1 files changed, 368 insertions, 100 deletions

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index b1cb1dbf7417..c131985c3e6d 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -805,6 +805,34 @@ static int audit_in_mask(const struct audit_krule *rule, unsigned long val)
 	return rule->mask[word] & bit;
 }
 
+/**
+ * audit_filter_uring - apply filters to an io_uring operation
+ * @tsk: associated task
+ * @ctx: audit context
+ */
+static void audit_filter_uring(struct task_struct *tsk,
+			       struct audit_context *ctx)
+{
+	struct audit_entry *e;
+	enum audit_state state;
+
+	if (auditd_test_task(tsk))
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_URING_EXIT],
+				list) {
+		if (audit_in_mask(&e->rule, ctx->uring_op) &&
+		    audit_filter_rules(tsk, &e->rule, ctx, NULL, &state,
+				       false)) {
+			rcu_read_unlock();
+			ctx->current_state = state;
+			return;
+		}
+	}
+	rcu_read_unlock();
+}
+
 /* At syscall exit time, this filter is called if the audit_state is
  * not low enough that auditing cannot take place, but is also not
  * high enough that we already know we have to write an audit record
@@ -915,10 +943,81 @@ static inline void audit_free_aux(struct audit_context *context)
 		context->aux = aux->next;
 		kfree(aux);
 	}
+	context->aux = NULL;
 	while ((aux = context->aux_pids)) {
 		context->aux_pids = aux->next;
 		kfree(aux);
 	}
+	context->aux_pids = NULL;
+}
+
+/**
+ * audit_reset_context - reset a audit_context structure
+ * @ctx: the audit_context to reset
+ *
+ * All fields in the audit_context will be reset to an initial state, all
+ * references held by fields will be dropped, and private memory will be
+ * released.  When this function returns the audit_context will be suitable
+ * for reuse, so long as the passed context is not NULL or a dummy context.
+ */
+static void audit_reset_context(struct audit_context *ctx)
+{
+	if (!ctx)
+		return;
+
+	/* if ctx is non-null, reset the "ctx->state" regardless */
+	ctx->context = AUDIT_CTX_UNUSED;
+	if (ctx->dummy)
+		return;
+
+	/*
+	 * NOTE: It shouldn't matter in what order we release the fields, so
+	 *       release them in the order in which they appear in the struct;
+	 *       this gives us some hope of quickly making sure we are
+	 *       resetting the audit_context properly.
+	 *
+	 *       Other things worth mentioning:
+	 *       - we don't reset "dummy"
+	 *       - we don't reset "state", we do reset "current_state"
+	 *       - we preserve "filterkey" if "state" is AUDIT_STATE_RECORD
+	 *       - much of this is likely overkill, but play it safe for now
+	 *       - we really need to work on improving the audit_context struct
+	 */
+
+	ctx->current_state = ctx->state;
+	ctx->serial = 0;
+	ctx->major = 0;
+	ctx->uring_op = 0;
+	ctx->ctime = (struct timespec64){ .tv_sec = 0, .tv_nsec = 0 };
+	memset(ctx->argv, 0, sizeof(ctx->argv));
+	ctx->return_code = 0;
+	ctx->prio = (ctx->state == AUDIT_STATE_RECORD ? ~0ULL : 0);
+	ctx->return_valid = AUDITSC_INVALID;
+	audit_free_names(ctx);
+	if (ctx->state != AUDIT_STATE_RECORD) {
+		kfree(ctx->filterkey);
+		ctx->filterkey = NULL;
+	}
+	audit_free_aux(ctx);
+	kfree(ctx->sockaddr);
+	ctx->sockaddr = NULL;
+	ctx->sockaddr_len = 0;
+	ctx->pid = ctx->ppid = 0;
+	ctx->uid = ctx->euid = ctx->suid = ctx->fsuid = KUIDT_INIT(0);
+	ctx->gid = ctx->egid = ctx->sgid = ctx->fsgid = KGIDT_INIT(0);
+	ctx->personality = 0;
+	ctx->arch = 0;
+	ctx->target_pid = 0;
+	ctx->target_auid = ctx->target_uid = KUIDT_INIT(0);
+	ctx->target_sessionid = 0;
+	ctx->target_sid = 0;
+	ctx->target_comm[0] = '\0';
+	unroll_tree_refs(ctx, NULL, 0);
+	WARN_ON(!list_empty(&ctx->killed_trees));
+	ctx->type = 0;
+	audit_free_module(ctx);
+	ctx->fds[0] = -1;
+	audit_proctitle_free(ctx);
 }
 
