summaryrefslogtreecommitdiff
path: root/src/core/namespace.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/core/namespace.c')
-rw-r--r--src/core/namespace.c760
1 files changed, 519 insertions, 241 deletions
diff --git a/src/core/namespace.c b/src/core/namespace.c
index 045321e1d4..43a2f4ba6e 100644
--- a/src/core/namespace.c
+++ b/src/core/namespace.c
@@ -1,5 +1,3 @@
-/*-*- Mode: C; c-basic-offset: 8; indent-tabs-mode: nil -*-*/
-
/***
This file is part of systemd.
@@ -20,23 +18,34 @@
***/
#include <errno.h>
-#include <sys/mount.h>
-#include <string.h>
+#include <sched.h>
#include <stdio.h>
-#include <unistd.h>
+#include <string.h>
+#include <sys/mount.h>
#include <sys/stat.h>
-#include <sched.h>
+#include <unistd.h>
#include <linux/fs.h>
-#include "strv.h"
-#include "util.h"
-#include "path-util.h"
-#include "missing.h"
-#include "loopback-setup.h"
+#include "alloc-util.h"
#include "dev-setup.h"
-#include "selinux-util.h"
-#include "namespace.h"
+#include "fd-util.h"
+#include "fs-util.h"
+#include "loopback-setup.h"
+#include "missing.h"
#include "mkdir.h"
+#include "mount-util.h"
+#include "namespace.h"
+#include "path-util.h"
+#include "selinux-util.h"
+#include "socket-util.h"
+#include "string-table.h"
+#include "string-util.h"
+#include "strv.h"
+#include "umask-util.h"
+#include "user-util.h"
+#include "util.h"
+
+#define DEV_MOUNT_OPTIONS (MS_NOSUID|MS_STRICTATIME|MS_NOEXEC)
typedef enum MountMode {
/* This is ordered by priority! */
@@ -45,62 +54,230 @@ typedef enum MountMode {
PRIVATE_TMP,
PRIVATE_VAR_TMP,
PRIVATE_DEV,
- PRIVATE_BUS_ENDPOINT,
- READWRITE
+ READWRITE,
} MountMode;
typedef struct BindMount {
- const char *path;
+ const char *path; /* stack memory, doesn't need to be freed explicitly */
+ char *chased; /* malloc()ed memory, needs to be freed */
MountMode mode;
- bool done;
- bool ignore;
+ bool ignore; /* Ignore if path does not exist */
} BindMount;
+typedef struct TargetMount {
+ const char *path;
+ MountMode mode;
+ bool ignore; /* Ignore if path does not exist */
+} TargetMount;
+
+/*
+ * The following Protect tables are to protect paths and mark some of them
+ * READONLY, in case a path is covered by an option from another table, then
+ * it is marked READWRITE in the current one, and the more restrictive mode is
+ * applied from that other table. This way all options can be combined in a
+ * safe and comprehensible way for users.
+ */
+
+/* ProtectKernelTunables= option and the related filesystem APIs */
+static const TargetMount protect_kernel_tunables_table[] = {
+ { "/proc/sys", READONLY, false },
+ { "/proc/sysrq-trigger", READONLY, true },
+ { "/proc/latency_stats", READONLY, true },
+ { "/proc/mtrr", READONLY, true },
+ { "/proc/apm", READONLY, true },
+ { "/proc/acpi", READONLY, true },
+ { "/proc/timer_stats", READONLY, true },
+ { "/proc/asound", READONLY, true },
+ { "/proc/bus", READONLY, true },
+ { "/proc/fs", READONLY, true },
+ { "/proc/irq", READONLY, true },
+ { "/sys", READONLY, false },
+ { "/sys/kernel/debug", READONLY, true },
+ { "/sys/kernel/tracing", READONLY, true },
+ { "/sys/fs/cgroup", READWRITE, false }, /* READONLY is set by ProtectControlGroups= option */
+};
+
+/*
+ * ProtectHome=read-only table, protect $HOME and $XDG_RUNTIME_DIR and rest of
+ * system should be protected by ProtectSystem=
+ */
+static const TargetMount protect_home_read_only_table[] = {
+ { "/home", READONLY, true },
+ { "/run/user", READONLY, true },
+ { "/root", READONLY, true },
+};
+
+/* ProtectHome=yes table */
+static const TargetMount protect_home_yes_table[] = {
+ { "/home", INACCESSIBLE, true },
+ { "/run/user", INACCESSIBLE, true },
+ { "/root", INACCESSIBLE, true },
+};
+
+/* ProtectSystem=yes table */
+static const TargetMount protect_system_yes_table[] = {
+ { "/usr", READONLY, false },
+ { "/boot", READONLY, true },
+ { "/efi", READONLY, true },
+};
+
+/* ProtectSystem=full includes ProtectSystem=yes */
+static const TargetMount protect_system_full_table[] = {
+ { "/usr", READONLY, false },
+ { "/boot", READONLY, true },
+ { "/efi", READONLY, true },
+ { "/etc", READONLY, false },
+};
+
+/*
+ * ProtectSystem=strict table. In this strict mode, we mount everything
+ * read-only, except for /proc, /dev, /sys which are the kernel API VFS,
+ * which are left writable, but PrivateDevices= + ProtectKernelTunables=
+ * protect those, and these options should be fully orthogonal.
