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
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230522221000.603769-1-sarthakkukreti@chromium.org>
Date:   Mon, 22 May 2023 15:09:55 -0700
From:   Sarthak Kukreti <sarthakkukreti@...omium.org>
To:     dm-devel@...hat.com, linux-block@...r.kernel.org,
        linux-ext4@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-fsdevel@...r.kernel.org
Cc:     Jens Axboe <axboe@...nel.dk>,
        "Michael S. Tsirkin" <mst@...hat.com>,
        Jason Wang <jasowang@...hat.com>,
        Stefan Hajnoczi <stefanha@...hat.com>,
        Alasdair Kergon <agk@...hat.com>,
        Mike Snitzer <snitzer@...nel.org>,
        Christoph Hellwig <hch@...radead.org>,
        Brian Foster <bfoster@...hat.com>,
        Theodore Ts'o <tytso@....edu>,
        Andreas Dilger <adilger.kernel@...ger.ca>,
        Bart Van Assche <bvanassche@...gle.com>,
        "Darrick J. Wong" <djwong@...nel.org>,
        Sarthak Kukreti <sarthakkukreti@...omium.org>
Subject: [PATCH v7 5/5] loop: Add support for provision requests

On Mon, May 22, 2023 at 9:37 AM Darrick J. Wong <djwong@...nel.org> wrote:
>
> If someone calls fallocate(UNSHARE_RANGE) on a loop bdev, shouldn't
> there be a way to pass that through to the fallocate call to the backing
> file?
>
> --D
>

Yeah, I think we could add a REQ_UNSHARE bit (similar to REQ_NOUNMAP) to pass down the intent to the backing file (and possibly beyond...).

I took a stab at implementing it as a follow up patch so that there's less review churn on the current series. If it looks good, I can add it to the end of the series (or incorporate this into the existing block and loop patches):

From: Sarthak Kukreti <sarthakkukreti@...omium.org>
Date: Mon, 22 May 2023 14:18:15 -0700
Subject: [PATCH] block: Pass unshare intent via REQ_OP_PROVISION

Allow REQ_OP_PROVISION to pass in an extra REQ_UNSHARE bit to
annotate unshare requests to underlying layers. Layers that support
FALLOC_FL_UNSHARE will be able to use this as an indicator of which
fallocate() mode to use.

Signed-off-by: Sarthak Kukreti <sarthakkukreti@...omium.org>
---
 block/blk-lib.c           |  6 +++++-
 block/fops.c              |  6 +++++-
 drivers/block/loop.c      | 35 +++++++++++++++++++++++++++++------
 include/linux/blk_types.h |  3 +++
 include/linux/blkdev.h    |  3 ++-
 5 files changed, 44 insertions(+), 9 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 3cff5fb654f5..bea6f5a700b3 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -350,6 +350,7 @@ EXPORT_SYMBOL(blkdev_issue_secure_erase);
  * @sector:	start sector
  * @nr_sects:	number of sectors to provision
  * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @flags:	controls detailed behavior
  *
  * Description:
  *  Issues a provision request to the block device for the range of sectors.
@@ -357,7 +358,7 @@ EXPORT_SYMBOL(blkdev_issue_secure_erase);
  *  underlying storage pool to allocate space for this block range.
  */
 int blkdev_issue_provision(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp)
+		sector_t nr_sects, gfp_t gfp, unsigned flags)
 {
 	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
 	unsigned int max_sectors = bdev_max_provision_sectors(bdev);
@@ -380,6 +381,9 @@ int blkdev_issue_provision(struct block_device *bdev, sector_t sector,
 		bio->bi_iter.bi_sector = sector;
 		bio->bi_iter.bi_size = req_sects << SECTOR_SHIFT;
 
