linux-sg2042/block/blk-integrity.c

388 lines
10 KiB
C
Raw Normal View History

/*
* 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 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 16:04:11 +08:00
#include <linux/slab.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 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->integrity;
struct blk_integrity *b2 = gd2->integrity;
if (!b1 && !b2)
return 0;
if (!b1 || !b2)
return -1;
if (b1->sector_size != b2->sector_size) {
printk(KERN_ERR "%s: %s/%s sector sz %u != %u\n", __func__,
gd1->disk_name, gd2->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__,
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__,
gd1->disk_name, gd2->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__,
gd1->disk_name, gd2->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)
bi->flags |= INTEGRITY_FLAG_READ;
else
bi->flags &= ~INTEGRITY_FLAG_READ;
return count;
}
static ssize_t integrity_read_show(struct blk_integrity *bi, char *page)
{
return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_READ) != 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)
bi->flags |= INTEGRITY_FLAG_WRITE;
else
bi->flags &= ~INTEGRITY_FLAG_WRITE;
return count;
}
static ssize_t integrity_write_show(struct blk_integrity *bi, char *page)
{
return sprintf(page, "%d\n", (bi->flags & INTEGRITY_FLAG_WRITE) != 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 const 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: optional 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.
*/
int blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
{
struct blk_integrity *bi;
BUG_ON(disk == 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_to_dev(disk)->kobj,
"%s", "integrity")) {
kmem_cache_free(integrity_cachep, bi);
return -1;
}
kobject_uevent(&bi->kobj, KOBJ_ADD);
bi->flags |= INTEGRITY_FLAG_READ | INTEGRITY_FLAG_WRITE;
bi->sector_size = queue_logical_block_size(disk->queue);
disk->integrity = bi;
} else
bi = disk->integrity;
/* Use the provided profile as template */
if (template != NULL) {
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;
} else
bi->name = "unsupported";
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(&bi->kobj);
kmem_cache_free(integrity_cachep, bi);
disk->integrity = NULL;
}
EXPORT_SYMBOL(blk_integrity_unregister);