Fixed MTP to work with TWRP

security/Kconfig

@@ -0,0 +1,172 @@
+#
+# Security configuration
+#
+
+menu "Security options"
+
+source security/keys/Kconfig
+
+config SECURITY_DMESG_RESTRICT
+	bool "Restrict unprivileged access to the kernel syslog"
+	default n
+	help
+	  This enforces restrictions on unprivileged users reading the kernel
+	  syslog via dmesg(8).
+
+	  If this option is not selected, no restrictions will be enforced
+	  unless the dmesg_restrict sysctl is explicitly set to (1).
+
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY
+	bool "Enable different security models"
+	depends on SYSFS
+	help
+	  This allows you to choose different security modules to be
+	  configured into your kernel.
+
+	  If this option is not selected, the default Linux security
+	  model will be used.
+
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITYFS
+	bool "Enable the securityfs filesystem"
+	help
+	  This will build the securityfs filesystem.  It is currently used by
+	  the TPM bios character driver and IMA, an integrity provider.  It is
+	  not used by SELinux or SMACK.
+
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_NETWORK
+	bool "Socket and Networking Security Hooks"
+	depends on SECURITY
+	help
+	  This enables the socket and networking security hooks.
+	  If enabled, a security module can use these hooks to
+	  implement socket and networking access controls.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_NETWORK_XFRM
+	bool "XFRM (IPSec) Networking Security Hooks"
+	depends on XFRM && SECURITY_NETWORK
+	help
+	  This enables the XFRM (IPSec) networking security hooks.
+	  If enabled, a security module can use these hooks to
+	  implement per-packet access controls based on labels
+	  derived from IPSec policy.  Non-IPSec communications are
+	  designated as unlabelled, and only sockets authorized
+	  to communicate unlabelled data can send without using
+	  IPSec.
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_PATH
+	bool "Security hooks for pathname based access control"
+	depends on SECURITY
+	help
+	  This enables the security hooks for pathname based access control.
+	  If enabled, a security module can use these hooks to
+	  implement pathname based access controls.
+	  If you are unsure how to answer this question, answer N.
+
+config INTEL_TXT
+	bool "Enable Intel(R) Trusted Execution Technology (Intel(R) TXT)"
+	depends on HAVE_INTEL_TXT
+	help
+	  This option enables support for booting the kernel with the
+	  Trusted Boot (tboot) module. This will utilize
+	  Intel(R) Trusted Execution Technology to perform a measured launch
+	  of the kernel. If the system does not support Intel(R) TXT, this
+	  will have no effect.
+
+	  Intel TXT will provide higher assurance of system configuration and
+	  initial state as well as data reset protection.  This is used to
+	  create a robust initial kernel measurement and verification, which
+	  helps to ensure that kernel security mechanisms are functioning
+	  correctly. This level of protection requires a root of trust outside
+	  of the kernel itself.
+
+	  Intel TXT also helps solve real end user concerns about having
+	  confidence that their hardware is running the VMM or kernel that
+	  it was configured with, especially since they may be responsible for
+	  providing such assurances to VMs and services running on it.
+
+	  See <http://www.intel.com/technology/security/> for more information
+	  about Intel(R) TXT.
+	  See <http://tboot.sourceforge.net> for more information about tboot.
+	  See Documentation/intel_txt.txt for a description of how to enable
+	  Intel TXT support in a kernel boot.
+
+	  If you are unsure as to whether this is required, answer N.
+
+config LSM_MMAP_MIN_ADDR
+	int "Low address space for LSM to protect from user allocation"
+	depends on SECURITY && SECURITY_SELINUX
+	default 32768 if ARM || (ARM64 && COMPAT)
+	default 65536
+	help
+	  This is the portion of low virtual memory which should be protected
+	  from userspace allocation.  Keeping a user from writing to low pages
+	  can help reduce the impact of kernel NULL pointer bugs.
+
+	  For most ia64, ppc64 and x86 users with lots of address space
+	  a value of 65536 is reasonable and should cause no problems.
+	  On arm and other archs it should not be higher than 32768.
+	  Programs which use vm86 functionality or have some need to map
+	  this low address space will need the permission specific to the
+	  systems running LSM.
+
+source security/selinux/Kconfig
+source security/smack/Kconfig
+source security/tomoyo/Kconfig
+source security/apparmor/Kconfig
+source security/yama/Kconfig
+
+source security/integrity/Kconfig
+source security/tz_iccc/Kconfig
+
+choice
+	prompt "Default security module"
+	default DEFAULT_SECURITY_SELINUX if SECURITY_SELINUX
+	default DEFAULT_SECURITY_SMACK if SECURITY_SMACK
+	default DEFAULT_SECURITY_TOMOYO if SECURITY_TOMOYO
+	default DEFAULT_SECURITY_APPARMOR if SECURITY_APPARMOR
+	default DEFAULT_SECURITY_YAMA if SECURITY_YAMA
+	default DEFAULT_SECURITY_DAC
+
+	help
+	  Select the security module that will be used by default if the
+	  kernel parameter security= is not specified.
+
+	config DEFAULT_SECURITY_SELINUX
+		bool "SELinux" if SECURITY_SELINUX=y
+
+	config DEFAULT_SECURITY_SMACK
+		bool "Simplified Mandatory Access Control" if SECURITY_SMACK=y
+
+	config DEFAULT_SECURITY_TOMOYO
+		bool "TOMOYO" if SECURITY_TOMOYO=y
+
+	config DEFAULT_SECURITY_APPARMOR
+		bool "AppArmor" if SECURITY_APPARMOR=y
+
+	config DEFAULT_SECURITY_YAMA
+		bool "Yama" if SECURITY_YAMA=y
+
+	config DEFAULT_SECURITY_DAC
+		bool "Unix Discretionary Access Controls"
+
+endchoice
+
+config DEFAULT_SECURITY
+	string
+	default "selinux" if DEFAULT_SECURITY_SELINUX
+	default "smack" if DEFAULT_SECURITY_SMACK
+	default "tomoyo" if DEFAULT_SECURITY_TOMOYO
+	default "apparmor" if DEFAULT_SECURITY_APPARMOR
+	default "yama" if DEFAULT_SECURITY_YAMA
+	default "" if DEFAULT_SECURITY_DAC
+
+endmenu
+

security/Makefile

@@ -0,0 +1,38 @@
+#
+# Makefile for the kernel security code
+#
+
+obj-$(CONFIG_KEYS)			+= keys/
+subdir-$(CONFIG_SECURITY_SELINUX)	+= selinux
+subdir-$(CONFIG_SECURITY_SMACK)		+= smack
+subdir-$(CONFIG_SECURITY_TOMOYO)        += tomoyo
+subdir-$(CONFIG_SECURITY_APPARMOR)	+= apparmor
+subdir-$(CONFIG_SECURITY_YAMA)		+= yama
+
+# always enable default capabilities
+obj-y					+= commoncap.o
+obj-$(CONFIG_MMU)			+= min_addr.o
+
+# Object file lists
+obj-$(CONFIG_SECURITY)			+= security.o capability.o
+obj-$(CONFIG_SECURITYFS)		+= inode.o
+obj-$(CONFIG_SECURITY_SELINUX)		+= selinux/
+obj-$(CONFIG_SECURITY_SMACK)		+= smack/
+obj-$(CONFIG_AUDIT)			+= lsm_audit.o
+obj-$(CONFIG_SECURITY_TOMOYO)		+= tomoyo/
+obj-$(CONFIG_SECURITY_APPARMOR)		+= apparmor/
+obj-$(CONFIG_SECURITY_YAMA)		+= yama/
+obj-$(CONFIG_CGROUP_DEVICE)		+= device_cgroup.o
+
+# Object integrity file lists
+subdir-$(CONFIG_INTEGRITY)		+= integrity
+obj-$(CONFIG_INTEGRITY)			+= integrity/
+
+# TIMA uevent 
+obj-$(CONFIG_TIMA)     += tima_uevent/tima_uevent.o
+
+#ICCC
+obj-$(CONFIG_TZ_ICCC)	  += tz_iccc/
+# Knox SDP
+obj-$(CONFIG_SDP) += sdp/
+obj-$(CONFIG_SDP) += sdp/built-in.o