 static inline struct audit_context *audit_alloc_context(enum audit_state state)
@@ -928,6 +1027,7 @@ static inline struct audit_context *audit_alloc_context(enum audit_state state)
 	context = kzalloc(sizeof(*context), GFP_KERNEL);
 	if (!context)
 		return NULL;
+	context->context = AUDIT_CTX_UNUSED;
 	context->state = state;
 	context->prio = state == AUDIT_STATE_RECORD ? ~0ULL : 0;
 	INIT_LIST_HEAD(&context->killed_trees);
@@ -953,7 +1053,7 @@ int audit_alloc(struct task_struct *tsk)
 	char *key = NULL;
 
 	if (likely(!audit_ever_enabled))
-		return 0; /* Return if not auditing. */
+		return 0;
 
 	state = audit_filter_task(tsk, &key);
 	if (state == AUDIT_STATE_DISABLED) {
@@ -973,16 +1073,37 @@ int audit_alloc(struct task_struct *tsk)
 	return 0;
 }
 
+/**
+ * audit_alloc_kernel - allocate an audit_context for a kernel task
+ * @tsk: the kernel task
+ *
+ * Similar to the audit_alloc() function, but intended for kernel private
+ * threads.  Returns zero on success, negative values on failure.
+ */
+int audit_alloc_kernel(struct task_struct *tsk)
+{
+	/*
+	 * At the moment we are just going to call into audit_alloc() to
+	 * simplify the code, but there two things to keep in mind with this
+	 * approach:
+	 *
+	 * 1. Filtering internal kernel tasks is a bit laughable in almost all
+	 * cases, but there is at least one case where there is a benefit:
+	 * the '-a task,never' case allows the admin to effectively disable
+	 * task auditing at runtime.
+	 *
+	 * 2. The {set,clear}_task_syscall_work() ops likely have zero effect
+	 * on these internal kernel tasks, but they probably don't hurt either.
+	 */
+	return audit_alloc(tsk);
+}
+
 static inline void audit_free_context(struct audit_context *context)
 {
-	audit_free_module(context);
-	audit_free_names(context);
-	unroll_tree_refs(context, NULL, 0);
+	/* resetting is extra work, but it is likely just noise */
+	audit_reset_context(context);
 	free_tree_refs(context);
-	audit_free_aux(context);
 	kfree(context->filterkey);
-	kfree(context->sockaddr);
-	audit_proctitle_free(context);
 	kfree(context);
 }
 
@@ -1479,6 +1600,44 @@ out:
 	audit_log_end(ab);
 }
 
+/**
+ * audit_log_uring - generate a AUDIT_URINGOP record
+ * @ctx: the audit context
+ */
+static void audit_log_uring(struct audit_context *ctx)
+{
+	struct audit_buffer *ab;
+	const struct cred *cred;
+
+	ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_URINGOP);
+	if (!ab)
+		return;
+	cred = current_cred();
+	audit_log_format(ab, "uring_op=%d", ctx->uring_op);
+	if (ctx->return_valid != AUDITSC_INVALID)
+		audit_log_format(ab, " success=%s exit=%ld",
+				 (ctx->return_valid == AUDITSC_SUCCESS ?
+				  "yes" : "no"),
+				 ctx->return_code);
+	audit_log_format(ab,
+			 " items=%d"
+			 " ppid=%d pid=%d uid=%u gid=%u euid=%u suid=%u"
+			 " fsuid=%u egid=%u sgid=%u fsgid=%u",
+			 ctx->name_count,
+			 task_ppid_nr(current), task_tgid_nr(current),
+			 from_kuid(&init_user_ns, cred->uid),
+			 from_kgid(&init_user_ns, cred->gid),
+			 from_kuid(&init_user_ns, cred->euid),
+			 from_kuid(&init_user_ns, cred->suid),
+			 from_kuid(&init_user_ns, cred->fsuid),
+			 from_kgid(&init_user_ns, cred->egid),
+			 from_kgid(&init_user_ns, cred->sgid),
+			 from_kgid(&init_user_ns, cred->fsgid));
+	audit_log_task_context(ab);
+	audit_log_key(ab, ctx->filterkey);
+	audit_log_end(ab);
+}
+
 static void audit_log_exit(void)
 {
 	int i, call_panic = 0;
@@ -1489,29 +1648,38 @@ static void audit_log_exit(void)
 