+		if (flags & BLKDEV_UNSHARE_RANGE)
+			bio->bi_opf |= REQ_UNSHARE;
+
 		sector += req_sects;
 		nr_sects -= req_sects;
 		if (!nr_sects) {
diff --git a/block/fops.c b/block/fops.c
index be2e41f160bf..6848756f0557 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -659,7 +659,11 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	case FALLOC_FL_KEEP_SIZE:
 	case FALLOC_FL_UNSHARE_RANGE | FALLOC_FL_KEEP_SIZE:
 		error = blkdev_issue_provision(bdev, start >> SECTOR_SHIFT,
-					       len >> SECTOR_SHIFT, GFP_KERNEL);
+					       len >> SECTOR_SHIFT, GFP_KERNEL,
+					       (mode &
+						FALLOC_FL_UNSHARE_RANGE) ?
+						       BLKDEV_UNSHARE_RANGE :
+						       0);
 		break;
 	case FALLOC_FL_ZERO_RANGE:
 	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 7fe1a6629754..c844b145d666 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -306,6 +306,30 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq,
 	return 0;
 }
 
+static bool validate_fallocate_mode(struct loop_device *lo, int mode)
+{
+	bool ret = true;
+
+	switch (mode) {
+	case FALLOC_FL_PUNCH_HOLE:
+	case FALLOC_FL_ZERO_RANGE:
+		if (!bdev_max_discard_sectors(lo->lo_device))
+			ret = false;
+		break;
+	case 0:
+	case FALLOC_FL_UNSHARE_RANGE:
+		if (!bdev_max_provision_sectors(lo->lo_device))
+			ret = false;
+		break;
+
+	default:
+		ret = false;
+	}
+
+	return ret;
+}
+
+
 static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 			int mode)
 {
@@ -316,11 +340,7 @@ static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
 	struct file *file = lo->lo_backing_file;
 	int ret;
 
-	if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE) &&
-	    !bdev_max_discard_sectors(lo->lo_device))
-		return -EOPNOTSUPP;
-
-	if (mode == 0 && !bdev_max_provision_sectors(lo->lo_device))
+	if (!validate_fallocate_mode(lo, mode))
 		return -EOPNOTSUPP;
 
 	mode |= FALLOC_FL_KEEP_SIZE;
@@ -493,7 +513,10 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	case REQ_OP_DISCARD:
 		return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
 	case REQ_OP_PROVISION:
-		return lo_fallocate(lo, rq, pos, 0);
+		return lo_fallocate(lo, rq, pos,
+				    (rq->cmd_flags & REQ_UNSHARE) ?
+					    FALLOC_FL_UNSHARE_RANGE :
+					    0);
 	case REQ_OP_WRITE:
 		if (cmd->use_aio)
 			return lo_rw_aio(lo, cmd, pos, ITER_SOURCE);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index b7bb0226fdee..1a536fd897cb 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -423,6 +423,8 @@ enum req_flag_bits {
 	 */
 	/* for REQ_OP_WRITE_ZEROES: */
 	__REQ_NOUNMAP,		/* do not free blocks when zeroing */
+	/* for REQ_OP_PROVISION: */
+	__REQ_UNSHARE,		/* unshare blocks */
 
 	__REQ_NR_BITS,		/* stops here */
 };
@@ -451,6 +453,7 @@ enum req_flag_bits {
 #define REQ_FS_PRIVATE	(__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE)
 
 #define REQ_NOUNMAP	(__force blk_opf_t)(1ULL << __REQ_NOUNMAP)
+#define REQ_UNSHARE	(__force blk_opf_t)(1ULL << __REQ_UNSHARE)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 462ce586d46f..60c09b0d3fc9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1049,10 +1049,11 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp);
 
 extern int blkdev_issue_provision(struct block_device *bdev, sector_t sector,
-		sector_t nr_sects, gfp_t gfp_mask);
+		sector_t nr_sects, gfp_t gfp_mask, unsigned int flags);
 
 #define BLKDEV_ZERO_NOUNMAP	(1 << 0)  /* do not free blocks */
 #define BLKDEV_ZERO_NOFALLBACK	(1 << 1)  /* don't write explicit zeroes */
+#define BLKDEV_UNSHARE_RANGE	(1 << 2)  /* unshare range on provision */
 
 extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
-- 
2.39.2

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