+ * (And of course /home and friends are also left writable, as ProtectHome=
+ * shall manage those, orthogonally).
+ */
+static const TargetMount protect_system_strict_table[] = {
+ { "/", READONLY, false },
+ { "/proc", READWRITE, false }, /* ProtectKernelTunables= */
+ { "/sys", READWRITE, false }, /* ProtectKernelTunables= */
+ { "/dev", READWRITE, false }, /* PrivateDevices= */
+ { "/home", READWRITE, true }, /* ProtectHome= */
+ { "/run/user", READWRITE, true }, /* ProtectHome= */
+ { "/root", READWRITE, true }, /* ProtectHome= */
+};
+
+static void set_bind_mount(BindMount **p, const char *path, MountMode mode, bool ignore) {
+ (*p)->path = path;
+ (*p)->mode = mode;
+ (*p)->ignore = ignore;
+}
+
static int append_mounts(BindMount **p, char **strv, MountMode mode) {
char **i;
assert(p);
STRV_FOREACH(i, strv) {
+ bool ignore = false;
- (*p)->ignore = false;
- (*p)->done = false;
-
- if ((mode == INACCESSIBLE || mode == READONLY || mode == READWRITE) && (*i)[0] == '-') {
- (*p)->ignore = true;
+ if (IN_SET(mode, INACCESSIBLE, READONLY, READWRITE) && startswith(*i, "-")) {
(*i)++;
+ ignore = true;
}
if (!path_is_absolute(*i))
return -EINVAL;
- (*p)->path = *i;
- (*p)->mode = mode;
+ set_bind_mount(p, *i, mode, ignore);
(*p)++;
}
return 0;
}
-static int mount_path_compare(const void *a, const void *b) {
- const BindMount *p = a, *q = b;
- int d;
+static int append_target_mounts(BindMount **p, const char *root_directory, const TargetMount *mounts, const size_t size) {
+ unsigned i;
- d = path_compare(p->path, q->path);
+ assert(p);
+ assert(mounts);
+
+ for (i = 0; i < size; i++) {
+ /*
+ * Here we assume that the ignore field is set during
+ * declaration we do not support "-" at the beginning.
