linux/block/blk-integrity.c

433 lines
11 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* blk-integrity.c - Block layer data integrity extensions
*
* Copyright (C) 2007, 2008 Oracle Corporation
* Written by: Martin K. Petersen <martin.petersen@oracle.com>
*/
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/mempool.h>
#include <linux/bio.h>
#include <linux/scatterlist.h>
#include <linux/export.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
#include <linux/slab.h>
#include "blk.h"
/**
* blk_rq_count_integrity_sg - Count number of integrity scatterlist elements
* @q: request queue
* @bio: bio with integrity metadata attached
*
* Description: Returns the number of elements required in a
* scatterlist corresponding to the integrity metadata in a bio.
*/
int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio)
{
struct bio_vec iv, ivprv = { NULL };
unsigned int segments = 0;
unsigned int seg_size = 0;
struct bvec_iter iter;
int prev = 0;
bio_for_each_integrity_vec(iv, bio, iter) {
if (prev) {
if (!biovec_phys_mergeable(q, &ivprv, &iv))
goto new_segment;
if (seg_size + iv.bv_len > queue_max_segment_size(q))
goto new_segment;
seg_size += iv.bv_len;
} else {
new_segment:
segments++;
seg_size = iv.bv_len;
}
prev = 1;
ivprv = iv;
}
return segments;
}
EXPORT_SYMBOL(blk_rq_count_integrity_sg);
/**
* blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
* @q: request queue
* @bio: bio 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_queue *q, struct bio *bio,
struct scatterlist *sglist)
{
struct bio_vec iv, ivprv = { NULL };
struct scatterlist *sg = NULL;
unsigned int segments = 0;
struct bvec_iter iter;
int prev = 0;
bio_for_each_integrity_vec(iv, bio, iter) {
if (prev) {
if (!biovec_phys_mergeable(q, &ivprv, &iv))
goto new_segment;
if (sg->length + iv.bv_len > queue_max_segment_size(q))
goto new_segment;
sg->length += iv.bv_len;
} else {
new_segment:
if (!sg)
sg = sglist;
else {
sg_unmark_end(sg);
sg = sg_next(sg);
}
sg_set_page(sg, iv.bv_page, iv.bv_len, iv.bv_offset);
segments++;
}
prev = 1;
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 disks
* @gd1: Disk to compare
* @gd2: Disk 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 gendisk devices have
* compatible integrity formats.
*/
int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
{
struct blk_integrity *b1 = &gd1->queue->integrity;
struct blk_integrity *b2 = &gd2->queue->integrity;
if (!b1->profile && !b2->profile)
return 0;
if (!b1->profile || !b2->profile)
return -1;
if (b1->interval_exp != b2->interval_exp) {
pr_err("%s: %s/%s protection interval %u != %u\n",
__func__, gd1->disk_name, gd2->disk_name,
1 << b1->interval_exp, 1 << b2->interval_exp);
return -1;
}
if (b1->tuple_size != b2->tuple_size) {
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)) {
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) {
pr_err("%s: %s/%s type %s != %s\n", __func__,
gd1->disk_name, gd2->disk_name,
b1->profile->name, b2->profile->name);
return -1;
}
return 0;
}
EXPORT_SYMBOL(blk_integrity_compare);
bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
struct request *next)
{
if (blk_integrity_rq(req) == 0 && blk_integrity_rq(next) == 0)
return true;
if (blk_integrity_rq(req) == 0 || blk_integrity_rq(next) == 0)
return false;
if (bio_integrity(req->bio)->bip_flags !=
bio_integrity(next->bio)->bip_flags)
return false;
if (req->nr_integrity_segments + next->nr_integrity_segments >
q->limits.max_integrity_segments)
return false;
if (integrity_req_gap_back_merge(req, next->bio))
return false;
return true;
}
EXPORT_SYMBOL(blk_integrity_merge_rq);
bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
struct bio *bio)
{
int nr_integrity_segs;
struct bio *next = bio->bi_next;
if (blk_integrity_rq(req) == 0 && bio_integrity(bio) == NULL)
return true;
if (blk_integrity_rq(req) == 0 || bio_integrity(bio) == NULL)
return false;
if (bio_integrity(req->bio)->bip_flags != bio_integrity(bio)->bip_flags)
return false;
bio->bi_next = NULL;
nr_integrity_segs = blk_rq_count_integrity_sg(q, bio);
bio->bi_next = next;
if (req->nr_integrity_segments + nr_integrity_segs >
q->limits.max_integrity_segments)
return false;
req->nr_integrity_segments += nr_integrity_segs;
return true;
}
EXPORT_SYMBOL(blk_integrity_merge_bio);
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 gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
struct blk_integrity *bi = &disk->queue->integrity;
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 gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj);
struct blk_integrity *bi = &disk->queue->integrity;
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->profile && bi->profile->name)
return sprintf(page, "%s\n", bi->profile->name);
else
return sprintf(page, "none\n");
}
static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page)
{
return sprintf(page, "%u\n", bi->tag_size);
}
static ssize_t integrity_interval_show(struct blk_integrity *bi, char *page)
{
return sprintf(page, "%u\n",
bi->interval_exp ? 1 << bi->interval_exp : 0);
}
static ssize_t integrity_verify_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)
bi->flags |= BLK_INTEGRITY_VERIFY;
else
bi->flags &= ~BLK_INTEGRITY_VERIFY;
return count;
}
static ssize_t integrity_verify_show(struct blk_integrity *bi, char *page)
{
return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_VERIFY) != 0);
}
static ssize_t integrity_generate_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)
bi->flags |= BLK_INTEGRITY_GENERATE;
else
bi->flags &= ~BLK_INTEGRITY_GENERATE;
return count;
}
static ssize_t integrity_generate_show(struct blk_integrity *bi, char *page)
{
return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_GENERATE) != 0);
}
static ssize_t integrity_device_show(struct blk_integrity *bi, char *page)
{
return sprintf(page, "%u\n",
(bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) != 0);
}
static struct integrity_sysfs_entry integrity_format_entry = {