security/apparmor/Kconfig

@@ -0,0 +1,43 @@
+config SECURITY_APPARMOR
+	bool "AppArmor support"
+	depends on SECURITY && NET
+	select AUDIT
+	select SECURITY_PATH
+	select SECURITYFS
+	select SECURITY_NETWORK
+	default n
+	help
+	  This enables the AppArmor security module.
+	  Required userspace tools (if they are not included in your
+	  distribution) and further information may be found at
+	  http://apparmor.wiki.kernel.org
+
+	  If you are unsure how to answer this question, answer N.
+
+config SECURITY_APPARMOR_BOOTPARAM_VALUE
+	int "AppArmor boot parameter default value"
+	depends on SECURITY_APPARMOR
+	range 0 1
+	default 1
+	help
+	  This option sets the default value for the kernel parameter
+	  'apparmor', which allows AppArmor to be enabled or disabled
+          at boot.  If this option is set to 0 (zero), the AppArmor
+	  kernel parameter will default to 0, disabling AppArmor at
+	  boot.  If this option is set to 1 (one), the AppArmor
+	  kernel parameter will default to 1, enabling AppArmor at
+	  boot.
+
+	  If you are unsure how to answer this question, answer 1.
+
+config SECURITY_APPARMOR_HASH
+	bool "SHA1 hash of loaded profiles"
+	depends on SECURITY_APPARMOR
+	depends on CRYPTO
+	select CRYPTO_SHA1
+	default y
+
+	help
+	  This option selects whether sha1 hashing is done against loaded
+          profiles and exported for inspection to user space via the apparmor
+          filesystem.

security/apparmor/Makefile

@@ -0,0 +1,70 @@
+# Makefile for AppArmor Linux Security Module
+#
+obj-$(CONFIG_SECURITY_APPARMOR) += apparmor.o
+
+apparmor-y := apparmorfs.o audit.o capability.o context.o ipc.o lib.o match.o \
+              path.o domain.o policy.o policy_unpack.o procattr.o lsm.o \
+              resource.o sid.o file.o
+apparmor-$(CONFIG_SECURITY_APPARMOR_HASH) += crypto.o
+
+clean-files := capability_names.h rlim_names.h
+
+
+# Build a lower case string table of capability names
+# Transforms lines from
+#    #define CAP_DAC_OVERRIDE     1
+# to
+#    [1] = "dac_override",
+quiet_cmd_make-caps = GEN     $@
+cmd_make-caps = echo "static const char *const capability_names[] = {" > $@ ;\
+	sed $< >>$@ -r -n -e '/CAP_FS_MASK/d' \
+	-e 's/^\#define[ \t]+CAP_([A-Z0-9_]+)[ \t]+([0-9]+)/[\2] = "\L\1",/p';\
+	echo "};" >> $@ ;\
+	echo -n '\#define AA_FS_CAPS_MASK "' >> $@ ;\
+	sed $< -r -n -e '/CAP_FS_MASK/d' \
+	    -e 's/^\#define[ \t]+CAP_([A-Z0-9_]+)[ \t]+([0-9]+)/\L\1/p' | \
+	     tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@
+
+
+# Build a lower case string table of rlimit names.
+# Transforms lines from
+#    #define RLIMIT_STACK		3	/* max stack size */
+# to
+#    [RLIMIT_STACK] = "stack",
+#
+# and build a second integer table (with the second sed cmd), that maps
+# RLIMIT defines to the order defined in asm-generic/resource.h  This is
+# required by policy load to map policy ordering of RLIMITs to internal
+# ordering for architectures that redefine an RLIMIT.
+# Transforms lines from
+#    #define RLIMIT_STACK		3	/* max stack size */
+# to
+# RLIMIT_STACK, 
+#
+# and build the securityfs entries for the mapping.
+# Transforms lines from
+#    #define RLIMIT_FSIZE        1   /* Maximum filesize */
+#    #define RLIMIT_STACK		3	/* max stack size */
+# to
+# #define AA_FS_RLIMIT_MASK "fsize stack"
+quiet_cmd_make-rlim = GEN     $@
+cmd_make-rlim = echo "static const char *const rlim_names[RLIM_NLIMITS] = {" \
+	> $@ ;\
+	sed $< >> $@ -r -n \
+	    -e 's/^\# ?define[ \t]+(RLIMIT_([A-Z0-9_]+)).*/[\1] = "\L\2",/p';\
+	echo "};" >> $@ ;\
+	echo "static const int rlim_map[RLIM_NLIMITS] = {" >> $@ ;\
+	sed -r -n "s/^\# ?define[ \t]+(RLIMIT_[A-Z0-9_]+).*/\1,/p" $< >> $@ ;\
+	echo "};" >> $@ ; \
+	echo -n '\#define AA_FS_RLIMIT_MASK "' >> $@ ;\
+	sed -r -n 's/^\# ?define[ \t]+RLIMIT_([A-Z0-9_]+).*/\L\1/p' $< | \
+	    tr '\n' ' ' | sed -e 's/ $$/"\n/' >> $@
+
+$(obj)/capability.o : $(obj)/capability_names.h
+$(obj)/resource.o : $(obj)/rlim_names.h
+$(obj)/capability_names.h : $(srctree)/include/uapi/linux/capability.h \
+			    $(src)/Makefile
+	$(call cmd,make-caps)
+$(obj)/rlim_names.h : $(srctree)/include/uapi/asm-generic/resource.h \
+		      $(src)/Makefile
+	$(call cmd,make-rlim)