 	context->personality = current->personality;
 
-	ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL);
-	if (!ab)
-		return;		/* audit_panic has been called */
-	audit_log_format(ab, "arch=%x syscall=%d",
-			 context->arch, context->major);
-	if (context->personality != PER_LINUX)
-		audit_log_format(ab, " per=%lx", context->personality);
-	if (context->return_valid != AUDITSC_INVALID)
-		audit_log_format(ab, " success=%s exit=%ld",
-				 (context->return_valid==AUDITSC_SUCCESS)?"yes":"no",
-				 context->return_code);
-
-	audit_log_format(ab,
-			 " a0=%lx a1=%lx a2=%lx a3=%lx items=%d",
-			 context->argv[0],
-			 context->argv[1],
-			 context->argv[2],
-			 context->argv[3],
-			 context->name_count);
-
-	audit_log_task_info(ab);
-	audit_log_key(ab, context->filterkey);
-	audit_log_end(ab);
+	switch (context->context) {
+	case AUDIT_CTX_SYSCALL:
+		ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL);
+		if (!ab)
+			return;
+		audit_log_format(ab, "arch=%x syscall=%d",
+				 context->arch, context->major);
+		if (context->personality != PER_LINUX)
+			audit_log_format(ab, " per=%lx", context->personality);
+		if (context->return_valid != AUDITSC_INVALID)
+			audit_log_format(ab, " success=%s exit=%ld",
+					 (context->return_valid == AUDITSC_SUCCESS ?
+					  "yes" : "no"),
+					 context->return_code);
+		audit_log_format(ab,
+				 " a0=%lx a1=%lx a2=%lx a3=%lx items=%d",
+				 context->argv[0],
+				 context->argv[1],
+				 context->argv[2],
+				 context->argv[3],
+				 context->name_count);
+		audit_log_task_info(ab);
+		audit_log_key(ab, context->filterkey);
+		audit_log_end(ab);
+		break;
+	case AUDIT_CTX_URING:
+		audit_log_uring(context);
+		break;
+	default:
+		BUG();
+		break;
+	}
 
 	for (aux = context->aux; aux; aux = aux->next) {
 
@@ -1602,21 +1770,22 @@ static void audit_log_exit(void)
 		audit_log_name(context, n, NULL, i++, &call_panic);
 	}
 
-	audit_log_proctitle();
+	if (context->context == AUDIT_CTX_SYSCALL)
+		audit_log_proctitle();
 
 	/* Send end of event record to help user space know we are finished */
 	ab = audit_log_start(context, GFP_KERNEL, AUDIT_EOE);
 	if (ab)
 		audit_log_end(ab);
 	if (call_panic)
-		audit_panic("error converting sid to string");
+		audit_panic("error in audit_log_exit()");
 }
 
 /**
  * __audit_free - free a per-task audit context
  * @tsk: task whose audit context block to free
  *
- * Called from copy_process and do_exit
+ * Called from copy_process, do_exit, and the io_uring code
  */
 void __audit_free(struct task_struct *tsk)
 {
@@ -1625,6 +1794,7 @@ void __audit_free(struct task_struct *tsk)
 	if (!context)
 		return;
 
