The audit-related parameters in struct task_struct should ideally be collected together and accessed through a standard audit API. Collect the existing loginuid, sessionid and audit_context together in a new struct audit_task_info called "audit" in struct task_struct. Use kmem_cache to manage this pool of memory. Un-inline audit_free() to be able to always recover that memory. Please see the upstream github issue https://github.com/linux-audit/audit-kernel/issues/81 but that issue has been closed with this patch included with https://github.com/linux-audit/audit-kernel/issues/90 Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt;

--- include/linux/audit.h | 49 +++++++++++++++++++++++------------ include/linux/sched.h | 7 +---- init/init_task.c | 3 +-- init/main.c | 2 ++ kernel/audit.c | 71 +++++++++++++++++++++++++++++++++++++++++++++++++-- kernel/audit.h | 5 ++++ kernel/auditsc.c | 26 ++++++++++--------- kernel/fork.c | 1 - 8 files changed, 124 insertions(+), 40 deletions(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index 1e69d9fe16da..bde346e73f0c 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -86,6 +86,16 @@ struct audit_field { u32 op; }; +struct audit_task_info { + kuid_t loginuid; + unsigned int sessionid; +#ifdef CONFIG_AUDITSYSCALL + struct audit_context *ctx; +#endif +}; + +extern struct audit_task_info init_struct_audit; + extern int is_audit_feature_set(int which); extern int __init audit_register_class(int class, unsigned *list); @@ -122,6 +132,9 @@ struct audit_field { #ifdef CONFIG_AUDIT /* These are defined in audit.c */ /* Public API */ +extern int audit_alloc(struct task_struct *task); +extern void audit_free(struct task_struct *task); +extern void __init audit_task_init(void); extern __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...); @@ -164,16 +177,28 @@ extern void audit_log_key(struct audit_buffer *ab, static inline kuid_t audit_get_loginuid(struct task_struct *tsk) { - return tsk->loginuid; + if (!tsk->audit) + return INVALID_UID; + return tsk->audit->loginuid; } static inline unsigned int audit_get_sessionid(struct task_struct *tsk) { - return tsk->sessionid; + if (!tsk->audit) + return AUDIT_SID_UNSET; + return tsk->audit->sessionid; } extern u32 audit_enabled; #else /* CONFIG_AUDIT */ +static inline int audit_alloc(struct task_struct *task) +{ + return 0; +} +static inline void audit_free(struct task_struct *task) +{ } +static inline void __init audit_task_init(void) +{ } static inline __printf(4, 5) void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) @@ -239,8 +264,6 @@ static inline unsigned int audit_get_sessionid(struct task_struct *tsk) /* These are defined in auditsc.c */ /* Public API */ -extern int audit_alloc(struct task_struct *task); -extern void __audit_free(struct task_struct *task); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); @@ -263,12 +286,14 @@ extern void audit_seccomp_actions_logged(const char *names, static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx) { - task->audit_context = ctx; + task->audit->ctx = ctx; } static inline struct audit_context *audit_context(void) { - return current->audit_context; + if (!current->audit) + return NULL; + return current->audit->ctx; } static inline bool audit_dummy_context(void) @@ -276,11 +301,7 @@ static inline bool audit_dummy_context(void) void *p = audit_context(); return !p || *(int *)p; } -static inline void audit_free(struct task_struct *task) -{ - if (unlikely(task->audit_context)) - __audit_free(task); -} + static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) @@ -470,12 +491,6 @@ static inline void audit_fanotify(unsigned int response) extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ -static inline int audit_alloc(struct task_struct *task) -{ - return 0; -} -static inline void audit_free(struct task_struct *task) -{ } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) diff --git a/include/linux/sched.h b/include/linux/sched.h index 765119df759a..6850d1e48ace 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -31,7 +31,6 @@ #include <linux/rseq.h> /* task_struct member predeclarations (sorted alphabetically): */ -struct audit_context; struct backing_dev_info; struct bio_list; struct blk_plug; @@ -886,11 +885,7 @@ struct task_struct { struct callback_head *task_works; #ifdef CONFIG_AUDIT -#ifdef CONFIG_AUDITSYSCALL - struct audit_context *audit_context; -#endif - kuid_t loginuid; - unsigned int sessionid; + struct audit_task_info *audit; #endif struct seccomp seccomp; diff --git a/init/init_task.c b/init/init_task.c index 39c3109acc1a..f9685e1edda1 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -122,8 +122,7 @@ struct task_struct init_task .thread_group = LIST_HEAD_INIT(init_task.thread_group), .thread_node = LIST_HEAD_INIT(init_signals.thread_head), #ifdef CONFIG_AUDIT - .loginuid = INVALID_UID, - .sessionid = AUDIT_SID_UNSET, + .audit = &init_struct_audit, #endif #ifdef CONFIG_PERF_EVENTS .perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex), diff --git a/init/main.c b/init/main.c index e2e80ca3165a..8a1c36625d12 100644 --- a/init/main.c +++ b/init/main.c @@ -92,6 +92,7 @@ #include <linux/rodata_test.h> #include <linux/jump_label.h> #include <linux/mem_encrypt.h> +#include <linux/audit.h> #include <asm/io.h> #include <asm/bugs.h> @@ -727,6 +728,7 @@ asmlinkage __visible void __init start_kernel(void) nsfs_init(); cpuset_init(); cgroup_init(); + audit_task_init(); taskstats_init_early(); delayacct_init(); diff --git a/kernel/audit.c b/kernel/audit.c index c89ea48c70a6..67498c5690bb 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -215,6 +215,73 @@ struct audit_reply { struct sk_buff *skb; }; +static struct kmem_cache *audit_task_cache; + +void __init audit_task_init(void) +{ + audit_task_cache = kmem_cache_create("audit_task", + sizeof(struct audit_task_info), + 0, SLAB_PANIC, NULL); +} + +/** + * audit_alloc - allocate an audit info block for a task + * @tsk: task + * + * Call audit_alloc_syscall to filter on the task information and + * allocate a per-task audit context if necessary. This is called from + * copy_process, so no lock is needed. + */ +int audit_alloc(struct task_struct *tsk) +{ + int ret = 0; + struct audit_task_info *info; + + info = kmem_cache_alloc(audit_task_cache, GFP_KERNEL); + if (!info) { + ret = -ENOMEM; + goto out; + } + info->loginuid = audit_get_loginuid(current); + info->sessionid = audit_get_sessionid(current); + tsk->audit = info; + + ret = audit_alloc_syscall(tsk); + if (ret) { + tsk->audit = NULL; + kmem_cache_free(audit_task_cache, info); + } +out: + return ret; +} + +struct audit_task_info init_struct_audit = { + .loginuid = INVALID_UID, + .sessionid = AUDIT_SID_UNSET, +#ifdef CONFIG_AUDITSYSCALL + .ctx = NULL, +#endif +}; + +/** + * audit_free - free per-task audit info + * @tsk: task whose audit info block to free + * + * Called from copy_process and do_exit + */ +void audit_free(struct task_struct *tsk) +{ + struct audit_task_info *info = tsk->audit; + + audit_free_syscall(tsk); + /* Freeing the audit_task_info struct must be performed after + * audit_log_exit() due to need for loginuid and sessionid. + */ + info = tsk->audit; + tsk->audit = NULL; + kmem_cache_free(audit_task_cache, info); +} + /** * auditd_test_task - Check to see if a given task is an audit daemon * @task: the task to check @@ -2266,8 +2333,8 @@ int audit_set_loginuid(kuid_t loginuid) sessionid = (unsigned int)atomic_inc_return(&session_id); } - current->sessionid = sessionid; - current->loginuid = loginuid; + current->audit->sessionid = sessionid; + current->audit->loginuid = loginuid; out: audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc); return rc; diff --git a/kernel/audit.h b/kernel/audit.h index 958d5b8fc1b3..c00e2ee3c6b3 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -264,6 +264,8 @@ extern void audit_log_d_path_exe(struct audit_buffer *ab, extern unsigned int audit_serial(void); extern int auditsc_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial); +extern int audit_alloc_syscall(struct task_struct *tsk); +extern void audit_free_syscall(struct task_struct *tsk); extern void audit_put_watch(struct audit_watch *watch); extern void audit_get_watch(struct audit_watch *watch); @@ -305,6 +307,9 @@ extern void audit_filter_inodes(struct task_struct *tsk, extern struct list_head *audit_killed_trees(void); #else /* CONFIG_AUDITSYSCALL */ #define auditsc_get_stamp(c, t, s) 0 +#define audit_alloc_syscall(t) 0 +#define audit_free_syscall(t) {} + #define audit_put_watch(w) {} #define audit_get_watch(w) {} #define audit_to_watch(k, p, l, o) (-EINVAL) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index d1eab1d4a930..8090eff7868d 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -885,23 +885,25 @@ static inline struct audit_context *audit_alloc_context(enum audit_state state) return context; } -/** - * audit_alloc - allocate an audit context block for a task +/* + * audit_alloc_syscall - allocate an audit context block for a task * @tsk: task * * Filter on the task information and allocate a per-task audit context * if necessary. Doing so turns on system call auditing for the - * specified task. This is called from copy_process, so no lock is - * needed. + * specified task. This is called from copy_process via audit_alloc, so + * no lock is needed. */ -int audit_alloc(struct task_struct *tsk) +int audit_alloc_syscall(struct task_struct *tsk) { struct audit_context *context; enum audit_state state; char *key = NULL; - if (likely(!audit_ever_enabled)) + if (likely(!audit_ever_enabled)) { + audit_set_context(tsk, NULL); return 0; /* Return if not auditing. */ + } state = audit_filter_task(tsk, &key); if (state == AUDIT_DISABLED) { @@ -911,7 +913,7 @@ int audit_alloc(struct task_struct *tsk) if (!(context = audit_alloc_context(state))) { kfree(key); - audit_log_lost("out of memory in audit_alloc"); + audit_log_lost("out of memory in audit_alloc_syscall"); return -ENOMEM; } context->filterkey = key; @@ -1555,14 +1557,15 @@ static void audit_log_exit(void) } /** - * __audit_free - free a per-task audit context + * audit_free_syscall - free per-task audit context info * @tsk: task whose audit context block to free * - * Called from copy_process and do_exit + * Called from audit_free */ -void __audit_free(struct task_struct *tsk) +void audit_free_syscall(struct task_struct *tsk) { - struct audit_context *context = tsk->audit_context; + struct audit_task_info *info = tsk->audit; + struct audit_context *context = info->ctx; if (!context) return; @@ -1585,7 +1588,6 @@ void __audit_free(struct task_struct *tsk) if (context->current_state == AUDIT_RECORD_CONTEXT) audit_log_exit(); } - audit_set_context(tsk, NULL); audit_free_context(context); } diff --git a/kernel/fork.c b/kernel/fork.c index a60459947f18..1107bd8b8ad8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1836,7 +1836,6 @@ static __latent_entropy struct task_struct *copy_process( p->start_time = ktime_get_ns(); p->real_start_time = ktime_get_boot_ns(); p->io_context = NULL; - audit_set_context(p, NULL); cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); -- 1.8.3.1

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(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; Acked-by: Steve Grubb <sgrubb(a)redhat.com&gt; Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; --- 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

On Fri, Mar 15, 2019 at 7:33 PM Richard Guy Briggs <rgb(a)redhat.com&gt; 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(a)redhat.com&gt; > Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; > Acked-by: Steve Grubb <sgrubb(a)redhat.com&gt; > Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; 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(a)redhat.com&gt; > --- > 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.

Add support for reading the audit container identifier from the proc filesystem. This is a read from the proc entry of the form /proc/PID/audit_containerid where PID is the process ID of the task whose audit container identifier is sought. The read expects up to a u64 value (unset: 18446744073709551615). This read requires CAP_AUDIT_CONTROL. Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; --- fs/proc/base.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 2505c46c8701..0b833cbdf5b6 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1295,6 +1295,24 @@ static ssize_t proc_sessionid_read(struct file * file, char __user * buf, .llseek = generic_file_llseek, }; +static ssize_t proc_contid_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*2]; +

+ if (!task) + return -ESRCH; + /* if we don't have caps, reject */ + if (!capable(CAP_AUDIT_CONTROL)) + return -EPERM; + length = scnprintf(tmpbuf, TMPBUFLEN*2, "%llu", audit_get_contid(task)); + put_task_struct(task); + return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); +} + static ssize_t proc_contid_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -1325,6 +1343,7 @@ static ssize_t proc_contid_write(struct file *file, const char __user *buf, } static const struct file_operations proc_contid_operations = { + .read = proc_contid_read, .write = proc_contid_write, .llseek = generic_file_llseek, }; @@ -3039,7 +3058,7 @@ 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), + REG("audit_containerid", S_IWUSR|S_IRUSR, proc_contid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), @@ -3428,7 +3447,7 @@ 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), + REG("audit_containerid", S_IWUSR|S_IRUSR, proc_contid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), -- 1.8.3.1

On 2019-03-18 07:10, Neil Horman wrote: > On Fri, Mar 15, 2019 at 02:29:51PM -0400, Richard Guy Briggs wrote: > > Add support for reading the audit container identifier from the proc > > filesystem. > > > > This is a read from the proc entry of the form > > /proc/PID/audit_containerid where PID is the process ID of the task > > whose audit container identifier is sought. > > > > The read expects up to a u64 value (unset: 18446744073709551615). > > > > This read requires CAP_AUDIT_CONTROL. > > > > Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; > > Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; > > --- > > fs/proc/base.c | 23 +++++++++++++++++++++-- > > 1 file changed, 21 insertions(+), 2 deletions(-) > > > > diff --git a/fs/proc/base.c b/fs/proc/base.c > > index 2505c46c8701..0b833cbdf5b6 100644 > > --- a/fs/proc/base.c > > +++ b/fs/proc/base.c > > @@ -1295,6 +1295,24 @@ static ssize_t proc_sessionid_read(struct file * file, char __user * buf, > > .llseek = generic_file_llseek, > > }; > > > > +static ssize_t proc_contid_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*2]; > > + > Sorry, didn't notice this previously, but.. > Why *2 here? Its not wrong per-se, but would it be better to just change > TMPBUFLEN to be 22 bytes unilaterally? Its only ever used on stack calls that > arent that deep, and then you won't have to think about adjusting this call site > if you ever change the value of TMPBUFLEN in the future. TMPBUFLEN is 11 to accomodate a decimal representation of a u32 with terminating NULL. Since the contid is a u64, it was least disruptive and made sense to me to just double it. I could define a TMPBUFLEN2 to be 21 if you prefer?