.attr = { .name = "format", .mode = 0444 },
.show = integrity_format_show,
};
static struct integrity_sysfs_entry integrity_tag_size_entry = {
.attr = { .name = "tag_size", .mode = 0444 },
.show = integrity_tag_size_show,
};
static struct integrity_sysfs_entry integrity_interval_entry = {
.attr = { .name = "protection_interval_bytes", .mode = 0444 },
.show = integrity_interval_show,
};
static struct integrity_sysfs_entry integrity_verify_entry = {
.attr = { .name = "read_verify", .mode = 0644 },
.show = integrity_verify_show,
.store = integrity_verify_store,
};
static struct integrity_sysfs_entry integrity_generate_entry = {
.attr = { .name = "write_generate", .mode = 0644 },
.show = integrity_generate_show,
.store = integrity_generate_store,
};
static struct integrity_sysfs_entry integrity_device_entry = {
.attr = { .name = "device_is_integrity_capable", .mode = 0444 },
.show = integrity_device_show,
};
static struct attribute *integrity_attrs[] = {
&integrity_format_entry.attr,
&integrity_tag_size_entry.attr,
&integrity_interval_entry.attr,
&integrity_verify_entry.attr,
&integrity_generate_entry.attr,
&integrity_device_entry.attr,
NULL,
};
ATTRIBUTE_GROUPS(integrity);
static const struct sysfs_ops integrity_ops = {
.show = &integrity_attr_show,
.store = &integrity_attr_store,
};
static struct kobj_type integrity_ktype = {
.default_groups = integrity_groups,
.sysfs_ops = &integrity_ops,
};
static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter)
{
return BLK_STS_OK;
}
static const struct blk_integrity_profile nop_profile = {
.name = "nop",
.generate_fn = blk_integrity_nop_fn,
.verify_fn = blk_integrity_nop_fn,
};
/**
* blk_integrity_register - Register a gendisk as being integrity-capable
* @disk: struct gendisk pointer to make integrity-aware
* @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. See
* Documentation/block/data-integrity.rst.
*/
void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
{
struct blk_integrity *bi = &disk->queue->integrity;
bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
template->flags;
bi->interval_exp = template->interval_exp ? :
ilog2(queue_logical_block_size(disk->queue));
bi->profile = template->profile ? template->profile : &nop_profile;
bi->tuple_size = template->tuple_size;
bi->tag_size = template->tag_size;
block: get rid of blk_integrity_revalidate() Commit 25520d55cdb6 ("block: Inline blk_integrity in struct gendisk") introduced blk_integrity_revalidate(), which seems to assume ownership of the stable pages flag and unilaterally clears it if no blk_integrity profile is registered: if (bi->profile) disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; else disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; It's called from revalidate_disk() and rescan_partitions(), making it impossible to enable stable pages for drivers that support partitions and don't use blk_integrity: while the call in revalidate_disk() can be trivially worked around (see zram, which doesn't support partitions and hence gets away with zram_revalidate_disk()), rescan_partitions() can be triggered from userspace at any time. This breaks rbd, where the ceph messenger is responsible for generating/verifying CRCs. Since blk_integrity_{un,}register() "must" be used for (un)registering the integrity profile with the block layer, move BDI_CAP_STABLE_WRITES setting there. This way drivers that call blk_integrity_register() and use integrity infrastructure won't interfere with drivers that don't but still want stable pages. Fixes: 25520d55cdb6 ("block: Inline blk_integrity in struct gendisk") Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org # 4.4+, needs backporting Tested-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-18 18:43:20 +02:00
disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
}
EXPORT_SYMBOL(blk_integrity_register);
/**
* blk_integrity_unregister - Unregister block integrity profile
* @disk: disk whose integrity profile to unregister
*
* Description: This function unregisters the integrity capability from
* a block device.
*/
void blk_integrity_unregister(struct gendisk *disk)
{
block: get rid of blk_integrity_revalidate() Commit 25520d55cdb6 ("block: Inline blk_integrity in struct gendisk") introduced blk_integrity_revalidate(), which seems to assume ownership of the stable pages flag and unilaterally clears it if no blk_integrity profile is registered: if (bi->profile) disk->queue->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; else disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES; It's called from revalidate_disk() and rescan_partitions(), making it impossible to enable stable pages for drivers that support partitions and don't use blk_integrity: while the call in revalidate_disk() can be trivially worked around (see zram, which doesn't support partitions and hence gets away with zram_revalidate_disk()), rescan_partitions() can be triggered from userspace at any time. This breaks rbd, where the ceph messenger is responsible for generating/verifying CRCs. Since blk_integrity_{un,}register() "must" be used for (un)registering the integrity profile with the block layer, move BDI_CAP_STABLE_WRITES setting there. This way drivers that call blk_integrity_register() and use integrity infrastructure won't interfere with drivers that don't but still want stable pages. Fixes: 25520d55cdb6 ("block: Inline blk_integrity in struct gendisk") Cc: "Martin K. Petersen" <martin.petersen@oracle.com> Cc: Christoph Hellwig <hch@lst.de> Cc: Mike Snitzer <snitzer@redhat.com> Cc: stable@vger.kernel.org # 4.4+, needs backporting Tested-by: Dan Williams <dan.j.williams@intel.com> Signed-off-by: Ilya Dryomov <idryomov@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
2017-04-18 18:43:20 +02:00
disk->queue->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
}
EXPORT_SYMBOL(blk_integrity_unregister);
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);
}