On Fri, Mar 15, 2019 at 7:33 PM Richard Guy Briggs <rgb@xxxxxxxxxx> wrote: > Implement the proc fs write to set the audit container identifier of a > process, emitting an AUDIT_CONTAINER_OP record to document the event. > > This is a write from the container orchestrator task to a proc entry of > the form /proc/PID/audit_containerid where PID is the process ID of the > newly created task that is to become the first task in a container, or > an additional task added to a container. > > The write expects up to a u64 value (unset: 18446744073709551615). > > The writer must have capability CAP_AUDIT_CONTROL. > > This will produce a record such as this: > type=CONTAINER_OP msg=audit(2018-06-06 12:39:29.636:26949) : op=set opid=2209 old-contid=18446744073709551615 contid=123456 pid=628 auid=root uid=root tty=ttyS0 ses=1 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 comm=bash exe=/usr/bin/bash res=yes > > The "op" field indicates an initial set. The "pid" to "ses" fields are > the orchestrator while the "opid" field is the object's PID, the process > being "contained". Old and new audit container identifier values are > given in the "contid" fields, while res indicates its success. > > It is not permitted to unset the audit container identifier. > A child inherits its parent's audit container identifier. > > See: https://github.com/linux-audit/audit-kernel/issues/90 > See: https://github.com/linux-audit/audit-userspace/issues/51 > See: https://github.com/linux-audit/audit-testsuite/issues/64 > See: https://github.com/linux-audit/audit-kernel/wiki/RFE-Audit-Container-ID > > Signed-off-by: Richard Guy Briggs <rgb@xxxxxxxxxx> > Acked-by: Serge Hallyn <serge@xxxxxxxxxx> > Acked-by: Steve Grubb <sgrubb@xxxxxxxxxx> > Signed-off-by: Richard Guy Briggs <rgb@xxxxxxxxxx> Note that you have duplicate Signed-off here ^^ Took me a while to understand the flow in audit_set_contid(), but once understood it all made perfect sense, so: Reviewed-by: Ondrej Mosnacek <omosnace@xxxxxxxxxx> > --- > fs/proc/base.c | 36 ++++++++++++++++++++++++ > include/linux/audit.h | 25 +++++++++++++++++ > include/uapi/linux/audit.h | 2 ++ > kernel/audit.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++ > 4 files changed, 131 insertions(+) > > diff --git a/fs/proc/base.c b/fs/proc/base.c > index a23651ce6960..2505c46c8701 100644 > --- a/fs/proc/base.c > +++ b/fs/proc/base.c > @@ -1294,6 +1294,40 @@ static ssize_t proc_sessionid_read(struct file * file, char __user * buf, > .read = proc_sessionid_read, > .llseek = generic_file_llseek, > }; > + > +static ssize_t proc_contid_write(struct file *file, const char __user *buf, > + size_t count, loff_t *ppos) > +{ > + struct inode *inode = file_inode(file); > + u64 contid; > + 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 = kstrtou64_from_user(buf, count, 10, &contid); > + if (rv < 0) { > + put_task_struct(task); > + return rv; > + } > + > + rv = audit_set_contid(task, contid); > + put_task_struct(task); > + if (rv < 0) > + return rv; > + return count; > +} > + > +static const struct file_operations proc_contid_operations = { > + .write = proc_contid_write, > + .llseek = generic_file_llseek, > +}; > #endif > > #ifdef CONFIG_FAULT_INJECTION > @@ -3005,6 +3039,7 @@ static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, > #ifdef CONFIG_AUDIT > REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), > REG("sessionid", S_IRUGO, proc_sessionid_operations), > + REG("audit_containerid", S_IWUSR, proc_contid_operations), > #endif > #ifdef CONFIG_FAULT_INJECTION > REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), > @@ -3393,6 +3428,7 @@ static int proc_tid_comm_permission(struct inode *inode, int mask) > #ifdef CONFIG_AUDIT > REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), > REG("sessionid", S_IRUGO, proc_sessionid_operations), > + REG("audit_containerid", S_IWUSR, proc_contid_operations), > #endif > #ifdef CONFIG_FAULT_INJECTION > REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), > diff --git a/include/linux/audit.h b/include/linux/audit.h > index bde346e73f0c..301337776193 100644 > --- a/include/linux/audit.h > +++ b/include/linux/audit.h > @@ -89,6 +89,7 @@ struct audit_field { > struct audit_task_info { > kuid_t loginuid; > unsigned int sessionid; > + u64 contid; > #ifdef CONFIG_AUDITSYSCALL > struct audit_context *ctx; > #endif > @@ -189,6 +190,15 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk) > return tsk->audit->sessionid; > } > > +extern int audit_set_contid(struct task_struct *tsk, u64 contid); > + > +static inline u64 audit_get_contid(struct task_struct *tsk) > +{ > + if (!tsk->audit) > + return AUDIT_CID_UNSET; > + return tsk->audit->contid; > +} > + > extern u32 audit_enabled; > #else /* CONFIG_AUDIT */ > static inline int audit_alloc(struct task_struct *task) > @@ -250,6 +260,11 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk) > return AUDIT_SID_UNSET; > } > > +static inline u64 audit_get_contid(struct task_struct *tsk) > +{ > + return AUDIT_CID_UNSET; > +} > + > #define audit_enabled AUDIT_OFF > #endif /* CONFIG_AUDIT */ > > @@ -606,6 +621,16 @@ static inline bool audit_loginuid_set(struct task_struct *tsk) > return uid_valid(audit_get_loginuid(tsk)); > } > > +static inline bool audit_contid_valid(u64 contid) > +{ > + return contid != AUDIT_CID_UNSET; > +} > + > +static inline bool audit_contid_set(struct task_struct *tsk) > +{ > + return audit_contid_valid(audit_get_contid(tsk)); > +} > + > static inline void audit_log_string(struct audit_buffer *ab, const char *buf) > { > audit_log_n_string(ab, buf, strlen(buf)); > diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h > index 36a7e3f18e69..d475cf3b4d7f 100644 > --- a/include/uapi/linux/audit.h > +++ b/include/uapi/linux/audit.h > @@ -71,6 +71,7 @@ > #define AUDIT_TTY_SET 1017 /* Set TTY auditing status */ > #define AUDIT_SET_FEATURE 1018 /* Turn an audit feature on or off */ > #define AUDIT_GET_FEATURE 1019 /* Get which features are enabled */ > +#define AUDIT_CONTAINER_OP 1020 /* Define the container id and information */ > > #define AUDIT_FIRST_USER_MSG 1100 /* Userspace messages mostly uninteresting to kernel */ > #define AUDIT_USER_AVC 1107 /* We filter this differently */ > @@ -471,6 +472,7 @@ struct audit_tty_status { > > #define AUDIT_UID_UNSET (unsigned int)-1 > #define AUDIT_SID_UNSET ((unsigned int)-1) > +#define AUDIT_CID_UNSET ((u64)-1) > > /* audit_rule_data supports filter rules with both integer and string > * fields. It corresponds with AUDIT_ADD_RULE, AUDIT_DEL_RULE and > diff --git a/kernel/audit.c b/kernel/audit.c > index 67498c5690bb..b5c702abeb42 100644 > --- a/kernel/audit.c > +++ b/kernel/audit.c > @@ -244,6 +244,7 @@ int audit_alloc(struct task_struct *tsk) > } > info->loginuid = audit_get_loginuid(current); > info->sessionid = audit_get_sessionid(current); > + info->contid = audit_get_contid(current); > tsk->audit = info; > > ret = audit_alloc_syscall(tsk); > @@ -258,6 +259,7 @@ int audit_alloc(struct task_struct *tsk) > struct audit_task_info init_struct_audit = { > .loginuid = INVALID_UID, > .sessionid = AUDIT_SID_UNSET, > + .contid = AUDIT_CID_UNSET, > #ifdef CONFIG_AUDITSYSCALL > .ctx = NULL, > #endif > @@ -2341,6 +2343,72 @@ int audit_set_loginuid(kuid_t loginuid) > } > > /** > + * audit_set_contid - set current task's audit contid > + * @contid: contid value > + * > + * Returns 0 on success, -EPERM on permission failure. > + * > + * Called (set) from fs/proc/base.c::proc_contid_write(). > + */ > +int audit_set_contid(struct task_struct *task, u64 contid) > +{ > + u64 oldcontid; > + int rc = 0; > + struct audit_buffer *ab; > + uid_t uid; > + struct tty_struct *tty; > + char comm[sizeof(current->comm)]; > + > + task_lock(task); > + /* Can't set if audit disabled */ > + if (!task->audit) { > + task_unlock(task); > + return -ENOPROTOOPT; > + } > + oldcontid = audit_get_contid(task); > + read_lock(&tasklist_lock); > + /* Don't allow the audit containerid to be unset */ > + if (!audit_contid_valid(contid)) > + rc = -EINVAL; > + /* if we don't have caps, reject */ > + else if (!capable(CAP_AUDIT_CONTROL)) > + rc = -EPERM; > + /* if task has children or is not single-threaded, deny */ > + else if (!list_empty(&task->children)) > + rc = -EBUSY; > + else if (!(thread_group_leader(task) && thread_group_empty(task))) > + rc = -EALREADY; > + read_unlock(&tasklist_lock); > + if (!rc) > + task->audit->contid = contid; > + task_unlock(task); > + > + if (!audit_enabled) > + return rc; > + > + ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONTAINER_OP); > + if (!ab) > + return rc; > + > + uid = from_kuid(&init_user_ns, task_uid(current)); > + tty = audit_get_tty(); > + audit_log_format(ab, "op=set opid=%d old-contid=%llu contid=%llu pid=%d uid=%u auid=%u tty=%s ses=%u", > + task_tgid_nr(task), oldcontid, contid, > + task_tgid_nr(current), uid, > + from_kuid(&init_user_ns, audit_get_loginuid(current)), > + tty ? tty_name(tty) : "(none)", > + audit_get_sessionid(current)); > + audit_put_tty(tty); > + audit_log_task_context(ab); > + audit_log_format(ab, " comm="); > + audit_log_untrustedstring(ab, get_task_comm(comm, current)); > + audit_log_d_path_exe(ab, current->mm); > + audit_log_format(ab, " res=%d", !rc); > + audit_log_end(ab); > + return rc; > +} > + > +/** > * audit_log_end - end one audit record > * @ab: the audit_buffer > * > -- > 1.8.3.1 > -- Ondrej Mosnacek <omosnace at redhat dot com> Software Engineer, Security Technologies Red Hat, Inc.