> I'm fine with doing this in another patch later, but it seems like a worthwhile > cleanup > > functionality looks good beyond that nit. > > > + if (!task) > > + return -ESRCH; > > + /* if we don't have caps, reject */ > > + if (!capable(CAP_AUDIT_CONTROL)) > > + return -EPERM; > > + length = scnprintf(tmpbuf, TMPBUFLEN*2, "%llu", audit_get_contid(task)); > > + put_task_struct(task); > > + return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); > > +} > > + > > static ssize_t proc_contid_write(struct file *file, const char __user *buf, > > size_t count, loff_t *ppos) > > { > > @@ -1325,6 +1343,7 @@ static ssize_t proc_contid_write(struct file *file, const char __user *buf, > > } > > > > static const struct file_operations proc_contid_operations = { > > + .read = proc_contid_read, > > .write = proc_contid_write, > > .llseek = generic_file_llseek, > > }; > > @@ -3039,7 +3058,7 @@ 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), > > + REG("audit_containerid", S_IWUSR|S_IRUSR, proc_contid_operations), > > #endif > > #ifdef CONFIG_FAULT_INJECTION > > REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), > > @@ -3428,7 +3447,7 @@ 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), > > + REG("audit_containerid", S_IWUSR|S_IRUSR, proc_contid_operations), > > #endif > > #ifdef CONFIG_FAULT_INJECTION > > REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), > > -- > > 1.8.3.1 > > > > > Acked-by: Neil Horman <nhorman(a)tuxdriver.com&gt; > - RGB -- Richard Guy Briggs <rgb(a)redhat.com&gt; Sr. S/W Engineer, Kernel Security, Base Operating Systems Remote, Ottawa, Red Hat Canada IRC: rgb, SunRaycer Voice: +1.647.777.2635, Internal: (81) 32635

Add support for reading the audit container identifier from the proc filesystem. This is a read from the proc entry of the form /proc/PID/audit_containerid where PID is the process ID of the task whose audit container identifier is sought. The read expects up to a u64 value (unset: 18446744073709551615). This read requires CAP_AUDIT_CONTROL. Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt;

--- fs/proc/base.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/fs/proc/base.c b/fs/proc/base.c index 2505c46c8701..0b833cbdf5b6 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1295,6 +1295,24 @@ static ssize_t proc_sessionid_read(struct file * file, char __user * buf, .llseek = generic_file_llseek, }; +static ssize_t proc_contid_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*2]; + + if (!task) + return -ESRCH; + /* if we don't have caps, reject */ + if (!capable(CAP_AUDIT_CONTROL)) + return -EPERM; + length = scnprintf(tmpbuf, TMPBUFLEN*2, "%llu", audit_get_contid(task)); + put_task_struct(task); + return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); +} + static ssize_t proc_contid_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { @@ -1325,6 +1343,7 @@ static ssize_t proc_contid_write(struct file *file, const char __user *buf, } static const struct file_operations proc_contid_operations = { + .read = proc_contid_read, .write = proc_contid_write, .llseek = generic_file_llseek, }; @@ -3039,7 +3058,7 @@ 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), + REG("audit_containerid", S_IWUSR|S_IRUSR, proc_contid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), @@ -3428,7 +3447,7 @@ 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), + REG("audit_containerid", S_IWUSR|S_IRUSR, proc_contid_operations), #endif #ifdef CONFIG_FAULT_INJECTION REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), -- 1.8.3.1

Create a new audit record AUDIT_CONTAINER_ID to document the audit container identifier of a process if it is present. Called from audit_log_exit(), syscalls are covered. A sample raw event: type=SYSCALL msg=audit(1519924845.499:257): arch=c000003e syscall=257 success=yes exit=3 a0=ffffff9c a1=56374e1cef30 a2=241 a3=1b6 items=2 ppid=606 pid=635 auid=0 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts0 ses=3 comm="bash" exe="/usr/bin/bash" subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key="tmpcontainerid" type=CWD msg=audit(1519924845.499:257): cwd="/root" type=PATH msg=audit(1519924845.499:257): item=0 name="/tmp/" inode=13863 dev=00:27 mode=041777 ouid=0 ogid=0 rdev=00:00 obj=system_u:object_r:tmp_t:s0 nametype= PARENT cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 type=PATH msg=audit(1519924845.499:257): item=1 name="/tmp/tmpcontainerid" inode=17729 dev=00:27 mode=0100644 ouid=0 ogid=0 rdev=00:00 obj=unconfined_u:object_r:user_tmp_t:s0 nametype=CREATE cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 type=PROCTITLE msg=audit(1519924845.499:257): proctitle=62617368002D6300736C65657020313B206563686F2074657374203E202F746D702F746D70636F6E7461696E65726964 type=CONTAINER_ID msg=audit(1519924845.499:257): contid=123458 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(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; Acked-by: Steve Grubb <sgrubb(a)redhat.com&gt; Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; --- include/linux/audit.h | 5 +++++ include/uapi/linux/audit.h | 1 + kernel/audit.c | 21 +++++++++++++++++++++ kernel/auditsc.c | 2 ++ 4 files changed, 29 insertions(+) diff --git a/include/linux/audit.h b/include/linux/audit.h index 301337776193..43438192ca2a 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -199,6 +199,8 @@ static inline u64 audit_get_contid(struct task_struct *tsk) return tsk->audit->contid; } +extern void audit_log_contid(struct audit_context *context, u64 contid); + extern u32 audit_enabled; #else /* CONFIG_AUDIT */ static inline int audit_alloc(struct task_struct *task) @@ -265,6 +267,9 @@ static inline u64 audit_get_contid(struct task_struct *tsk) return AUDIT_CID_UNSET; } +static inline void audit_log_contid(struct audit_context *context, u64 contid) +{ } + #define audit_enabled AUDIT_OFF #endif /* CONFIG_AUDIT */ diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index d475cf3b4d7f..a6383e28b2c8 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -115,6 +115,7 @@ #define AUDIT_REPLACE 1329 /* Replace auditd if this packet unanswerd */ #define AUDIT_KERN_MODULE 1330 /* Kernel Module events */ #define AUDIT_FANOTIFY 1331 /* Fanotify access decision */ +#define AUDIT_CONTAINER_ID 1332 /* Container ID */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/audit.c b/kernel/audit.c index b5c702abeb42..8cc0e88d7f2a 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -2127,6 +2127,27 @@ void audit_log_session_info(struct audit_buffer *ab) audit_log_format(ab, "auid=%u ses=%u", auid, sessionid); } +/* + * audit_log_contid - report container info + * @context: task or local context for record + * @contid: container ID to report + */ +void audit_log_contid(struct audit_context *context, u64 contid) +{ + struct audit_buffer *ab; + + if (!audit_contid_valid(contid)) + return; + /* Generate AUDIT_CONTAINER_ID record with container ID */ + ab = audit_log_start(context, GFP_KERNEL, AUDIT_CONTAINER_ID); + if (!ab) + return; + audit_log_format(ab, "contid=%llu", contid); + audit_log_end(ab); + return; +} +EXPORT_SYMBOL(audit_log_contid); + void audit_log_key(struct audit_buffer *ab, char *key) { audit_log_format(ab, " key="); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 8090eff7868d..a8c8b44b954d 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1548,6 +1548,8 @@ static void audit_log_exit(void) audit_log_proctitle(); + audit_log_contid(context, audit_get_contid(current)); + /* Send end of event record to help user space know we are finished */ ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE); if (ab) -- 1.8.3.1

On Fri, Mar 15, 2019 at 7:34 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > Create a new audit record AUDIT_CONTAINER_ID to document the audit > container identifier of a process if it is present. > > Called from audit_log_exit(), syscalls are covered. > > A sample raw event: > type=SYSCALL msg=audit(1519924845.499:257): arch=c000003e syscall=257 success=yes exit=3 a0=ffffff9c a1=56374e1cef30 a2=241 a3=1b6 items=2 ppid=606 pid=635 auid=0 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts0 ses=3 comm="bash" exe="/usr/bin/bash" subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key="tmpcontainerid" > type=CWD msg=audit(1519924845.499:257): cwd="/root" > type=PATH msg=audit(1519924845.499:257): item=0 name="/tmp/" inode=13863 dev=00:27 mode=041777 ouid=0 ogid=0 rdev=00:00 obj=system_u:object_r:tmp_t:s0 nametype= PARENT cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 > type=PATH msg=audit(1519924845.499:257): item=1 name="/tmp/tmpcontainerid" inode=17729 dev=00:27 mode=0100644 ouid=0 ogid=0 rdev=00:00 obj=unconfined_u:object_r:user_tmp_t:s0 nametype=CREATE cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 > type=PROCTITLE msg=audit(1519924845.499:257): proctitle=62617368002D6300736C65657020313B206563686F2074657374203E202F746D702F746D70636F6E7461696E65726964 > type=CONTAINER_ID msg=audit(1519924845.499:257): contid=123458 > > 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(a)redhat.com&gt; > Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; > Acked-by: Steve Grubb <sgrubb(a)redhat.com&gt; > Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; Barring one minor nit below, Reviewed-by: Ondrej Mosnacek <omosnace(a)redhat.com&gt; > --- > include/linux/audit.h | 5 +++++ > include/uapi/linux/audit.h | 1 + > kernel/audit.c | 21 +++++++++++++++++++++ > kernel/auditsc.c | 2 ++ > 4 files changed, 29 insertions(+) > > diff --git a/include/linux/audit.h b/include/linux/audit.h > index 301337776193..43438192ca2a 100644 > --- a/include/linux/audit.h > +++ b/include/linux/audit.h > @@ -199,6 +199,8 @@ static inline u64 audit_get_contid(struct task_struct *tsk) > return tsk->audit->contid; > } > > +extern void audit_log_contid(struct audit_context *context, u64 contid); > + > extern u32 audit_enabled; > #else /* CONFIG_AUDIT */ > static inline int audit_alloc(struct task_struct *task) > @@ -265,6 +267,9 @@ static inline u64 audit_get_contid(struct task_struct *tsk) > return AUDIT_CID_UNSET; > } > > +static inline void audit_log_contid(struct audit_context *context, u64 contid) > +{ } > + > #define audit_enabled AUDIT_OFF > #endif /* CONFIG_AUDIT */ > > diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h > index d475cf3b4d7f..a6383e28b2c8 100644 > --- a/include/uapi/linux/audit.h > +++ b/include/uapi/linux/audit.h > @@ -115,6 +115,7 @@ > #define AUDIT_REPLACE 1329 /* Replace auditd if this packet unanswerd */ > #define AUDIT_KERN_MODULE 1330 /* Kernel Module events */ > #define AUDIT_FANOTIFY 1331 /* Fanotify access decision */ > +#define AUDIT_CONTAINER_ID 1332 /* Container ID */ > > #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ > #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ > diff --git a/kernel/audit.c b/kernel/audit.c > index b5c702abeb42..8cc0e88d7f2a 100644 > --- a/kernel/audit.c > +++ b/kernel/audit.c > @@ -2127,6 +2127,27 @@ void audit_log_session_info(struct audit_buffer *ab) > audit_log_format(ab, "auid=%u ses=%u", auid, sessionid); > } > > +/* > + * audit_log_contid - report container info > + * @context: task or local context for record > + * @contid: container ID to report > + */ > +void audit_log_contid(struct audit_context *context, u64 contid) > +{ > + struct audit_buffer *ab; > + > + if (!audit_contid_valid(contid)) > + return; > + /* Generate AUDIT_CONTAINER_ID record with container ID */ > + ab = audit_log_start(context, GFP_KERNEL, AUDIT_CONTAINER_ID); > + if (!ab) > + return; > + audit_log_format(ab, "contid=%llu", contid); Just realized that you *might* get a compiler/static checker warning since u64 could technically be something else than unsigned long long on some arches... maybe this is not case in the kernel, but might be safer to cast it to unsigned long long before passing to audit_log_format(). Possibly there are similar occurrences in previous (later) patches that I didn't (won't) notice.

> + audit_log_end(ab); > + return; > +} > +EXPORT_SYMBOL(audit_log_contid); > + > void audit_log_key(struct audit_buffer *ab, char *key) > { > audit_log_format(ab, " key="); > diff --git a/kernel/auditsc.c b/kernel/auditsc.c > index 8090eff7868d..a8c8b44b954d 100644 > --- a/kernel/auditsc.c > +++ b/kernel/auditsc.c > @@ -1548,6 +1548,8 @@ static void audit_log_exit(void) > > audit_log_proctitle(); > > + audit_log_contid(context, audit_get_contid(current)); > + > /* Send end of event record to help user space know we are finished */ > ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE); > if (ab) Ondrej Mosnacek <omosnace at redhat dot com>

Add audit container identifier support to ptrace and signals. In particular, the "ref" field provides a way to label the auxiliary record to which it is associated. Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; --- include/linux/audit.h | 1 + kernel/audit.c | 2 ++ kernel/audit.h | 2 ++ kernel/auditsc.c | 23 +++++++++++++++++------ 4 files changed, 22 insertions(+), 6 deletions(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index 43438192ca2a..ebd6625ca80e 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -35,6 +35,7 @@ struct audit_sig_info { uid_t uid; pid_t pid; char ctx[0]; + u64 cid; };

