block: Inline blk_integrity in struct gendisk

Up until now the_integrity profile has been dynamically allocated and
attached to struct gendisk after the disk has been made active.

This causes problems because NVMe devices need to register the profile
prior to the partition table being read due to a mandatory metadata
buffer requirement. In addition, DM goes through hoops to deal with
preallocating, but not initializing integrity profiles.

Since the integrity profile is small (4 bytes + a pointer), Christoph
suggested moving it to struct gendisk proper. This requires several
changes:

 - Moving the blk_integrity definition to genhd.h.

 - Inlining blk_integrity in struct gendisk.

 - Removing the dynamic allocation code.

 - Adding helper functions which allow gendisk to set up and tear down
   the integrity sysfs dir when a disk is added/deleted.

 - Adding a blk_integrity_revalidate() callback for updating the stable
   pages bdi setting.

 - The calls that depend on whether a device has an integrity profile or
   not now key off of the bi->profile pointer.

 - Simplifying the integrity support routines in DM (Mike Snitzer).

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Reported-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
This commit is contained in:
Martin K. Petersen 2015-10-21 13:19:49 -04:00 committed by Jens Axboe
parent 4c241d08db
commit 25520d55cd
10 changed files with 153 additions and 182 deletions

View file

@ -30,10 +30,6 @@
#include "blk.h"
static struct kmem_cache *integrity_cachep;
static const char *bi_unsupported_name = "unsupported";
/**
* blk_rq_count_integrity_sg - Count number of integrity scatterlist elements
* @q: request queue
@ -146,13 +142,13 @@ EXPORT_SYMBOL(blk_rq_map_integrity_sg);
*/
int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
{
struct blk_integrity *b1 = gd1->integrity;
struct blk_integrity *b2 = gd2->integrity;
struct blk_integrity *b1 = &gd1->integrity;
struct blk_integrity *b2 = &gd2->integrity;
if (!b1 && !b2)
if (!b1->profile && !b2->profile)
return 0;
if (!b1 || !b2)
if (!b1->profile || !b2->profile)
return -1;
if (b1->interval_exp != b2->interval_exp) {
@ -163,21 +159,21 @@ int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
}
if (b1->tuple_size != b2->tuple_size) {
printk(KERN_ERR "%s: %s/%s tuple sz %u != %u\n", __func__,
pr_err("%s: %s/%s tuple sz %u != %u\n", __func__,
gd1->disk_name, gd2->disk_name,
b1->tuple_size, b2->tuple_size);
return -1;
}
if (b1->tag_size && b2->tag_size && (b1->tag_size != b2->tag_size)) {
printk(KERN_ERR "%s: %s/%s tag sz %u != %u\n", __func__,
pr_err("%s: %s/%s tag sz %u != %u\n", __func__,
gd1->disk_name, gd2->disk_name,
b1->tag_size, b2->tag_size);
return -1;
}
if (b1->profile != b2->profile) {
printk(KERN_ERR "%s: %s/%s type %s != %s\n", __func__,
pr_err("%s: %s/%s type %s != %s\n", __func__,
gd1->disk_name, gd2->disk_name,
b1->profile->name, b2->profile->name);
return -1;
@ -250,7 +246,7 @@ static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr,
char *page)
{
struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
struct blk_integrity *bi = blk_get_integrity(disk);
struct blk_integrity *bi = &disk->integrity;
struct integrity_sysfs_entry *entry =
container_of(attr, struct integrity_sysfs_entry, attr);
@ -262,7 +258,7 @@ static ssize_t integrity_attr_store(struct kobject *kobj,
size_t count)
{
struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
struct blk_integrity *bi = blk_get_integrity(disk);
struct blk_integrity *bi = &disk->integrity;
struct integrity_sysfs_entry *entry =
container_of(attr, struct integrity_sysfs_entry, attr);
ssize_t ret = 0;
@ -275,7 +271,7 @@ static ssize_t integrity_attr_store(struct kobject *kobj,
static ssize_t integrity_format_show(struct blk_integrity *bi, char *page)
{
if (bi != NULL && bi->profile->name != NULL)
if (bi->profile && bi->profile->name)
return sprintf(page, "%s\n", bi->profile->name);
else
return sprintf(page, "none\n");
@ -283,18 +279,13 @@ static ssize_t integrity_format_show(struct blk_integrity *bi, char *page)
static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page)
{
if (bi != NULL)
return sprintf(page, "%u\n", bi->tag_size);
else
return sprintf(page, "0\n");
return sprintf(page, "%u\n", bi->tag_size);
}
static ssize_t integrity_interval_show(struct blk_integrity *bi, char *page)
{
if (bi != NULL)
return sprintf(page, "%u\n", 1 << bi->interval_exp);
else
return sprintf(page, "0\n");
return sprintf(page, "%u\n",
bi->interval_exp ? 1 << bi->interval_exp : 0);
}
static ssize_t integrity_verify_store(struct blk_integrity *bi,
@ -388,113 +379,78 @@ static const struct sysfs_ops integrity_ops = {
