163 lines
5.1 KiB
Diff
163 lines
5.1 KiB
Diff
From 27ad4900501c615b7c6b266bf23948e5606dba53 Mon Sep 17 00:00:00 2001
|
|
From: Logan Gunthorpe <logang@deltatee.com>
|
|
Date: Wed, 27 Jul 2022 15:52:46 -0600
|
|
Subject: [PATCH 50/83] mdadm: Don't open md device for CREATE and ASSEMBLE
|
|
|
|
The mdadm command tries to open the md device for most modes, first
|
|
thing, no matter what. When running to create or assemble an array,
|
|
in most cases, the md device will not exist, the open call will fail
|
|
and everything will proceed correctly.
|
|
|
|
However, when running tests, a create or assembly command may be run
|
|
shortly after stopping an array and the old md device file may still
|
|
be around. Then, if create_on_open is set in the kernel, a new md
|
|
device will be created when mdadm does its initial open.
|
|
|
|
When mdadm gets around to creating the new device with the new_array
|
|
parameter it issues this error:
|
|
|
|
mdadm: Fail to create md0 when using
|
|
/sys/module/md_mod/parameters/new_array, fallback to creation via node
|
|
|
|
This is because an mddev was already created by the kernel with the
|
|
earlier open() call and thus the new one being created will fail with
|
|
EEXIST. The mdadm command will still successfully be created due to
|
|
falling back to the node creation method. However, the error message
|
|
itself will fail any test that's running it.
|
|
|
|
This issue is a race condition that is very rare, but a recent change
|
|
in the kernel caused this to happen more frequently: about 1 in 50
|
|
times.
|
|
|
|
To fix this, don't bother trying to open the md device for CREATE,
|
|
ASSEMBLE and BUILD commands, as the file descriptor will never be used
|
|
anyway even if it is successfully openned. The mdfd has not been used
|
|
for these commands since:
|
|
|
|
7f91af49ad09 ("Delay creation of array devices for assemble/build/create")
|
|
|
|
The checks that were done on the open device can be changed to being
|
|
done with stat.
|
|
|
|
Side note: it would be nice to disable create_on_open as well to help
|
|
solve this, but it seems the work for this was never finished. By default,
|
|
mdadm will create using the old node interface when a name is specified
|
|
unless the user specifically puts names=yes in a config file, which
|
|
doesn't seem to be common or desirable to require this..
|
|
|
|
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
|
|
Signed-off-by: Jes Sorensen <jsorensen@fb.com>
|
|
---
|
|
lib.c | 12 ++++++++++++
|
|
mdadm.c | 40 ++++++++++++++++++++--------------------
|
|
mdadm.h | 1 +
|
|
3 files changed, 33 insertions(+), 20 deletions(-)
|
|
|
|
diff --git a/lib.c b/lib.c
|
|
index 7e3e3d47..e395b28d 100644
|
|
--- a/lib.c
|
|
+++ b/lib.c
|
|
@@ -164,6 +164,18 @@ char *stat2devnm(struct stat *st)
|
|
return devid2devnm(st->st_rdev);
|
|
}
|
|
|
|
+bool stat_is_md_dev(struct stat *st)
|
|
+{
|
|
+ if ((S_IFMT & st->st_mode) != S_IFBLK)
|
|
+ return false;
|
|
+ if (major(st->st_rdev) == MD_MAJOR)
|
|
+ return true;
|
|
+ if (major(st->st_rdev) == (unsigned)get_mdp_major())
|
|
+ return true;
|
|
+
|
|
+ return false;
|
|
+}
|
|
+
|
|
char *fd2devnm(int fd)
|
|
{
|
|
struct stat stb;
|
|
diff --git a/mdadm.c b/mdadm.c
|
|
index 845e4466..972adb52 100644
|
|
--- a/mdadm.c
|
|
+++ b/mdadm.c
|
|
@@ -1329,6 +1329,9 @@ int main(int argc, char *argv[])
|
|
|
|
if (mode == MANAGE || mode == BUILD || mode == CREATE ||
|
|
mode == GROW || (mode == ASSEMBLE && ! c.scan)) {
|
|
+ struct stat stb;
|
|
+ int ret;
|
|
+
|
|
if (devs_found < 1) {
|
|
pr_err("an md device must be given in this mode\n");
|
|
exit(2);
|
|
@@ -1341,6 +1344,12 @@ int main(int argc, char *argv[])
|
|
mdfd = open_mddev(devlist->devname, 1);
|
|
if (mdfd < 0)
|
|
exit(1);
|
|
+
|
|
+ ret = fstat(mdfd, &stb);
|
|
+ if (ret) {
|
|
+ pr_err("fstat failed on %s.\n", devlist->devname);
|
|
+ exit(1);
|
|
+ }
|
|
} else {
|
|
char *bname = basename(devlist->devname);
|
|
|
|
@@ -1348,30 +1357,21 @@ int main(int argc, char *argv[])
|
|
pr_err("Name %s is too long.\n", devlist->devname);
|
|
exit(1);
|
|
}
|
|
- /* non-existent device is OK */
|
|
- mdfd = open_mddev(devlist->devname, 0);
|
|
- }
|
|
- if (mdfd == -2) {
|
|
- pr_err("device %s exists but is not an md array.\n", devlist->devname);
|
|
- exit(1);
|
|
- }
|
|
- if ((int)ident.super_minor == -2) {
|
|
- struct stat stb;
|
|
- if (mdfd < 0) {
|
|
+
|
|
+ ret = stat(devlist->devname, &stb);
|
|
+ if (ident.super_minor == -2 && ret != 0) {
|
|
pr_err("--super-minor=dev given, and listed device %s doesn't exist.\n",
|
|
- devlist->devname);
|
|
+ devlist->devname);
|
|
+ exit(1);
|
|
+ }
|
|
+
|
|
+ if (!ret && !stat_is_md_dev(&stb)) {
|
|
+ pr_err("device %s exists but is not an md array.\n", devlist->devname);
|
|
exit(1);
|
|
}
|
|
- fstat(mdfd, &stb);
|
|
- ident.super_minor = minor(stb.st_rdev);
|
|
- }
|
|
- if (mdfd >= 0 && mode != MANAGE && mode != GROW) {
|
|
- /* We don't really want this open yet, we just might
|
|
- * have wanted to check some things
|
|
- */
|
|
- close(mdfd);
|
|
- mdfd = -1;
|
|
}
|
|
+ if (ident.super_minor == -2)
|
|
+ ident.super_minor = minor(stb.st_rdev);
|
|
}
|
|
|
|
if (s.raiddisks) {
|
|
diff --git a/mdadm.h b/mdadm.h
|
|
index adb7cdaa..8208b81e 100644
|
|
--- a/mdadm.h
|
|
+++ b/mdadm.h
|
|
@@ -1672,6 +1672,7 @@ void *super1_make_v0(struct supertype *st, struct mdinfo *info, mdp_super_t *sb0
|
|
extern char *stat2kname(struct stat *st);
|
|
extern char *fd2kname(int fd);
|
|
extern char *stat2devnm(struct stat *st);
|
|
+bool stat_is_md_dev(struct stat *st);
|
|
extern char *fd2devnm(int fd);
|
|
extern void udev_block(char *devnm);
|
|
extern void udev_unblock(void);
|
|
--
|
|
2.38.1
|
|
|