sysfs: allow sysfs_read to detect and drop removed disks

All operations that rely on loading from an existing container (like
--add) will fail after a disk has been removed.  Provide an option to
skip missing / offline disks rather than abort.  We attempt to do this
in the load_super_{imsm,ddf}_all cases when mdmon is running i.e. we
already have a consitent version of the metadata running in the system.
Otherwise, we fail as normal and let the administrator fix up the
container.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>

1 files changed, 21 insertions, 5 deletions

diff --git a/sysfs.c b/sysfs.c
index b9fd3da..2dad7d3 100644
--- a/sysfs.c
+++ b/sysfs.c
@@ -272,18 +272,34 @@ struct mdinfo *sysfs_read(int fd, int devnum, unsigned long options)
 			}
 			
 		}
-		dev->next = sra->devs;
-		sra->devs = dev;
-
 		strcpy(dev->sys_name, de->d_name);
 		dev->disk.raid_disk = strtoul(buf, &ep, 10);
 		if (*ep) dev->disk.raid_disk = -1;
 
 		strcpy(dbase, "block/dev");
-		if (load_sys(fname, buf))
-			goto abort;
+		if (load_sys(fname, buf)) {
+			free(dev);
+			if (options & SKIP_GONE_DEVS)
+				continue;
+			else
+				goto abort;
+		}
 		sscanf(buf, "%d:%d", &dev->disk.major, &dev->disk.minor);
 
+		/* special case check for block devices that can go 'offline' */
+		if (options & SKIP_GONE_DEVS) {
+			strcpy(dbase, "block/device/state");
+			if (load_sys(fname, buf) == 0 &&
+			    strncmp(buf, "offline", 7) == 0) {
+				free(dev);
+				continue;
+			}
+		}
+
+		/* finally add this disk to the array */
+		dev->next = sra->devs;
+		sra->devs = dev;
+
 		if (options & GET_OFFSET) {
 			strcpy(dbase, "offset");
 			if (load_sys(fname, buf))