+	/* this may generate CONFIG_CHANGE records */
 	if (!list_empty(&context->killed_trees))
 		audit_kill_trees(context);
 
@@ -1633,14 +1803,21 @@ void __audit_free(struct task_struct *tsk)
 	 * random task_struct that doesn't doesn't have any meaningful data we
 	 * need to log via audit_log_exit().
 	 */
-	if (tsk == current && !context->dummy && context->in_syscall) {
+	if (tsk == current && !context->dummy) {
 		context->return_valid = AUDITSC_INVALID;
 		context->return_code = 0;
-
-		audit_filter_syscall(tsk, context);
-		audit_filter_inodes(tsk, context);
-		if (context->current_state == AUDIT_STATE_RECORD)
-			audit_log_exit();
+		if (context->context == AUDIT_CTX_SYSCALL) {
+			audit_filter_syscall(tsk, context);
+			audit_filter_inodes(tsk, context);
+			if (context->current_state == AUDIT_STATE_RECORD)
+				audit_log_exit();
+		} else if (context->context == AUDIT_CTX_URING) {
+			/* TODO: verify this case is real and valid */
+			audit_filter_uring(tsk, context);
+			audit_filter_inodes(tsk, context);
+			if (context->current_state == AUDIT_STATE_RECORD)
+				audit_log_uring(context);
+		}
 	}
 
 	audit_set_context(tsk, NULL);
@@ -1648,6 +1825,131 @@ void __audit_free(struct task_struct *tsk)
 }
 
