Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760545AbYFGFAr (ORCPT ); Sat, 7 Jun 2008 01:00:47 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1757485AbYFGE6m (ORCPT ); Sat, 7 Jun 2008 00:58:42 -0400 Received: from jaguar.mkp.net ([192.139.46.146]:38420 "EHLO jaguar.mkp.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751893AbYFGE5p (ORCPT ); Sat, 7 Jun 2008 00:57:45 -0400 Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: [PATCH 5 of 7] block: Block/request layer data integrity support X-Mercurial-Node: 5be7c534c9542dc4bab1706758516c75510910df Message-Id: <5be7c534c9542dc4bab1.1212814538@sermon.lab.mkp.net> In-Reply-To: Date: Sat, 07 Jun 2008 00:55:38 -0400 From: "Martin K. Petersen" To: linux-kernel@vger.kernel.org, linux-scsi@vger.kernel.org Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 32923 Lines: 981 10 files changed, 849 insertions(+) Documentation/block/data-integrity.txt | 327 +++++++++++++++++++++++++++ block/Kconfig | 12 block/Makefile | 1 block/blk-core.c | 7 block/blk-integrity.c | 385 ++++++++++++++++++++++++++++++++ block/blk-merge.c | 3 block/blk.h | 8 block/elevator.c | 6 include/linux/blkdev.h | 97 ++++++++ include/linux/genhd.h | 3 Support for merging and mapping bio integrity metadata. Block device integrity type registration. Signed-off-by: Martin K. Petersen --- diff -r f2ae9d5bce4c -r 5be7c534c954 Documentation/block/data-integrity.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Documentation/block/data-integrity.txt Sat Jun 07 00:45:15 2008 -0400 @@ -0,0 +1,327 @@ +---------------------------------------------------------------------- +1. INTRODUCTION + +Modern filesystems feature checksumming of data and metadata to +protect against data corruption. However, the detection of the +corruption is done at read time which could potentially be months +after the data was written. At that point the original data that the +application tried to write is most likely lost. + +The solution is to ensure that the disk is actually storing what the +application meant it to. Recent additions to both the SCSI family +protocols (SBC Data Integrity Field, SCC protection proposal) as well +as SATA/T13 (External Path Protection) try to remedy this by adding +support for appending integrity metadata to an I/O. The integrity +metadata (or protection information in SCSI terminology) includes a +checksum for each sector as well as an incrementing counter that +ensures the individual sectors are written in the right order. And +for some protection schemes also that the I/O is written to the right +place on disk. + +Current storage controllers and devices implement various protective +measures, for instance checksumming and scrubbing. But these +technologies are working in their own isolated domains or at best +between adjacent nodes in the I/O path. The interesting thing about +DIF and the other integrity extensions is that the protection format +is well defined and every node in the I/O path can verify the +integrity of the I/O and reject it if corruption is detected. This +allows not only corruption prevention but also isolation of the point +of failure. + +---------------------------------------------------------------------- +2. THE DATA INTEGRITY EXTENSIONS + +As written, the protocol extensions only protect the path between +controller and storage device. However, many controllers actually +allow the operating system to interact with the integrity metadata +(IMD). We have been working with several FC/SAS HBA vendors to enable +the protection information to be transferred to and from their +controllers. + +The SCSI Data Integrity Field works by appending 8 bytes of protection +information to each sector. The data + integrity metadata is stored +in 520 byte sectors on disk. Data + IMD are interleaved when +transferred between the controller and target. The T13 proposal is +similar. + +Because it is highly inconvenient for operating systems to deal with +520 (and 4104) byte sectors, we approached several HBA vendors and +encouraged them to allow separation of the data and integrity metadata +scatter-gather lists. + +The controller will interleave the buffers on write and split them on +read. This means that the Linux can DMA the data buffers to and from +host memory