+ */
+ const TargetMount *m = &mounts[i];
+ const char *path = prefix_roota(root_directory, m->path);
+
+ if (!path_is_absolute(path))
+ return -EINVAL;
+
+ set_bind_mount(p, path, m->mode, m->ignore);
+ (*p)++;
+ }
+
+ return 0;
+}
+
+static int append_protect_kernel_tunables(BindMount **p, const char *root_directory) {
+ assert(p);
+
+ return append_target_mounts(p, root_directory, protect_kernel_tunables_table,
+ ELEMENTSOF(protect_kernel_tunables_table));
+}
+
+static int append_protect_home(BindMount **p, const char *root_directory, ProtectHome protect_home) {
+ int r = 0;
+
+ assert(p);
+
+ if (protect_home == PROTECT_HOME_NO)
+ return 0;
+
+ switch (protect_home) {
+ case PROTECT_HOME_READ_ONLY:
+ r = append_target_mounts(p, root_directory, protect_home_read_only_table,
+ ELEMENTSOF(protect_home_read_only_table));
+ break;
+ case PROTECT_HOME_YES:
+ r = append_target_mounts(p, root_directory, protect_home_yes_table,
+ ELEMENTSOF(protect_home_yes_table));
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+
+ return r;
+}
- if (d == 0) {
- /* If the paths are equal, check the mode */
- if (p->mode < q->mode)
- return -1;
+static int append_protect_system(BindMount **p, const char *root_directory, ProtectSystem protect_system) {
+ int r = 0;
- if (p->mode > q->mode)
- return 1;
+ assert(p);
+ if (protect_system == PROTECT_SYSTEM_NO)
return 0;
+
+ switch (protect_system) {
+ case PROTECT_SYSTEM_STRICT:
+ r = append_target_mounts(p, root_directory, protect_system_strict_table,
+ ELEMENTSOF(protect_system_strict_table));
+ break;
+ case PROTECT_SYSTEM_YES:
+ r = append_target_mounts(p, root_directory, protect_system_yes_table,
+ ELEMENTSOF(protect_system_yes_table));
+ break;
+ case PROTECT_SYSTEM_FULL:
+ r = append_target_mounts(p, root_directory, protect_system_full_table,
+ ELEMENTSOF(protect_system_full_table));
+ break;
+ default:
+ r = -EINVAL;
+ break;
}
+ return r;
+}
+
+static int mount_path_compare(const void *a, const void *b) {
+ const BindMount *p = a, *q = b;
+ int d;
+
/* If the paths are not equal, then order prefixes first */
- return d;
+ d = path_compare(p->path, q->path);
+ if (d != 0)
+ return d;
+
+ /* If the paths are equal, check the mode */
+ if (p->mode < q->mode)
+ return -1;
+
+ if (p->mode > q->mode)
+ return 1;
+
+ return 0;
}
static void drop_duplicates(BindMount *m, unsigned *n) {
@@ -109,16 +286,110 @@ static void drop_duplicates(BindMount *m, unsigned *n) {
assert(m);
assert(n);
+ /* Drops duplicate entries. Expects that the array is properly ordered already. */
+
for (f = m, t = m, previous = NULL; f < m+*n; f++) {
- /* The first one wins */
- if (previous && path_equal(f->path, previous->path))
+ /* The first one wins (which is the one with the more restrictive mode), see mount_path_compare()
+ * above. */
+ if (previous && path_equal(f->path, previous->path)) {
+ log_debug("%s is duplicate.", f->path);
continue;
+ }
*t = *f;
-
previous = t;
+ t++;
+ }
+
+ *n = t - m;
+}
+
+static void drop_inaccessible(BindMount *m, unsigned *n) {
+ BindMount *f, *t;
+ const char *clear = NULL;
+
+ assert(m);
+ assert(n);
+
+ /* Drops all entries obstructed by another entry further up the tree. Expects that the array is properly
+ * ordered already. */
+
+ for (f = m, t = m; f < m+*n; f++) {
+
+ /* If we found a path set for INACCESSIBLE earlier, and this entry has it as prefix we should drop
+ * it, as inaccessible paths really should drop the entire subtree. */
+ if (clear && path_startswith(f->path, clear)) {
+ log_debug("%s is masked by %s.", f->path, clear);
+ continue;
+ }
+
+ clear = f->mode == INACCESSIBLE ? f->path : NULL;
+
+ *t = *f;
+ t++;
+ }
+
+ *n = t - m;
+}
+
+static void drop_nop(BindMount *m, unsigned *n) {
+ BindMount *f, *t;
+
+ assert(m);
+ assert(n);
+
+ /* Drops all entries which have an immediate parent that has the same type, as they are redundant. Assumes the
