audit by executable name

This is to be used to audit by executable path rules, but audit watches should be able to share this code eventually.

At the moment the audit watch code is a lot more complex. That code only creates one fsnotify watch per parent directory. That 'audit_parent' in turn has a list of 'audit_watches' which contain the name, ino, dev of the specific object we care about. This just creates one fsnotify watch per object we care about. So if you watch 100 inodes in /etc this code will create 100 fsnotify watches on /etc. The audit_watch code will instead create 1 fsnotify watch on /etc (the audit_parent) and then 100 individual watches chained from that fsnotify mark.

We should be able to convert the audit_watch code to do one fsnotify mark per watch and simplify things/remove a whole lot of code. After that conversion we should be able to convert the audit_fsnotify code to support that hierarchy if the optimization is necessary.

Move the access to the entry for audit_match_signal() to the beginning of the audit_del_rule() function in case the entry found is the same one passed in. This will enable it to be used by audit_autoremove_mark_rule(), kill_rules() and audit_remove_parent_watches().

This is a heavily modified and merged version of two patches originally submitted by Eric Paris.

Cc Peter Moody <[email protected]>

Cc Eric Paris <[email protected]>

Signed-off-by Richard Guy Briggs <[email protected]>

---
 kernel/Makefile         |    2 +-
 kernel/audit.h          |   14 +++
 kernel/audit_fsnotify.c |  215 +++++++++++++++++++++++++++++++++++++++++++
 kernel/auditfilter.c    |    2 +-
 4 files changed, 231 insertions(+), 2 deletions(-)
 create mode 100644 kernel/audit_fsnotify.c

kernel/Makefile +1 -1

index 60c302c..58b5b52 100644
@@ -64,7 +64,7 @@ obj-$(CONFIG_SMP) += stop_machine.o
 obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o
 obj-$(CONFIG_AUDIT) += audit.o auditfilter.o
 obj-$(CONFIG_AUDITSYSCALL) += auditsc.o
-obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o
+obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o audit_fsnotify.o
 obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
 obj-$(CONFIG_GCOV_KERNEL) += gcov/
 obj-$(CONFIG_KPROBES) += kprobes.o

kernel/audit.h +2 -0

index d641f9b..46d10dd 100644
@@ -50,6 +50,7 @@ enum audit_state {
 
 /* Rule lists */
 struct audit_watch;
+struct audit_fsnotify_mark;
 struct audit_tree;
 struct audit_chunk;
 

@@ -252,6 +253,7 @@ struct audit_net {
 extern int selinux_audit_rule_update(void);
 
 extern struct mutex audit_filter_mutex;
+extern int audit_del_rule(struct audit_entry *);
 extern void audit_free_rule_rcu(struct rcu_head *);
 extern struct list_head audit_filter_list[];
 

@@ -269,6 +271,13 @@ extern int audit_add_watch(struct audit_krule *krule,

struct list_head **list); extern void audit_remove_watch_rule(struct audit_krule *krule);
extern char *audit_watch_path(struct audit_watch *watch); extern int audit_watch_compare(struct audit_watch *watch, unsigned long
ino, dev_t dev); +
+extern struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule, char *pathname, int len); +extern char *audit_mark_path(struct audit_fsnotify_mark *mark);

kernel/audit.h +3 -0

+extern void audit_remove_mark(struct audit_fsnotify_mark *audit_mark);
+extern void audit_remove_mark_rule(struct audit_krule *krule);
+extern int audit_mark_compare(struct audit_fsnotify_mark *mark, unsigned

long ino, dev_t dev); +
#else
#define audit_put_watch(w) {}
#define audit_get_watch(w) {}

kernel/audit.h +5 -0

@@ -278,6 +287,11 @@ extern int audit_watch_compare(struct audit_watch
 *watch, unsigned long ino, dev #define audit_watch_path(w) ""
 #define audit_watch_compare(w, i, d) 0
 
+#define audit_alloc_mark(k, p, l) (ERR_PTR(-EINVAL))
+#define audit_mark_path(m) ""
+#define audit_remove_mark(m)
+#define audit_remove_mark_rule(k)
+#define audit_mark_compare(m, i, d) 0
 #endif /* CONFIG_AUDIT_WATCH */
 
 #ifdef CONFIG_AUDIT_TREE

kernel/audit_fsnotify.c new file +47 -0

new file mode 100644
index 0000000..654c6c7
@@ -0,0 +1,215 @@
+/* audit_fsnotify.c -- tracking inodes
+ *
+ * Copyright 2003-2009,2014-2015 Red Hat, Inc.
+ * Copyright 2005 Hewlett-Packard Development Company, L.P.
+ * Copyright 2005 IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/audit.h>
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/fs.h>
+#include <linux/fsnotify_backend.h>
+#include <linux/namei.h>
+#include <linux/netlink.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include "audit.h"
+
+/*
+ * this mark lives on the parent directory of the inode in question.
+ * but dev, ino, and path are about the child
+ */
+struct audit_fsnotify_mark {
+	dev_t dev;		/* associated superblock device */
+	unsigned long ino;	/* associated inode number */
+	char *path;		/* insertion path */
+	struct fsnotify_mark mark; /* fsnotify mark on the inode */
+	struct audit_krule *rule;
+};
+
+/* fsnotify handle. */
+static struct fsnotify_group *audit_fsnotify_group;
+
+/* fsnotify events we care about. */
+#define AUDIT_FS_EVENTS (FS_MOVE | FS_CREATE | FS_DELETE | FS_DELETE_SELF

|\ + FS_MOVE_SELF | FS_EVENT_ON_CHILD)

kernel/audit_fsnotify.c new file +2 -0

+
+static void audit_fsnotify_mark_free(struct audit_fsnotify_mark

*audit_mark) +{

kernel/audit_fsnotify.c new file +18 -0

+	kfree(audit_mark->path);
+	kfree(audit_mark);
+}
+
+static void audit_fsnotify_free_mark(struct fsnotify_mark *mark)
+{
+	struct audit_fsnotify_mark *audit_mark;
+
+	audit_mark = container_of(mark, struct audit_fsnotify_mark, mark);
+	audit_fsnotify_mark_free(audit_mark);
+}
+
+char *audit_mark_path(struct audit_fsnotify_mark *mark)
+{
+	return mark->path;
+}
+
+int audit_mark_compare(struct audit_fsnotify_mark *mark, unsigned long ino,