.store = &integrity_attr_store,
};
static int __init blk_dev_integrity_init(void)
{
integrity_cachep = kmem_cache_create("blkdev_integrity",
sizeof(struct blk_integrity),
0, SLAB_PANIC, NULL);
return 0;
}
subsys_initcall(blk_dev_integrity_init);
static void blk_integrity_release(struct kobject *kobj)
{
struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
struct blk_integrity *bi = blk_get_integrity(disk);
kmem_cache_free(integrity_cachep, bi);
}
static struct kobj_type integrity_ktype = {
.default_attrs = integrity_attrs,
.sysfs_ops = &integrity_ops,
.release = blk_integrity_release,
};
bool blk_integrity_is_initialized(struct gendisk *disk)
{
struct blk_integrity *bi = blk_get_integrity(disk);
return (bi && bi->profile->name && strcmp(bi->profile->name,
bi_unsupported_name) != 0);
}
EXPORT_SYMBOL(blk_integrity_is_initialized);
/**
* blk_integrity_register - Register a gendisk as being integrity-capable
* @disk: struct gendisk pointer to make integrity-aware
* @template: optional integrity profile to register
* @template: block integrity profile to register
*
* Description: When a device needs to advertise itself as being able
* to send/receive integrity metadata it must use this function to
* register the capability with the block layer. The template is a
* blk_integrity struct with values appropriate for the underlying
* hardware. If template is NULL the new profile is allocated but
* not filled out. See Documentation/block/data-integrity.txt.
* Description: When a device needs to advertise itself as being able to
* send/receive integrity metadata it must use this function to register
* the capability with the block layer. The template is a blk_integrity
* struct with values appropriate for the underlying hardware. See
* Documentation/block/data-integrity.txt.
*/
int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
{
struct blk_integrity *bi;
struct blk_integrity *bi = &disk->integrity;
BUG_ON(disk == NULL);
bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
template->flags;
bi->interval_exp = ilog2(queue_logical_block_size(disk->queue));
bi->profile = template->profile;
bi->tuple_size = template->tuple_size;
bi->tag_size = template->tag_size;
if (disk->integrity == NULL) {
bi = kmem_cache_alloc(integrity_cachep,
GFP_KERNEL | __GFP_ZERO);
if (!bi)
return -1;
if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,
&disk_to_dev(disk)->kobj,
"%s", "integrity")) {
kmem_cache_free(integrity_cachep, bi);
return -1;
}
kobject_uevent(&disk->integrity_kobj, KOBJ_ADD);
bi->flags |= BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE;
bi->interval_exp = ilog2(queue_logical_block_size(disk->queue));
disk->integrity = bi;
} else
bi = disk->integrity;
/* Use the provided profile as template */
if (template != NULL) {
bi->profile = template->profile;
bi->tuple_size = template->tuple_size;
bi->tag_size = template->tag_size;
bi->flags |= template->flags;
} else
bi->profile->name = bi_unsupported_name;
disk->queue->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
return 0;
blk_integrity_revalidate(disk);
}
EXPORT_SYMBOL(blk_integrity_register);
/**
* blk_integrity_unregister - Remove block integrity profile
* @disk: disk whose integrity profile to deallocate
* blk_integrity_unregister - Unregister block integrity profile
* @disk: disk whose integrity profile to unregister
*
* Description: This function frees all memory used by the block
* integrity profile. To be called at device teardown.
* Description: This function unregisters the integrity capability from
* a block device.
*/
void blk_integrity_unregister(struct gendisk *disk)
{
struct blk_integrity *bi;
blk_integrity_revalidate(disk);
memset(&disk->integrity, 0, sizeof(struct blk_integrity));
}
EXPORT_SYMBOL(blk_integrity_unregister);
if (!disk || !disk->integrity)
void blk_integrity_revalidate(struct gendisk *disk)
{
struct blk_integrity *bi = &disk->integrity;
if (!(disk->flags & GENHD_FL_UP))
return;
disk->queue->backing_dev_info.capabilities &= ~BDI_CAP_STABLE_WRITES;
if (bi->profile)
disk->queue->backing_dev_info.capabilities |=
BDI_CAP_STABLE_WRITES;
else
disk->queue->backing_dev_info.capabilities &=
~BDI_CAP_STABLE_WRITES;
}
bi = disk->integrity;
void blk_integrity_add(struct gendisk *disk)
{
if (kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype,
&disk_to_dev(disk)->kobj, "%s", "integrity"))
return;
kobject_uevent(&disk->integrity_kobj, KOBJ_ADD);
}
void blk_integrity_del(struct gendisk *disk)
{
kobject_uevent(&disk->integrity_kobj, KOBJ_REMOVE);
kobject_del(&disk->integrity_kobj);
kobject_put(&disk->integrity_kobj);
disk->integrity = NULL;
}
EXPORT_SYMBOL(blk_integrity_unregister);