+ * list is ordered by prefixes. */
+
+ for (f = m, t = m; f < m+*n; f++) {
+
+ /* Only suppress such subtrees for READONLY and READWRITE entries */
+ if (IN_SET(f->mode, READONLY, READWRITE)) {
+ BindMount *p;
+ bool found = false;
+
+ /* Now let's find the first parent of the entry we are looking at. */
+ for (p = t-1; p >= m; p--) {
+ if (path_startswith(f->path, p->path)) {
+ found = true;
+ break;
+ }
+ }
+
+ /* We found it, let's see if it's the same mode, if so, we can drop this entry */
+ if (found && p->mode == f->mode) {
+ log_debug("%s is redundant by %s", f->path, p->path);
+ continue;
+ }
+ }
+
+ *t = *f;
+ t++;
+ }
+
+ *n = t - m;
+}
+
+static void drop_outside_root(const char *root_directory, BindMount *m, unsigned *n) {
+ BindMount *f, *t;
+
+ assert(m);
+ assert(n);
+
+ if (!root_directory)
+ return;
+
+ /* Drops all mounts that are outside of the root directory. */
+ for (f = m, t = m; f < m+*n; f++) {
+
+ if (!path_startswith(f->path, root_directory)) {
+ log_debug("%s is outside of root directory.", f->path);
+ continue;
+ }
+
+ *t = *f;
t++;
}
@@ -148,7 +419,7 @@ static int mount_dev(BindMount *m) {
dev = strjoina(temporary_mount, "/dev");
(void) mkdir(dev, 0755);
- if (mount("tmpfs", dev, "tmpfs", MS_NOSUID|MS_STRICTATIME, "mode=755") < 0) {
+ if (mount("tmpfs", dev, "tmpfs", DEV_MOUNT_OPTIONS, "mode=755") < 0) {
r = -errno;
goto fail;
}
@@ -232,6 +503,8 @@ static int mount_dev(BindMount *m) {
*/
(void) mkdir_p_label(m->path, 0755);
+ /* Unmount everything in old /dev */
+ umount_recursive(m->path, 0);
if (mount(dev, m->path, NULL, MS_MOVE, NULL) < 0) {
r = -errno;
goto fail;
@@ -262,79 +535,6 @@ fail:
return r;
}
-static int mount_kdbus(BindMount *m) {
-
- char temporary_mount[] = "/tmp/kdbus-dev-XXXXXX";
- _cleanup_free_ char *basepath = NULL;
- _cleanup_umask_ mode_t u;
- char *busnode = NULL, *root;
- struct stat st;
- int r;
-
- assert(m);
-
- u = umask(0000);
-
- if (!mkdtemp(temporary_mount))
- return log_error_errno(errno, "Failed create temp dir: %m");
-
- root = strjoina(temporary_mount, "/kdbus");
- (void) mkdir(root, 0755);
- if (mount("tmpfs", root, "tmpfs", MS_NOSUID|MS_STRICTATIME, "mode=777") < 0) {
- r = -errno;
- goto fail;
- }
-
- /* create a new /dev/null dev node copy so we have some fodder to
- * bind-mount the custom endpoint over. */
- if (stat("/dev/null", &st) < 0) {
- log_error_errno(errno, "Failed to stat /dev/null: %m");
- r = -errno;
- goto fail;
- }
-
- busnode = strjoina(root, "/bus");
- if (mknod(busnode, (st.st_mode & ~07777) | 0600, st.st_rdev) < 0) {
- log_error_errno(errno, "mknod() for %s failed: %m", busnode);
- r = -errno;
- goto fail;
- }
-
- r = mount(m->path, busnode, NULL, MS_BIND, NULL);
- if (r < 0) {
- log_error_errno(errno, "bind mount of %s failed: %m", m->path);
- r = -errno;
- goto fail;
- }
-
- basepath = dirname_malloc(m->path);
- if (!basepath) {
- r = -ENOMEM;
- goto fail;
- }
-
- if (mount(root, basepath, NULL, MS_MOVE, NULL) < 0) {
- log_error_errno(errno, "bind mount of %s failed: %m", basepath);
- r = -errno;
- goto fail;
- }
-
- rmdir(temporary_mount);
- return 0;
-
-fail:
- if (busnode) {
- umount(busnode);
- unlink(busnode);
- }
-
- umount(root);
- rmdir(root);
- rmdir(temporary_mount);
-
- return r;
-}
-
static int apply_mount(
BindMount *m,
const char *tmp_dir,
@@ -345,23 +545,41 @@ static int apply_mount(
assert(m);
+ log_debug("Applying namespace mount on %s", m->path);
+
switch (m->mode) {
- case INACCESSIBLE:
+ case INACCESSIBLE: {
+ struct stat target;
/* First, get rid of everything that is below if there
* is anything... Then, overmount it with an
- * inaccessible directory. */
- umount_recursive(m->path, 0);
+ * inaccessible path. */
+ (void) umount_recursive(m->path, 0);
- what = "/run/systemd/inaccessible";
