mdadm/0103-Create-tell-udev-md-device-is-not-ready-when-first-c.patch

From cd6cbb08c458cee07acb1d854e04532b29ec87bf Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Fri, 28 Apr 2017 15:05:50 +1000
Subject: [PATCH] Create: tell udev md device is not ready when first created.
Git-commit: cd6cbb08c458cee07acb1d854e04532b29ec87bf
Patch-mainline: mdadm-4.0+
References: bsc#1069165, bsc#1069167, bsc#1068030

When an array is created the content is not initialized,
so it could have remnants of an old filesystem or md array
etc on it.
udev will see this and might try to activate it, which is almost
certainly not what is wanted.

So create a mechanism for mdadm to communicate with udev to tell
it that the device isn't ready.  This mechanism is the existance
of a file /run/mdadm/created-mdXXX where mdXXX is the md device name.

When creating an array, mdadm will create the file.
A new udev rule file, 01-md-raid-creating.rules, will detect the
precense of thst file and set ENV{SYSTEMD_READY}="0".
This is fairly uniformly used to suppress actions based on the
contents of the device.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jes Sorensen <jsorensen@fb.com>
Signed-off-by: Coly Li <colyli@suse.de>

---
 Assemble.c                  |  2 +-
 Build.c                     |  2 +-
 Create.c                    |  9 +++++++-
 Incremental.c               |  4 ++--
 Makefile                    |  4 ++--
 lib.c                       | 29 +++++++++++++++++++++++++
 mdadm.h                     |  4 +++-
 mdopen.c                    | 52 ++++++++++++++++++++++++++++-----------------
 udev-md-raid-creating.rules |  7 ++++++
 9 files changed, 86 insertions(+), 27 deletions(-)
 create mode 100644 udev-md-raid-creating.rules

diff --git a/Assemble.c b/Assemble.c
index d6beb23..a9442c8 100644
--- a/Assemble.c
+++ b/Assemble.c
@@ -1478,7 +1478,7 @@ try_again:
 			name = strchr(name, ':')+1;
 
 		mdfd = create_mddev(mddev, name, ident->autof, trustworthy,
-				    chosen_name);
+				    chosen_name, 0);
 	}
 	if (mdfd < 0) {
 		st->ss->free_super(st);
diff --git a/Build.c b/Build.c
index 11ba12f..665d906 100644
--- a/Build.c
+++ b/Build.c
@@ -109,7 +109,7 @@ int Build(char *mddev, struct mddev_dev *devlist,
 	/* We need to create the device.  It can have no name. */
 	map_lock(&map);
 	mdfd = create_mddev(mddev, NULL, c->autof, LOCAL,
-			    chosen_name);
+			    chosen_name, 0);
 	if (mdfd < 0) {
 		map_unlock(&map);
 		return 1;
diff --git a/Create.c b/Create.c
index 6ca0924..df1bc20 100644
--- a/Create.c
+++ b/Create.c
@@ -605,7 +605,7 @@ int Create(struct supertype *st, char *mddev,
 
 	/* We need to create the device */
 	map_lock(&map);
-	mdfd = create_mddev(mddev, name, c->autof, LOCAL, chosen_name);
+	mdfd = create_mddev(mddev, name, c->autof, LOCAL, chosen_name, 1);
 	if (mdfd < 0) {
 		map_unlock(&map);
 		return 1;
@@ -620,6 +620,7 @@ int Create(struct supertype *st, char *mddev,
 			chosen_name);
 		close(mdfd);
 		map_unlock(&map);
+		udev_unblock();
 		return 1;
 	}
 	mddev = chosen_name;
@@ -1053,9 +1054,15 @@ int Create(struct supertype *st, char *mddev,
 		pr_err("not starting array - not enough devices.\n");
 	}
 	close(mdfd);
+	/* Give udev a moment to process the Change event caused
+	 * by the close.
+	 */
+	usleep(100*1000);
+	udev_unblock();
 	return 0;
 
  abort:
+	udev_unblock();
 	map_lock(&map);
  abort_locked:
 	map_remove(&map, fd2devnm(mdfd));
diff --git a/Incremental.c b/Incremental.c
index 66c5b03..4789e36 100644
--- a/Incremental.c
+++ b/Incremental.c
@@ -320,7 +320,7 @@ int Incremental(struct mddev_dev *devlist, struct context *c,
 