dev_t dev) +{

kernel/audit_fsnotify.c new file +13 -0

+	if (mark->ino == AUDIT_INO_UNSET)
+		return 0;
+	return (mark->ino == ino) && (mark->dev == dev);
+}
+
+static void audit_update_mark(struct audit_fsnotify_mark *audit_mark,
+			     struct inode *inode)
+{
+	audit_mark->dev = inode ? inode->i_sb->s_dev : AUDIT_DEV_UNSET;
+	audit_mark->ino = inode ? inode->i_ino : AUDIT_INO_UNSET;
+}
+
+struct audit_fsnotify_mark *audit_alloc_mark(struct audit_krule *krule,

char *pathname, int len) +{

kernel/audit_fsnotify.c new file +28 -0

+	struct audit_fsnotify_mark *audit_mark;
+	struct path path;
+	struct dentry *dentry;
+	struct inode *inode;
+	int ret;
+
+	if (pathname[0] != '/' || pathname[len-1] == '/')
+		return ERR_PTR(-EINVAL);
+
+	dentry = kern_path_locked(pathname, &path);
+	if (IS_ERR(dentry))
+		return (void *)dentry; /* returning an error */
+	inode = path.dentry->d_inode;
+	mutex_unlock(&inode->i_mutex);
+
+	audit_mark = kzalloc(sizeof(*audit_mark), GFP_KERNEL);
+	if (unlikely(!audit_mark)) {
+		audit_mark = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	fsnotify_init_mark(&audit_mark->mark, audit_fsnotify_free_mark);
+	audit_mark->mark.mask = AUDIT_FS_EVENTS;
+	audit_mark->path = pathname;
+	audit_update_mark(audit_mark, dentry->d_inode);
+	audit_mark->rule = krule;
+
+	ret = fsnotify_add_mark(&audit_mark->mark, audit_fsnotify_group, inode,

NULL, true); + if (ret < 0) {

kernel/audit_fsnotify.c new file +10 -0

+		audit_fsnotify_mark_free(audit_mark);
+		audit_mark = ERR_PTR(ret);
+	}
+out:
+	dput(dentry);
+	path_put(&path);
+	return audit_mark;
+}
+
+static void audit_mark_log_rule_change(struct audit_fsnotify_mark

*audit_mark, char *op) +{

kernel/audit_fsnotify.c new file +32 -0

+	struct audit_buffer *ab;
+	struct audit_krule *rule = audit_mark->rule;
+	if (!audit_enabled)
+		return;
+	ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
+	if (unlikely(!ab))
+		return;
+	audit_log_format(ab, "auid=%u ses=%u op=",
+			 from_kuid(&init_user_ns, audit_get_loginuid(current)),
+			 audit_get_sessionid(current));
+	audit_log_string(ab, op);
+	audit_log_format(ab, " path=");
+	audit_log_untrustedstring(ab, audit_mark->path);
+	audit_log_key(ab, rule->filterkey);
+	audit_log_format(ab, " list=%d res=1", rule->listnr);
+	audit_log_end(ab);
+}
+
+void audit_remove_mark(struct audit_fsnotify_mark *audit_mark)
+{
+	fsnotify_destroy_mark(&audit_mark->mark, audit_fsnotify_group);
+	fsnotify_put_mark(&audit_mark->mark);
+}
+
+void audit_remove_mark_rule(struct audit_krule *krule)
+{
+	struct audit_fsnotify_mark *mark = krule->exe;
+
+	audit_remove_mark(mark);
+}
+
+static void audit_autoremove_mark_rule(struct audit_fsnotify_mark

*audit_mark) +{

kernel/audit_fsnotify.c new file +58 -0

+	struct audit_krule *rule = audit_mark->rule;
+	struct audit_entry *entry = container_of(rule, struct audit_entry, rule);
+
+	audit_mark_log_rule_change(audit_mark, "autoremove_rule");
+	audit_del_rule(entry);
+}
+
+/* Update mark data in audit rules based on fsnotify events. */
+static int audit_mark_handle_event(struct fsnotify_group *group,
+				    struct inode *to_tell,
+				    struct fsnotify_mark *inode_mark,
+				    struct fsnotify_mark *vfsmount_mark,
+				    u32 mask, void *data, int data_type,
+				    const unsigned char *dname, u32 cookie)
+{
+	struct audit_fsnotify_mark *audit_mark;
+	struct inode *inode = NULL;
+
+	audit_mark = container_of(inode_mark, struct audit_fsnotify_mark, mark);
+
+	BUG_ON(group != audit_fsnotify_group);
+
+	switch (data_type) {
+	case (FSNOTIFY_EVENT_PATH):
+		inode = ((struct path *)data)->dentry->d_inode;
+		break;
+	case (FSNOTIFY_EVENT_INODE):
+		inode = (struct inode *)data;
+		break;
+	default:
+		BUG();
+		return 0;
+	};
+
+	if (mask & (FS_CREATE|FS_MOVED_TO|FS_DELETE|FS_MOVED_FROM)) {
+		if (audit_compare_dname_path(dname, audit_mark->path, AUDIT_NAME_FULL))
+			return 0;
+		audit_update_mark(audit_mark, inode);
+	} else if (mask & (FS_DELETE_SELF|FS_UNMOUNT|FS_MOVE_SELF))
+		audit_autoremove_mark_rule(audit_mark);
+
+	return 0;
+}
+
+static const struct fsnotify_ops audit_mark_fsnotify_ops = {
+	.handle_event =	audit_mark_handle_event,
+};
+
+static int __init audit_fsnotify_init(void)
+{
+	audit_fsnotify_group = fsnotify_alloc_group(&audit_mark_fsnotify_ops);
+	if (IS_ERR(audit_fsnotify_group)) {
+		audit_fsnotify_group = NULL;
+		audit_panic("cannot create audit fsnotify group");
+	}
+	return 0;
+}
+device_initcall(audit_fsnotify_init);

kernel/auditfilter.c +1 -1

index 018719a..3d99196 100644
@@ -935,7 +935,7 @@ static inline int audit_add_rule(struct audit_entry
 *entry) }
 
 /* Remove an existing rule from filterlist. */
-static inline int audit_del_rule(struct audit_entry *entry)
+int audit_del_rule(struct audit_entry *entry)
 {
 	struct audit_entry  *e;
 	struct audit_tree *tree = entry->rule.tree;

This adds the ability audit the actions of a not-yet-running process.

