diff options
Diffstat (limited to 'drivers/md/dm-table.c')
| -rw-r--r-- | drivers/md/dm-table.c | 1961 |
1 files changed, 1287 insertions, 674 deletions
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index f221812b7dbc..ad0a60a07b93 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2001 Sistina Software (UK) Limited. * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved. @@ -5,11 +6,13 @@ * This file is released under the GPL. */ -#include "dm.h" +#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> @@ -18,51 +21,16 @@ #include <linux/mutex.h> #include <linux/delay.h> #include <linux/atomic.h> +#include <linux/blk-mq.h> +#include <linux/mount.h> +#include <linux/dax.h> #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; - unsigned 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; - unsigned integrity_supported:1; - unsigned singleton: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)) */ @@ -105,7 +73,7 @@ static sector_t high(struct dm_table *t, unsigned int l, unsigned int n) n = get_child(n, CHILDREN_PER_NODE - 1); if (n >= t->counts[l]) - return (sector_t) - 1; + return (sector_t) -1; return get_node(t, l, n)[KEYS_PER_NODE - 1]; } @@ -129,24 +97,6 @@ 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. @@ -155,27 +105,18 @@ static int alloc_targets(struct dm_table *t, unsigned int num) { sector_t *n_highs; struct dm_target *n_targets; - int n = t->num_targets; /* * Allocate both the target array and offset array at once. - * Append an empty entry to catch sectors beyond the end of - * the device. */ - n_highs = (sector_t *) dm_vcalloc(num + 1, 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); - if (n) { - memcpy(n_highs, t->highs, sizeof(*n_highs) * n); - memcpy(n_targets, t->targets, sizeof(*n_targets) * n); - } - - memset(n_highs + n, -1, sizeof(*n_highs) * (num - n)); - vfree(t->highs); + memset(n_highs, -1, sizeof(*n_highs) * num); t->num_allocated = num; t->highs = n_highs; @@ -184,86 +125,90 @@ static int alloc_targets(struct dm_table *t, unsigned int num) return 0; } -int dm_table_create(struct dm_table **result, fmode_t mode, - unsigned num_targets, struct mapped_device *md) +int dm_table_create(struct dm_table **result, blk_mode_t mode, + unsigned int num_targets, struct mapped_device *md) { - struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL); + struct dm_table *t; + + if (num_targets > DM_MAX_TARGETS) + return -EOVERFLOW; + + t = kzalloc(sizeof(*t), GFP_KERNEL); if (!t) return -ENOMEM; INIT_LIST_HEAD(&t->devices); - INIT_LIST_HEAD(&t->target_callbacks); + init_rwsem(&t->devices_lock); if (!num_targets) num_targets = KEYS_PER_NODE; num_targets = dm_round_up(num_targets, KEYS_PER_NODE); + if (!num_targets) { + kfree(t); + return -EOVERFLOW; + } + if (alloc_targets(t, num_targets)) { kfree(t); return -ENOMEM; } + t->type = DM_TYPE_NONE; t->mode = mode; t->md = md; + t->flush_bypasses_map = true; *result = t; return 0; } -static void free_devices(struct list_head *devices) +static void free_devices(struct list_head *devices, struct mapped_device *md) { struct list_head *tmp, *next; list_for_each_safe(tmp, next, devices) { struct dm_dev_internal *dd = list_entry(tmp, struct dm_dev_internal, list); - DMWARN("dm_table_destroy: dm_put_device call missing for %s", - dd->dm_dev.name); + DMWARN("%s: dm_table_destroy: dm_put_device call missing for %s", + dm_device_name(md), dd->dm_dev->name); + dm_put_table_device(md, dd->dm_dev); kfree(dd); } } +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); + free_devices(&t->devices, t->md); dm_free_md_mempools(t->mempools); - kfree(t); -} + dm_table_destroy_crypto_profile(t); -/* - * Checks to see if we need to extend highs or targets. - */ -static inline int check_space(struct dm_table *t) -{ - if (t->num_targets >= t->num_allocated) - return alloc_targets(t, t->num_allocated * 2); - - return 0; + kfree(t); } /* @@ -273,115 +218,86 @@ static struct dm_dev_internal *find_device(struct list_head *l, dev_t dev) { struct dm_dev_internal *dd; - list_for_each_entry (dd, l, list) - if (dd->dm_dev.bdev->bd_dev == dev) + list_for_each_entry(dd, l, list) + if (dd->dm_dev->bdev->bd_dev == dev) return dd; return NULL; } /* - * Open a device so we can use it as a map destination. - */ -static int open_dev(struct dm_dev_internal *d, dev_t dev, - struct mapped_device *md) -{ - static char *_claim_ptr = "I belong to device-mapper"; - struct block_device *bdev; - - int r; - - BUG_ON(d->dm_dev.bdev); - - bdev = blkdev_get_by_dev(dev, d->dm_dev.mode | FMODE_EXCL, _claim_ptr); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - - r = bd_link_disk_holder(bdev, dm_disk(md)); - if (r) { - blkdev_put(bdev, d->dm_dev.mode | FMODE_EXCL); - return r; - } - - d->dm_dev.bdev = bdev; - return 0; -} - -/* - * Close a device that we've been using. - */ -static void close_dev(struct dm_dev_internal *d, struct mapped_device *md) -{ - if (!d->dm_dev.bdev) - return; - - bd_unlink_disk_holder(d->dm_dev.bdev, dm_disk(md)); - blkdev_put(d->dm_dev.bdev, d->dm_dev.mode | FMODE_EXCL); - d->dm_dev.bdev = NULL; -} - -/* * If possible, this checks an area of a destination device is invalid. */ 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; } + /* + * If the target is mapped to zoned block device(s), check + * that the zones are not partially mapped. + */ + if (bdev_is_zoned(bdev)) { + unsigned int zone_sectors = bdev_zone_sectors(bdev); + + if (!bdev_is_zone_aligned(bdev, start)) { + 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; + } + + /* + * Note: The last zone of a zoned block device may be smaller + * than other zones. So for a target mapping the end of a + * zoned block device with such a zone, len would not be zone + * aligned. We do not allow such last smaller zone to be part + * of the mapping here to ensure that mappings with multiple + * devices do not end up with a smaller zone in the middle of + * the sector range. + */ + if (!bdev_is_zone_aligned(bdev, len)) { + 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; + } + } + if (logical_block_size_sectors <= 1) 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; } @@ -392,170 +308,232 @@ 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, +static int upgrade_mode(struct dm_dev_internal *dd, blk_mode_t new_mode, struct mapped_device *md) { int r; - struct dm_dev_internal dd_new, dd_old; - - dd_new = dd_old = *dd; + struct dm_dev *old_dev, *new_dev; - dd_new.dm_dev.mode |= new_mode; - dd_new.dm_dev.bdev = NULL; + old_dev = dd->dm_dev; - r = open_dev(&dd_new, dd->dm_dev.bdev->bd_dev, md); + r = dm_get_table_device(md, dd->dm_dev->bdev->bd_dev, + dd->dm_dev->mode | new_mode, &new_dev); if (r) return r; - dd->dm_dev.mode |= new_mode; - close_dev(&dd_old, md); + dd->dm_dev = new_dev; + dm_put_table_device(md, old_dev); return 0; } /* - * Add a device to the list, or just increment the usage count if - * it's already present. + * Note: the __ref annotation is because this function can call the __init + * marked early_lookup_bdev when called during early boot code from dm-init.c. */ -int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode, - struct dm_dev **result) +int __ref dm_devt_from_path(const char *path, dev_t *dev_p) { int r; - dev_t uninitialized_var(dev); - struct dm_dev_internal *dd; + dev_t dev; unsigned int major, minor; - struct dm_table *t = ti->table; char dummy; - BUG_ON(!t); - 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 { - /* convert the path to a device */ - struct block_device *bdev = lookup_bdev(path); - - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - dev = bdev->bd_dev; - bdput(bdev); + r = lookup_bdev(path, &dev); +#ifndef MODULE + if (r && system_state < SYSTEM_RUNNING) + r = early_lookup_bdev(path, &dev); +#endif + if (r) + return r; } + *dev_p = dev; + return 0; +} +EXPORT_SYMBOL(dm_devt_from_path); + +/* + * Add a device to the list, or just increment the usage count if + * it's already present. + */ +int dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, + struct dm_dev **result) +{ + int r; + dev_t dev; + struct dm_dev_internal *dd; + struct dm_table *t = ti->table; + + BUG_ON(!t); + + r = dm_devt_from_path(path, &dev); + if (r) + return r; + + if (dev == disk_devt(t->md->disk)) + return -EINVAL; + + down_write(&t->devices_lock); dd = find_device(&t->devices, dev); if (!dd) { dd = kmalloc(sizeof(*dd), GFP_KERNEL); - if (!dd) - return -ENOMEM; - - dd->dm_dev.mode = mode; - dd->dm_dev.bdev = NULL; + if (!dd) { + r = -ENOMEM; + goto unlock_ret_r; + } - if ((r = open_dev(dd, dev, t->md))) { + r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev); + if (r) { kfree(dd); - return r; + goto unlock_ret_r; } - format_dev_t(dd->dm_dev.name, dev); - - atomic_set(&dd->count, 0); + refcount_set(&dd->count, 1); list_add(&dd->list, &t->devices); + goto out; - } else if (dd->dm_dev.mode != (mode | dd->dm_dev.mode)) { + } else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) { r = upgrade_mode(dd, mode, t->md); if (r) - return r; + goto unlock_ret_r; } - atomic_inc(&dd->count); - - *result = &dd->dm_dev; + refcount_inc(&dd->count); +out: + up_write(&t->devices_lock); + *result = dd->dm_dev; return 0; + +unlock_ret_r: + up_write(&t->devices_lock); + return r; } EXPORT_SYMBOL(dm_get_device); -int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { 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: " + mutex_lock(&q->limits_lock); + /* + * BLK_FEAT_ATOMIC_WRITES is not inherited from the bottom device in + * blk_stack_limits(), so do it manually. + */ + limits->features |= (q->limits.features & BLK_FEAT_ATOMIC_WRITES); + + 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); /* - * Check if merge fn is supported. - * If not we'll force DM to use PAGE_SIZE or - * smaller I/O, just to be safe. + * Only stack the integrity profile if the target doesn't have native + * integrity support. */ - if (dm_queue_merge_is_compulsory(q) && !ti->type->merge) - blk_limits_max_hw_sectors(limits, - (unsigned int) (PAGE_SIZE >> 9)); + if (!dm_target_has_integrity(ti->type)) + queue_limits_stack_integrity_bdev(limits, bdev); + mutex_unlock(&q->limits_lock); return 0; } -EXPORT_SYMBOL_GPL(dm_set_device_limits); /* * Decrement a device's use count and remove it if necessary. */ void dm_put_device(struct dm_target *ti, struct dm_dev *d) { - struct dm_dev_internal *dd = container_of(d, struct dm_dev_internal, - dm_dev); + int found = 0; + struct dm_table *t = ti->table; + struct list_head *devices = &t->devices; + struct dm_dev_internal *dd; - if (atomic_dec_and_test(&dd->count)) { - close_dev(dd, ti->table->md); + down_write(&t->devices_lock); + + list_for_each_entry(dd, devices, list) { + if (dd->dm_dev == d) { + found = 1; + break; + } + } + if (!found) { + DMERR("%s: device %s not in table devices list", + dm_device_name(t->md), d->name); + goto unlock_ret; + } + if (refcount_dec_and_test(&dd->count)) { + dm_put_table_device(t->md, d); list_del(&dd->list); kfree(dd); } + +unlock_ret: + up_write(&t->devices_lock); } 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)); } /* * Used to dynamically allocate the arg array. + * + * We do first allocation with GFP_NOIO because dm-mpath and dm-thin must + * process messages even if some device is suspended. These messages have a + * small fixed number of arguments. + * + * On the other hand, dm-switch needs to process bulk data using messages and + * excessive use of GFP_NOIO could cause trouble. */ -static char **realloc_argv(unsigned *array_size, char **old_argv) +static char **realloc_argv(unsigned int *size, char **old_argv) { char **argv; - unsigned new_size; + unsigned int new_size; + gfp_t gfp; - new_size = *array_size ? *array_size * 2 : 64; - argv = kmalloc(new_size * sizeof(*argv), GFP_KERNEL); + if (*size) { + new_size = *size * 2; + gfp = GFP_KERNEL; + } else { + new_size = 8; + gfp = GFP_NOIO; + } + argv = kmalloc_array(new_size, sizeof(*argv), gfp); if (argv) { - memcpy(argv, old_argv, *array_size * sizeof(*argv)); - *array_size = new_size; + if (old_argv) + memcpy(argv, old_argv, *size * sizeof(*argv)); + *size = new_size; } kfree(old_argv); @@ -568,7 +546,7 @@ static char **realloc_argv(unsigned *array_size, char **old_argv) int dm_split_args(int *argc, char ***argvp, char *input) { char *start, *end = input, *out, **argv = NULL; - unsigned array_size = 0; + unsigned int array_size = 0; *argc = 0; @@ -625,6 +603,12 @@ int dm_split_args(int *argc, char ***argvp, char *input) return 0; } +static void dm_set_stacking_limits(struct queue_limits *limits) +{ + blk_set_stacking_limits(limits); + limits->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT | BLK_FEAT_POLL; +} + /* * Impose necessary and sufficient conditions on a devices's table such * that any incoming bio which respects its logical_block_size can be @@ -632,8 +616,8 @@ 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 @@ -653,17 +637,17 @@ 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 = 0; + unsigned int i; /* * Check each entry in the table in turn. */ - while (i < dm_table_get_num_targets(table)) { - 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); + dm_set_stacking_limits(&ti_limits); /* combine