all lists on lists.proxmox.com
 help / color / mirror / Atom feed
From: Thomas Lamprecht <t.lamprecht@proxmox.com>
To: pve-devel@lists.proxmox.com
Subject: [PATCH cluster 01/34] pmxcfs: reject changes to the cluster ID file from user space
Date: Mon, 16 Nov 2026 01:46:13 +0100	[thread overview]
Message-ID: <20261116004703.2908294-2-t.lamprecht@proxmox.com> (raw)
In-Reply-To: <20261116004703.2908294-1-t.lamprecht@proxmox.com>

The cluster ID identifies a cluster or standalone node and must remain
stable during normal operation. Reserve /etc/pve/cluster-id for pmxcfs
by rejecting local changes to its content and stored metadata with
EACCES, and report the file as read-only.

Protect timestamps too: changing them updates the entry's version and
writer and replicates like a content change. Keep the existing chmod
and chown behavior, which does not change stored data.

Allow rmdir to remove a directory left at this path by an older node;
otherwise it would prevent ID generation. The kernel already rejects
rmdir on the regular file.

Cluster-delivered operations bypass these local filesystem guards, so
the ID still replicates normally, including between mixed versions.

Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
 src/pmxcfs/cfs-plug-memdb.c | 42 ++++++++++++++++++
 src/pmxcfs/cfs-utils.c      |  8 ++++
 src/pmxcfs/cfs-utils.h      |  4 ++
 src/pmxcfs/check_memdb.c    | 86 +++++++++++++++++++++++++++++++++++++
 4 files changed, 140 insertions(+)

diff --git a/src/pmxcfs/cfs-plug-memdb.c b/src/pmxcfs/cfs-plug-memdb.c
index dd32684..6040017 100644
--- a/src/pmxcfs/cfs-plug-memdb.c
+++ b/src/pmxcfs/cfs-plug-memdb.c
@@ -129,6 +129,10 @@ static int cfs_plug_memdb_getattr(cfs_plug_t *plug, const char *path, struct sta
 
     if (te) {
         tree_entry_stat(te, stbuf, cfs_is_quorate());
+        /* user space can change neither the content nor the stored metadata of the ID file */
+        if (path_is_cluster_id(path)) {
+            stbuf->st_mode &= ~(S_IWUSR | S_IWGRP | S_IWOTH);
+        }
         memdb_tree_entry_free(te);
         return 0;
     }
@@ -186,6 +190,12 @@ static int cfs_plug_memdb_open(cfs_plug_t *plug, const char *path, struct fuse_f
     g_return_val_if_fail(path != NULL, PARAM_CHECK_ERRNO);
     g_return_val_if_fail(fi != NULL, PARAM_CHECK_ERRNO);
 
+    /* only affects local user space, dcdb applies the operations of other nodes directly */
+    if (path_is_cluster_id(path) &&
+        ((fi->flags & O_ACCMODE) != O_RDONLY || (fi->flags & (O_TRUNC | O_APPEND)))) {
+        return -EACCES;
+    }
+
     memdb_tree_entry_t *te;
 
     cfs_plug_memdb_t *mdb = (cfs_plug_memdb_t *)plug;
@@ -255,6 +265,10 @@ static int cfs_plug_memdb_write(
     g_return_val_if_fail(path != NULL, PARAM_CHECK_ERRNO);
     g_return_val_if_fail(buf != NULL, PARAM_CHECK_ERRNO);
 
+    if (path_is_cluster_id(path)) {
+        return -EACCES;
+    }
+
     int res;
 
     cfs_plug_memdb_t *mdb = (cfs_plug_memdb_t *)plug;
@@ -276,6 +290,10 @@ static int cfs_plug_memdb_truncate(cfs_plug_t *plug, const char *path, off_t siz
     g_return_val_if_fail(plug->ops == &cfs_ops, PARAM_CHECK_ERRNO);
     g_return_val_if_fail(path != NULL, PARAM_CHECK_ERRNO);
 
+    if (path_is_cluster_id(path)) {
+        return -EACCES;
+    }
+
     int res;
 
     cfs_plug_memdb_t *mdb = (cfs_plug_memdb_t *)plug;
@@ -298,6 +316,10 @@ cfs_plug_memdb_create(cfs_plug_t *plug, const char *path, mode_t mode, struct fu
     g_return_val_if_fail(path != NULL, PARAM_CHECK_ERRNO);
     g_return_val_if_fail(fi != NULL, PARAM_CHECK_ERRNO);
 
