81 lines
3.3 KiB
Diff
81 lines
3.3 KiB
Diff
|
From 215adedb16aa082d052f84705338de0d77721fe0 Mon Sep 17 00:00:00 2001
|
||
|
|
Message-Id: <215adedb16aa082d052f84705338de0d77721fe0@dist-git>
|
||
|
|
From: Michal Privoznik <mprivozn@redhat.com>
|
||
|
|
Date: Tue, 6 Sep 2022 13:43:22 +0200
|
||
|
|
Subject: [PATCH] qemu_namespace: Fix a corner case in
|
||
|
|
qemuDomainGetPreservedMounts()
|
||
|
|
|
||
|
|
When setting up namespace for QEMU we look at mount points under
|
||
|
|
/dev (like /dev/pts, /dev/mqueue/, etc.) because we want to
|
||
|
|
preserve those (which is done by moving them to a temp location,
|
||
|
|
unshare(), and then moving them back). We have a convenience
|
||
|
|
helper - qemuDomainGetPreservedMounts() - that processes the
|
||
|
|
mount table and (optionally) moves the other filesystems too.
|
||
|
|
This helper is also used when attempting to create a path in NS,
|
||
|
|
because the path, while starting with "/dev/" prefix, may
|
||
|
|
actually lead to one of those filesystems that we preserved.
|
||
|
|
|
||
|
|
And here comes the corner case: while we require the parent mount
|
||
|
|
table to be in shared mode (equivalent of `mount --make-rshared /'),
|
||
|
|
these mount events propagate iff the target path exist inside the
|
||
|
|
slave mount table (= QEMU's private namespace). And since we
|
||
|
|
create only a subset of /dev nodes, well, that assumption is not
|
||
|
|
always the case.
|
||
|
|
|
||
|
|
For instance, assume that a domain is already running, no
|
||
|
|
hugepages were configured for it nor any hugetlbfs is mounted.
|
||
|
|
Now, when a hugetlbfs is mounted into '/dev/hugepages', this is
|
||
|
|
propagated into the QEMU's namespace, but since the target dir
|
||
|
|
does not exist in the private /dev, the FS is not mounted in the
|
||
|
|
namespace.
|
||
|
|
|
||
|
|
Fortunately, this difference between namespaces is visible when
|
||
|
|
comparing /proc/mounts and /proc/$PID/mounts (where PID is the
|
||
|
|
QEMU's PID). Therefore, if possible we should look at the latter.
|
||
|
|
|
||
|
|
Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
|
||
|
|
Reviewed-by: Martin Kletzander <mkletzan@redhat.com>
|
||
|
|
(cherry picked from commit 46b03819ae8d833b11c2aaccb2c2a0361727f51b)
|
||
|
|
Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=2123196
|
||
|
|
Signed-off-by: Michal Privoznik <mprivozn@redhat.com>
|
||
|
|
---
|
||
|
|
src/qemu/qemu_namespace.c | 10 +++++++++-
|
||
|
|
1 file changed, 9 insertions(+), 1 deletion(-)
|
||
|
|
|
||
|
|
diff --git a/src/qemu/qemu_namespace.c b/src/qemu/qemu_namespace.c
|
||
|
|
index 4bff325a2c..fc286ab0be 100644
|
||
|
|
--- a/src/qemu/qemu_namespace.c
|
||
|
|
+++ b/src/qemu/qemu_namespace.c
|
||
|
|
@@ -110,6 +110,8 @@ qemuDomainGetPreservedMountPath(virQEMUDriverConfig *cfg,
|
||
|
|
* b) generate backup path for all the entries in a)
|
||
|
|
*
|
||
|
|
* Any of the return pointers can be NULL. Both arrays are NULL-terminated.
|
||
|
|
+ * Get the mount table either from @vm's PID (if running), or from the
|
||
|
|
+ * namespace we're in (if @vm's not running).
|
||
|
|
*
|
||
|
|
* Returns 0 on success, -1 otherwise (with error reported)
|
||
|
|
*/
|
||
|
|
@@ -124,12 +126,18 @@ qemuDomainGetPreservedMounts(virQEMUDriverConfig *cfg,
|
||
|
|
size_t nmounts = 0;
|
||
|
|
g_auto(GStrv) paths = NULL;
|
||
|
|
g_auto(GStrv) savePaths = NULL;
|
||
|
|
+ g_autofree char *mountsPath = NULL;
|
||
|
|
size_t i;
|
||
|
|
|
||
|
|
if (ndevPath)
|
||
|
|
*ndevPath = 0;
|
||
|
|
|
||
|
|
- if (virFileGetMountSubtree(QEMU_PROC_MOUNTS, "/dev", &mounts, &nmounts) < 0)
|
||
|
|
+ if (vm->pid > 0)
|
||
|
|
+ mountsPath = g_strdup_printf("/proc/%lld/mounts", (long long) vm->pid);
|
||
|
|
+ else
|
||
|
|
+ mountsPath = g_strdup(QEMU_PROC_MOUNTS);
|
||
|
|
+
|
||
|
|
+ if (virFileGetMountSubtree(mountsPath, "/dev", &mounts, &nmounts) < 0)
|
||
|
|
return -1;
|
||
|
|
|
||
|
|
if (nmounts == 0)
|
||
|
|
--
|
||
|
|
2.38.0
|
||
|
|
|