+ if (lstat(m->path, &target) < 0)
+ return log_debug_errno(errno, "Failed to lstat() %s to determine what to mount over it: %m", m->path);
+
+ what = mode_to_inaccessible_node(target.st_mode);
+ if (!what) {
+ log_debug("File type not supported for inaccessible mounts. Note that symlinks are not allowed");
+ return -ELOOP;
+ }
break;
+ }
case READONLY:
case READWRITE:
- /* Nothing to mount here, we just later toggle the
- * MS_RDONLY bit for the mount point */
- return 0;
+
+ r = path_is_mount_point(m->path, 0);
+ if (r < 0)
+ return log_debug_errno(r, "Failed to determine whether %s is already a mount point: %m", m->path);
+ if (r > 0) /* Nothing to do here, it is already a mount. We just later toggle the MS_RDONLY bit for the mount point if needed. */
+ return 0;
+
+ /* This isn't a mount point yet, let's make it one. */
+ what = m->path;
+ break;
case PRIVATE_TMP:
what = tmp_dir;
@@ -374,85 +592,155 @@ static int apply_mount(
case PRIVATE_DEV:
return mount_dev(m);
- case PRIVATE_BUS_ENDPOINT:
- return mount_kdbus(m);
-
default:
assert_not_reached("Unknown mode");
}
assert(what);
- r = mount(what, m->path, NULL, MS_BIND|MS_REC, NULL);
- if (r >= 0)
- log_debug("Successfully mounted %s to %s", what, m->path);
- else if (m->ignore && errno == ENOENT)
+ if (mount(what, m->path, NULL, MS_BIND|MS_REC, NULL) < 0)
+ return log_debug_errno(errno, "Failed to mount %s to %s: %m", what, m->path);
+
+ log_debug("Successfully mounted %s to %s", what, m->path);
+ return 0;
+}
+
+static int make_read_only(BindMount *m, char **blacklist) {
+ int r = 0;
+
+ assert(m);
+
+ if (IN_SET(m->mode, INACCESSIBLE, READONLY))
+ r = bind_remount_recursive(m->path, true, blacklist);
+ else if (m->mode == PRIVATE_DEV) { /* Can be readonly but the submounts can't*/
+ if (mount(NULL, m->path, NULL, MS_REMOUNT|DEV_MOUNT_OPTIONS|MS_RDONLY, NULL) < 0)
+ r = -errno;
+ } else
return 0;
+ /* Not that we only turn on the MS_RDONLY flag here, we never turn it off. Something that was marked read-only
+ * already stays this way. This improves compatibility with container managers, where we won't attempt to undo
+ * read-only mounts already applied. */
+
return r;
}
-static int make_read_only(BindMount *m) {
+static int chase_all_symlinks(const char *root_directory, BindMount *m, unsigned *n) {
+ BindMount *f, *t;
int r;
assert(m);
+ assert(n);
- if (IN_SET(m->mode, INACCESSIBLE, READONLY))
- r = bind_remount_recursive(m->path, true);
- else if (IN_SET(m->mode, READWRITE, PRIVATE_TMP, PRIVATE_VAR_TMP, PRIVATE_DEV))
- r = bind_remount_recursive(m->path, false);
- else
- r = 0;
+ /* Since mount() will always follow symlinks and we need to take the different root directory into account we
+ * chase the symlinks on our own first. This call wil do so for all entries and remove all entries where we
+ * can't resolve the path, and which have been marked for such removal. */
- if (m->ignore && r == -ENOENT)
- return 0;
+ for (f = m, t = m; f < m+*n; f++) {
- return r;
+ r = chase_symlinks(f->path, root_directory, &f->chased);
+ if (r == -ENOENT && f->ignore) /* Doesn't exist? Then remove it! */
+ continue;
+ if (r < 0)
+ return log_debug_errno(r, "Failed to chase symlinks for %s: %m", f->path);
+
+ if (path_equal(f->path, f->chased))
+ f->chased = mfree(f->chased);
+ else {
+ log_debug("Chased %s → %s", f->path, f->chased);
+ f->path = f->chased;
+ }
+
+ *t = *f;
+ t++;
+ }
+
+ *n = t - m;
+ return 0;
+}
+
+static unsigned namespace_calculate_mounts(
+ char** read_write_paths,
+ char** read_only_paths,
+ char** inaccessible_paths,
+ const char* tmp_dir,
+ const char* var_tmp_dir,
+ bool private_dev,
+ bool protect_sysctl,
+ bool protect_cgroups,
+ ProtectHome protect_home,
+ ProtectSystem protect_system) {
+
+ unsigned protect_home_cnt;
+ unsigned protect_system_cnt =
+ (protect_system == PROTECT_SYSTEM_STRICT ?