+    if (path_is_cluster_id(path)) {
+        return -EACCES;
+    }
+
     int res;
 
     cfs_plug_memdb_t *mdb = (cfs_plug_memdb_t *)plug;
@@ -318,6 +340,10 @@ static int cfs_plug_memdb_mkdir(cfs_plug_t *plug, const char *path, mode_t mode)
     g_return_val_if_fail(plug->ops == &cfs_ops, PARAM_CHECK_ERRNO);
     g_return_val_if_fail(path != NULL, PARAM_CHECK_ERRNO);
 
+    if (path_is_cluster_id(path)) {
+        return -EACCES;
+    }
+
     int res;
 
     cfs_plug_memdb_t *mdb = (cfs_plug_memdb_t *)plug;
@@ -337,6 +363,10 @@ static int cfs_plug_memdb_rmdir(cfs_plug_t *plug, const char *path) {
     g_return_val_if_fail(plug->ops == &cfs_ops, PARAM_CHECK_ERRNO);
     g_return_val_if_fail(path != NULL, PARAM_CHECK_ERRNO);
 
+    /* no cluster ID check: the kernel refuses rmdir on the regular file, and a directory that a
+     * node without the check created at that path must stay removable, as it keeps the ID from
+     * being written */
+
     int res;
 
     cfs_plug_memdb_t *mdb = (cfs_plug_memdb_t *)plug;
@@ -357,6 +387,10 @@ static int cfs_plug_memdb_rename(cfs_plug_t *plug, const char *from, const char
     g_return_val_if_fail(from != NULL, PARAM_CHECK_ERRNO);
     g_return_val_if_fail(to != NULL, PARAM_CHECK_ERRNO);
 
+    if (path_is_cluster_id(from) || path_is_cluster_id(to)) {
+        return -EACCES;
+    }
+
     int res;
 
     cfs_plug_memdb_t *mdb = (cfs_plug_memdb_t *)plug;
@@ -376,6 +410,10 @@ static int cfs_plug_memdb_unlink(cfs_plug_t *plug, const char *path) {
     g_return_val_if_fail(plug->ops == &cfs_ops, PARAM_CHECK_ERRNO);
     g_return_val_if_fail(path != NULL, PARAM_CHECK_ERRNO);
 
+    if (path_is_cluster_id(path)) {
+        return -EACCES;
+    }
+
     int res;
 
     cfs_plug_memdb_t *mdb = (cfs_plug_memdb_t *)plug;
@@ -396,6 +434,10 @@ static int cfs_plug_memdb_utimens(cfs_plug_t *plug, const char *path, const stru
     g_return_val_if_fail(path != NULL, PARAM_CHECK_ERRNO);
     g_return_val_if_fail(tv != NULL, PARAM_CHECK_ERRNO);
 
+    if (path_is_cluster_id(path)) {
+        return -EACCES;
+    }
+
     int res;
 
     cfs_plug_memdb_t *mdb = (cfs_plug_memdb_t *)plug;
diff --git a/src/pmxcfs/cfs-utils.c b/src/pmxcfs/cfs-utils.c
index db5e3ed..7527324 100644
--- a/src/pmxcfs/cfs-utils.c
+++ b/src/pmxcfs/cfs-utils.c
@@ -339,3 +339,11 @@ gboolean path_is_lockdir(const char *path) {
 
     return (strncmp(path, "priv/lock/", 10) == 0) && path[10];
 }
+
+gboolean path_is_cluster_id(const char *path) {
+    size_t len;
+    const char *component = path_next_component(&path, &len);
+
+    return component && path_component_is(component, len, CFS_CLUSTER_ID_FN) &&
+           !path_next_component(&path, &len);
+}
diff --git a/src/pmxcfs/cfs-utils.h b/src/pmxcfs/cfs-utils.h
index ed67264..175be38 100644
--- a/src/pmxcfs/cfs-utils.h
+++ b/src/pmxcfs/cfs-utils.h
@@ -34,6 +34,8 @@
 #define VARLIBDIR "/var/lib/pve-cluster"
 #define RUNDIR "/run/pve-cluster"
 