This patch implements the ability to filter on the executable path. Instead of just hard coding the ino and dev of the executable we care about at the moment the rule is inserted into the kernel, use the new audit_fsnotify infrastructure to manage this dynamically. This means that if the filename does not yet exist but the containing directory does, or if the inode in question is unlinked and creat'd (aka updated) the rule will just continue to work. If the containing directory is moved or deleted or the filesystem is unmounted, the rule is deleted automatically. A future enhancement would be to have the rule survive across directory disruptions.

This is a heavily modified version of a patch originally submitted by Eric Paris with some ideas from Peter Moody.

Cc Peter Moody <[email protected]>

Cc Eric Paris <[email protected]>

Signed-off-by Richard Guy Briggs <[email protected]>

---
 include/linux/audit.h      |    1 +
 include/uapi/linux/audit.h |    5 +++-
 kernel/audit.h             |    4 +++
 kernel/audit_tree.c        |    2 +
 kernel/audit_watch.c       |   31 +++++++++++++++++++++++++
 kernel/auditfilter.c       |   53 ++++++++++++++++++++++++++++++++++++++++-
 kernel/auditsc.c           |    3 ++
 7 files changed, 97 insertions(+), 2 deletions(-)

include/linux/audit.h +1 -0

index c2e7e3a..aee456f 100644
@@ -59,6 +59,7 @@ struct audit_krule {
 	struct audit_field	*inode_f; /* quick access to an inode field */
 	struct audit_watch	*watch;	/* associated watch */
 	struct audit_tree	*tree;	/* associated watched tree */
+	struct audit_fsnotify_mark	*exe;
 	struct list_head	rlist;	/* entry in audit_{watch,tree}.rules list */
 	struct list_head	list;	/* for AUDIT_LIST* purposes only */
 	u64			prio;

include/uapi/linux/audit.h +4 -1

index 971df22..e2ca600 100644
@@ -266,6 +266,7 @@
 #define AUDIT_OBJ_UID	109
 #define AUDIT_OBJ_GID	110
 #define AUDIT_FIELD_COMPARE	111
+#define AUDIT_EXE	112
 
 #define AUDIT_ARG0      200
 #define AUDIT_ARG1      (AUDIT_ARG0+1)

@@ -324,8 +325,10 @@ enum {
 
 #define AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT	0x00000001
 #define AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME	0x00000002
+#define AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH	0x00000004
 #define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \
-				  AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME)
+				  AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME | \
+				  AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH )
 
 /* deprecated: AUDIT_VERSION_* */
 #define AUDIT_VERSION_LATEST 		AUDIT_FEATURE_BITMAP_ALL

kernel/audit.h +0 -0

index 46d10dd..dadf86a 100644
@@ -277,6 +277,8 @@ extern char *audit_mark_path(struct audit_fsnotify_mark
 *mark); extern void audit_remove_mark(struct audit_fsnotify_mark
 *audit_mark); extern void audit_remove_mark_rule(struct audit_krule
 *krule);
 extern int audit_mark_compare(struct audit_fsnotify_mark *mark, unsigned
 long ino, dev_t dev); +extern int audit_dupe_exe(struct audit_krule *new,

struct audit_krule *old); +extern int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark);

#else
#define audit_put_watch(w) {}

kernel/audit.h +2 -0

@@ -292,6 +294,8 @@ extern int audit_mark_compare(struct audit_fsnotify_mark
 *mark, unsigned long in #define audit_remove_mark(m)
 #define audit_remove_mark_rule(k)
 #define audit_mark_compare(m, i, d) 0
+#define audit_exe_compare(t, m) (-EINVAL)
+#define audit_dupe_exe(n, o) (-EINVAL)
 #endif /* CONFIG_AUDIT_WATCH */
 
 #ifdef CONFIG_AUDIT_TREE

kernel/audit_tree.c +2 -0

index b0f9877..94ecdab 100644
@@ -479,6 +479,8 @@ static void kill_rules(struct audit_tree *tree)
 		if (rule->tree) {
 			/* not a half-baked one */
 			audit_tree_log_remove_rule(rule);
+			if (entry->rule.exe)
+				audit_remove_mark(entry->rule.exe);
 			rule->tree = NULL;
 			list_del_rcu(&entry->list);
 			list_del(&entry->rule.list);

kernel/audit_watch.c +4 -0

index c668bfc..1255dbf 100644
@@ -312,6 +312,8 @@ static void audit_update_watch(struct audit_parent
 *parent, list_replace(&oentry->rule.list,
 					     &nentry->rule.list);
 			}
+			if (oentry->rule.exe)
+				audit_remove_mark(oentry->rule.exe);
 
 			audit_watch_log_rule_change(r, owatch, "updated_rules");
 

@@ -342,6 +344,8 @@ static void audit_remove_parent_watches(struct
 audit_parent *parent) list_for_each_entry_safe(r, nextr, &w->rules, rlist)
 {
 			e = container_of(r, struct audit_entry, rule);
 			audit_watch_log_rule_change(r, w, "remove_rule");
+			if (e->rule.exe)
+				audit_remove_mark(e->rule.exe);
 			list_del(&r->rlist);
 			list_del(&r->list);

kernel/audit_watch.c +21 -0

 			list_del_rcu(&e->list);

@@ -514,3 +518,30 @@ static int __init audit_watch_init(void)
 	return 0;
 }
 device_initcall(audit_watch_init);
+
+int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old)
+{
+	struct audit_fsnotify_mark *audit_mark;
+	char *pathname;
+
+	pathname = kstrdup(audit_mark_path(old->exe), GFP_KERNEL);
+	if (!pathname)
+		return -ENOMEM;
+
+	audit_mark = audit_alloc_mark(new, pathname, strlen(pathname));
+	if (IS_ERR(audit_mark)) {
+		kfree(pathname);
+		return PTR_ERR(audit_mark);
+	}
+	new->exe = audit_mark;
+
+	return 0;
+}
+
+int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark

*mark) +{

kernel/audit_watch.c +5 -0

+	unsigned long ino = tsk->mm->exe_file->f_inode->i_ino;
+	dev_t dev = tsk->mm->exe_file->f_inode->i_sb->s_dev;
+
+	return audit_mark_compare(mark, ino, dev);
+}

kernel/auditfilter.c +6 -0

index 3d99196..c662638 100644
@@ -405,6 +405,12 @@ static int audit_field_valid(struct audit_entry *entry,
 struct audit_field *f) if (f->val > AUDIT_MAX_FIELD_COMPARE)
 			return -EINVAL;
 		break;
+	case AUDIT_EXE:
+		if (f->op != Audit_equal)
+			return -EINVAL;
+		if (entry->rule.listnr != AUDIT_FILTER_EXIT)
+			return -EINVAL;
+		break;
 	};
 	return 0;
 }

@@ -419,6 +425,7 @@ static struct audit_entry *audit_data_to_entry(struct

audit_rule_data *data, size_t remain = datasz - sizeof(struct audit_rule_data);

kernel/auditfilter.c +21 -0

 	int i;
 	char *str;
+	struct audit_fsnotify_mark *audit_mark;
 
 	entry = audit_to_entry_common(data);
 	if (IS_ERR(entry))

@@ -539,6 +546,24 @@ static struct audit_entry *audit_data_to_entry(struct
 audit_rule_data *data, entry->rule.buflen += f->val;
 			entry->rule.filterkey = str;
 			break;
+		case AUDIT_EXE:
+			if (entry->rule.exe || f->val > PATH_MAX)
+				goto exit_free;
+			str = audit_unpack_string(&bufp, &remain, f->val);
+			if (IS_ERR(str)) {
+				err = PTR_ERR(str);
+				goto exit_free;
+			}
+			entry->rule.buflen += f->val;
+
+			audit_mark = audit_alloc_mark(&entry->rule, str, f->val);
+			if (IS_ERR(audit_mark)) {
+				kfree(str);
+				err = PTR_ERR(audit_mark);
+				goto exit_free;
+			}
+			entry->rule.exe = audit_mark;
+			break;
 		}
 	}
 

@@ -551,6 +576,8 @@ exit_nofree:
 exit_free:
 	if (entry->rule.tree)
 		audit_put_tree(entry->rule.tree); /* that's the temporary one */
+	if (entry->rule.exe)
+		audit_remove_mark(entry->rule.exe); /* that's the template one */
 	audit_free_rule(entry);
 	return ERR_PTR(err);
 }

@@ -615,6 +642,10 @@ static struct audit_rule_data
 *audit_krule_to_data(struct audit_krule *krule) data->buflen +=

data->values[i] =

kernel/auditfilter.c +25 -1

 				audit_pack_string(&bufp, krule->filterkey);
 			break;
+		case AUDIT_EXE:
+			data->buflen += data->values[i] =
+				audit_pack_string(&bufp, audit_mark_path(krule->exe));
+			break;
 		case AUDIT_LOGINUID_SET:
 			if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) {
 				data->fields[i] = AUDIT_LOGINUID;

@@ -678,6 +709,12 @@ static int audit_compare_rule(struct audit_krule *a,
 struct audit_krule *b) if (strcmp(a->filterkey, b->filterkey))
 				return 1;
 			break;
+		case AUDIT_EXE:
+			/* both paths exist based on above type compare */
+			if (strcmp(audit_mark_path(a->exe),
+				   audit_mark_path(b->exe)))
+				return 1;
+			break;
 		case AUDIT_UID:
 		case AUDIT_EUID:
 		case AUDIT_SUID:

@@ -799,8 +836,14 @@ struct audit_entry *audit_dupe_rule(struct audit_krule
 *old) err = -ENOMEM;
 			else
 				new->filterkey = fk;
+			break;
+		case AUDIT_EXE:
+			err = audit_dupe_exe(new, old);
+			break;
 		}
 		if (err) {
+			if (new->exe)
+				audit_remove_mark(new->exe);
 			audit_free_rule(entry);
 			return ERR_PTR(err);
 		}

@@ -963,6 +1006,9 @@ int audit_del_rule(struct audit_entry *entry)
 	if (e->rule.tree)
 		audit_remove_tree_rule(&e->rule);
 
+	if (e->rule.exe)
+		audit_remove_mark_rule(&e->rule);
+
 #ifdef CONFIG_AUDITSYSCALL
 	if (!dont_count)
 		audit_n_rules--;

@@ -1067,8 +1113,11 @@ int audit_rule_change(int type, __u32 portid, int
 seq, void *data, WARN_ON(1);
 	}
 
-	if (err || type == AUDIT_DEL_RULE)
+	if (err || type == AUDIT_DEL_RULE) {
+		if (entry->rule.exe)
+			audit_remove_mark(entry->rule.exe);
 		audit_free_rule(entry);
+	}
 
 	return err;
 }

@@ -1360,6 +1409,8 @@ static int update_lsm_rule(struct audit_krule *r)
 		return 0;
 
 	nentry = audit_dupe_rule(r);
+	if (entry->rule.exe)
+		audit_remove_mark(entry->rule.exe);
 	if (IS_ERR(nentry)) {
 		/* save the first error encountered for the
 		 * return value */

kernel/auditsc.c +3 -0

index 701ea5c..e9bac2b 100644
@@ -466,6 +466,9 @@ static int audit_filter_rules(struct task_struct *tsk,
 				result = audit_comparator(ctx->ppid, f->op, f->val);
 			}
 			break;
+		case AUDIT_EXE:
+			result = audit_exe_compare(tsk, rule->exe);
+			break;
 		case AUDIT_UID:
 			result = audit_uid_comparator(cred->uid, f->op, f->uid);
 			break;

Quoted 18 lines · Richard Guy Briggs

This adds the ability audit the actions of a not-yet-running process.