+ ELEMENTSOF(protect_system_strict_table) :
+ ((protect_system == PROTECT_SYSTEM_FULL) ?
+ ELEMENTSOF(protect_system_full_table) :
+ ((protect_system == PROTECT_SYSTEM_YES) ?
+ ELEMENTSOF(protect_system_yes_table) : 0)));
+
+ protect_home_cnt =
+ (protect_home == PROTECT_HOME_YES ?
+ ELEMENTSOF(protect_home_yes_table) :
+ ((protect_home == PROTECT_HOME_READ_ONLY) ?
+ ELEMENTSOF(protect_home_read_only_table) : 0));
+
+ return !!tmp_dir + !!var_tmp_dir +
+ strv_length(read_write_paths) +
+ strv_length(read_only_paths) +
+ strv_length(inaccessible_paths) +
+ private_dev +
+ (protect_sysctl ? ELEMENTSOF(protect_kernel_tunables_table) : 0) +
+ (protect_cgroups ? 1 : 0) +
+ protect_home_cnt + protect_system_cnt;
}
int setup_namespace(
const char* root_directory,
- char** read_write_dirs,
- char** read_only_dirs,
- char** inaccessible_dirs,
+ char** read_write_paths,
+ char** read_only_paths,
+ char** inaccessible_paths,
const char* tmp_dir,
const char* var_tmp_dir,
- const char* bus_endpoint_path,
bool private_dev,
+ bool protect_sysctl,
+ bool protect_cgroups,
ProtectHome protect_home,
ProtectSystem protect_system,
unsigned long mount_flags) {
BindMount *m, *mounts = NULL;
+ bool make_slave = false;
unsigned n;
int r = 0;
if (mount_flags == 0)
mount_flags = MS_SHARED;
- if (unshare(CLONE_NEWNS) < 0)
- return -errno;
+ n = namespace_calculate_mounts(read_write_paths,
+ read_only_paths,
+ inaccessible_paths,
+ tmp_dir, var_tmp_dir,
+ private_dev, protect_sysctl,
+ protect_cgroups, protect_home,
+ protect_system);
- n = !!tmp_dir + !!var_tmp_dir + !!bus_endpoint_path +
- strv_length(read_write_dirs) +
- strv_length(read_only_dirs) +
- strv_length(inaccessible_dirs) +
- private_dev +
- (protect_home != PROTECT_HOME_NO ? 3 : 0) +
- (protect_system != PROTECT_SYSTEM_NO ? 2 : 0) +
- (protect_system == PROTECT_SYSTEM_FULL ? 1 : 0);
+ /* Set mount slave mode */
+ if (root_directory || n > 0)
+ make_slave = true;
if (n > 0) {
m = mounts = (BindMount *) alloca0(n * sizeof(BindMount));
- r = append_mounts(&m, read_write_dirs, READWRITE);
+ r = append_mounts(&m, read_write_paths, READWRITE);
if (r < 0)
return r;
- r = append_mounts(&m, read_only_dirs, READONLY);
+ r = append_mounts(&m, read_only_paths, READONLY);
if (r < 0)
return r;
- r = append_mounts(&m, inaccessible_dirs, INACCESSIBLE);
+ r = append_mounts(&m, inaccessible_paths, INACCESSIBLE);
if (r < 0)
return r;
@@ -474,101 +762,112 @@ int setup_namespace(
m++;
}
- if (bus_endpoint_path) {
- m->path = prefix_roota(root_directory, bus_endpoint_path);
- m->mode = PRIVATE_BUS_ENDPOINT;
- m++;
- }
-
- if (protect_home != PROTECT_HOME_NO) {
- const char *home_dir, *run_user_dir, *root_dir;
+ if (protect_sysctl)
+ append_protect_kernel_tunables(&m, root_directory);
- home_dir = prefix_roota(root_directory, "/home");
- home_dir = strjoina("-", home_dir);
- run_user_dir = prefix_roota(root_directory, "/run/user");
- run_user_dir = strjoina("-", run_user_dir);
- root_dir = prefix_roota(root_directory, "/root");
- root_dir = strjoina("-", root_dir);
