-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From 55e20fb88be7512c80baa7514bc815e4cec4d22c Mon Sep 17 00:00:00 2001
From: Wolfgang Bumiller <w.bumiller@proxmox.com>
Date: Fri, 10 Feb 2017 09:13:40 +0100
-Subject: [PATCH] PVE: [Config] lxc.service: start after a potential
+Subject: [PATCH lxc 1/3] PVE: [Config] lxc.service: start after a potential
syslog.service
+We could add this as a snippet from pve-container instead.
+
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
---
config/init/systemd/lxc.service.in | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/config/init/systemd/lxc.service.in b/config/init/systemd/lxc.service.in
-index cd6199671..77541917e 100644
+index e3745dc2d..fbe46f1d7 100644
--- a/config/init/systemd/lxc.service.in
+++ b/config/init/systemd/lxc.service.in
@@ -1,6 +1,6 @@
[Unit]
Description=LXC Container Initialization and Autoboot Code
--After=network.target lxc-net.service
-+After=syslog.service network.target lxc-net.service
+-After=network.target lxc-net.service remote-fs.target
++After=network.target lxc-net.service remote-fs.target syslog.target
Wants=lxc-net.service
Documentation=man:lxc-autostart man:lxc
--- /dev/null
+From a1a53a511f065d68520337cbbba627b4164da865 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Fabian=20Gr=C3=BCnbichler?= <f.gruenbichler@proxmox.com>
+Date: Wed, 9 Nov 2016 09:14:26 +0100
+Subject: [PATCH lxc 2/3] PVE: [Config] deny rw mounting of /sys and /proc
+
+Note that we don't actually make use of this anymore, since
+we switched to the generated profiles which already do this.
+
+this would allow root in a privileged container to change
+the permissions of /sys on the host, which could lock out
+non-root users.
+
+if a rw /sys is desired, set "lxc.mount.auto" accordingly
+---
+ config/apparmor/abstractions/container-base | 6 +++++-
+ config/apparmor/abstractions/container-base.in | 6 +++++-
+ 2 files changed, 10 insertions(+), 2 deletions(-)
+
+diff --git a/config/apparmor/abstractions/container-base b/config/apparmor/abstractions/container-base
+index 077476559..fbd70fdf5 100644
+--- a/config/apparmor/abstractions/container-base
++++ b/config/apparmor/abstractions/container-base
+@@ -82,7 +82,6 @@
+ deny mount fstype=debugfs -> /var/lib/ureadahead/debugfs/,
+ mount fstype=proc -> /proc/,
+ mount fstype=sysfs -> /sys/,
+- mount options=(rw, nosuid, nodev, noexec, remount) -> /sys/,
+ deny /sys/firmware/efi/efivars/** rwklx,
+ deny /sys/kernel/security/** rwklx,
+ mount options=(move) /sys/fs/cgroup/cgmanager/ -> /sys/fs/cgroup/cgmanager.lower/,
+@@ -91,6 +90,11 @@
+ # deny reads from debugfs
+ deny /sys/kernel/debug/{,**} rwklx,
+
++ # prevent rw mounting of /sys, because that allows changing its global permissions
++ deny mount -> /proc/,
++ deny mount -> /sys/,
++# mount options=(rw, nosuid, nodev, noexec, remount) -> /sys/,
++
+ # allow paths to be made slave, shared, private or unbindable
+ # FIXME: This currently doesn't work due to the apparmor parser treating those as allowing all mounts.
+ # mount options=(rw,make-slave) -> **,
+diff --git a/config/apparmor/abstractions/container-base.in b/config/apparmor/abstractions/container-base.in
+index 2606fb64c..3e61c62ea 100644
+--- a/config/apparmor/abstractions/container-base.in
++++ b/config/apparmor/abstractions/container-base.in
+@@ -83,7 +83,6 @@
+ deny mount fstype=debugfs -> /var/lib/ureadahead/debugfs/,
+ mount fstype=proc -> /proc/,
+ mount fstype=sysfs -> /sys/,
+- mount options=(rw, nosuid, nodev, noexec, remount) -> /sys/,
+ deny /sys/firmware/efi/efivars/** rwklx,
+ deny /sys/kernel/security/** rwklx,
+ mount options=(ro, nosuid, nodev, noexec, remount, strictatime) -> /sys/fs/cgroup/,
+@@ -91,6 +90,11 @@
+ # deny reads from debugfs
+ deny /sys/kernel/debug/{,**} rwklx,
+
++ # prevent rw mounting of /sys, because that allows changing its global permissions
++ deny mount -> /proc/,
++ deny mount -> /sys/,
++# mount options=(rw, nosuid, nodev, noexec, remount) -> /sys/,
++
+ # allow paths to be made slave, shared, private or unbindable
+ # FIXME: This currently doesn't work due to the apparmor parser treating those as allowing all mounts.
+ # mount options=(rw,make-slave) -> **,
+--
+2.20.1
+
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Fri, 10 Feb 2017 09:15:37 +0100
-Subject: [PATCH] PVE: [Down] run lxcnetaddbr when instantiating veths
-
-FIXME: Why aren't we using regular up-scripts?
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- src/lxc/network.c | 5 +++++
- 1 file changed, 5 insertions(+)
-
-diff --git a/src/lxc/network.c b/src/lxc/network.c
-index 65727f6b5..cd8d0bb14 100644
---- a/src/lxc/network.c
-+++ b/src/lxc/network.c
-@@ -503,6 +503,11 @@ static int instantiate_veth(struct lxc_handler *handler, struct lxc_netdev *netd
- netdev->upscript, "up", argv);
- if (err < 0)
- goto out_delete;
-+ } else if (netdev->link[0] == '\0') {
-+ err = run_script(handler->name, "net", "/usr/share/lxc/lxcnetaddbr", "up",
-+ "veth", veth1, (char*) NULL);
-+ if (err)
-+ goto out_delete;
- }
-
- DEBUG("Instantiated veth \"%s/%s\", index is \"%d\"", veth1, veth2,
---
-2.20.1
-
--- /dev/null
+From 08f4569b8f5fb9769ed6a76ddd1040a577d0b2fe Mon Sep 17 00:00:00 2001
+From: Wolfgang Bumiller <w.bumiller@proxmox.com>
+Date: Tue, 13 Aug 2019 13:57:22 +0200
+Subject: [PATCH lxc 3/3] PVE: [Config] attach: always use getent
+
+In debian buster, some libnss plugins (if installed) can
+cause getpwent to segfault instead of erroring out cleanly.
+To avoid this, stick to always using getent.
+
+Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
+---
+ src/lxc/attach.c | 28 ++--------------------------
+ 1 file changed, 2 insertions(+), 26 deletions(-)
+
+diff --git a/src/lxc/attach.c b/src/lxc/attach.c
+index 406b8ec74..0a82c0a5d 100644
+--- a/src/lxc/attach.c
++++ b/src/lxc/attach.c
+@@ -1454,12 +1454,8 @@ int lxc_attach_run_command(void *payload)
+
+ int lxc_attach_run_shell(void* payload)
+ {
+- __do_free char *buf = NULL;
+ uid_t uid;
+- struct passwd pwent;
+- struct passwd *pwentp = NULL;
+ char *user_shell;
+- size_t bufsize;
+ int ret;
+
+ /* Ignore payload parameter. */
+@@ -1467,32 +1463,13 @@ int lxc_attach_run_shell(void* payload)
+
+ uid = getuid();
+
+- bufsize = sysconf(_SC_GETPW_R_SIZE_MAX);
+- if (bufsize == -1)
+- bufsize = 1024;
+-
+- buf = malloc(bufsize);
+- if (buf) {
+- ret = getpwuid_r(uid, &pwent, buf, bufsize, &pwentp);
+- if (!pwentp) {
+- if (ret == 0)
+- WARN("Could not find matched password record");
+-
+- WARN("Failed to get password record - %u", uid);
+- }
+- }
+-
+ /* This probably happens because of incompatible nss implementations in
+ * host and container (remember, this code is still using the host's
+ * glibc but our mount namespace is in the container) we may try to get
+ * the information by spawning a [getent passwd uid] process and parsing
+ * the result.