 /**
+ * audit_return_fixup - fixup the return codes in the audit_context
+ * @ctx: the audit_context
+ * @success: true/false value to indicate if the operation succeeded or not
+ * @code: operation return code
+ *
+ * We need to fixup the return code in the audit logs if the actual return
+ * codes are later going to be fixed by the arch specific signal handlers.
+ */
+static void audit_return_fixup(struct audit_context *ctx,
+			       int success, long code)
+{
+	/*
+	 * This is actually a test for:
+	 * (rc == ERESTARTSYS ) || (rc == ERESTARTNOINTR) ||
+	 * (rc == ERESTARTNOHAND) || (rc == ERESTART_RESTARTBLOCK)
+	 *
+	 * but is faster than a bunch of ||
+	 */
+	if (unlikely(code <= -ERESTARTSYS) &&
+	    (code >= -ERESTART_RESTARTBLOCK) &&
+	    (code != -ENOIOCTLCMD))
+		ctx->return_code = -EINTR;
+	else
+		ctx->return_code  = code;
+	ctx->return_valid = (success ? AUDITSC_SUCCESS : AUDITSC_FAILURE);
+}
+
+/**
+ * __audit_uring_entry - prepare the kernel task's audit context for io_uring
+ * @op: the io_uring opcode
+ *
+ * This is similar to audit_syscall_entry() but is intended for use by io_uring
+ * operations.  This function should only ever be called from
+ * audit_uring_entry() as we rely on the audit context checking present in that
+ * function.
+ */
+void __audit_uring_entry(u8 op)
+{
+	struct audit_context *ctx = audit_context();
+
+	if (ctx->state == AUDIT_STATE_DISABLED)
+		return;
+
+	/*
+	 * NOTE: It's possible that we can be called from the process' context
+	 *       before it returns to userspace, and before audit_syscall_exit()
+	 *       is called.  In this case there is not much to do, just record
+	 *       the io_uring details and return.
+	 */
+	ctx->uring_op = op;
+	if (ctx->context == AUDIT_CTX_SYSCALL)
+		return;
+
+	ctx->dummy = !audit_n_rules;
+	if (!ctx->dummy && ctx->state == AUDIT_STATE_BUILD)
+		ctx->prio = 0;
+
+	ctx->context = AUDIT_CTX_URING;
+	ctx->current_state = ctx->state;
+	ktime_get_coarse_real_ts64(&ctx->ctime);
+}
+
+/**
+ * __audit_uring_exit - wrap up the kernel task's audit context after io_uring
+ * @success: true/false value to indicate if the operation succeeded or not
+ * @code: operation return code
+ *
+ * This is similar to audit_syscall_exit() but is intended for use by io_uring
+ * operations.  This function should only ever be called from
+ * audit_uring_exit() as we rely on the audit context checking present in that
+ * function.
+ */
+void __audit_uring_exit(int success, long code)
+{
+	struct audit_context *ctx = audit_context();
+
+	if (ctx->context == AUDIT_CTX_SYSCALL) {
+		/*
+		 * NOTE: See the note in __audit_uring_entry() about the case
+		 *       where we may be called from process context before we
+		 *       return to userspace via audit_syscall_exit().  In this
+		 *       case we simply emit a URINGOP record and bail, the
+		 *       normal syscall exit handling will take care of
+		 *       everything else.
+		 *       It is also worth mentioning that when we are called,
+		 *       the current process creds may differ from the creds
+		 *       used during the normal syscall processing; keep that
+		 *       in mind if/when we move the record generation code.
+		 */
+
+		/*
+		 * We need to filter on the syscall info here to decide if we
+		 * should emit a URINGOP record.  I know it seems odd but this
+		 * solves the problem where users have a filter to block *all*
+		 * syscall records in the "exit" filter; we want to preserve
+		 * the behavior here.
+		 */
+		audit_filter_syscall(current, ctx);
+		if (ctx->current_state != AUDIT_STATE_RECORD)
+			audit_filter_uring(current, ctx);
+		audit_filter_inodes(current, ctx);
+		if (ctx->current_state != AUDIT_STATE_RECORD)
+			return;
+
+		audit_log_uring(ctx);
+		return;
+	}
+
+	/* this may generate CONFIG_CHANGE records */
+	if (!list_empty(&ctx->killed_trees))
+		audit_kill_trees(ctx);
+
+	/* run through both filters to ensure we set the filterkey properly */
+	audit_filter_uring(current, ctx);
+	audit_filter_inodes(current, ctx);
+	if (ctx->current_state != AUDIT_STATE_RECORD)
+		goto out;
+	audit_return_fixup(ctx, success, code);
+	audit_log_exit();
+
+out:
+	audit_reset_context(ctx);
+}
+
+/**
  * __audit_syscall_entry - fill in an audit record at syscall entry
  * @major: major syscall type (function)
  * @a1: additional syscall register 1
@@ -1672,7 +1974,12 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
 	if (!audit_enabled || !context)
 		return;
 
-	BUG_ON(context->in_syscall || context->name_count);
+	WARN_ON(context->context != AUDIT_CTX_UNUSED);
+	WARN_ON(context->name_count);
+	if (context->context != AUDIT_CTX_UNUSED || context->name_count) {
+		audit_panic("unrecoverable error in audit_syscall_entry()");
+		return;
+	}
 
 	state = context->state;
 	if (state == AUDIT_STATE_DISABLED)
@@ -1691,10 +1998,8 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
 	context->argv[1]    = a2;
 	context->argv[2]    = a3;
 	context->argv[3]    = a4;
-	context->serial     = 0;
-	context->in_syscall = 1;
+	context->context = AUDIT_CTX_SYSCALL;
 	context->current_state  = state;
-	context->ppid       = 0;
 	ktime_get_coarse_real_ts64(&context->ctime);
 }
 
@@ -1711,63 +2016,27 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
  */
 void __audit_syscall_exit(int success, long return_code)
 {
-	struct audit_context *context;
+	struct audit_context *context = audit_context();
 
-	context = audit_context();
-	if (!context)
-		return;
+	if (!context || context->dummy ||
+	    context->context != AUDIT_CTX_SYSCALL)
+		goto out;
 
+	/* this may generate CONFIG_CHANGE records */
 	if (!list_empty(&context->killed_trees))
 		audit_kill_trees(context);
 