-
- r = append_mounts(&m, STRV_MAKE(home_dir, run_user_dir, root_dir),
- protect_home == PROTECT_HOME_READ_ONLY ? READONLY : INACCESSIBLE);
- if (r < 0)
- return r;
+ if (protect_cgroups) {
+ m->path = prefix_roota(root_directory, "/sys/fs/cgroup");
+ m->mode = READONLY;
+ m++;
}
- if (protect_system != PROTECT_SYSTEM_NO) {
- const char *usr_dir, *boot_dir, *etc_dir;
-
- usr_dir = prefix_roota(root_directory, "/usr");
- boot_dir = prefix_roota(root_directory, "/boot");
- boot_dir = strjoina("-", boot_dir);
- etc_dir = prefix_roota(root_directory, "/etc");
+ r = append_protect_home(&m, root_directory, protect_home);
+ if (r < 0)
+ return r;
- r = append_mounts(&m, protect_system == PROTECT_SYSTEM_FULL
- ? STRV_MAKE(usr_dir, boot_dir, etc_dir)
- : STRV_MAKE(usr_dir, boot_dir), READONLY);
- if (r < 0)
- return r;
- }
+ r = append_protect_system(&m, root_directory, protect_system);
+ if (r < 0)
+ return r;
assert(mounts + n == m);
+ /* Resolve symlinks manually first, as mount() will always follow them relative to the host's
+ * root. Moreover we want to suppress duplicates based on the resolved paths. This of course is a bit
+ * racy. */
+ r = chase_all_symlinks(root_directory, mounts, &n);
+ if (r < 0)
+ goto finish;
+
qsort(mounts, n, sizeof(BindMount), mount_path_compare);
+
drop_duplicates(mounts, &n);
+ drop_outside_root(root_directory, mounts, &n);
+ drop_inaccessible(mounts, &n);
+ drop_nop(mounts, &n);
+ }
+
+ if (unshare(CLONE_NEWNS) < 0) {
+ r = -errno;
+ goto finish;
}
- if (n > 0 || root_directory) {
+ if (make_slave) {
/* Remount / as SLAVE so that nothing now mounted in the namespace
shows up in the parent */
- if (mount(NULL, "/", NULL, MS_SLAVE|MS_REC, NULL) < 0)
- return -errno;
+ if (mount(NULL, "/", NULL, MS_SLAVE|MS_REC, NULL) < 0) {
+ r = -errno;
+ goto finish;
+ }
}
if (root_directory) {
- /* Turn directory into bind mount */
- if (mount(root_directory, root_directory, NULL, MS_BIND|MS_REC, NULL) < 0)
- return -errno;
+ /* Turn directory into bind mount, if it isn't one yet */
+ r = path_is_mount_point(root_directory, AT_SYMLINK_FOLLOW);
+ if (r < 0)
+ goto finish;
+ if (r == 0) {
+ if (mount(root_directory, root_directory, NULL, MS_BIND|MS_REC, NULL) < 0) {
+ r = -errno;
+ goto finish;
+ }
+ }
}
if (n > 0) {
+ char **blacklist;
+ unsigned j;
+
+ /* First round, add in all special mounts we need */
for (m = mounts; m < mounts + n; ++m) {
r = apply_mount(m, tmp_dir, var_tmp_dir);
if (r < 0)
- goto fail;
+ goto finish;
}
+ /* Create a blacklist we can pass to bind_mount_recursive() */
+ blacklist = newa(char*, n+1);
+ for (j = 0; j < n; j++)
+ blacklist[j] = (char*) mounts[j].path;
+ blacklist[j] = NULL;
+
+ /* Second round, flip the ro bits if necessary. */
for (m = mounts; m < mounts + n; ++m) {
- r = make_read_only(m);
+ r = make_read_only(m, blacklist);
if (r < 0)
- goto fail;
+ goto finish;
}
}
if (root_directory) {
/* MS_MOVE does not work on MS_SHARED so the remount MS_SHARED will be done later */
r = mount_move_root(root_directory);
-