+ */
+- if (!pwentp)
+- user_shell = lxc_attach_getpwshell(uid);
+- else
+- user_shell = pwent.pw_shell;
+-
++ user_shell = lxc_attach_getpwshell(uid);
+ if (user_shell)
+ execlp(user_shell, user_shell, (char *)NULL);
+
+@@ -1502,8 +1479,7 @@ int lxc_attach_run_shell(void* payload)
+ execlp("/bin/sh", "/bin/sh", (char *)NULL);
+
+ SYSERROR("Failed to execute shell");
+- if (!pwentp)
+- free(user_shell);
++ free(user_shell);
+
+ return -1;
+ }
+--
+2.20.1
+
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: =?UTF-8?q?Fabian=20Gr=C3=BCnbichler?= <f.gruenbichler@proxmox.com>
-Date: Wed, 9 Nov 2016 09:14:26 +0100
-Subject: [PATCH] PVE: [Config] deny rw mounting of /sys and /proc
-
-this would allow root in a privileged container to change
-the permissions of /sys on the host, which could lock out
-non-root users.
-
-if a rw /sys is desired, set "lxc.mount.auto" accordingly
----
- config/apparmor/abstractions/container-base | 6 +++++-
- config/apparmor/abstractions/container-base.in | 6 +++++-
- 2 files changed, 10 insertions(+), 2 deletions(-)
-
-diff --git a/config/apparmor/abstractions/container-base b/config/apparmor/abstractions/container-base
-index 077476559..fbd70fdf5 100644
---- a/config/apparmor/abstractions/container-base
-+++ b/config/apparmor/abstractions/container-base
-@@ -82,7 +82,6 @@
- deny mount fstype=debugfs -> /var/lib/ureadahead/debugfs/,
- mount fstype=proc -> /proc/,
- mount fstype=sysfs -> /sys/,
-- mount options=(rw, nosuid, nodev, noexec, remount) -> /sys/,
- deny /sys/firmware/efi/efivars/** rwklx,
- deny /sys/kernel/security/** rwklx,
- mount options=(move) /sys/fs/cgroup/cgmanager/ -> /sys/fs/cgroup/cgmanager.lower/,
-@@ -91,6 +90,11 @@
- # deny reads from debugfs
- deny /sys/kernel/debug/{,**} rwklx,
-
-+ # prevent rw mounting of /sys, because that allows changing its global permissions
-+ deny mount -> /proc/,
-+ deny mount -> /sys/,
-+# mount options=(rw, nosuid, nodev, noexec, remount) -> /sys/,
-+
- # allow paths to be made slave, shared, private or unbindable
- # FIXME: This currently doesn't work due to the apparmor parser treating those as allowing all mounts.
- # mount options=(rw,make-slave) -> **,
-diff --git a/config/apparmor/abstractions/container-base.in b/config/apparmor/abstractions/container-base.in
-index 2606fb64c..3e61c62ea 100644
---- a/config/apparmor/abstractions/container-base.in
-+++ b/config/apparmor/abstractions/container-base.in
-@@ -83,7 +83,6 @@
- deny mount fstype=debugfs -> /var/lib/ureadahead/debugfs/,
- mount fstype=proc -> /proc/,
- mount fstype=sysfs -> /sys/,
-- mount options=(rw, nosuid, nodev, noexec, remount) -> /sys/,
- deny /sys/firmware/efi/efivars/** rwklx,
- deny /sys/kernel/security/** rwklx,
- mount options=(ro, nosuid, nodev, noexec, remount, strictatime) -> /sys/fs/cgroup/,
-@@ -91,6 +90,11 @@
- # deny reads from debugfs
- deny /sys/kernel/debug/{,**} rwklx,
-
-+ # prevent rw mounting of /sys, because that allows changing its global permissions
-+ deny mount -> /proc/,
-+ deny mount -> /sys/,
-+# mount options=(rw, nosuid, nodev, noexec, remount) -> /sys/,
-+
- # allow paths to be made slave, shared, private or unbindable
- # FIXME: This currently doesn't work due to the apparmor parser treating those as allowing all mounts.
- # mount options=(rw,make-slave) -> **,
---
-2.20.1
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Mon, 20 Nov 2017 10:49:41 +0100
-Subject: [PATCH] PVE: [Up] possibility to run lxc-monitord as a regular daemon
-
-lxc-monitord instances are spawned on demand and, if this
-happens from a service, the daemon is considered part of
-it by systemd, as it is running in the same cgroups. This
-can be avoided by leaving it running permanently.
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- .gitignore | 1 +
- config/init/systemd/Makefile.am | 10 ++--
- config/init/systemd/lxc-monitord.service.in | 12 +++++
- configure.ac | 1 +
- lxc.spec.in | 1 +
- src/lxc/cmd/lxc_monitord.c | 60 +++++++++++++++------
- 6 files changed, 64 insertions(+), 21 deletions(-)
- create mode 100644 config/init/systemd/lxc-monitord.service.in
-
-diff --git a/.gitignore b/.gitignore
-index b2d4657c4..36d0b7013 100644
---- a/.gitignore
-+++ b/.gitignore
-@@ -119,6 +119,7 @@ config/bash/lxc
- config/init/common/lxc-containers
- config/init/common/lxc-net
- config/init/systemd/lxc-autostart-helper
-+config/init/systemd/lxc-monitord.service
- config/init/systemd/lxc-net.service
- config/init/systemd/lxc.service
- config/init/systemd/lxc@.service
-diff --git a/config/init/systemd/Makefile.am b/config/init/systemd/Makefile.am
-index c448850d1..4a4fde5e7 100644
---- a/config/init/systemd/Makefile.am
-+++ b/config/init/systemd/Makefile.am
-@@ -2,19 +2,21 @@ EXTRA_DIST = \
- lxc-apparmor-load \
- lxc.service.in \
- lxc@.service.in \
-- lxc-net.service.in
-+ lxc-net.service.in \
-+ lxc-monitord.service.in
-
- if INIT_SCRIPT_SYSTEMD
--BUILT_SOURCES = lxc.service lxc@.service lxc-net.service
-+BUILT_SOURCES = lxc.service lxc@.service lxc-net.service lxc-monitord.service
-
--install-systemd: lxc.service lxc@.service lxc-net.service lxc-apparmor-load
-+install-systemd: lxc.service lxc@.service lxc-net.service lxc-monitord.service lxc-apparmor-load
- $(MKDIR_P) $(DESTDIR)$(SYSTEMD_UNIT_DIR)
-- $(INSTALL_DATA) lxc.service lxc@.service lxc-net.service $(DESTDIR)$(SYSTEMD_UNIT_DIR)/
-+ $(INSTALL_DATA) lxc.service lxc@.service lxc-net.service lxc-monitord.service $(DESTDIR)$(SYSTEMD_UNIT_DIR)/
-
- uninstall-systemd:
- rm -f $(DESTDIR)$(SYSTEMD_UNIT_DIR)/lxc.service
- rm -f $(DESTDIR)$(SYSTEMD_UNIT_DIR)/lxc@.service
- rm -f $(DESTDIR)$(SYSTEMD_UNIT_DIR)/lxc-net.service
-+ rm -f $(DESTDIR)$(SYSTEMD_UNIT_DIR)/lxc-monitord.service
- rmdir $(DESTDIR)$(SYSTEMD_UNIT_DIR) || :
-
- pkglibexec_SCRIPTS = lxc-apparmor-load
-diff --git a/config/init/systemd/lxc-monitord.service.in b/config/init/systemd/lxc-monitord.service.in
-new file mode 100644
-index 000000000..406351688