+#define CFS_CLUSTER_ID_FN "cluster-id"
+
 #define CFS_MAX(a, b) (((a) > (b)) ? (a) : (b))
 #define CFS_MIN(a, b) (((a) < (b)) ? (a) : (b))
 
@@ -98,4 +100,6 @@ gboolean path_is_lxc_conf(const char *path);
 
 gboolean path_is_lockdir(const char *path);
 
+gboolean path_is_cluster_id(const char *path);
+
 #endif /* _PVE_CFS_UTILS_H_ */
diff --git a/src/pmxcfs/check_memdb.c b/src/pmxcfs/check_memdb.c
index f21abd0..1ca1372 100644
--- a/src/pmxcfs/check_memdb.c
+++ b/src/pmxcfs/check_memdb.c
@@ -26,6 +26,7 @@
 #include <string.h>
 #include <unistd.h>
 
+#include "cfs-plug-memdb.h"
 #include "cfs-utils.h"
 #include "memdb.h"
 #include "status.h"
@@ -220,6 +221,87 @@ START_TEST(test_version_and_members_json) {
 }
 END_TEST
 
+START_TEST(test_path_is_cluster_id) {
+    ck_assert(path_is_cluster_id("cluster-id"));
+    ck_assert(path_is_cluster_id("/cluster-id"));
+    ck_assert(path_is_cluster_id("//cluster-id/"));
+
+    ck_assert(!path_is_cluster_id(""));
+    ck_assert(!path_is_cluster_id("/"));
+    ck_assert(!path_is_cluster_id("cluster-i"));
+    ck_assert(!path_is_cluster_id("cluster-id.new"));
+    ck_assert(!path_is_cluster_id("cluster-id/x"));
+    ck_assert(!path_is_cluster_id("nodes/n1/cluster-id"));
+}
+END_TEST
+
+START_TEST(test_cluster_id_fuse_read_only) {
+    time_t ctime = 1234;
+    const char *id = "abcdefghijklmnopqrst\n";
+    gpointer data;
+    struct fuse_file_info fi = {0};
+    struct fuse_file_info fi_write = {.flags = O_WRONLY};
+    struct fuse_file_info fi_trunc = {.flags = O_RDONLY | O_TRUNC};
+    struct fuse_file_info fi_append = {.flags = O_RDONLY | O_APPEND};
+    struct timespec tv[2] = {{.tv_sec = 42}, {.tv_sec = 42}};
+    struct stat stbuf;
+
+    cfs_plug_t *plug = (cfs_plug_t *)cfs_plug_memdb_new("memdb", memdb, NULL);
+    ck_assert(plug != NULL);
+
+    ck_assert(plug->ops->create(plug, "cluster-id", 0644, &fi) == -EACCES);
+    ck_assert(plug->ops->mkdir(plug, "cluster-id", 0755) == -EACCES);
+    ck_assert(memdb_read(memdb, "cluster-id", &data) == -ENOENT);
+
+    /* pmxcfs itself goes to the memdb directly */
+    ck_assert(memdb_create(memdb, "cluster-id", 0, ctime) == 0);
+    ck_assert(memdb_write(memdb, "cluster-id", 0, ctime, id, 21, 0, 1) == 21);
+
+    memdb_tree_entry_t *before = memdb_getattr(memdb, "cluster-id");
+    ck_assert(before != NULL);
+
+    ck_assert(plug->ops->open(plug, "cluster-id", &fi) == 0);
+    ck_assert(plug->ops->open(plug, "cluster-id", &fi_write) == -EACCES);
+    ck_assert(plug->ops->open(plug, "cluster-id", &fi_trunc) == -EACCES);
+    ck_assert(plug->ops->open(plug, "cluster-id", &fi_append) == -EACCES);
+    ck_assert(plug->ops->write(plug, "cluster-id", "x", 1, 0, &fi) == -EACCES);
+    ck_assert(plug->ops->truncate(plug, "cluster-id", 0) == -EACCES);
+    ck_assert(plug->ops->unlink(plug, "cluster-id") == -EACCES);
+    ck_assert(plug->ops->rename(plug, "cluster-id", "moved") == -EACCES);
+    ck_assert(plug->ops->mkdir(plug, "cluster-id", 0755) == -EACCES);
+    ck_assert(plug->ops->utimens(plug, "cluster-id", tv) == -EACCES);
+
+    ck_assert(plug->ops->create(plug, "other", 0644, &fi) == 0);
+    ck_assert(plug->ops->write(plug, "other", "x", 1, 0, &fi) == 1);
+    ck_assert(plug->ops->rename(plug, "other", "cluster-id") == -EACCES);
+
+    ck_assert(memdb_read(memdb, "cluster-id", &data) == 21);
+    ck_assert(memcmp(data, id, 21) == 0);
+    g_free(data);
+
+    /* not even the metadata changed */
+    memdb_tree_entry_t *after = memdb_getattr(memdb, "cluster-id");
+    ck_assert(after != NULL);
+    ck_assert(after->version == before->version);
+    ck_assert(after->mtime == before->mtime);
+    memdb_tree_entry_free(before);
+    memdb_tree_entry_free(after);
+
+    cfs_set_quorate(1, TRUE);
+    ck_assert(plug->ops->getattr(plug, "cluster-id", &stbuf) == 0);
+    ck_assert((stbuf.st_mode & 0777) == 0444);
+    ck_assert(plug->ops->getattr(plug, "other", &stbuf) == 0);
+    ck_assert((stbuf.st_mode & 0777) == 0666);
+
+    /* a directory at the path, as a node without the check can create, stays removable */
+    ck_assert(memdb_delete(memdb, "cluster-id", 0, ctime) == 0);
+    ck_assert(memdb_mkdir(memdb, "cluster-id", 0, ctime) == 0);
+    ck_assert(plug->ops->rmdir(plug, "cluster-id") == 0);
+
+    plug->destroy_plug(plug);
+}
+END_TEST
+
 START_TEST(test_truncate_grow) {
     const char *fn = "/f1";
     time_t ctime = 1234;
@@ -504,6 +586,10 @@ static Suite *memdb_suite(void) {
 