View file

@ -630,6 +630,7 @@ void add_disk(struct gendisk *disk)
WARN_ON(retval);
disk_add_events(disk);
blk_integrity_add(disk);
}
EXPORT_SYMBOL(add_disk);
@ -638,6 +639,7 @@ void del_gendisk(struct gendisk *disk)
struct disk_part_iter piter;
struct hd_struct *part;
blk_integrity_del(disk);
disk_del_events(disk);
/* invalidate stuff */

View file

@ -428,6 +428,7 @@ rescan:
if (disk->fops->revalidate_disk)
disk->fops->revalidate_disk(disk);
blk_integrity_revalidate(disk);
check_disk_size_change(disk, bdev);
bdev->bd_invalidated = 0;
if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))

View file

@ -1014,15 +1014,16 @@ static int dm_table_build_index(struct dm_table *t)
return r;
}
static bool integrity_profile_exists(struct gendisk *disk)
{
return !!blk_get_integrity(disk);
}
/*
* 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.
*/
static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t,
bool match_all)
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;
@ -1030,10 +1031,8 @@ static struct gendisk * dm_table_get_integrity_disk(struct dm_table *t,
list_for_each_entry(dd, devices, list) {
template_disk = dd->dm_dev->bdev->bd_disk;
if (!blk_get_integrity(template_disk))
if (!integrity_profile_exists(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;
@ -1052,34 +1051,40 @@ no_integrity:
}
/*
* 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
* 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
* must be resumed before they will have an initialized integity
* profile). Consequently, stacked DM devices force a 2 stage integrity
* profile validation: First pass during table load, final pass during
* resume.
*/
static int dm_table_prealloc_integrity(struct dm_table *t, struct mapped_device *md)
static int dm_table_register_integrity(struct dm_table *t)
{
struct mapped_device *md = t->md;
struct gendisk *template_disk = NULL;
template_disk = dm_table_get_integrity_disk(t, false);
template_disk = dm_table_get_integrity_disk(t);
if (!template_disk)
return 0;
if (!blk_integrity_is_initialized(dm_disk(md))) {
if (!integrity_profile_exists(dm_disk(md))) {
t->integrity_supported = 1;
return blk_integrity_register(dm_disk(md), NULL);
/*
* Register integrity profile during table load; we can do
* this because the final profile must match during resume.
*/
blk_integrity_register(dm_disk(md),
blk_get_integrity(template_disk));
return 0;
}
/*
* If DM device already has an initalized integrity
* If DM device already has an initialized integrity
* profile the new profile should not conflict.
*/
if (blk_integrity_is_initialized(template_disk) &&
blk_integrity_compare(dm_disk(md), template_disk) < 0) {
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),
@ -1087,7 +1092,7 @@ static int dm_table_prealloc_integrity(struct dm_table *t, struct mapped_device
return 1;
}
/* Preserve existing initialized integrity profile */
/* Preserve existing integrity profile */
t->integrity_supported = 1;
return 0;
}
@ -1112,7 +1117,7 @@ int dm_table_complete(struct dm_table *t)
return r;
}
r = dm_table_prealloc_integrity(t, t->md);
r = dm_table_register_integrity(t);
if (r) {
DMERR("could not register integrity profile.");