---- /dev/null
-+++ b/config/init/systemd/lxc-monitord.service.in
-@@ -0,0 +1,12 @@
-+[Unit]
-+Description=LXC Container Monitoring Daemon
-+After=syslog.service network.target
-+
-+[Service]
-+Type=simple
-+ExecStart=@LIBEXECDIR@/lxc/lxc-monitord --daemon
-+StandardOutput=syslog
-+StandardError=syslog
-+
-+[Install]
-+WantedBy=multi-user.target
-diff --git a/configure.ac b/configure.ac
-index 645a2166d..6260f483f 100644
---- a/configure.ac
-+++ b/configure.ac
-@@ -796,6 +796,7 @@ AC_CONFIG_FILES([
- config/init/systemd/lxc.service
- config/init/systemd/lxc@.service
- config/init/systemd/lxc-net.service
-+ config/init/systemd/lxc-monitord.service
- config/init/sysvinit/Makefile
- config/init/sysvinit/lxc-containers
- config/init/sysvinit/lxc-net
-diff --git a/lxc.spec.in b/lxc.spec.in
-index ec6321c33..ea6789fb6 100644
---- a/lxc.spec.in
-+++ b/lxc.spec.in
-@@ -251,6 +251,7 @@ fi
- %{_unitdir}/lxc-net.service
- %{_unitdir}/lxc.service
- %{_unitdir}/lxc@.service
-+%{_unitdir}/lxc-monitord.service
- %else
- %{_sysconfdir}/rc.d/init.d/lxc
- %{_sysconfdir}/rc.d/init.d/lxc-net
-diff --git a/src/lxc/cmd/lxc_monitord.c b/src/lxc/cmd/lxc_monitord.c
-index 3b931b361..d3cc35978 100644
---- a/src/lxc/cmd/lxc_monitord.c
-+++ b/src/lxc/cmd/lxc_monitord.c
-@@ -359,17 +359,44 @@ static void lxc_monitord_sig_handler(int sig)
-
- int main(int argc, char *argv[])
- {
-- int ret, pipefd;
-+ int ret, pipefd = -1;
- char logpath[PATH_MAX];
- sigset_t mask;
-- char *lxcpath = argv[1];
-+ const char *lxcpath = NULL;
- bool mainloop_opened = false;
- bool monitord_created = false;
-+ bool persistent = false;
- struct lxc_log log;
-
-- if (argc != 3) {
-+ if (argc > 1 && !strcmp(argv[1], "--daemon")) {
-+ persistent = true;
-+ --argc;
-+ ++argv;
-+ }
-+
-+ if (argc > 1) {
-+ lxcpath = argv[1];
-+ --argc;
-+ ++argv;
-+ } else {
-+ lxcpath = lxc_global_config_value("lxc.lxcpath");
-+ if (!lxcpath) {
-+ ERROR("Out of memory getting lxcpath");
-+ exit(EXIT_FAILURE);
-+ }
-+ }
-+
-+ if (argc > 1) {
-+ if (lxc_safe_int(argv[1], &pipefd) < 0)
-+ exit(EXIT_FAILURE);
-+ --argc;
-+ ++argv;
-+ }
-+
-+ if (argc != 1 || (persistent != (pipefd == -1))) {
- fprintf(stderr,
-- "Usage: lxc-monitord lxcpath sync-pipe-fd\n\n"
-+ "Usage: lxc-monitord lxcpath sync-pipe-fd\n"
-+ " lxc-monitord --daemon lxcpath\n\n"
- "NOTE: lxc-monitord is intended for use by lxc internally\n"
- " and does not need to be run by hand\n\n");
- exit(EXIT_FAILURE);
-@@ -392,9 +419,6 @@ int main(int argc, char *argv[])
- INFO("Failed to open log file %s, log will be lost", lxcpath);
- lxc_log_options_no_override();
-
-- if (lxc_safe_int(argv[2], &pipefd) < 0)
-- exit(EXIT_FAILURE);
--
- if (sigfillset(&mask) ||
- sigdelset(&mask, SIGILL) ||
- sigdelset(&mask, SIGSEGV) ||
-@@ -427,15 +451,17 @@ int main(int argc, char *argv[])
- goto on_error;
- monitord_created = true;
-
-- /* sync with parent, we're ignoring the return from write
-- * because regardless if it works or not, the following
-- * close will sync us with the parent process. the
-- * if-empty-statement construct is to quiet the
-- * warn-unused-result warning.
-- */
-- if (lxc_write_nointr(pipefd, "S", 1))
-- ;
-- close(pipefd);
-+ if (pipefd != -1) {
-+ /* sync with parent, we're ignoring the return from write
-+ * because regardless if it works or not, the following
-+ * close will sync us with the parent process. the
-+ * if-empty-statement construct is to quiet the
-+ * warn-unused-result warning.
-+ */
-+ if (lxc_write_nointr(pipefd, "S", 1))
-+ ;
-+ close(pipefd);
-+ }
-
- if (lxc_monitord_mainloop_add(&monitor)) {
- ERROR("Failed to add mainloop handlers");
-@@ -446,7 +472,7 @@ int main(int argc, char *argv[])
- lxc_raw_getpid(), monitor.lxcpath);
-
- for (;;) {
-- ret = lxc_mainloop(&monitor.descr, 1000 * 30);
-+ ret = lxc_mainloop(&monitor.descr, persistent ? -1 : 1000 * 30);
- if (ret) {
- ERROR("mainloop returned an error");
- break;
---
-2.20.1
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Wed, 2 Jan 2019 14:37:58 +0100
-Subject: [PATCH] PVE: [Config] Disable lxc.monitor cgroup
-
-When not using relative cgroups this makes lxc unusable
-within systemd service files as the service cgroup becomes
-empty.
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- src/lxc/start.c | 22 +++++++++++-----------
- 1 file changed, 11 insertions(+), 11 deletions(-)
-
-diff --git a/src/lxc/start.c b/src/lxc/start.c
-index a9a07bc83..0169cf8e3 100644
---- a/src/lxc/start.c
-+++ b/src/lxc/start.c
-@@ -2026,17 +2026,17 @@ int __lxc_start(const char *name, struct lxc_handler *handler,
- goto out_fini_nonet;
- }
-
-- if (!cgroup_ops->monitor_create(cgroup_ops, handler)) {
-- ERROR("Failed to create monitor cgroup");
-- ret = -1;
-- goto out_fini_nonet;
-- }
--
-- if (!cgroup_ops->monitor_enter(cgroup_ops, handler->monitor_pid)) {
-- ERROR("Failed to enter monitor cgroup");
-- ret = -1;
-- goto out_fini_nonet;
-- }
-+ //if (!cgroup_ops->monitor_create(cgroup_ops, handler)) {
-+ // ERROR("Failed to create monitor cgroup");
-+ // ret = -1;
-+ // goto out_fini_nonet;
-+ //}
-+
-+ //if (!cgroup_ops->monitor_enter(cgroup_ops, handler->monitor_pid)) {
-+ // ERROR("Failed to enter monitor cgroup");
-+ // ret = -1;
-+ // goto out_fini_nonet;
-+ //}
-
- if (geteuid() == 0 && !lxc_list_empty(&conf->id_map)) {
- /* If the backing store is a device, mount it here and now. */
---
-2.20.1
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Wed, 28 Mar 2018 13:37:28 +0200
-Subject: [PATCH] PVE: [Up] separate the limiting from the namespaced cgroup
- root
-
-When cgroup namespaces are enabled a privileged container
-with mixed cgroups has full write access to its own root
-cgroup effectively allowing it to overwrite values written
-from the outside or configured via lxc.cgroup.*.
-
-This patch causes an additional 'ns/' directory to be
-created in all cgroups if cgroup namespaces and cgfsng are
-being used in order to combat this.