security/apparmor/apparmorfs.c

@@ -0,0 +1,969 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor /sys/kernel/security/apparmor interface functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/ctype.h>
+#include <linux/security.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/namei.h>
+#include <linux/capability.h>
+#include <linux/rcupdate.h>
+
+#include "include/apparmor.h"
+#include "include/apparmorfs.h"
+#include "include/audit.h"
+#include "include/context.h"
+#include "include/crypto.h"
+#include "include/policy.h"
+#include "include/resource.h"
+
+/**
+ * aa_mangle_name - mangle a profile name to std profile layout form
+ * @name: profile name to mangle  (NOT NULL)
+ * @target: buffer to store mangled name, same length as @name (MAYBE NULL)
+ *
+ * Returns: length of mangled name
+ */
+static int mangle_name(char *name, char *target)
+{
+	char *t = target;
+
+	while (*name == '/' || *name == '.')
+		name++;
+
+	if (target) {
+		for (; *name; name++) {
+			if (*name == '/')
+				*(t)++ = '.';
+			else if (isspace(*name))
+				*(t)++ = '_';
+			else if (isalnum(*name) || strchr("._-", *name))
+				*(t)++ = *name;
+		}
+
+		*t = 0;
+	} else {
+		int len = 0;
+		for (; *name; name++) {
+			if (isalnum(*name) || isspace(*name) ||
+			    strchr("/._-", *name))
+				len++;
+		}
+
+		return len;
+	}
+
+	return t - target;
+}
+
+/**
+ * aa_simple_write_to_buffer - common routine for getting policy from user
+ * @op: operation doing the user buffer copy
+ * @userbuf: user buffer to copy data from  (NOT NULL)
+ * @alloc_size: size of user buffer (REQUIRES: @alloc_size >= @copy_size)
+ * @copy_size: size of data to copy from user buffer
+ * @pos: position write is at in the file (NOT NULL)
+ *
+ * Returns: kernel buffer containing copy of user buffer data or an
+ *          ERR_PTR on failure.
+ */
+static char *aa_simple_write_to_buffer(int op, const char __user *userbuf,
+				       size_t alloc_size, size_t copy_size,
+				       loff_t *pos)
+{
+	char *data;
+
+	BUG_ON(copy_size > alloc_size);
+
+	if (*pos != 0)
+		/* only writes from pos 0, that is complete writes */
+		return ERR_PTR(-ESPIPE);
+
+	/*
+	 * Don't allow profile load/replace/remove from profiles that don't
+	 * have CAP_MAC_ADMIN
+	 */
+	if (!aa_may_manage_policy(op))
+		return ERR_PTR(-EACCES);
+
+	/* freed by caller to simple_write_to_buffer */
+	data = kvmalloc(alloc_size);
+	if (data == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(data, userbuf, copy_size)) {
+		kvfree(data);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return data;
+}
+
+
+/* .load file hook fn to load policy */
+static ssize_t profile_load(struct file *f, const char __user *buf, size_t size,
+			    loff_t *pos)
+{
+	char *data;
+	ssize_t error;
+
+	data = aa_simple_write_to_buffer(OP_PROF_LOAD, buf, size, size, pos);
+
+	error = PTR_ERR(data);
+	if (!IS_ERR(data)) {
+		error = aa_replace_profiles(data, size, PROF_ADD);
+		kvfree(data);
+	}
+
+	return error;
+}
+
+static const struct file_operations aa_fs_profile_load = {
+	.write = profile_load,
+	.llseek = default_llseek,
+};
+
+/* .replace file hook fn to load and/or replace policy */
+static ssize_t profile_replace(struct file *f, const char __user *buf,
+			       size_t size, loff_t *pos)
+{
+	char *data;
+	ssize_t error;
+
+	data = aa_simple_write_to_buffer(OP_PROF_REPL, buf, size, size, pos);
+	error = PTR_ERR(data);
+	if (!IS_ERR(data)) {
+		error = aa_replace_profiles(data, size, PROF_REPLACE);
+		kvfree(data);
+	}
+
+	return error;
+}
+
+static const struct file_operations aa_fs_profile_replace = {
+	.write = profile_replace,
+	.llseek = default_llseek,
+};
+
+/* .remove file hook fn to remove loaded policy */
+static ssize_t profile_remove(struct file *f, const char __user *buf,
+			      size_t size, loff_t *pos)
+{
+	char *data;
+	ssize_t error;
+
+	/*
+	 * aa_remove_profile needs a null terminated string so 1 extra
+	 * byte is allocated and the copied data is null terminated.
+	 */
+	data = aa_simple_write_to_buffer(OP_PROF_RM, buf, size + 1, size, pos);
+
+	error = PTR_ERR(data);
+	if (!IS_ERR(data)) {
+		data[size] = 0;
+		error = aa_remove_profiles(data, size);
+		kvfree(data);
+	}
+
+	return error;
+}
+
+static const struct file_operations aa_fs_profile_remove = {
+	.write = profile_remove,
+	.llseek = default_llseek,
+};
+
+static int aa_fs_seq_show(struct seq_file *seq, void *v)
+{
+	struct aa_fs_entry *fs_file = seq->private;
+
+	if (!fs_file)
+		return 0;
+
+	switch (fs_file->v_type) {
+	case AA_FS_TYPE_BOOLEAN:
+		seq_printf(seq, "%s\n", fs_file->v.boolean ? "yes" : "no");
+		break;
+	case AA_FS_TYPE_STRING:
+		seq_printf(seq, "%s\n", fs_file->v.string);
+		break;
+	case AA_FS_TYPE_U64:
+		seq_printf(seq, "%#08lx\n", fs_file->v.u64);
+		break;
+	default:
+		/* Ignore unpritable entry types. */
+		break;
+	}
+
+	return 0;
+}
+
+static int aa_fs_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, aa_fs_seq_show, inode->i_private);
+}
+
+const struct file_operations aa_fs_seq_file_ops = {
+	.owner		= THIS_MODULE,
+	.open		= aa_fs_seq_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int aa_fs_seq_profile_open(struct inode *inode, struct file *file,
+				  int (*show)(struct seq_file *, void *))
+{
+	struct aa_replacedby *r = aa_get_replacedby(inode->i_private);
+	int error = single_open(file, show, r);
+
+	if (error) {
+		file->private_data = NULL;
+		aa_put_replacedby(r);
+	}
+
+	return error;
+}
+
+static int aa_fs_seq_profile_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = (struct seq_file *) file->private_data;
+	if (seq)
+		aa_put_replacedby(seq->private);
+	return single_release(inode, file);
+}
+
+static int aa_fs_seq_profname_show(struct seq_file *seq, void *v)
+{
+	struct aa_replacedby *r = seq->private;
+	struct aa_profile *profile = aa_get_profile_rcu(&r->profile);
+	seq_printf(seq, "%s\n", profile->base.name);
+	aa_put_profile(profile);
+
+	return 0;
+}
+
+static int aa_fs_seq_profname_open(struct inode *inode, struct file *file)
+{