all target devices' limits */ if (ti->type->iterate_devices) @@ -687,12 +671,12 @@ 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; } @@ -704,7 +688,7 @@ 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", @@ -712,98 +696,102 @@ int dm_table_add_target(struct dm_table *t, const char *type, return -EINVAL; } - if ((r = check_space(t))) - return r; + 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; } + if (start + len < start || start + len > LLONG_MAX >> SECTOR_SHIFT) { + DMERR("%s: too large device", dm_device_name(t->md)); + return -EINVAL; + } - tgt->type = dm_get_target_type(type); - if (!tgt->type) { - DMERR("%s: %s: unknown target type", dm_device_name(t->md), - 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) { - DMERR("%s: target type %s must appear alone in table", - dm_device_name(t->md), type); - return -EINVAL; + ti->error = "singleton target type must appear alone in table"; + goto bad; } - t->singleton = 1; + t->singleton = true; } - if (dm_target_always_writeable(tgt->type) && !(t->mode & FMODE_WRITE)) { - DMERR("%s: target type %s may not be included in read-only tables", - dm_device_name(t->md), type); - return -EINVAL; + if (dm_target_always_writeable(ti->type) && + !(t->mode & BLK_OPEN_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) { - DMERR("%s: immutable target type %s cannot be mixed with other target types", - dm_device_name(t->md), t->immutable_target_type->name); - return -EINVAL; + 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) { - DMERR("%s: immutable target type %s cannot be mixed with other target types", - dm_device_name(t->md), tgt->type->name); - return -EINVAL; + 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; } - 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"; - r = -EINVAL; + 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); + + if (!ti->flush_bypasses_map) + t->flush_bypasses_map = false; + 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; } /* * Target argument parsing helpers. */ -static int validate_next_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, - unsigned *value, char **error, unsigned grouped) +static int validate_next_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned int *value, char **error, unsigned int grouped) { const char *arg_str = dm_shift_arg(arg_set); char dummy; @@ -820,15 +808,15 @@ static int validate_next_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, return 0; } -int dm_read_arg(struct dm_arg *arg, struct dm_arg_set *arg_set, - unsigned *value, char **error) +int dm_read_arg(const struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned int *value, char **error) { return validate_next_arg(arg, arg_set, value, error, 0); } EXPORT_SYMBOL(dm_read_arg); -int dm_read_arg_group(struct dm_arg *arg, struct dm_arg_set *arg_set, - unsigned *value, char **error) +int dm_read_arg_group(const struct dm_arg *arg, struct dm_arg_set *arg_set, + unsigned int *value, char **error) { return validate_next_arg(arg, arg_set, value, error, 1); } @@ -849,7 +837,7 @@ const char *dm_shift_arg(struct dm_arg_set *as) } EXPORT_SYMBOL(dm_shift_arg); -void dm_consume_args(struct dm_arg_set *as, unsigned num_args) +void dm_consume_args(struct dm_arg_set *as, unsigned int num_args) { BUG_ON(as->argc < num_args); as->argc -= num_args; @@ -857,46 +845,133 @@ void dm_consume_args(struct dm_arg_set *as, unsigned num_args) } EXPORT_SYMBOL(dm_consume_args); -static int dm_table_set_type(struct dm_table *t) +static bool __table_type_bio_based(enum dm_queue_mode table_type) { - unsigned i; - unsigned bio_based = 0, request_based = 0; - struct dm_target *tgt; - struct dm_dev_internal *dd; - struct list_head *devices; + return (table_type == DM_TYPE_BIO_BASED || + table_type == DM_TYPE_DAX_BIO_BASED); +} - for (i = 0; i < t->num_targets; i++) { - tgt = t->targets + i; - if (dm_target_request_based(tgt)) +static bool __table_type_request_based(enum dm_queue_mode table_type) +{ + return table_type == DM_TYPE_REQUEST_BASED; +} + +void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type) +{ + t->type = type; +} +EXPORT_SYMBOL_GPL(dm_table_set_type); + +/* validate the dax capability of the target device span */ +static int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + if (dev->dax_dev) + return false; + + DMDEBUG("%pg: error: dax unsupported by block device", dev->bdev); + return true; +} + +/* Check devices support synchronous DAX */ +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); +} + +static bool dm_table_supports_dax(struct dm_table *t, + iterate_devices_callout_fn iterate_fn) +{ + /* Ensure that all targets support DAX. */ + 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 (dm_target_is_wildcard(ti->type) || + !ti->type->iterate_devices || + ti->type->iterate_devices(ti, iterate_fn, NULL)) + return false; + } + + return true; +} + +static int device_is_not_rq_stackable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct block_device *bdev = dev->bdev; + struct request_queue *q = bdev_get_queue(bdev); + + /* request-based cannot stack on partitions! */ + if (bdev_is_partition(bdev)) + return true; + + return !queue_is_mq(q); +} + +static int dm_table_determine_type(struct dm_table *t) +{ + unsigned int bio_based = 0, request_based = 0, hybrid = 0; + 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); + + if (t->type != DM_TYPE_NONE) { + /* target already set the table's type */ + if (t->type == DM_TYPE_BIO_BASED) { + /* possibly upgrade to a variant of bio-based */ + goto verify_bio_based; + } + BUG_ON(t->type == DM_TYPE_DAX_BIO_BASED); + goto verify_rq_based; + } + + 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(ti)) request_based = 1; else bio_based = 1; if (bio_based && request_based) { - DMWARN("Inconsistent table: different target types" - " can't be mixed up"); + DMERR("Inconsistent table: different target types can't be mixed up"); return -EINVAL; } } + if (hybrid && !bio_based && !request_based) { + /* + * The targets can work either way. + * Determine the type from the live device. + * Default to bio-based if device is new. + */ + if (__table_type_request_based(live_md_type)) + request_based = 1; + else + bio_based = 1; + } + if (bio_based) { +verify_bio_based: /* We must use this table as bio-based */ t->type = DM_TYPE_BIO_BASED; + 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; + } return 0; } BUG_ON(!request_based); /* No targets in this table */ - /* Non-request-stackable devices can't be used for request-based dm */ - devices = dm_table_get_devices(t); - list_for_each_entry(dd, devices, list) { - if (!blk_queue_stackable(bdev_get_queue(dd->dm_dev.bdev))) { - DMWARN("table load rejected: including" - " non-request-stackable devices"); - return -EINVAL; - } - } + t->type = DM_TYPE_REQUEST_BASED; +verify_rq_based: /* * Request-based dm supports only tables that have a single target now. * To support multiple targets, request splitting support is needed, @@ -904,16 +979,41 @@ static int dm_table_set_type(struct dm_table *t) * (e.g. request completion process for partial completion.) */ if (t->num_targets > 1) { - DMWARN("Request-based dm doesn't support multiple targets yet"); + DMERR("request-based DM doesn't support multiple targets"); return -EINVAL; } - t->type = DM_TYPE_REQUEST_BASED; + if (list_empty(devices)) { + int srcu_idx; + struct dm_table *live_table = dm_get_live_table(t->md, &srcu_idx); + + /* inherit live table's type */ + if (live_table) + t->type = live_table->type; + dm_put_live_table(t->md, srcu_idx); + return 0; + } + + ti = dm_table_get_immutable_target(t); + if (!ti) { + DMERR("table load rejected: immutable target is required"); + return -EINVAL; + } 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 (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_is_not_rq_stackable, NULL)) { + DMERR("table load rejected: including non-request-stackable devices"); + return -EINVAL; + } return 0; } -unsigned dm_table_get_type(struct dm_table *t) +enum dm_queue_mode dm_table_get_type(struct dm_table *t) { return t->type; } @@ -923,45 +1023,83 @@ struct target_type *dm_table_get_immutable_target_type(struct dm_table *t) return t->immutable_target_type; } +struct dm_target *dm_table_get_immutable_target(struct dm_table *t) +{ + /* Immutable target is implicitly a singleton */ + if (t->num_targets > 1 || + !dm_target_is_immutable(t->targets[0].type)) + return NULL; + + return t->targets; +} + +struct dm_target *dm_table_get_wildcard_target(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 (dm_target_is_wildcard(ti->type)) + return ti; + } + + return NULL; +} + bool dm_table_request_based(struct dm_table *t) { - return dm_table_get_type(t) == DM_TYPE_REQUEST_BASED; + return __table_type_request_based(dm_table_get_type(t)); } -int dm_table_alloc_md_mempools(struct dm_table *t) +static int dm_table_alloc_md_mempools(struct dm_table *t, struct mapped_device *md) { - unsigned type = dm_table_get_type(t); - unsigned per_bio_data_size = 0; - struct dm_target *tgt; - unsigned i; + enum dm_queue_mode type = dm_table_get_type(t); + 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; + unsigned int bioset_flags = 0; 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 (type == DM_TYPE_BIO_BASED) - for (i = 0; i < t->num_targets; i++) { - tgt = t->targets + i; - per_bio_data_size = max(per_bio_data_size, tgt->per_bio_data_size); - } - - t->mempools = dm_alloc_md_mempools(type, t->integrity_supported, per_bio_data_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; -} + if (md->queue->limits.features & BLK_FEAT_POLL) + bioset_flags |= BIOSET_PERCPU_CACHE; -struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t) -{ - return t->mempools; + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, 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); + } + 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, bioset_flags)) + goto out_free_pools; +init_bs: + if (bioset_init(&pools->bs, pool_size, front_pad, 0)) + 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) @@ -976,7 +1114,7 @@ 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; @@ -1012,84 +1150,376 @@ static int dm_table_build_index(struct dm_table *t) return r; } +#ifdef CONFIG_BLK_INLINE_ENCRYPTION + +struct dm_crypto_profile { + struct blk_crypto_profile profile; + struct mapped_device *md; +}; + +static int dm_keyslot_evict_callback(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + const struct blk_crypto_key *key = data; + + blk_crypto_evict_key(dev->bdev, key); + return 0; +} + /* - * Get a disk whose integrity profile reflects the table's profile. - * If %match_all is true, all devices' profiles must match. - * If %match_all is false, all devices must at least have an - * allocated integrity profile; but uninitialized is ok. - * Returns NULL if integrity support was inconsistent or unavailable. + * When an inline encryption key is evicted from a device-mapper device, evict + * it from all the underlying devices. */ -static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t, - bool match_all) +static int dm_keyslot_evict(struct blk_crypto_profile *profile, + const struct blk_crypto_key *key, unsigned int slot) { - struct list_head *devices = dm_table_get_devices(t); - struct dm_dev_internal *dd = NULL; - struct gendisk *prev_disk = NULL, *template_disk = NULL; + struct mapped_device *md = + container_of(profile, struct dm_crypto_profile, profile)->md; + struct dm_table *t; + int srcu_idx; - list_for_each_entry(dd, devices, list) { - template_disk = dd->dm_dev.bdev->bd_disk; - if (!blk_get_integrity(template_disk)) - goto no_integrity; - if (!match_all && !blk_integrity_is_initialized(template_disk)) - continue; /* skip uninitialized profiles */ - else if (prev_disk && - blk_integrity_compare(prev_disk, template_disk) < 0) - goto no_integrity; - prev_disk = template_disk; - } - - return template_disk; - -no_integrity: - if (prev_disk) - DMWARN("%s: integrity not set: %s and %s profile mismatch", - dm_device_name(t->md), - prev_disk->disk_name, - template_disk->disk_name); - return NULL; + t = dm_get_live_table(md, &srcu_idx); + if (!t) + goto put_live_table; + + 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, + (void *)key); + } + +put_live_table: + dm_put_live_table(md, srcu_idx); + return 0; +} + +enum dm_wrappedkey_op { + DERIVE_SW_SECRET, + IMPORT_KEY, + GENERATE_KEY, + PREPARE_KEY, +}; + +struct dm_wrappedkey_op_args { + enum dm_wrappedkey_op op; + int err; + union { + struct { + const u8 *eph_key; + size_t eph_key_size; + u8 *sw_secret; + } derive_sw_secret; + struct { + const u8 *raw_key; + size_t raw_key_size; + u8 *lt_key; + } import_key; + struct { + u8 *lt_key; + } generate_key; + struct { + const u8 *lt_key; + size_t lt_key_size; + u8 *eph_key; + } prepare_key; + }; +}; + +static int dm_wrappedkey_op_callback(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + struct dm_wrappedkey_op_args *args = data; + struct block_device *bdev = dev->bdev; + struct blk_crypto_profile *profile = + bdev_get_queue(bdev)->crypto_profile; + int err = -EOPNOTSUPP; + + if (!args->err) + return 0; + + switch (args->op) { + case DERIVE_SW_SECRET: + err = blk_crypto_derive_sw_secret( + bdev, + args->derive_sw_secret.eph_key, + args->derive_sw_secret.eph_key_size, + args->derive_sw_secret.sw_secret); + break; + case IMPORT_KEY: + err = blk_crypto_import_key(profile, + args->import_key.raw_key, + args->import_key.raw_key_size, + args->import_key.lt_key); + break; + case GENERATE_KEY: + err = blk_crypto_generate_key(profile, + args->generate_key.lt_key); + break; + case PREPARE_KEY: + err = blk_crypto_prepare_key(profile, + args->prepare_key.lt_key, + args->prepare_key.lt_key_size, + args->prepare_key.eph_key); + break; + } + args->err = err; + + /* Try another device in case this fails. */ + return 0; +} + +static int dm_exec_wrappedkey_op(struct blk_crypto_profile *profile, + struct dm_wrappedkey_op_args *args) +{ + struct mapped_device *md = + container_of(profile, struct dm_crypto_profile, profile)->md; + struct dm_target *ti; + struct dm_table *t; + int srcu_idx; + int i; + + args->err = -EOPNOTSUPP; + + t = dm_get_live_table(md, &srcu_idx); + if (!t) + goto out; + + /* + * blk-crypto currently has no support for multiple incompatible + * implementations of wrapped inline crypto keys on a single system. + * It was already checked earlier that support for wrapped keys was + * declared on all underlying devices. Thus, all the underlying devices + * should support all wrapped key operations and they should behave + * identically, i.e. work with the same keys. So, just executing the + * operation on the first device on which it works suffices for now. + */ + for (i = 0; i < t->num_targets; i++) { + ti = dm_table_get_target(t, i); + if (!ti->type->iterate_devices) + continue; + ti->type->iterate_devices(ti, dm_wrappedkey_op_callback, args); + if (!args->err) + break; + } +out: + dm_put_live_table(md, srcu_idx); + return args->err; +} + +static int dm_derive_sw_secret(struct blk_crypto_profile *profile, + const u8 *eph_key, size_t eph_key_size, + u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]) +{ + struct dm_wrappedkey_op_args args = { + .op = DERIVE_SW_SECRET, + .derive_sw_secret = { + .eph_key = eph_key, + .eph_key_size = eph_key_size, + .sw_secret = sw_secret, + }, + }; + return dm_exec_wrappedkey_op(profile, &args); +} + +static int dm_import_key(struct blk_crypto_profile *profile, + const u8 *raw_key, size_t raw_key_size, + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]) +{ + struct dm_wrappedkey_op_args args = { + .op = IMPORT_KEY, + .import_key = { + .raw_key = raw_key, + .raw_key_size = raw_key_size, + .lt_key = lt_key, + }, + }; + return dm_exec_wrappedkey_op(profile, &args); +} + +static int dm_generate_key(struct blk_crypto_profile *profile, + u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]) +{ + struct dm_wrappedkey_op_args args = { + .op = GENERATE_KEY, + .generate_key = { + .lt_key = lt_key, + }, + }; + return dm_exec_wrappedkey_op(profile, &args); +} + +static int dm_prepare_key(struct blk_crypto_profile *profile, + const u8 *lt_key, size_t lt_key_size, + u8 eph_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]) +{ + struct dm_wrappedkey_op_args args = { + .op = PREPARE_KEY, + .prepare_key = { + .lt_key = lt_key, + .lt_key_size = lt_key_size, + .eph_key = eph_key, + }, + }; + return dm_exec_wrappedkey_op(profile, &args); +} + +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; } /* - * Register the mapped device for blk_integrity support if - * the underlying devices have an integrity profile. But all devices - * may not have matching profiles (checking all devices isn't reliable - * during table load because this table may use other DM device(s) which - * must be resumed before they will have an initialized integity profile). - * Stacked DM devices force a 2 stage integrity profile validation: - * 1 - during load, validate all initialized integrity profiles match - * 2 - during resume, validate all integrity profiles match + * 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_prealloc_integrity(struct dm_table *t, struct mapped_device *md) +static int dm_table_construct_crypto_profile(struct dm_table *t) { - struct gendisk *template_disk = NULL; + struct dm_crypto_profile *dmcp; + struct blk_crypto_profile *profile; + unsigned int i; + bool empty_profile = true; - template_disk = dm_table_get_integrity_disk(t, false); - if (!template_disk) - return 0; + 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)); + profile->key_types_supported = ~0; + + for (i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - if (!blk_integrity_is_initialized(dm_disk(md))) { - t->integrity_supported = 1; - return blk_integrity_register(dm_disk(md), NULL); + 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 (profile->key_types_supported & BLK_CRYPTO_KEY_TYPE_HW_WRAPPED) { + profile->ll_ops.derive_sw_secret = dm_derive_sw_secret; + profile->ll_ops.import_key = dm_import_key; + profile->ll_ops.generate_key = dm_generate_key; + profile->ll_ops.prepare_key = dm_prepare_key; + } + + 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 DM device already has an initalized integrity - * profile the new profile should not conflict. + * If the new profile doesn't actually support any crypto capabilities, + * we may as well represent it with a NULL profile. */ - if (blk_integrity_is_initialized(template_disk) && - 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); - return 1; + 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; } - /* Preserve existing initialized integrity profile */ - t->integrity_supported = 1; + /* + * 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. @@ -1098,9 +1528,9 @@ int dm_table_complete(struct dm_table *t) { int r; - r = dm_table_set_type(t); + r = dm_table_determine_type(t); if (r) { - DMERR("unable to set table type"); + DMERR("unable to determine table type"); return r; } @@ -1110,13 +1540,13 @@ int dm_table_complete(struct dm_table *t) return r; } - r = dm_table_prealloc_integrity(t, t->md); + r = dm_table_construct_crypto_profile(t); if (r) { - DMERR("could not register integrity profile."); + DMERR("could not construct crypto profile."); return r; } - r = dm_table_alloc_md_mempools(t); + r = dm_table_alloc_md_mempools(t, t->md); if (r) DMERR("unable to allocate mempools"); @@ -1135,12 +1565,6 @@ 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); @@ -1148,24 +1572,16 @@ void dm_table_event(struct dm_table *t) } EXPORT_SYMBOL(dm_table_event); -sector_t dm_table_get_size(struct dm_table *t) +inline sector_t