struct audit_buffer; diff --git a/kernel/audit.c b/kernel/audit.c index 8cc0e88d7f2a..cfa659b3f6c4 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -138,6 +138,7 @@ struct audit_net { kuid_t audit_sig_uid = INVALID_UID; pid_t audit_sig_pid = -1; u32 audit_sig_sid = 0; +u64 audit_sig_cid = AUDIT_CID_UNSET; /* Records can be lost in several ways: 0) [suppressed in audit_alloc] @@ -1515,6 +1516,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memcpy(sig_data->ctx, ctx, len); security_release_secctx(ctx, len); } + sig_data->cid = audit_sig_cid; audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, sig_data, sizeof(*sig_data) + len); kfree(sig_data); diff --git a/kernel/audit.h b/kernel/audit.h index c00e2ee3c6b3..c5ac6436317e 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -148,6 +148,7 @@ struct audit_context { kuid_t target_uid; unsigned int target_sessionid; u32 target_sid; + u64 target_cid; char target_comm[TASK_COMM_LEN]; struct audit_tree_refs *trees, *first_trees; @@ -344,6 +345,7 @@ extern void audit_filter_inodes(struct task_struct *tsk, extern pid_t audit_sig_pid; extern kuid_t audit_sig_uid; extern u32 audit_sig_sid; +extern u64 audit_sig_cid; extern int audit_filter(int msgtype, unsigned int listtype); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index a8c8b44b954d..f04e115df5dc 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -113,6 +113,7 @@ struct audit_aux_data_pids { kuid_t target_uid[AUDIT_AUX_PIDS]; unsigned int target_sessionid[AUDIT_AUX_PIDS]; u32 target_sid[AUDIT_AUX_PIDS]; + u64 target_cid[AUDIT_AUX_PIDS]; char target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN]; int pid_count; }; @@ -1514,7 +1515,7 @@ static void audit_log_exit(void) for (aux = context->aux_pids; aux; aux = aux->next) { struct audit_aux_data_pids *axs = (void *)aux; - for (i = 0; i < axs->pid_count; i++) + for (i = 0; i < axs->pid_count; i++) { if (audit_log_pid_context(context, axs->target_pid[i], axs->target_auid[i], axs->target_uid[i], @@ -1522,14 +1523,20 @@ static void audit_log_exit(void) axs->target_sid[i], axs->target_comm[i])) call_panic = 1; + audit_log_contid(context, axs->target_cid[i]); + } } - if (context->target_pid && - audit_log_pid_context(context, context->target_pid, - context->target_auid, context->target_uid, - context->target_sessionid, - context->target_sid, context->target_comm)) + if (context->target_pid) { + if (audit_log_pid_context(context, context->target_pid, + context->target_auid, + context->target_uid, + context->target_sessionid, + context->target_sid, + context->target_comm)) call_panic = 1; + audit_log_contid(context, context->target_cid); + } if (context->pwd.dentry && context->pwd.mnt) { ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD); @@ -2360,6 +2367,7 @@ void __audit_ptrace(struct task_struct *t) context->target_uid = task_uid(t); context->target_sessionid = audit_get_sessionid(t); security_task_getsecid(t, &context->target_sid); + context->target_cid = audit_get_contid(t); memcpy(context->target_comm, t->comm, TASK_COMM_LEN); } @@ -2387,6 +2395,7 @@ int audit_signal_info(int sig, struct task_struct *t) else audit_sig_uid = uid; security_task_getsecid(current, &audit_sig_sid); + audit_sig_cid = audit_get_contid(current); } if (!audit_signals || audit_dummy_context()) @@ -2400,6 +2409,7 @@ int audit_signal_info(int sig, struct task_struct *t) ctx->target_uid = t_uid; ctx->target_sessionid = audit_get_sessionid(t); security_task_getsecid(t, &ctx->target_sid); + ctx->target_cid = audit_get_contid(t); memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN); return 0; } @@ -2421,6 +2431,7 @@ int audit_signal_info(int sig, struct task_struct *t) axp->target_uid[axp->pid_count] = t_uid; axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t); security_task_getsecid(t, &axp->target_sid[axp->pid_count]); + axp->target_cid[axp->pid_count] = audit_get_contid(t); memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN); axp->pid_count++; -- 1.8.3.1

Add audit container identifier support to ptrace and signals. In particular, the "ref" field provides a way to label the auxiliary record to which it is associated. Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; --- include/linux/audit.h | 1 + kernel/audit.c | 2 ++ kernel/audit.h | 2 ++ kernel/auditsc.c | 23 +++++++++++++++++------ 4 files changed, 22 insertions(+), 6 deletions(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index 43438192ca2a..ebd6625ca80e 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -35,6 +35,7 @@ struct audit_sig_info { uid_t uid; pid_t pid; char ctx[0]; + u64 cid; };

struct audit_buffer; diff --git a/kernel/audit.c b/kernel/audit.c index 8cc0e88d7f2a..cfa659b3f6c4 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -138,6 +138,7 @@ struct audit_net { kuid_t audit_sig_uid = INVALID_UID; pid_t audit_sig_pid = -1; u32 audit_sig_sid = 0; +u64 audit_sig_cid = AUDIT_CID_UNSET; /* Records can be lost in several ways: 0) [suppressed in audit_alloc] @@ -1515,6 +1516,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) memcpy(sig_data->ctx, ctx, len); security_release_secctx(ctx, len); } + sig_data->cid = audit_sig_cid; audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, sig_data, sizeof(*sig_data) + len); kfree(sig_data); diff --git a/kernel/audit.h b/kernel/audit.h index c00e2ee3c6b3..c5ac6436317e 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -148,6 +148,7 @@ struct audit_context { kuid_t target_uid; unsigned int target_sessionid; u32 target_sid; + u64 target_cid; char target_comm[TASK_COMM_LEN]; struct audit_tree_refs *trees, *first_trees; @@ -344,6 +345,7 @@ extern void audit_filter_inodes(struct task_struct *tsk, extern pid_t audit_sig_pid; extern kuid_t audit_sig_uid; extern u32 audit_sig_sid; +extern u64 audit_sig_cid; extern int audit_filter(int msgtype, unsigned int listtype); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index a8c8b44b954d..f04e115df5dc 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -113,6 +113,7 @@ struct audit_aux_data_pids { kuid_t target_uid[AUDIT_AUX_PIDS]; unsigned int target_sessionid[AUDIT_AUX_PIDS]; u32 target_sid[AUDIT_AUX_PIDS]; + u64 target_cid[AUDIT_AUX_PIDS]; char target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN]; int pid_count; }; @@ -1514,7 +1515,7 @@ static void audit_log_exit(void) for (aux = context->aux_pids; aux; aux = aux->next) { struct audit_aux_data_pids *axs = (void *)aux; - for (i = 0; i < axs->pid_count; i++) + for (i = 0; i < axs->pid_count; i++) { if (audit_log_pid_context(context, axs->target_pid[i], axs->target_auid[i], axs->target_uid[i], @@ -1522,14 +1523,20 @@ static void audit_log_exit(void) axs->target_sid[i], axs->target_comm[i])) call_panic = 1; + audit_log_contid(context, axs->target_cid[i]); + } } - if (context->target_pid && - audit_log_pid_context(context, context->target_pid, - context->target_auid, context->target_uid, - context->target_sessionid, - context->target_sid, context->target_comm)) + if (context->target_pid) { + if (audit_log_pid_context(context, context->target_pid, + context->target_auid, + context->target_uid, + context->target_sessionid, + context->target_sid, + context->target_comm)) call_panic = 1; + audit_log_contid(context, context->target_cid); + } if (context->pwd.dentry && context->pwd.mnt) { ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD); @@ -2360,6 +2367,7 @@ void __audit_ptrace(struct task_struct *t) context->target_uid = task_uid(t); context->target_sessionid = audit_get_sessionid(t); security_task_getsecid(t, &context->target_sid); + context->target_cid = audit_get_contid(t); memcpy(context->target_comm, t->comm, TASK_COMM_LEN); } @@ -2387,6 +2395,7 @@ int audit_signal_info(int sig, struct task_struct *t) else audit_sig_uid = uid; security_task_getsecid(current, &audit_sig_sid); + audit_sig_cid = audit_get_contid(current); } if (!audit_signals || audit_dummy_context()) @@ -2400,6 +2409,7 @@ int audit_signal_info(int sig, struct task_struct *t) ctx->target_uid = t_uid; ctx->target_sessionid = audit_get_sessionid(t); security_task_getsecid(t, &ctx->target_sid); + ctx->target_cid = audit_get_contid(t); memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN); return 0; } @@ -2421,6 +2431,7 @@ int audit_signal_info(int sig, struct task_struct *t) axp->target_uid[axp->pid_count] = t_uid; axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t); security_task_getsecid(t, &axp->target_sid[axp->pid_count]); + axp->target_cid[axp->pid_count] = audit_get_contid(t); memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN); axp->pid_count++; -- 1.8.3.1

On 2019-03-27 22:17, Ondrej Mosnacek wrote: > On Fri, Mar 15, 2019 at 7:34 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > > Add audit container identifier support to ptrace and signals. In > > particular, the "ref" field provides a way to label the auxiliary record > > to which it is associated. > > > > Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; > > Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; > > Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; > > --- > > include/linux/audit.h | 1 + > > kernel/audit.c | 2 ++ > > kernel/audit.h | 2 ++ > > kernel/auditsc.c | 23 +++++++++++++++++------ > > 4 files changed, 22 insertions(+), 6 deletions(-) > > > > diff --git a/include/linux/audit.h b/include/linux/audit.h > > index 43438192ca2a..ebd6625ca80e 100644 > > --- a/include/linux/audit.h > > +++ b/include/linux/audit.h > > @@ -35,6 +35,7 @@ struct audit_sig_info { > > uid_t uid; > > pid_t pid; > > char ctx[0]; > > + u64 cid; > > }; > > It seems like this structure implicitly defines the format of some > message that is sent to userspace... If so, how will userspace detect > that a new format (including the cid) is being used? Even assuming the > fixed order as pointed out by Neil, the message still seems to be > variable-sized so userspace cannot even use the length to infer that. > Am I missing something here? (I hope I am :) How humble of you again. No, you're not missing something. This ends up being an api change... That can be fixed in userspace by checking for AUDIT_FEATURE_BITMAP_CONTAINERID, but how do we make a newer kernel not break an older userspace... I think this was the original rationale for adding it after the ctx but totally missing the fact that the latter is a variable-length field.

This patch really should be split into audit_sig_cid changes in a patch by itself and target_cid changes which could go with the second and fourth patches.

> > struct audit_buffer; > > diff --git a/kernel/audit.c b/kernel/audit.c > > index 8cc0e88d7f2a..cfa659b3f6c4 100644 > > --- a/kernel/audit.c > > +++ b/kernel/audit.c > > @@ -138,6 +138,7 @@ struct audit_net { > > kuid_t audit_sig_uid = INVALID_UID; > > pid_t audit_sig_pid = -1; > > u32 audit_sig_sid = 0; > > +u64 audit_sig_cid = AUDIT_CID_UNSET; > > > > /* Records can be lost in several ways: > > 0) [suppressed in audit_alloc] > > @@ -1515,6 +1516,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) > > memcpy(sig_data->ctx, ctx, len); > > security_release_secctx(ctx, len); > > } > > + sig_data->cid = audit_sig_cid; > > audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, > > sig_data, sizeof(*sig_data) + len); > > kfree(sig_data); > > diff --git a/kernel/audit.h b/kernel/audit.h > > index c00e2ee3c6b3..c5ac6436317e 100644 > > --- a/kernel/audit.h > > +++ b/kernel/audit.h > > @@ -148,6 +148,7 @@ struct audit_context { > > kuid_t target_uid; > > unsigned int target_sessionid; > > u32 target_sid; > > + u64 target_cid; > > char target_comm[TASK_COMM_LEN]; > > > > struct audit_tree_refs *trees, *first_trees; > > @@ -344,6 +345,7 @@ extern void audit_filter_inodes(struct task_struct *tsk, > > extern pid_t audit_sig_pid; > > extern kuid_t audit_sig_uid; > > extern u32 audit_sig_sid; > > +extern u64 audit_sig_cid; > > > > extern int audit_filter(int msgtype, unsigned int listtype); > > > > diff --git a/kernel/auditsc.c b/kernel/auditsc.c > > index a8c8b44b954d..f04e115df5dc 100644 > > --- a/kernel/auditsc.c > > +++ b/kernel/auditsc.c > > @@ -113,6 +113,7 @@ struct audit_aux_data_pids { > > kuid_t target_uid[AUDIT_AUX_PIDS]; > > unsigned int target_sessionid[AUDIT_AUX_PIDS]; > > u32 target_sid[AUDIT_AUX_PIDS]; > > + u64 target_cid[AUDIT_AUX_PIDS]; > > char target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN]; > > int pid_count; > > }; > > @@ -1514,7 +1515,7 @@ static void audit_log_exit(void) > > for (aux = context->aux_pids; aux; aux = aux->next) { > > struct audit_aux_data_pids *axs = (void *)aux; > > > > - for (i = 0; i < axs->pid_count; i++) > > + for (i = 0; i < axs->pid_count; i++) { > > if (audit_log_pid_context(context, axs->target_pid[i], > > axs->target_auid[i], > > axs->target_uid[i], > > @@ -1522,14 +1523,20 @@ static void audit_log_exit(void) > > axs->target_sid[i], > > axs->target_comm[i])) > > call_panic = 1; > > + audit_log_contid(context, axs->target_cid[i]); > > + } > > } > > > > - if (context->target_pid && > > - audit_log_pid_context(context, context->target_pid, > > - context->target_auid, context->target_uid, > > - context->target_sessionid, > > - context->target_sid, context->target_comm)) > > + if (context->target_pid) { > > + if (audit_log_pid_context(context, context->target_pid, > > + context->target_auid, > > + context->target_uid, > > + context->target_sessionid, > > + context->target_sid, > > + context->target_comm)) > > call_panic = 1; > > + audit_log_contid(context, context->target_cid); > > + } > > > > if (context->pwd.dentry && context->pwd.mnt) { > > ab = audit_log_start(context, GFP_KERNEL, AUDIT_CWD); > > @@ -2360,6 +2367,7 @@ void __audit_ptrace(struct task_struct *t) > > context->target_uid = task_uid(t); > > context->target_sessionid = audit_get_sessionid(t); > > security_task_getsecid(t, &context->target_sid); > > + context->target_cid = audit_get_contid(t); > > memcpy(context->target_comm, t->comm, TASK_COMM_LEN); > > } > > > > @@ -2387,6 +2395,7 @@ int audit_signal_info(int sig, struct task_struct *t) > > else > > audit_sig_uid = uid; > > security_task_getsecid(current, &audit_sig_sid); > > + audit_sig_cid = audit_get_contid(current); > > } > > > > if (!audit_signals || audit_dummy_context()) > > @@ -2400,6 +2409,7 @@ int audit_signal_info(int sig, struct task_struct *t) > > ctx->target_uid = t_uid; > > ctx->target_sessionid = audit_get_sessionid(t); > > security_task_getsecid(t, &ctx->target_sid); > > + ctx->target_cid = audit_get_contid(t); > > memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN); > > return 0; > > } > > @@ -2421,6 +2431,7 @@ int audit_signal_info(int sig, struct task_struct *t) > > axp->target_uid[axp->pid_count] = t_uid; > > axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t); > > security_task_getsecid(t, &axp->target_sid[axp->pid_count]); > > + axp->target_cid[axp->pid_count] = audit_get_contid(t); > > memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN); > > axp->pid_count++; > > > > Ondrej Mosnacek <omosnace at redhat dot com> - RGB