This patch implements the ability to filter on the executable path. Instead of just hard coding the ino and dev of the executable we care about at the moment the rule is inserted into the kernel, use the new audit_fsnotify infrastructure to manage this dynamically. This means that if the filename does not yet exist but the containing directory does, or if the inode in question is unlinked and creat'd (aka updated) the rule will just continue to work. If the containing directory is moved or deleted or the filesystem is unmounted, the rule is deleted automatically. A future enhancement would be to have the rule survive across directory disruptions.

This is a heavily modified version of a patch originally submitted by Eric Paris with some ideas from Peter Moody.

Cc Peter Moody <[email protected]>

Cc Eric Paris <[email protected]>

Signed-off-by Richard Guy Briggs <[email protected]>

Quoted 9 lines

---
 include/linux/audit.h      |    1 +
 include/uapi/linux/audit.h |    5 +++-
 kernel/audit.h             |    4 +++
 kernel/audit_tree.c        |    2 +
 kernel/audit_watch.c       |   31 +++++++++++++++++++++++++
 kernel/auditfilter.c       |   53 ++++++++++++++++++++++++++++++++++++++++-
 kernel/auditsc.c           |    3 ++
 7 files changed, 97 insertions(+), 2 deletions(-)

Merged, although some more minor whitespace tweaks were necessary for checkpatch. On a related note, if you're not running ./scripts/checlpatch.pl on your patches before sending them out, I would recommend it. It isn't perfect, but it can catch some silly things that we all do from time to time.

Also, one last thing. It is pretty late in the -rcX cycle to merge these two patches, but considering that we've been talking about these for a while, I'm reasonably okay merging them. In the future, if it isn't in audit#next by the time -rc5 is released, it isn't going to make the merge window.

Quoted 265 lines

include/linux/audit.h +1 -0

index c2e7e3a..aee456f 100644
@@ -59,6 +59,7 @@ struct audit_krule {
 	struct audit_field	*inode_f; /* quick access to an inode field */
 	struct audit_watch	*watch;	/* associated watch */
 	struct audit_tree	*tree;	/* associated watched tree */
+	struct audit_fsnotify_mark	*exe;
 	struct list_head	rlist;	/* entry in audit_{watch,tree}.rules list */
 	struct list_head	list;	/* for AUDIT_LIST* purposes only */
 	u64			prio;

include/uapi/linux/audit.h +4 -1

index 971df22..e2ca600 100644
@@ -266,6 +266,7 @@
 #define AUDIT_OBJ_UID	109
 #define AUDIT_OBJ_GID	110
 #define AUDIT_FIELD_COMPARE	111
+#define AUDIT_EXE	112
 
 #define AUDIT_ARG0      200
 #define AUDIT_ARG1      (AUDIT_ARG0+1)

@@ -324,8 +325,10 @@ enum {
 
 #define AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT	0x00000001
 #define AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME	0x00000002
+#define AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH	0x00000004
 #define AUDIT_FEATURE_BITMAP_ALL (AUDIT_FEATURE_BITMAP_BACKLOG_LIMIT | \
-				  AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME)
+				  AUDIT_FEATURE_BITMAP_BACKLOG_WAIT_TIME | \
+				  AUDIT_FEATURE_BITMAP_EXECUTABLE_PATH )
 
 /* deprecated: AUDIT_VERSION_* */
 #define AUDIT_VERSION_LATEST 		AUDIT_FEATURE_BITMAP_ALL

kernel/audit.h +0 -0

index 46d10dd..dadf86a 100644
@@ -277,6 +277,8 @@ extern char *audit_mark_path(struct audit_fsnotify_mark
 *mark); extern void audit_remove_mark(struct audit_fsnotify_mark
 *audit_mark); extern void audit_remove_mark_rule(struct audit_krule
 *krule);
 extern int audit_mark_compare(struct audit_fsnotify_mark *mark, unsigned
 long ino, dev_t dev); +extern int audit_dupe_exe(struct audit_krule *new,

struct audit_krule *old); +extern int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark);

#else
#define audit_put_watch(w) {}

kernel/audit.h +2 -0

@@ -292,6 +294,8 @@ extern int audit_mark_compare(struct audit_fsnotify_mark
 *mark, unsigned long in #define audit_remove_mark(m)
 #define audit_remove_mark_rule(k)
 #define audit_mark_compare(m, i, d) 0
+#define audit_exe_compare(t, m) (-EINVAL)
+#define audit_dupe_exe(n, o) (-EINVAL)
 #endif /* CONFIG_AUDIT_WATCH */
 
 #ifdef CONFIG_AUDIT_TREE

kernel/audit_tree.c +2 -0

index b0f9877..94ecdab 100644
@@ -479,6 +479,8 @@ static void kill_rules(struct audit_tree *tree)
 		if (rule->tree) {
 			/* not a half-baked one */
 			audit_tree_log_remove_rule(rule);
+			if (entry->rule.exe)
+				audit_remove_mark(entry->rule.exe);
 			rule->tree = NULL;
 			list_del_rcu(&entry->list);
 			list_del(&entry->rule.list);

kernel/audit_watch.c +4 -0

index c668bfc..1255dbf 100644
@@ -312,6 +312,8 @@ static void audit_update_watch(struct audit_parent
 *parent, list_replace(&oentry->rule.list,
 					     &nentry->rule.list);
 			}
+			if (oentry->rule.exe)
+				audit_remove_mark(oentry->rule.exe);
 
 			audit_watch_log_rule_change(r, owatch, "updated_rules");
 

@@ -342,6 +344,8 @@ static void audit_remove_parent_watches(struct
 audit_parent *parent) list_for_each_entry_safe(r, nextr, &w->rules, rlist)
 {
 			e = container_of(r, struct audit_entry, rule);
 			audit_watch_log_rule_change(r, w, "remove_rule");
+			if (e->rule.exe)
+				audit_remove_mark(e->rule.exe);
 			list_del(&r->rlist);
 			list_del(&r->list);

kernel/audit_watch.c +21 -0

 			list_del_rcu(&e->list);

