[PATCH] Avoid hidden cgroup mount points

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Currently the scan of the /proc/mounts file used to find cgroup mount
points doesn't take into account that mount points may hidden by other
mount points. For, example in certain Kubernetes environments the
/proc/mounts contains the following lines:

  cgroup /sys/fs/cgroup/net_prio,net_cls cgroup ...
  tmpfs /sys/fs/cgroup tmpfs ...
  cgroup /sys/fs/cgroup/net_cls,net_prio cgroup ...

In this particular environment the first mount point is hidden by the
second one. The correct mount point is the third one, but libvirt will
never process it because it only checks the first mount point for each
controller (net_cls in this case). So libvirt will try to use the first
mount point, which doesn't actually exist, and the complete detection
process will fail.

To avoid that issue this patch changes the virCgroupDetectMountsFromFile
function so that when there are duplicates it takes the information from
the last line in /proc/mounts. This requires removing the previous
explicit condition to skip duplicates, and adding code to free the
memory used by the processing of duplicated lines.

Related-To: https://bugzilla.redhat.com/1468214
Related-To: https://github.com/kubevirt/libvirt/issues/4
Signed-off-by: Juan Hernandez <jhernand@xxxxxxxxxx>
---
 src/util/vircgroup.c                | 23 ++++++++++++++---------
 tests/vircgroupdata/kubevirt.mounts | 36 ++++++++++++++++++++++++++++++++++++
 tests/vircgroupdata/kubevirt.parsed | 10 ++++++++++
 tests/vircgrouptest.c               |  1 +
 4 files changed, 61 insertions(+), 9 deletions(-)
 create mode 100644 tests/vircgroupdata/kubevirt.mounts
 create mode 100644 tests/vircgroupdata/kubevirt.parsed

diff --git a/src/util/vircgroup.c b/src/util/vircgroup.c
index 5aa1db5..41d90e7 100644
--- a/src/util/vircgroup.c
+++ b/src/util/vircgroup.c
@@ -397,6 +397,7 @@ virCgroupDetectMountsFromFile(virCgroupPtr group,
             const char *typestr = virCgroupControllerTypeToString(i);
             int typelen = strlen(typestr);
             char *tmp = entry.mnt_opts;
+            struct virCgroupController *controller = &group->controllers[i];
             while (tmp) {
                 char *next = strchr(tmp, ',');
                 int len;
@@ -406,18 +407,21 @@ virCgroupDetectMountsFromFile(virCgroupPtr group,
                 } else {
                     len = strlen(tmp);
                 }
-                /* NB, the same controller can appear >1 time in mount list
-                 * due to bind mounts from one location to another. Pick the
-                 * first entry only
-                 */
-                if (typelen == len && STREQLEN(typestr, tmp, len) &&
-                    !group->controllers[i].mountPoint) {
+
+                if (typelen == len && STREQLEN(typestr, tmp, len)) {
                     char *linksrc;
                     struct stat sb;
                     char *tmp2;
 
-                    if (VIR_STRDUP(group->controllers[i].mountPoint,
-                                   entry.mnt_dir) < 0)
+                    /* Note that the lines in /proc/mounts have the same
+                     * order than the mount operations, and that there may
+                     * be duplicates due to bind mounts. This means
+                     * that the same mount point may be processed more than
+                     * once. We need to save the results of the last one,
+                     * and we need to be careful to release the memory used
+                     * by previous processing. */
+                    VIR_FREE(controller->mountPoint);
+                    if (VIR_STRDUP(controller->mountPoint, entry.mnt_dir) < 0)
                         goto error;
 