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- src/lxc/cgroups/cgfsng.c | 80 +++++++++++++++++++++++++++++-------
- src/lxc/cgroups/cgroup.h | 18 +++++++--
- src/lxc/commands.c | 87 ++++++++++++++++++++++++++++++----------
- src/lxc/commands.h | 2 +
- src/lxc/criu.c | 4 +-
- src/lxc/start.c | 28 +++++++++----
- 6 files changed, 171 insertions(+), 48 deletions(-)
-
-diff --git a/src/lxc/cgroups/cgfsng.c b/src/lxc/cgroups/cgfsng.c
-index 1e6a45cff..c09b4ea71 100644
---- a/src/lxc/cgroups/cgfsng.c
-+++ b/src/lxc/cgroups/cgfsng.c
-@@ -808,6 +808,7 @@ static struct hierarchy *add_hierarchy(struct hierarchy ***h, char **clist, char
- new->mountpoint = mountpoint;
- new->container_base_path = container_base_path;
- new->container_full_path = NULL;
-+ new->container_inner_path = NULL;
- new->monitor_full_path = NULL;
- new->version = type;
- new->cgroup2_chown = NULL;
-@@ -1048,6 +1049,9 @@ static int cgroup_rmdir(struct hierarchy **hierarchies,
-
- free(h->container_full_path);
- h->container_full_path = NULL;
-+
-+ free(h->container_inner_path);
-+ h->container_inner_path = NULL;
- }
-
- return 0;
-@@ -1059,6 +1063,7 @@ struct generic_userns_exec_data {
- struct lxc_conf *conf;
- uid_t origuid; /* target uid in parent namespace */
- char *path;
-+ bool inner;
- };
-
- static int cgroup_rmdir_wrapper(void *data)
-@@ -1104,6 +1109,7 @@ __cgfsng_ops static void cgfsng_payload_destroy(struct cgroup_ops *ops,
- wrap.container_cgroup = ops->container_cgroup;
- wrap.hierarchies = ops->hierarchies;
- wrap.conf = handler->conf;
-+ wrap.inner = false;
-
- if (handler->conf && !lxc_list_empty(&handler->conf->id_map))
- ret = userns_exec_1(handler->conf, cgroup_rmdir_wrapper, &wrap,
-@@ -1306,17 +1312,26 @@ static bool monitor_create_path_for_hierarchy(struct hierarchy *h, char *cgname)
- return cg_unified_create_cgroup(h, cgname);
- }
-
--static bool container_create_path_for_hierarchy(struct hierarchy *h, char *cgname)
-+static bool container_create_path_for_hierarchy(struct hierarchy *h, char *cgname, bool inner)
- {
- int ret;
-+ char *path;
-
-- if (!cg_legacy_handle_cpuset_hierarchy(h, cgname)) {
-+ if (!inner && !cg_legacy_handle_cpuset_hierarchy(h, cgname)) {
- ERROR("Failed to handle legacy cpuset controller");
- return false;
- }
-
-- h->container_full_path = must_make_path(h->mountpoint, h->container_base_path, cgname, NULL);
-- ret = mkdir_eexist_on_last(h->container_full_path, 0755);
-+ if (inner) {
-+ path = must_make_path(h->container_full_path, CGROUP_NAMESPACE_SUBDIR, NULL);
-+ h->container_inner_path = path;
-+ ret = mkdir(path, 0755);
-+ } else {
-+ path = must_make_path(h->mountpoint, h->container_base_path, cgname, NULL);
-+ h->container_full_path = path;
-+ ret = mkdir_eexist_on_last(path, 0755);
-+ }
-+
- if (ret < 0) {
- ERROR("Failed to create cgroup \"%s\"", h->container_full_path);
- return false;
-@@ -1408,11 +1423,29 @@ __cgfsng_ops static inline bool cgfsng_monitor_create(struct cgroup_ops *ops,
- return true;
- }
-
-+static inline bool cgfsng_create_inner(struct cgroup_ops *ops)
-+{
-+ size_t i;
-+ bool ret = true;
-+ char *cgname = must_make_path(ops->container_cgroup, CGROUP_NAMESPACE_SUBDIR, NULL);
-+ for (i = 0; ops->hierarchies[i]; i++) {
-+ if (!container_create_path_for_hierarchy(ops->hierarchies[i], cgname, true)) {
-+ SYSERROR("Failed to create %s namespace subdirectory: %s",
-+ ops->hierarchies[i]->container_full_path, strerror(errno));
-+ ret = false;
-+ break;
-+ }
-+ }
-+ free(cgname);
-+ return ret;
-+}
-+
- /* Try to create the same cgroup in all hierarchies. Start with cgroup_pattern;
- * next cgroup_pattern-1, -2, ..., -999.
- */
- __cgfsng_ops static inline bool cgfsng_payload_create(struct cgroup_ops *ops,
-- struct lxc_handler *handler)
-+ struct lxc_handler *handler,
-+ bool inner)
- {
- __do_free char *container_cgroup = NULL, *tmp = NULL;
- int i;
-@@ -1422,7 +1455,12 @@ __cgfsng_ops static inline bool cgfsng_payload_create(struct cgroup_ops *ops,
- struct lxc_conf *conf = handler->conf;
-
- if (ops->container_cgroup)
-+ return inner ? cgfsng_create_inner(ops) : false;
-+
-+ if (inner) {
-+ ERROR("cgfsng_create called twice for inner cgroup");
- return false;
-+ }
-
- if (!conf)
- return false;
-@@ -1453,7 +1491,7 @@ __cgfsng_ops static inline bool cgfsng_payload_create(struct cgroup_ops *ops,
-
- for (i = 0; ops->hierarchies[i]; i++) {
- if (!container_create_path_for_hierarchy(ops->hierarchies[i],
-- container_cgroup)) {
-+ container_cgroup, false)) {
- ERROR("Failed to create cgroup \"%s\"",
- ops->hierarchies[i]->container_full_path);
- for (int j = 0; j < i; j++)
-@@ -1475,7 +1513,8 @@ __cgfsng_ops static inline bool cgfsng_payload_create(struct cgroup_ops *ops,
- }
-
- __cgfsng_ops static bool __do_cgroup_enter(struct cgroup_ops *ops, pid_t pid,
-- bool monitor)
-+ bool monitor,
-+ bool inner)
- {
- int len;
- char pidstr[INTTYPE_TO_STRLEN(pid_t)];
-@@ -1494,6 +1533,9 @@ __cgfsng_ops static bool __do_cgroup_enter(struct cgroup_ops *ops, pid_t pid,
- if (monitor)
- path = must_make_path(ops->hierarchies[i]->monitor_full_path,
- "cgroup.procs", NULL);
-+ else if (inner)
-+ path = must_make_path(ops->hierarchies[i]->container_inner_path,
-+ "cgroup.procs", NULL);
- else
- path = must_make_path(ops->hierarchies[i]->container_full_path,
- "cgroup.procs", NULL);
-@@ -1509,12 +1551,12 @@ __cgfsng_ops static bool __do_cgroup_enter(struct cgroup_ops *ops, pid_t pid,
-
- __cgfsng_ops static bool cgfsng_monitor_enter(struct cgroup_ops *ops, pid_t pid)
- {
-- return __do_cgroup_enter(ops, pid, true);
-+ return __do_cgroup_enter(ops, pid, true, false);
- }
-
--static bool cgfsng_payload_enter(struct cgroup_ops *ops, pid_t pid)
-+static bool cgfsng_payload_enter(struct cgroup_ops *ops, pid_t pid, bool inner)
- {
-- return __do_cgroup_enter(ops, pid, false);
-+ return __do_cgroup_enter(ops, pid, false, inner);
- }
-
- static int chowmod(char *path, uid_t chown_uid, gid_t chown_gid,
-@@ -1578,8 +1620,12 @@ static int chown_cgroup_wrapper(void *data)
-
- for (int i = 0; arg->hierarchies[i]; i++) {
- __do_free char *fullpath = NULL;
-+ __do_free char *inner_guard = NULL;
- char *path = arg->hierarchies[i]->container_full_path;
-
-+ if (arg->inner)
-+ path = inner_guard = must_make_path(path, CGROUP_NAMESPACE_SUBDIR, NULL);
-+
- ret = chowmod(path, destuid, nsgid, 0775);
- if (ret < 0)
- return -1;
-@@ -1612,7 +1658,8 @@ static int chown_cgroup_wrapper(void *data)
- }
-
- __cgfsng_ops static bool cgfsng_chown(struct cgroup_ops *ops,
-- struct lxc_conf *conf)
-+ struct lxc_conf *conf,
-+ bool inner)
- {
- struct generic_userns_exec_data wrap;
-
-@@ -1626,6 +1673,7 @@ __cgfsng_ops static bool cgfsng_chown(struct cgroup_ops *ops,
- wrap.path = NULL;
- wrap.hierarchies = ops->hierarchies;
- wrap.conf = conf;
-+ wrap.inner = inner;
-
- if (userns_exec_1(conf, chown_cgroup_wrapper, &wrap,
- "chown_cgroup_wrapper") < 0) {
-@@ -2100,7 +2148,8 @@ __cgfsng_ops static bool cgfsng_unfreeze(struct cgroup_ops *ops)
- }
-
- __cgfsng_ops static const char *cgfsng_get_cgroup(struct cgroup_ops *ops,
-- const char *controller)
-+ const char *controller,
-+ bool inner)
- {
- struct hierarchy *h;
-
-@@ -2111,6 +2160,9 @@ __cgfsng_ops static const char *cgfsng_get_cgroup(struct cgroup_ops *ops,
- return NULL;
- }
-
-+ if (inner)
-+ return h->container_inner_path ? h->container_inner_path + strlen(h->mountpoint) : NULL;
-+
- return h->container_full_path ? h->container_full_path + strlen(h->mountpoint) : NULL;
- }
-
-@@ -2143,7 +2195,7 @@ static int __cg_unified_attach(const struct hierarchy *h, const char *name,
- size_t len;
- int fret = -1, idx = 0;
-
-- container_cgroup = lxc_cmd_get_cgroup_path(name, lxcpath, controller);
-+ container_cgroup = lxc_cmd_get_attach_cgroup_path(name, lxcpath, controller);
- /* not running */
- if (!container_cgroup)
- return 0;
-@@ -2220,7 +2272,7 @@ __cgfsng_ops static bool cgfsng_attach(struct cgroup_ops *ops, const char *name,
- continue;
- }
-
-- path = lxc_cmd_get_cgroup_path(name, lxcpath, h->controllers[0]);
-+ path = lxc_cmd_get_attach_cgroup_path(name, lxcpath, h->controllers[0]);
- /* not running */
- if (!path)
- continue;
-diff --git a/src/lxc/cgroups/cgroup.h b/src/lxc/cgroups/cgroup.h
-index f3f0f6726..35d207feb 100644
---- a/src/lxc/cgroups/cgroup.h
-+++ b/src/lxc/cgroups/cgroup.h
-@@ -32,6 +32,12 @@
- #define MONITOR_CGROUP "lxc.monitor"
- #define PIVOT_CGROUP "lxc.pivot"
-
-+/* When lxc.cgroup.protect_limits is in effect the container's cgroup namespace
-+ * will be moved into an additional subdirectory "cgns/" inside the cgroup in
-+ * order to prevent it from accessing the outer limiting cgroup.