+	return aa_fs_seq_profile_open(inode, file, aa_fs_seq_profname_show);
+}
+
+static const struct file_operations aa_fs_profname_fops = {
+	.owner		= THIS_MODULE,
+	.open		= aa_fs_seq_profname_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= aa_fs_seq_profile_release,
+};
+
+static int aa_fs_seq_profmode_show(struct seq_file *seq, void *v)
+{
+	struct aa_replacedby *r = seq->private;
+	struct aa_profile *profile = aa_get_profile_rcu(&r->profile);
+	seq_printf(seq, "%s\n", aa_profile_mode_names[profile->mode]);
+	aa_put_profile(profile);
+
+	return 0;
+}
+
+static int aa_fs_seq_profmode_open(struct inode *inode, struct file *file)
+{
+	return aa_fs_seq_profile_open(inode, file, aa_fs_seq_profmode_show);
+}
+
+static const struct file_operations aa_fs_profmode_fops = {
+	.owner		= THIS_MODULE,
+	.open		= aa_fs_seq_profmode_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= aa_fs_seq_profile_release,
+};
+
+static int aa_fs_seq_profattach_show(struct seq_file *seq, void *v)
+{
+	struct aa_replacedby *r = seq->private;
+	struct aa_profile *profile = aa_get_profile_rcu(&r->profile);
+	if (profile->attach)
+		seq_printf(seq, "%s\n", profile->attach);
+	else if (profile->xmatch)
+		seq_puts(seq, "<unknown>\n");
+	else
+		seq_printf(seq, "%s\n", profile->base.name);
+	aa_put_profile(profile);
+
+	return 0;
+}
+
+static int aa_fs_seq_profattach_open(struct inode *inode, struct file *file)
+{
+	return aa_fs_seq_profile_open(inode, file, aa_fs_seq_profattach_show);
+}
+
+static const struct file_operations aa_fs_profattach_fops = {
+	.owner		= THIS_MODULE,
+	.open		= aa_fs_seq_profattach_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= aa_fs_seq_profile_release,
+};
+
+static int aa_fs_seq_hash_show(struct seq_file *seq, void *v)
+{
+	struct aa_replacedby *r = seq->private;
+	struct aa_profile *profile = aa_get_profile_rcu(&r->profile);
+	unsigned int i, size = aa_hash_size();
+
+	if (profile->hash) {
+		for (i = 0; i < size; i++)
+			seq_printf(seq, "%.2x", profile->hash[i]);
+		seq_puts(seq, "\n");
+	}
+
+	return 0;
+}
+
+static int aa_fs_seq_hash_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, aa_fs_seq_hash_show, inode->i_private);
+}
+
+static const struct file_operations aa_fs_seq_hash_fops = {
+	.owner		= THIS_MODULE,
+	.open		= aa_fs_seq_hash_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+/** fns to setup dynamic per profile/namespace files **/
+void __aa_fs_profile_rmdir(struct aa_profile *profile)
+{
+	struct aa_profile *child;
+	int i;
+
+	if (!profile)
+		return;
+
+	list_for_each_entry(child, &profile->base.profiles, base.list)
+		__aa_fs_profile_rmdir(child);
+
+	for (i = AAFS_PROF_SIZEOF - 1; i >= 0; --i) {
+		struct aa_replacedby *r;
+		if (!profile->dents[i])
+			continue;
+
+		r = profile->dents[i]->d_inode->i_private;
+		securityfs_remove(profile->dents[i]);
+		aa_put_replacedby(r);
+		profile->dents[i] = NULL;
+	}
+}
+
+void __aa_fs_profile_migrate_dents(struct aa_profile *old,
+				   struct aa_profile *new)
+{
+	int i;
+
+	for (i = 0; i < AAFS_PROF_SIZEOF; i++) {
+		new->dents[i] = old->dents[i];
+		old->dents[i] = NULL;
+	}
+}
+
+static struct dentry *create_profile_file(struct dentry *dir, const char *name,
+					  struct aa_profile *profile,
+					  const struct file_operations *fops)
+{
+	struct aa_replacedby *r = aa_get_replacedby(profile->replacedby);
+	struct dentry *dent;
+
+	dent = securityfs_create_file(name, S_IFREG | 0444, dir, r, fops);
+	if (IS_ERR(dent))
+		aa_put_replacedby(r);
+
+	return dent;
+}
+
+/* requires lock be held */
+int __aa_fs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
+{
+	struct aa_profile *child;
+	struct dentry *dent = NULL, *dir;
+	int error;
+
+	if (!parent) {
+		struct aa_profile *p;
+		p = aa_deref_parent(profile);
+		dent = prof_dir(p);
+		/* adding to parent that previously didn't have children */
+		dent = securityfs_create_dir("profiles", dent);
+		if (IS_ERR(dent))
+			goto fail;
+		prof_child_dir(p) = parent = dent;
+	}
+
+	if (!profile->dirname) {
+		int len, id_len;
+		len = mangle_name(profile->base.name, NULL);
+		id_len = snprintf(NULL, 0, ".%ld", profile->ns->uniq_id);
+
+		profile->dirname = kmalloc(len + id_len + 1, GFP_KERNEL);
+		if (!profile->dirname)
+			goto fail;
+
+		mangle_name(profile->base.name, profile->dirname);
+		sprintf(profile->dirname + len, ".%ld", profile->ns->uniq_id++);
+	}
+
+	dent = securityfs_create_dir(profile->dirname, parent);
+	if (IS_ERR(dent))
+		goto fail;
+	prof_dir(profile) = dir = dent;
+
+	dent = create_profile_file(dir, "name", profile, &aa_fs_profname_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	profile->dents[AAFS_PROF_NAME] = dent;
+
+	dent = create_profile_file(dir, "mode", profile, &aa_fs_profmode_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	profile->dents[AAFS_PROF_MODE] = dent;
+
+	dent = create_profile_file(dir, "attach", profile,
+				   &aa_fs_profattach_fops);
+	if (IS_ERR(dent))
+		goto fail;
+	profile->dents[AAFS_PROF_ATTACH] = dent;
+
+	if (profile->hash) {
+		dent = create_profile_file(dir, "sha1", profile,
+					   &aa_fs_seq_hash_fops);
+		if (IS_ERR(dent))
+			goto fail;
+		profile->dents[AAFS_PROF_HASH] = dent;
+	}
+
+	list_for_each_entry(child, &profile->base.profiles, base.list) {
+		error = __aa_fs_profile_mkdir(child, prof_child_dir(profile));
+		if (error)
+			goto fail2;
+	}
+
+	return 0;
+
+fail:
+	error = PTR_ERR(dent);
+
+fail2:
+	__aa_fs_profile_rmdir(profile);
+
+	return error;
+}
+
+void __aa_fs_namespace_rmdir(struct aa_namespace *ns)
+{
+	struct aa_namespace *sub;
+	struct aa_profile *child;
+	int i;
+
+	if (!ns)
+		return;
+
+	list_for_each_entry(child, &ns->base.profiles, base.list)
+		__aa_fs_profile_rmdir(child);
+
+	list_for_each_entry(sub, &ns->sub_ns, base.list) {
+		mutex_lock(&sub->lock);
+		__aa_fs_namespace_rmdir(sub);
+		mutex_unlock(&sub->lock);
+	}
+
+	for (i = AAFS_NS_SIZEOF - 1; i >= 0; --i) {
+		securityfs_remove(ns->dents[i]);
+		ns->dents[i] = NULL;
+	}
+}
+
+int __aa_fs_namespace_mkdir(struct aa_namespace *ns, struct dentry *parent,