-	if (!context->dummy && context->in_syscall) {
-		if (success)
-			context->return_valid = AUDITSC_SUCCESS;
-		else
-			context->return_valid = AUDITSC_FAILURE;
+	/* run through both filters to ensure we set the filterkey properly */
+	audit_filter_syscall(current, context);
+	audit_filter_inodes(current, context);
+	if (context->current_state < AUDIT_STATE_RECORD)
+		goto out;
 
-		/*
-		 * we need to fix up the return code in the audit logs if the
-		 * actual return codes are later going to be fixed up by the
-		 * arch specific signal handlers
-		 *
-		 * This is actually a test for:
-		 * (rc == ERESTARTSYS ) || (rc == ERESTARTNOINTR) ||
-		 * (rc == ERESTARTNOHAND) || (rc == ERESTART_RESTARTBLOCK)
-		 *
-		 * but is faster than a bunch of ||
-		 */
-		if (unlikely(return_code <= -ERESTARTSYS) &&
-		    (return_code >= -ERESTART_RESTARTBLOCK) &&
-		    (return_code != -ENOIOCTLCMD))
-			context->return_code = -EINTR;
-		else
-			context->return_code  = return_code;
-
-		audit_filter_syscall(current, context);
-		audit_filter_inodes(current, context);
-		if (context->current_state == AUDIT_STATE_RECORD)
-			audit_log_exit();
-	}
-
-	context->in_syscall = 0;
-	context->prio = context->state == AUDIT_STATE_RECORD ? ~0ULL : 0;
-
-	audit_free_module(context);
-	audit_free_names(context);
-	unroll_tree_refs(context, NULL, 0);
-	audit_free_aux(context);
-	context->aux = NULL;
-	context->aux_pids = NULL;
-	context->target_pid = 0;
-	context->target_sid = 0;
-	context->sockaddr_len = 0;
-	context->type = 0;
-	context->fds[0] = -1;
-	if (context->state != AUDIT_STATE_RECORD) {
-		kfree(context->filterkey);
-		context->filterkey = NULL;
-	}
+	audit_return_fixup(context, success, return_code);
+	audit_log_exit();
+
+out:
+	audit_reset_context(context);
 }
 
 static inline void handle_one(const struct inode *inode)
@@ -1919,7 +2188,7 @@ void __audit_getname(struct filename *name)
 	struct audit_context *context = audit_context();
 	struct audit_names *n;
 
-	if (!context->in_syscall)
+	if (context->context == AUDIT_CTX_UNUSED)
 		return;
 
 	n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN);
@@ -1991,7 +2260,7 @@ void __audit_inode(struct filename *name, const struct dentry *dentry,
 	struct list_head *list = &audit_filter_list[AUDIT_FILTER_FS];
 	int i;
 
-	if (!context->in_syscall)
+	if (context->context == AUDIT_CTX_UNUSED)
 		return;
 
 	rcu_read_lock();
@@ -2109,7 +2378,7 @@ void __audit_inode_child(struct inode *parent,
 	struct list_head *list = &audit_filter_list[AUDIT_FILTER_FS];
 	int i;
 
-	if (!context->in_syscall)
+	if (context->context == AUDIT_CTX_UNUSED)
 		return;
 
 	rcu_read_lock();
@@ -2208,7 +2477,7 @@ EXPORT_SYMBOL_GPL(__audit_inode_child);
 int auditsc_get_stamp(struct audit_context *ctx,
 		       struct timespec64 *t, unsigned int *serial)
 {
-	if (!ctx->in_syscall)
+	if (ctx->context == AUDIT_CTX_UNUSED)
 		return 0;
 	if (!ctx->serial)
 		ctx->serial = audit_serial();
@@ -2706,8 +2975,7 @@ void audit_seccomp_actions_logged(const char *names, const char *old_names,
 struct list_head *audit_killed_trees(void)
 {
 	struct audit_context *ctx = audit_context();
-
-	if (likely(!ctx || !ctx->in_syscall))
+	if (likely(!ctx || ctx->context == AUDIT_CTX_UNUSED))
 		return NULL;
 	return &ctx->killed_trees;
 }