without changes to the page cache. + +Also, the 16-bit CRC checksum mandated by both the SCSI and SATA specs +is somewhat heavy to compute in software. Benchmarks found that +calculating this checksum had a significant impact on system +performance for a number of workloads. Some controllers allow a +lighter-weight checksum to be used when interfacing with the operating +system. Emulex, for instance, supports the TCP/IP checksum instead. +The IP checksum received from the OS is converted to the 16-bit CRC +when writing and vice versa. This allows the integrity metadata to be +generated by Linux or the application at very low cost (comparable to +software RAID5). + +The IP checksum is weaker than the CRC in terms of detecting bit +errors. However, the strength is really in the separation of the data +buffers and the integrity metadata. These two distinct buffers much +match up for an I/O to complete. + +The separation of the data and integrity metadata buffers as well as +the choice in checksums is referred to as the Data Integrity +Extensions. As these extensions are outside the scope of the protocol +bodies (T10, T13), Oracle and its partners are trying to standardize +them within the Storage Networking Industry Association. + +---------------------------------------------------------------------- +3. KERNEL CHANGES + +The data integrity framework in Linux enables protection information +to be pinned to I/Os and sent to/received from controllers that +support it. + +The advantage to the integrity extensions in SCSI and SATA is that +they enable us to protect the entire path from application to storage +device. However, at the same time this is also the biggest +disadvantage. It means that the protection information must be in a +format that can be understood by the disk. + +Generally Linux/POSIX applications are agnostic to the intricacies of +the storage devices they are accessing. The virtual filesystem switch +and the block layer make things like hardware sector size and +transport protocols completely transparent to the application. + +However, this level of detail is required when preparing the +protection information to send to a disk. Consequently, the very +concept of an end-to-end protection scheme is a layering violation. +It is completely unreasonable for an application to be aware whether +it is accessing a SCSI or SATA disk. + +The data integrity support implemented in Linux attempts to hide this +from the application. As far as the application (and to some extent +the kernel) is concerned, the integrity metadata is opaque information +that's attached to the I/O. + +The current implementation allows the block layer to automatically +generate the protection information for any I/O. Eventually the +intent is to move the integrity metadata calculation to userspace for +user data. Metadata and other I/O that originates within the kernel +will still use the automatic generation interface. + +Some storage devices allow each hardware sector to be tagged with a +16-bit value. The owner of this tag space is the owner of the block +device. I.e. the filesystem in most cases. The filesystem can use +this extra space to tag sectors as they see fit. Because the tag +space is limited, the block interface allows tagging bigger chunks by +way of interleaving. This way, 8*16 bits of information can be +attached to a typical 4KB filesystem block. + +This also means that applications such as fsck and mkfs will need +access to manipulate the tags from user space. A passthrough +interface for this is being worked on. + + +---------------------------------------------------------------------- +4. BLOCK LAYER IMPLEMENTATION DETAILS + +4.1 BIO + +The data integrity patches add a new field to struct bio when +CONFIG_BLK_DEV_INTEGRITY is enabled. bio->bi_integrity is a pointer +to a struct bip which contains the bio integrity payload. Essentially +a bip is a trimmed down struct bio which holds a bio_vec containing +the integrity metadata and the required housekeeping information (bvec +pool, vector count, etc.) + +A kernel subsystem can enable data integrity protection on a bio by +calling bio_integrity_alloc(bio). This will allocate and attach the +bip to the bio. + +Individual pages containing integrity