Fork of alistair23 Linux kernel for reMarkable from https://github.com/alistair23/linux
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

472 lines
12 KiB

// SPDX-License-Identifier: GPL-2.0
/*
* bio-integrity.c - bio data integrity extensions
*
* Copyright (C) 2007, 2008, 2009 Oracle Corporation
* Written by: Martin K. Petersen <martin.petersen@oracle.com>
*/
#include <linux/blkdev.h>
#include <linux/mempool.h>
#include <linux/export.h>
#include <linux/bio.h>
#include <linux/workqueue.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 -&gt; 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&#39;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&#39;t seem to be any matching order. * If the script can&#39;t find a place to put a new include (mostly because the file doesn&#39;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&#39;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&#39;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&#39;m fairly confident about the coverage of this conversion patch. If there is a breakage, it&#39;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 &lt;tj@kernel.org&gt; Guess-its-ok-by: Christoph Lameter &lt;cl@linux-foundation.org&gt; Cc: Ingo Molnar &lt;mingo@redhat.com&gt; Cc: Lee Schermerhorn &lt;Lee.Schermerhorn@hp.com&gt;
12 years ago
#include <linux/slab.h>
#include "blk.h"
#define BIP_INLINE_VECS 4
static struct kmem_cache *bip_slab;
static struct workqueue_struct *kintegrityd_wq;
void blk_flush_integrity(void)
{
flush_workqueue(kintegrityd_wq);
}
void __bio_integrity_free(struct bio_set *bs, struct bio_integrity_payload *bip)
{
if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
if (bip->bip_vec)
bvec_free(&bs->bvec_integrity_pool, bip->bip_vec,
bip->bip_slab);
mempool_free(bip, &bs->bio_integrity_pool);
} else {
kfree(bip);
}
}
/**
* bio_integrity_alloc - Allocate integrity payload and attach it to bio
* @bio: bio to attach integrity metadata to
* @gfp_mask: Memory allocation mask
* @nr_vecs: Number of integrity metadata scatter-gather elements
*
* Description: This function prepares a bio for attaching integrity
* metadata. nr_vecs specifies the maximum number of pages containing
* integrity metadata that can be attached.
*/
struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
gfp_t gfp_mask,
unsigned int nr_vecs)
{
struct bio_integrity_payload *bip;
struct bio_set *bs = bio->bi_pool;
unsigned inline_vecs;
if (!bs || !mempool_initialized(&bs->bio_integrity_pool)) {
bip = kmalloc(struct_size(bip, bip_inline_vecs, nr_vecs), gfp_mask);
inline_vecs = nr_vecs;
} else {
bip = mempool_alloc(&bs->bio_integrity_pool, gfp_mask);
inline_vecs = BIP_INLINE_VECS;
}
if (unlikely(!bip))
return ERR_PTR(-ENOMEM);
memset(bip, 0, sizeof(*bip));
if (nr_vecs > inline_vecs) {
unsigned long idx = 0;
bip->bip_vec = bvec_alloc(gfp_mask, nr_vecs, &idx,
&bs->bvec_integrity_pool);
if (!bip->bip_vec)
goto err;
bip->bip_max_vcnt = bvec_nr_vecs(idx);
bip->bip_slab = idx;
} else {
bip->bip_vec = bip->bip_inline_vecs;
bip->bip_max_vcnt = inline_vecs;
}
bip->bip_bio = bio;
bio->bi_integrity = bip;
bio->bi_opf |= REQ_INTEGRITY;
return bip;
err:
__bio_integrity_free(bs, bip);
return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(bio_integrity_alloc);
/**
* bio_integrity_free - Free bio integrity payload
* @bio: bio containing bip to be freed
*
* Description: Used to free the integrity portion of a bio. Usually
* called from bio_free().
*/
void bio_integrity_free(struct bio *bio)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
struct bio_set *bs = bio->bi_pool;
if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
kfree(page_address(bip->bip_vec->bv_page) +
bip->bip_vec->bv_offset);
__bio_integrity_free(bs, bip);
bio->bi_integrity = NULL;
bio->bi_opf &= ~REQ_INTEGRITY;
}
/**
* bio_integrity_add_page - Attach integrity metadata
* @bio: bio to update
* @page: page containing integrity metadata
* @len: number of bytes of integrity metadata in page
* @offset: start offset within page
*
* Description: Attach a page containing integrity metadata to bio.