-+ */
-+#define CGROUP_NAMESPACE_SUBDIR "cgns"
-+
- struct lxc_handler;
- struct lxc_conf;
- struct lxc_list;
-@@ -72,6 +78,9 @@ typedef enum {
- * @monitor_full_path
- * - The full path to the monitor's cgroup.
- *
-+ * @container_inner_path
-+ * - The full path to the container's inner cgroup when protect_limits is used.
-+ *
- * @version
- * - legacy hierarchy
- * If the hierarchy is a legacy hierarchy this will be set to
-@@ -90,6 +99,7 @@ struct hierarchy {
- char *mountpoint;
- char *container_base_path;
- char *container_full_path;
-+ char *container_inner_path;
- char *monitor_full_path;
- int version;
- };
-@@ -144,9 +154,9 @@ struct cgroup_ops {
- void (*monitor_destroy)(struct cgroup_ops *ops, struct lxc_handler *handler);
- bool (*monitor_create)(struct cgroup_ops *ops, struct lxc_handler *handler);
- bool (*monitor_enter)(struct cgroup_ops *ops, pid_t pid);
-- bool (*payload_create)(struct cgroup_ops *ops, struct lxc_handler *handler);
-- bool (*payload_enter)(struct cgroup_ops *ops, pid_t pid);
-- const char *(*get_cgroup)(struct cgroup_ops *ops, const char *controller);
-+ bool (*payload_create)(struct cgroup_ops *ops, struct lxc_handler *handler, bool inner);
-+ bool (*payload_enter)(struct cgroup_ops *ops, pid_t pid, bool inner);
-+ const char *(*get_cgroup)(struct cgroup_ops *ops, const char *controller, bool inner);
- bool (*escape)(const struct cgroup_ops *ops, struct lxc_conf *conf);
- int (*num_hierarchies)(struct cgroup_ops *ops);
- bool (*get_hierarchies)(struct cgroup_ops *ops, int n, char ***out);
-@@ -158,7 +168,7 @@ struct cgroup_ops {
- bool (*unfreeze)(struct cgroup_ops *ops);
- bool (*setup_limits)(struct cgroup_ops *ops, struct lxc_conf *conf,
- bool with_devices);
-- bool (*chown)(struct cgroup_ops *ops, struct lxc_conf *conf);
-+ bool (*chown)(struct cgroup_ops *ops, struct lxc_conf *conf, bool inner);
- bool (*attach)(struct cgroup_ops *ops, const char *name,
- const char *lxcpath, pid_t pid);
- bool (*mount)(struct cgroup_ops *ops, struct lxc_handler *handler,
-diff --git a/src/lxc/commands.c b/src/lxc/commands.c
-index 90e3c5863..93406bb7e 100644
---- a/src/lxc/commands.c
-+++ b/src/lxc/commands.c
-@@ -425,20 +425,8 @@ static int lxc_cmd_get_clone_flags_callback(int fd, struct lxc_cmd_req *req,
- return lxc_cmd_rsp_send(fd, &rsp);
- }
-
--/*
-- * lxc_cmd_get_cgroup_path: Calculate a container's cgroup path for a
-- * particular subsystem. This is the cgroup path relative to the root
-- * of the cgroup filesystem.
-- *
-- * @name : name of container to connect to
-- * @lxcpath : the lxcpath in which the container is running
-- * @subsystem : the subsystem being asked about
-- *
-- * Returns the path on success, NULL on failure. The caller must free() the
-- * returned path.
-- */
--char *lxc_cmd_get_cgroup_path(const char *name, const char *lxcpath,
-- const char *subsystem)
-+char *do_lxc_cmd_get_cgroup_path(const char *name, const char *lxcpath,
-+ const char *subsystem, bool inner)
- {
- int ret, stopped;
- struct lxc_cmd_rr cmd = {
-@@ -451,8 +439,18 @@ char *lxc_cmd_get_cgroup_path(const char *name, const char *lxcpath,
-
- cmd.req.data = subsystem;
- cmd.req.datalen = 0;
-- if (subsystem)
-- cmd.req.datalen = strlen(subsystem) + 1;
-+ if (subsystem) {
-+ size_t subsyslen = strlen(subsystem);
-+ if (inner) {
-+ char *data = alloca(subsyslen+2);
-+ memcpy(data, subsystem, subsyslen+1);
-+ data[subsyslen+1] = 1;
-+ cmd.req.datalen = subsyslen+2,
-+ cmd.req.data = data;
-+ } else {
-+ cmd.req.datalen = subsyslen+1;
-+ }
-+ }
-
- ret = lxc_cmd(name, &cmd, &stopped, lxcpath, NULL);
- if (ret < 0)
-@@ -467,6 +465,42 @@ char *lxc_cmd_get_cgroup_path(const char *name, const char *lxcpath,
- return cmd.rsp.data;
- }
-
-+/*
-+ * lxc_cmd_get_cgroup_path: Calculate a container's cgroup path for a
-+ * particular subsystem. This is the cgroup path relative to the root
-+ * of the cgroup filesystem.
-+ *
-+ * @name : name of container to connect to
-+ * @lxcpath : the lxcpath in which the container is running
-+ * @subsystem : the subsystem being asked about
-+ *
-+ * Returns the path on success, NULL on failure. The caller must free() the
-+ * returned path.
-+ */
-+char *lxc_cmd_get_cgroup_path(const char *name, const char *lxcpath,
-+ const char *subsystem)
-+{
-+ return do_lxc_cmd_get_cgroup_path(name, lxcpath, subsystem, false);
-+}
-+
-+/*
-+ * lxc_cmd_get_attach_cgroup_path: Calculate a container's inner cgroup path
-+ * for a particular subsystem. This is the cgroup path relative to the root
-+ * of the cgroup filesystem.
-+ *
-+ * @name : name of container to connect to
-+ * @lxcpath : the lxcpath in which the container is running
-+ * @subsystem : the subsystem being asked about
-+ *
-+ * Returns the path on success, NULL on failure. The caller must free() the
-+ * returned path.
-+ */
-+char *lxc_cmd_get_attach_cgroup_path(const char *name, const char *lxcpath,
-+ const char *subsystem)
-+{
-+ return do_lxc_cmd_get_cgroup_path(name, lxcpath, subsystem, true);
-+}
-+
- static int lxc_cmd_get_cgroup_callback(int fd, struct lxc_cmd_req *req,
- struct lxc_handler *handler,
- struct lxc_epoll_descr *descr)
-@@ -475,10 +509,21 @@ static int lxc_cmd_get_cgroup_callback(int fd, struct lxc_cmd_req *req,
- struct lxc_cmd_rsp rsp;
- struct cgroup_ops *cgroup_ops = handler->cgroup_ops;
-
-- if (req->datalen > 0)
-- path = cgroup_ops->get_cgroup(cgroup_ops, req->data);
-- else
-- path = cgroup_ops->get_cgroup(cgroup_ops, NULL);
-+ if (req->datalen > 0) {
-+ const char *subsystem;
-+ size_t subsyslen;
-+ bool inner = false;
-+ subsystem = req->data;
-+ subsyslen = strlen(subsystem);
-+ if (req->datalen == subsyslen+2)
-+ inner = (subsystem[subsyslen+1] == 1);
-+
-+ path = cgroup_ops->get_cgroup(cgroup_ops, req->data, inner);
-+ } else {
-+ // FIXME: cgroup separation for cgroup v2 cannot be handled
-+ // like we used to do v1 here... need to figure this out...
-+ path = cgroup_ops->get_cgroup(cgroup_ops, NULL, false);
-+ }
- if (!path)
- return -1;
-
-@@ -653,7 +698,7 @@ static int lxc_cmd_stop_callback(int fd, struct lxc_cmd_req *req,
- * lxc_unfreeze() would do another cmd (GET_CGROUP) which would
- * deadlock us.
