| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1385513128-5035-19-git-send-email-kmo@daterainc.com>
Date: Tue, 26 Nov 2013 16:45:22 -0800
From: Kent Overstreet <kmo@...erainc.com>
To: linux-kernel@...r.kernel.org, linux-fsdevel@...r.kernel.org,
hch@...radead.org
Cc: Kent Overstreet <kmo@...erainc.com>, Jens Axboe <axboe@...nel.dk>,
Alasdair Kergon <agk@...hat.com>, dm-devel@...hat.com
Subject: [PATCH 19/25] dm: Refactor for new bio cloning/splitting
We need to convert the dm code to the new bvec_iter primitives which
respect bi_bvec_done; they also allow us to drastically simplify dm's
bio splitting code.
Also, it's no longer necessary to save/restore the bvec array anymore -
driver conversions for immutable bvecs are done, so drivers should never
be modifying it.
Also kill bio_sector_offset(), dm was the only user and it doesn't make
much sense anymore.
Signed-off-by: Kent Overstreet <kmo@...erainc.com>
Cc: Jens Axboe <axboe@...nel.dk>
Cc: Alasdair Kergon <agk@...hat.com>
Cc: dm-devel@...hat.com
Reviewed-by: Mike Snitzer <snitzer@...hat.com>
---
drivers/md/dm-bio-record.h | 25 -------
drivers/md/dm.c | 174 ++++++---------------------------------------
fs/bio.c | 72 -------------------
include/linux/bio.h | 2 -
4 files changed, 20 insertions(+), 253 deletions(-)
diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h
index 4f46e8e..dd36461 100644
--- a/drivers/md/dm-bio-record.h
+++ b/drivers/md/dm-bio-record.h
@@ -17,49 +17,24 @@
* original bio state.
*/
-struct dm_bio_vec_details {
-#if PAGE_SIZE < 65536
- __u16 bv_len;
- __u16 bv_offset;
-#else
- unsigned bv_len;
- unsigned bv_offset;
-#endif
-};
-
struct dm_bio_details {
struct block_device *bi_bdev;
unsigned long bi_flags;
struct bvec_iter bi_iter;
- struct dm_bio_vec_details bi_io_vec[BIO_MAX_PAGES];
};
static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
{
- unsigned i;
-
bd->bi_bdev = bio->bi_bdev;
bd->bi_flags = bio->bi_flags;
bd->bi_iter = bio->bi_iter;
-
- for (i = 0; i < bio->bi_vcnt; i++) {
- bd->bi_io_vec[i].bv_len = bio->bi_io_vec[i].bv_len;
- bd->bi_io_vec[i].bv_offset = bio->bi_io_vec[i].bv_offset;
- }
}
static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
{
- unsigned i;
-
bio->bi_bdev = bd->bi_bdev;
bio->bi_flags = bd->bi_flags;
bio->bi_iter = bd->bi_iter;
-
- for (i = 0; i < bio->bi_vcnt; i++) {
- bio->bi_io_vec[i].bv_len = bd->bi_io_vec[i].bv_len;
- bio->bi_io_vec[i].bv_offset = bd->bi_io_vec[i].bv_offset;
- }
}
#endif
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ccd064e..44a2fa6 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1155,7 +1155,6 @@ struct clone_info {
struct dm_io *io;
sector_t sector;
sector_t sector_count;
- unsigned short idx;
};
static void bio_setup_sector(struct bio *bio, sector_t sector, sector_t len)
@@ -1164,68 +1163,24 @@ static void bio_setup_sector(struct bio *bio, sector_t sector, sector_t len)
bio->bi_iter.bi_size = to_bytes(len);
}
-static void bio_setup_bv(struct bio *bio, unsigned short idx, unsigned short bv_count)
-{
- bio->bi_iter.bi_idx = idx;
- bio->bi_vcnt = idx + bv_count;
- bio->bi_flags &= ~(1 << BIO_SEG_VALID);
-}
-
-static void clone_bio_integrity(struct bio *bio, struct bio *clone,
- unsigned short idx, unsigned len, unsigned offset,
- unsigned trim)
-{
- if (!bio_integrity(bio))
- return;
-
- bio_integrity_clone(clone, bio, GFP_NOIO);
-
- if (trim)
- bio_integrity_trim(clone, bio_sector_offset(bio, idx, offset), len);
-}
-
-/*
- * Creates a little bio that just does part of a bvec.
- */
-static void clone_split_bio(struct dm_target_io *tio, struct bio *bio,
- sector_t sector, unsigned short idx,
- unsigned offset, unsigned len)
-{
- struct bio *clone = &tio->clone;
- struct bio_vec *bv = bio->bi_io_vec + idx;
-
- *clone->bi_io_vec = *bv;
-
- bio_setup_sector(clone, sector, len);
-
- clone->bi_bdev = bio->bi_bdev;
- clone->bi_rw = bio->bi_rw;
- clone->bi_vcnt = 1;
- clone->bi_io_vec->bv_offset = offset;
- clone->bi_io_vec->bv_len = clone->bi_iter.bi_size;
- clone->bi_flags |= 1 << BIO_CLONED;
-
- clone_bio_integrity(bio, clone, idx, len, offset, 1);
-}
-
/*
* Creates a bio that consists of range of complete bvecs.
