int validate_hardware_logical_block_alignment(struct dm_table *table, */ unsigned short remaining = 0; - struct dm_target *uninitialized_var(ti); + struct dm_target *ti; struct queue_limits ti_limits; - unsigned i; + unsigned int i; /* * Check each entry in the table in turn. */ - for (i = 0; i < dm_table_get_num_targets(table); i++) { - ti = dm_table_get_target(table, i); + for (i = 0; i < t->num_targets; i++) { + ti = dm_table_get_target(t, i); blk_set_stacking_limits(&ti_limits); @@ -693,12 +618,12 @@ static int validate_hardware_logical_block_alignment(struct dm_table *table, } if (remaining) { - DMWARN("%s: table line %u (start sect %llu len %llu) " - "not aligned to h/w logical block size %u", - dm_device_name(table->md), i, - (unsigned long long) ti->begin, - (unsigned long long) ti->len, - limits->logical_block_size); + DMERR("%s: table line %u (start sect %llu len %llu) " + "not aligned to h/w logical block size %u", + dm_device_name(t->md), i, + (unsigned long long) ti->begin, + (unsigned long long) ti->len, + limits->logical_block_size); return -EINVAL; } @@ -710,7 +635,7 @@ int dm_table_add_target(struct dm_table *t, const char *type, { int r = -EINVAL, argc; char **argv; - struct dm_target *tgt; + struct dm_target *ti; if (t->singleton) { DMERR("%s: target type %s must appear alone in table", @@ -720,84 +645,87 @@ int dm_table_add_target(struct dm_table *t, const char *type, BUG_ON(t->num_targets >= t->num_allocated); - tgt = t->targets + t->num_targets; - memset(tgt, 0, sizeof(*tgt)); + ti = t->targets + t->num_targets; + memset(ti, 0, sizeof(*ti)); if (!len) { DMERR("%s: zero-length target", dm_device_name(t->md)); return -EINVAL; } - tgt->type = dm_get_target_type(type); - if (!tgt->type) { + ti->type = dm_get_target_type(type); + if (!ti->type) { DMERR("%s: %s: unknown target type", dm_device_name(t->md), type); return -EINVAL; } - if (dm_target_needs_singleton(tgt->type)) { + if (dm_target_needs_singleton(ti->type)) { if (t->num_targets) { - tgt->error = "singleton target type must appear alone in table"; + ti->error = "singleton target type must appear alone in table"; goto bad; } t->singleton = true; } - if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) { - tgt->error = "target type may not be included in a read-only table"; + if (dm_target_always_writeable(ti->type) && !(t->mode & FMODE_WRITE)) { + ti->error = "target type may not be included in a read-only table"; goto bad; } if (t->immutable_target_type) { - if (t->immutable_target_type != tgt->type) { - tgt->error = "immutable target type cannot be mixed with other target types"; + if (t->immutable_target_type != ti->type) { + ti->error = "immutable target type cannot be mixed with other target types"; goto bad; } - } else if (dm_target_is_immutable(tgt->type)) { + } else if (dm_target_is_immutable(ti->type)) { if (t->num_targets) { - tgt->error = "immutable target type cannot be mixed with other target types"; + ti->error = "immutable target type cannot be mixed with other target types"; goto bad; } - t->immutable_target_type = tgt->type; + t->immutable_target_type = ti->type; } - if (dm_target_has_integrity(tgt->type)) + if (dm_target_has_integrity(ti->type)) t->integrity_added = 1; - tgt->table = t; - tgt->begin = start; - tgt->len = len; - tgt->error = "Unknown error"; + ti->table = t; + ti->begin = start; + ti->len = len; + ti->error = "Unknown error"; /* * Does this target adjoin the previous one ? */ - if (!adjoin(t, tgt)) { - tgt->error = "Gap in table"; + if (!adjoin(t, ti)) { + ti->error = "Gap in table"; goto bad; } r = dm_split_args(&argc, &argv, params); if (r) { - tgt->error = "couldn't split parameters (insufficient memory)"; + ti->error = "couldn't split parameters"; goto bad; } - r = tgt->type->ctr(tgt, argc, argv); + r = ti->type->ctr(ti, argc, argv); kfree(argv); if (r) goto bad; - t->highs[t->num_targets++] = tgt->begin + tgt->len - 1; + t->highs[t->num_targets++] = ti->begin + ti->len - 1; - if (!tgt->num_discard_bios && tgt->discards_supported) + if (!ti->num_discard_bios && ti->discards_supported) DMWARN("%s: %s: ignoring discards_supported because num_discard_bios is zero.", dm_device_name(t->md), type); + if (ti->limit_swap_bios && !static_key_enabled(&swap_bios_enabled.key)) + static_branch_enable(&swap_bios_enabled); + return 0; bad: - DMERR("%s: %s: %s", dm_device_name(t->md), type, tgt->error); - dm_put_target_type(tgt->type); + DMERR("%s: %s: %s (%pe)", dm_device_name(t->md), type, ti->error, ERR_PTR(r)); + dm_put_target_type(ti->type); return r; } @@ -863,8 +791,7 @@ EXPORT_SYMBOL(dm_consume_args); static bool __table_type_bio_based(enum dm_queue_mode table_type) { return (table_type == DM_TYPE_BIO_BASED || - table_type == DM_TYPE_DAX_BIO_BASED || - table_type == DM_TYPE_NVME_BIO_BASED); + table_type == DM_TYPE_DAX_BIO_BASED); } static bool __table_type_request_based(enum dm_queue_mode table_type) @@ -879,45 +806,41 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type) EXPORT_SYMBOL_GPL(dm_table_set_type); /* validate the dax capability of the target device span */ -int device_supports_dax(struct dm_target *ti, struct dm_dev *dev, +static int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - int blocksize = *(int *) data; + if (dev->dax_dev) + return false; - return generic_fsdax_supported(dev->dax_dev, dev->bdev, blocksize, - start, len); + DMDEBUG("%pg: error: dax unsupported by block device", dev->bdev); + return true; } /* Check devices support synchronous DAX */ -static int device_dax_synchronous(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_not_dax_synchronous_capable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - return dev->dax_dev && dax_synchronous(dev->dax_dev); + return !dev->dax_dev || !dax_synchronous(dev->dax_dev); } -bool dm_table_supports_dax(struct dm_table *t, - iterate_devices_callout_fn iterate_fn, int *blocksize) +static bool dm_table_supports_dax(struct dm_table *t, + iterate_devices_callout_fn iterate_fn) { - struct dm_target *ti; - unsigned i; - /* Ensure that all targets support DAX. */ - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); if (!ti->type->direct_access) return false; if (!ti->type->iterate_devices || - !ti->type->iterate_devices(ti, iterate_fn, blocksize)) + ti->type->iterate_devices(ti, iterate_fn, NULL)) return false; } return true; } -static bool dm_table_does_not_support_partial_completion(struct dm_table *t); - static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { @@ -925,7 +848,7 @@ static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev, struct request_queue *q = bdev_get_queue(bdev); /* request-based cannot stack on partitions! */ - if (bdev != bdev->bd_contains) + if (bdev_is_partition(bdev)) return false; return queue_is_mq(q); @@ -933,12 +856,10 @@ static int device_is_rq_stackable(struct dm_target *ti, struct dm_dev *dev, static int dm_table_determine_type(struct dm_table *t) { - unsigned i; unsigned bio_based = 0, request_based = 0, hybrid = 0; - struct dm_target *tgt; + struct dm_target *ti; struct list_head *devices = dm_table_get_devices(t); enum dm_queue_mode live_md_type = dm_get_md_type(t->md); - int page_size = PAGE_SIZE; if (t->type != DM_TYPE_NONE) { /* target already set the table's type */ @@ -947,15 +868,14 @@ static int dm_table_determine_type(struct dm_table *t) goto verify_bio_based; } BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED); - BUG_ON(t->type == DM_TYPE_NVME_BIO_BASED); goto verify_rq_based; } - for (i = 0; i < t->num_targets; i++) { - tgt = t->targets + i; - if (dm_target_hybrid(tgt)) + for (unsigned int i = 0; i < t->num_targets; i++) { + ti = dm_table_get_target(t, i); + if (dm_target_hybrid(ti)) hybrid = 1; - else if (dm_target_request_based(tgt)) + else if (dm_target_request_based(ti)) request_based = 1; else bio_based = 1; @@ -983,18 +903,9 @@ static int dm_table_determine_type(struct dm_table *t) verify_bio_based: /* We must use this table as bio-based */ t->type = DM_TYPE_BIO_BASED; - if (dm_table_supports_dax(t, device_supports_dax, &page_size) || + if (dm_table_supports_dax(t, device_not_dax_capable) || (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) { t->type = DM_TYPE_DAX_BIO_BASED; - } else { - /* Check if upgrading to NVMe bio-based is valid or required */ - tgt = dm_table_get_immutable_target(t); - if (tgt && !tgt->max_io_len && dm_table_does_not_support_partial_completion(t)) { - t->type = DM_TYPE_NVME_BIO_BASED; - goto verify_rq_based; /* must be stacked directly on NVMe (blk-mq) */ - } else if (list_empty(devices) && live_md_type == DM_TYPE_NVME_BIO_BASED) { - t->type = DM_TYPE_NVME_BIO_BASED; - } } return 0; } @@ -1011,8 +922,7 @@ verify_rq_based: * (e.g. request completion process for partial completion.) */ if (t->num_targets > 1) { - DMERR("%s DM doesn't support multiple targets", - t->type == DM_TYPE_NVME_BIO_BASED ? "nvme bio-based" : "request-based"); + DMERR("request-based DM doesn't support multiple targets"); return -EINVAL; } @@ -1027,18 +937,18 @@ verify_rq_based: return 0; } - tgt = dm_table_get_immutable_target(t); - if (!tgt) { + ti = dm_table_get_immutable_target(t); + if (!ti) { DMERR("table load rejected: immutable target is required"); return -EINVAL; - } else if (tgt->max_io_len) { + } else if (ti->max_io_len) { DMERR("table load rejected: immutable target that splits IO is not supported"); return -EINVAL; } /* Non-request-stackable devices can't be used for request-based dm */ - if (!tgt->type->iterate_devices || - !tgt->type->iterate_devices(tgt, device_is_rq_stackable, NULL)) { + if (!ti->type->iterate_devices || + !ti->type->iterate_devices(ti, device_is_rq_stackable, NULL)) { DMERR("table load rejected: including non-request-stackable devices"); return -EINVAL; } @@ -1068,11 +978,9 @@ struct dm_target *dm_table_get_immutable_target(struct dm_table *t) struct dm_target *dm_table_get_wildcard_target(struct dm_table *t) { - struct dm_target *ti; - unsigned i; + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); if (dm_target_is_wildcard(ti->type)) return ti; } @@ -1090,43 +998,61 @@ bool dm_table_request_based(struct dm_table *t) return __table_type_request_based(dm_table_get_type(t)); } +static bool dm_table_supports_poll(struct dm_table *t); + static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md) { enum dm_queue_mode type = dm_table_get_type(t); - unsigned per_io_data_size = 0; - unsigned min_pool_size = 0; - struct dm_target *ti; - unsigned i; + unsigned int per_io_data_size = 0, front_pad, io_front_pad; + unsigned int min_pool_size = 0, pool_size; + struct dm_md_mempools *pools; if (unlikely(type == DM_TYPE_NONE)) { - DMWARN("no table type is set, can't allocate mempools"); + DMERR("no table type is set, can't allocate mempools"); return -EINVAL; } - if (__table_type_bio_based(type)) - for (i = 0; i < t->num_targets; i++) { - ti = t->targets + i; - per_io_data_size = max(per_io_data_size, ti->per_io_data_size); - min_pool_size = max(min_pool_size, ti->num_flush_bios); - } - - t->mempools = dm_alloc_md_mempools(md, type, t->integrity_supported, - per_io_data_size, min_pool_size); - if (!t->mempools) + pools = kzalloc_node(sizeof(*pools), GFP_KERNEL, md->numa_node_id); + if (!pools) return -ENOMEM; - return 0; -} + if (type == DM_TYPE_REQUEST_BASED) { + pool_size = dm_get_reserved_rq_based_ios(); + front_pad = offsetof(struct dm_rq_clone_bio_info, clone); + goto init_bs; + } -void dm_table_free_md_mempools(struct dm_table *t) -{ - dm_free_md_mempools(t->mempools); - t->mempools = NULL; -} + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); -struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t) -{ - return t->mempools; + per_io_data_size = max(per_io_data_size, ti->per_io_data_size); + min_pool_size = max(min_pool_size, ti->num_flush_bios); + } + pool_size = max(dm_get_reserved_bio_based_ios(), min_pool_size); + front_pad = roundup(per_io_data_size, + __alignof__(struct dm_target_io)) + DM_TARGET_IO_BIO_OFFSET; + + io_front_pad = roundup(per_io_data_size, + __alignof__(struct dm_io)) + DM_IO_BIO_OFFSET; + if (bioset_init(&pools->io_bs, pool_size, io_front_pad, + dm_table_supports_poll(t) ? BIOSET_PERCPU_CACHE : 0)) + goto out_free_pools; + if (t->integrity_supported && + bioset_integrity_create(&pools->io_bs, pool_size)) + goto out_free_pools; +init_bs: + if (bioset_init(&pools->bs, pool_size, front_pad, 0)) + goto out_free_pools; + if (t->integrity_supported && + bioset_integrity_create(&pools->bs, pool_size)) + goto out_free_pools; + + t->mempools = pools; + return 0; + +out_free_pools: + dm_free_md_mempools(pools); + return -ENOMEM; } static int setup_indexes(struct dm_table *t) @@ -1141,7 +1067,7 @@ static int setup_indexes(struct dm_table *t) total += t->counts[i]; } - indexes = (sector_t *) dm_vcalloc(total, (unsigned long) NODE_SIZE); + indexes = kvcalloc(total, NODE_SIZE, GFP_KERNEL); if (!indexes) return -ENOMEM; @@ -1186,15 +1112,15 @@ static bool integrity_profile_exists(struct gendisk *disk) * Get a disk whose integrity profile reflects the table's profile. * Returns NULL if integrity support was inconsistent or unavailable. */ -static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t) +static struct gendisk *dm_table_get_integrity_disk(struct dm_table *t) { struct list_head *devices = dm_table_get_devices(t); struct dm_dev_internal *dd = NULL; struct gendisk *prev_disk = NULL, *template_disk = NULL; - unsigned i; - for (i = 0; i < dm_table_get_num_targets(t); i++) { + for (unsigned int i = 0; i < t->num_targets; i++) { struct dm_target *ti = dm_table_get_target(t, i); + if (!dm_target_passes_integrity(ti->type)) goto no_integrity; } @@ -1259,10 +1185,10 @@ static int dm_table_register_integrity(struct dm_table *t) * profile the new profile should not conflict. */ if (blk_integrity_compare(dm_disk(md), template_disk) < 0) { - DMWARN("%s: conflict with existing integrity profile: " - "%s profile mismatch", - dm_device_name(t->md), - template_disk->disk_name); + DMERR("%s: conflict with existing integrity profile: " + "%s profile mismatch", + dm_device_name(t->md), + template_disk->disk_name); return 1; } @@ -1271,6 +1197,206 @@ static int dm_table_register_integrity(struct dm_table *t) return 0; } +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + +struct dm_crypto_profile { + struct blk_crypto_profile profile; + struct mapped_device *md; +}; + +struct dm_keyslot_evict_args { + const struct blk_crypto_key *key; + int err; +}; + +static int dm_keyslot_evict_callback(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct dm_keyslot_evict_args *args = data; + int err; + + err = blk_crypto_evict_key(bdev_get_queue(dev->bdev), args->key); + if (!args->err) + args->err = err; + /* Always try to evict the key from all devices. */ + return 0; +} + +/* + * When an inline encryption key is evicted from a device-mapper device, evict + * it from all the underlying devices. + */ +static int dm_keyslot_evict(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, unsigned int slot) +{ + struct mapped_device *md = + container_of(profile, struct dm_crypto_profile, profile)->md; + struct dm_keyslot_evict_args args = { key }; + struct dm_table *t; + int srcu_idx; + + t = dm_get_live_table(md, &srcu_idx); + if (!t) + return 0; + + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + if (!ti->type->iterate_devices) + continue; + ti->type->iterate_devices(ti, dm_keyslot_evict_callback, &args); + } + + dm_put_live_table(md, srcu_idx); + return args.err; +} + +static int +device_intersect_crypto_capabilities(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct blk_crypto_profile *parent = data; + struct blk_crypto_profile *child = + bdev_get_queue(dev->bdev)->crypto_profile; + + blk_crypto_intersect_capabilities(parent, child); + return 0; +} + +void dm_destroy_crypto_profile(struct blk_crypto_profile *profile) +{ + struct dm_crypto_profile *dmcp = container_of(profile, + struct dm_crypto_profile, + profile); + + if (!profile) + return; + + blk_crypto_profile_destroy(profile); + kfree(dmcp); +} + +static void dm_table_destroy_crypto_profile(struct dm_table *t) +{ + dm_destroy_crypto_profile(t->crypto_profile); + t->crypto_profile = NULL; +} + +/* + * Constructs and initializes t->crypto_profile with a crypto profile that + * represents the common set of crypto capabilities of the devices described by + * the dm_table. However, if the constructed crypto profile doesn't support all + * crypto capabilities that are supported by the current mapped_device, it + * returns an error instead, since we don't support removing crypto capabilities + * on table changes. Finally, if the constructed crypto profile is "empty" (has + * no crypto capabilities at all), it just sets t->crypto_profile to NULL. + */ +static int dm_table_construct_crypto_profile(struct dm_table *t) +{ + struct dm_crypto_profile *dmcp; + struct blk_crypto_profile *profile; + unsigned int i; + bool empty_profile = true; + + dmcp = kmalloc(sizeof(*dmcp), GFP_KERNEL); + if (!dmcp) + return -ENOMEM; + dmcp->md = t->md; + + profile = &dmcp->profile; + blk_crypto_profile_init(profile, 0); + profile->ll_ops.keyslot_evict = dm_keyslot_evict; + profile->max_dun_bytes_supported = UINT_MAX; + memset(profile->modes_supported, 0xFF, + sizeof(profile->modes_supported)); + + for (i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + if (!dm_target_passes_crypto(ti->type)) { + blk_crypto_intersect_capabilities(profile, NULL); + break; + } + if (!ti->type->iterate_devices) + continue; + ti->type->iterate_devices(ti, + device_intersect_crypto_capabilities, + profile); + } + + if (t->md->queue && + !blk_crypto_has_capabilities(profile, + t->md->queue->crypto_profile)) { + DMERR("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!"); + dm_destroy_crypto_profile(profile); + return -EINVAL; + } + + /* + * If the new profile doesn't actually support any crypto capabilities, + * we may as well represent it with a NULL profile. + */ + for (i = 0; i < ARRAY_SIZE(profile->modes_supported); i++) { + if (profile->modes_supported[i]) { + empty_profile = false; + break; + } + } + + if (empty_profile) { + dm_destroy_crypto_profile(profile); + profile = NULL; + } + + /* + * t->crypto_profile is only set temporarily while the table is being + * set up, and it gets set to NULL after the profile has been + * transferred to the request_queue. + */ + t->crypto_profile = profile; + + return 0; +} + +static void dm_update_crypto_profile(struct request_queue *q, + struct dm_table *t) +{ + if (!t->crypto_profile) + return; + + /* Make the crypto profile less restrictive. */ + if (!q->crypto_profile) { + blk_crypto_register(t->crypto_profile, q); + } else { + blk_crypto_update_capabilities(q->crypto_profile, + t->crypto_profile); + dm_destroy_crypto_profile(t->crypto_profile); + } + t->crypto_profile = NULL; +} + +#else /* CONFIG_BLK_INLINE_ENCRYPTION */ + +static int dm_table_construct_crypto_profile(struct dm_table *t) +{ + return 0; +} + +void dm_destroy_crypto_profile(struct blk_crypto_profile *profile) +{ +} + +static void dm_table_destroy_crypto_profile(struct dm_table *t) +{ +} + +static void dm_update_crypto_profile(struct request_queue *q, + struct dm_table *t) +{ +} + +#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */ + /* * Prepares the table for use by building the indices, * setting the type, and allocating mempools. @@ -1297,6 +1423,12 @@ int dm_table_complete(struct dm_table *t) return r; } + r = dm_table_construct_crypto_profile(t); + if (r) { + DMERR("could not construct crypto profile."); + return r; + } + r = dm_table_alloc_md_mempools(t, t->md); if (r) DMERR("unable to allocate mempools"); @@ -1316,12 +1448,6 @@ void dm_table_event_callback(struct dm_table *t, void dm_table_event(struct dm_table *t) { - /* - * You can no longer call dm_table_event() from interrupt - * context, use a bottom half instead. - */ - BUG_ON(in_interrupt()); - mutex_lock(&_event_lock); if (t->event_fn) t->event_fn(t->event_context); @@ -1335,14 +1461,6 @@ inline sector_t dm_table_get_size(struct dm_table *t) } EXPORT_SYMBOL(dm_table_get_size); -struct dm_target *dm_table_get_target(struct dm_table *t, unsigned int index) -{ - if (index >= t->num_targets) - return NULL; - - return t->targets + index; -} - /* * Search the btree for the correct target. * @@ -1369,6 +1487,51 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) return &t->targets[(KEYS_PER_NODE * n) + k]; } +static int device_not_poll_capable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct request_queue *q = bdev_get_queue(dev->bdev); + + return !test_bit(QUEUE_FLAG_POLL, &q->queue_flags); +} + +/* + * type->iterate_devices() should be called when the sanity check needs to + * iterate and check all underlying data devices. iterate_devices() will + * iterate all underlying data devices until