- */
-- if (!cgroup_ops->get_cgroup(cgroup_ops, "freezer"))
-+ if (!cgroup_ops->get_cgroup(cgroup_ops, "freezer", false))
- return 0;
-
- if (cgroup_ops->unfreeze(cgroup_ops))
-diff --git a/src/lxc/commands.h b/src/lxc/commands.h
-index d7d0c6096..042892a42 100644
---- a/src/lxc/commands.h
-+++ b/src/lxc/commands.h
-@@ -89,6 +89,8 @@ extern int lxc_cmd_console(const char *name, int *ttynum, int *fd,
- */
- extern char *lxc_cmd_get_cgroup_path(const char *name, const char *lxcpath,
- const char *subsystem);
-+extern char *lxc_cmd_get_attach_cgroup_path(const char *name,
-+ const char *lxcpath, const char *subsystem);
- extern int lxc_cmd_get_clone_flags(const char *name, const char *lxcpath);
- extern char *lxc_cmd_get_config_item(const char *name, const char *item, const char *lxcpath);
- extern char *lxc_cmd_get_name(const char *hashed_sock);
-diff --git a/src/lxc/criu.c b/src/lxc/criu.c
-index 86f6f1836..15a703c4f 100644
---- a/src/lxc/criu.c
-+++ b/src/lxc/criu.c
-@@ -332,7 +332,7 @@ static void exec_criu(struct cgroup_ops *cgroup_ops, struct lxc_conf *conf,
- } else {
- const char *p;
-
-- p = cgroup_ops->get_cgroup(cgroup_ops, controllers[0]);
-+ p = cgroup_ops->get_cgroup(cgroup_ops, controllers[0], false);
- if (!p) {
- ERROR("failed to get cgroup path for %s", controllers[0]);
- goto err;
-@@ -975,7 +975,7 @@ static void do_restore(struct lxc_container *c, int status_pipe, struct migrate_
- goto out_fini_handler;
- handler->cgroup_ops = cgroup_ops;
-
-- if (!cgroup_ops->payload_create(cgroup_ops, handler)) {
-+ if (!cgroup_ops->payload_create(cgroup_ops, handler, false)) {
- ERROR("failed creating groups");
- goto out_fini_handler;
- }
-diff --git a/src/lxc/start.c b/src/lxc/start.c
-index 0169cf8e3..db0625af5 100644
---- a/src/lxc/start.c
-+++ b/src/lxc/start.c
-@@ -1726,7 +1726,7 @@ static int lxc_spawn(struct lxc_handler *handler)
- }
- }
-
-- if (!cgroup_ops->payload_create(cgroup_ops, handler)) {
-+ if (!cgroup_ops->payload_create(cgroup_ops, handler, false)) {
- ERROR("Failed creating cgroups");
- goto out_delete_net;
- }
-@@ -1841,10 +1841,10 @@ static int lxc_spawn(struct lxc_handler *handler)
- goto out_delete_net;
- }
-
-- if (!cgroup_ops->payload_enter(cgroup_ops, handler->pid))
-+ if (!cgroup_ops->payload_enter(cgroup_ops, handler->pid, false))
- goto out_delete_net;
-
-- if (!cgroup_ops->chown(cgroup_ops, handler->conf))
-+ if (!cgroup_ops->chown(cgroup_ops, handler->conf, false))
- goto out_delete_net;
-
- /* If not done yet, we're now ready to preserve the network namespace */
-@@ -1902,16 +1902,30 @@ static int lxc_spawn(struct lxc_handler *handler)
- }
- }
-
-- ret = lxc_sync_barrier_child(handler, LXC_SYNC_CGROUP_UNSHARE);
-- if (ret < 0)
-- goto out_delete_net;
--
- if (!cgroup_ops->setup_limits(cgroup_ops, handler->conf, true)) {
- ERROR("Failed to setup legacy device cgroup controller limits");
- goto out_delete_net;
- }
- TRACE("Set up legacy device cgroup controller limits");
-
-+ if (cgns_supported()) {
-+ if (!cgroup_ops->payload_create(cgroup_ops, handler, true)) {
-+ ERROR("failed to create inner cgroup separation layer");
-+ goto out_delete_net;
-+ }
-+ if (!cgroup_ops->payload_enter(cgroup_ops, handler->pid, true)) {
-+ ERROR("failed to enter inner cgroup separation layer");
-+ goto out_delete_net;
-+ }
-+ if (!cgroup_ops->chown(cgroup_ops, handler->conf, true)) {
-+ ERROR("failed chown inner cgroup separation layer");
-+ goto out_delete_net;
-+ }
-+ }
-+
-+ if (lxc_sync_barrier_child(handler, LXC_SYNC_CGROUP_UNSHARE))
-+ goto out_delete_net;
-+
- if (handler->ns_clone_flags & CLONE_NEWCGROUP) {
- /* Now we're ready to preserve the cgroup namespace */
- ret = lxc_try_preserve_ns(handler->pid, "cgroup");
---
-2.20.1
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Wed, 28 Mar 2018 13:41:46 +0200
-Subject: [PATCH] PVE: [Up] start/initutils: make cgroupns separation level
- configurable
-
-Adds a new global config variable `lxc.cgroup.separate`
-which controls whether a separation directory for cgroup
-namespaces should be used.
-Can be empty, "privileged", "unprivileged" or "both".
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- src/lxc/initutils.c | 17 +++++++++--------
- src/lxc/initutils.h | 1 +
- src/lxc/start.c | 25 ++++++++++++++-----------
- 3 files changed, 24 insertions(+), 19 deletions(-)
-
-diff --git a/src/lxc/initutils.c b/src/lxc/initutils.c
-index da3363294..5e33afc58 100644
---- a/src/lxc/initutils.c
-+++ b/src/lxc/initutils.c
-@@ -64,14 +64,15 @@ static char *copy_global_config_value(char *p)
- const char *lxc_global_config_value(const char *option_name)
- {
- static const char * const options[][2] = {
-- { "lxc.bdev.lvm.vg", DEFAULT_VG },
-- { "lxc.bdev.lvm.thin_pool", DEFAULT_THIN_POOL },
-- { "lxc.bdev.zfs.root", DEFAULT_ZFSROOT },
-- { "lxc.bdev.rbd.rbdpool", DEFAULT_RBDPOOL },
-- { "lxc.lxcpath", NULL },
-- { "lxc.default_config", NULL },
-- { "lxc.cgroup.pattern", NULL },
-- { "lxc.cgroup.use", NULL },
-+ { "lxc.bdev.lvm.vg", DEFAULT_VG },
-+ { "lxc.bdev.lvm.thin_pool", DEFAULT_THIN_POOL },
-+ { "lxc.bdev.zfs.root", DEFAULT_ZFSROOT },
-+ { "lxc.bdev.rbd.rbdpool", DEFAULT_RBDPOOL },
-+ { "lxc.lxcpath", NULL },
-+ { "lxc.default_config", NULL },
-+ { "lxc.cgroup.pattern", NULL },
-+ { "lxc.cgroup.use", NULL },
-+ { "lxc.cgroup.protect_limits", DEFAULT_CGPROTECT },
- { NULL, NULL },
- };
-
-diff --git a/src/lxc/initutils.h b/src/lxc/initutils.h
-index 6bf23a706..b542e6015 100644
---- a/src/lxc/initutils.h
-+++ b/src/lxc/initutils.h
-@@ -42,6 +42,7 @@
- #define DEFAULT_THIN_POOL "lxc"
- #define DEFAULT_ZFSROOT "lxc"
- #define DEFAULT_RBDPOOL "lxc"
-+#define DEFAULT_CGPROTECT "privileged"
-
- #ifndef PR_SET_MM
- #define PR_SET_MM 35
-diff --git a/src/lxc/start.c b/src/lxc/start.c
-index db0625af5..0ee7f9636 100644
---- a/src/lxc/start.c
-+++ b/src/lxc/start.c
-@@ -1909,17 +1909,20 @@ static int lxc_spawn(struct lxc_handler *handler)
- TRACE("Set up legacy device cgroup controller limits");
-
- if (cgns_supported()) {
-- if (!cgroup_ops->payload_create(cgroup_ops, handler, true)) {
-- ERROR("failed to create inner cgroup separation layer");
-- goto out_delete_net;
-- }
-- if (!cgroup_ops->payload_enter(cgroup_ops, handler->pid, true)) {
-- ERROR("failed to enter inner cgroup separation layer");
-- goto out_delete_net;
-- }
-- if (!cgroup_ops->chown(cgroup_ops, handler->conf, true)) {
-- ERROR("failed chown inner cgroup separation layer");
-- goto out_delete_net;
-+ const char *tmp = lxc_global_config_value("lxc.cgroup.protect_limits");
-+ if (!strcmp(tmp, "both") || !strcmp(tmp, wants_to_map_ids ? "unprivileged" : "privileged")) {
-+ if (!cgroup_ops->payload_create(cgroup_ops, handler, true)) {
-+ ERROR("failed to create inner cgroup separation layer");
-+ goto out_delete_net;
-+ }
-+ if (!cgroup_ops->payload_enter(cgroup_ops, handler->pid, true)) {
-+ ERROR("failed to enter inner cgroup separation layer");
-+ goto out_delete_net;
-+ }
-+ if (!cgroup_ops->chown(cgroup_ops, handler->conf, true)) {
-+ ERROR("failed chown inner cgroup separation layer");
-+ goto out_delete_net;
-+ }
- }
- }
-
---
-2.20.1
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Fri, 23 Dec 2016 15:57:24 +0100
-Subject: [PATCH] PVE: [Config] namespace separation
-
-* rename cgroup namespace directory to ns
-* set lxc.cgroup.protect_limits default to 'both'
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- src/lxc/cgroups/cgroup.h | 2 +-
- src/lxc/initutils.h | 2 +-
- 2 files changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/src/lxc/cgroups/cgroup.h b/src/lxc/cgroups/cgroup.h
-index 35d207feb..be9df33a2 100644
---- a/src/lxc/cgroups/cgroup.h
-+++ b/src/lxc/cgroups/cgroup.h
-@@ -36,7 +36,7 @@
- * will be moved into an additional subdirectory "cgns/" inside the cgroup in
- * order to prevent it from accessing the outer limiting cgroup.