metadata can subsequently be +attached using bio_integrity_add_page(). + +bio_free() will automatically free the bip. + + +4.2 BLOCK DEVICE + +Because the format of the protection data is tied to the physical +disk, each block device has been extended with a block integrity +profile (struct blk_integrity). This optional profile is registered +with the block layer using blk_integrity_register(). + +The profile contains callback functions for generating and verifying +the protection data, as well as getting and setting application tags. +The profile also contains a few constants to aid in completing, +merging and splitting the integrity metadata. + +Layered block devices will need to pick a profile that's appropriate +for all subdevices. blk_integrity_compare() can help with that. DM +and MD linear, RAID0 and RAID1 are currently supported. RAID4/5/6 +will require extra work due to the application tag. + + +---------------------------------------------------------------------- +5.0 BLOCK LAYER INTEGRITY API + +5.1 NORMAL FILESYSTEM + + The normal filesystem is unaware that the underlying block device + is capable of sending/receiving integrity metadata. The IMD will + be automatically generated by the block layer at submit_bio() time + in case of a WRITE. A READ request will cause the I/O integrity + to be verified upon completion. + + IMD generation and verification can be toggled using the + + /sys/class/block//integrity/write_generate + + and + + /sys/class/block//integrity/read_verify + + flags. + + +5.2 INTEGRITY-AWARE FILESYSTEM + + A filesystem that is integrity-aware can prepare I/Os with IMD + attached. It can also use the application tag space if this is + supported by the block device. + + + int bdev_integrity_enabled(block_device, int rw); + + bdev_integrity_enabled() will return 1 if the block device + supports integrity metadata transfer for the data direction + specified in 'rw'. + + bdev_integrity_enabled() honors the write_generate and + read_verify flags in sysfs and will respond accordingly. + + + int bio_integrity_prep(bio); + + To generate IMD for WRITE and to set up buffers for READ, the + filesystem must call bio_integrity_prep(bio). + + Prior to calling this function, the bio data direction and start + sector must be set, and the bio should have all data pages + added. It is up to the caller to ensure that the bio does not + change while I/O is in progress. + + bio_integrity_prep() should only be called if + bio_integrity_enabled() returned 1. + + + int bio_integrity_tag_size(bio); + + If the filesystem wants to use the application tag space it will + first have to find out how much storage space is available. + Because tag space is generally limited (usually 2 bytes per + sector regardless of sector size), the integrity framework + supports interleaving the information between the sectors in an + I/O. + + Filesystems can call bio_integrity_tag_size(bio) to find out how + many bytes of storage are available for that particular bio. + + Another option is bdev_get_tag_size(block_device) which will + return the number of available bytes per hardware sector. + + + int bio_integrity_set_tag(bio, void *tag_buf, len); + + After a successful return from bio_integrity_prep(), + bio_integrity_set_tag() can be used to attach an opaque tag + buffer to a bio. Obviously this only makes sense if the I/O is + a WRITE. + + + int bio_integrity_get_tag(bio, void *tag_buf, len); + + Similarly, at READ I/O completion time the filesystem can + retrieve the tag buffer using bio_integrity_get_tag(). + + +6.3 PASSING EXISTING INTEGRITY METADATA + + Filesystems that either generate their own integrity metadata or + are capable of transferring IMD from user space can use the + following calls: + + + struct bip * bio_integrity_alloc(bio, gfp_mask, nr_pages); + + Allocates the bio integrity payload and hangs it off of the bio. + nr_pages indicate how many pages of protection data need to be + stored in the integrity bio_vec list (similar to bio_alloc()). + + The integrity payload will be freed at bio_free() time. + + + int bio_integrity_add_page(bio, page, len, offset); + + Attaches a page containing integrity metadata to an existing + bio. The bio must have an existing bip, + i.e. bio_integrity_alloc() must