it encounters a non-zero return + * code, returned by whether the input iterate_devices_callout_fn, or + * iterate_devices() itself internally. + * + * For some target type (e.g. dm-stripe), one call of iterate_devices() may + * iterate multiple underlying devices internally, in which case a non-zero + * return code returned by iterate_devices_callout_fn will stop the iteration + * in advance. + * + * Cases requiring _any_ underlying device supporting some kind of attribute, + * should use the iteration structure like dm_table_any_dev_attr(), or call + * it directly. @func should handle semantics of positive examples, e.g. + * capable of something. + * + * Cases requiring _all_ underlying devices supporting some kind of attribute, + * should use the iteration structure like dm_table_supports_nowait() or + * dm_table_supports_discards(). Or introduce dm_table_all_devs_attr() that + * uses an @anti_func that handle semantics of counter examples, e.g. not + * capable of something. So: return !dm_table_any_dev_attr(t, anti_func, data); + */ +static bool dm_table_any_dev_attr(struct dm_table *t, + iterate_devices_callout_fn func, void *data) +{ + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + if (ti->type->iterate_devices && + ti->type->iterate_devices(ti, func, data)) + return true; + } + + return false; +} + static int count_device(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { @@ -1379,24 +1542,34 @@ static int count_device(struct dm_target *ti, struct dm_dev *dev, return 0; } +static bool dm_table_supports_poll(struct dm_table *t) +{ + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + if (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_not_poll_capable, NULL)) + return false; + } + + return true; +} + /* * Check whether a table has no data devices attached using each * target's iterate_devices method. * Returns false if the result is unknown because a target doesn't * support iterate_devices. */ -bool dm_table_has_no_data_devices(struct dm_table *table) +bool dm_table_has_no_data_devices(struct dm_table *t) { - struct dm_target *ti; - unsigned i, num_devices; - - for (i = 0; i < dm_table_get_num_targets(table); i++) { - ti = dm_table_get_target(table, i); + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + unsigned num_devices = 0; if (!ti->type->iterate_devices) return false; - num_devices = 0; ti->type->iterate_devices(ti, count_device, &num_devices); if (num_devices) return false; @@ -1405,72 +1578,67 @@ bool dm_table_has_no_data_devices(struct dm_table *table) return true; } -static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_not_zoned_model(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { struct request_queue *q = bdev_get_queue(dev->bdev); enum blk_zoned_model *zoned_model = data; - return q && blk_queue_zoned_model(q) == *zoned_model; + return blk_queue_zoned_model(q) != *zoned_model; } +/* + * Check the device zoned model based on the target feature flag. If the target + * has the DM_TARGET_ZONED_HM feature flag set, host-managed zoned devices are + * also accepted but all devices must have the same zoned model. If the target + * has the DM_TARGET_MIXED_ZONED_MODEL feature set, the devices can have any + * zoned model with all zoned devices having the same zone size. + */ static bool dm_table_supports_zoned_model(struct dm_table *t, enum blk_zoned_model zoned_model) { - struct dm_target *ti; - unsigned i; - - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); - - if (zoned_model == BLK_ZONED_HM && - !dm_target_supports_zoned_hm(ti->type)) - return false; + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - if (!ti->type->iterate_devices || - !ti->type->iterate_devices(ti, device_is_zoned_model, &zoned_model)) - return false; + if (dm_target_supports_zoned_hm(ti->type)) { + if (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_not_zoned_model, + &zoned_model)) + return false; + } else if (!dm_target_supports_mixed_zoned_model(ti->type)) { + if (zoned_model == BLK_ZONED_HM) + return false; + } } return true; } -static int device_matches_zone_sectors(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_not_matches_zone_sectors(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); unsigned int *zone_sectors = data; - return q && blk_queue_zone_sectors(q) == *zone_sectors; -} - -static bool dm_table_matches_zone_sectors(struct dm_table *t, - unsigned int zone_sectors) -{ - struct dm_target *ti; - unsigned i; - - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); - - if (!ti->type->iterate_devices || - !ti->type->iterate_devices(ti, device_matches_zone_sectors, &zone_sectors)) - return false; - } - - return true; + if (!bdev_is_zoned(dev->bdev)) + return 0; + return bdev_zone_sectors(dev->bdev) != *zone_sectors; } -static int validate_hardware_zoned_model(struct dm_table *table, +/* + * Check consistency of zoned model and zone sectors across all targets. For + * zone sectors, if the destination device is a zoned block device, it shall + * have the specified zone_sectors. + */ +static int validate_hardware_zoned_model(struct dm_table *t, enum blk_zoned_model zoned_model, unsigned int zone_sectors) { if (zoned_model == BLK_ZONED_NONE) return 