- */
--#define CGROUP_NAMESPACE_SUBDIR "cgns"
-+#define CGROUP_NAMESPACE_SUBDIR "ns"
-
- struct lxc_handler;
- struct lxc_conf;
-diff --git a/src/lxc/initutils.h b/src/lxc/initutils.h
-index b542e6015..78d3f2b10 100644
---- a/src/lxc/initutils.h
-+++ b/src/lxc/initutils.h
-@@ -42,7 +42,7 @@
- #define DEFAULT_THIN_POOL "lxc"
- #define DEFAULT_ZFSROOT "lxc"
- #define DEFAULT_RBDPOOL "lxc"
--#define DEFAULT_CGPROTECT "privileged"
-+#define DEFAULT_CGPROTECT "both"
-
- #ifndef PR_SET_MM
- #define PR_SET_MM 35
---
-2.20.1
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Tue, 13 Aug 2019 13:57:22 +0200
-Subject: [PATCH] PVE: [Config] attach: always use getent
-
-In debian buster, some libnss plugins (if installed) can
-cause getpwent to segfault instead of erroring out cleanly.
-To avoid this, stick to always using getent.
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- src/lxc/attach.c | 28 ++--------------------------
- 1 file changed, 2 insertions(+), 26 deletions(-)
-
-diff --git a/src/lxc/attach.c b/src/lxc/attach.c
-index 80c41fe26..f30f192e3 100644
---- a/src/lxc/attach.c
-+++ b/src/lxc/attach.c
-@@ -1506,12 +1506,8 @@ int lxc_attach_run_command(void *payload)
-
- int lxc_attach_run_shell(void* payload)
- {
-- __do_free char *buf = NULL;
- uid_t uid;
-- struct passwd pwent;
-- struct passwd *pwentp = NULL;
- char *user_shell;
-- size_t bufsize;
- int ret;
-
- /* Ignore payload parameter. */
-@@ -1519,32 +1515,13 @@ int lxc_attach_run_shell(void* payload)
-
- uid = getuid();
-
-- bufsize = sysconf(_SC_GETPW_R_SIZE_MAX);
-- if (bufsize == -1)
-- bufsize = 1024;
--
-- buf = malloc(bufsize);
-- if (buf) {
-- ret = getpwuid_r(uid, &pwent, buf, bufsize, &pwentp);
-- if (!pwentp) {
-- if (ret == 0)
-- WARN("Could not find matched password record");
--
-- WARN("Failed to get password record - %u", uid);
-- }
-- }
--
- /* This probably happens because of incompatible nss implementations in
- * host and container (remember, this code is still using the host's
- * glibc but our mount namespace is in the container) we may try to get
- * the information by spawning a [getent passwd uid] process and parsing
- * the result.
- */
-- if (!pwentp)
-- user_shell = lxc_attach_getpwshell(uid);
-- else
-- user_shell = pwent.pw_shell;
--
-+ user_shell = lxc_attach_getpwshell(uid);
- if (user_shell)
- execlp(user_shell, user_shell, (char *)NULL);
-
-@@ -1554,8 +1531,7 @@ int lxc_attach_run_shell(void* payload)
- execlp("/bin/sh", "/bin/sh", (char *)NULL);
-
- SYSERROR("Failed to execute shell");
-- if (!pwentp)
-- free(user_shell);
-+ free(user_shell);
-
- return -1;
- }
---
-2.20.1
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Wed, 10 Jul 2019 14:29:54 +0200
-Subject: [PATCH] init: add ExecReload to lxc.service to only reload profiles
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- config/init/systemd/lxc.service.in | 1 +
- 1 file changed, 1 insertion(+)
-
-diff --git a/config/init/systemd/lxc.service.in b/config/init/systemd/lxc.service.in
-index 77541917e..e4c086e0a 100644
---- a/config/init/systemd/lxc.service.in
-+++ b/config/init/systemd/lxc.service.in
-@@ -10,6 +10,7 @@ RemainAfterExit=yes
- ExecStartPre=@LIBEXECDIR@/lxc/lxc-apparmor-load
- ExecStart=@LIBEXECDIR@/lxc/lxc-containers start
- ExecStop=@LIBEXECDIR@/lxc/lxc-containers stop
-+ExecReload=@LIBEXECDIR@/lxc/lxc-apparmor-load
- # Environment=BOOTUP=serial
- # Environment=CONSOLETYPE=serial
- Delegate=yes
---
-2.20.1
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Fri, 2 Aug 2019 12:57:42 +0200
-Subject: [PATCH] apparmor: generate ro,bind,remount rule list
-
-and update to changes based on lxd
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- src/lxc/lsm/apparmor.c | 114 ++++++++++++++++++++++++++++++++++++-----
- 1 file changed, 100 insertions(+), 14 deletions(-)
-
-diff --git a/src/lxc/lsm/apparmor.c b/src/lxc/lsm/apparmor.c
-index e32b12531..47f825866 100644
---- a/src/lxc/lsm/apparmor.c
-+++ b/src/lxc/lsm/apparmor.c
-@@ -149,6 +149,16 @@ static const char AA_PROFILE_BASE[] =
- "# mount options=(rw,make-unbindable) -> **,\n"
- "# mount options=(rw,make-runbindable) -> **,\n"
- "\n"
-+"# Allow limited modification of mount propagation\n"
-+" mount options=(rw,make-slave) -> /,\n"
-+" mount options=(rw,make-rslave) -> /,\n"
-+" mount options=(rw,make-shared) -> /,\n"
-+" mount options=(rw,make-rshared) -> /,\n"
-+" mount options=(rw,make-private) -> /,\n"
-+" mount options=(rw,make-rprivate) -> /,\n"
-+" mount options=(rw,make-unbindable) -> /,\n"
-+" mount options=(rw,make-runbindable) -> /,\n"
-+"\n"
- " # allow bind-mounts of anything except /proc, /sys and /dev\n"
- " mount options=(rw,bind) /[^spd]*{,/**},\n"
- " mount options=(rw,bind) /d[^e]*{,/**},\n"
-@@ -167,15 +177,18 @@ static const char AA_PROFILE_BASE[] =
- " mount options=(rw,bind) /sy[^s]*{,/**},\n"
- " mount options=(rw,bind) /sys?*{,/**},\n"
- "\n"
--" # allow various ro-bind-*re*-mounts\n"
--" mount options=(ro,remount,bind),\n"
--" mount options=(ro,remount,bind,nosuid),\n"
--" mount options=(ro,remount,bind,noexec),\n"
--" mount options=(ro,remount,bind,nodev),\n"
--" mount options=(ro,remount,bind,nosuid,noexec),\n"
--" mount options=(ro,remount,bind,noexec,nodev),\n"
--" mount options=(ro,remount,bind,nodev,nosuid),\n"
--" mount options=(ro,remount,bind,nosuid,noexec,nodev),\n"
-+" # Allow rbind-mounts of anything except /, /dev, /proc and /sys\n"
-+" mount options=(rw,rbind) /[^spd]*{,/**},\n"
-+" mount options=(rw,rbind) /d[^e]*{,/**},\n"
-+" mount options=(rw,rbind) /de[^v]*{,/**},\n"
-+" mount options=(rw,rbind) /dev?*{,/**},\n"
-+" mount options=(rw,rbind) /p[^r]*{,/**},\n"
-+" mount options=(rw,rbind) /pr[^o]*{,/**},\n"