have been called. For a WRITE, + the integrity metadata in the pages must be in a format + understood by the target device with the notable exception that + the sector numbers will be remapped as the request traverses the + I/O stack. This implies that the pages added using this call + will be modified during I/O! The first reference tag in the + integrity metadata must have a value of bip->bip_sector. + + Pages can be added using bio_integrity_add_page() as long as + there is room in the bip bio_vec array (nr_pages). + + Upon completion of a READ operation, the attached pages will + contain the integrity metadata received from the storage device. + It is up to the receiver to process them and verify data + integrity upon completion. + + +6.4 REGISTERING A BLOCK DEVICE AS CAPABLE OF EXCHANGING INTEGRITY + METADATA + + To enable integrity exchange on a block device the gendisk must be + registered as capable: + + int blk_integrity_register(gendisk, blk_integrity); + + The blk_integrity struct is a template and should contain the + following: + + static struct blk_integrity my_profile = { + .name = "STANDARDSBODY-TYPE-VARIANT-CSUM", + .generate_fn = my_generate_fn, + .verify_fn = my_verify_fn, + .get_tag_fn = my_get_tag_fn, + .set_tag_fn = my_set_tag_fn, + .tuple_size = sizeof(struct my_tuple_size), + .tag_size = , + }; + + 'name' is a text string which will be visible in sysfs. This is + part of the userland API so chose it carefully and never change + it. The format is standards body-type-variant. + E.g. T10-DIF-TYPE1-IP or T13-EPP-0-CRC. + + 'generate_fn' generates appropriate integrity metadata (for WRITE). + + 'verify_fn' verifies that the data buffer matches the integrity + metadata. + + 'tuple_size' must be set to match the size of the integrity + metadata per sector. I.e. 8 for DIF and EPP. + + 'tag_size' must be set to identify how many bytes of tag space + are available per hardware sector. For DIF this is either 2 or + 0 depending on the value of the Control Mode Page ATO bit. + + See 6.2 for a description of get_tag_fn and set_tag_fn. + +---------------------------------------------------------------------- +2007-12-24 Martin K. Petersen diff -r f2ae9d5bce4c -r 5be7c534c954 block/Kconfig --- a/block/Kconfig Sat Jun 07 00:45:15 2008 -0400 +++ b/block/Kconfig Sat Jun 07 00:45:15 2008 -0400 @@ -81,6 +81,18 @@ 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. + endif # BLOCK config BLOCK_COMPAT diff -r f2ae9d5bce4c -r 5be7c534c954 block/Makefile --- a/block/Makefile Sat Jun 07 00:45:15 2008 -0400 +++ b/block/Makefile Sat Jun 07 00:45:15 2008 -0400 @@ -14,3 +14,4 @@ obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o obj-$(CONFIG_BLOCK_COMPAT) += compat_ioctl.o +obj-$(CONFIG_BLK_DEV_INTEGRITY) += blk-integrity.o diff -r f2ae9d5bce4c -r 5be7c534c954 block/blk-core.c --- a/block/blk-core.c Sat Jun 07 00:45:15 2008 -0400 +++ b/block/blk-core.c Sat Jun 07 00:45:15 2008 -0400 @@ -143,6 +143,10 @@ 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 @@ */ 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); diff -r f2ae9d5bce4c -r 5be7c534c954 block/blk-integrity.c --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/block/blk-integrity.c Sat Jun 07 00:45:15 2008 -0400 @@ -0,0 +1,385 @@ +/* + * blk-integrity.c - Block layer data integrity extensions + * + * Copyright (C) 2007, 2008 Oracle Corporation + * Written by: Martin K. Petersen + * + * 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 +#include +#include +#include + +#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)) + ; + else + 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); + ssize_t ret = -EIO; + + if (entry->show) + ret = entry->show(bi, page); + + return ret; +} + +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 == 1) + 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 == 1) + 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")) + 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); +} +EXPORT_SYMBOL(blk_integrity_unregister); diff -r f2ae9d5bce4c -r 5be7c534c954 block/blk-merge.c --- a/block/blk-merge.c Sat Jun 07 00:45:15 2008 -0400 +++ b/block/blk-merge.c Sat Jun 07 00:45:15 2008 -0400 @@ -441,6 +441,9 @@ || 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 diff -r