| 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
| ||
|
Date: Thu, 16 Jan 2020 15:36:03 +0300
From: Kirill Tkhai <ktkhai@...tuozzo.com>
To: linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
martin.petersen@...cle.com, axboe@...nel.dk, tytso@....edu,
adilger.kernel@...ger.ca, Chaitanya.Kulkarni@....com,
darrick.wong@...cle.com, ming.lei@...hat.com, osandov@...com,
jthumshirn@...e.de, minwoo.im.dev@...il.com, damien.lemoal@....com,
andrea.parri@...rulasolutions.com, hare@...e.com, tj@...nel.org,
ajay.joshi@....com, sagi@...mberg.me, dsterba@...e.com,
chaitanya.kulkarni@....com, bvanassche@....org,
dhowells@...hat.com, asml.silence@...il.com, ktkhai@...tuozzo.com
Subject: [PATCH block v2 2/3] block: Add support for REQ_NOZERO flag
This adds support for REQ_NOZERO extension of REQ_OP_WRITE_ZEROES
operation, which encourages a block device driver to just allocate
blocks (or mark them allocated) instead of actual blocks zeroing.
REQ_NOZERO is aimed to be used for network filesystems providing
a block device interface. Also, block devices, which map a file
on other filesystem (like loop), may use this for less fragmentation
and batching fallocate() requests. Hypervisors like QEMU may
introduce optimizations of clusters allocations based on this.
BLKDEV_ZERO_ALLOCATE is a new corresponding flag for
blkdev_issue_zeroout().
CC: Martin K. Petersen <martin.petersen@...cle.com>
Signed-off-by: Kirill Tkhai <ktkhai@...tuozzo.com>
---
block/blk-core.c | 6 +++---
block/blk-lib.c | 17 ++++++++++-------
block/blk-merge.c | 9 ++++++---
block/blk-settings.c | 17 +++++++++++++++++
fs/block_dev.c | 4 ++++
include/linux/blk_types.h | 5 ++++-
include/linux/blkdev.h | 31 ++++++++++++++++++++++++-------
7 files changed, 68 insertions(+), 21 deletions(-)
diff --git a/block/blk-core.c b/block/blk-core.c
index 50a5de025d5e..2edcd55624f1 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -978,7 +978,7 @@ generic_make_request_checks(struct bio *bio)
goto not_supported;
break;
case REQ_OP_WRITE_ZEROES:
- if (!q->limits.max_write_zeroes_sectors)
+ if (!blk_queue_get_max_write_zeroes_sectors(q, bio->bi_opf))
goto not_supported;
break;
default:
@@ -1250,10 +1250,10 @@ EXPORT_SYMBOL(submit_bio);
static int blk_cloned_rq_check_limits(struct request_queue *q,
struct request *rq)
{
- if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, req_op(rq))) {
+ if (blk_rq_sectors(rq) > blk_queue_get_max_sectors(q, rq->cmd_flags)) {
printk(KERN_ERR "%s: over max size limit. (%u > %u)\n",
__func__, blk_rq_sectors(rq),
- blk_queue_get_max_sectors(q, req_op(rq)));
+ blk_queue_get_max_sectors(q, rq->cmd_flags));
return -EIO;
}
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 3e38c93cfc53..3e80279eb029 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -214,7 +214,7 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
struct bio **biop, unsigned flags)
{
struct bio *bio = *biop;
- unsigned int max_write_zeroes_sectors;
+ unsigned int max_write_zeroes_sectors, req_flags = 0;
struct request_queue *q = bdev_get_queue(bdev);
if (!q)
@@ -224,18 +224,21 @@ static int __blkdev_issue_write_zeroes(struct block_device *bdev,
return -EPERM;
/* Ensure that max_write_zeroes_sectors doesn't overflow bi_size */
- max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev, 0);
+ max_write_zeroes_sectors = bdev_write_zeroes_sectors(bdev, flags);
if (max_write_zeroes_sectors == 0)
return -EOPNOTSUPP;
+ if (flags & BLKDEV_ZERO_NOUNMAP)
+ req_flags |= REQ_NOUNMAP;
+ if (flags & BLKDEV_ZERO_ALLOCATE)
+ req_flags |= REQ_NOZERO|REQ_NOUNMAP;
+
while (nr_sects) {
bio = blk_next_bio(bio, 0, gfp_mask);
bio->bi_iter.bi_sector = sector;
bio_set_dev(bio, bdev);
- bio->bi_opf = REQ_OP_WRITE_ZEROES;
- if (flags & BLKDEV_ZERO_NOUNMAP)
- bio->bi_opf |= REQ_NOUNMAP;