-+" mount options=(rw,rbind) /pro[^c]*{,/**},\n"
-+" mount options=(rw,rbind) /proc?*{,/**},\n"
-+" mount options=(rw,rbind) /s[^y]*{,/**},\n"
-+" mount options=(rw,rbind) /sy[^s]*{,/**},\n"
-+" mount options=(rw,rbind) /sys?*{,/**},\n"
- "\n"
- " # allow moving mounts except for /proc, /sys and /dev\n"
- " mount options=(rw,move) /[^spd]*{,/**},\n"
-@@ -341,12 +354,13 @@ static const char AA_PROFILE_NESTING_BASE[] =
- "\n"
- " mount fstype=proc -> /usr/lib/*/lxc/**,\n"
- " mount fstype=sysfs -> /usr/lib/*/lxc/**,\n"
--" mount options=(rw,bind),\n"
--" mount options=(rw,rbind),\n"
--" mount options=(rw,make-rshared),\n"
- "\n"
-- /* FIXME: What's the state here on apparmor's side? */
--" # there doesn't seem to be a way to ask for:\n"
-+" # Allow nested LXD\n"
-+" mount none -> /var/lib/lxd/shmounts/,\n"
-+" mount /var/lib/lxd/shmounts/ -> /var/lib/lxd/shmounts/,\n"
-+" mount options=bind /var/lib/lxd/shmounts/** -> /var/lib/lxd/**,\n"
-+"\n"
-+" # FIXME: There doesn't seem to be a way to ask for:\n"
- " # mount options=(ro,nosuid,nodev,noexec,remount,bind),\n"
- " # as we always get mount to $cdir/proc/sys with those flags denied\n"
- " # So allow all mounts until that is straightened out:\n"
-@@ -648,6 +662,76 @@ static bool is_privileged(struct lxc_conf *conf)
- return lxc_list_empty(&conf->id_map);
- }
-
-+static const char* AA_ALL_DEST_PATH_LIST[] = {
-+ " -> /[^spd]*{,/**},\n",
-+ " -> /d[^e]*{,/**},\n",
-+ " -> /de[^v]*{,/**},\n",
-+ " -> /dev/.[^l]*{,/**},\n",
-+ " -> /dev/.l[^x]*{,/**},\n",
-+ " -> /dev/.lx[^c]*{,/**},\n",
-+ " -> /dev/.lxc?*{,/**},\n",
-+ " -> /dev/[^.]*{,/**},\n",
-+ " -> /dev?*{,/**},\n",
-+ " -> /p[^r]*{,/**},\n",
-+ " -> /pr[^o]*{,/**},\n",
-+ " -> /pro[^c]*{,/**},\n",
-+ " -> /proc?*{,/**},\n",
-+ " -> /s[^y]*{,/**},\n",
-+ " -> /sy[^s]*{,/**},\n",
-+ " -> /sys?*{,/**},\n",
-+ NULL,
-+};
-+
-+static void append_remount_rule(char **profile, size_t *size, const char *rule)
-+{
-+ size_t rule_len = strlen(rule);
-+
-+ for (const char **dest = AA_ALL_DEST_PATH_LIST; *dest; ++dest) {
-+ must_append_sized(profile, size, rule, rule_len);
-+ must_append_sized(profile, size, *dest, strlen(*dest));
-+ }
-+}
-+
-+static void append_all_remount_rules(char **profile, size_t *size)
-+{
-+ must_append_sized(profile, size,
-+ "# allow various ro-bind-*re*mounts\n",
-+ sizeof("# allow various ro-bind-*re*mounts\n")-1);
-+
-+ static struct mntopt_t {
-+ const char *opt;
-+ size_t len;
-+ } mnt_opt_list[] = {
-+ { ",nodev", sizeof(",nodev")-1 },
-+ { ",nosuid", sizeof(",nosuid")-1 },
-+ { ",noexec", sizeof(",noexec")-1 },
-+ };
-+
-+ const size_t opt_count = sizeof(mnt_opt_list) / sizeof(mnt_opt_list[0]);
-+
-+ char buf[128] = "mount options=(ro,remount,bind";
-+ const size_t start = strlen(buf);
-+ for (size_t i = 0; i != 1 << opt_count; ++i) {
-+ size_t at = start;
-+ unsigned opt_bit = 1;
-+
-+ for (size_t o = 0; o != opt_count; ++o, opt_bit <<= 1) {
-+ if (i & opt_bit) {
-+ struct mntopt_t *opt = &mnt_opt_list[o];
-+ memcpy(&buf[at], opt->opt, opt->len);
-+ at += opt->len;
-+ }
-+ }
-+
-+ memcpy(&buf[at], ")", sizeof(")"));
-+ append_remount_rule(profile, size, buf);
-+ memcpy(&buf[at], ",noatime)", sizeof(",noatime)"));
-+ append_remount_rule(profile, size, buf);
-+ memcpy(&buf[at], ",strictatime)", sizeof(",strictatime)"));
-+ append_remount_rule(profile, size, buf);
-+ }
-+}
-+
- static char *get_apparmor_profile_content(struct lxc_conf *conf, const char *lxcpath)
- {
- char *profile, *profile_name_full;
-@@ -665,6 +749,8 @@ static char *get_apparmor_profile_content(struct lxc_conf *conf, const char *lxc
- must_append_sized(&profile, &size, AA_PROFILE_BASE,
- STRARRAYLEN(AA_PROFILE_BASE));
-
-+ append_all_remount_rules(&profile, &size);
-+
- if (aa_supports_unix)
- must_append_sized(&profile, &size, AA_PROFILE_UNIX_SOCKETS,
- STRARRAYLEN(AA_PROFILE_UNIX_SOCKETS));
---
-2.20.1
-
+++ /dev/null
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Wed, 23 Oct 2019 10:53:21 +0200
-Subject: [PATCH] apparmor: Prevent writes to /proc/acpi/**
-
-Same as #3117.
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
----
- src/lxc/lsm/apparmor.c | 1 +
- 1 file changed, 1 insertion(+)
-
-diff --git a/src/lxc/lsm/apparmor.c b/src/lxc/lsm/apparmor.c
-index 47f825866..8aebb21af 100644
---- a/src/lxc/lsm/apparmor.c
-+++ b/src/lxc/lsm/apparmor.c
-@@ -121,6 +121,7 @@ static const char AA_PROFILE_BASE[] =
- " # block some other dangerous paths\n"
- " deny @{PROC}/kcore rwklx,\n"
- " deny @{PROC}/sysrq-trigger rwklx,\n"
-+" deny @{PROC}/acpi/** rwklx,\n"
- "\n"
- " # deny writes in /sys except for /sys/fs/cgroup, also allow\n"
- " # fusectl, securityfs and debugfs to be mounted there (read-only)\n"
---
-2.20.1
-
pve/0001-PVE-Config-lxc.service-start-after-a-potential-syslo.patch
-pve/0002-PVE-Down-run-lxcnetaddbr-when-instantiating-veths.patch
-pve/0003-PVE-Config-deny-rw-mounting-of-sys-and-proc.patch
-pve/0004-PVE-Up-possibility-to-run-lxc-monitord-as-a-regular-.patch
-pve/0005-PVE-Config-Disable-lxc.monitor-cgroup.patch
-pve/0006-PVE-Up-separate-the-limiting-from-the-namespaced-cgr.patch
-pve/0007-PVE-Up-start-initutils-make-cgroupns-separation-leve.patch
-pve/0008-PVE-Config-namespace-separation.patch
-pve/0009-PVE-Config-attach-always-use-getent.patch
-pve/0010-init-add-ExecReload-to-lxc.service-to-only-reload-pr.patch
-pve/0011-apparmor-generate-ro-bind-remount-rule-list.patch
-pve/0012-apparmor-Prevent-writes-to-proc-acpi.patch
+pve/0002-PVE-Config-deny-rw-mounting-of-sys-and-proc.patch
+pve/0003-PVE-Config-attach-always-use-getent.patch
-Subproject commit 344b8ee293f4d3730a70a6ccaa03d7e4a516ae95
+Subproject commit d8ccf906038e7ca3241e572192ffa59999adb923