@@ -514,3 +518,30 @@ static int __init audit_watch_init(void)
 	return 0;
 }
 device_initcall(audit_watch_init);
+
+int audit_dupe_exe(struct audit_krule *new, struct audit_krule *old)
+{
+	struct audit_fsnotify_mark *audit_mark;
+	char *pathname;
+
+	pathname = kstrdup(audit_mark_path(old->exe), GFP_KERNEL);
+	if (!pathname)
+		return -ENOMEM;
+
+	audit_mark = audit_alloc_mark(new, pathname, strlen(pathname));
+	if (IS_ERR(audit_mark)) {
+		kfree(pathname);
+		return PTR_ERR(audit_mark);
+	}
+	new->exe = audit_mark;
+
+	return 0;
+}
+
+int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark

*mark) +{

kernel/audit_watch.c +5 -0

+	unsigned long ino = tsk->mm->exe_file->f_inode->i_ino;
+	dev_t dev = tsk->mm->exe_file->f_inode->i_sb->s_dev;
+
+	return audit_mark_compare(mark, ino, dev);
+}

kernel/auditfilter.c +6 -0

index 3d99196..c662638 100644
@@ -405,6 +405,12 @@ static int audit_field_valid(struct audit_entry *entry,
 struct audit_field *f) if (f->val > AUDIT_MAX_FIELD_COMPARE)
 			return -EINVAL;
 		break;
+	case AUDIT_EXE:
+		if (f->op != Audit_equal)
+			return -EINVAL;
+		if (entry->rule.listnr != AUDIT_FILTER_EXIT)
+			return -EINVAL;
+		break;
 	};
 	return 0;
 }

@@ -419,6 +425,7 @@ static struct audit_entry *audit_data_to_entry(struct

audit_rule_data *data, size_t remain = datasz - sizeof(struct audit_rule_data);

kernel/auditfilter.c +21 -0

 	int i;
 	char *str;
+	struct audit_fsnotify_mark *audit_mark;
 
 	entry = audit_to_entry_common(data);
 	if (IS_ERR(entry))

@@ -539,6 +546,24 @@ static struct audit_entry *audit_data_to_entry(struct
 audit_rule_data *data, entry->rule.buflen += f->val;
 			entry->rule.filterkey = str;
 			break;
+		case AUDIT_EXE:
+			if (entry->rule.exe || f->val > PATH_MAX)
+				goto exit_free;
+			str = audit_unpack_string(&bufp, &remain, f->val);
+			if (IS_ERR(str)) {
+				err = PTR_ERR(str);
+				goto exit_free;
+			}
+			entry->rule.buflen += f->val;
+
+			audit_mark = audit_alloc_mark(&entry->rule, str, f->val);
+			if (IS_ERR(audit_mark)) {
+				kfree(str);
+				err = PTR_ERR(audit_mark);
+				goto exit_free;
+			}
+			entry->rule.exe = audit_mark;
+			break;
 		}
 	}
 

@@ -551,6 +576,8 @@ exit_nofree:
 exit_free:
 	if (entry->rule.tree)
 		audit_put_tree(entry->rule.tree); /* that's the temporary one */
+	if (entry->rule.exe)
+		audit_remove_mark(entry->rule.exe); /* that's the template one */
 	audit_free_rule(entry);
 	return ERR_PTR(err);
 }

@@ -615,6 +642,10 @@ static struct audit_rule_data
 *audit_krule_to_data(struct audit_krule *krule) data->buflen +=

data->values[i] =

kernel/auditfilter.c +25 -1

 				audit_pack_string(&bufp, krule->filterkey);
 			break;
+		case AUDIT_EXE:
+			data->buflen += data->values[i] =
+				audit_pack_string(&bufp, audit_mark_path(krule->exe));
+			break;
 		case AUDIT_LOGINUID_SET:
 			if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) {
 				data->fields[i] = AUDIT_LOGINUID;

@@ -678,6 +709,12 @@ static int audit_compare_rule(struct audit_krule *a,
 struct audit_krule *b) if (strcmp(a->filterkey, b->filterkey))
 				return 1;
 			break;
+		case AUDIT_EXE:
+			/* both paths exist based on above type compare */
+			if (strcmp(audit_mark_path(a->exe),
+				   audit_mark_path(b->exe)))
+				return 1;
+			break;
 		case AUDIT_UID:
 		case AUDIT_EUID:
 		case AUDIT_SUID:

@@ -799,8 +836,14 @@ struct audit_entry *audit_dupe_rule(struct audit_krule
 *old) err = -ENOMEM;
 			else
 				new->filterkey = fk;
+			break;
+		case AUDIT_EXE:
+			err = audit_dupe_exe(new, old);
+			break;
 		}
 		if (err) {
+			if (new->exe)
+				audit_remove_mark(new->exe);
 			audit_free_rule(entry);
 			return ERR_PTR(err);
 		}

@@ -963,6 +1006,9 @@ int audit_del_rule(struct audit_entry *entry)
 	if (e->rule.tree)
 		audit_remove_tree_rule(&e->rule);
 
+	if (e->rule.exe)
+		audit_remove_mark_rule(&e->rule);
+
 #ifdef CONFIG_AUDITSYSCALL
 	if (!dont_count)
 		audit_n_rules--;

@@ -1067,8 +1113,11 @@ int audit_rule_change(int type, __u32 portid, int
 seq, void *data, WARN_ON(1);
 	}
 
-	if (err || type == AUDIT_DEL_RULE)
+	if (err || type == AUDIT_DEL_RULE) {
+		if (entry->rule.exe)
+			audit_remove_mark(entry->rule.exe);
 		audit_free_rule(entry);
+	}
 
 	return err;
 }

@@ -1360,6 +1409,8 @@ static int update_lsm_rule(struct audit_krule *r)
 		return 0;
 
 	nentry = audit_dupe_rule(r);
+	if (entry->rule.exe)
+		audit_remove_mark(entry->rule.exe);
 	if (IS_ERR(nentry)) {
 		/* save the first error encountered for the
 		 * return value */

kernel/auditsc.c +0 -0

index 701ea5c..e9bac2b 100644
@@ -466,6 +466,9 @@ static int audit_filter_rules(struct task_struct *tsk,
 				result = audit_comparator(ctx->ppid, f->op, f->val);

Quoted 8 lines

kernel/auditsc.c +3 -0

 			}
 			break;
+		case AUDIT_EXE:
+			result = audit_exe_compare(tsk, rule->exe);
+			break;
 		case AUDIT_UID:
 			result = audit_uid_comparator(cred->uid, f->op, f->uid);
 			break;

Signature · 2 lines

paul moore
security @ redhat

Quoted 5 lines · Paul Moore

Merged, although some more minor whitespace tweaks were necessary for checkpatch. On a related note, if you're not running ./scripts/checlpatch.pl on your patches before sending them out, I would recommend it. It isn't perfect, but it can catch some silly things that we all do from time to time.

