| 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: <1615563895-28565-3-git-send-email-sergei.shtepa@veeam.com>
Date: Fri, 12 Mar 2021 18:44:54 +0300
From: Sergei Shtepa <sergei.shtepa@...am.com>
To: Christoph Hellwig <hch@...radead.org>,
Mike Snitzer <snitzer@...hat.com>,
Alasdair Kergon <agk@...hat.com>,
Hannes Reinecke <hare@...e.de>, Jens Axboe <axboe@...nel.dk>,
<dm-devel@...hat.com>, <linux-block@...r.kernel.org>,
<linux-kernel@...r.kernel.org>, <linux-api@...r.kernel.org>
CC: <sergei.shtepa@...am.com>, <pavel.tide@...am.com>
Subject: [PATCH v7 2/3] block: add bdev_interposer
bdev_interposer allows to redirect bio requests to another devices.
Signed-off-by: Sergei Shtepa <sergei.shtepa@...am.com>
---
block/bio.c | 2 ++
block/blk-core.c | 57 +++++++++++++++++++++++++++++++++++++++
block/genhd.c | 54 +++++++++++++++++++++++++++++++++++++
include/linux/blk_types.h | 3 +++
include/linux/blkdev.h | 9 +++++++
5 files changed, 125 insertions(+)
diff --git a/block/bio.c b/block/bio.c
index a1c4d2900c7a..0bfbf06475ee 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -640,6 +640,8 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src)
bio_set_flag(bio, BIO_THROTTLED);
if (bio_flagged(bio_src, BIO_REMAPPED))
bio_set_flag(bio, BIO_REMAPPED);
+ if (bio_flagged(bio_src, BIO_INTERPOSED))
+ bio_set_flag(bio, BIO_INTERPOSED);
bio->bi_opf = bio_src->bi_opf;
bio->bi_ioprio = bio_src->bi_ioprio;
bio->bi_write_hint = bio_src->bi_write_hint;
diff --git a/block/blk-core.c b/block/blk-core.c
index fc60ff208497..da1abc4c27a9 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1018,6 +1018,55 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
return ret;
}
+static noinline blk_qc_t submit_bio_interposed(struct bio *bio)
+{
+ blk_qc_t ret = BLK_QC_T_NONE;
+ struct bio_list bio_list[2] = { };
+ struct gendisk *orig_disk;
+
+ if (current->bio_list) {
+ bio_list_add(¤t->bio_list[0], bio);
+ return BLK_QC_T_NONE;
+ }
+
+ orig_disk = bio->bi_bdev->bd_disk;
+ if (unlikely(bio_queue_enter(bio)))
+ return BLK_QC_T_NONE;
+
+ current->bio_list = bio_list;
+
+ do {
+ struct block_device *interposer = bio->bi_bdev->bd_interposer;
+
+ if (unlikely(!interposer)) {
+ /* interposer was removed */
+ bio_list_add(¤t->bio_list[0], bio);
+ break;
+ }
+ /* assign bio to interposer device */
+ bio_set_dev(bio, interposer);
+ bio_set_flag(bio, BIO_INTERPOSED);
+
+ if (!submit_bio_checks(bio))
+ break;
+ /*
+ * Because the current->bio_list is initialized,
+ * the submit_bio callback will always return BLK_QC_T_NONE.
+ */
+ interposer->bd_disk->fops->submit_bio(bio);
+ } while (false);
+
+ current->bio_list = NULL;
+
+ blk_queue_exit(orig_disk->queue);
+
+ /* Resubmit remaining bios */
+ while ((bio = bio_list_pop(&bio_list[0])))
+ ret = submit_bio_noacct(bio);
+
+ return ret;
+}
+
/**
* submit_bio_noacct - re-submit a bio to the block device layer for I/O
* @bio: The bio describing the location in memory and on the device.
@@ -1029,6 +1078,14 @@ static blk_qc_t __submit_bio_noacct_mq(struct bio *bio)
*/
blk_qc_t submit_bio_noacct(struct bio *bio)
{
+ /*
+ * Checking the BIO_INTERPOSED flag is necessary so that the bio
+ * created by the bdev_interposer do not get to it for processing.
+ */
+ if (bdev_has_interposer(bio->bi_bdev) &&
+ !bio_flagged(bio, BIO_INTERPOSED))
+ return submit_bio_interposed(bio);
+
if (!submit_bio_checks(bio))
return BLK_QC_T_NONE;
diff --git a/block/genhd.c b/block/genhd.c
index c55e8f0fced1..c840ecffea68 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -30,6 +30,11 @@
static struct kobject *block_depr;
DECLARE_RWSEM(bdev_lookup_sem);
+/*
+ * Prevents different block-layer interposers from attaching or detaching
+ * to the block device at the same time.
+ */
+static DEFINE_MUTEX(bdev_interposer_attach_lock);
/* for extended dynamic devt allocation, currently only one major is used */
#define NR_EXT_DEVT (1 << MINORBITS)
@@ -1940,3 +1945,52 @@ static void disk_release_events(struct gendisk *disk)
WARN_ON_ONCE(disk->ev && disk->ev->block != 1);
kfree(disk->ev);
}
+
+int bdev_interposer_attach(struct block_device *original,
+ struct block_device *interposer)
+{
+ int ret = 0;
+
+ if (WARN_ON(((!original) || (!interposer))))
+ return -EINVAL;
+ /*
+ * interposer should be simple, no a multi-queue device
+ */
+ if (!interposer->bd_disk->fops->submit_bio)
+ return -EINVAL;
+
+ if (WARN_ON(!blk_mq_is_queue_frozen(original->bd_disk->queue)))
+ return -EPERM;
+
+ mutex_lock(&bdev_interposer_attach_lock);
+
+ if (bdev_has_interposer(original))
+ ret = -EBUSY;
+ else {
+ original->bd_interposer = bdgrab(interposer);
+ if (!original->bd_interposer)
+ ret = -ENODEV;
+ }
+
+ mutex_unlock(&bdev_interposer_attach_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(bdev_interposer_attach);
+
+void bdev_interposer_detach(struct block_device *original)
+{
+ if (WARN_ON(!original))
+ return;
+
+ if (WARN_ON(!blk_mq_is_queue_frozen(original->bd_disk->queue)))
+ return;
+
+ mutex_lock(&bdev_interposer_attach_lock);
+ if (bdev_has_interposer(original)) {
+ bdput(original->bd_interposer);
+ original->bd_interposer = NULL;
+ }
+ mutex_unlock(&bdev_interposer_attach_lock);
+}
+EXPORT_SYMBOL_GPL(bdev_interposer_detach);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index db026b6ec15a..13bda4732cf5 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -19,6 +19,7 @@ struct io_context;
struct cgroup_subsys_state;
typedef void (bio_end_io_t) (struct bio *);
struct bio_crypt_ctx;
+struct bdev_interposer;
struct block_device {
sector_t bd_start_sect;
@@ -46,6 +47,7 @@ struct block_device {
spinlock_t bd_size_lock; /* for bd_inode->i_size updates */
struct gendisk * bd_disk;
struct backing_dev_info *bd_bdi;
+ struct block_device *bd_interposer;
/* The counter of freeze processes */
int bd_fsfreeze_count;
@@ -304,6 +306,7 @@ enum {
BIO_CGROUP_ACCT, /* has been accounted to a cgroup */
BIO_TRACKED, /* set if bio goes through the rq_qos path */
BIO_REMAPPED,
+ BIO_INTERPOSED, /* bio was reassigned to another block device */
BIO_FLAG_LAST
};
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index bc6bc8383b43..90f62b4197da 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -2031,4 +2031,13 @@ int fsync_bdev(struct block_device *bdev);
int freeze_bdev(struct block_device *bdev);
int thaw_bdev(struct block_device *bdev);
+static inline bool bdev_has_interposer(struct block_device *bdev)
+{
+ return (bdev->bd_interposer != NULL);
+};
+
+int bdev_interposer_attach(struct block_device *original,
+ struct block_device *interposer);
+void bdev_interposer_detach(struct block_device *original);
+
#endif /* _LINUX_BLKDEV_H */
--
2.20.1
Powered by blists - more mailing lists