*/
int bio_integrity_add_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
struct bio_vec *iv;
if (bip->bip_vcnt >= bip->bip_max_vcnt) {
printk(KERN_ERR "%s: bip_vec full\n", __func__);
return 0;
}
iv = bip->bip_vec + bip->bip_vcnt;
if (bip->bip_vcnt &&
bvec_gap_to_prev(bio->bi_disk->queue,
&bip->bip_vec[bip->bip_vcnt - 1], offset))
return 0;
iv->bv_page = page;
iv->bv_len = len;
iv->bv_offset = offset;
bip->bip_vcnt++;
return len;
}
EXPORT_SYMBOL(bio_integrity_add_page);
/**
* bio_integrity_process - Process integrity metadata for a bio
* @bio: bio to generate/verify integrity metadata for
* @proc_iter: iterator to process
* @proc_fn: Pointer to the relevant processing function
*/
static blk_status_t bio_integrity_process(struct bio *bio,
struct bvec_iter *proc_iter, integrity_processing_fn *proc_fn)
{
struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
struct blk_integrity_iter iter;
struct bvec_iter bviter;
struct bio_vec bv;
struct bio_integrity_payload *bip = bio_integrity(bio);
blk_status_t ret = BLK_STS_OK;
void *prot_buf = page_address(bip->bip_vec->bv_page) +
bip->bip_vec->bv_offset;
iter.disk_name = bio->bi_disk->disk_name;
iter.interval = 1 << bi->interval_exp;
iter.seed = proc_iter->bi_sector;
iter.prot_buf = prot_buf;
__bio_for_each_segment(bv, bio, bviter, *proc_iter) {
void *kaddr = kmap_atomic(bv.bv_page);
iter.data_buf = kaddr + bv.bv_offset;
iter.data_size = bv.bv_len;
ret = proc_fn(&iter);
if (ret) {
kunmap_atomic(kaddr);
return ret;
}
kunmap_atomic(kaddr);
}
return ret;
}
/**
* bio_integrity_prep - Prepare bio for integrity I/O
* @bio: bio to prepare
*
* Description: Checks if the bio already has an integrity payload attached.
* If it does, the payload has been generated by another kernel subsystem,
* and we just pass it through. Otherwise allocates integrity payload.
* The bio must have data direction, target device and start sector set priot
* to calling. In the WRITE case, integrity metadata will be generated using
* the block device's integrity function. In the READ case, the buffer
* will be prepared for DMA and a suitable end_io handler set up.
*/
bool bio_integrity_prep(struct bio *bio)
{
struct bio_integrity_payload *bip;
struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
struct request_queue *q = bio->bi_disk->queue;
void *buf;
unsigned long start, end;
unsigned int len, nr_pages;
unsigned int bytes, offset, i;
unsigned int intervals;
blk_status_t status;
if (!bi)
return true;
if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
return true;
if (!bio_sectors(bio))
return true;
/* Already protected? */
if (bio_integrity(bio))
return true;
if (bio_data_dir(bio) == READ) {
if (!bi->profile->verify_fn ||
!(bi->flags & BLK_INTEGRITY_VERIFY))
return true;
} else {
if (!bi->profile->generate_fn ||
!(bi->flags & BLK_INTEGRITY_GENERATE))
return true;
}
intervals = bio_integrity_intervals(bi, bio_sectors(bio));
/* Allocate kernel buffer for protection data */
len = intervals * bi->tuple_size;
buf = kmalloc(len, GFP_NOIO | q->bounce_gfp);
status = BLK_STS_RESOURCE;
if (unlikely(buf == NULL)) {
printk(KERN_ERR "could not allocate integrity buffer\n");
goto err_end_io;
}
end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
start = ((unsigned long) buf) >> PAGE_SHIFT;
nr_pages = end - start;
/* Allocate bio integrity payload and integrity vectors */
bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages);
if (IS_ERR(bip)) {
printk(KERN_ERR "could not allocate data integrity bioset\n");
kfree(buf);
status = BLK_STS_RESOURCE;
goto err_end_io;
}
bip->bip_flags |= BIP_BLOCK_INTEGRITY;
bip->bip_iter.bi_size = len;
bip_set_seed(bip, bio->bi_iter.bi_sector);
if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM)
bip->bip_flags |= BIP_IP_CHECKSUM;
/* Map it */
offset = offset_in_page(buf);
for (i = 0 ; i < nr_pages ; i++) {
int ret;
bytes = PAGE_SIZE - offset;
if (len <= 0)
break;
if (bytes > len)
bytes = len;
ret = bio_integrity_add_page(bio, virt_to_page(buf),
bytes, offset);
if (ret == 0) {
printk(KERN_ERR "could not attach integrity payload\n");
status = BLK_STS_RESOURCE;
goto err_end_io;
}
if (ret < bytes)
break;
buf += bytes;
len -= bytes;
offset = 0;
}
/* Auto-generate integrity metadata if this is a write */
if (bio_data_dir(bio) == WRITE) {
bio_integrity_process(bio, &bio->bi_iter,
bi->profile->generate_fn);
} else {
bip->bio_iter = bio->bi_iter;
}
return true;
err_end_io:
bio->bi_status = status;
bio_endio(bio);
return false;
}
EXPORT_SYMBOL(bio_integrity_prep);
/**
* bio_integrity_verify_fn - Integrity I/O completion worker
* @work: Work struct stored in bio to be verified
*
* Description: This workqueue function is called to complete a READ
* request. The function verifies the transferred integrity metadata
* and then calls the original bio end_io function.