 		/* Couldn't find an existing array, maybe make a new one */
 		mdfd = create_mddev(match ? match->devname : NULL,
-				    name_to_use, c->autof, trustworthy, chosen_name);
+				    name_to_use, c->autof, trustworthy, chosen_name, 0);
 
 		if (mdfd < 0)
 			goto out_unlock;
@@ -1596,7 +1596,7 @@ static int Incremental_container(struct supertype *st, char *devname,
 					    ra->name,
 					    c->autof,
 					    trustworthy,
-					    chosen_name);
+					    chosen_name, 0);
 		}
 		if (only && (!mp || strcmp(mp->devnm, only) != 0))
 			continue;
diff --git a/Makefile b/Makefile
index 6850696..021d3ad 100644
--- a/Makefile
+++ b/Makefile
@@ -256,8 +256,8 @@ install-man: mdadm.8 md.4 mdadm.conf.5 mdmon.8
 	$(INSTALL) -D -m 644 md.4 $(DESTDIR)$(MAN4DIR)/md.4
 	$(INSTALL) -D -m 644 mdadm.conf.5 $(DESTDIR)$(MAN5DIR)/mdadm.conf.5
 
-install-udev: udev-md-raid-arrays.rules udev-md-raid-assembly.rules
-	@for file in 63-md-raid-arrays.rules 64-md-raid-assembly.rules ; \
+install-udev: udev-md-raid-arrays.rules udev-md-raid-assembly.rules udev-md-raid-creating.rules
+	@for file in 01-md-raid-creating.rules 63-md-raid-arrays.rules 64-md-raid-assembly.rules ; \
 	do sed -e 's,BINDIR,$(BINDIR),g' udev-$${file#??-} > .install.tmp.1 && \
 	   $(ECHO) $(INSTALL) -D -m 644 udev-$${file#??-} $(DESTDIR)$(UDEVDIR)/rules.d/$$file ; \
 	   $(INSTALL) -D -m 644 .install.tmp.1 $(DESTDIR)$(UDEVDIR)/rules.d/$$file ; \
diff --git a/lib.c b/lib.c
index b640634..7e44b1f 100644
--- a/lib.c
+++ b/lib.c
@@ -163,6 +163,35 @@ char *fd2devnm(int fd)
 	return NULL;
 }
 
+/* When we create a new array, we don't want the content to
+ * be immediately examined by udev - it is probably meaningless.
+ * So create /run/mdadm/creating-FOO and expect that a udev
+ * rule will noticed this and act accordingly.
+ */
+static char block_path[] = "/run/mdadm/creating-%s";
+static char *unblock_path = NULL;
+void udev_block(char *devnm)
+{
+	int fd;
+	char *path = NULL;
+
+	xasprintf(&path, block_path, devnm);
+	fd = open(path, O_CREAT|O_RDWR, 0600);
+	if (fd >= 0) {
+		close(fd);
+		unblock_path = path;
+	} else
+		free(path);
+}
+
+void udev_unblock(void)
+{
+	if (unblock_path)
+		unlink(unblock_path);
+	free(unblock_path);
+	unblock_path = NULL;
+}
+
 /*
  * convert a major/minor pair for a block device into a name in /dev, if possible.
  * On the first call, walk /dev collecting name.
diff --git a/mdadm.h b/mdadm.h
index 1bbacfe..6a382a7 100644
--- a/mdadm.h
+++ b/mdadm.h
@@ -1533,7 +1533,7 @@ extern char *get_md_name(char *devnm);
 extern char DefaultConfFile[];
 