+ bio->bi_opf = REQ_OP_WRITE_ZEROES | req_flags;
if (nr_sects > max_write_zeroes_sectors) {
bio->bi_iter.bi_size = max_write_zeroes_sectors << 9;
@@ -362,7 +365,7 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t bs_mask;
struct bio *bio;
struct blk_plug plug;
- bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev, 0);
+ bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev, flags);
bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
if ((sector | nr_sects) & bs_mask)
@@ -391,7 +394,7 @@ int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
try_write_zeroes = false;
goto retry;
}
- if (!bdev_write_zeroes_sectors(bdev, 0)) {
+ if (!bdev_write_zeroes_sectors(bdev, flags)) {
/*
* Zeroing offload support was indicated, but the
* device reported ILLEGAL REQUEST (for some devices
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 347782a24a35..e3ce4b87bbaa 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -105,15 +105,18 @@ static struct bio *blk_bio_discard_split(struct request_queue *q,
static struct bio *blk_bio_write_zeroes_split(struct request_queue *q,
struct bio *bio, struct bio_set *bs, unsigned *nsegs)
{
+ unsigned int max_sectors;
+
+ max_sectors = blk_queue_get_max_write_zeroes_sectors(q, bio->bi_opf);
*nsegs = 0;
- if (!q->limits.max_write_zeroes_sectors)
+ if (!max_sectors)
return NULL;
- if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors)
+ if (bio_sectors(bio) <= max_sectors)
return NULL;
- return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs);
+ return bio_split(bio, max_sectors, GFP_NOIO, bs);
}
static struct bio *blk_bio_write_same_split(struct request_queue *q,
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 5f6dcc7a47bd..f682374c5106 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -48,6 +48,7 @@ void blk_set_default_limits(struct queue_limits *lim)
lim->chunk_sectors = 0;
lim->max_write_same_sectors = 0;
lim->max_write_zeroes_sectors = 0;
+ lim->max_allocate_sectors = 0;
lim->max_discard_sectors = 0;
lim->max_hw_discard_sectors = 0;
lim->discard_granularity = 0;
@@ -83,6 +84,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
lim->max_dev_sectors = UINT_MAX;
lim->max_write_same_sectors = UINT_MAX;
lim->max_write_zeroes_sectors = UINT_MAX;
+ lim->max_allocate_sectors = UINT_MAX;
}
EXPORT_SYMBOL(blk_set_stacking_limits);
@@ -257,6 +259,19 @@ void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
}
EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
+/**
+ * blk_queue_max_allocate_sectors - set max sectors for a single
+ * allocate request
+ * @q: the request queue for the device
+ * @max_allocate_sectors: maximum number of sectors to write per command
+ **/
+void blk_queue_max_allocate_sectors(struct request_queue *q,
+ unsigned int max_allocate_sectors)
+{
+ q->limits.max_allocate_sectors = max_allocate_sectors;
+}
+EXPORT_SYMBOL(blk_queue_max_allocate_sectors);
+
/**
* blk_queue_max_segments - set max hw segments for a request for this queue
* @q: the request queue for the device
@@ -506,6 +521,8 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
b->max_write_same_sectors);
t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
b->max_write_zeroes_sectors);
+ t->max_allocate_sectors = min(t->max_allocate_sectors,
+ b->max_allocate_sectors);
t->bounce_pfn = min_not_zero(t->bounce_pfn, b->bounce_pfn);
t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 69bf2fb6f7cd..1ffef894b3bd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -2122,6 +2122,10 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
break;
+ case FALLOC_FL_KEEP_SIZE:
+ error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+ GFP_KERNEL, BLKDEV_ZERO_ALLOCATE | BLKDEV_ZERO_NOFALLBACK);
+ break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