*/
static void bio_integrity_verify_fn(struct work_struct *work)
{
struct bio_integrity_payload *bip =
container_of(work, struct bio_integrity_payload, bip_work);
struct bio *bio = bip->bip_bio;
struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
/*
* At the moment verify is called bio's iterator was advanced
* during split and completion, we need to rewind iterator to
* it's original position.
*/
bio->bi_status = bio_integrity_process(bio, &bip->bio_iter,
bi->profile->verify_fn);
bio_integrity_free(bio);
bio_endio(bio);
}
/**
* __bio_integrity_endio - Integrity I/O completion function
* @bio: Protected bio
*
* Description: Completion for integrity I/O
*
* Normally I/O completion is done in interrupt context. However,
* verifying I/O integrity is a time-consuming task which must be run
* in process context. This function postpones completion
* accordingly.
*/
bool __bio_integrity_endio(struct bio *bio)
{
bio-integrity: Fix regression if profile verify_fn is NULL In dm-integrity target we register integrity profile that have both generate_fn and verify_fn callbacks set to NULL. This is used if dm-integrity is stacked under a dm-crypt device for authenticated encryption (integrity payload contains authentication tag and IV seed). In this case the verification is done through own crypto API processing inside dm-crypt; integrity profile is only holder of these data. (And memory is owned by dm-crypt as well.) After the commit (and previous changes) Commit 7c20f11680a441df09de7235206f70115fbf6290 Author: Christoph Hellwig &lt;hch@lst.de&gt; Date: Mon Jul 3 16:58:43 2017 -0600 bio-integrity: stop abusing bi_end_io we get this crash: : BUG: unable to handle kernel NULL pointer dereference at (null) : IP: (null) : *pde = 00000000 ... : : Workqueue: kintegrityd bio_integrity_verify_fn : task: f48ae180 task.stack: f4b5c000 : EIP: (null) : EFLAGS: 00210286 CPU: 0 : EAX: f4b5debc EBX: 00001000 ECX: 00000001 EDX: 00000000 : ESI: 00001000 EDI: ed25f000 EBP: f4b5dee8 ESP: f4b5dea4 : DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 : CR0: 80050033 CR2: 00000000 CR3: 32823000 CR4: 001406d0 : Call Trace: : ? bio_integrity_process+0xe3/0x1e0 : bio_integrity_verify_fn+0xea/0x150 : process_one_work+0x1c7/0x5c0 : worker_thread+0x39/0x380 : kthread+0xd6/0x110 : ? process_one_work+0x5c0/0x5c0 : ? kthread_worker_fn+0x100/0x100 : ? kthread_worker_fn+0x100/0x100 : ret_from_fork+0x19/0x24 : Code: Bad EIP value. : EIP: (null) SS:ESP: 0068:f4b5dea4 : CR2: 0000000000000000 Patch just skip the whole verify workqueue if verify_fn is set to NULL. Fixes: 7c20f116 (&#34;bio-integrity: stop abusing bi_end_io&#34;) Signed-off-by: Milan Broz &lt;gmazyland@gmail.com&gt; [hch: trivial whitespace fix] Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt; Signed-off-by: Jens Axboe &lt;axboe@kernel.dk&gt;
5 years ago
struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
struct bio_integrity_payload *bip = bio_integrity(bio);
bio-integrity: Fix regression if profile verify_fn is NULL In dm-integrity target we register integrity profile that have both generate_fn and verify_fn callbacks set to NULL. This is used if dm-integrity is stacked under a dm-crypt device for authenticated encryption (integrity payload contains authentication tag and IV seed). In this case the verification is done through own crypto API processing inside dm-crypt; integrity profile is only holder of these data. (And memory is owned by dm-crypt as well.) After the commit (and previous changes) Commit 7c20f11680a441df09de7235206f70115fbf6290 Author: Christoph Hellwig &lt;hch@lst.de&gt; Date: Mon Jul 3 16:58:43 2017 -0600 bio-integrity: stop abusing bi_end_io we get this crash: : BUG: unable to handle kernel NULL pointer dereference at (null) : IP: (null) : *pde = 00000000 ... : : Workqueue: kintegrityd bio_integrity_verify_fn : task: f48ae180 task.stack: f4b5c000 : EIP: (null) : EFLAGS: 00210286 CPU: 0 : EAX: f4b5debc EBX: 00001000 ECX: 00000001 EDX: 