Commit 7ba1ba12 authored by Martin K. Petersen's avatar Martin K. Petersen Committed by Jens Axboe

block: Block layer data integrity support

Some block devices support verifying the integrity of requests by way
of checksums or other protection information that is submitted along
with the I/O.

This patch implements support for generating and verifying integrity
metadata, as well as correctly merging, splitting and cloning bios and
requests that have this extra information attached.

See Documentation/block/data-integrity.txt for more information.
Signed-off-by: default avatarMartin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: default avatarJens Axboe <jens.axboe@oracle.com>
parent 51d654e1
......@@ -81,6 +81,18 @@ config BLK_DEV_BSG
If unsure, say N.
config BLK_DEV_INTEGRITY
bool "Block layer data integrity support"
---help---
Some storage devices allow extra information to be
stored/retrieved to help protect the data. The block layer
data integrity option provides hooks which can be used by
filesystems to ensure better data integrity.
Say yes here if you have a storage device that provides the
T10/SCSI Data Integrity Field or the T13/ATA External Path
Protection. If in doubt, say N.
endif # BLOCK
config BLOCK_COMPAT
......
......@@ -14,3 +14,4 @@ obj-$(CONFIG_IOSCHED_CFQ) += cfq-iosched.o
obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o
obj-$(CONFIG_BLK_DEV_INTEGRITY) += blk-integrity.o
......@@ -143,6 +143,10 @@ static void req_bio_endio(struct request *rq, struct bio *bio,
bio->bi_size -= nbytes;
bio->bi_sector += (nbytes >> 9);
if (bio_integrity(bio))
bio_integrity_advance(bio, nbytes);
if (bio->bi_size == 0)
bio_endio(bio, error);
} else {
......@@ -1381,6 +1385,9 @@ static inline void __generic_make_request(struct bio *bio)
*/
blk_partition_remap(bio);
if (bio_integrity_enabled(bio) && bio_integrity_prep(bio))
goto end_io;
if (old_sector != -1)
blk_add_trace_remap(q, bio, old_dev, bio->bi_sector,
old_sector);
......
/*
* blk-integrity.c - Block layer data integrity extensions
*
* Copyright (C) 2007, 2008 Oracle Corporation
* Written by: Martin K. Petersen <martin.petersen@oracle.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License version
* 2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; see the file COPYING. If not, write to
* the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139,
* USA.
*
*/
#include <linux/blkdev.h>
#include <linux/mempool.h>
#include <linux/bio.h>
#include <linux/scatterlist.h>
#include "blk.h"
static struct kmem_cache *integrity_cachep;
/**
* blk_rq_count_integrity_sg - Count number of integrity scatterlist elements
* @rq: request with integrity metadata attached
*
* Description: Returns the number of elements required in a
* scatterlist corresponding to the integrity metadata in a request.
*/
int blk_rq_count_integrity_sg(struct request *rq)
{
struct bio_vec *iv, *ivprv;
struct req_iterator iter;
unsigned int segments;
ivprv = NULL;
segments = 0;
rq_for_each_integrity_segment(iv, rq, iter) {
if (!ivprv || !BIOVEC_PHYS_MERGEABLE(ivprv, iv))
segments++;
ivprv = iv;
}
return segments;
}
EXPORT_SYMBOL(blk_rq_count_integrity_sg);
/**
* blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
* @rq: request with integrity metadata attached
* @sglist: target scatterlist
*
* Description: Map the integrity vectors in request into a
* scatterlist. The scatterlist must be big enough to hold all
* elements. I.e. sized using blk_rq_count_integrity_sg().
*/
int blk_rq_map_integrity_sg(struct request *rq, struct scatterlist *sglist)
{
struct bio_vec *iv, *ivprv;
struct req_iterator iter;
struct scatterlist *sg;
unsigned int segments;
ivprv = NULL;
sg = NULL;
segments = 0;
rq_for_each_integrity_segment(iv, rq, iter) {
if (ivprv) {
if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv))
goto new_segment;
sg->length += iv->bv_len;
} else {
new_segment:
if (!sg)
sg = sglist;
else {
sg->page_link &= ~0x02;
sg = sg_next(sg);
}
sg_set_page(sg, iv->bv_page, iv->bv_len, iv->bv_offset);
segments++;
}
ivprv = iv;
}
if (sg)
sg_mark_end(sg);
return segments;
}
EXPORT_SYMBOL(blk_rq_map_integrity_sg);
/**
* blk_integrity_compare - Compare integrity profile of two block devices
* @b1: Device to compare
* @b2: Device to compare
*
* Description: Meta-devices like DM and MD need to verify that all
* sub-devices use the same integrity format before advertising to
* upper layers that they can send/receive integrity metadata. This
* function can be used to check whether two block devices have
* compatible integrity formats.