GFP_KERNEL, 0);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 70254ae11769..9ed166860099 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -335,7 +335,9 @@ enum req_flag_bits {
/* command specific flags for REQ_OP_WRITE_ZEROES: */
__REQ_NOUNMAP, /* do not free blocks when zeroing */
-
+ __REQ_NOZERO, /* only notify about allocated blocks,
+ * and do not actual zero them
+ */
__REQ_HIPRI,
/* for driver use */
@@ -362,6 +364,7 @@ enum req_flag_bits {
#define REQ_CGROUP_PUNT (1ULL << __REQ_CGROUP_PUNT)
#define REQ_NOUNMAP (1ULL << __REQ_NOUNMAP)
+#define REQ_NOZERO (1ULL << __REQ_NOZERO)
#define REQ_HIPRI (1ULL << __REQ_HIPRI)
#define REQ_DRV (1ULL << __REQ_DRV)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4cd69552df9a..f4ec5db64432 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -336,6 +336,7 @@ struct queue_limits {
unsigned int max_hw_discard_sectors;
unsigned int max_write_same_sectors;
unsigned int max_write_zeroes_sectors;
+ unsigned int max_allocate_sectors;
unsigned int discard_granularity;
unsigned int discard_alignment;
@@ -988,9 +989,19 @@ static inline struct bio_vec req_bvec(struct request *rq)
return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter);
}
+static inline unsigned int blk_queue_get_max_write_zeroes_sectors(
+ struct request_queue *q, unsigned int op_flags)
+{
+ if (op_flags & REQ_NOZERO)
+ return q->limits.max_allocate_sectors;
+ return q->limits.max_write_zeroes_sectors;
+}
+
static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
- int op)
+ unsigned int op_flags)
{
+ int op = op_flags & REQ_OP_MASK;
+
if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
return min(q->limits.max_discard_sectors,
UINT_MAX >> SECTOR_SHIFT);
@@ -999,7 +1010,7 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
return q->limits.max_write_same_sectors;
if (unlikely(op == REQ_OP_WRITE_ZEROES))
- return q->limits.max_write_zeroes_sectors;
+ return blk_queue_get_max_write_zeroes_sectors(q, op_flags);
return q->limits.max_sectors;
}
@@ -1029,10 +1040,10 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
if (!q->limits.chunk_sectors ||
req_op(rq) == REQ_OP_DISCARD ||
req_op(rq) == REQ_OP_SECURE_ERASE)
- return blk_queue_get_max_sectors(q, req_op(rq));
+ return blk_queue_get_max_sectors(q, rq->cmd_flags);
return min(blk_max_size_offset(q, offset),
- blk_queue_get_max_sectors(q, req_op(rq)));
+ blk_queue_get_max_sectors(q, rq->cmd_flags));
}
static inline unsigned int blk_rq_count_bios(struct request *rq)
@@ -1078,6 +1089,8 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q,
unsigned int max_write_same_sectors);
extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
unsigned int max_write_same_sectors);
+extern void blk_queue_max_allocate_sectors(struct request_queue *q,
+ unsigned int max_allocate_sectors);
extern void blk_queue_logical_block_size(struct request_queue *, unsigned short);
extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
extern void blk_queue_alignment_offset(struct request_queue *q,
@@ -1219,6 +1232,7 @@ extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
#define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */
#define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */
+#define BLKDEV_ZERO_ALLOCATE (1 << 2) /* allocate range of blocks */
extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
@@ -1423,10 +1437,13 @@ static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev,
{
struct request_queue *q = bdev_get_queue(bdev);
- if (q)
- return q->limits.max_write_zeroes_sectors;
+ if (!q)
+ return 0;
- return 0;
+ if (flags & BLKDEV_ZERO_ALLOCATE)
+ return q->limits.max_allocate_sectors;
+ else
+ return q->limits.max_write_zeroes_sectors;
}
static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
Powered by blists - more mailing lists