+			    const char *name)
+{
+	struct aa_namespace *sub;
+	struct aa_profile *child;
+	struct dentry *dent, *dir;
+	int error;
+
+	if (!name)
+		name = ns->base.name;
+
+	dent = securityfs_create_dir(name, parent);
+	if (IS_ERR(dent))
+		goto fail;
+	ns_dir(ns) = dir = dent;
+
+	dent = securityfs_create_dir("profiles", dir);
+	if (IS_ERR(dent))
+		goto fail;
+	ns_subprofs_dir(ns) = dent;
+
+	dent = securityfs_create_dir("namespaces", dir);
+	if (IS_ERR(dent))
+		goto fail;
+	ns_subns_dir(ns) = dent;
+
+	list_for_each_entry(child, &ns->base.profiles, base.list) {
+		error = __aa_fs_profile_mkdir(child, ns_subprofs_dir(ns));
+		if (error)
+			goto fail2;
+	}
+
+	list_for_each_entry(sub, &ns->sub_ns, base.list) {
+		mutex_lock(&sub->lock);
+		error = __aa_fs_namespace_mkdir(sub, ns_subns_dir(ns), NULL);
+		mutex_unlock(&sub->lock);
+		if (error)
+			goto fail2;
+	}
+
+	return 0;
+
+fail:
+	error = PTR_ERR(dent);
+
+fail2:
+	__aa_fs_namespace_rmdir(ns);
+
+	return error;
+}
+
+
+#define list_entry_next(pos, member) \
+	list_entry(pos->member.next, typeof(*pos), member)
+#define list_entry_is_head(pos, head, member) (&pos->member == (head))
+
+/**
+ * __next_namespace - find the next namespace to list
+ * @root: root namespace to stop search at (NOT NULL)
+ * @ns: current ns position (NOT NULL)
+ *
+ * Find the next namespace from @ns under @root and handle all locking needed
+ * while switching current namespace.
+ *
+ * Returns: next namespace or NULL if at last namespace under @root
+ * Requires: ns->parent->lock to be held
+ * NOTE: will not unlock root->lock
+ */
+static struct aa_namespace *__next_namespace(struct aa_namespace *root,
+					     struct aa_namespace *ns)
+{
+	struct aa_namespace *parent, *next;
+
+	/* is next namespace a child */
+	if (!list_empty(&ns->sub_ns)) {
+		next = list_first_entry(&ns->sub_ns, typeof(*ns), base.list);
+		mutex_lock(&next->lock);
+		return next;
+	}
+
+	/* check if the next ns is a sibling, parent, gp, .. */
+	parent = ns->parent;
+	while (ns != root) {
+		mutex_unlock(&ns->lock);
+		next = list_entry_next(ns, base.list);
+		if (!list_entry_is_head(next, &parent->sub_ns, base.list)) {
+			mutex_lock(&next->lock);
+			return next;
+		}
+		ns = parent;
+		parent = parent->parent;
+	}
+
+	return NULL;
+}
+
+/**
+ * __first_profile - find the first profile in a namespace
+ * @root: namespace that is root of profiles being displayed (NOT NULL)
+ * @ns: namespace to start in   (NOT NULL)
+ *
+ * Returns: unrefcounted profile or NULL if no profile
+ * Requires: profile->ns.lock to be held
+ */
+static struct aa_profile *__first_profile(struct aa_namespace *root,
+					  struct aa_namespace *ns)
+{
+	for (; ns; ns = __next_namespace(root, ns)) {
+		if (!list_empty(&ns->base.profiles))
+			return list_first_entry(&ns->base.profiles,
+						struct aa_profile, base.list);
+	}
+	return NULL;
+}
+
+/**
+ * __next_profile - step to the next profile in a profile tree
+ * @profile: current profile in tree (NOT NULL)
+ *
+ * Perform a depth first traversal on the profile tree in a namespace
+ *
+ * Returns: next profile or NULL if done
+ * Requires: profile->ns.lock to be held
+ */
+static struct aa_profile *__next_profile(struct aa_profile *p)
+{
+	struct aa_profile *parent;
+	struct aa_namespace *ns = p->ns;
+
+	/* is next profile a child */
+	if (!list_empty(&p->base.profiles))
+		return list_first_entry(&p->base.profiles, typeof(*p),
+					base.list);
+
+	/* is next profile a sibling, parent sibling, gp, sibling, .. */
+	parent = rcu_dereference_protected(p->parent,
+					   mutex_is_locked(&p->ns->lock));
+	while (parent) {
+		p = list_entry_next(p, base.list);
+		if (!list_entry_is_head(p, &parent->base.profiles, base.list))
+			return p;
+		p = parent;
+		parent = rcu_dereference_protected(parent->parent,
+					    mutex_is_locked(&parent->ns->lock));
+	}
+
+	/* is next another profile in the namespace */
+	p = list_entry_next(p, base.list);
+	if (!list_entry_is_head(p, &ns->base.profiles, base.list))
+		return p;
+
+	return NULL;
+}
+
+/**
+ * next_profile - step to the next profile in where ever it may be
+ * @root: root namespace  (NOT NULL)
+ * @profile: current profile  (NOT NULL)
+ *
+ * Returns: next profile or NULL if there isn't one
+ */
+static struct aa_profile *next_profile(struct aa_namespace *root,
+				       struct aa_profile *profile)
+{
+	struct aa_profile *next = __next_profile(profile);
+	if (next)
+		return next;
+
+	/* finished all profiles in namespace move to next namespace */
+	return __first_profile(root, __next_namespace(root, profile->ns));
+}
+
+/**
+ * p_start - start a depth first traversal of profile tree
+ * @f: seq_file to fill
+ * @pos: current position
+ *
+ * Returns: first profile under current namespace or NULL if none found
+ *
+ * acquires first ns->lock
+ */
+static void *p_start(struct seq_file *f, loff_t *pos)
+{
+	struct aa_profile *profile = NULL;
+	struct aa_namespace *root = aa_current_profile()->ns;
+	loff_t l = *pos;
+	f->private = aa_get_namespace(root);
+
+
+	/* find the first profile */
+	mutex_lock(&root->lock);
+	profile = __first_profile(root, root);
+
+	/* skip to position */
+	for (; profile && l > 0; l--)
+		profile = next_profile(root, profile);
+
+	return profile;
+}
+
+/**
+ * p_next - read the next profile entry
+ * @f: seq_file to fill
+ * @p: profile previously returned
+ * @pos: current position
+ *
+ * Returns: next profile after @p or NULL if none
+ *
+ * may acquire/release locks in namespace tree as necessary
+ */
+static void *p_next(struct seq_file *f, void *p, loff_t *pos)
+{
+	struct aa_profile *profile = p;
+	struct aa_namespace *ns = f->private;
+	(*pos)++;
+
+	return next_profile(ns, profile);
+}
+
+/**
+ * p_stop - stop depth first traversal
+ * @f: seq_file we are filling
+ * @p: the last profile writen
+ *
+ * Release all locking done by p_start/p_next on namespace tree
+ */
+static void p_stop(struct seq_file *f, void *p)
+{
+	struct aa_profile *profile = p;
+	struct aa_namespace *root = f->private, *ns;