*/
int blk_integrity_compare(struct block_device *bd1, struct block_device *bd2)
{
struct blk_integrity *b1 = bd1->bd_disk->integrity;
struct blk_integrity *b2 = bd2->bd_disk->integrity;
BUG_ON(bd1->bd_disk == NULL);
BUG_ON(bd2->bd_disk == NULL);
if (!b1 || !b2)
return 0;
if (b1->sector_size != b2->sector_size) {
printk(KERN_ERR "%s: %s/%s sector sz %u != %u\n", __func__,
bd1->bd_disk->disk_name, bd2->bd_disk->disk_name,
b1->sector_size, b2->sector_size);
return -1;
}
if (b1->tuple_size != b2->tuple_size) {
printk(KERN_ERR "%s: %s/%s tuple sz %u != %u\n", __func__,
bd1->bd_disk->disk_name, bd2->bd_disk->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__,
bd1->bd_disk->disk_name, bd2->bd_disk->disk_name,
b1->tag_size, b2->tag_size);
return -1;
}
if (strcmp(b1->name, b2->name)) {
printk(KERN_ERR "%s: %s/%s type %s != %s\n", __func__,
bd1->bd_disk->disk_name, bd2->bd_disk->disk_name,
b1->name, b2->name);
return -1;
}
return 0;
}
EXPORT_SYMBOL(blk_integrity_compare);
struct integrity_sysfs_entry {
struct attribute attr;
ssize_t (*show)(struct blk_integrity *, char *);
ssize_t (*store)(struct blk_integrity *, const char *, size_t);
};
static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr,
char *page)
{
struct blk_integrity *bi =
container_of(kobj, struct blk_integrity, kobj);
struct integrity_sysfs_entry *entry =
container_of(attr, struct integrity_sysfs_entry, attr);
return entry->show(bi, page);
}
static ssize_t integrity_attr_store(struct kobject *kobj, struct attribute *attr,
const char *page, size_t count)
{
struct blk_integrity *bi =
container_of(kobj, struct blk_integrity, kobj);
struct integrity_sysfs_entry *entry =
container_of(attr, struct integrity_sysfs_entry, attr);
ssize_t ret = 0;
if (entry->store)
ret = entry->store(bi, page, count);
return ret;
}
static ssize_t integrity_format_show(struct blk_integrity *bi, char *page)
{
if (bi != NULL && bi->name != NULL)
return sprintf(page, "%s\n", bi->name);
else
return sprintf(page, "none\n");
}
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");
}
static ssize_t integrity_read_store(struct blk_integrity *bi,
const char *page, size_t count)
{
char *p = (char *) page;
unsigned long val = simple_strtoul(p, &p, 10);
if (val)
set_bit(INTEGRITY_FLAG_READ, &bi->flags);
else
clear_bit(INTEGRITY_FLAG_READ, &bi->flags);
return count;
}
static ssize_t integrity_read_show(struct blk_integrity *bi, char *page)
{
return sprintf(page, "%d\n",
test_bit(INTEGRITY_FLAG_READ, &bi->flags) ? 1 : 0);
}
static ssize_t integrity_write_store(struct blk_integrity *bi,
const char *page, size_t count)
{
char *p = (char *) page;
unsigned long val = simple_strtoul(p, &p, 10);
if (val)
set_bit(INTEGRITY_FLAG_WRITE, &bi->flags);
else
clear_bit(INTEGRITY_FLAG_WRITE, &bi->flags);
return count;
}
static ssize_t integrity_write_show(struct blk_integrity *bi, char *page)
{
return sprintf(page, "%d\n",
test_bit(INTEGRITY_FLAG_WRITE, &bi->flags) ? 1 : 0);
}
static struct integrity_sysfs_entry integrity_format_entry = {
.attr = { .name = "format", .mode = S_IRUGO },
.show = integrity_format_show,
};
static struct integrity_sysfs_entry integrity_tag_size_entry = {
.attr = { .name = "tag_size", .mode = S_IRUGO },
.show = integrity_tag_size_show,
};
static struct integrity_sysfs_entry integrity_read_entry = {
.attr = { .name = "read_verify", .mode = S_IRUGO | S_IWUSR },
.show = integrity_read_show,
.store = integrity_read_store,
};
static struct integrity_sysfs_entry integrity_write_entry = {
.attr = { .name = "write_generate", .mode = S_IRUGO | S_IWUSR },