dm_table_get_size(struct dm_table *t) { return t->num_targets ? (t->highs[t->num_targets - 1] + 1) : 0; } 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. * - * Caller should check returned pointer with dm_target_is_valid() + * Caller should check returned pointer for NULL * to trap I/O beyond end of device. */ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) @@ -1173,6 +1589,9 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) unsigned int l, n = 0, k = 0; sector_t *node; + if (unlikely(sector >= dm_table_get_size(t))) + return NULL; + for (l = 0; l < t->depth; l++) { n = get_child(n, k); node = get_node(t, l, n); @@ -1185,10 +1604,47 @@ struct dm_target *dm_table_find_target(struct dm_table *t, sector_t sector) return &t->targets[(KEYS_PER_NODE * n) + k]; } +/* + * 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) { - unsigned *num_devices = data; + unsigned int *num_devices = data; (*num_devices)++; @@ -1201,13 +1657,11 @@ static int count_device(struct dm_target *ti, struct dm_dev *dev, * 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 *uninitialized_var(ti); - unsigned i = 0, num_devices = 0; - - while (i < dm_table_get_num_targets(table)) { - 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 int num_devices = 0; if (!ti->type->iterate_devices) return false; @@ -1220,25 +1674,141 @@ bool dm_table_has_no_data_devices(struct dm_table *table) return true; } +bool dm_table_is_wildcard(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 (!dm_target_is_wildcard(ti->type)) + return false; + } + + return true; +} + +static int device_not_zoned(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + bool *zoned = data; + + return bdev_is_zoned(dev->bdev) != *zoned; +} + +static int device_is_zoned_model(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + return bdev_is_zoned(dev->bdev); +} + +/* + * 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(struct dm_table *t, bool zoned) +{ + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + /* + * For the wildcard target (dm-error), if we do not have a + * backing device, we must always return false. If we have a + * backing device, the result must depend on checking zoned + * model, like for any other target. So for this, check directly + * if the target backing device is zoned as we get "false" when + * dm-error was set without a backing device. + */ + if (dm_target_is_wildcard(ti->type) && + !ti->type->iterate_devices(ti, device_is_zoned_model, NULL)) + return false; + + if (dm_target_supports_zoned_hm(ti->type)) { + if (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_not_zoned, + &zoned)) + return false; + } else if (!dm_target_supports_mixed_zoned_model(ti->type)) { + if (zoned) + return false; + } + } + + return true; +} + +static int device_not_matches_zone_sectors(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) +{ + unsigned int *zone_sectors = data; + + if (!bdev_is_zoned(dev->bdev)) + return 0; + return bdev_zone_sectors(dev->bdev) != *zone_sectors; +} + +/* + * 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(struct dm_table *t, bool zoned, + unsigned int zone_sectors) +{ + if (!zoned) + return 0; + + if (!dm_table_supports_zoned(t, zoned)) { + DMERR("%s: zoned model is not consistent across all devices", + dm_device_name(t->md)); + return -EINVAL; + } + + /* Check zone size validity and compatibility */ + if (!zone_sectors || !is_power_of_2(zone_sectors)) + return -EINVAL; + + 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; + } + + return 0; +} + /* * 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 *uninitialized_var(ti); struct queue_limits ti_limits; - unsigned i = 0; + unsigned int zone_sectors = 0; + bool zoned = false; - blk_set_stacking_limits(limits); + dm_set_stacking_limits(limits); - while (i < dm_table_get_num_targets(table)) { - blk_set_stacking_limits(&ti_limits); + t->integrity_supported = true; + 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++); + if (!dm_target_passes_integrity(ti->type)) + t->integrity_supported = false; + } - if (!ti->type->iterate_devices) + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); + + dm_set_stacking_limits(&ti_limits); + + if (!ti->type->iterate_devices) { + /* Set I/O hints portion of queue limits */ + if (ti->type->io_hints) + ti->type->io_hints(ti, &ti_limits); goto combine_limits; + } /* * Combine queue limits of all the devices this target uses. @@ -1246,6 +1816,15 @@ int dm_calculate_queue_limits(struct dm_table *table, ti->type->iterate_devices(ti, dm_set_device_limits, &ti_limits); + if (!zoned && (ti_limits.features & BLK_FEAT_ZONED)) { + /* + * After stacking all limits, validate all devices + * in table support this zoned model and zone sectors. + */ + zoned = (ti_limits.features & BLK_FEAT_ZONED); + zone_sectors = ti_limits.chunk_sectors; + } + /* Set I/O hints portion of queue limits */ if (ti->type->io_hints) ti->type->io_hints(ti, &ti_limits); @@ -1264,218 +1843,290 @@ combine_limits: * for the table. */ if (blk_stack_limits(limits, &ti_limits, 0) < 0) - DMWARN("%s: adding target device " - "(start sect %llu len %llu) " + 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); + + if (t->integrity_supported || + dm_target_has_integrity(ti->type)) { + if (!queue_limits_stack_integrity(limits, &ti_limits)) { + DMWARN("%s: adding target device (start sect %llu len %llu) " + "disabled integrity support due to incompatibility", + dm_device_name(t->md), + (unsigned long long) ti->begin, + (unsigned long long) ti->len); + t->integrity_supported = false; + } + } + } + + /* + * Verify that the zoned model and zone sectors, as determined before + * any .io_hints override, are the same across all devices in the table. + * - this is especially relevant if .io_hints is emulating a disk-managed + * zoned model on host-managed zoned block devices. + * BUT... + */ + if (limits->features & BLK_FEAT_ZONED) { + /* + * ...IF the above limits stacking determined a zoned model + * validate that all of the table's devices conform to it. + */ + zoned = limits->features & BLK_FEAT_ZONED; + zone_sectors = limits->chunk_sectors; } + if (validate_hardware_zoned(t, zoned, zone_sectors)) + return -EINVAL; - return validate_hardware_logical_block_alignment(table, limits); + return validate_hardware_logical_block_alignment(t, limits); } /* - * Set the integrity profile for this device if all devices used have - * matching profiles. We're quite deep in the resume path but still - * don't know if all devices (particularly DM devices this device - * may be stacked on) have matching