+
+	if (profile) {
+		for (ns = profile->ns; ns && ns != root; ns = ns->parent)
+			mutex_unlock(&ns->lock);
+	}
+	mutex_unlock(&root->lock);
+	aa_put_namespace(root);
+}
+
+/**
+ * seq_show_profile - show a profile entry
+ * @f: seq_file to file
+ * @p: current position (profile)    (NOT NULL)
+ *
+ * Returns: error on failure
+ */
+static int seq_show_profile(struct seq_file *f, void *p)
+{
+	struct aa_profile *profile = (struct aa_profile *)p;
+	struct aa_namespace *root = f->private;
+
+	if (profile->ns != root)
+		seq_printf(f, ":%s://", aa_ns_name(root, profile->ns));
+	seq_printf(f, "%s (%s)\n", profile->base.hname,
+		   aa_profile_mode_names[profile->mode]);
+
+	return 0;
+}
+
+static const struct seq_operations aa_fs_profiles_op = {
+	.start = p_start,
+	.next = p_next,
+	.stop = p_stop,
+	.show = seq_show_profile,
+};
+
+static int profiles_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &aa_fs_profiles_op);
+}
+
+static int profiles_release(struct inode *inode, struct file *file)
+{
+	return seq_release(inode, file);
+}
+
+static const struct file_operations aa_fs_profiles_fops = {
+	.open = profiles_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = profiles_release,
+};
+
+
+/** Base file system setup **/
+static struct aa_fs_entry aa_fs_entry_file[] = {
+	AA_FS_FILE_STRING("mask", "create read write exec append mmap_exec " \
+				  "link lock"),
+	{ }
+};
+
+static struct aa_fs_entry aa_fs_entry_domain[] = {
+	AA_FS_FILE_BOOLEAN("change_hat",	1),
+	AA_FS_FILE_BOOLEAN("change_hatv",	1),
+	AA_FS_FILE_BOOLEAN("change_onexec",	1),
+	AA_FS_FILE_BOOLEAN("change_profile",	1),
+	{ }
+};
+
+static struct aa_fs_entry aa_fs_entry_policy[] = {
+	AA_FS_FILE_BOOLEAN("set_load",          1),
+	{}
+};
+
+static struct aa_fs_entry aa_fs_entry_features[] = {
+	AA_FS_DIR("policy",			aa_fs_entry_policy),
+	AA_FS_DIR("domain",			aa_fs_entry_domain),
+	AA_FS_DIR("file",			aa_fs_entry_file),
+	AA_FS_FILE_U64("capability",		VFS_CAP_FLAGS_MASK),
+	AA_FS_DIR("rlimit",			aa_fs_entry_rlimit),
+	AA_FS_DIR("caps",			aa_fs_entry_caps),
+	{ }
+};
+
+static struct aa_fs_entry aa_fs_entry_apparmor[] = {
+	AA_FS_FILE_FOPS(".load", 0640, &aa_fs_profile_load),
+	AA_FS_FILE_FOPS(".replace", 0640, &aa_fs_profile_replace),
+	AA_FS_FILE_FOPS(".remove", 0640, &aa_fs_profile_remove),
+	AA_FS_FILE_FOPS("profiles", 0640, &aa_fs_profiles_fops),
+	AA_FS_DIR("features", aa_fs_entry_features),
+	{ }
+};
+
+static struct aa_fs_entry aa_fs_entry =
+	AA_FS_DIR("apparmor", aa_fs_entry_apparmor);
+
+/**
+ * aafs_create_file - create a file entry in the apparmor securityfs
+ * @fs_file: aa_fs_entry to build an entry for (NOT NULL)
+ * @parent: the parent dentry in the securityfs
+ *
+ * Use aafs_remove_file to remove entries created with this fn.
+ */
+static int __init aafs_create_file(struct aa_fs_entry *fs_file,
+				   struct dentry *parent)
+{
+	int error = 0;
+
+	fs_file->dentry = securityfs_create_file(fs_file->name,
+						 S_IFREG | fs_file->mode,
+						 parent, fs_file,
+						 fs_file->file_ops);
+	if (IS_ERR(fs_file->dentry)) {
+		error = PTR_ERR(fs_file->dentry);
+		fs_file->dentry = NULL;
+	}
+	return error;
+}
+
+static void __init aafs_remove_dir(struct aa_fs_entry *fs_dir);
+/**
+ * aafs_create_dir - recursively create a directory entry in the securityfs
+ * @fs_dir: aa_fs_entry (and all child entries) to build (NOT NULL)
+ * @parent: the parent dentry in the securityfs
+ *
+ * Use aafs_remove_dir to remove entries created with this fn.
+ */
+static int __init aafs_create_dir(struct aa_fs_entry *fs_dir,
+				  struct dentry *parent)
+{
+	struct aa_fs_entry *fs_file;
+	struct dentry *dir;
+	int error;
+
+	dir = securityfs_create_dir(fs_dir->name, parent);
+	if (IS_ERR(dir))
+		return PTR_ERR(dir);
+	fs_dir->dentry = dir;
+
+	for (fs_file = fs_dir->v.files; fs_file && fs_file->name; ++fs_file) {
+		if (fs_file->v_type == AA_FS_TYPE_DIR)
+			error = aafs_create_dir(fs_file, fs_dir->dentry);
+		else
+			error = aafs_create_file(fs_file, fs_dir->dentry);
+		if (error)
+			goto failed;
+	}
+
+	return 0;
+
+failed:
+	aafs_remove_dir(fs_dir);
+
+	return error;
+}
+
+/**
+ * aafs_remove_file - drop a single file entry in the apparmor securityfs
+ * @fs_file: aa_fs_entry to detach from the securityfs (NOT NULL)
+ */
+static void __init aafs_remove_file(struct aa_fs_entry *fs_file)
+{
+	if (!fs_file->dentry)
+		return;
+
+	securityfs_remove(fs_file->dentry);
+	fs_file->dentry = NULL;
+}
+
+/**
+ * aafs_remove_dir - recursively drop a directory entry from the securityfs
+ * @fs_dir: aa_fs_entry (and all child entries) to detach (NOT NULL)
+ */
+static void __init aafs_remove_dir(struct aa_fs_entry *fs_dir)
+{
+	struct aa_fs_entry *fs_file;
+
+	for (fs_file = fs_dir->v.files; fs_file && fs_file->name; ++fs_file) {
+		if (fs_file->v_type == AA_FS_TYPE_DIR)
+			aafs_remove_dir(fs_file);
+		else
+			aafs_remove_file(fs_file);
+	}
+
+	aafs_remove_file(fs_dir);
+}
+
+/**
+ * aa_destroy_aafs - cleanup and free aafs
+ *
+ * releases dentries allocated by aa_create_aafs
+ */
+void __init aa_destroy_aafs(void)
+{
+	aafs_remove_dir(&aa_fs_entry);
+}
+
+/**
+ * aa_create_aafs - create the apparmor security filesystem
+ *
+ * dentries created here are released by aa_destroy_aafs
+ *
+ * Returns: error on failure
+ */
+static int __init aa_create_aafs(void)
+{
+	int error;
+
+	if (!apparmor_initialized)
+		return 0;
+
+	if (aa_fs_entry.dentry) {
+		AA_ERROR("%s: AppArmor securityfs already exists\n", __func__);
+		return -EEXIST;
+	}
+
+	/* Populate fs tree. */
+	error = aafs_create_dir(&aa_fs_entry, NULL);
+	if (error)
+		goto error;
+
+	error = __aa_fs_namespace_mkdir(root_ns, aa_fs_entry.dentry,
+					"policy");
+	if (error)
+		goto error;
+
+	/* TODO: add support for apparmorfs_null and apparmorfs_mnt */
+
+	/* Report that AppArmor fs is enabled */
+	aa_info_message("AppArmor Filesystem Enabled");
+	return 0;
+
+error:
+	aa_destroy_aafs();
+	AA_ERROR("Error creating AppArmor securityfs\n");
+	return error;
+}
+
+fs_initcall(aa_create_aafs);