     add_test(s, test_guest_config_properties_last_wins, "guest_config_properties_last_wins");
 
+    add_test(s, test_path_is_cluster_id, "path_is_cluster_id");
+
+    add_test(s, test_cluster_id_fuse_read_only, "cluster_id_fuse_read_only");
+
     add_test(s, test_indextest1, "indextest1");
 
     add_test(s, test_loaddb1, "loaddb1");
-- 
2.47.3





  reply	other threads:[~2026-11-16  0:48 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-16  0:46 [PATCH cluster/guest-common/qemu-server/container/manager/docs 00/34] fix #7846: guest identity (uid) and cluster ID Thomas Lamprecht
2026-11-16  0:46 ` Thomas Lamprecht [this message]
2026-11-16  0:46 ` [PATCH cluster 02/34] pmxcfs: generate a cluster ID on standalone nodes Thomas Lamprecht
2026-11-16  0:46 ` [PATCH cluster 03/34] pmxcfs: dfsm: add a callback that runs once all members are in sync Thomas Lamprecht
2026-11-16  0:46 ` [PATCH cluster 04/34] pmxcfs: quorum: pass the corosync membership to an optional listener Thomas Lamprecht
2026-11-16  0:46 ` [PATCH cluster 05/34] pmxcfs: dcdb: generate the cluster ID once the cluster is in sync Thomas Lamprecht
2026-11-16  0:46 ` [PATCH cluster 06/34] cluster: add helper to read the cluster ID Thomas Lamprecht
2026-11-16  0:46 ` [PATCH cluster 07/34] pmxcfs: allow removing the cluster ID file in forced local mode Thomas Lamprecht
2026-11-16  0:46 ` [PATCH guest-common 08/34] guest identity: add helpers for the guest uid and registration time Thomas Lamprecht
2026-11-17 10:47   ` Dominik Csapak
2026-11-16  0:46 ` [PATCH guest-common 09/34] abstract config: assign a guest identity and keep it on config writes Thomas Lamprecht
2026-11-17 10:47   ` Dominik Csapak
2026-11-17 12:47     ` Dominik Csapak
2026-11-16  0:46 ` [PATCH guest-common 10/34] abstract config: let the VMID reservation return the previous state Thomas Lamprecht
2026-11-16  0:46 ` [PATCH guest-common 11/34] guest identity: allow taking over a uid that is unused in the cluster Thomas Lamprecht
2026-11-17 13:14   ` Dominik Csapak
2026-11-16  0:46 ` [PATCH qemu-server 12/34] api: restore: release the VMID if a restore to an unused VMID fails Thomas Lamprecht
2026-11-16  0:46 ` [PATCH qemu-server 13/34] api: migrate, clone: refuse targets that would drop the guest identity Thomas Lamprecht
2026-11-16  0:46 ` [PATCH qemu-server 14/34] fix #7846: config: add a guest identity to the 'meta' property Thomas Lamprecht
2026-11-16  0:46 ` [PATCH qemu-server 15/34] restore: take over the guest uid from the backup where possible Thomas Lamprecht
2026-11-17 15:17   ` Dominik Csapak
2026-11-16  0:46 ` [PATCH qemu-server 16/34] api: remote migration: take over the guest uid from the source Thomas Lamprecht
2026-11-17 15:26   ` Dominik Csapak