.show = integrity_write_show,
.store = integrity_write_store,
};
static struct attribute *integrity_attrs[] = {
&integrity_format_entry.attr,
&integrity_tag_size_entry.attr,
&integrity_read_entry.attr,
&integrity_write_entry.attr,
NULL,
};
static struct sysfs_ops integrity_ops = {
.show = &integrity_attr_show,
.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 blk_integrity *bi =
container_of(kobj, struct blk_integrity, kobj);
kmem_cache_free(integrity_cachep, bi);
}
static struct kobj_type integrity_ktype = {
.default_attrs = integrity_attrs,
.sysfs_ops = &integrity_ops,
.release = blk_integrity_release,
};
/**
* blk_integrity_register - Register a gendisk as being integrity-capable
* @disk: struct gendisk pointer to make integrity-aware
* @template: integrity profile
*
* 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)
{
struct blk_integrity *bi;
BUG_ON(disk == NULL);
BUG_ON(template == NULL);
if (disk->integrity == NULL) {
bi = kmem_cache_alloc(integrity_cachep, GFP_KERNEL | __GFP_ZERO);
if (!bi)
return -1;
if (kobject_init_and_add(&bi->kobj, &integrity_ktype,
&disk->dev.kobj, "%s", "integrity")) {
kmem_cache_free(integrity_cachep, bi);
return -1;
}
kobject_uevent(&bi->kobj, KOBJ_ADD);
set_bit(INTEGRITY_FLAG_READ, &bi->flags);
set_bit(INTEGRITY_FLAG_WRITE, &bi->flags);
bi->sector_size = disk->queue->hardsect_size;
disk->integrity = bi;
} else
bi = disk->integrity;
/* Use the provided profile as template */
bi->name = template->name;
bi->generate_fn = template->generate_fn;
bi->verify_fn = template->verify_fn;
bi->tuple_size = template->tuple_size;
bi->set_tag_fn = template->set_tag_fn;
bi->get_tag_fn = template->get_tag_fn;
bi->tag_size = template->tag_size;
return 0;
}
EXPORT_SYMBOL(blk_integrity_register);
/**
* blk_integrity_unregister - Remove block integrity profile
* @disk: disk whose integrity profile to deallocate
*
* Description: This function frees all memory used by the block
* integrity profile. To be called at device teardown.
*/
void blk_integrity_unregister(struct gendisk *disk)
{
struct blk_integrity *bi;
if (!disk || !disk->integrity)
return;
bi = disk->integrity;
kobject_uevent(&bi->kobj, KOBJ_REMOVE);
kobject_del(&bi->kobj);
kobject_put(&disk->dev.kobj);
kmem_cache_free(integrity_cachep, bi);
}
EXPORT_SYMBOL(blk_integrity_unregister);
......@@ -441,6 +441,9 @@ static int attempt_merge(struct request_queue *q, struct request *req,
|| next->special)
return 0;
if (blk_integrity_rq(req) != blk_integrity_rq(next))
return 0;
/*
* If we are allowed to merge, then append bio list
* from next to rq and release next. merge_requests_fn
......
......@@ -51,4 +51,12 @@ static inline int queue_congestion_off_threshold(struct request_queue *q)
return q->nr_congestion_off;
}
#if defined(CONFIG_BLK_DEV_INTEGRITY)
#define rq_for_each_integrity_segment(bvl, _rq, _iter) \
__rq_for_each_bio(_iter.bio, _rq) \
bip_for_each_vec(bvl, _iter.bio->bi_integrity, _iter.i)
#endif /* BLK_DEV_INTEGRITY */
#endif
......@@ -86,6 +86,12 @@ int elv_rq_merge_ok(struct request *rq, struct bio *bio)
if (rq->rq_disk != bio->bi_bdev->bd_disk || rq->special)
return 0;
/*
* only merge integrity protected bio into ditto rq
*/
if (bio_integrity(bio) != blk_integrity_rq(rq))
return 0;
if (!elv_iosched_allow_merge(rq, bio))
return 0;
......
......@@ -19,6 +19,7 @@ else
obj-y += no-block.o
endif
obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o
obj-$(CONFIG_INOTIFY) += inotify.o
obj-$(CONFIG_INOTIFY_USER) += inotify_user.o
obj-$(CONFIG_EPOLL) += eventpoll.o
......
This diff is collapsed.
