[Devel] [PATCH hci-8.1 v5 7/7] drivers/md/push_backup: add event file descriptor interface

[Andrey Zhadchenko <andrey.zhadchenko@virtuozzo.com>]

The backup tool currently waits for the next cluster range to back up
by sleeping inside the "push_backup_read" target message. target_message()
calls into the target under dm_get_live_table(), i.e. with md->io_barrier
SRCU read-locked, so for the whole time the tool waits for a write to be
intercepted anything doing synchronize_srcu(&md->io_barrier) on this device
is stuck: dm suspend, table reload/remove and in particular
dm_internal_suspend_fast() called by "@stats_create". An unrelated dm-stats
consumer therefore hangs together with everything that later queues behind
md->suspend_lock.

Add a file descriptor based interface that does not involve dm messages
on the data path:

  push_backup_get_fd        - returns an anon inode fd in the message
                              result
  read(fd, &range, 16)      - next struct dm_push_backup_range to back up;
                              0 when the backup is finished,
                              ESTALE when not running,
                              ENODEV after the target is destroyed
  write(fd, &range, 16)     - acknowledge the range, same as
                              push_backup_write

The fd is bound to the target, not to a backup session, and keeps
working across stop and a later start.

We can't access/uninstall fd across all processes that have it, so add kref
on the push_backup struct and tie it to number of fds. Free only when
everything is gone.

The legacy messages are kept for compatibility but we will clean them up
later. They now share the code with the fd, which changes two things:
pb_message() parsed u64 but passed unsigned int to push_backup_write(),
so "push_backup_write 4294967296:1" acked cluster 0 and now fails with
-E2BIG, and push_backup_read printed "%u" ranges, which was wrong on
devices with 2^32 or more clusters.

Also free the pbio before requeuing its request in resubmit_pbios().
In-flight requests pin the mapped device (dm_start_request() ->
dm_get()), not the target, so once the last request is requeued the
target may be destroyed together with pbio_pool. The dm messages run
under the live table and are safe, but the fd write path holds no md
reference.

Bump the target version to 1.1.0.

https://virtuozzo.atlassian.net/browse/VSTOR-152912
Signed-off-by: Andrey Zhadchenko <andrey.zhadchenko@virtuozzo.com>
Reviewed-by: Alexander Ivanov <alexander.ivanov@virtuozzo.com>
---
v2: free the pbio before dm_requeue_original_rq() in resubmit_pbios(),
    the requeue may drop the last md reference and let .dtr run
v3: install the fd only after its number fits into the result buffer
    (reserve fd -> DMEMIT -> overflow check -> anon_inode_getfile ->
    fd_install); rename pb->dead to pb->destroyed; prefix the UAPI type
    as struct dm_push_backup_range; read() requires exactly
    sizeof(range) like write(); subject prefix aligned with the rest of
    the series
v4: commit message typos
v5: header: the fd survives stop/start, -1/errno, EINTR, EFAULT,
    EBADMSG and write() errors, O_CLOEXEC, "dmsetup message" is of
    no use; pb_destroy() NULLs the pointers it frees; blank line
    after the declaration in resubmit_pbios(); commit message:
    legacy u64 parsing changes, correct resubmit_pbios() rationale,
    version bump to 1.1.0

 drivers/md/dm-push-backup.c         | 218 ++++++++++++++++++++++++----
 include/uapi/linux/dm-push-backup.h |  48 ++++++
 2 files changed, 237 insertions(+), 29 deletions(-)
 create mode 100644 include/uapi/linux/dm-push-backup.h

diff --git a/drivers/md/dm-push-backup.c b/drivers/md/dm-push-backup.c
index 52ba80b703ff1..c85e8446895d7 100644
--- a/drivers/md/dm-push-backup.c
+++ b/drivers/md/dm-push-backup.c
@@ -15,6 +15,11 @@
 #include <linux/ctype.h>
 #include <linux/dm-io.h>
 #include <linux/blk-mq.h>
+#include <linux/anon_inodes.h>
+#include <linux/file.h>
+#include <linux/kref.h>
+#include <linux/uaccess.h>
+#include <linux/dm-push-backup.h>
 
 
 #define DM_MSG_PREFIX "push-backup"
@@ -46,6 +51,9 @@ struct push_backup {
 	u64 clu_size;
 	u64 nr_clus;
 