*/
static void clone_bio(struct dm_target_io *tio, struct bio *bio,
- sector_t sector, unsigned short idx,
- unsigned short bv_count, unsigned len)
+ sector_t sector, unsigned len)
{
struct bio *clone = &tio->clone;
- unsigned trim = 0;
- __bio_clone(clone, bio);
- bio_setup_sector(clone, sector, len);
- bio_setup_bv(clone, idx, bv_count);
+ __bio_clone_fast(clone, bio);
+
+ if (bio_integrity(bio))
+ bio_integrity_clone(clone, bio, GFP_NOIO);
+
+ bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector));
+ clone->bi_iter.bi_size = to_bytes(len);
- if (idx != bio->bi_iter.bi_idx ||
- clone->bi_iter.bi_size < bio->bi_iter.bi_size)
- trim = 1;
- clone_bio_integrity(bio, clone, idx, len, 0, trim);
+ if (bio_integrity(bio))
+ bio_integrity_trim(clone, 0, len);
}
static struct dm_target_io *alloc_tio(struct clone_info *ci,
@@ -1258,7 +1213,7 @@ static void __clone_and_map_simple_bio(struct clone_info *ci,
* ci->bio->bi_max_vecs is BIO_INLINE_VECS anyway, for both flush
* and discard, so no need for concern about wasted bvec allocations.
*/
- __bio_clone(clone, ci->bio);
+ __bio_clone_fast(clone, ci->bio);
if (len)
bio_setup_sector(clone, ci->sector, len);
@@ -1287,10 +1242,7 @@ static int __send_empty_flush(struct clone_info *ci)
}
static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti,
- sector_t sector, int nr_iovecs,
- unsigned short idx, unsigned short bv_count,
- unsigned offset, unsigned len,
- unsigned split_bvec)
+ sector_t sector, unsigned len)
{
struct bio *bio = ci->bio;
struct dm_target_io *tio;
@@ -1304,11 +1256,8 @@ static void __clone_and_map_data_bio(struct clone_info *ci, struct dm_target *ti
num_target_bios = ti->num_write_bios(ti, bio);
for (target_bio_nr = 0; target_bio_nr < num_target_bios; target_bio_nr++) {
- tio = alloc_tio(ci, ti, nr_iovecs, target_bio_nr);
- if (split_bvec)
- clone_split_bio(tio, bio, sector, idx, offset, len);
- else
- clone_bio(tio, bio, sector, idx, bv_count, len);
+ tio = alloc_tio(ci, ti, 0, target_bio_nr);
+ clone_bio(tio, bio, sector, len);
__map_bio(tio);
}
}
@@ -1380,68 +1329,13 @@ static int __send_write_same(struct clone_info *ci)
}
/*
- * Find maximum number of sectors / bvecs we can process with a single bio.
- */
-static sector_t __len_within_target(struct clone_info *ci, sector_t max, int *idx)
-{
- struct bio *bio = ci->bio;
- sector_t bv_len, total_len = 0;
-
- for (*idx = ci->idx; max && (*idx < bio->bi_vcnt); (*idx)++) {
- bv_len = to_sector(bio->bi_io_vec[*idx].bv_len);
-
- if (bv_len > max)
- break;
-
- max -= bv_len;
- total_len += bv_len;
- }
-
- return total_len;
-}
-
-static int __split_bvec_across_targets(struct clone_info *ci,
- struct dm_target *ti, sector_t max)
-{
- struct bio *bio = ci->bio;
- struct bio_vec *bv = bio->bi_io_vec + ci->idx;
- sector_t remaining = to_sector(bv->bv_len);
- unsigned offset = 0;
- sector_t len;
-
- do {
- if (offset) {
- ti = dm_table_find_target(ci->map, ci->sector);
- if (!dm_target_is_valid(ti))
- return -EIO;
-
- max = max_io_len(ci->sector, ti);
- }
-
- len = min(remaining, max);
-
- __clone_and_map_data_bio(ci, ti, ci->sector, 1, ci->idx, 0,
- bv->bv_offset + offset, len, 1);
-
- ci->sector += len;
- ci->sector_count -= len;
- offset += to_bytes(len);
- } while (remaining -= len);
-
- ci->idx++;
-
- return 0;
-}
-
-/*
* Select the correct strategy for processing a non-flush bio.
*/
static int __split_and_process_non_flush(struct clone_info *ci)
{
struct bio *bio = ci->bio;
struct dm_target *ti;
- sector_t len, max;
- int idx;
+ unsigned len;
if (unlikely(bio->bi_rw & REQ_DISCARD))
return __send_discard(ci);
@@ -1452,41 +1346,14 @@ static int __split_and_process_non_flush(struct clone_info *ci)
if (!dm_target_is_valid(ti))
return -EIO;
- max = max_io_len(ci->sector, ti);
-
- /*
- * Optimise for the simple case where we can do all of
- * the remaining io with a single clone.