00000000 : ESI: 00001000 EDI: ed25f000 EBP: f4b5dee8 ESP: f4b5dea4 : DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 : CR0: 80050033 CR2: 00000000 CR3: 32823000 CR4: 001406d0 : Call Trace: : ? bio_integrity_process+0xe3/0x1e0 : bio_integrity_verify_fn+0xea/0x150 : process_one_work+0x1c7/0x5c0 : worker_thread+0x39/0x380 : kthread+0xd6/0x110 : ? process_one_work+0x5c0/0x5c0 : ? kthread_worker_fn+0x100/0x100 : ? kthread_worker_fn+0x100/0x100 : ret_from_fork+0x19/0x24 : Code: Bad EIP value. : EIP: (null) SS:ESP: 0068:f4b5dea4 : CR2: 0000000000000000 Patch just skip the whole verify workqueue if verify_fn is set to NULL. Fixes: 7c20f116 (&#34;bio-integrity: stop abusing bi_end_io&#34;) Signed-off-by: Milan Broz &lt;gmazyland@gmail.com&gt; [hch: trivial whitespace fix] Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt; Signed-off-by: Jens Axboe &lt;axboe@kernel.dk&gt;
5 years ago
if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
(bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->profile->verify_fn) {
INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
queue_work(kintegrityd_wq, &bip->bip_work);
return false;
}
bio_integrity_free(bio);
return true;
}
/**
* bio_integrity_advance - Advance integrity vector
* @bio: bio whose integrity vector to update
* @bytes_done: number of data bytes that have been completed
*
* Description: This function calculates how many integrity bytes the
* number of completed data bytes correspond to and advances the
* integrity vector accordingly.
*/
void bio_integrity_advance(struct bio *bio, unsigned int bytes_done)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
unsigned bytes = bio_integrity_bytes(bi, bytes_done >> 9);
bip->bip_iter.bi_sector += bytes_done >> 9;
bvec_iter_advance(bip->bip_vec, &bip->bip_iter, bytes);
}
/**
* bio_integrity_trim - Trim integrity vector
* @bio: bio whose integrity vector to update
*
* Description: Used to trim the integrity vector in a cloned bio.
*/
void bio_integrity_trim(struct bio *bio)
{
struct bio_integrity_payload *bip = bio_integrity(bio);
struct blk_integrity *bi = blk_get_integrity(bio->bi_disk);
bip->bip_iter.bi_size = bio_integrity_bytes(bi, bio_sectors(bio));
}
EXPORT_SYMBOL(bio_integrity_trim);
/**
* bio_integrity_clone - Callback for cloning bios with integrity metadata
* @bio: New bio
* @bio_src: Original bio
* @gfp_mask: Memory allocation mask
*
* Description: Called to allocate a bip when cloning a bio
*/
int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
gfp_t gfp_mask)
{
struct bio_integrity_payload *bip_src = bio_integrity(bio_src);
struct bio_integrity_payload *bip;
BUG_ON(bip_src == NULL);
bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
if (IS_ERR(bip))
return PTR_ERR(bip);
memcpy(bip->bip_vec, bip_src->bip_vec,
bip_src->bip_vcnt * sizeof(struct bio_vec));
bip->bip_vcnt = bip_src->bip_vcnt;
bip->bip_iter = bip_src->bip_iter;
return 0;
}
EXPORT_SYMBOL(bio_integrity_clone);
int bioset_integrity_create(struct bio_set *bs, int pool_size)
{
if (mempool_initialized(&bs->bio_integrity_pool))
return 0;
if (mempool_init_slab_pool(&bs->bio_integrity_pool,
pool_size, bip_slab))
return -1;
if (biovec_init_pool(&bs->bvec_integrity_pool, pool_size)) {
mempool_exit(&bs->bio_integrity_pool);
return -1;
}
return 0;
}
EXPORT_SYMBOL(bioset_integrity_create);
void bioset_integrity_free(struct bio_set *bs)
{
mempool_exit(&bs->bio_integrity_pool);
mempool_exit(&bs->bvec_integrity_pool);
}
void __init bio_integrity_init(void)
{
/*
* kintegrityd won't block much but may burn a lot of CPU cycles.
* Make it highpri CPU intensive wq with max concurrency of 1.
*/
kintegrityd_wq = alloc_workqueue("kintegrityd", WQ_MEM_RECLAIM |
WQ_HIGHPRI | WQ_CPU_INTENSIVE, 1);
if (!kintegrityd_wq)
panic("Failed to create kintegrityd\n");
bip_slab = kmem_cache_create("bio_integrity_payload",
sizeof(struct bio_integrity_payload) +
sizeof(struct bio_vec) * BIP_INLINE_VECS,
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
}