No excuses... I have been running it pretty regularly and got lazy and distracted with patch revisions. I can't say I agree with the no space before closing round parenthesis due to legibility, but will comply.

Quoted 5 lines

Also, one last thing. It is pretty late in the -rcX cycle to merge these two patches, but considering that we've been talking about these for a while, I'm reasonably okay merging them. In the future, if it isn't in audit#next by the time -rc5 is released, it isn't going to make the merge window.

I've been quite aware of that looming merge window... This feature has been iterating for a while, so there are no big surprises. I was aiming for earlier. :)

This adds the ability to audit the actions of children of a not-yet-running process.

This is a split-out of a heavily modified version of a patch originally submitted by Eric Paris with some ideas from Peter Moody.

Cc Peter Moody <[email protected]>

Cc Eric Paris <[email protected]>

Signed-off-by Richard Guy Briggs <[email protected]>

---
 include/uapi/linux/audit.h |    1 +
 kernel/auditfilter.c       |    5 +++++
 kernel/auditsc.c           |   11 +++++++++++
 3 files changed, 17 insertions(+), 0 deletions(-)

include/uapi/linux/audit.h +1 -0

index e2ca600..55a8dec 100644
@@ -267,6 +267,7 @@
 #define AUDIT_OBJ_GID	110
 #define AUDIT_FIELD_COMPARE	111
 #define AUDIT_EXE	112
+#define AUDIT_EXE_CHILDREN	113
 
 #define AUDIT_ARG0      200
 #define AUDIT_ARG1      (AUDIT_ARG0+1)

kernel/auditfilter.c +3 -0

index c662638..802f0cc 100644
@@ -406,6 +406,7 @@ static int audit_field_valid(struct audit_entry *entry,
 struct audit_field *f) return -EINVAL;
 		break;
 	case AUDIT_EXE:
+	case AUDIT_EXE_CHILDREN:
 		if (f->op != Audit_equal)
 			return -EINVAL;
 		if (entry->rule.listnr != AUDIT_FILTER_EXIT)

@@ -547,6 +548,7 @@ static struct audit_entry *audit_data_to_entry(struct
 audit_rule_data *data, entry->rule.filterkey = str;
 			break;
 		case AUDIT_EXE:
+		case AUDIT_EXE_CHILDREN:
 			if (entry->rule.exe || f->val > PATH_MAX)
 				goto exit_free;
 			str = audit_unpack_string(&bufp, &remain, f->val);

@@ -643,6 +645,7 @@ static struct audit_rule_data
 *audit_krule_to_data(struct audit_krule *krule) audit_pack_string(&bufp,
 krule->filterkey);
 			break;
 		case AUDIT_EXE:
+		case AUDIT_EXE_CHILDREN:
 			data->buflen += data->values[i] =
 				audit_pack_string(&bufp, audit_mark_path(krule->exe));

kernel/auditfilter.c +2 -0

 			break;

@@ -710,6 +713,7 @@ static int audit_compare_rule(struct audit_krule *a,
 struct audit_krule *b) return 1;
 			break;
 		case AUDIT_EXE:
+		case AUDIT_EXE_CHILDREN:
 			/* both paths exist based on above type compare */
 			if (strcmp(audit_mark_path(a->exe),
 				   audit_mark_path(b->exe)))

@@ -838,6 +842,7 @@ struct audit_entry *audit_dupe_rule(struct audit_krule
 *old) new->filterkey = fk;
 			break;
 		case AUDIT_EXE:
+		case AUDIT_EXE_CHILDREN:
 			err = audit_dupe_exe(new, old);
 			break;
 		}

kernel/auditsc.c +4 -0

index e9bac2b..4f2b515 100644
@@ -469,6 +469,17 @@ static int audit_filter_rules(struct task_struct *tsk,
 		case AUDIT_EXE:
 			result = audit_exe_compare(tsk, rule->exe);
 			break;
+		case AUDIT_EXE_CHILDREN:
+		{
+			struct task_struct *ptsk;
+			for (ptsk = tsk; ptsk->parent->pid > 0; ptsk =

find_task_by_vpid(ptsk->parent->pid)) { + if

rule->exe)) {

kernel/auditsc.c +6 -0

+					++result;
+					break;
+				}
+			}
+		}
+			break;
 		case AUDIT_UID:
 			result = audit_uid_comparator(cred->uid, f->op, f->uid);
 			break;

Quoted 14 lines · Richard Guy Briggs

This adds the ability to audit the actions of children of a not-yet-running
process.

This is a split-out of a heavily modified version of a patch originally submitted by Eric Paris with some ideas from Peter Moody.

Cc Peter Moody <[email protected]>

Cc Eric Paris <[email protected]>

Signed-off-by Richard Guy Briggs <[email protected]>

Quoted 6 lines

---

 include/uapi/linux/audit.h |    1 +
 kernel/auditfilter.c       |    5 +++++
 kernel/auditsc.c           |   11 +++++++++++
 3 files changed, 17 insertions(+), 0 deletions(-)

I'm still not really comfortable with that loop and since there hasn't been a really convincing use case I'm going to pass on this patch for right now. If someone comes up with a *really* compelling case in the future I'll reconsider it.

Quoted 22 lines · Paul Moore

Quoted 14 lines · Richard Guy Briggs

This adds the ability to audit the actions of children of a not-yet-running
process.

This is a split-out of a heavily modified version of a patch originally submitted by Eric Paris with some ideas from Peter Moody.

