@@ -11,3 +11,19 @@ Description:
or have its own /proc/$pid/capcontainerid set to write
or read.
+
+What: Capability to set or get the Audit Container Identifier
+Date: 2020-??
+KernelVersion: 5.10?
+Contact: linux-audit@redhat.com
+Format: u32
+Users: auditd, libaudit, audit-testsuite, podman(?), container orchestrators
+Description:
+ The /proc/$pid/audit_capcontainerid pseudofile is
+ written to set and is read to get the capability of
+ process $pid to write or to read the /proc/$pid/containerid
+ audit container identifier of any of its descendants.
+ "1" allows and "0" denies that capability. This
+ property is an extension to CAP_AUDIT_CONTROL outside of
+ the initial user namespace.
+
@@ -1381,6 +1381,58 @@ static const struct file_operations proc_contid_operations = {
.write = proc_contid_write,
.llseek = generic_file_llseek,
};
+
+static ssize_t proc_capcontid_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct inode *inode = file_inode(file);
+ struct task_struct *task = get_proc_task(inode);
+ ssize_t length;
+ char tmpbuf[TMPBUFLEN];
+
+ if (!task)
+ return -ESRCH;
+ length = audit_get_capcontid_proc(tmpbuf, TMPBUFLEN, task);
+ put_task_struct(task);
+ if (length < 0)
+ return length;
+ return simple_read_from_buffer(buf, count, ppos, tmpbuf, length);
+}
+
+static ssize_t proc_capcontid_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct inode *inode = file_inode(file);
+ u32 capcontid;
+ int rv;
+ struct task_struct *task = get_proc_task(inode);
+
+ if (!task)
+ return -ESRCH;
+ if (*ppos != 0) {
+ /* No partial writes. */
+ put_task_struct(task);
+ return -EINVAL;
+ }
+
+ rv = kstrtou32_from_user(buf, count, 10, &capcontid);
+ if (rv < 0) {
+ put_task_struct(task);
+ return rv;
+ }
+
+ rv = audit_set_capcontid(task, capcontid);
+ put_task_struct(task);
+ if (rv < 0)
+ return rv;
+ return count;
+}
+
+static const struct file_operations proc_capcontid_operations = {
+ .read = proc_capcontid_read,
+ .write = proc_capcontid_write,
+ .llseek = generic_file_llseek,
+};
#endif
#ifdef CONFIG_FAULT_INJECTION
@@ -3284,6 +3336,7 @@ static const struct pid_entry tgid_base_stuff[] = {
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
REG("audit_containerid", S_IWUSR|S_IRUSR, proc_contid_operations),
+ REG("audit_capcontainerid", S_IWUSR|S_IRUSR, proc_capcontid_operations),
#endif
#ifdef CONFIG_FAULT_INJECTION
REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
@@ -3624,6 +3677,7 @@ static const struct pid_entry tid_base_stuff[] = {
REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations),
REG("sessionid", S_IRUGO, proc_sessionid_operations),
REG("audit_containerid", S_IWUSR|S_IRUSR, proc_contid_operations),
+ REG("audit_capcontainerid", S_IWUSR|S_IRUSR, proc_capcontid_operations),
#endif
#ifdef CONFIG_FAULT_INJECTION
REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
@@ -214,8 +214,10 @@ extern void audit_set_sessionid_iouring(unsigned int sessionid);
extern int audit_get_contid_proc(char *tmpbuf, int TMPBUFLEN,
struct task_struct *task);
-
+extern int audit_get_capcontid_proc(char *tmpbuf, int TMPBUFLEN,
+ struct task_struct *task);
extern int audit_set_contid(struct task_struct *tsk, u64 contid);
+extern int audit_set_capcontid(struct task_struct *tsk, u32 enable);
extern void audit_copy_namespaces(struct net *net, struct task_struct *tsk);
extern void audit_switch_task_namespaces(struct nsproxy *ns,
@@ -73,6 +73,7 @@
#define AUDIT_GET_FEATURE 1019 /* Get which features are enabled */
#define AUDIT_CONTAINER_OP 1020 /* Define the container id and info */
#define AUDIT_SIGNAL_INFO2 1021 /* Get info auditd signal sender */
+#define AUDIT_SET_CAPCONTID 1022 /* Set cap_contid of a task */
#define AUDIT_FIRST_USER_MSG 1100 /* Userspace messages mostly uninteresting to kernel */
#define AUDIT_USER_AVC 1107 /* We filter this differently */
@@ -238,6 +238,7 @@ struct audit_task_info {
kuid_t loginuid;