Standalone audit records have the timestamp and serial number generated on the fly and as such are unique, making them standalone. This new function audit_alloc_local() generates a local audit context that will be used only for a standalone record and its auxiliary record(s). The context is discarded immediately after the local associated records are produced. Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; --- include/linux/audit.h | 8 ++++++++ kernel/audit.h | 1 + kernel/auditsc.c | 35 ++++++++++++++++++++++++++++++----- 3 files changed, 39 insertions(+), 5 deletions(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index ebd6625ca80e..6db5aba7cc01 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -285,6 +285,8 @@ static inline void audit_log_contid(struct audit_context *context, u64 contid) /* These are defined in auditsc.c */ /* Public API */ +extern struct audit_context *audit_alloc_local(gfp_t gfpflags); +extern void audit_free_context(struct audit_context *context); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); @@ -512,6 +514,12 @@ static inline void audit_fanotify(unsigned int response) extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ +static inline struct audit_context *audit_alloc_local(gfp_t gfpflags) +{ + return NULL; +} +static inline void audit_free_context(struct audit_context *context) +{ } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) diff --git a/kernel/audit.h b/kernel/audit.h index c5ac6436317e..2a1a8b8a8019 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -111,6 +111,7 @@ struct audit_proctitle { struct audit_context { int dummy; /* must be the first element */ int in_syscall; /* 1 if task is in a syscall */ + bool local; /* local context needed */ enum audit_state state, current_state; unsigned int serial; /* serial number for record */ int major; /* syscall number */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index f04e115df5dc..aa5d13b4fbbb 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -872,11 +872,13 @@ static inline void audit_free_aux(struct audit_context *context) } } -static inline struct audit_context *audit_alloc_context(enum audit_state state) +static inline struct audit_context *audit_alloc_context(enum audit_state state, + gfp_t gfpflags) { struct audit_context *context; - context = kzalloc(sizeof(*context), GFP_KERNEL); + /* We can be called in atomic context via audit_tg() */ + context = kzalloc(sizeof(*context), gfpflags); if (!context) return NULL; context->state = state; @@ -912,7 +914,8 @@ int audit_alloc_syscall(struct task_struct *tsk) return 0; } - if (!(context = audit_alloc_context(state))) { + context = audit_alloc_context(state, GFP_KERNEL); + if (!context) { kfree(key); audit_log_lost("out of memory in audit_alloc_syscall"); return -ENOMEM; @@ -924,8 +927,29 @@ int audit_alloc_syscall(struct task_struct *tsk) return 0; } -static inline void audit_free_context(struct audit_context *context) +struct audit_context *audit_alloc_local(gfp_t gfpflags) { + struct audit_context *context = NULL; + + if (!audit_ever_enabled) + goto out; /* Return if not auditing. */ + context = audit_alloc_context(AUDIT_RECORD_CONTEXT, gfpflags); + if (!context) { + audit_log_lost("out of memory in audit_alloc_local"); + goto out; + } + context->serial = audit_serial(); + ktime_get_coarse_real_ts64(&context->ctime); + context->local = true; +out: + return context; +} +EXPORT_SYMBOL(audit_alloc_local); + +void audit_free_context(struct audit_context *context) +{ + if (!context) + return; audit_free_names(context); unroll_tree_refs(context, NULL, 0); free_tree_refs(context); @@ -935,6 +959,7 @@ static inline void audit_free_context(struct audit_context *context) audit_proctitle_free(context); kfree(context); } +EXPORT_SYMBOL(audit_free_context); static int audit_log_pid_context(struct audit_context *context, pid_t pid, kuid_t auid, kuid_t uid, unsigned int sessionid, @@ -2163,7 +2188,7 @@ void __audit_inode_child(struct inode *parent, int auditsc_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial) { - if (!ctx->in_syscall) + if (!ctx->in_syscall && !ctx->local) return 0; if (!ctx->serial) ctx->serial = audit_serial(); -- 1.8.3.1

Standalone audit records have the timestamp and serial number generated on the fly and as such are unique, making them standalone. This new function audit_alloc_local() generates a local audit context that will be used only for a standalone record and its auxiliary record(s). The context is discarded immediately after the local associated records are produced. Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; --- include/linux/audit.h | 8 ++++++++ kernel/audit.h | 1 + kernel/auditsc.c | 35 ++++++++++++++++++++++++++++++----- 3 files changed, 39 insertions(+), 5 deletions(-)

diff --git a/include/linux/audit.h b/include/linux/audit.h index ebd6625ca80e..6db5aba7cc01 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -285,6 +285,8 @@ static inline void audit_log_contid(struct audit_context *context, u64 contid) /* These are defined in auditsc.c */ /* Public API */ +extern struct audit_context *audit_alloc_local(gfp_t gfpflags); +extern void audit_free_context(struct audit_context *context); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); @@ -512,6 +514,12 @@ static inline void audit_fanotify(unsigned int response) extern int audit_n_rules; extern int audit_signals; #else /* CONFIG_AUDITSYSCALL */ +static inline struct audit_context *audit_alloc_local(gfp_t gfpflags) +{ + return NULL; +} +static inline void audit_free_context(struct audit_context *context) +{ } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) diff --git a/kernel/audit.h b/kernel/audit.h index c5ac6436317e..2a1a8b8a8019 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -111,6 +111,7 @@ struct audit_proctitle { struct audit_context { int dummy; /* must be the first element */ int in_syscall; /* 1 if task is in a syscall */ + bool local; /* local context needed */

enum audit_state state, current_state; unsigned int serial; /* serial number for record */ int major; /* syscall number */

On 2019-04-01 10:49, Paul Moore wrote: > On Fri, Mar 15, 2019 at 2:34 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > > Standalone audit records have the timestamp and serial number generated > > on the fly and as such are unique, making them standalone. This new > > function audit_alloc_local() generates a local audit context that will > > be used only for a standalone record and its auxiliary record(s). The > > context is discarded immediately after the local associated records are > > produced. > > > > Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; > > Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; > > --- > > include/linux/audit.h | 8 ++++++++ > > kernel/audit.h | 1 + > > kernel/auditsc.c | 35 ++++++++++++++++++++++++++++++----- > > 3 files changed, 39 insertions(+), 5 deletions(-) > > ... > > > diff --git a/include/linux/audit.h b/include/linux/audit.h > > index ebd6625ca80e..6db5aba7cc01 100644 > > --- a/include/linux/audit.h > > +++ b/include/linux/audit.h > > @@ -285,6 +285,8 @@ static inline void audit_log_contid(struct audit_context *context, u64 contid) > > > > /* These are defined in auditsc.c */ > > /* Public API */ > > +extern struct audit_context *audit_alloc_local(gfp_t gfpflags); > > +extern void audit_free_context(struct audit_context *context); > > extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, > > unsigned long a2, unsigned long a3); > > extern void __audit_syscall_exit(int ret_success, long ret_value); > > @@ -512,6 +514,12 @@ static inline void audit_fanotify(unsigned int response) > > extern int audit_n_rules; > > extern int audit_signals; > > #else /* CONFIG_AUDITSYSCALL */ > > +static inline struct audit_context *audit_alloc_local(gfp_t gfpflags) > > +{ > > + return NULL; > > +} > > +static inline void audit_free_context(struct audit_context *context) > > +{ } > > static inline void audit_syscall_entry(int major, unsigned long a0, > > unsigned long a1, unsigned long a2, > > unsigned long a3) > > diff --git a/kernel/audit.h b/kernel/audit.h > > index c5ac6436317e..2a1a8b8a8019 100644 > > --- a/kernel/audit.h > > +++ b/kernel/audit.h > > @@ -111,6 +111,7 @@ struct audit_proctitle { > > struct audit_context { > > int dummy; /* must be the first element */ > > int in_syscall; /* 1 if task is in a syscall */ > > + bool local; /* local context needed */ > > It's very possible I've missed it, but "local" never gets used in any > meaningful way in this patchset does it? It is used in audit_alloc_local() to signal to audit_get_stamp() that in absence of a syscall flag, check for a local flag to continue rather than return.

Add audit container identifier auxiliary record to user event standalone records. Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt;

--- kernel/audit.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) diff --git a/kernel/audit.c b/kernel/audit.c index cfa659b3f6c4..cf448599ef34 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1142,12 +1142,6 @@ static void audit_log_common_recv_msg(struct audit_context *context, audit_log_task_context(*ab); } -static inline void audit_log_user_recv_msg(struct audit_buffer **ab, - u16 msg_type) -{ - audit_log_common_recv_msg(NULL, ab, msg_type); -} - int is_audit_feature_set(int i) { return af.features & AUDIT_FEATURE_TO_MASK(i); @@ -1409,13 +1403,16 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ + struct audit_context *context; + err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); if (err) break; } - audit_log_user_recv_msg(&ab, msg_type); + context = audit_alloc_local(GFP_KERNEL); + audit_log_common_recv_msg(context, &ab, msg_type); if (msg_type != AUDIT_USER_TTY) audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, @@ -1431,6 +1428,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) audit_log_n_untrustedstring(ab, data, size); } audit_log_end(ab); + audit_log_contid(context, audit_get_contid(current)); + audit_free_context(context); } break; case AUDIT_ADD_RULE: -- 1.8.3.1

Implement audit container identifier filtering using the AUDIT_CONTID field name to send an 8-character string representing a u64 since the value field is only u32. Sending it as two u32 was considered, but gathering and comparing two fields was more complex. The feature indicator is AUDIT_FEATURE_BITMAP_CONTAINERID. See: https://github.com/linux-audit/audit-kernel/issues/91 See: https://github.com/linux-audit/audit-userspace/issues/40 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(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; --- include/linux/audit.h | 1 + include/uapi/linux/audit.h | 5 ++++- kernel/audit.h | 1 + kernel/auditfilter.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/auditsc.c | 3 +++ 5 files changed, 56 insertions(+), 1 deletion(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index 6db5aba7cc01..fa19fa408931 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -77,6 +77,7 @@ struct audit_field { u32 type; union { u32 val; + u64 val64; kuid_t uid; kgid_t gid; struct { diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index a6383e28b2c8..741ab6f38294 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -265,6 +265,7 @@ #define AUDIT_LOGINUID_SET 24 #define AUDIT_SESSIONID 25 /* Session ID */ #define AUDIT_FSTYPE 26 /* FileSystem Type */ +#define AUDIT_CONTID 27 /* Container ID */ /* These are ONLY useful when checking * at syscall exit time (AUDIT_AT_EXIT). */ @@ -345,6 +346,7 @@ enum { #define AUDIT_FEATURE_BITMAP_SESSIONID_FILTER 0x00000010 #define AUDIT_FEATURE_BITMAP_LOST_RESET 0x00000020 #define AUDIT_FEATURE_BITMAP_FILTER_FS 0x00000040 +#define AUDIT_FEATURE_BITMAP_CONTAINERID 0x00000080 #define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \ AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME | \ @@ -352,7 +354,8 @@ enum { AUDIT_FEATURE_BITMAP_EXCLUDE_EXTEND | \ AUDIT_FEATURE_BITMAP_SESSIONID_FILTER | \ AUDIT_FEATURE_BITMAP_LOST_RESET | \ - AUDIT_FEATURE_BITMAP_FILTER_FS) + AUDIT_FEATURE_BITMAP_FILTER_FS | \ + AUDIT_FEATURE_BITMAP_CONTAINERID) /* deprecated: AUDIT_VERSION_* */ #define AUDIT_VERSION_LATEST AUDIT_FEATURE_BITMAP_ALL diff --git a/kernel/audit.h b/kernel/audit.h index 2a1a8b8a8019..3a40b608bf8d 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -230,6 +230,7 @@ static inline int audit_hash_ino(u32 ino) extern int audit_match_class(int class, unsigned syscall); extern int audit_comparator(const u32 left, const u32 op, const u32 right); +extern int audit_comparator64(const u64 left, const u32 op, const u64 right); extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right); extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right); extern int parent_len(const char *path); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index add360b46b38..516b8e58959e 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -410,6 +410,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) /* FALL THROUGH */ case AUDIT_ARCH: case AUDIT_FSTYPE: + case AUDIT_CONTID: if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; break; @@ -582,6 +583,14 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, } entry->rule.exe = audit_mark; break; + case AUDIT_CONTID: + if (f->val != sizeof(u64)) + goto exit_free; + str = audit_unpack_string(&bufp, &remain, f->val); + if (IS_ERR(str)) + goto exit_free; + f->val64 = ((u64 *)str)[0]; + break; } } @@ -664,6 +673,11 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) data->buflen += data->values[i] = audit_pack_string(&bufp, audit_mark_path(krule->exe)); break; + case AUDIT_CONTID: + data->buflen += data->values[i] = sizeof(u64); + for (i = 0; i < sizeof(u64); i++) + ((char *)bufp)[i] = ((char *)&f->val64)[i];

+ break; case AUDIT_LOGINUID_SET: if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { data->fields[i] = AUDIT_LOGINUID; @@ -750,6 +764,10 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) return 1; break; + case AUDIT_CONTID: + if (a->fields[i].val64 != b->fields[i].val64) + return 1; + break; default: if (a->fields[i].val != b->fields[i].val) return 1; @@ -1206,6 +1224,31 @@ int audit_comparator(u32 left, u32 op, u32 right) } } +int audit_comparator64(u64 left, u32 op, u64 right) +{ + switch (op) { + case Audit_equal: + return (left == right); + case Audit_not_equal: + return (left != right); + case Audit_lt: + return (left < right); + case Audit_le: + return (left <= right); + case Audit_gt: + return (left > right); + case Audit_ge: + return (left >= right); + case Audit_bitmask: + return (left & right); + case Audit_bittest: + return ((left & right) == right); + default: + BUG(); + return 0; + } +} + int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) { switch (op) { @@ -1344,6 +1387,10 @@ int audit_filter(int msgtype, unsigned int listtype) result = audit_comparator(audit_loginuid_set(current), f->op, f->val); break; + case AUDIT_CONTID: + result = audit_comparator64(audit_get_contid(current), + f->op, f->val64); + break; case AUDIT_MSGTYPE: result = audit_comparator(msgtype, f->op, f->val); break; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index aa5d13b4fbbb..2d74238e9638 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -616,6 +616,9 @@ static int audit_filter_rules(struct task_struct *tsk, case AUDIT_LOGINUID_SET: result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val); break; + case AUDIT_CONTID: + result = audit_comparator64(audit_get_contid(tsk), f->op, f->val64); + break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: -- 1.8.3.1