security/apparmor/audit.c

@@ -0,0 +1,209 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor auditing functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/audit.h>
+#include <linux/socket.h>
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/policy.h"
+
+const char *const op_table[] = {
+	"null",
+
+	"sysctl",
+	"capable",
+
+	"unlink",
+	"mkdir",
+	"rmdir",
+	"mknod",
+	"truncate",
+	"link",
+	"symlink",
+	"rename_src",
+	"rename_dest",
+	"chmod",
+	"chown",
+	"getattr",
+	"open",
+
+	"file_perm",
+	"file_lock",
+	"file_mmap",
+	"file_mprotect",
+
+	"create",
+	"post_create",
+	"bind",
+	"connect",
+	"listen",
+	"accept",
+	"sendmsg",
+	"recvmsg",
+	"getsockname",
+	"getpeername",
+	"getsockopt",
+	"setsockopt",
+	"socket_shutdown",
+
+	"ptrace",
+
+	"exec",
+	"change_hat",
+	"change_profile",
+	"change_onexec",
+
+	"setprocattr",
+	"setrlimit",
+
+	"profile_replace",
+	"profile_load",
+	"profile_remove"
+};
+
+const char *const audit_mode_names[] = {
+	"normal",
+	"quiet_denied",
+	"quiet",
+	"noquiet",
+	"all"
+};
+
+static const char *const aa_audit_type[] = {
+	"AUDIT",
+	"ALLOWED",
+	"DENIED",
+	"HINT",
+	"STATUS",
+	"ERROR",
+	"KILLED",
+	"AUTO"
+};
+
+/*
+ * Currently AppArmor auditing is fed straight into the audit framework.
+ *
+ * TODO:
+ * netlink interface for complain mode
+ * user auditing, - send user auditing to netlink interface
+ * system control of whether user audit messages go to system log
+ */
+
+/**
+ * audit_base - core AppArmor function.
+ * @ab: audit buffer to fill (NOT NULL)
+ * @ca: audit structure containing data to audit (NOT NULL)
+ *
+ * Record common AppArmor audit data from @sa
+ */
+static void audit_pre(struct audit_buffer *ab, void *ca)
+{
+	struct common_audit_data *sa = ca;
+
+	if (aa_g_audit_header) {
+		audit_log_format(ab, "apparmor=");
+		audit_log_string(ab, aa_audit_type[sa->aad->type]);
+	}
+
+	if (sa->aad->op) {
+		audit_log_format(ab, " operation=");
+		audit_log_string(ab, op_table[sa->aad->op]);
+	}
+
+	if (sa->aad->info) {
+		audit_log_format(ab, " info=");
+		audit_log_string(ab, sa->aad->info);
+		if (sa->aad->error)
+			audit_log_format(ab, " error=%d", sa->aad->error);
+	}
+
+	if (sa->aad->profile) {
+		struct aa_profile *profile = sa->aad->profile;
+		if (profile->ns != root_ns) {
+			audit_log_format(ab, " namespace=");
+			audit_log_untrustedstring(ab, profile->ns->base.hname);
+		}
+		audit_log_format(ab, " profile=");
+		audit_log_untrustedstring(ab, profile->base.hname);
+	}
+
+	if (sa->aad->name) {
+		audit_log_format(ab, " name=");
+		audit_log_untrustedstring(ab, sa->aad->name);
+	}
+}
+
+/**
+ * aa_audit_msg - Log a message to the audit subsystem
+ * @sa: audit event structure (NOT NULL)
+ * @cb: optional callback fn for type specific fields (MAYBE NULL)
+ */
+void aa_audit_msg(int type, struct common_audit_data *sa,
+		  void (*cb) (struct audit_buffer *, void *))
+{
+	sa->aad->type = type;
+	common_lsm_audit(sa, audit_pre, cb);
+}
+
+/**
+ * aa_audit - Log a profile based audit event to the audit subsystem
+ * @type: audit type for the message
+ * @profile: profile to check against (NOT NULL)
+ * @gfp: allocation flags to use
+ * @sa: audit event (NOT NULL)
+ * @cb: optional callback fn for type specific fields (MAYBE NULL)
+ *
+ * Handle default message switching based off of audit mode flags
+ *
+ * Returns: error on failure
+ */
+int aa_audit(int type, struct aa_profile *profile, gfp_t gfp,
+	     struct common_audit_data *sa,
+	     void (*cb) (struct audit_buffer *, void *))
+{
+	BUG_ON(!profile);
+
+	if (type == AUDIT_APPARMOR_AUTO) {
+		if (likely(!sa->aad->error)) {
+			if (AUDIT_MODE(profile) != AUDIT_ALL)
+				return 0;
+			type = AUDIT_APPARMOR_AUDIT;
+		} else if (COMPLAIN_MODE(profile))
+			type = AUDIT_APPARMOR_ALLOWED;
+		else
+			type = AUDIT_APPARMOR_DENIED;
+	}
+	if (AUDIT_MODE(profile) == AUDIT_QUIET ||
+	    (type == AUDIT_APPARMOR_DENIED &&
+	     AUDIT_MODE(profile) == AUDIT_QUIET))
+		return sa->aad->error;
+
+	if (KILL_MODE(profile) && type == AUDIT_APPARMOR_DENIED)
+		type = AUDIT_APPARMOR_KILL;
+
+	if (!unconfined(profile))
+		sa->aad->profile = profile;
+
+	aa_audit_msg(type, sa, cb);
+
+	if (sa->aad->type == AUDIT_APPARMOR_KILL)
+		(void)send_sig_info(SIGKILL, NULL,
+				    sa->u.tsk ?  sa->u.tsk : current);
+
+	if (sa->aad->type == AUDIT_APPARMOR_ALLOWED)
+		return complain_error(sa->aad->error);
+
+	return sa->aad->error;
+}

security/apparmor/capability.c

@@ -0,0 +1,143 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor capability mediation functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/gfp.h>
+
+#include "include/apparmor.h"
+#include "include/capability.h"
+#include "include/context.h"
+#include "include/policy.h"
+#include "include/audit.h"
+
+/*
+ * Table of capability names: we generate it from capabilities.h.
+ */
+#include "capability_names.h"
+
+struct aa_fs_entry aa_fs_entry_caps[] = {
+	AA_FS_FILE_STRING("mask", AA_FS_CAPS_MASK),
+	{ }
+};
+
+struct audit_cache {
+	struct aa_profile *profile;
+	kernel_cap_t caps;
+};
+
+static DEFINE_PER_CPU(struct audit_cache, audit_cache);
+
+/**
+ * audit_cb - call back for capability components of audit struct
+ * @ab - audit buffer   (NOT NULL)
+ * @va - audit struct to audit data from  (NOT NULL)
+ */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	audit_log_format(ab, " capname=");
+	audit_log_untrustedstring(ab, capability_names[sa->u.cap]);
+}
+
+/**
+ * audit_caps - audit a capability
+ * @profile: profile being tested for confinement (NOT NULL)
+ * @cap: capability tested
+ * @error: error code returned by test
+ *
+ * Do auditing of capability and handle, audit/complain/kill modes switching
+ * and duplicate message elimination.
+ *
+ * Returns: 0 or sa->error on success,  error code on failure
+ */
+static int audit_caps(struct aa_profile *profile, int cap, int error)
+{
+	struct audit_cache *ent;
+	int type = AUDIT_APPARMOR_AUTO;
+	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
+	sa.type = LSM_AUDIT_DATA_CAP;
+	sa.aad = &aad;
+	sa.u.cap = cap;
+	sa.aad->op = OP_CAPABLE;
+	sa.aad->error = error;
+
+	if (likely(!error)) {
+		/* test if auditing is being forced */
+		if (likely((AUDIT_MODE(profile) != AUDIT_ALL) &&
+			   !cap_raised(profile->caps.audit, cap)))
+			return 0;
+		type = AUDIT_APPARMOR_AUDIT;
+	} else if (KILL_MODE(profile) ||
+		   cap_raised(profile->caps.kill, cap)) {
+		type = AUDIT_APPARMOR_KILL;
+	} else if (cap_raised(profile->caps.quiet, cap) &&
+		   AUDIT_MODE(profile) != AUDIT_NOQUIET &&
+		   AUDIT_MODE(profile) != AUDIT_ALL) {
+		/* quiet auditing */
+		return error;
+	}
+
+	/* Do simple duplicate message elimination */
+	ent = &get_cpu_var(audit_cache);
+	if (profile == ent->profile && cap_raised(ent->caps, cap)) {
+		put_cpu_var(audit_cache);
+		if (COMPLAIN_MODE(profile))
+			return complain_error(error);
+		return error;
+	} else {
+		aa_put_profile(ent->profile);
+		ent->profile = aa_get_profile(profile);
+		cap_raise(ent->caps, cap);
+	}
+	put_cpu_var(audit_cache);
+
+	return aa_audit(type, profile, GFP_ATOMIC, &sa, audit_cb);
+}
+
+/**
+ * profile_capable - test if profile allows use of capability @cap
+ * @profile: profile being enforced    (NOT NULL, NOT unconfined)
+ * @cap: capability to test if allowed
+ *
+ * Returns: 0 if allowed else -EPERM
+ */
+static int profile_capable(struct aa_profile *profile, int cap)
+{
+	return cap_raised(profile->caps.allow, cap) ? 0 : -EPERM;
+}
+
+/**
+ * aa_capable - test permission to use capability
+ * @profile: profile being tested against (NOT NULL)
+ * @cap: capability to be tested
+ * @audit: whether an audit record should be generated
+ *
+ * Look up capability in profile capability set.
+ *
+ * Returns: 0 on success, or else an error code.
+ */
+int aa_capable(struct aa_profile *profile, int cap, int audit)
+{
+	int error = profile_capable(profile, cap);
+
+	if (!audit) {
+		if (COMPLAIN_MODE(profile))
+			return complain_error(error);
+		return error;
+	}
+
+	return audit_caps(profile, cap, error);
+}