+	struct kref ref;
+	bool destroyed;
+
 	bool alive;
 	void *map;
 	u64 map_bits;
@@ -69,6 +77,16 @@ struct push_backup {
 	struct rw_semaphore ctl_rwsem;
 };
 
+static void pb_release(struct kref *ref)
+{
+	kfree(container_of(ref, struct push_backup, ref));
+}
+
+static void pb_put(struct push_backup *pb)
+{
+	kref_put(&pb->ref, pb_release);
+}
+
 static u64 pbio_first_required_for_backup_clu(struct push_backup *pb, struct pb_bio *pbio)
 {
 	u64 clu;
@@ -196,9 +214,11 @@ static void resubmit_pbios(struct push_backup *pb, struct list_head *list)
 	struct pb_bio *pbio;
 
 	while ((pbio = list_first_entry_or_null(list, struct pb_bio, list)) != NULL) {
+		struct request *rq = pbio->rq;
+
 		list_del_init(&pbio->list);
-		dm_requeue_original_rq(pbio->rq);
 		mempool_free(pbio, pb->pbio_pool);
+		dm_requeue_original_rq(rq);
 	}
 }
 
@@ -411,35 +431,41 @@ static int push_backup_stop(struct push_backup *pb,
 	return 0;
 }
 
-static int push_backup_read(struct push_backup *pb,
-			    char *result, unsigned int maxlen)
+static bool pb_has_event(struct push_backup *pb)
+{
+	return READ_ONCE(pb->destroyed) || !READ_ONCE(pb->map) ||
+	       !READ_ONCE(pb->alive) || !READ_ONCE(pb->map_bits) ||
+	       !list_empty_careful(&pb->pending);
+}
+
+/*
+ * Returns:
+ *   1       - next range to back up is stored in @clu/@nr
+ *   0       - backup is finished (nothing left to back up)
+ *   -EAGAIN - nothing pending at the moment
+ *   -ESTALE - backup is not running (not started, stopped or expired)
+ *   -ENODEV - target was destroyed
+ */
+static int pb_next_range(struct push_backup *pb, u64 *clu, u64 *nr)
 {
-	unsigned int left, right, sz = 0;
 	struct pb_bio *pbio;
+	u64 left, right;
 	int ret;
 
-	if (!pb)
-		return -EBADF;
-	if (!pb->map)
-		return -ESTALE;
-again:
-	if (wait_event_interruptible(pb->waitq,
-				     !list_empty_careful(&pb->pending) ||
-				     !pb->alive || !pb->map_bits))
-		return -EINTR;
-
 	spin_lock_irq(&pb->lock);
+	ret = -ENODEV;
+	if (pb->destroyed)
+		goto unlock;
 	ret = -ESTALE;
-	if (!pb->alive)
+	if (!pb->map || !pb->alive)
 		goto unlock;
 	ret = 0;
 	if (!pb->map_bits)
 		goto unlock;
+	ret = -EAGAIN;
 	pbio = list_first_entry_or_null(&pb->pending, typeof(*pbio), list);
-	if (unlikely(!pbio)) {
-		spin_unlock_irq(&pb->lock);
-		goto again;
-	}
+	if (!pbio)
+		goto unlock;
 
 	ret = -EBADMSG;
 	left = pbio_first_required_for_backup_clu(pb, pbio);
@@ -452,15 +478,47 @@ static int push_backup_read(struct push_backup *pb,
 	else
 		right = pb->nr_clus - 1;
 
-	DMEMIT("%u:%u", left, right - left + 1);
+	*clu = left;
+	*nr = right - left + 1;
 	ret = 1;
 unlock:
 	spin_unlock_irq(&pb->lock);
 	return ret;
 }
 
-static int push_backup_write(struct push_backup *pb,
-			     unsigned int clu, unsigned int nr)
+static int pb_wait_range(struct push_backup *pb, bool nonblock,
+			 u64 *clu, u64 *nr)
+{
+	int ret;
+
+	while (1) {
+		ret = pb_next_range(pb, clu, nr);
+		if (ret != -EAGAIN || nonblock)
+			return ret;
+		if (wait_event_interruptible(pb->waitq, pb_has_event(pb)))
+			return -ERESTARTSYS;
+	}
+}
+
+static int push_backup_read(struct push_backup *pb,
+			    char *result, unsigned int maxlen)
+{
+	unsigned int sz = 0;
+	u64 clu, nr;
+	int ret;
+
+	if (!pb)
+		return -EBADF;
+
+	ret = pb_wait_range(pb, false, &clu, &nr);
+	if (ret == -ERESTARTSYS)
+		ret = -EINTR;
+	if (ret == 1)
+		DMEMIT("%llu:%llu", clu, nr);
+	return ret;
+}
+
+static int push_backup_write(struct push_backup *pb, u64 clu, u64 nr)
 {
 	u64 i, key, nr_clus = pb->nr_clus;
 	LIST_HEAD(pbio_list);
@@ -471,11 +529,13 @@ static int push_backup_write(struct push_backup *pb,
 		return -EBADF;
 	if (clu >= nr_clus || nr > nr_clus - clu)
 		return -E2BIG;
-	if (!pb->map)
-		return -ESTALE;
 
 	spin_lock_irq(&pb->lock);
-	if (!pb->alive) {
+	if (pb->destroyed) {
+		spin_unlock_irq(&pb->lock);
+		return -ENODEV;
+	}
+	if (!pb->map || !pb->alive) {
 		spin_unlock_irq(&pb->lock);
 		return -ESTALE;
 	}
@@ -530,6 +590,84 @@ static int push_backup_write(struct push_backup *pb,
 	return 0;
 }
 
+static ssize_t pb_fd_read(struct file *file, char __user *buf,
+			  size_t count, loff_t *ppos)
+{
+	struct push_backup *pb = file->private_data;
+	struct dm_push_backup_range range;
+	int ret;
+
+	if (count != sizeof(range))
+		return -EINVAL;
+
+	ret = pb_wait_range(pb, file->f_flags & O_NONBLOCK,
+			    &range.clu, &range.nr);
+	if (ret <= 0)
+		return ret;
+
+	if (copy_to_user(buf, &range, sizeof(range)))
+		return -EFAULT;
+	return sizeof(range);
+}
+
+static ssize_t pb_fd_write(struct file *file, const char __user *buf,
+			   size_t count, loff_t *ppos)
+{
+	struct push_backup *pb = file->private_data;
+	struct dm_push_backup_range range;
+	int ret;
+
+	if (count != sizeof(range))
+		return -EINVAL;
+	if (copy_from_user(&range, buf, sizeof(range)))
+		return -EFAULT;
+
+	ret = push_backup_write(pb, range.clu, range.nr);
+	return ret ? : sizeof(range);
+}
+
+static int pb_fd_release(struct inode *inode, struct file *file)
+{
+	pb_put(file->private_data);
+	return 0;
+}
+
+static const struct file_operations pb_fops = {
+	.owner		= THIS_MODULE,
+	.read		= pb_fd_read,
+	.write		= pb_fd_write,
+	.release	= pb_fd_release,
+};
+
+static int push_backup_get_fd(struct push_backup *pb,
+			      char *result, unsigned int maxlen)
+{
+	unsigned int sz = 0;
+	struct file *file;
+	int fd;
+
+	fd = get_unused_fd_flags(O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	DMEMIT("%d", fd);
+	if (sz + 1 >= maxlen) {
+		put_unused_fd(fd);
+		return 1;
+	}
+
+	kref_get(&pb->ref);
+	file = anon_inode_getfile("[push_backup]", &pb_fops, pb, O_RDWR);
+	if (IS_ERR(file)) {
+		pb_put(pb);
+		put_unused_fd(fd);
+		return PTR_ERR(file);
+	}
+
+	fd_install(fd, file);
+	return 1;
+}
+
 static int push_backup_statistics(struct push_backup *pb, char *result,
 				  unsigned int maxlen)
 {
@@ -608,6 +746,10 @@ static int pb_message(struct dm_target *ti, unsigned int argc, char **argv,
 		ret = push_backup_write(pb, val, val2);
 	} else if (!strcmp(argv[0], "push_backup_statistics")) {
 		ret = push_backup_statistics(pb, result, maxlen);
+	} else if (!strcmp(argv[0], "push_backup_get_fd")) {
+		if (argc != 1)
+			goto unlock;
+		ret = push_backup_get_fd(pb, result, maxlen);
 	} else {
 		ret = -ENOTSUPP;
 	}
@@ -622,18 +764,35 @@ static int pb_message(struct dm_target *ti, unsigned int argc, char **argv,
 }
 static void pb_destroy(struct push_backup *pb)
 {
+	void *map, *pending_map;
+
 	WARN_ON_ONCE(pb->nr_delayed);
 
+	spin_lock_irq(&pb->lock);
+	pb->destroyed = true;
+	map = pb->map; /* It's not zero if stop was not called */
+	pb->map = NULL;
+	pending_map = pb->pending_map;
+	pb->pending_map = NULL;
+	spin_unlock_irq(&pb->lock);
+
+	wake_up_interruptible(&pb->waitq);
+
 	timer_shutdown_sync(&pb->deadline_timer);
 	if (pb->wq)
 		destroy_workqueue(pb->wq);
-	kvfree(pb->map); /* Is's not zero if stop was not called */
-	kvfree(pb->pending_map);
+	pb->wq = NULL;
+	kvfree(map);
+	kvfree(pending_map);
 	kvfree(pb->pending_htable);
+	pb->pending_htable = NULL;
 	mempool_destroy(pb->pbio_pool);
+	pb->pbio_pool = NULL;
 	if (pb->origin_dev)
 		dm_put_device(pb->ti, pb->origin_dev);
-	kfree(pb);
+	pb->origin_dev = NULL;
+	pb->ti = NULL;
+	pb_put(pb);
 }
 
 /*
@@ -652,6 +811,7 @@ static int pb_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	pb = kzalloc(sizeof(*pb), GFP_KERNEL);
 	if (!pb)
 		goto err;
+	kref_init(&pb->ref);
 	spin_lock_init(&pb->lock);
 	init_rwsem(&pb->ctl_rwsem);
 	bio_list_init(&pb->deferred_bios);
@@ -761,7 +921,7 @@ static loff_t pb_llseek_hole(struct dm_target *ti, loff_t offset,
 
 static struct target_type pb_target = {
 	.name = "push_backup",
-	.version = {1, 0, 0},
+	.version = {1, 1, 0},
 	.features = DM_TARGET_SINGLETON,
 	.module = THIS_MODULE,
 	.ctr = pb_ctr,
diff --git a/include/uapi/linux/dm-push-backup.h b/include/uapi/linux/dm-push-backup.h
new file mode 100644
index 0000000000000..7e24835f2c83a
--- /dev/null
+++ b/include/uapi/linux/dm-push-backup.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ *  Copyright (c) 2026 Virtuozzo International GmbH. All rights reserved.
+ */
+
+/*
+ * Userspace interface of the dm-push-backup target's event file descriptor.
+ *
+ * The fd is obtained with the "push_backup_get_fd" target message; the fd
+ * is installed into the calling process and the number is returned in the
+ * message result buffer.
+ *
+ * The fd is bound to the target and push_backup_stop does not invalidate
+ * it.
+ *
+ * Both read() and write() operate on exactly one struct dm_push_backup_range
+ * and fail with EINVAL for any other count. On failure they return -1 and
+ * set errno as usual.
+ *
+ * read(fd, &range, sizeof(range)):
+ *   sizeof(range) - @range holds the next cluster range that must be backed
+ *                   up before the writes postponed on it may proceed.
+ *                   Reading does not consume anything: the same (or a wider)
+ *                   range is returned until it is acknowledged via write().
+ *   0             - backup has finished, nothing is left to back up.
+ *   EAGAIN        - O_NONBLOCK is set and no writes are pending.
+ *   ESTALE        - backup is not running (not started, stopped or expired).
+ *   ENODEV        - the target has been destroyed.
+ *   EINTR         - interrupted by a signal while waiting.
+ *   EFAULT        - @range is not accessible.
+ *   EBADMSG       - internal inconsistency of the pending state.
+ *
+ * write(fd, &range, sizeof(range)):
+ *   acknowledge that @range has been backed up; equivalent to the
+ *   "push_backup_write clu:nr" message. Fails with E2BIG if @range is out
+ *   of the device, ESTALE and ENODEV as read(), and EFAULT.
+ */
+#ifndef _UAPI_LINUX_DM_PUSH_BACKUP_H
+#define _UAPI_LINUX_DM_PUSH_BACKUP_H
+
+#include <linux/types.h>
+
+struct dm_push_backup_range {
+	__u64 clu;	/* first cluster */
+	__u64 nr;	/* number of clusters */
+};
+
+#endif /* _UAPI_LINUX_DM_PUSH_BACKUP_H */
-- 
2.43.5

_______________________________________________
Devel mailing list
Devel@openvz.org
https://lists.openvz.org/mailman/listinfo/devel