0; - if (!dm_table_supports_zoned_model(table, zoned_model)) { + if (!dm_table_supports_zoned_model(t, zoned_model)) { DMERR("%s: zoned model is not consistent across all devices", - dm_device_name(table->md)); + dm_device_name(t->md)); return -EINVAL; } @@ -1478,9 +1646,9 @@ static int validate_hardware_zoned_model(struct dm_table *table, if (!zone_sectors || !is_power_of_2(zone_sectors)) return -EINVAL; - if (!dm_table_matches_zone_sectors(table, zone_sectors)) { - DMERR("%s: zone sectors is not consistent across all devices", - dm_device_name(table->md)); + if (dm_table_any_dev_attr(t, device_not_matches_zone_sectors, &zone_sectors)) { + DMERR("%s: zone sectors is not consistent across all zoned devices", + dm_device_name(t->md)); return -EINVAL; } @@ -1490,21 +1658,19 @@ static int validate_hardware_zoned_model(struct dm_table *table, /* * Establish the new table's queue_limits and validate them. */ -int dm_calculate_queue_limits(struct dm_table *table, +int dm_calculate_queue_limits(struct dm_table *t, struct queue_limits *limits) { - struct dm_target *ti; struct queue_limits ti_limits; - unsigned i; enum blk_zoned_model zoned_model = BLK_ZONED_NONE; unsigned int zone_sectors = 0; blk_set_stacking_limits(limits); - for (i = 0; i < dm_table_get_num_targets(table); i++) { - blk_set_stacking_limits(&ti_limits); + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - ti = dm_table_get_target(table, i); + blk_set_stacking_limits(&ti_limits); if (!ti->type->iterate_devices) goto combine_limits; @@ -1545,25 +1711,9 @@ combine_limits: DMWARN("%s: adding target device " "(start sect %llu len %llu) " "caused an alignment inconsistency", - dm_device_name(table->md), + dm_device_name(t->md), (unsigned long long) ti->begin, (unsigned long long) ti->len); - - /* - * FIXME: this should likely be moved to blk_stack_limits(), would - * also eliminate limits->zoned stacking hack in dm_set_device_limits() - */ - if (limits->zoned == BLK_ZONED_NONE && ti_limits.zoned != BLK_ZONED_NONE) { - /* - * By default, the stacked limits zoned model is set to - * BLK_ZONED_NONE in blk_set_stacking_limits(). Update - * this model using the first target model reported - * that is not BLK_ZONED_NONE. This will be either the - * first target device zoned model or the model reported - * by the target .io_hints. - */ - limits->zoned = ti_limits.zoned; - } } /* @@ -1581,10 +1731,10 @@ combine_limits: zoned_model = limits->zoned; zone_sectors = limits->chunk_sectors; } - if (validate_hardware_zoned_model(table, zoned_model, zone_sectors)) + if (validate_hardware_zoned_model(t, zoned_model, zone_sectors)) return -EINVAL; - return validate_hardware_logical_block_alignment(table, limits); + return validate_hardware_logical_block_alignment(t, limits); } /* @@ -1623,22 +1773,19 @@ static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev, unsigned long flush = (unsigned long) data; struct request_queue *q = bdev_get_queue(dev->bdev); - return q && (q->queue_flags & flush); + return (q->queue_flags & flush); } static bool dm_table_supports_flush(struct dm_table *t, unsigned long flush) { - struct dm_target *ti; - unsigned i; - /* * Require at least one underlying device to support flushes. * t->devices includes internal dm devices such as mirror logs * so we need to use iterate_devices here, which targets * supporting flushes must provide. */ - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); if (!ti->num_flush_bios) continue; @@ -1668,29 +1815,10 @@ static int device_dax_write_cache_enabled(struct dm_target *ti, return false; } -static int dm_table_supports_dax_write_cache(struct dm_table *t) -{ - struct dm_target *ti; - unsigned i; - - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); - - if (ti->type->iterate_devices && - ti->type->iterate_devices(ti, - device_dax_write_cache_enabled, NULL)) - return true; - } - - return false; -} - -static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_is_rotational(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return q && blk_queue_nonrot(q); + return !bdev_nonrot(dev->bdev); } static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, @@ -1698,88 +1826,49 @@ static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, { struct request_queue *q = bdev_get_queue(dev->bdev); - return q && !blk_queue_add_random(q); -} - -static bool dm_table_all_devices_attribute(struct dm_table *t, - iterate_devices_callout_fn func) -{ - struct dm_target *ti; - unsigned i; - - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); - - if (!ti->type->iterate_devices || - !ti->type->iterate_devices(ti, func, NULL)) - return false; - } - - return true; -} - -static int device_no_partial_completion(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) -{ - char b[BDEVNAME_SIZE]; - - /* For now, NVMe devices are the only devices of this class */ - return (strncmp(bdevname(dev->bdev, b), "nvme", 4) == 0); -} - -static bool dm_table_does_not_support_partial_completion(struct dm_table *t) -{ - return dm_table_all_devices_attribute(t, device_no_partial_completion); + return !blk_queue_add_random(q); } -static int device_not_write_same_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { struct request_queue *q = bdev_get_queue(dev->bdev); - return q && !q->limits.max_write_same_sectors; + return !q->limits.max_write_zeroes_sectors; } -static bool dm_table_supports_write_same(struct dm_table *t) +static bool dm_table_supports_write_zeroes(struct dm_table *t) { - struct dm_target *ti; - unsigned i; - - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - if (!ti->num_write_same_bios) + if (!ti->num_write_zeroes_bios) return false; if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, device_not_write_same_capable, NULL)) + ti->type->iterate_devices(ti, device_not_write_zeroes_capable, NULL)) return false; } return true; } -static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_not_nowait_capable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return q && !q->limits.max_write_zeroes_sectors; + return !bdev_nowait(dev->bdev); } -static bool dm_table_supports_write_zeroes(struct dm_table *t) +static bool dm_table_supports_nowait(struct dm_table *t) { - struct dm_target *ti; - unsigned i = 0; - - while (i < dm_table_get_num_targets(t)) { - ti = dm_table_get_target(t, i++); + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - if (!ti->num_write_zeroes_bios) + if (!dm_target_supports_nowait(ti->type)) return false; if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, device_not_write_zeroes_capable, NULL)) + ti->type->iterate_devices(ti, device_not_nowait_capable, NULL)) return false; } @@ -1789,18 +1878,13 @@ static bool dm_table_supports_write_zeroes(struct dm_table *t) static int device_not_discard_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return q && !blk_queue_discard(q); + return !bdev_max_discard_sectors(dev->bdev); } static bool dm_table_supports_discards(struct dm_table *t) { - struct dm_target *ti; - unsigned i; - - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); if (!ti->num_discard_bios) return false; @@ -1823,18 +1907,13 @@ static int device_not_secure_erase_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return q && !blk_queue_secure_erase(q); + return !bdev_max_secure_erase_sectors(dev->bdev); } static bool dm_table_supports_secure_erase(struct dm_table *t) { - struct dm_target *ti; - unsigned int i; - - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); if (!ti->num_secure_erase_bios) return false; @@ -1851,56 +1930,35 @@ static int device_requires_stable_pages(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return q && bdi_cap_stable_pages_required(q->backing_dev_info); + return bdev_stable_writes(dev->bdev); } -/* - * If any underlying device requires stable pages, a table must require - * them as well. Only targets that support iterate_devices are considered: - * don't want error, zero, etc to require stable pages. - */ -static bool dm_table_requires_stable_pages(struct dm_table *t) -{ - struct dm_target *ti; - unsigned i; - - for (i = 0; i < dm_table_get_num_targets(t); i++) { - ti = dm_table_get_target(t, i); - - if (ti->type->iterate_devices && - ti->type->iterate_devices(ti, device_requires_stable_pages, NULL)) - return true; - } - - return false; -} - -void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, - struct queue_limits *limits) +int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, + struct queue_limits *limits) { bool wc = false, fua = false; - int page_size = PAGE_SIZE; + int r; /* * Copy table's limits to the DM device's request_queue */ q->limits = *limits; + if (dm_table_supports_nowait(t)) + blk_queue_flag_set(QUEUE_FLAG_NOWAIT, q); + else + blk_queue_flag_clear(QUEUE_FLAG_NOWAIT, q); + if (!dm_table_supports_discards(t)) { - blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q); - /* Must also clear discard limits... */ q->limits.max_discard_sectors = 0; q->limits.max_hw_discard_sectors = 0; q->limits.discard_granularity = 0; q->limits.discard_alignment = 0; q->limits.discard_misaligned = 0; - } else - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); + } - if (dm_table_supports_secure_erase(t)) - blk_queue_flag_set(QUEUE_FLAG_SECERASE, q); + if (!dm_table_supports_secure_erase(t)) + q->limits.max_secure_erase_sectors = 0; if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) { wc = true; @@ -1909,25 +1967,23 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, } blk_queue_write_cache(q, wc, fua); - if (dm_table_supports_dax(t, device_supports_dax, &page_size)) { + if (dm_table_supports_dax(t, device_not_dax_capable)) { blk_queue_flag_set(QUEUE_FLAG_DAX, q); - if (dm_table_supports_dax(t, device_dax_synchronous, NULL)) + if (dm_table_supports_dax(t, device_not_dax_synchronous_capable)) set_dax_synchronous(t->md->dax_dev); } else blk_queue_flag_clear(QUEUE_FLAG_DAX, q); - if (dm_table_supports_dax_write_cache(t)) + if (dm_table_any_dev_attr(t, device_dax_write_cache_enabled, NULL)) dax_write_cache(t->md->dax_dev, true); /* Ensure that all underlying devices are non-rotational. */ - if (dm_table_all_devices_attribute(t, device_is_nonrot)) - blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - else + if (dm_table_any_dev_attr(t, device_is_rotational, NULL)) blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); + else + blk_queue_flag_set(QUEUE_FLAG_NONROT, q); - if (!dm_table_supports_write_same(t)) - q->limits.max_write_same_sectors = 0; if (!dm_table_supports_write_zeroes(t)) q->limits.max_write_zeroes_sectors = 0; @@ -1936,11 +1992,14 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, /* * Some devices don't use blk_integrity but still want stable pages * because they do their own checksumming. + * If any underlying device requires stable pages, a table must require + * them as well. Only targets that support iterate_devices are considered: + * don't want error, zero, etc to require stable pages. */ - if (dm_table_requires_stable_pages(t)) - q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; + if (dm_table_any_dev_attr(t, device_requires_stable_pages, NULL)) + blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, q); else - q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; + blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, q); /* * Determine whether or not this queue's I/O timings contribute @@ -1948,28 +2007,40 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not * have it set. */ - if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random)) + if (blk_queue_add_random(q) && + dm_table_any_dev_attr(t, device_is_not_random, NULL)) blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q); /* - * For a zoned target, the number of zones should be updated for the - * correct value to be exposed in sysfs queue/nr_zones. For a BIO based - * target, this is all that is needed. + * For a zoned target, setup the zones related queue attributes + * and resources necessary for zone append emulation if necessary. */ -#ifdef CONFIG_BLK_DEV_ZONED if (blk_queue_is_zoned(q)) { - WARN_ON_ONCE(queue_is_mq(q)); - q->nr_zones = blkdev_nr_zones(t->md->disk); + r = dm_set_zones_restrictions(t, q); + if (r) + return r; + if (!static_key_enabled(&zoned_enabled.key)) + static_branch_enable(&zoned_enabled); } -#endif - /* Allow reads to exceed readahead limits */ - q->backing_dev_info->io_pages = limits->max_sectors >> (PAGE_SHIFT - 9); -} + dm_update_crypto_profile(q, t); + disk_update_readahead(t->md->disk); -unsigned int dm_table_get_num_targets(struct dm_table *t) -{ - return t->num_targets; + /* + * Check for request-based device is left to + * dm_mq_init_request_queue()->blk_mq_init_allocated_queue(). + * + * For bio-based device, only set QUEUE_FLAG_POLL when all + * underlying devices supporting polling. + */ + if (__table_type_bio_based(t->type)) { + if (dm_table_supports_poll(t)) + blk_queue_flag_set(QUEUE_FLAG_POLL, q); + else + blk_queue_flag_clear(QUEUE_FLAG_POLL, q); + } + + return 0; } struct list_head *dm_table_get_devices(struct dm_table *t) @@ -1991,12 +2062,11 @@ enum suspend_mode { static void suspend_targets(struct dm_table *t, enum suspend_mode mode) { - int i = t->num_targets; - struct dm_target *ti = t->targets; - lockdep_assert_held(&t->md->suspend_lock); - while (i--) { + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + switch (mode) { case PRESUSPEND: if (ti->type->presuspend) @@ -2011,7 +2081,6 @@ static void suspend_targets(struct dm_table *t, enum suspend_mode mode) ti->type->postsuspend(ti); break; } - ti++; } } @@ -2041,12 +2110,13 @@ void dm_table_postsuspend_targets(struct dm_table *t) int dm_table_resume_targets(struct dm_table *t) { - int i, r = 0; + unsigned int i; + int r = 0; lockdep_assert_held(&t->md->suspend_lock); for (i = 0; i < t->num_targets; i++) { - struct dm_target *ti = t->targets + i; + struct dm_target *ti = dm_table_get_target(t, i); if (!ti->type->preresume) continue; @@ -2060,7 +2130,7 @@ int dm_table_resume_targets(struct dm_table *t) } for (i = 0; i < t->num_targets; i++) { - struct dm_target *ti = t->targets + i; + struct dm_target *ti = dm_table_get_target(t, i); if (ti->type->resume) ti->type->resume(ti); @@ -2069,38 +2139,6 @@ int dm_table_resume_targets(struct dm_table *t) return 0; } -void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb) -{ - list_add(&cb->list, &t->target_callbacks); -} -EXPORT_SYMBOL_GPL(dm_table_add_target_callbacks); - -int dm_table_any_congested(struct dm_table *t, int bdi_bits) -{ - struct dm_dev_internal *dd; - struct list_head *devices = dm_table_get_devices(t); - struct dm_target_callbacks *cb; - int r = 0; - - list_for_each_entry(dd, devices, list) { - struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev); - char b[BDEVNAME_SIZE]; - - if (likely(q)) - r |= bdi_congested(q->backing_dev_info, bdi_bits); - else - DMWARN_LIMIT("%s: any_congested: nonexistent device %s", - dm_device_name(t->md), - bdevname(dd->dm_dev->bdev, b)); - } - - list_for_each_entry(cb, &t->target_callbacks, list) - if (cb->congested_fn) - r |= cb->congested_fn(cb, bdi_bits); - - return r; -} - struct mapped_device *dm_table_get_md(struct dm_table *t) { return t->md; @@ -2115,16 +2153,11 @@ EXPORT_SYMBOL_GPL(dm_table_device_name); void dm_table_run_md_queue_async(struct dm_table *t) { - struct mapped_device *md; - struct request_queue *queue; - if (!dm_table_request_based(t)) return; - md = dm_table_get_md(t); - queue = dm_get_md_queue(md); - if (queue) - blk_mq_run_hw_queues(queue, true); + if (t->md->queue) + blk_mq_run_hw_queues(t->md->queue, true); } EXPORT_SYMBOL(dm_table_run_md_queue_async); |