Cc Peter Moody <[email protected]>

Cc Eric Paris <[email protected]>

Signed-off-by Richard Guy Briggs <[email protected]>

Quoted 6 lines

---

 include/uapi/linux/audit.h |    1 +
 kernel/auditfilter.c       |    5 +++++
 kernel/auditsc.c           |   11 +++++++++++
 3 files changed, 17 insertions(+), 0 deletions(-)

Quoted 4 lines

I'm still not really comfortable with that loop and since there hasn't been a really convincing use case I'm going to pass on this patch for right now. If someone comes up with a *really* compelling case in the future I'll reconsider it.

Its the same reason strace has a -f option. Sometimes you need to also see what the children did. For example, maybe you want to audit file access to a specific directory and several cgi-bin programs can get there. You could write a rule for apache and be done. Or maybe, you have an app that lets people have shell access and you need to see files accessed or connections opened. Or maybe its a control panel application with helper scripts and you need to see changes that its making. Or maybe you have a program that is at risk of being compromised and you want to see if someone gets a shell from it. There are a lot of cases where it could be useful.

-Steve

--
Linux-audit mailing list
[email protected]
https://www.redhat.com/mailman/listinfo/linux-audit

Quoted 38 lines · Steve Grubb

Quoted 22 lines · Paul Moore

Quoted 14 lines · Richard Guy Briggs

This adds the ability to audit the actions of children of a not-yet-running
process.

This is a split-out of a heavily modified version of a patch originally submitted by Eric Paris with some ideas from Peter Moody.

Cc Peter Moody <[email protected]>

Cc Eric Paris <[email protected]>

Signed-off-by Richard Guy Briggs <[email protected]>

Quoted 6 lines

---

 include/uapi/linux/audit.h |    1 +
 kernel/auditfilter.c       |    5 +++++
 kernel/auditsc.c           |   11 +++++++++++
 3 files changed, 17 insertions(+), 0 deletions(-)

Quoted 4 lines

I'm still not really comfortable with that loop and since there hasn't been a really convincing use case I'm going to pass on this patch for right now. If someone comes up with a *really* compelling case in the future I'll reconsider it.

Its the same reason strace has a -f option. Sometimes you need to also see what the children did. For example, maybe you want to audit file access to a specific directory and several cgi-bin programs can get there. You could write a rule for apache and be done. Or maybe, you have an app that lets people have shell access and you need to see files accessed or connections opened. Or maybe its a control panel application with helper scripts and you need to see changes that its making. Or maybe you have a program that is at risk of being compromised and you want to see if someone gets a shell from it. There are a lot of cases where it could be useful.

Quoted 6 lines

-Steve

--
Linux-audit mailing list
[email protected]
https://www.redhat.com/mailman/listinfo/linux-audit

I guess what I'm saying is that I'm not currently convinced that there is enough value in this to offset the risk I feel the loop presents. I understand the use cases that you are mentioning, the are the same as the last time we discussed this, but I'm going to need something better than that.

paul moore

Quoted 5 lines · Paul Moore

I guess what I'm saying is that I'm not currently convinced that there is enough value in this to offset the risk I feel the loop presents. I understand the use cases that you are mentioning, the are the same as the last time we discussed this, but I'm going to need something better than that.

Can you better describe the loop that concerns you? I don't quite see it.

Quoted 8 lines · Richard Guy Briggs

Quoted 5 lines · Paul Moore

I guess what I'm saying is that I'm not currently convinced that there is enough value in this to offset the risk I feel the loop presents. I understand the use cases that you are mentioning, the are the same as the last time we discussed this, but I'm going to need something better than that.

Quoted 2 lines

Can you better describe the loop that concerns you? I don't quite see it.

It would be the only loop in the patch, look at the for loop in audit_filter_rules() which iterates up the process' parent chain.

paul moore

Quoted 12 lines · Paul Moore

Quoted 10 lines · Richard Guy Briggs

Quoted 5 lines · Paul Moore

I guess what I'm saying is that I'm not currently convinced that there is enough value in this to offset the risk I feel the loop presents. I understand the use cases that you are mentioning, the are the same as the last time we discussed this, but I'm going to need something better than that.

Can you better describe the loop that concerns you? I don't quite see it.

Quoted 2 lines

It would be the only loop in the patch, look at the for loop in audit_filter_rules() which iterates up the process' parent chain.

Sorry, I should reword that... What risk do you see in that loop? It works up the task ancestry tree until it triggers, or hits init for that PID namespace that terminates the loop. Do you see a risk in the numerical pids rolling underneath the loop?

I *do* notice that find_task_by_vpid(pid_t) must be replaced with find_task_by_pid_ns(pid_t, &init_pid_ns), since task_struct->pid is always stored in the initial PID namespace.

Quoted 13 lines · Richard Guy Briggs

Quoted 12 lines · Paul Moore

Quoted 10 lines · Richard Guy Briggs

Quoted 5 lines · Paul Moore

I guess what I'm saying is that I'm not currently convinced that there is enough value in this to offset the risk I feel the loop presents. I understand the use cases that you are mentioning, the are the same as the last time we discussed this, but I'm going to need something better than that.

Can you better describe the loop that concerns you? I don't quite see it.

Quoted 7 lines

Quoted 2 lines

It would be the only loop in the patch, look at the for loop in audit_filter_rules() which iterates up the process' parent chain.

Sorry, I should reword that... What risk do you see in that loop? It works up the task ancestry tree until it triggers, or hits init for that PID namespace that terminates the loop. Do you see a risk in the numerical pids rolling underneath the loop?

I suppose there is some risk of PID overlap, and while that is a concern, it isn't my first.

My main concern is that a malicious user could add an extra level of burden to the system by making an absurdly tall process tree and then hammer the system with trivial, short lived syscalls. Granted, there are userspace limits which would bound the impact to some extent, but there is no way to really reduce the risk. You could further put hard limits on the loop, but what good would that do? Malicious users would just know to blow past that limit before they did their Evil Deeds.

I'll say it again; I'm not completely opposed to something like this - perhaps in some modified form - but I have yet to see a need for this functionality that is great enough to counter the risk.

Quoted 3 lines

I *do* notice that find_task_by_vpid(pid_t) must be replaced with find_task_by_pid_ns(pid_t, &init_pid_ns), since task_struct->pid is always stored in the initial PID namespace.

Another thing that needs to be resolved.

paul moore