On 2019-03-18 21:02, Ondrej Mosnacek wrote: > On Fri, Mar 15, 2019 at 7:35 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > > > > Implement audit container identifier filtering using the AUDIT_CONTID > > field name to send an 8-character string representing a u64 since the > > value field is only u32. > > > > Sending it as two u32 was considered, but gathering and comparing two > > fields was more complex. > > > > The feature indicator is AUDIT_FEATURE_BITMAP_CONTAINERID. > > > > See: https://github.com/linux-audit/audit-kernel/issues/91 > > See: https://github.com/linux-audit/audit-userspace/issues/40 > > 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(a)redhat.com&gt; > > Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; > > --- > > include/linux/audit.h | 1 + > > include/uapi/linux/audit.h | 5 ++++- > > kernel/audit.h | 1 + > > kernel/auditfilter.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ > > kernel/auditsc.c | 3 +++ > > 5 files changed, 56 insertions(+), 1 deletion(-) > > > > diff --git a/include/linux/audit.h b/include/linux/audit.h > > index 6db5aba7cc01..fa19fa408931 100644 > > --- a/include/linux/audit.h > > +++ b/include/linux/audit.h > > @@ -77,6 +77,7 @@ struct audit_field { > > u32 type; > > union { > > u32 val; > > + u64 val64; > > kuid_t uid; > > kgid_t gid; > > struct { > > diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h > > index a6383e28b2c8..741ab6f38294 100644 > > --- a/include/uapi/linux/audit.h > > +++ b/include/uapi/linux/audit.h > > @@ -265,6 +265,7 @@ > > #define AUDIT_LOGINUID_SET 24 > > #define AUDIT_SESSIONID 25 /* Session ID */ > > #define AUDIT_FSTYPE 26 /* FileSystem Type */ > > +#define AUDIT_CONTID 27 /* Container ID */ > > > > /* These are ONLY useful when checking > > * at syscall exit time (AUDIT_AT_EXIT). */ > > @@ -345,6 +346,7 @@ enum { > > #define AUDIT_FEATURE_BITMAP_SESSIONID_FILTER 0x00000010 > > #define AUDIT_FEATURE_BITMAP_LOST_RESET 0x00000020 > > #define AUDIT_FEATURE_BITMAP_FILTER_FS 0x00000040 > > +#define AUDIT_FEATURE_BITMAP_CONTAINERID 0x00000080 > > > > #define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \ > > AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME | \ > > @@ -352,7 +354,8 @@ enum { > > AUDIT_FEATURE_BITMAP_EXCLUDE_EXTEND | \ > > AUDIT_FEATURE_BITMAP_SESSIONID_FILTER | \ > > AUDIT_FEATURE_BITMAP_LOST_RESET | \ > > - AUDIT_FEATURE_BITMAP_FILTER_FS) > > + AUDIT_FEATURE_BITMAP_FILTER_FS | \ > > + AUDIT_FEATURE_BITMAP_CONTAINERID) > > > > /* deprecated: AUDIT_VERSION_* */ > > #define AUDIT_VERSION_LATEST AUDIT_FEATURE_BITMAP_ALL > > diff --git a/kernel/audit.h b/kernel/audit.h > > index 2a1a8b8a8019..3a40b608bf8d 100644 > > --- a/kernel/audit.h > > +++ b/kernel/audit.h > > @@ -230,6 +230,7 @@ static inline int audit_hash_ino(u32 ino) > > > > extern int audit_match_class(int class, unsigned syscall); > > extern int audit_comparator(const u32 left, const u32 op, const u32 right); > > +extern int audit_comparator64(const u64 left, const u32 op, const u64 right); > > extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right); > > extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right); > > extern int parent_len(const char *path); > > diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c > > index add360b46b38..516b8e58959e 100644 > > --- a/kernel/auditfilter.c > > +++ b/kernel/auditfilter.c > > @@ -410,6 +410,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) > > /* FALL THROUGH */ > > case AUDIT_ARCH: > > case AUDIT_FSTYPE: > > + case AUDIT_CONTID: > > if (f->op != Audit_not_equal && f->op != Audit_equal) > > return -EINVAL; > > break; > > @@ -582,6 +583,14 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, > > } > > entry->rule.exe = audit_mark; > > break; > > + case AUDIT_CONTID: > > + if (f->val != sizeof(u64)) > > + goto exit_free; > > + str = audit_unpack_string(&bufp, &remain, f->val); > > + if (IS_ERR(str)) > > + goto exit_free; > > + f->val64 = ((u64 *)str)[0]; > > + break; > > } > > } > > > > @@ -664,6 +673,11 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) > > data->buflen += data->values[i] = > > audit_pack_string(&bufp, audit_mark_path(krule->exe)); > > break; > > + case AUDIT_CONTID: > > + data->buflen += data->values[i] = sizeof(u64); > > + for (i = 0; i < sizeof(u64); i++) > > + ((char *)bufp)[i] = ((char *)&f->val64)[i]; > > How about just: > > memcpy(bufp, &f->val64, sizeof(u64)); > > instead of the awkward for loop? It is simpler and also more in line > with the code in audit_pack_string(). I'll grant you that. I'll use that instead.

> Also, doesn't this loop interfere with the outer loop that also uses > 'i' as the control variable? Yes, it does. Thank you for catching that. Doing a auditctl -l reveals this. > > + break; > > case AUDIT_LOGINUID_SET: > > if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { > > data->fields[i] = AUDIT_LOGINUID; > > @@ -750,6 +764,10 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) > > if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) > > return 1; > > break; > > + case AUDIT_CONTID: > > + if (a->fields[i].val64 != b->fields[i].val64) > > + return 1; > > + break; > > default: > > if (a->fields[i].val != b->fields[i].val) > > return 1; > > @@ -1206,6 +1224,31 @@ int audit_comparator(u32 left, u32 op, u32 right) > > } > > } > > > > +int audit_comparator64(u64 left, u32 op, u64 right) > > +{ > > + switch (op) { > > + case Audit_equal: > > + return (left == right); > > + case Audit_not_equal: > > + return (left != right); > > + case Audit_lt: > > + return (left < right); > > + case Audit_le: > > + return (left <= right); > > + case Audit_gt: > > + return (left > right); > > + case Audit_ge: > > + return (left >= right); > > + case Audit_bitmask: > > + return (left & right); > > + case Audit_bittest: > > + return ((left & right) == right); > > + default: > > + BUG(); > > + return 0; > > + } > > +} > > + > > int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) > > { > > switch (op) { > > @@ -1344,6 +1387,10 @@ int audit_filter(int msgtype, unsigned int listtype) > > result = audit_comparator(audit_loginuid_set(current), > > f->op, f->val); > > break; > > + case AUDIT_CONTID: > > + result = audit_comparator64(audit_get_contid(current), > > + f->op, f->val64); > > + break; > > case AUDIT_MSGTYPE: > > result = audit_comparator(msgtype, f->op, f->val); > > break; > > diff --git a/kernel/auditsc.c b/kernel/auditsc.c > > index aa5d13b4fbbb..2d74238e9638 100644 > > --- a/kernel/auditsc.c > > +++ b/kernel/auditsc.c > > @@ -616,6 +616,9 @@ static int audit_filter_rules(struct task_struct *tsk, > > case AUDIT_LOGINUID_SET: > > result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val); > > break; > > + case AUDIT_CONTID: > > + result = audit_comparator64(audit_get_contid(tsk), f->op, f->val64); > > + break; > > case AUDIT_SUBJ_USER: > > case AUDIT_SUBJ_ROLE: > > case AUDIT_SUBJ_TYPE: > > -- > > 1.8.3.1 > > > > > -- > Ondrej Mosnacek <omosnace at redhat dot com> > Associate Software Engineer, Security Technologies > Red Hat, Inc. - RGB -- Richard Guy Briggs <rgb(a)redhat.com&gt; Sr. S/W Engineer, Kernel Security, Base Operating Systems Remote, Ottawa, Red Hat Canada IRC: rgb, SunRaycer Voice: +1.647.777.2635, Internal: (81) 32635

Implement audit container identifier filtering using the AUDIT_CONTID field name to send an 8-character string representing a u64 since the value field is only u32. Sending it as two u32 was considered, but gathering and comparing two fields was more complex. The feature indicator is AUDIT_FEATURE_BITMAP_CONTAINERID. See: https://github.com/linux-audit/audit-kernel/issues/91 See: https://github.com/linux-audit/audit-userspace/issues/40 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(a)redhat.com&gt; Acked-by: Serge Hallyn <serge(a)hallyn.com&gt; --- include/linux/audit.h | 1 + include/uapi/linux/audit.h | 5 ++++- kernel/audit.h | 1 + kernel/auditfilter.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ kernel/auditsc.c | 3 +++ 5 files changed, 56 insertions(+), 1 deletion(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index 6db5aba7cc01..fa19fa408931 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -77,6 +77,7 @@ struct audit_field { u32 type; union { u32 val; + u64 val64; kuid_t uid; kgid_t gid; struct { diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index a6383e28b2c8..741ab6f38294 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -265,6 +265,7 @@ #define AUDIT_LOGINUID_SET 24 #define AUDIT_SESSIONID 25 /* Session ID */ #define AUDIT_FSTYPE 26 /* FileSystem Type */ +#define AUDIT_CONTID 27 /* Container ID */ /* These are ONLY useful when checking * at syscall exit time (AUDIT_AT_EXIT). */ @@ -345,6 +346,7 @@ enum { #define AUDIT_FEATURE_BITMAP_SESSIONID_FILTER 0x00000010 #define AUDIT_FEATURE_BITMAP_LOST_RESET 0x00000020 #define AUDIT_FEATURE_BITMAP_FILTER_FS 0x00000040 +#define AUDIT_FEATURE_BITMAP_CONTAINERID 0x00000080 #define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \ AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME | \ @@ -352,7 +354,8 @@ enum { AUDIT_FEATURE_BITMAP_EXCLUDE_EXTEND | \ AUDIT_FEATURE_BITMAP_SESSIONID_FILTER | \ AUDIT_FEATURE_BITMAP_LOST_RESET | \ - AUDIT_FEATURE_BITMAP_FILTER_FS) + AUDIT_FEATURE_BITMAP_FILTER_FS | \ + AUDIT_FEATURE_BITMAP_CONTAINERID) /* deprecated: AUDIT_VERSION_* */ #define AUDIT_VERSION_LATEST AUDIT_FEATURE_BITMAP_ALL diff --git a/kernel/audit.h b/kernel/audit.h index 2a1a8b8a8019..3a40b608bf8d 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -230,6 +230,7 @@ static inline int audit_hash_ino(u32 ino) extern int audit_match_class(int class, unsigned syscall); extern int audit_comparator(const u32 left, const u32 op, const u32 right); +extern int audit_comparator64(const u64 left, const u32 op, const u64 right); extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right); extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right); extern int parent_len(const char *path); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index add360b46b38..516b8e58959e 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -410,6 +410,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) /* FALL THROUGH */ case AUDIT_ARCH: case AUDIT_FSTYPE: + case AUDIT_CONTID: if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; break; @@ -582,6 +583,14 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, } entry->rule.exe = audit_mark; break; + case AUDIT_CONTID: + if (f->val != sizeof(u64)) + goto exit_free; + str = audit_unpack_string(&bufp, &remain, f->val); + if (IS_ERR(str)) + goto exit_free; + f->val64 = ((u64 *)str)[0]; + break; } } @@ -664,6 +673,11 @@ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) data->buflen += data->values[i] = audit_pack_string(&bufp, audit_mark_path(krule->exe)); break; + case AUDIT_CONTID: + data->buflen += data->values[i] = sizeof(u64); + for (i = 0; i < sizeof(u64); i++) + ((char *)bufp)[i] = ((char *)&f->val64)[i]; + break; case AUDIT_LOGINUID_SET: if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { data->fields[i] = AUDIT_LOGINUID; @@ -750,6 +764,10 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) return 1; break; + case AUDIT_CONTID: + if (a->fields[i].val64 != b->fields[i].val64) + return 1; + break; default: if (a->fields[i].val != b->fields[i].val) return 1; @@ -1206,6 +1224,31 @@ int audit_comparator(u32 left, u32 op, u32 right) } } +int audit_comparator64(u64 left, u32 op, u64 right) +{ + switch (op) { + case Audit_equal: + return (left == right); + case Audit_not_equal: + return (left != right); + case Audit_lt: + return (left < right); + case Audit_le: + return (left <= right); + case Audit_gt: + return (left > right); + case Audit_ge: + return (left >= right); + case Audit_bitmask: + return (left & right); + case Audit_bittest: + return ((left & right) == right); + default: + BUG(); + return 0; + } +} + int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) { switch (op) { @@ -1344,6 +1387,10 @@ int audit_filter(int msgtype, unsigned int listtype) result = audit_comparator(audit_loginuid_set(current), f->op, f->val); break; + case AUDIT_CONTID: + result = audit_comparator64(audit_get_contid(current), + f->op, f->val64); + break; case AUDIT_MSGTYPE: result = audit_comparator(msgtype, f->op, f->val); break; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index aa5d13b4fbbb..2d74238e9638 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -616,6 +616,9 @@ static int audit_filter_rules(struct task_struct *tsk, case AUDIT_LOGINUID_SET: result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val); break; + case AUDIT_CONTID: + result = audit_comparator64(audit_get_contid(tsk), f->op, f->val64); + break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: -- 1.8.3.1