unsigned int sessionid;
struct audit_contobj *cont;
+ u32 capcontid;
#ifdef CONFIG_AUDITSYSCALL
struct audit_context *ctx;
#endif
@@ -308,6 +309,15 @@ static inline u64 audit_get_contid(struct task_struct *tsk)
return info->cont->id;
}
+static inline u32 audit_get_capcontid(struct task_struct *tsk)
+{
+ struct audit_task_info *info = tsk->audit;
+
+ if (!info)
+ return 0;
+ return info->capcontid;
+}
+
inline struct audit_context *_audit_context(struct task_struct *tsk)
{
struct audit_task_info *info = tsk->audit;
@@ -419,6 +429,7 @@ static void audit_alloc_task(struct task_struct *tsk)
rcu_read_lock();
info->cont = _audit_contobj_get_bytask(current);
rcu_read_unlock();
+ info->capcontid = 0;
tsk->audit = info;
}
@@ -2987,6 +2998,56 @@ static bool audit_contid_isnesting(struct task_struct *tsk)
return !isowner && ownerisparent;
}
+int audit_set_capcontid(struct task_struct *tsk, u32 enable)
+{
+ u32 oldcapcontid;
+ int rc = 0;
+ struct audit_buffer *ab;
+ struct audit_task_info *info = tsk->audit;
+
+ if (!info)
+ return -ENOPROTOOPT;
+ oldcapcontid = audit_get_capcontid(tsk);
+ /* if task is not descendant, block */
+ if (tsk == current || !task_is_descendant(current, tsk))
+ rc = -EXDEV;
+ else if (current_user_ns() == &init_user_ns) {
+ if (!capable(CAP_AUDIT_CONTROL) &&
+ !audit_get_capcontid(current))
+ rc = -EPERM;
+ }
+ if (!rc)
+ info->capcontid = enable;
+
+ if (!audit_enabled)
+ return rc;
+
+ ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_SET_CAPCONTID);
+ if (!ab)
+ return rc;
+
+ audit_log_format(ab,
+ "opid=%d capcontid=%u old-capcontid=%u",
+ task_tgid_nr(tsk), enable, oldcapcontid);
+ audit_log_end(ab);
+ return rc;
+}
+
+int audit_get_capcontid_proc(char *tmpbuf, int TMPBUFLEN,
+ struct task_struct *tsk)
+{
+ int length;
+
+ /* if we don't have caps, reject */
+ if (!capable(CAP_AUDIT_CONTROL) && !audit_get_capcontid(current)) {
+ length = -EPERM;
+ goto out;
+ }
+ length = scnprintf(tmpbuf, TMPBUFLEN, "%u", audit_get_capcontid(tsk));
+out:
+ return length;
+}
+
/*
* audit_set_contid - set current task's audit contid
* @tsk: target task
@@ -3020,7 +3081,7 @@ int audit_set_contid(struct task_struct *tsk, u64 contid)
if (contid == AUDIT_CID_UNSET) {
/* Don't allow the contid to be unset */
rc = -EINVAL;
- } else if (!capable(CAP_AUDIT_CONTROL)) {
+ } else if (!capable(CAP_AUDIT_CONTROL) && !audit_get_capcontid(current)) {
/* if we don't have caps, reject */
rc = -EPERM;
} else if (!list_empty(&tsk->children) ||
@@ -3110,7 +3171,7 @@ int audit_get_contid_proc(char *tmpbuf, int TMPBUFLEN,
int length;
/* if we don't have caps, reject */
- if (!capable(CAP_AUDIT_CONTROL)) {
+ if (!capable(CAP_AUDIT_CONTROL) && !audit_get_capcontid(current)) {
length = -EPERM;
goto out;
}
Provide a mechanism similar to CAP_AUDIT_CONTROL to explicitly give a process in a non-init user namespace the capability to set audit container identifiers of individual children. Provide the /proc/$PID/audit_capcontid interface to capcontid. Valid values are: 1==enabled, 0==disabled Writing a "1" to this special file for the target process $PID will enable the target process to set audit container identifiers of its descendants. A process must already have CAP_AUDIT_CONTROL in the initial user namespace or have had audit_capcontid enabled by a previous use of this feature by its parent on this process in order to be able to enable it for another process. The target process must be a descendant of the calling process. Report this action in new message type AUDIT_SET_CAPCONTID 1022 with fields opid= capcontid= old-capcontid= Add an entry to Documentation/ABI. Signed-off-by: Richard Guy Briggs <rgb@redhat.com> --- .../ABI/testing/procfs-audit_containerid | 16 +++++ fs/proc/base.c | 54 +++++++++++++++ include/linux/audit.h | 4 +- include/uapi/linux/audit.h | 1 + kernel/audit.c | 65 ++++++++++++++++++- 5 files changed, 137 insertions(+), 3 deletions(-)