                     tmp2 = strrchr(entry.mnt_dir, '/');
@@ -453,7 +457,8 @@ virCgroupDetectMountsFromFile(virCgroupPtr group,
                                 VIR_WARN("Expecting a symlink at %s for controller %s",
                                          linksrc, typestr);
                             } else {
-                                group->controllers[i].linkPoint = linksrc;
+                                VIR_FREE(controller->linkPoint);
+                                controller->linkPoint = linksrc;
                             }
                         }
                     }
diff --git a/tests/vircgroupdata/kubevirt.mounts b/tests/vircgroupdata/kubevirt.mounts
new file mode 100644
index 0000000..b0d31bb
--- /dev/null
+++ b/tests/vircgroupdata/kubevirt.mounts
@@ -0,0 +1,36 @@
+tmpfs /sys/fs/cgroup tmpfs rw,nosuid,nodev,noexec,relatime,mode=755 0 0
+cgroup /sys/fs/cgroup/systemd cgroup rw,nosuid,nodev,noexec,relatime,xattr,release_agent=/usr/lib/systemd/systemd-cgroups-agent,name=systemd 0 0
+cgroup /sys/fs/cgroup/cpuacct,cpu cgroup rw,nosuid,nodev,noexec,relatime,cpuacct,cpu 0 0
+cgroup /sys/fs/cgroup/pids cgroup rw,nosuid,nodev,noexec,relatime,pids 0 0
+cgroup /sys/fs/cgroup/blkio cgroup rw,nosuid,nodev,noexec,relatime,blkio 0 0
+cgroup /sys/fs/cgroup/cpuset cgroup rw,nosuid,nodev,noexec,relatime,cpuset 0 0
+cgroup /sys/fs/cgroup/memory cgroup rw,nosuid,nodev,noexec,relatime,memory 0 0
+cgroup /sys/fs/cgroup/hugetlb cgroup rw,nosuid,nodev,noexec,relatime,hugetlb 0 0
+cgroup /sys/fs/cgroup/devices cgroup rw,nosuid,nodev,noexec,relatime,devices 0 0
+cgroup /sys/fs/cgroup/freezer cgroup rw,nosuid,nodev,noexec,relatime,freezer 0 0
+cgroup /sys/fs/cgroup/perf_event cgroup rw,nosuid,nodev,noexec,relatime,perf_event 0 0
+cgroup /sys/fs/cgroup/net_prio,net_cls cgroup rw,nosuid,nodev,noexec,relatime,net_prio,net_cls 0 0
+tmpfs /host-sys/fs/cgroup tmpfs ro,nosuid,nodev,noexec,relatime,mode=755 0 0
+cgroup /host-sys/fs/cgroup/systemd cgroup rw,nosuid,nodev,noexec,relatime,xattr,release_agent=/usr/lib/systemd/systemd-cgroups-agent,name=systemd 0 0
+cgroup /host-sys/fs/cgroup/cpu,cpuacct cgroup rw,nosuid,nodev,noexec,relatime,cpuacct,cpu 0 0
+cgroup /host-sys/fs/cgroup/pids cgroup rw,nosuid,nodev,noexec,relatime,pids 0 0
+cgroup /host-sys/fs/cgroup/blkio cgroup rw,nosuid,nodev,noexec,relatime,blkio 0 0
+cgroup /host-sys/fs/cgroup/cpuset cgroup rw,nosuid,nodev,noexec,relatime,cpuset 0 0
+cgroup /host-sys/fs/cgroup/memory cgroup rw,nosuid,nodev,noexec,relatime,memory 0 0
+cgroup /host-sys/fs/cgroup/hugetlb cgroup rw,nosuid,nodev,noexec,relatime,hugetlb 0 0
+cgroup /host-sys/fs/cgroup/devices cgroup rw,nosuid,nodev,noexec,relatime,devices 0 0
+cgroup /host-sys/fs/cgroup/freezer cgroup rw,nosuid,nodev,noexec,relatime,freezer 0 0
+cgroup /host-sys/fs/cgroup/perf_event cgroup rw,nosuid,nodev,noexec,relatime,perf_event 0 0
+cgroup /host-sys/fs/cgroup/net_cls,net_prio cgroup rw,nosuid,nodev,noexec,relatime,net_prio,net_cls 0 0
+tmpfs /sys/fs/cgroup tmpfs ro,nosuid,nodev,noexec,relatime,mode=755 0 0
+cgroup /sys/fs/cgroup/systemd cgroup rw,nosuid,nodev,noexec,relatime,xattr,release_agent=/usr/lib/systemd/systemd-cgroups-agent,name=systemd 0 0
+cgroup /sys/fs/cgroup/cpu,cpuacct cgroup rw,nosuid,nodev,noexec,relatime,cpuacct,cpu 0 0
+cgroup /sys/fs/cgroup/pids cgroup rw,nosuid,nodev,noexec,relatime,pids 0 0
+cgroup /sys/fs/cgroup/blkio cgroup rw,nosuid,nodev,noexec,relatime,blkio 0 0
+cgroup /sys/fs/cgroup/cpuset cgroup rw,nosuid,nodev,noexec,relatime,cpuset 0 0
+cgroup /sys/fs/cgroup/memory cgroup rw,nosuid,nodev,noexec,relatime,memory 0 0
+cgroup /sys/fs/cgroup/hugetlb cgroup rw,nosuid,nodev,noexec,relatime,hugetlb 0 0
+cgroup /sys/fs/cgroup/devices cgroup rw,nosuid,nodev,noexec,relatime,devices 0 0
+cgroup /sys/fs/cgroup/freezer cgroup rw,nosuid,nodev,noexec,relatime,freezer 0 0
+cgroup /sys/fs/cgroup/perf_event cgroup rw,nosuid,nodev,noexec,relatime,perf_event 0 0
+cgroup /sys/fs/cgroup/net_cls,net_prio cgroup rw,nosuid,nodev,noexec,relatime,net_prio,net_cls 0 0
diff --git a/tests/vircgroupdata/kubevirt.parsed b/tests/vircgroupdata/kubevirt.parsed
new file mode 100644
index 0000000..3377af0
--- /dev/null
+++ b/tests/vircgroupdata/kubevirt.parsed
@@ -0,0 +1,10 @@
+cpu          /sys/fs/cgroup/cpu,cpuacct
+cpuacct      /sys/fs/cgroup/cpu,cpuacct
+cpuset       /sys/fs/cgroup/cpuset
+memory       /sys/fs/cgroup/memory
+devices      /sys/fs/cgroup/devices
+freezer      /sys/fs/cgroup/freezer
+blkio        /sys/fs/cgroup/blkio
+net_cls      /sys/fs/cgroup/net_cls,net_prio
+perf_event   /sys/fs/cgroup/perf_event
+name=systemd /sys/fs/cgroup/systemd
diff --git a/tests/vircgrouptest.c b/tests/vircgrouptest.c
index 8af5e2c..b932b1a 100644
--- a/tests/vircgrouptest.c
+++ b/tests/vircgrouptest.c
@@ -885,6 +885,7 @@ mymain(void)
     DETECT_MOUNTS("cgroups3");
     DETECT_MOUNTS("all-in-one");
     DETECT_MOUNTS("no-cgroups");
+    DETECT_MOUNTS("kubevirt");
 
     if (virTestRun("New cgroup for self", testCgroupNewForSelf, NULL) < 0)
         ret = -1;
-- 
2.9.4

--
libvir-list mailing list
libvir-list@xxxxxxxxxx
https://www.redhat.com/mailman/listinfo/libvir-list



[Index of Archives]     [Virt Tools]     [Libvirt Users]     [Lib OS Info]     [Fedora Users]     [Fedora Desktop]     [Fedora SELinux]     [Big List of Linux Books]     [Yosemite News]     [KDE Users]     [Fedora Tools]
  Powered by Linux