Audit events could happen in a network namespace outside of a task context due to packets received from the net that trigger an auditing rule prior to being associated with a running task. The network namespace could be in use by multiple containers by association to the tasks in that network namespace. We still want a way to attribute these events to any potential containers. Keep a list per network namespace to track these audit container identifiiers. Add/increment the audit container identifier on: - initial setting of the audit container identifier via /proc - clone/fork call that inherits an audit container identifier - unshare call that inherits an audit container identifier - setns call that inherits an audit container identifier Delete/decrement the audit container identifier on: - an inherited audit container identifier dropped when child set - process exit - unshare call that drops a net namespace - setns call that drops a net namespace See: https://github.com/linux-audit/audit-kernel/issues/92 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(a)redhat.com&gt; --- include/linux/audit.h | 19 ++++++++++++ kernel/audit.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++-- kernel/nsproxy.c | 4 +++ 3 files changed, 106 insertions(+), 3 deletions(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index fa19fa408931..70255c2dfb9f 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -27,6 +27,7 @@ #include <linux/ptrace.h> #include <linux/namei.h> /* LOOKUP_* */ #include <uapi/linux/audit.h> +#include <linux/refcount.h> #define AUDIT_INO_UNSET ((unsigned long)-1) #define AUDIT_DEV_UNSET ((dev_t)-1) @@ -99,6 +100,13 @@ struct audit_task_info { extern struct audit_task_info init_struct_audit; +struct audit_contid { + struct list_head list; + u64 id; + refcount_t refcount; + struct rcu_head rcu; +}; + extern int is_audit_feature_set(int which); extern int __init audit_register_class(int class, unsigned *list); @@ -202,6 +210,10 @@ static inline u64 audit_get_contid(struct task_struct *tsk) } extern void audit_log_contid(struct audit_context *context, u64 contid); +extern void audit_netns_contid_add(struct net *net, u64 contid); +extern void audit_netns_contid_del(struct net *net, u64 contid); +extern void audit_switch_task_namespaces(struct nsproxy *ns, + struct task_struct *p); extern u32 audit_enabled; #else /* CONFIG_AUDIT */ @@ -271,6 +283,13 @@ static inline u64 audit_get_contid(struct task_struct *tsk) static inline void audit_log_contid(struct audit_context *context, u64 contid) { } +static inline void audit_netns_contid_add(struct net *net, u64 contid) +{ } +static inline void audit_netns_contid_del(struct net *net, u64 contid) +{ } +static inline void audit_switch_task_namespaces(struct nsproxy *ns, + struct task_struct *p) +{ } #define audit_enabled AUDIT_OFF #endif /* CONFIG_AUDIT */ diff --git a/kernel/audit.c b/kernel/audit.c index cf448599ef34..7fa3194f5342 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -72,6 +72,7 @@ #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <net/netns/generic.h> +#include <net/net_namespace.h> #include "audit.h" @@ -99,9 +100,13 @@ /** * struct audit_net - audit private network namespace data * @sk: communication socket + * @contid_list: audit container identifier list + * @contid_list_lock audit container identifier list lock */ struct audit_net { struct sock *sk; + struct list_head contid_list; + spinlock_t contid_list_lock; }; /** @@ -275,8 +280,11 @@ struct audit_task_info init_struct_audit = { void audit_free(struct task_struct *tsk) { struct audit_task_info *info = tsk->audit; + struct nsproxy *ns = tsk->nsproxy; audit_free_syscall(tsk); + if (ns) + audit_netns_contid_del(ns->net_ns, audit_get_contid(tsk)); /* Freeing the audit_task_info struct must be performed after * audit_log_exit() due to need for loginuid and sessionid. */ @@ -376,6 +384,73 @@ static struct sock *audit_get_sk(const struct net *net) return aunet->sk; } +void audit_netns_contid_add(struct net *net, u64 contid) +{ + struct audit_net *aunet = net_generic(net, audit_net_id); + struct list_head *contid_list = &aunet->contid_list; + struct audit_contid *cont; + + if (!audit_contid_valid(contid)) + return; + if (!aunet) + return; + spin_lock(&aunet->contid_list_lock); + if (!list_empty(contid_list)) + list_for_each_entry_rcu(cont, contid_list, list) + if (cont->id == contid) { + refcount_inc(&cont->refcount); + goto out; + } + cont = kmalloc(sizeof(struct audit_contid), GFP_ATOMIC); + if (cont) { + INIT_LIST_HEAD(&cont->list); + cont->id = contid; + refcount_set(&cont->refcount, 1); + list_add_rcu(&cont->list, contid_list); + } +out: + spin_unlock(&aunet->contid_list_lock); +} + +void audit_netns_contid_del(struct net *net, u64 contid) +{ + struct audit_net *aunet; + struct list_head *contid_list; + struct audit_contid *cont = NULL; + + if (!net) + return; + if (!audit_contid_valid(contid)) + return; + aunet = net_generic(net, audit_net_id); + if (!aunet) + return; + contid_list = &aunet->contid_list; + spin_lock(&aunet->contid_list_lock); + if (!list_empty(contid_list)) + list_for_each_entry_rcu(cont, contid_list, list) + if (cont->id == contid) { + if (refcount_dec_and_test(&cont->refcount)) { + list_del_rcu(&cont->list); + kfree_rcu(cont, rcu); + } + break; + } + spin_unlock(&aunet->contid_list_lock); +} + +void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p) +{ + u64 contid = audit_get_contid(p); + struct nsproxy *new = p->nsproxy; + + if (!audit_contid_valid(contid)) + return; + audit_netns_contid_del(ns->net_ns, contid); + if (new) + audit_netns_contid_add(new->net_ns, contid); +} + void audit_panic(const char *message) { switch (audit_failure) { @@ -1619,7 +1694,6 @@ static int __net_init audit_net_init(struct net *net) .flags = NL_CFG_F_NONROOT_RECV, .groups = AUDIT_NLGRP_MAX, }; - struct audit_net *aunet = net_generic(net, audit_net_id); aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg); @@ -1628,7 +1702,8 @@ static int __net_init audit_net_init(struct net *net) return -ENOMEM; } aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; - + INIT_LIST_HEAD(&aunet->contid_list); + spin_lock_init(&aunet->contid_list_lock); return 0; } @@ -2380,6 +2455,7 @@ int audit_set_contid(struct task_struct *task, u64 contid) uid_t uid; struct tty_struct *tty; char comm[sizeof(current->comm)]; + struct net *net = task->nsproxy->net_ns; task_lock(task); /* Can't set if audit disabled */ @@ -2401,8 +2477,12 @@ int audit_set_contid(struct task_struct *task, u64 contid) else if (!(thread_group_leader(task) && thread_group_empty(task))) rc = -EALREADY; read_unlock(&tasklist_lock); - if (!rc) + if (!rc) { + if (audit_contid_valid(oldcontid)) + audit_netns_contid_del(net, oldcontid); task->audit->contid = contid; + audit_netns_contid_add(net, contid); + } task_unlock(task); if (!audit_enabled) diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index f6c5d330059a..718b1201ae70 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -27,6 +27,7 @@ #include <linux/syscalls.h> #include <linux/cgroup.h> #include <linux/perf_event.h> +#include <linux/audit.h> static struct kmem_cache *nsproxy_cachep; @@ -140,6 +141,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) struct nsproxy *old_ns = tsk->nsproxy; struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns); struct nsproxy *new_ns; + u64 contid = audit_get_contid(tsk); if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | CLONE_NEWPID | CLONE_NEWNET | @@ -167,6 +169,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) return PTR_ERR(new_ns); tsk->nsproxy = new_ns; + audit_netns_contid_add(new_ns->net_ns, contid); return 0; } @@ -224,6 +227,7 @@ void switch_task_namespaces(struct task_struct *p, struct nsproxy *new) ns = p->nsproxy; p->nsproxy = new; task_unlock(p); + audit_switch_task_namespaces(ns, p); if (ns && atomic_dec_and_test(&ns->count)) free_nsproxy(ns); -- 1.8.3.1

On Fri, Mar 15, 2019 at 7:35 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > Audit events could happen in a network namespace outside of a task > context due to packets received from the net that trigger an auditing > rule prior to being associated with a running task. The network > namespace could be in use by multiple containers by association to the > tasks in that network namespace. We still want a way to attribute > these events to any potential containers. Keep a list per network > namespace to track these audit container identifiiers. > > Add/increment the audit container identifier on: > - initial setting of the audit container identifier via /proc > - clone/fork call that inherits an audit container identifier > - unshare call that inherits an audit container identifier > - setns call that inherits an audit container identifier > Delete/decrement the audit container identifier on: > - an inherited audit container identifier dropped when child set > - process exit > - unshare call that drops a net namespace > - setns call that drops a net namespace > > See: https://github.com/linux-audit/audit-kernel/issues/92 > 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(a)redhat.com&gt; > --- > include/linux/audit.h | 19 ++++++++++++ > kernel/audit.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++-- > kernel/nsproxy.c | 4 +++ > 3 files changed, 106 insertions(+), 3 deletions(-) > > diff --git a/include/linux/audit.h b/include/linux/audit.h > index fa19fa408931..70255c2dfb9f 100644 > --- a/include/linux/audit.h > +++ b/include/linux/audit.h > @@ -27,6 +27,7 @@ > #include <linux/ptrace.h> > #include <linux/namei.h> /* LOOKUP_* */ > #include <uapi/linux/audit.h> > +#include <linux/refcount.h> > > #define AUDIT_INO_UNSET ((unsigned long)-1) > #define AUDIT_DEV_UNSET ((dev_t)-1) > @@ -99,6 +100,13 @@ struct audit_task_info { > > extern struct audit_task_info init_struct_audit; > > +struct audit_contid { > + struct list_head list; > + u64 id; > + refcount_t refcount; Hm, since we only ever touch the refcount under a spinlock, I wonder if we could just make it a regular unsigned int (we don't need the atomicity guarantees). OTOH, refcount_t comes with some extra overflow checking, so it's probably better to leave it as is...

> + struct rcu_head rcu; > +}; > + > extern int is_audit_feature_set(int which); > > extern int __init audit_register_class(int class, unsigned *list); > @@ -202,6 +210,10 @@ static inline u64 audit_get_contid(struct task_struct *tsk) > } > > extern void audit_log_contid(struct audit_context *context, u64 contid); > +extern void audit_netns_contid_add(struct net *net, u64 contid); > +extern void audit_netns_contid_del(struct net *net, u64 contid); > +extern void audit_switch_task_namespaces(struct nsproxy *ns, > + struct task_struct *p); > > extern u32 audit_enabled; > #else /* CONFIG_AUDIT */ > @@ -271,6 +283,13 @@ static inline u64 audit_get_contid(struct task_struct *tsk) > > static inline void audit_log_contid(struct audit_context *context, u64 contid) > { } > +static inline void audit_netns_contid_add(struct net *net, u64 contid) > +{ } > +static inline void audit_netns_contid_del(struct net *net, u64 contid) > +{ } > +static inline void audit_switch_task_namespaces(struct nsproxy *ns, > + struct task_struct *p) > +{ } > > #define audit_enabled AUDIT_OFF > #endif /* CONFIG_AUDIT */ > diff --git a/kernel/audit.c b/kernel/audit.c > index cf448599ef34..7fa3194f5342 100644 > --- a/kernel/audit.c > +++ b/kernel/audit.c > @@ -72,6 +72,7 @@ > #include <linux/freezer.h> > #include <linux/pid_namespace.h> > #include <net/netns/generic.h> > +#include <net/net_namespace.h> > > #include "audit.h" > > @@ -99,9 +100,13 @@ > /** > * struct audit_net - audit private network namespace data > * @sk: communication socket > + * @contid_list: audit container identifier list > + * @contid_list_lock audit container identifier list lock > */ > struct audit_net { > struct sock *sk; > + struct list_head contid_list; > + spinlock_t contid_list_lock; > }; > > /** > @@ -275,8 +280,11 @@ struct audit_task_info init_struct_audit = { > void audit_free(struct task_struct *tsk) > { > struct audit_task_info *info = tsk->audit; > + struct nsproxy *ns = tsk->nsproxy; > > audit_free_syscall(tsk); > + if (ns) > + audit_netns_contid_del(ns->net_ns, audit_get_contid(tsk)); > /* Freeing the audit_task_info struct must be performed after > * audit_log_exit() due to need for loginuid and sessionid. > */ > @@ -376,6 +384,73 @@ static struct sock *audit_get_sk(const struct net *net) > return aunet->sk; > } > > +void audit_netns_contid_add(struct net *net, u64 contid) > +{ > + struct audit_net *aunet = net_generic(net, audit_net_id); > + struct list_head *contid_list = &aunet->contid_list; > + struct audit_contid *cont; > + > + if (!audit_contid_valid(contid)) > + return; > + if (!aunet) > + return; > + spin_lock(&aunet->contid_list_lock); > + if (!list_empty(contid_list)) > + list_for_each_entry_rcu(cont, contid_list, list) > + if (cont->id == contid) { > + refcount_inc(&cont->refcount); > + goto out; > + } > + cont = kmalloc(sizeof(struct audit_contid), GFP_ATOMIC); > + if (cont) { > + INIT_LIST_HEAD(&cont->list); > + cont->id = contid; > + refcount_set(&cont->refcount, 1); > + list_add_rcu(&cont->list, contid_list); > + } > +out: > + spin_unlock(&aunet->contid_list_lock); > +} > + > +void audit_netns_contid_del(struct net *net, u64 contid) > +{ > + struct audit_net *aunet; > + struct list_head *contid_list; > + struct audit_contid *cont = NULL; > + > + if (!net) > + return; > + if (!audit_contid_valid(contid)) > + return; > + aunet = net_generic(net, audit_net_id); > + if (!aunet) > + return; > + contid_list = &aunet->contid_list; > + spin_lock(&aunet->contid_list_lock); > + if (!list_empty(contid_list)) > + list_for_each_entry_rcu(cont, contid_list, list) > + if (cont->id == contid) { > + if (refcount_dec_and_test(&cont->refcount)) { > + list_del_rcu(&cont->list); > + kfree_rcu(cont, rcu); > + } > + break; > + } > + spin_unlock(&aunet->contid_list_lock); > +} > + > +void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p) > +{ > + u64 contid = audit_get_contid(p); > + struct nsproxy *new = p->nsproxy; > + > + if (!audit_contid_valid(contid)) > + return; > + audit_netns_contid_del(ns->net_ns, contid); > + if (new) > + audit_netns_contid_add(new->net_ns, contid); > +} > + > void audit_panic(const char *message) > { > switch (audit_failure) { > @@ -1619,7 +1694,6 @@ static int __net_init audit_net_init(struct net *net) > .flags = NL_CFG_F_NONROOT_RECV, > .groups = AUDIT_NLGRP_MAX, > }; > - > struct audit_net *aunet = net_generic(net, audit_net_id); > > aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg); > @@ -1628,7 +1702,8 @@ static int __net_init audit_net_init(struct net *net) > return -ENOMEM; > } > aunet->sk->sk_sndtimeo = MAX_SCHEDULE_TIMEOUT; > - > + INIT_LIST_HEAD(&aunet->contid_list); > + spin_lock_init(&aunet->contid_list_lock); > return 0; > } > > @@ -2380,6 +2455,7 @@ int audit_set_contid(struct task_struct *task, u64 contid) > uid_t uid; > struct tty_struct *tty; > char comm[sizeof(current->comm)]; > + struct net *net = task->nsproxy->net_ns; > > task_lock(task); > /* Can't set if audit disabled */ > @@ -2401,8 +2477,12 @@ int audit_set_contid(struct task_struct *task, u64 contid) > else if (!(thread_group_leader(task) && thread_group_empty(task))) > rc = -EALREADY; > read_unlock(&tasklist_lock); > - if (!rc) > + if (!rc) { > + if (audit_contid_valid(oldcontid)) > + audit_netns_contid_del(net, oldcontid); > task->audit->contid = contid; > + audit_netns_contid_add(net, contid); > + } > task_unlock(task); > > if (!audit_enabled) > diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c > index f6c5d330059a..718b1201ae70 100644 > --- a/kernel/nsproxy.c > +++ b/kernel/nsproxy.c > @@ -27,6 +27,7 @@ > #include <linux/syscalls.h> > #include <linux/cgroup.h> > #include <linux/perf_event.h> > +#include <linux/audit.h> > > static struct kmem_cache *nsproxy_cachep; > > @@ -140,6 +141,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) > struct nsproxy *old_ns = tsk->nsproxy; > struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns); > struct nsproxy *new_ns; > + u64 contid = audit_get_contid(tsk); > > if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | > CLONE_NEWPID | CLONE_NEWNET | > @@ -167,6 +169,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) > return PTR_ERR(new_ns); > > tsk->nsproxy = new_ns; > + audit_netns_contid_add(new_ns->net_ns, contid); > return 0; > } > > @@ -224,6 +227,7 @@ void switch_task_namespaces(struct task_struct *p, struct nsproxy *new) > ns = p->nsproxy; > p->nsproxy = new; > task_unlock(p); > + audit_switch_task_namespaces(ns, p); Since we call audit_switch_task_namespaces() after task_unlock(), could there be a potential race condition? I'm not going to dive too much into this now, because it's getting late here, but on first look it seems like p->nsproxy could change under our hands before we fetch it in audit_switch_task_namespaces()...