- /* at this point, we cannot rollback */
if (r < 0)
- return r;
+ goto finish;
}
/* Remount / as the desired mode. Not that this will not
* reestablish propagation from our side to the host, since
* what's disconnected is disconnected. */
if (mount(NULL, "/", NULL, mount_flags | MS_REC, NULL) < 0) {
- /* at this point, we cannot rollback */
- return -errno;
+ r = -errno;
+ goto finish;
}
- return 0;
+ r = 0;
-fail:
- if (n > 0) {
- for (m = mounts; m < mounts + n; ++m)
- if (m->done)
- (void) umount2(m->path, MNT_DETACH);
- }
+finish:
+ for (m = mounts; m < mounts + n; m++)
+ free(m->chased);
return r;
}
@@ -645,16 +944,7 @@ int setup_tmp_dirs(const char *id, char **tmp_dir, char **var_tmp_dir) {
int setup_netns(int netns_storage_socket[2]) {
_cleanup_close_ int netns = -1;
- union {
- struct cmsghdr cmsghdr;
- uint8_t buf[CMSG_SPACE(sizeof(int))];
- } control = {};
- struct msghdr mh = {
- .msg_control = &control,
- .msg_controllen = sizeof(control),
- };
- struct cmsghdr *cmsg;
- int r;
+ int r, q;
assert(netns_storage_socket);
assert(netns_storage_socket[0] >= 0);
@@ -671,12 +961,8 @@ int setup_netns(int netns_storage_socket[2]) {
if (lockf(netns_storage_socket[0], F_LOCK, 0) < 0)
return -errno;
- if (recvmsg(netns_storage_socket[0], &mh, MSG_DONTWAIT|MSG_CMSG_CLOEXEC) < 0) {
- if (errno != EAGAIN) {
- r = -errno;
- goto fail;
- }
-
+ netns = receive_one_fd(netns_storage_socket[0], MSG_DONTWAIT);
+ if (netns == -EAGAIN) {
/* Nothing stored yet, so let's create a new namespace */
if (unshare(CLONE_NEWNET) < 0) {
@@ -693,15 +979,13 @@ int setup_netns(int netns_storage_socket[2]) {
}
r = 1;
- } else {
- /* Yay, found something, so let's join the namespace */
- CMSG_FOREACH(cmsg, &mh)
- if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == SCM_RIGHTS) {
- assert(cmsg->cmsg_len == CMSG_LEN(sizeof(int)));
- netns = *(int*) CMSG_DATA(cmsg);
- }
+ } else if (netns < 0) {
+ r = netns;
+ goto fail;
+ } else {
+ /* Yay, found something, so let's join the namespace */
if (setns(netns, CLONE_NEWNET) < 0) {
r = -errno;
goto fail;
@@ -710,21 +994,14 @@ int setup_netns(int netns_storage_socket[2]) {
r = 0;
}
- cmsg = CMSG_FIRSTHDR(&mh);
- cmsg->cmsg_level = SOL_SOCKET;
- cmsg->cmsg_type = SCM_RIGHTS;
- cmsg->cmsg_len = CMSG_LEN(sizeof(int));
- memcpy(CMSG_DATA(cmsg), &netns, sizeof(int));
- mh.msg_controllen = cmsg->cmsg_len;
-
- if (sendmsg(netns_storage_socket[1], &mh, MSG_DONTWAIT|MSG_NOSIGNAL) < 0) {
- r = -errno;
+ q = send_one_fd(netns_storage_socket[1], netns, MSG_DONTWAIT);
+ if (q < 0) {
+ r = q;
goto fail;
}
fail:
- lockf(netns_storage_socket[0], F_ULOCK, 0);
-
+ (void) lockf(netns_storage_socket[0], F_ULOCK, 0);
return r;
}
@@ -740,6 +1017,7 @@ static const char *const protect_system_table[_PROTECT_SYSTEM_MAX] = {
[PROTECT_SYSTEM_NO] = "no",
[PROTECT_SYSTEM_YES] = "yes",
[PROTECT_SYSTEM_FULL] = "full",
+ [PROTECT_SYSTEM_STRICT] = "strict",
};
DEFINE_STRING_TABLE_LOOKUP(protect_system, ProtectSystem);
generated by cgit v1.2.3-54-g00ecf (git 2.45.2) at 2024-07-22 23:42:28 +0000