| 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: <20200212183129.GO6874@magnolia>
Date: Wed, 12 Feb 2020 10:31:29 -0800
From: "Darrick J. Wong" <darrick.wong@...cle.com>
To: Kirill Tkhai <ktkhai@...tuozzo.com>
Cc: martin.petersen@...cle.com, bob.liu@...cle.com, axboe@...nel.dk,
agk@...hat.com, snitzer@...hat.com, dm-devel@...hat.com,
song@...nel.org, tytso@....edu, adilger.kernel@...ger.ca,
Chaitanya.Kulkarni@....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,
bvanassche@....org, dhowells@...hat.com, asml.silence@...il.com,
linux-block@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v6 4/6] block: Add support for REQ_ALLOCATE flag
On Wed, Feb 12, 2020 at 08:33:52PM +0300, Kirill Tkhai wrote:
> Hi, Darrick,
>
> On 12.02.2020 19:58, Darrick J. Wong wrote:
> > On Mon, Feb 10, 2020 at 12:33:53PM +0300, Kirill Tkhai wrote:
> >> This adds support for REQ_ALLOCATE 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_ALLOCATE 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().
> >>
> >> Stacking devices start from zero max_allocate_sectors limit for now,
> >> and the support is going to be implemented separate for each device
> >> in the future.
> >>
> >> Signed-off-by: Kirill Tkhai <ktkhai@...tuozzo.com>
> >> Reviewed-by: Bob Liu <bob.liu@...cle.com>
> >> ---
> >> block/blk-lib.c | 17 ++++++++++-------
> >> block/blk-settings.c | 4 ++++
> >> fs/block_dev.c | 4 ++++
> >> include/linux/blk_types.h | 5 ++++-
> >> include/linux/blkdev.h | 13 ++++++++++---
> >> 5 files changed, 32 insertions(+), 11 deletions(-)
> >>
> >> diff --git a/block/blk-lib.c b/block/blk-lib.c
> >> index 3e38c93cfc53..9cd6f86523ba 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_ALLOCATE|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-settings.c b/block/blk-settings.c
> >> index c8eda2e7b91e..8d5df9d37239 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 = 0;
> >> }
> >> EXPORT_SYMBOL(blk_set_stacking_limits);
> >>
> >> @@ -506,6 +508,8 @@ 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);
> >
> > I think this should be ^^^ indented to match the other calls.
>
> The only idea I have about this is something like the below. But the below is over 90 char...
>
> error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
> GFP_KERNEL,
> BLKDEV_ZERO_ALLOCATE | BLKDEV_ZERO_NOFALLBACK);
>
> Could you please clarify what you mean?
I mostly meant that the indent for the nth lines ought to be more than a
single indent to make it easier to scan through the code, but you're
right, the kernel indentation style is uglier. I could suggest
something like this, which actually does fit:
case FALLOC_FL_KEEP_SIZE:
error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
GFP_KERNEL,
BLKDEV_ZERO_ALLOCATE | BLKDEV_ZERO_NOFALLBACK);
break;
But that's apparently apocryphal. :/
--D
> >> 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..86accd2caa4e 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_ALLOCATE, /* only notify about allocated blocks,
> >> + * and do not actually zero them
> >
> > "only notify"? Is someone getting a notification? Or are we simply
> > "notifying" the device that it must ensure allocated blocks?
> >
> > If it's that last one, then perhaps this should be reworded:
> >
> > /*
> > * Ensure the LBA range is backed by physical storage
> > * without writing zeroes to the blocks.
> > */
>
> Sounds good.
>
> >> + */
> >> __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_ALLOCATE (1ULL << __REQ_ALLOCATE)
> >> #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 55a714161684..40707f980a2e 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;
> >>
> >> @@ -990,6 +991,8 @@ static inline struct bio_vec req_bvec(struct request *rq)
> >> static inline unsigned int blk_queue_get_max_write_zeroes_sectors(
> >> struct request_queue *q, unsigned int op_flags)
> >> {
> >> + if (op_flags & REQ_ALLOCATE)
> >> + return q->limits.max_allocate_sectors;
> >> return q->limits.max_write_zeroes_sectors;
> >> }
> >>
> >> @@ -1226,6 +1229,7 @@ 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,
> >> @@ -1430,10 +1434,13 @@ 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)
> >>
> >>
>
> Thanks,
> Kirill
Powered by blists - more mailing lists