> > if (ns && atomic_dec_and_test(&ns->count)) > free_nsproxy(ns); > -- > 1.8.3.1 Ondrej Mosnacek <omosnace at redhat dot com>

On 2019-03-27 23:42, Ondrej Mosnacek wrote: > On Fri, Mar 15, 2019 at 7:35 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > > Audit events could happen in a network namespace outside of a task > > context due to packets received from the net that trigger an auditing > > rule prior to being associated with a running task. The network > > namespace could be in use by multiple containers by association to the > > tasks in that network namespace. We still want a way to attribute > > these events to any potential containers. Keep a list per network > > namespace to track these audit container identifiiers. > > > > Add/increment the audit container identifier on: > > - initial setting of the audit container identifier via /proc > > - clone/fork call that inherits an audit container identifier > > - unshare call that inherits an audit container identifier > > - setns call that inherits an audit container identifier > > Delete/decrement the audit container identifier on: > > - an inherited audit container identifier dropped when child set > > - process exit > > - unshare call that drops a net namespace > > - setns call that drops a net namespace > > > > See: https://github.com/linux-audit/audit-kernel/issues/92 > > 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(a)redhat.com&gt; > > --- > > include/linux/audit.h | 19 ++++++++++++ > > kernel/audit.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++-- > > kernel/nsproxy.c | 4 +++ > > 3 files changed, 106 insertions(+), 3 deletions(-) > > > > diff --git a/include/linux/audit.h b/include/linux/audit.h > > index fa19fa408931..70255c2dfb9f 100644 > > --- a/include/linux/audit.h > > +++ b/include/linux/audit.h > > @@ -27,6 +27,7 @@ > > #include <linux/ptrace.h> > > #include <linux/namei.h> /* LOOKUP_* */ > > #include <uapi/linux/audit.h> > > +#include <linux/refcount.h> > > > > #define AUDIT_INO_UNSET ((unsigned long)-1) > > #define AUDIT_DEV_UNSET ((dev_t)-1) > > @@ -99,6 +100,13 @@ struct audit_task_info { > > > > extern struct audit_task_info init_struct_audit; > > > > +struct audit_contid { > > + struct list_head list; > > + u64 id; > > + refcount_t refcount; > > Hm, since we only ever touch the refcount under a spinlock, I wonder > if we could just make it a regular unsigned int (we don't need the > atomicity guarantees). OTOH, refcount_t comes with some extra overflow > checking, so it's probably better to leave it as is... Since the update is done using rcu-safe methods, do we even need the spin_lock? Neil? Paul?

On 2019-03-28 11:46, Paul Moore wrote: > On Wed, Mar 27, 2019 at 9:12 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > > > > On 2019-03-27 23:42, Ondrej Mosnacek wrote: > > > On Fri, Mar 15, 2019 at 7:35 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > > > > Audit events could happen in a network namespace outside of a task > > > > context due to packets received from the net that trigger an auditing > > > > rule prior to being associated with a running task. The network > > > > namespace could be in use by multiple containers by association to the > > > > tasks in that network namespace. We still want a way to attribute > > > > these events to any potential containers. Keep a list per network > > > > namespace to track these audit container identifiiers. > > > > > > > > Add/increment the audit container identifier on: > > > > - initial setting of the audit container identifier via /proc > > > > - clone/fork call that inherits an audit container identifier > > > > - unshare call that inherits an audit container identifier > > > > - setns call that inherits an audit container identifier > > > > Delete/decrement the audit container identifier on: > > > > - an inherited audit container identifier dropped when child set > > > > - process exit > > > > - unshare call that drops a net namespace > > > > - setns call that drops a net namespace > > > > > > > > See: https://github.com/linux-audit/audit-kernel/issues/92 > > > > 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(a)redhat.com&gt; > > > > --- > > > > include/linux/audit.h | 19 ++++++++++++ > > > > kernel/audit.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++-- > > > > kernel/nsproxy.c | 4 +++ > > > > 3 files changed, 106 insertions(+), 3 deletions(-) > > > > > > > > diff --git a/include/linux/audit.h b/include/linux/audit.h > > > > index fa19fa408931..70255c2dfb9f 100644 > > > > --- a/include/linux/audit.h > > > > +++ b/include/linux/audit.h > > > > @@ -27,6 +27,7 @@ > > > > #include <linux/ptrace.h> > > > > #include <linux/namei.h> /* LOOKUP_* */ > > > > #include <uapi/linux/audit.h> > > > > +#include <linux/refcount.h> > > > > > > > > #define AUDIT_INO_UNSET ((unsigned long)-1) > > > > #define AUDIT_DEV_UNSET ((dev_t)-1) > > > > @@ -99,6 +100,13 @@ struct audit_task_info { > > > > > > > > extern struct audit_task_info init_struct_audit; > > > > > > > > +struct audit_contid { > > > > + struct list_head list; > > > > + u64 id; > > > > + refcount_t refcount; > > > > > > Hm, since we only ever touch the refcount under a spinlock, I wonder > > > if we could just make it a regular unsigned int (we don't need the > > > atomicity guarantees). OTOH, refcount_t comes with some extra overflow > > > checking, so it's probably better to leave it as is... > > > > Since the update is done using rcu-safe methods, do we even need the > > spin_lock? Neil? Paul? > > As discussed, the refcount field is protected against simultaneous > writes by the spinlock that protects additions/removals from the list > as a whole so I don't believe the refcount_t atomicity is critical in > this regard. > > Where it gets tricky, and I can't say I'm 100% confident on my answer > here, is if refcount was a regular int and we wanted to access it > outside of a spinlock (to be clear, it doesn't look like this patch > currently does this). With RCU, if refcount was a regular int > (unsigned or otherwise), I believe it would be possible for different > threads of execution to potentially see different values of refcount > (assuming one thread was adding/removing from the list). Using a > refcount_t would protect against this, alternatively, taking the > spinlock should also protect against this. Ok, from the above it isn't clear to me if you are happy with the current code or would prefer any changes, or from below that you still need to work it through to make a pronouncement. It sounds to me you would be ok with *either* spinlock *or* refcount_t, but don't see the need for both.

On 2019-03-28 11:46, Paul Moore wrote: > On Wed, Mar 27, 2019 at 9:12 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > > > > On 2019-03-27 23:42, Ondrej Mosnacek wrote: > > > On Fri, Mar 15, 2019 at 7:35 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > > > > Audit events could happen in a network namespace outside of a task > > > > context due to packets received from the net that trigger an auditing > > > > rule prior to being associated with a running task. The network > > > > namespace could be in use by multiple containers by association to the > > > > tasks in that network namespace. We still want a way to attribute > > > > these events to any potential containers. Keep a list per network > > > > namespace to track these audit container identifiiers. > > > > > > > > Add/increment the audit container identifier on: > > > > - initial setting of the audit container identifier via /proc > > > > - clone/fork call that inherits an audit container identifier > > > > - unshare call that inherits an audit container identifier > > > > - setns call that inherits an audit container identifier > > > > Delete/decrement the audit container identifier on: > > > > - an inherited audit container identifier dropped when child set > > > > - process exit > > > > - unshare call that drops a net namespace > > > > - setns call that drops a net namespace > > > > > > > > See: https://github.com/linux-audit/audit-kernel/issues/92 > > > > 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(a)redhat.com&gt; > > > > --- > > > > include/linux/audit.h | 19 ++++++++++++ > > > > kernel/audit.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++-- > > > > kernel/nsproxy.c | 4 +++ > > > > 3 files changed, 106 insertions(+), 3 deletions(-) > > > > > > > > diff --git a/include/linux/audit.h b/include/linux/audit.h > > > > index fa19fa408931..70255c2dfb9f 100644 > > > > --- a/include/linux/audit.h > > > > +++ b/include/linux/audit.h > > > > @@ -27,6 +27,7 @@ > > > > #include <linux/ptrace.h> > > > > #include <linux/namei.h> /* LOOKUP_* */ > > > > #include <uapi/linux/audit.h> > > > > +#include <linux/refcount.h> > > > > > > > > #define AUDIT_INO_UNSET ((unsigned long)-1) > > > > #define AUDIT_DEV_UNSET ((dev_t)-1) > > > > @@ -99,6 +100,13 @@ struct audit_task_info { > > > > > > > > extern struct audit_task_info init_struct_audit; > > > > > > > > +struct audit_contid { > > > > + struct list_head list; > > > > + u64 id; > > > > + refcount_t refcount; > > > > > > Hm, since we only ever touch the refcount under a spinlock, I wonder > > > if we could just make it a regular unsigned int (we don't need the > > > atomicity guarantees). OTOH, refcount_t comes with some extra overflow > > > checking, so it's probably better to leave it as is... > > > > Since the update is done using rcu-safe methods, do we even need the > > spin_lock? Neil? Paul? > > As discussed, the refcount field is protected against simultaneous > writes by the spinlock that protects additions/removals from the list > as a whole so I don't believe the refcount_t atomicity is critical in > this regard. > > Where it gets tricky, and I can't say I'm 100% confident on my answer > here, is if refcount was a regular int and we wanted to access it > outside of a spinlock (to be clear, it doesn't look like this patch > currently does this). With RCU, if refcount was a regular int > (unsigned or otherwise), I believe it would be possible for different > threads of execution to potentially see different values of refcount > (assuming one thread was adding/removing from the list). Using a > refcount_t would protect against this, alternatively, taking the > spinlock should also protect against this. Ok, from the above it isn't clear to me if you are happy with the current code or would prefer any changes, or from below that you still need to work it through to make a pronouncement. It sounds to me you would be ok with *either* spinlock *or* refcount_t, but don't see the need for both.

> As we all know, RCU can be tricky at times, so I may be off on the > above; if I am, please provide an explanation so I (and likely others > as well) can learn a little bit more. :) > > -- > paul moore > www.paul-moore.com - RGB -- Richard Guy Briggs <rgb(a)redhat.com&gt; Sr. S/W Engineer, Kernel Security, Base Operating Systems Remote, Ottawa, Red Hat Canada IRC: rgb, SunRaycer Voice: +1.647.777.2635, Internal: (81) 32635

Audit events could happen in a network namespace outside of a task context due to packets received from the net that trigger an auditing rule prior to being associated with a running task. The network namespace could be in use by multiple containers by association to the tasks in that network namespace. We still want a way to attribute these events to any potential containers. Keep a list per network namespace to track these audit container identifiiers. Add/increment the audit container identifier on: - initial setting of the audit container identifier via /proc - clone/fork call that inherits an audit container identifier - unshare call that inherits an audit container identifier - setns call that inherits an audit container identifier Delete/decrement the audit container identifier on: - an inherited audit container identifier dropped when child set - process exit - unshare call that drops a net namespace - setns call that drops a net namespace See: https://github.com/linux-audit/audit-kernel/issues/92 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(a)redhat.com&gt; --- include/linux/audit.h | 19 ++++++++++++ kernel/audit.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++-- kernel/nsproxy.c | 4 +++ 3 files changed, 106 insertions(+), 3 deletions(-)

diff --git a/kernel/audit.c b/kernel/audit.c index cf448599ef34..7fa3194f5342 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -72,6 +72,7 @@ #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <net/netns/generic.h> +#include <net/net_namespace.h> #include "audit.h" @@ -99,9 +100,13 @@ /** * struct audit_net - audit private network namespace data * @sk: communication socket + * @contid_list: audit container identifier list + * @contid_list_lock audit container identifier list lock */ struct audit_net { struct sock *sk; + struct list_head contid_list; + spinlock_t contid_list_lock; }; /** @@ -275,8 +280,11 @@ struct audit_task_info init_struct_audit = { void audit_free(struct task_struct *tsk) { struct audit_task_info *info = tsk->audit; + struct nsproxy *ns = tsk->nsproxy; audit_free_syscall(tsk); + if (ns) + audit_netns_contid_del(ns->net_ns, audit_get_contid(tsk)); /* Freeing the audit_task_info struct must be performed after * audit_log_exit() due to need for loginuid and sessionid. */ @@ -376,6 +384,73 @@ static struct sock *audit_get_sk(const struct net *net) return aunet->sk; } +void audit_netns_contid_add(struct net *net, u64 contid) +{ + struct audit_net *aunet = net_generic(net, audit_net_id); + struct list_head *contid_list = &aunet->contid_list; + struct audit_contid *cont; + + if (!audit_contid_valid(contid)) + return; + if (!aunet) + return;

+ spin_lock(&aunet->contid_list_lock); + if (!list_empty(contid_list))

+ list_for_each_entry_rcu(cont, contid_list, list) + if (cont->id == contid) { + refcount_inc(&cont->refcount); + goto out; + } + cont = kmalloc(sizeof(struct audit_contid), GFP_ATOMIC);

+ if (cont) { + INIT_LIST_HEAD(&cont->list);

+ cont->id = contid; + refcount_set(&cont->refcount, 1); + list_add_rcu(&cont->list, contid_list); + } +out: + spin_unlock(&aunet->contid_list_lock); +}

On Fri, Mar 15, 2019 at 2:35 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > Audit events could happen in a network namespace outside of a task > context due to packets received from the net that trigger an auditing > rule prior to being associated with a running task. The network > namespace could be in use by multiple containers by association to the > tasks in that network namespace. We still want a way to attribute > these events to any potential containers. Keep a list per network > namespace to track these audit container identifiiers. > > Add/increment the audit container identifier on: > - initial setting of the audit container identifier via /proc > - clone/fork call that inherits an audit container identifier > - unshare call that inherits an audit container identifier > - setns call that inherits an audit container identifier > Delete/decrement the audit container identifier on: > - an inherited audit container identifier dropped when child set > - process exit > - unshare call that drops a net namespace > - setns call that drops a net namespace > > See: https://github.com/linux-audit/audit-kernel/issues/92 > 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(a)redhat.com&gt; > --- > include/linux/audit.h | 19 ++++++++++++ > kernel/audit.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++-- > kernel/nsproxy.c | 4 +++ > 3 files changed, 106 insertions(+), 3 deletions(-) ... > diff --git a/kernel/audit.c b/kernel/audit.c > index cf448599ef34..7fa3194f5342 100644 > --- a/kernel/audit.c > +++ b/kernel/audit.c > @@ -72,6 +72,7 @@ > #include <linux/freezer.h> > #include <linux/pid_namespace.h> > #include <net/netns/generic.h> > +#include <net/net_namespace.h> > > #include "audit.h" > > @@ -99,9 +100,13 @@ > /** > * struct audit_net - audit private network namespace data > * @sk: communication socket > + * @contid_list: audit container identifier list > + * @contid_list_lock audit container identifier list lock > */ > struct audit_net { > struct sock *sk; > + struct list_head contid_list; > + spinlock_t contid_list_lock; > }; > > /** > @@ -275,8 +280,11 @@ struct audit_task_info init_struct_audit = { > void audit_free(struct task_struct *tsk) > { > struct audit_task_info *info = tsk->audit; > + struct nsproxy *ns = tsk->nsproxy; > > audit_free_syscall(tsk); > + if (ns) > + audit_netns_contid_del(ns->net_ns, audit_get_contid(tsk)); > /* Freeing the audit_task_info struct must be performed after > * audit_log_exit() due to need for loginuid and sessionid. > */ > @@ -376,6 +384,73 @@ static struct sock *audit_get_sk(const struct net *net) > return aunet->sk; > } > > +void audit_netns_contid_add(struct net *net, u64 contid) > +{ > + struct audit_net *aunet = net_generic(net, audit_net_id); > + struct list_head *contid_list = &aunet->contid_list; > + struct audit_contid *cont; > + > + if (!audit_contid_valid(contid)) > + return; > + if (!aunet) > + return; We should move the contid_list assignment below this check, or decide that aunet is always going to valid (?) and get rid of this check completely.

