linux-kernel - [PATCH 2/2] loop: Better discard support for block devices

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: <20181030230624.61834-3-evgreen@chromium.org>
Date:   Tue, 30 Oct 2018 16:06:24 -0700
From:   Evan Green <evgreen@...omium.org>
To:     Jens Axboe <axboe@...nel.dk>
Cc:     Gwendal Grignou <gwendal@...omium.org>,
        Alexis Savery <asavery@...omium.org>,
        Evan Green <evgreen@...omium.org>, linux-block@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: [PATCH 2/2] loop: Better discard support for block devices

If the backing device for a loop device is a block device,
then mirror the discard properties of the underlying block
device into the loop device. While in there, differentiate
between REQ_OP_DISCARD and REQ_OP_WRITE_ZEROES, which are
different for block devices, but which the loop device had
just been lumping together.

Signed-off-by: Evan Green <evgreen@...omium.org>
---

 drivers/block/loop.c | 61 +++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 41 insertions(+), 20 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 28990fc94841a..176e65101c4ef 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -417,19 +417,14 @@ static int lo_read_transfer(struct loop_device *lo, struct request *rq,
 	return ret;
 }
 
-static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
+static int lo_discard(struct loop_device *lo, struct request *rq,
+		int mode, loff_t pos)
 {
-	/*
-	 * We use punch hole to reclaim the free space used by the
-	 * image a.k.a. discard. However we do not support discard if
-	 * encryption is enabled, because it may give an attacker
-	 * useful information.
-	 */
 	struct file *file = lo->lo_backing_file;
-	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
+	struct request_queue *q = lo->lo_queue;
 	int ret;
 
-	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
+	if (!blk_queue_discard(q)) {
 		ret = -EOPNOTSUPP;
 		goto out;
 	}
@@ -603,8 +598,13 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
 	case REQ_OP_FLUSH:
 		return lo_req_flush(lo, rq);
 	case REQ_OP_DISCARD:
+		return lo_discard(lo, rq,
+			FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, pos);
+
 	case REQ_OP_WRITE_ZEROES:
-		return lo_discard(lo, rq, pos);
+		return lo_discard(lo, rq,
+			FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE, pos);
+
 	case REQ_OP_WRITE:
 		if (lo->transfer)
 			return lo_write_transfer(lo, rq, pos);
@@ -859,6 +859,25 @@ static void loop_config_discard(struct loop_device *lo)
 	struct file *file = lo->lo_backing_file;
 	struct inode *inode = file->f_mapping->host;
 	struct request_queue *q = lo->lo_queue;
+	struct request_queue *backingq;
+
+	/*
+	 * If the backing device is a block device, mirror its discard
+	 * capabilities.
+	 */
+	if (S_ISBLK(inode->i_mode)) {
+		backingq = bdev_get_queue(inode->i_bdev);
+		blk_queue_max_discard_sectors(q,
+			backingq->limits.max_discard_sectors);
+
+		blk_queue_max_write_zeroes_sectors(q,
+			backingq->limits.max_write_zeroes_sectors);
+
+		q->limits.discard_granularity =
+			backingq->limits.discard_granularity;
+
+		q->limits.discard_alignment =
+			backingq->limits.discard_alignment;
 
 	/*
 	 * We use punch hole to reclaim the free space used by the
@@ -866,22 +885,24 @@ static void loop_config_discard(struct loop_device *lo)
 	 * encryption is enabled, because it may give an attacker
 	 * useful information.
 	 */
-	if ((!file->f_op->fallocate) ||
-	    lo->lo_encrypt_key_size) {
+	} else if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
 		q->limits.discard_granularity = 0;
 		q->limits.discard_alignment = 0;
 		blk_queue_max_discard_sectors(q, 0);
 		blk_queue_max_write_zeroes_sectors(q, 0);
-		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
-		return;
-	}
 
-	q->limits.discard_granularity = inode->i_sb->s_blocksize;
-	q->limits.discard_alignment = 0;
+	} else {
+		q->limits.discard_granularity = inode->i_sb->s_blocksize;
+		q->limits.discard_alignment = 0;
+
+		blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
+		blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
+	}
 
-	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
-	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+	if (q->limits.max_discard_sectors || q->limits.max_write_zeroes_sectors)
+		blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
 }
 
 static void loop_unprepare_queue(struct loop_device *lo)
-- 
2.16.4