return r;
@ -1278,29 +1283,30 @@ combine_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.
* Verify that all devices have an integrity profile that matches the
* DM device's registered integrity profile. If the profiles don't
* match then unregister the DM device's integrity profile.
*/
static void dm_table_set_integrity(struct dm_table *t)
static void dm_table_verify_integrity(struct dm_table *t)
{
struct gendisk *template_disk = NULL;
if (!blk_get_integrity(dm_disk(t->md)))
return;
if (t->integrity_supported) {
/*
* Verify that the original integrity profile
* matches all the devices in this table.
*/
template_disk = dm_table_get_integrity_disk(t);
if (template_disk &&
blk_integrity_compare(dm_disk(t->md), template_disk) >= 0)
return;
}
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
if (integrity_profile_exists(dm_disk(t->md))) {
DMWARN("%s: unable to establish an integrity profile",
dm_device_name(t->md));
blk_integrity_unregister(dm_disk(t->md));
}
}
static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev,
@ -1500,7 +1506,7 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
else
queue_flag_set_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
dm_table_set_integrity(t);
dm_table_verify_integrity(t);
/*
* Determine whether or not this queue's I/O timings contribute

View file

@ -1962,12 +1962,9 @@ int md_integrity_register(struct mddev *mddev)
* All component devices are integrity capable and have matching
* profiles, register the common profile for the md device.
*/
if (blk_integrity_register(mddev->gendisk,
bdev_get_integrity(reference->bdev)) != 0) {
printk(KERN_ERR "md: failed to register integrity for %s\n",
mdname(mddev));
return -EINVAL;
}
blk_integrity_register(mddev->gendisk,
bdev_get_integrity(reference->bdev));
printk(KERN_NOTICE "md: data integrity enabled on %s\n", mdname(mddev));
if (bioset_integrity_create(mddev->bio_set, BIO_POOL_SIZE)) {
printk(KERN_ERR "md: failed to create integrity pool for %s\n",

View file

@ -405,7 +405,6 @@ int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
.generate_fn = nd_pi_nop_generate_verify,
.verify_fn = nd_pi_nop_generate_verify,
};
int ret;
if (meta_size == 0)
return 0;
@ -414,10 +413,7 @@ int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
bi.tuple_size = meta_size;
bi.tag_size = meta_size;
ret = blk_integrity_register(disk, &bi);
if (ret)
return ret;
blk_integrity_register(disk, &bi);
blk_queue_max_integrity_segments(disk->queue, 1);
return 0;

View file

@ -538,7 +538,7 @@ static void nvme_dif_remap(struct request *req,
virt = bip_get_seed(bip);
phys = nvme_block_nr(ns, blk_rq_pos(req));
nlb = (blk_rq_bytes(req) >> ns->lba_shift);
ts = ns->disk->integrity->tuple_size;
ts = ns->disk->integrity.tuple_size;
for (i = 0; i < nlb; i++, virt++, phys++) {
pi = (struct t10_pi_tuple *)p;
@ -2044,8 +2044,7 @@ static int nvme_revalidate_disk(struct gendisk *disk)
ns->pi_type = pi_type;
blk_queue_logical_block_size(ns->queue, bs);
if (ns->ms && !blk_get_integrity(disk) && (disk->flags & GENHD_FL_UP) &&
!ns->ext)
if (ns->ms && !ns->ext)
nvme_init_integrity(ns);
if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))