f2ae9d5bce4c -r 5be7c534c954 block/blk.h --- a/block/blk.h Sat Jun 07 00:45:15 2008 -0400 +++ b/block/blk.h Sat Jun 07 00:45:15 2008 -0400 @@ -51,4 +51,12 @@ 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 diff -r f2ae9d5bce4c -r 5be7c534c954 block/elevator.c --- a/block/elevator.c Sat Jun 07 00:45:15 2008 -0400 +++ b/block/elevator.c Sat Jun 07 00:45:15 2008 -0400 @@ -84,6 +84,12 @@ * must be same device and not a special request */ 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)) diff -r f2ae9d5bce4c -r 5be7c534c954 include/linux/blkdev.h --- a/include/linux/blkdev.h Sat Jun 07 00:45:15 2008 -0400 +++ b/include/linux/blkdev.h Sat Jun 07 00:45:15 2008 -0400 @@ -113,6 +113,7 @@ __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_RW_META, /* metadata io request */ __REQ_COPY_USER, /* contains copies of user pages */ + __REQ_INTEGRITY, /* integrity metadata has been remapped */ __REQ_NR_BITS, /* stops here */ }; @@ -135,6 +136,7 @@ #define REQ_ALLOCED (1 << __REQ_ALLOCED) #define REQ_RW_META (1 << __REQ_RW_META) #define REQ_COPY_USER (1 << __REQ_COPY_USER) +#define REQ_INTEGRITY (1 << __REQ_INTEGRITY) #define BLK_MAX_CDB 16 @@ -866,6 +868,101 @@ MODULE_ALIAS("block-major-" __stringify(major) "-*") +#if defined(CONFIG_BLK_DEV_INTEGRITY) + +#define INTEGRITY_FLAG_READ 1 /* verify data integrity on read */ +#define INTEGRITY_FLAG_WRITE 2 /* generate data integrity on write */ + +struct blk_integrity_exchg { + void *prot_buf; + void *data_buf; + sector_t sector; + unsigned int data_size; + unsigned short sector_size; + const char *disk_name; +}; + +typedef void (integrity_gen_fn) (struct blk_integrity_exchg *); +typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *); +typedef void (integrity_set_tag_fn) (void *, void *, unsigned int); +typedef void (integrity_get_tag_fn) (void *, void *, unsigned int); + +struct blk_integrity { + integrity_gen_fn *generate_fn; + integrity_vrfy_fn *verify_fn; + integrity_set_tag_fn *set_tag_fn; + integrity_get_tag_fn *get_tag_fn; + + unsigned short flags; + unsigned short tuple_size; + unsigned short sector_size; + unsigned short tag_size; + + const char *name; + + struct kobject kobj; +}; + +extern int blk_integrity_register(struct gendisk *, struct blk_integrity *); +extern void blk_integrity_unregister(struct gendisk *); +extern int blk_integrity_compare(struct block_device *, struct block_device *); +extern int blk_rq_map_integrity_sg(struct request *, struct scatterlist *); +extern int blk_rq_count_integrity_sg(struct request *); + +static inline unsigned short blk_integrity_tuple_size(struct blk_integrity *bi) +{ + return (bi == NULL) ? 0 : bi->tuple_size; +} + +static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev) +{ + return bdev->bd_disk->integrity; +} + +static inline unsigned int bdev_get_tag_size(struct block_device *bdev) +{ + struct blk_integrity *bi = bdev_get_integrity(bdev); + + return (bi == NULL) ? 0 : bi->tag_size; +} + +static inline int bdev_integrity_enabled(struct block_device *bdev, int rw) +{ + struct blk_integrity *bi = bdev_get_integrity(bdev); + + if (bi == NULL) + return 0; + + if (rw == READ && bi->verify_fn != NULL && + test_bit(INTEGRITY_FLAG_READ, &bi->flags)) + return 1; + + if (rw == WRITE && bi->generate_fn != NULL && + test_bit(INTEGRITY_FLAG_WRITE, &bi->flags)) + return 1; + + return 0; +} + +static inline int blk_integrity_rq(struct request *rq) +{ + BUG_ON(rq->bio == NULL); + + return bio_integrity(rq->bio); +} + +#else /* CONFIG_BLK_DEV_INTEGRITY */ + +#define blk_integrity_rq(rq) (0) +#define bdev_get_integrity(a) (0) +#define bdev_get_tag_size(a) (0) +#define blk_integrity_compare(a, b) (0) +#define blk_integrity_register(a, b) (0) +#define blk_integrity_unregister(a) do { } while (0); + +#endif /* CONFIG_BLK_DEV_INTEGRITY */ + + #else /* CONFIG_BLOCK */ /* * stubs for when the block layer is configured out diff -r f2ae9d5bce4c -r 5be7c534c954 include/linux/genhd.h --- a/include/linux/genhd.h Sat Jun 07 00:45:15 2008 -0400 +++ b/include/linux/genhd.h Sat Jun 07 00:45:15 2008 -0400 @@ -141,6 +141,9 @@ struct disk_stats dkstats; #endif struct work_struct async_notify; +#ifdef CONFIG_BLK_DEV_INTEGRITY + struct blk_integrity *integrity; +#endif }; /* -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/