> + spin_lock(&aunet->contid_list_lock); > + if (!list_empty(contid_list)) We don't need the list_empty() check here do we? I think we can just call list_for_each_entry_rcu(), yes?

> + list_for_each_entry_rcu(cont, contid_list, list) > + if (cont->id == contid) { > + refcount_inc(&cont->refcount); > + goto out; > + } > + cont = kmalloc(sizeof(struct audit_contid), GFP_ATOMIC); If you had to guess, what do you think is going to be more common: bumping the refcount of an existing entry in the list, or adding a new entry? I'm asking because I always get a little nervous when doing allocations while holding a spinlock. Yes, you are doing it with GFP_ATOMIC, but it still seems like something to try and avoid if this is going to approach 50%. However, if the new entry is rare then the extra work of always doing the allocation before taking the lock and then freeing it afterwards might be a bad tradeoff.

My gut feeling says we might do about as many allocations as refcount bumps, but I could be thinking about this wrong. Moving the allocation outside the spinlock might also open the door to doing this as GFP_KERNEL, which is a good thing, but I haven't looked at the callers to see if that is possible (it may not be). That's an exercise left to the patch author (if he hasn't done that already). > + if (cont) { > + INIT_LIST_HEAD(&cont->list); Unless there is some guidance that INIT_LIST_HEAD() should be used regardless, you shouldn't need to call this here since list_add_rcu() will take care of any list.h related initialization.

> + cont->id = contid; > + refcount_set(&cont->refcount, 1); > + list_add_rcu(&cont->list, contid_list); > + } > +out: > + spin_unlock(&aunet->contid_list_lock); > +} -- paul moore www.paul-moore.com

On Tue, Apr 2, 2019 at 7:32 AM Neil Horman <nhorman(a)tuxdriver.com&gt; wrote: > On Mon, Apr 01, 2019 at 10:50:03AM -0400, Paul Moore wrote: > > On Fri, Mar 15, 2019 at 2:35 PM Richard Guy Briggs <rgb(a)redhat.com&gt; wrote: > > > Audit events could happen in a network namespace outside of a task > > > context due to packets received from the net that trigger an auditing > > > rule prior to being associated with a running task. The network > > > namespace could be in use by multiple containers by association to the > > > tasks in that network namespace. We still want a way to attribute > > > these events to any potential containers. Keep a list per network > > > namespace to track these audit container identifiiers. > > > > > > Add/increment the audit container identifier on: > > > - initial setting of the audit container identifier via /proc > > > - clone/fork call that inherits an audit container identifier > > > - unshare call that inherits an audit container identifier > > > - setns call that inherits an audit container identifier > > > Delete/decrement the audit container identifier on: > > > - an inherited audit container identifier dropped when child set > > > - process exit > > > - unshare call that drops a net namespace > > > - setns call that drops a net namespace > > > > > > See: https://github.com/linux-audit/audit-kernel/issues/92 > > > 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(a)redhat.com&gt; > > > --- > > > include/linux/audit.h | 19 ++++++++++++ > > > kernel/audit.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++++-- > > > kernel/nsproxy.c | 4 +++ > > > 3 files changed, 106 insertions(+), 3 deletions(-) > > > > ... > > > > > diff --git a/kernel/audit.c b/kernel/audit.c > > > index cf448599ef34..7fa3194f5342 100644 > > > --- a/kernel/audit.c > > > +++ b/kernel/audit.c > > > @@ -72,6 +72,7 @@ > > > #include <linux/freezer.h> > > > #include <linux/pid_namespace.h> > > > #include <net/netns/generic.h> > > > +#include <net/net_namespace.h> > > > > > > #include "audit.h" > > > > > > @@ -99,9 +100,13 @@ > > > /** > > > * struct audit_net - audit private network namespace data > > > * @sk: communication socket > > > + * @contid_list: audit container identifier list > > > + * @contid_list_lock audit container identifier list lock > > > */ > > > struct audit_net { > > > struct sock *sk; > > > + struct list_head contid_list; > > > + spinlock_t contid_list_lock; > > > }; > > > > > > /** > > > @@ -275,8 +280,11 @@ struct audit_task_info init_struct_audit = { > > > void audit_free(struct task_struct *tsk) > > > { > > > struct audit_task_info *info = tsk->audit; > > > + struct nsproxy *ns = tsk->nsproxy; > > > > > > audit_free_syscall(tsk); > > > + if (ns) > > > + audit_netns_contid_del(ns->net_ns, audit_get_contid(tsk)); > > > /* Freeing the audit_task_info struct must be performed after > > > * audit_log_exit() due to need for loginuid and sessionid. > > > */ > > > @@ -376,6 +384,73 @@ static struct sock *audit_get_sk(const struct net *net) > > > return aunet->sk; > > > } > > > > > > +void audit_netns_contid_add(struct net *net, u64 contid) > > > +{ > > > + struct audit_net *aunet = net_generic(net, audit_net_id); > > > + struct list_head *contid_list = &aunet->contid_list; > > > + struct audit_contid *cont; > > > + > > > + if (!audit_contid_valid(contid)) > > > + return; > > > + if (!aunet) > > > + return; > > > > We should move the contid_list assignment below this check, or decide > > that aunet is always going to valid (?) and get rid of this check > > completely. > > > I'm not sure why that would be needed. Finding the net_id list is an operation > of a map relating net namespaces to lists, not contids to lists. We could do > it, sure, but since they're unrelated operations, I don't think we experience > any slowdowns from doing it this way. In the first line of the function, when aunet is declared, it is also assigned a value using net_generic(): struct audit_net *aunet = net_generic(net, audit_net_id); Later in the function there is check to see if aunet is NULL, yet on the second line of the function (before the NULL check), there is this line of code: struct list_head *contid_list = &aunet->contid_list; ... which could result in the dereference of a NULL pointer if aunet is NULL. My suggestion was either to move this assignment below the aunet-NULL check or decide that aunet was always going to be valid (e.g. non-NULL) and do away with the aunet-NULL check completely. Richard has since replied that the aunet-NULL check has been demonstrated to be necessary so the proper thing to do would be to move the assignment. I believe that is what Richard is planning on doing.

> > > + if (cont) { > > > + INIT_LIST_HEAD(&cont->list); > > > > Unless there is some guidance that INIT_LIST_HEAD() should be used > > regardless, you shouldn't need to call this here since list_add_rcu() > > will take care of any list.h related initialization. > > There is a corner case that needs it. list_add_rcu has a check that gets > called, __list_add_valid. Its a noop in the regular case, but if > CONFIG_DEBUG_LIST is defined, its a check to ensure that the next and prev > pointers getting passed in aren't set to detectable corrupt values. If we pass > in garbage, we can get transient false positives on that check, so we need to > set the list pointers to known good values before hand, either by using kzalloc, > or INIT_LIST_HEAD, as has been done here. Given that we expressly set every > field of this structure, I think this is the right approach, as it uses the list > macro to expressly set the list values to their proper state. Good to know, thanks. -- paul moore www.paul-moore.com

Add audit container identifier auxiliary record(s) to NETFILTER_PKT event standalone records. Iterate through all potential audit container identifiers associated with a network namespace. Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; --- include/linux/audit.h | 5 +++++ kernel/audit.c | 41 +++++++++++++++++++++++++++++++++++++++++ net/netfilter/nft_log.c | 11 +++++++++-- net/netfilter/xt_AUDIT.c | 11 +++++++++-- 4 files changed, 64 insertions(+), 4 deletions(-) diff --git a/include/linux/audit.h b/include/linux/audit.h index 70255c2dfb9f..723e2d020228 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -214,6 +214,8 @@ static inline u64 audit_get_contid(struct task_struct *tsk) extern void audit_netns_contid_del(struct net *net, u64 contid); extern void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p); +extern void audit_log_netns_contid_list(struct net *net, + struct audit_context *context); extern u32 audit_enabled; #else /* CONFIG_AUDIT */ @@ -290,6 +292,9 @@ static inline void audit_netns_contid_del(struct net *net, u64 contid) static inline void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p) { } +static inline void audit_log_netns_contid_list(struct net *net, + struct audit_context *context) +{ } #define audit_enabled AUDIT_OFF #endif /* CONFIG_AUDIT */ diff --git a/kernel/audit.c b/kernel/audit.c index 7fa3194f5342..80ed323feeb5 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -451,6 +451,47 @@ void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p) audit_netns_contid_add(new->net_ns, contid); } +/** + * audit_log_netns_contid_list - List contids for the given network namespace + * @net: the network namespace of interest + * @context: the audit context to use + * + * Description: + * Issues a CONTAINER_ID record with a CSV list of contids associated + * with a network namespace to accompany a NETFILTER_PKT record. + */ +void audit_log_netns_contid_list(struct net *net, struct audit_context *context) +{ + struct audit_buffer *ab = NULL; + struct audit_contid *cont; + bool first = true; + struct audit_net *aunet; + + /* Generate AUDIT_CONTAINER_ID record with container ID CSV list */ + rcu_read_lock(); + aunet = net_generic(net, audit_net_id); + if (!aunet) + goto out; + list_for_each_entry_rcu(cont, &aunet->contid_list, list) { + if (first) { + ab = audit_log_start(context, GFP_ATOMIC, + AUDIT_CONTAINER_ID); + if (!ab) { + audit_log_lost("out of memory in audit_log_netns_contid_list"); + goto out; + } + audit_log_format(ab, "contid="); + } else + audit_log_format(ab, ","); + audit_log_format(ab, "%llu", cont->id); + first = false; + } + audit_log_end(ab); +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL(audit_log_netns_contid_list); + void audit_panic(const char *message) { switch (audit_failure) { diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index 655187bed5d8..bdb1ec2368a7 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -69,13 +69,16 @@ static void nft_log_eval_audit(const struct nft_pktinfo *pkt) struct sk_buff *skb = pkt->skb; struct audit_buffer *ab; int fam = -1; + struct audit_context *context; + struct net *net; if (!audit_enabled) return; - ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT); + context = audit_alloc_local(GFP_ATOMIC); + ab = audit_log_start(context, GFP_ATOMIC, AUDIT_NETFILTER_PKT); if (!ab) - return; + goto errout; audit_log_format(ab, "mark=%#x", skb->mark); @@ -102,6 +105,10 @@ static void nft_log_eval_audit(const struct nft_pktinfo *pkt) audit_log_format(ab, " saddr=? daddr=? proto=-1"); audit_log_end(ab); + net = xt_net(&pkt->xt); + audit_log_netns_contid_list(net, context); +errout: + audit_free_context(context); } static void nft_log_eval(const struct nft_expr *expr, diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c index af883f1b64f9..a3e547435f13 100644 --- a/net/netfilter/xt_AUDIT.c +++ b/net/netfilter/xt_AUDIT.c @@ -71,10 +71,13 @@ static bool audit_ip6(struct audit_buffer *ab, struct sk_buff *skb) { struct audit_buffer *ab; int fam = -1; + struct audit_context *context; + struct net *net; if (audit_enabled == AUDIT_OFF) - goto errout; - ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT); + goto out; + context = audit_alloc_local(GFP_ATOMIC); + ab = audit_log_start(context, GFP_ATOMIC, AUDIT_NETFILTER_PKT); if (ab == NULL) goto errout; @@ -104,7 +107,11 @@ static bool audit_ip6(struct audit_buffer *ab, struct sk_buff *skb) audit_log_end(ab); + net = xt_net(par); + audit_log_netns_contid_list(net, context); errout: + audit_free_context(context); +out: return XT_CONTINUE; } -- 1.8.3.1

Add audit container identifier auxiliary record(s) to NETFILTER_PKT event standalone records. Iterate through all potential audit container identifiers associated with a network namespace. Signed-off-by: Richard Guy Briggs <rgb(a)redhat.com&gt; --- include/linux/audit.h | 5 +++++ kernel/audit.c | 41 +++++++++++++++++++++++++++++++++++++++++ net/netfilter/nft_log.c | 11 +++++++++-- net/netfilter/xt_AUDIT.c | 11 +++++++++-- 4 files changed, 64 insertions(+), 4 deletions(-)

diff --git a/kernel/audit.c b/kernel/audit.c index 7fa3194f5342..80ed323feeb5 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -451,6 +451,47 @@ void audit_switch_task_namespaces(struct nsproxy *ns, struct task_struct *p) audit_netns_contid_add(new->net_ns, contid); } +/** + * audit_log_netns_contid_list - List contids for the given network namespace + * @net: the network namespace of interest + * @context: the audit context to use + * + * Description: + * Issues a CONTAINER_ID record with a CSV list of contids associated + * with a network namespace to accompany a NETFILTER_PKT record. + */ +void audit_log_netns_contid_list(struct net *net, struct audit_context *context) +{ + struct audit_buffer *ab = NULL; + struct audit_contid *cont; + bool first = true; + struct audit_net *aunet; + + /* Generate AUDIT_CONTAINER_ID record with container ID CSV list */ + rcu_read_lock(); + aunet = net_generic(net, audit_net_id); + if (!aunet) + goto out; + list_for_each_entry_rcu(cont, &aunet->contid_list, list) { + if (first) {

+ ab = audit_log_start(context, GFP_ATOMIC, + AUDIT_CONTAINER_ID); + if (!ab) { + audit_log_lost("out of memory in audit_log_netns_contid_list"); + goto out; + } + audit_log_format(ab, "contid="); + } else + audit_log_format(ab, ","); + audit_log_format(ab, "%llu", cont->id); + first = false; + } + audit_log_end(ab); +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL(audit_log_netns_contid_list);