......@@ -50,6 +50,11 @@ static struct biovec_slab bvec_slabs[BIOVEC_NR_POOLS] __read_mostly = {
*/
struct bio_set *fs_bio_set;
unsigned int bvec_nr_vecs(unsigned short idx)
{
return bvec_slabs[idx].nr_vecs;
}
struct bio_vec *bvec_alloc_bs(gfp_t gfp_mask, int nr, unsigned long *idx, struct bio_set *bs)
{
struct bio_vec *bvl;
......@@ -91,6 +96,9 @@ void bio_free(struct bio *bio, struct bio_set *bio_set)
mempool_free(bio->bi_io_vec, bio_set->bvec_pools[pool_idx]);
}
if (bio_integrity(bio))
bio_integrity_free(bio, bio_set);
mempool_free(bio, bio_set->bio_pool);
}
......@@ -249,9 +257,19 @@ struct bio *bio_clone(struct bio *bio, gfp_t gfp_mask)
{
struct bio *b = bio_alloc_bioset(gfp_mask, bio->bi_max_vecs, fs_bio_set);
if (b) {
b->bi_destructor = bio_fs_destructor;
__bio_clone(b, bio);
if (!b)
return NULL;
b->bi_destructor = bio_fs_destructor;
__bio_clone(b, bio);
if (bio_integrity(bio)) {
int ret;
ret = bio_integrity_clone(b, bio, fs_bio_set);
if (ret < 0)
return NULL;
}
return b;
......@@ -1223,6 +1241,9 @@ struct bio_pair *bio_split(struct bio *bi, mempool_t *pool, int first_sectors)
bp->bio1.bi_private = bi;
bp->bio2.bi_private = pool;
if (bio_integrity(bi))
bio_integrity_split(bi, bp, first_sectors);
return bp;
}
......@@ -1264,6 +1285,7 @@ void bioset_free(struct bio_set *bs)
if (bs->bio_pool)
mempool_destroy(bs->bio_pool);
bioset_integrity_free(bs);
biovec_free_pools(bs);
kfree(bs);
......@@ -1280,6 +1302,9 @@ struct bio_set *bioset_create(int bio_pool_size, int bvec_pool_size)
if (!bs->bio_pool)
goto bad;
if (bioset_integrity_create(bs, bio_pool_size))
goto bad;
if (!biovec_create_pools(bs, bvec_pool_size))
return bs;
......@@ -1306,6 +1331,7 @@ static int __init init_bio(void)
{
bio_slab = KMEM_CACHE(bio, SLAB_HWCACHE_ALIGN|SLAB_PANIC);
bio_integrity_init_slab();
biovec_init_slabs();
fs_bio_set = bioset_create(BIO_POOL_SIZE, 2);
......
</
......@@ -64,6 +64,7 @@ struct bio_vec {
struct bio_set;
struct bio;
struct bio_integrity_payload;
typedef void (bio_end_io_t) (struct bio *, int);
typedef void (bio_destructor_t) (struct bio *);
......@@ -112,6 +113,9 @@ struct bio {
atomic_t bi_cnt; /* pin count */
void *bi_private;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
struct bio_integrity_payload *bi_integrity; /* data integrity */
#endif
bio_destructor_t *bi_destructor; /* destructor */
};
......@@ -271,6 +275,29 @@ static inline void *bio_data(struct bio *bio)
*/
#define bio_get(bio) atomic_inc(&(bio)->bi_cnt)
#if defined(CONFIG_BLK_DEV_INTEGRITY)
/*
* bio integrity payload
*/
struct bio_integrity_payload {
struct bio *bip_bio; /* parent bio */
struct bio_vec *bip_vec; /* integrity data vector */
sector_t bip_sector; /* virtual start sector */
void *bip_buf; /* generated integrity data */
bio_end_io_t *bip_end_io; /* saved I/O completion fn */
int bip_error; /* saved I/O error */
unsigned int bip_size;
unsigned short bip_pool; /* pool the ivec came from */
unsigned short bip_vcnt; /* # of integrity bio_vecs */
unsigned short bip_idx; /* current bip_vec index */
struct work_struct bip_work; /* I/O completion */
};
#endif /* CONFIG_BLK_DEV_INTEGRITY */
/*
* A bio_pair is used when we need to split a bio.
......@@ -283,10 +310,14 @@ static inline void *bio_data(struct bio *bio)
* in bio2.bi_private
*/
struct bio_pair {
struct bio bio1, bio2;
struct bio_vec bv1, bv2;
atomic_t cnt;
int error;
struct bio bio1, bio2;
struct bio_vec bv1, bv2;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
struct bio_integrity_payload bip1, bip2;
struct bio_vec iv1, iv2;
#endif
atomic_t cnt;
int error;
};
extern struct bio_pair *bio_split(struct bio *bi, mempool_t *pool,
int first_sectors);
......@@ -334,6 +365,7 @@ extern struct bio *bio_copy_user_iov(struct request_queue *, struct sg_iovec *,
extern int bio_uncopy_user(struct bio *);
void zero_fill_bio(struct bio *bio);
extern struct bio_vec *bvec_alloc_bs(gfp_t, int, unsigned long *, struct bio_set *);
extern unsigned int bvec_nr_vecs(unsigned short idx);
/*
* bio_set is used to allow other portions of the IO system to