2026-11-16  0:46 ` [PATCH qemu-server 17/34] api: status: return the guest uid Thomas Lamprecht
2026-11-16  0:46 ` [PATCH container 18/34] config: add read-only meta property with the creation time Thomas Lamprecht
2026-11-16  0:46 ` [PATCH container 19/34] fix #7846: config: add a guest identity to the 'meta' property Thomas Lamprecht
2026-11-16  0:46 ` [PATCH container 20/34] api: migrate, clone: refuse targets that would drop the guest identity Thomas Lamprecht
2026-11-16  0:46 ` [PATCH container 21/34] restore: take over the guest uid from the backup where possible Thomas Lamprecht
2026-11-16  0:46 ` [PATCH container 22/34] restore: refuse overwriting a container with another guest's backup Thomas Lamprecht
2026-11-16  0:46 ` [PATCH container 23/34] migrate: remote: clean up the target on a tunnel version mismatch Thomas Lamprecht
2026-11-16  0:46 ` [PATCH container 24/34] api: remote migration: take over the guest uid from the source Thomas Lamprecht
2026-11-16  0:46 ` [PATCH container 25/34] api: status: return the guest uid Thomas Lamprecht
2026-11-16  0:46 ` [PATCH manager 26/34] api: cluster resources: add guest uid and registration time Thomas Lamprecht
2026-11-17 15:30   ` Dominik Csapak
2026-11-16  0:46 ` [PATCH manager 27/34] api: cluster status: add cluster ID Thomas Lamprecht
2026-11-16  0:46 ` [PATCH manager 28/34] ui: restore: allow overwriting a guest with a backup of another guest Thomas Lamprecht
2026-11-16  0:46 ` [PATCH manager 29/34] ui: migrate: refuse target nodes that would drop the guest identity Thomas Lamprecht
2026-11-16  0:46 ` [PATCH manager 30/34] ui: guest summary: show " Thomas Lamprecht
2026-11-17 15:44   ` Dominik Csapak
2026-11-16  0:46 ` [PATCH docs 31/34] vzdump: describe the guest identity of VMs and containers Thomas Lamprecht
2026-11-16  0:46 ` [PATCH docs 32/34] pvecm: document the cluster ID and how to get a new one Thomas Lamprecht
2026-11-16  0:46 ` [PATCH docs 33/34] qm: configuration: describe the read-only meta property Thomas Lamprecht
2026-11-16  0:46 ` [PATCH docs 34/34] pct: " Thomas Lamprecht
2026-11-17 10:47 ` [PATCH cluster/guest-common/qemu-server/container/manager/docs 00/34] fix #7846: guest identity (uid) and cluster ID Dominik Csapak
2026-11-17 11:29   ` Thomas Lamprecht
2026-11-17 11:55     ` Dominik Csapak
2026-11-17 12:47       ` Thomas Lamprecht
2026-11-17 13:54         ` Dominik Csapak
2026-11-17 15:55 ` Dominik Csapak

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261116004703.2908294-2-t.lamprecht@proxmox.com \
    --to=t.lamprecht@proxmox.com \
    --cc=pve-devel@lists.proxmox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.
Service provided by Proxmox Server Solutions GmbH | Privacy | Legal