profiles. Even if the profiles - * don't match we have no way to fail (to resume) at this point. + * Check if a target requires flush support even if none of the underlying + * devices need it (e.g. to persist target-specific metadata). */ -static void dm_table_set_integrity(struct dm_table *t) +static bool dm_table_supports_flush(struct dm_table *t) { - struct gendisk *template_disk = NULL; + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - if (!blk_get_integrity(dm_disk(t->md))) - return; + if (ti->num_flush_bios && ti->flush_supported) + return true; + } - template_disk = dm_table_get_integrity_disk(t, true); - if (template_disk) - blk_integrity_register(dm_disk(t->md), - blk_get_integrity(template_disk)); - else if (blk_integrity_is_initialized(dm_disk(t->md))) - DMWARN("%s: device no longer has a valid integrity profile", - dm_device_name(t->md)); - else - DMWARN("%s: unable to establish an integrity profile", - dm_device_name(t->md)); + return false; } -static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static int device_dax_write_cache_enabled(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) { - unsigned flush = (*(unsigned *)data); - struct request_queue *q = bdev_get_queue(dev->bdev); + struct dax_device *dax_dev = dev->dax_dev; - return q && (q->flush_flags & flush); + if (!dax_dev) + return false; + + if (dax_write_cache_enabled(dax_dev)) + return true; + return false; } -static bool dm_table_supports_flush(struct dm_table *t, unsigned flush) +static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev, + sector_t start, sector_t len, void *data) { - struct dm_target *ti; - unsigned i = 0; + struct request_queue *q = bdev_get_queue(dev->bdev); + int b; - /* - * 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. - */ - while (i < dm_table_get_num_targets(t)) { - ti = dm_table_get_target(t, i++); + mutex_lock(&q->limits_lock); + b = !q->limits.max_write_zeroes_sectors; + mutex_unlock(&q->limits_lock); + return b; +} - if (!ti->num_flush_bios) - continue; +static bool dm_table_supports_write_zeroes(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->flush_supported) - return 1; + if (!ti->num_write_zeroes_bios) + return false; - if (ti->type->iterate_devices && - ti->type->iterate_devices(ti, device_flush_capable, &flush)) - return 1; + if (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_not_write_zeroes_capable, NULL)) + return false; } - return 0; + return true; } -static bool dm_table_discard_zeroes_data(struct dm_table *t) +static bool dm_table_supports_nowait(struct dm_table *t) { - struct dm_target *ti; - unsigned i = 0; - - /* Ensure that all targets supports discard_zeroes_data. */ - 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->discard_zeroes_data_unsupported) - return 0; + if (!dm_target_supports_nowait(ti->type)) + return false; } - return 1; + return true; } -static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +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_nonrot(q); + return !bdev_max_discard_sectors(dev->bdev); } -static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +static bool dm_table_supports_discards(struct dm_table *t) { - struct request_queue *q = bdev_get_queue(dev->bdev); + 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; - return q && !blk_queue_add_random(q); + /* + * Either the target provides discard support (as implied by setting + * 'discards_supported') or it relies on _all_ data devices having + * discard support. + */ + if (!ti->discards_supported && + (!ti->type->iterate_devices || + ti->type->iterate_devices(ti, device_not_discard_capable, NULL))) + return false; + } + + return true; } -static bool dm_table_all_devices_attribute(struct dm_table *t, - iterate_devices_callout_fn func) +static int device_not_secure_erase_capable(struct dm_target *ti, + struct dm_dev *dev, sector_t start, + sector_t len, void *data) { - struct dm_target *ti; - unsigned i = 0; + return !bdev_max_secure_erase_sectors(dev->bdev); +} + +static bool dm_table_supports_secure_erase(struct dm_table *t) +{ + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - while (i < dm_table_get_num_targets(t)) { - ti = dm_table_get_target(t, i++); + if (!ti->num_secure_erase_bios) + return false; if (!ti->type->iterate_devices || - !ti->type->iterate_devices(ti, func, NULL)) - return 0; + ti->type->iterate_devices(ti, device_not_secure_erase_capable, NULL)) + return false; } - return 1; + return true; } -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_atomic_write_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 !bdev_can_atomic_write(dev->bdev); } -static bool dm_table_supports_write_same(struct dm_table *t) +static bool dm_table_supports_atomic_writes(struct dm_table *t) { - struct dm_target *ti; - unsigned i = 0; + for (unsigned int i = 0; i < t->num_targets; i++) { + struct dm_target *ti = dm_table_get_target(t, i); - while (i < dm_table_get_num_targets(t)) { - ti = dm_table_get_target(t, i++); + if (!dm_target_supports_atomic_writes(ti->type)) + return false; - if (!ti->num_write_same_bios) + if (!ti->type->iterate_devices) return false; - if (!ti->type->iterate_devices || - ti->type->iterate_devices(ti, device_not_write_same_capable, NULL)) + if (ti->type->iterate_devices(ti, + device_not_atomic_write_capable, NULL)) { return false; + } } + return true; +} +bool dm_table_supports_size_change(struct dm_table *t, sector_t old_size, + sector_t new_size) +{ + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && dm_has_zone_plugs(t->md) && + old_size != new_size) { + DMWARN("%s: device has zone write plug resources. " + "Cannot change size", + dm_device_name(t->md)); + return false; + } return true; } -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) { - unsigned flush = 0; + int r; + struct queue_limits old_limits; + + if (!dm_table_supports_nowait(t)) + limits->features &= ~BLK_FEAT_NOWAIT; /* - * Copy table's limits to the DM device's request_queue + * The current polling impementation does not support request based + * stacking. */ - q->limits = *limits; + if (!__table_type_bio_based(t->type)) + limits->features &= ~BLK_FEAT_POLL; - if (!dm_table_supports_discards(t)) - queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); - else - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); + if (!dm_table_supports_discards(t)) { + limits->max_hw_discard_sectors = 0; + limits->discard_granularity = 0; + limits->discard_alignment = 0; + } - if (dm_table_supports_flush(t, REQ_FLUSH)) { - flush |= REQ_FLUSH; - if (dm_table_supports_flush(t, REQ_FUA)) - flush |= REQ_FUA; + if (!dm_table_supports_write_zeroes(t)) { + limits->max_write_zeroes_sectors = 0; + limits->max_hw_wzeroes_unmap_sectors = 0; } - blk_queue_flush(q, flush); - if (!dm_table_discard_zeroes_data(t)) - q->limits.discard_zeroes_data = 0; + if (!dm_table_supports_secure_erase(t)) + limits->max_secure_erase_sectors = 0; - /* Ensure that all underlying devices are non-rotational. */ - if (dm_table_all_devices_attribute(t, device_is_nonrot)) - queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); + if (dm_table_supports_flush(t)) + limits->features |= BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA; + + if (dm_table_supports_dax(t, device_not_dax_capable)) + limits->features |= BLK_FEAT_DAX; else - queue_flag_clear_unlocked(QUEUE_FLAG_NONROT, q); + limits->features &= ~BLK_FEAT_DAX; + + /* For a zoned table, setup the zone related queue attributes. */ + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) { + if (limits->features & BLK_FEAT_ZONED) { + r = dm_set_zones_restrictions(t, q, limits); + if (r) + return r; + } else if (dm_has_zone_plugs(t->md)) { + DMWARN("%s: device has zone write plug resources. " + "Cannot switch to non-zoned table.", + dm_device_name(t->md)); + return -EINVAL; + } + } - if (!dm_table_supports_write_same(t)) - q->limits.max_write_same_sectors = 0; + if (dm_table_supports_atomic_writes(t)) + limits->features |= BLK_FEAT_ATOMIC_WRITES; - dm_table_set_integrity(t); + old_limits = queue_limits_start_update(q); + r = queue_limits_commit_update(q, limits); + if (r) + return r; /* - * Determine whether or not this queue's I/O timings contribute - * to the entropy pool, Only request-based targets use this. - * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not - * have it set. + * Now that the limits are set, check the zones mapped by the table + * and setup the resources for zone append emulation if necessary. */ - if (blk_queue_add_random(q) && dm_table_all_devices_attribute(t, device_is_not_random)) - queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q); + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && + (limits->features & BLK_FEAT_ZONED)) { + r = dm_revalidate_zones(t, q); + if (r) { + queue_limits_set(q, &old_limits); + return r; + } + } - /* - * QUEUE_FLAG_STACKABLE must be set after all queue settings are - * visible to other CPUs because, once the flag is set, incoming bios - * are processed by request-based dm, which refers to the queue - * settings. - * Until the flag set, bios are passed to bio-based dm and queued to - * md->deferred where queue settings are not needed yet. - * Those bios are passed to request-based dm at the resume time. - */ - smp_mb(); - if (dm_table_request_based(t)) - queue_flag_set_unlocked(QUEUE_FLAG_STACKABLE, q); -} + if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) + dm_finalize_zone_settings(t, limits); -unsigned int dm_table_get_num_targets(struct dm_table *t) -{ - return t->num_targets; + if (dm_table_supports_dax(t, device_not_dax_synchronous_capable)) + set_dax_synchronous(t->md->dax_dev); + + if (dm_table_any_dev_attr(t, device_dax_write_cache_enabled, NULL)) + dax_write_cache(t->md->dax_dev, true); + + dm_update_crypto_profile(q, t); + return 0; } struct list_head *dm_table_get_devices(struct dm_table *t) @@ -1483,25 +2134,39 @@ struct list_head *dm_table_get_devices(struct dm_table *t) return &t->devices; } -fmode_t dm_table_get_mode(struct dm_table *t) +blk_mode_t dm_table_get_mode(struct dm_table *t) { return t->mode; } EXPORT_SYMBOL(dm_table_get_mode); -static void suspend_targets(struct dm_table *t, unsigned postsuspend) +enum suspend_mode { + PRESUSPEND, + PRESUSPEND_UNDO, + POSTSUSPEND, +}; + +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--) { - if (postsuspend) { + 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) + ti->type->presuspend(ti); + break; + case PRESUSPEND_UNDO: + if (ti->type->presuspend_undo) + ti->type->presuspend_undo(ti); + break; + case POSTSUSPEND: if (ti->type->postsuspend) ti->type->postsuspend(ti); - } else if (ti->type->presuspend) - ti->type->presuspend(ti); - - ti++; + break; + } } } @@ -1510,7 +2175,15 @@ void dm_table_presuspend_targets(struct dm_table *t) if (!t) return; - suspend_targets(t, 0); + suspend_targets(t, PRESUSPEND); +} + +void dm_table_presuspend_undo_targets(struct dm_table *t) +{ + if (!t) + return; + + suspend_targets(t, PRESUSPEND_UNDO); } void dm_table_postsuspend_targets(struct dm_table *t) @@ -1518,26 +2191,32 @@ void dm_table_postsuspend_targets(struct dm_table *t) if (!t) return; - suspend_targets(t, 1); + suspend_targets(t, POSTSUSPEND); } 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; r = ti->type->preresume(ti); - if (r) + if (r) { + DMERR("%s: %s: preresume failed, error = %d", + dm_device_name(t->md), ti->type->name, r); return r; + } } 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); @@ -1546,91 +2225,25 @@ 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; -} - -int dm_table_any_busy_target(struct dm_table *t) -{ - unsigned i; - struct dm_target *ti; - - for (i = 0; i < t->num_targets; i++) { - ti = t->targets + i; - if (ti->type->busy && ti->type->busy(ti)) - return 1; - } - - return 0; -} - struct mapped_device *dm_table_get_md(struct dm_table *t) { return t->md; } EXPORT_SYMBOL(dm_table_get_md); -static int device_discard_capable(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) +const char *dm_table_device_name(struct dm_table *t) { - struct request_queue *q = bdev_get_queue(dev->bdev); - - return q && blk_queue_discard(q); + return dm_device_name(t->md); } +EXPORT_SYMBOL_GPL(dm_table_device_name); -bool dm_table_supports_discards(struct dm_table *t) +void dm_table_run_md_queue_async(struct dm_table *t) { - struct dm_target *ti; - unsigned i = 0; - - /* - * Unless any target used by the table set discards_supported, - * require at least one underlying device to support discards. - * t->devices includes internal dm devices such as mirror logs - * so we need to use iterate_devices here, which targets - * supporting discard selectively must provide. - */ - while (i < dm_table_get_num_targets(t)) { - ti = dm_table_get_target(t, i++); - - if (!ti->num_discard_bios) - continue; - - if (ti->discards_supported) - return 1; - - if (ti->type->iterate_devices && - ti->type->iterate_devices(ti, device_discard_capable, NULL)) - return 1; - } + if (!dm_table_request_based(t)) + return; - return 0; + if (t->md->queue) + blk_mq_run_hw_queues(t->md->queue, true); } +EXPORT_SYMBOL(dm_table_run_md_queue_async); + |