 extern int create_mddev(char *dev, char *name, int autof, int trustworthy,
-			char *chosen);
+			char *chosen, int block_udev);
 /* values for 'trustworthy' */
 #define	LOCAL	1
 #define	LOCAL_ANY 10
@@ -1567,6 +1567,8 @@ extern char *stat2kname(struct stat *st);
 extern char *fd2kname(int fd);
 extern char *stat2devnm(struct stat *st);
 extern char *fd2devnm(int fd);
+extern void udev_block(char *devnm);
+extern void udev_unblock(void);
 
 extern int in_initrd(void);
 
diff --git a/mdopen.c b/mdopen.c
index 82b97fc..099efa0 100644
--- a/mdopen.c
+++ b/mdopen.c
@@ -135,7 +135,7 @@ void make_parts(char *dev, int cnt)
  */
 
 int create_mddev(char *dev, char *name, int autof, int trustworthy,
-		 char *chosen)
+		 char *chosen, int block_udev)
 {
 	int mdfd;
 	struct stat stb;
@@ -147,6 +147,10 @@ int create_mddev(char *dev, char *name, int autof, int trustworthy,
 	char devname[37];
 	char devnm[32];
 	char cbuf[400];
+
+	if (!use_udev())
+		block_udev = 0;
+
 	if (chosen == NULL)
 		chosen = cbuf;
 
@@ -305,43 +309,53 @@ int create_mddev(char *dev, char *name, int autof, int trustworthy,
 		int fd;
 		int n = -1;
 		sprintf(devnm, "md_%s", cname);
+		if (block_udev)
+			udev_block(devnm);
 		fd = open("/sys/module/md_mod/parameters/new_array", O_WRONLY);
 		if (fd >= 0) {
 			n = write(fd, devnm, strlen(devnm));
 			close(fd);
 		}
-		if (n < 0)
+		if (n < 0) {
 			devnm[0] = 0;
+			udev_unblock();
+		}
 	}
 	if (num >= 0) {
 		int fd;
 		int n = -1;
 		sprintf(devnm, "md%d", num);
+		if (block_udev)
+			udev_block(devnm);
 		fd = open("/sys/module/md_mod/parameters/new_array", O_WRONLY);
 		if (fd >= 0) {
 			n = write(fd, devnm, strlen(devnm));
 			close(fd);
 		}
-		if (n < 0)
+		if (n < 0) {
 			devnm[0] = 0;
-	}
-	if (devnm[0])
-		;
-	else if (num < 0) {
-		/* need to choose a free number. */
-		char *_devnm = find_free_devnm(use_mdp);
-		if (_devnm == NULL) {
-			pr_err("No avail md devices - aborting\n");
-			return -1;
+			udev_unblock();
 		}
-		strcpy(devnm, _devnm);
-	} else {
-		sprintf(devnm, "%s%d", use_mdp?"md_d":"md", num);
-		if (mddev_busy(devnm)) {
-			pr_err("%s is already in use.\n",
-				dev);
-			return -1;
+	}
+	if (devnm[0] == 0) {
+		if (num < 0) {
+			/* need to choose a free number. */
+			char *_devnm = find_free_devnm(use_mdp);
+			if (_devnm == NULL) {
+				pr_err("No avail md devices - aborting\n");
+				return -1;
+			}
+			strcpy(devnm, _devnm);
+		} else {
+			sprintf(devnm, "%s%d", use_mdp?"md_d":"md", num);
+			if (mddev_busy(devnm)) {
+				pr_err("%s is already in use.\n",
+				       dev);
+				return -1;
+			}
 		}
+		if (block_udev)
+			udev_block(devnm);
 	}
 
 	sprintf(devname, "/dev/%s", devnm);
diff --git a/udev-md-raid-creating.rules b/udev-md-raid-creating.rules
new file mode 100644
index 0000000..2be466b
--- /dev/null
+++ b/udev-md-raid-creating.rules
@@ -0,0 +1,7 @@
+# do not edit this file, it will be overwritten on update
+# While mdadm is creating an array, it creates a file
+# /run/mdadm/creating-mdXXX.  If that file exists, then
+# the array is not "ready" and we should make sure the
+# content is ignored.
+
+KERNEL=="md*", TEST="/run/mdadm/creating-$kernel", ENV{SYSTEMD_READY}="0"
-- 
2.13.6