- */
- if (ci->sector_count <= max) {
- __clone_and_map_data_bio(ci, ti, ci->sector, bio->bi_max_vecs,
- ci->idx, bio->bi_vcnt - ci->idx, 0,
- ci->sector_count, 0);
- ci->sector_count = 0;
- return 0;
- }
-
- /*
- * There are some bvecs that don't span targets.
- * Do as many of these as possible.
- */
- if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) {
- len = __len_within_target(ci, max, &idx);
-
- __clone_and_map_data_bio(ci, ti, ci->sector, bio->bi_max_vecs,
- ci->idx, idx - ci->idx, 0, len, 0);
+ len = min_t(sector_t, max_io_len(ci->sector, ti), ci->sector_count);
- ci->sector += len;
- ci->sector_count -= len;
- ci->idx = idx;
+ __clone_and_map_data_bio(ci, ti, ci->sector, len);
- return 0;
- }
+ ci->sector += len;
+ ci->sector_count -= len;
- /*
- * Handle a bvec that must be split between two or more targets.
- */
- return __split_bvec_across_targets(ci, ti, max);
+ return 0;
}
/*
@@ -1512,7 +1379,6 @@ static void __split_and_process_bio(struct mapped_device *md,
ci.io->md = md;
spin_lock_init(&ci.io->endio_lock);
ci.sector = bio->bi_iter.bi_sector;
- ci.idx = bio->bi_iter.bi_idx;
start_io_acct(ci.io);
diff --git a/fs/bio.c b/fs/bio.c
index 00dc189..6e42b68 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -515,40 +515,6 @@ inline int bio_phys_segments(struct request_queue *q, struct bio *bio)
EXPORT_SYMBOL(bio_phys_segments);
/**
- * __bio_clone - clone a bio
- * @bio: destination bio
- * @bio_src: bio to clone
- *
- * Clone a &bio. Caller will own the returned bio, but not
- * the actual data it points to. Reference count of returned
- * bio will be one.
- */
-void __bio_clone(struct bio *bio, struct bio *bio_src)
-{
- if (bio_is_rw(bio_src)) {
- struct bio_vec bv;
- struct bvec_iter iter;
-
- bio_for_each_segment(bv, bio_src, iter)
- bio->bi_io_vec[bio->bi_vcnt++] = bv;
- } else if (bio_has_data(bio_src)) {
- memcpy(bio->bi_io_vec, bio_src->bi_io_vec,
- bio_src->bi_max_vecs * sizeof(struct bio_vec));
- bio->bi_vcnt = bio_src->bi_vcnt;
- }
-
- /*
- * most users will be overriding ->bi_bdev with a new target,
- * so we don't set nor calculate new physical/hw segment counts here
- */
- bio->bi_bdev = bio_src->bi_bdev;
- bio->bi_flags |= 1 << BIO_CLONED;
- bio->bi_rw = bio_src->bi_rw;
- bio->bi_iter = bio_src->bi_iter;
-}
-EXPORT_SYMBOL(__bio_clone);
-
-/**
* __bio_clone_fast - clone a bio that shares the original bio's biovec
* @bio: destination bio
* @bio_src: bio to clone
@@ -1921,44 +1887,6 @@ void bio_trim(struct bio *bio, int offset, int size)
}
EXPORT_SYMBOL_GPL(bio_trim);
-/**
- * bio_sector_offset - Find hardware sector offset in bio
- * @bio: bio to inspect
- * @index: bio_vec index
- * @offset: offset in bv_page
- *
- * Return the number of hardware sectors between beginning of bio
- * and an end point indicated by a bio_vec index and an offset
- * within that vector's page.
- */
-sector_t bio_sector_offset(struct bio *bio, unsigned short index,
- unsigned int offset)
-{
- unsigned int sector_sz;
- struct bio_vec *bv;
- sector_t sectors;
- int i;
-
- sector_sz = queue_logical_block_size(bio->bi_bdev->bd_disk->queue);
- sectors = 0;
-
- if (index >= bio->bi_iter.bi_idx)
- index = bio->bi_vcnt - 1;
-
- bio_for_each_segment_all(bv, bio, i) {
- if (i == index) {
- if (offset > bv->bv_offset)
- sectors += (offset - bv->bv_offset) / sector_sz;
- break;
- }
-
- sectors += bv->bv_len / sector_sz;
- }
-
- return sectors;
-}
-EXPORT_SYMBOL(bio_sector_offset);
-
/*
* create memory pools for biovec's in a bio_set.
* use the global biovec slabs created for general use.
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 1f83f4a..0c32a45 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -330,7 +330,6 @@ extern void bio_put(struct bio *);
extern void __bio_clone_fast(struct bio *, struct bio *);
extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
-extern void __bio_clone(struct bio *, struct bio *);
extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
extern struct bio_set *fs_bio_set;
@@ -370,7 +369,6 @@ extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int);
extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
unsigned int, unsigned int);
extern int bio_get_nr_vecs(struct block_device *);
-extern sector_t bio_sector_offset(struct bio *, unsigned short, unsigned int);
extern struct bio *bio_map_user(struct request_queue *, struct block_device *,
unsigned long, unsigned int, int, gfp_t);
struct sg_iovec;
--
1.8.4.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists