block: disk_events: introduce event flags

Currently, an empty disk->events field tells the block layer not to
forward media change events to user space. This was done in commit
7c88a168 ("block: don't propagate unlisted DISK_EVENTs to userland")
in order to avoid events from "fringe" drivers to be forwarded to user
space. By doing so, the block layer lost the information which events
were supported by a particular block device, and most importantly,
whether or not a given device supports media change events at all.

Prepare for not interpreting the "events" field this way in the future
any more. This is done by adding an additional field "event_flags" to
struct gendisk, and two flag bits that can be set to have the device
treated like one that had the "events" field set to a non-zero value
before. This applies only to the sd and sr drivers, which are changed to
set the new flags.

The new flags are DISK_EVENT_FLAG_POLL to enforce polling of the device
for synchronous events, and DISK_EVENT_FLAG_UEVENT to tell the
blocklayer to generate udev events from kernel events.

In order to add the event_flags field to struct gendisk, the events
field is converted to an "unsigned short"; it doesn't need to hold
values bigger than 2 anyway.

This patch doesn't change behavior.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

block/genhd.c

@@ -1632,7 +1632,7 @@ static unsigned long disk_events_poll_jiffies(struct gendisk *disk)
 	 */
 	if (ev->poll_msecs >= 0)
 		intv_msecs = ev->poll_msecs;
-	else if (disk->events)
+	else if (disk->event_flags & DISK_EVENT_FLAG_POLL)
 		intv_msecs = disk_events_dfl_poll_msecs;
 
 	return msecs_to_jiffies(intv_msecs);
@@ -1842,11 +1842,13 @@ static void disk_check_events(struct disk_events *ev,
 
 	/*
 	 * Tell userland about new events.  Only the events listed in
-	 * @disk->events are reported.  Unlisted events are processed the
-	 * same internally but never get reported to userland.
+	 * @disk->events are reported, and only if DISK_EVENT_FLAG_UEVENT
+	 * is set. Otherwise, events are processed internally but never
+	 * get reported to userland.
 	 */
 	for (i = 0; i < ARRAY_SIZE(disk_uevents); i++)
-		if (events & disk->events & (1 << i))
+		if ((events & disk->events & (1 << i)) &&
+		    (disk->event_flags & DISK_EVENT_FLAG_UEVENT))
 			envp[nr_events++] = disk_uevents[i];
 
 	if (nr_events)
@@ -1884,6 +1886,9 @@ static ssize_t disk_events_show(struct device *dev,
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
+	if (!(disk->event_flags & DISK_EVENT_FLAG_UEVENT))
+		return 0;
+
 	return __disk_events_show(disk->events, buf);
 }
 

drivers/scsi/sd.c

@@ -3293,6 +3293,7 @@ static void sd_probe_async(void *data, async_cookie_t cookie)
 	if (sdp->removable) {
 		gd->flags |= GENHD_FL_REMOVABLE;
 		gd->events |= DISK_EVENT_MEDIA_CHANGE;
+		gd->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT;
 	}
 
 	blk_pm_runtime_init(sdp->request_queue, dev);

drivers/scsi/sr.c

@@ -716,6 +716,7 @@ static int sr_probe(struct device *dev)
 	disk->fops = &sr_bdops;
 	disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
 	disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST;
+	disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT;
 
 	blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT);
 

include/linux/genhd.h

@@ -150,6 +150,13 @@ enum {
 	DISK_EVENT_EJECT_REQUEST		= 1 << 1, /* eject requested */
 };
 
+enum {
+	/* Poll even if events_poll_msecs is unset */
+	DISK_EVENT_FLAG_POLL			= 1 << 0,
+	/* Forward events to udev */
+	DISK_EVENT_FLAG_UEVENT			= 1 << 1,
+};
+
 struct disk_part_tbl {
 	struct rcu_head rcu_head;
 	int len;
@@ -184,7 +191,8 @@ struct gendisk {
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
 	char *(*devnode)(struct gendisk *gd, umode_t *mode);
 
-	unsigned int events;		/* supported events */
+	unsigned short events;		/* supported events */
+	unsigned short event_flags;	/* flags related to event processing */
 
 	/* Array of pointers to partitions indexed by partno.
 	 * Protected with matching bdev lock but stat and other