View file

@ -1075,7 +1075,7 @@ int revalidate_disk(struct gendisk *disk)
if (disk->fops->revalidate_disk)
ret = disk->fops->revalidate_disk(disk);
blk_integrity_revalidate(disk);
bdev = bdget_disk(disk, 0);
if (!bdev)
return ret;

View file

@ -1468,16 +1468,7 @@ struct blk_integrity_profile {
const char *name;
};
struct blk_integrity {
struct blk_integrity_profile *profile;
unsigned char flags;
unsigned char tuple_size;
unsigned char interval_exp;
unsigned char tag_size;
};
extern bool blk_integrity_is_initialized(struct gendisk *);
extern int blk_integrity_register(struct gendisk *, struct blk_integrity *);
extern void blk_integrity_register(struct gendisk *, struct blk_integrity *);
extern void blk_integrity_unregister(struct gendisk *);
extern int blk_integrity_compare(struct gendisk *, struct gendisk *);
extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
@ -1488,15 +1479,20 @@ extern bool blk_integrity_merge_rq(struct request_queue *, struct request *,
extern bool blk_integrity_merge_bio(struct request_queue *, struct request *,
struct bio *);
static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
{
struct blk_integrity *bi = &disk->integrity;
if (!bi->profile)
return NULL;
return bi;
}
static inline
struct blk_integrity *bdev_get_integrity(struct block_device *bdev)
{
return bdev->bd_disk->integrity;
}
static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
{
return disk->integrity;
return blk_get_integrity(bdev->bd_disk);
}
static inline bool blk_integrity_rq(struct request *rq)
@ -1570,10 +1566,9 @@ static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
{
return 0;
}
static inline int blk_integrity_register(struct gendisk *d,
static inline void blk_integrity_register(struct gendisk *d,
struct blk_integrity *b)
{
return 0;
}
static inline void blk_integrity_unregister(struct gendisk *d)
{
@ -1598,10 +1593,7 @@ static inline bool blk_integrity_merge_bio(struct request_queue *rq,
{
return true;
}
static inline bool blk_integrity_is_initialized(struct gendisk *g)
{
return 0;
}
static inline bool integrity_req_gap_back_merge(struct request *req,
struct bio *next)
{

View file

@ -163,6 +163,18 @@ struct disk_part_tbl {
struct disk_events;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
struct blk_integrity {
struct blk_integrity_profile *profile;
unsigned char flags;
unsigned char tuple_size;
unsigned char interval_exp;
unsigned char tag_size;
};
#endif /* CONFIG_BLK_DEV_INTEGRITY */
struct gendisk {
/* major, first_minor and minors are input parameters only,
* don't use directly. Use disk_devt() and disk_max_parts().
@ -198,9 +210,9 @@ struct gendisk {
atomic_t sync_io; /* RAID */
struct disk_events *ev;
#ifdef CONFIG_BLK_DEV_INTEGRITY
struct blk_integrity *integrity;
struct blk_integrity integrity;
struct kobject integrity_kobj;
#endif
#endif /* CONFIG_BLK_DEV_INTEGRITY */
int node_id;
};
@ -728,6 +740,16 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
#endif
}
#if defined(CONFIG_BLK_DEV_INTEGRITY)
extern void blk_integrity_add(struct gendisk *);
extern void blk_integrity_del(struct gendisk *);
extern void blk_integrity_revalidate(struct gendisk *);
#else /* CONFIG_BLK_DEV_INTEGRITY */
static inline void blk_integrity_add(struct gendisk *disk) { }
static inline void blk_integrity_del(struct gendisk *disk) { }
static inline void blk_integrity_revalidate(struct gendisk *disk) { }
#endif /* CONFIG_BLK_DEV_INTEGRITY */
#else /* CONFIG_BLOCK */
static inline void printk_all_partitions(void) { }