security/apparmor/context.c

@@ -0,0 +1,222 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor functions used to manipulate object security
+ * contexts.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ *
+ * AppArmor sets confinement on every task, via the the aa_task_cxt and
+ * the aa_task_cxt.profile, both of which are required and are not allowed
+ * to be NULL.  The aa_task_cxt is not reference counted and is unique
+ * to each cred (which is reference count).  The profile pointed to by
+ * the task_cxt is reference counted.
+ *
+ * TODO
+ * If a task uses change_hat it currently does not return to the old
+ * cred or task context but instead creates a new one.  Ideally the task
+ * should return to the previous cred if it has not been modified.
+ *
+ */
+
+#include "include/context.h"
+#include "include/policy.h"
+
+/**
+ * aa_alloc_task_context - allocate a new task_cxt
+ * @flags: gfp flags for allocation
+ *
+ * Returns: allocated buffer or NULL on failure
+ */
+struct aa_task_cxt *aa_alloc_task_context(gfp_t flags)
+{
+	return kzalloc(sizeof(struct aa_task_cxt), flags);
+}
+
+/**
+ * aa_free_task_context - free a task_cxt
+ * @cxt: task_cxt to free (MAYBE NULL)
+ */
+void aa_free_task_context(struct aa_task_cxt *cxt)
+{
+	if (cxt) {
+		aa_put_profile(cxt->profile);
+		aa_put_profile(cxt->previous);
+		aa_put_profile(cxt->onexec);
+
+		kzfree(cxt);
+	}
+}
+
+/**
+ * aa_dup_task_context - duplicate a task context, incrementing reference counts
+ * @new: a blank task context      (NOT NULL)
+ * @old: the task context to copy  (NOT NULL)
+ */
+void aa_dup_task_context(struct aa_task_cxt *new, const struct aa_task_cxt *old)
+{
+	*new = *old;
+	aa_get_profile(new->profile);
+	aa_get_profile(new->previous);
+	aa_get_profile(new->onexec);
+}
+
+/**
+ * aa_get_task_profile - Get another task's profile
+ * @task: task to query  (NOT NULL)
+ *
+ * Returns: counted reference to @task's profile
+ */
+struct aa_profile *aa_get_task_profile(struct task_struct *task)
+{
+	struct aa_profile *p;
+
+	rcu_read_lock();
+	p = aa_get_profile(__aa_task_profile(task));
+	rcu_read_unlock();
+
+	return p;
+}
+
+/**
+ * aa_replace_current_profile - replace the current tasks profiles
+ * @profile: new profile  (NOT NULL)
+ *
+ * Returns: 0 or error on failure
+ */
+int aa_replace_current_profile(struct aa_profile *profile)
+{
+	struct aa_task_cxt *cxt = current_cxt();
+	struct cred *new;
+	BUG_ON(!profile);
+
+	if (cxt->profile == profile)
+		return 0;
+
+	new  = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	cxt = cred_cxt(new);
+	if (unconfined(profile) || (cxt->profile->ns != profile->ns))
+		/* if switching to unconfined or a different profile namespace
+		 * clear out context state
+		 */
+		aa_clear_task_cxt_trans(cxt);
+
+	/* be careful switching cxt->profile, when racing replacement it
+	 * is possible that cxt->profile->replacedby->profile is the reference
+	 * keeping @profile valid, so make sure to get its reference before
+	 * dropping the reference on cxt->profile */
+	aa_get_profile(profile);
+	aa_put_profile(cxt->profile);
+	cxt->profile = profile;
+
+	commit_creds(new);
+	return 0;
+}
+
+/**
+ * aa_set_current_onexec - set the tasks change_profile to happen onexec
+ * @profile: system profile to set at exec  (MAYBE NULL to clear value)
+ *
+ * Returns: 0 or error on failure
+ */
+int aa_set_current_onexec(struct aa_profile *profile)
+{
+	struct aa_task_cxt *cxt;
+	struct cred *new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	cxt = cred_cxt(new);
+	aa_get_profile(profile);
+	aa_put_profile(cxt->onexec);
+	cxt->onexec = profile;
+
+	commit_creds(new);
+	return 0;
+}
+
+/**
+ * aa_set_current_hat - set the current tasks hat
+ * @profile: profile to set as the current hat  (NOT NULL)
+ * @token: token value that must be specified to change from the hat
+ *
+ * Do switch of tasks hat.  If the task is currently in a hat
+ * validate the token to match.
+ *
+ * Returns: 0 or error on failure
+ */
+int aa_set_current_hat(struct aa_profile *profile, u64 token)
+{
+	struct aa_task_cxt *cxt;
+	struct cred *new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+	BUG_ON(!profile);
+
+	cxt = cred_cxt(new);
+	if (!cxt->previous) {
+		/* transfer refcount */
+		cxt->previous = cxt->profile;
+		cxt->token = token;
+	} else if (cxt->token == token) {
+		aa_put_profile(cxt->profile);
+	} else {
+		/* previous_profile && cxt->token != token */
+		abort_creds(new);
+		return -EACCES;
+	}
+	cxt->profile = aa_get_newest_profile(profile);
+	/* clear exec on switching context */
+	aa_put_profile(cxt->onexec);
+	cxt->onexec = NULL;
+
+	commit_creds(new);
+	return 0;
+}
+
+/**
+ * aa_restore_previous_profile - exit from hat context restoring the profile
+ * @token: the token that must be matched to exit hat context
+ *
+ * Attempt to return out of a hat to the previous profile.  The token
+ * must match the stored token value.
+ *
+ * Returns: 0 or error of failure
+ */
+int aa_restore_previous_profile(u64 token)
+{
+	struct aa_task_cxt *cxt;
+	struct cred *new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	cxt = cred_cxt(new);
+	if (cxt->token != token) {
+		abort_creds(new);
+		return -EACCES;
+	}
+	/* ignore restores when there is no saved profile */
+	if (!cxt->previous) {
+		abort_creds(new);
+		return 0;
+	}
+
+	aa_put_profile(cxt->profile);
+	cxt->profile = aa_get_newest_profile(cxt->previous);
+	BUG_ON(!cxt->profile);
+	/* clear exec && prev information when restoring to previous context */
+	aa_clear_task_cxt_trans(cxt);
+
+	commit_creds(new);
+	return 0;
+}

security/apparmor/crypto.c

@@ -0,0 +1,95 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy loading interface function definitions.
+ *
+ * Copyright 2013 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * Fns to provide a checksum of policy that has been loaded this can be
+ * compared to userspace policy compiles to check loaded policy is what
+ * it should be.
+ */
+
+#include <crypto/hash.h>
+
+#include "include/apparmor.h"
+#include "include/crypto.h"
+
+static unsigned int apparmor_hash_size;
+
+static struct crypto_shash *apparmor_tfm;
+
+unsigned int aa_hash_size(void)
+{
+	return apparmor_hash_size;
+}
+
+int aa_calc_profile_hash(struct aa_profile *profile, u32 version, void *start,
+			 size_t len)
+{
+	struct {
+		struct shash_desc shash;
+		char ctx[crypto_shash_descsize(apparmor_tfm)];
+	} desc;
+	int error = -ENOMEM;
+	u32 le32_version = cpu_to_le32(version);
+
+	if (!apparmor_tfm)
+		return 0;
+
+	profile->hash = kzalloc(apparmor_hash_size, GFP_KERNEL);
+	if (!profile->hash)
+		goto fail;
+
+	desc.shash.tfm = apparmor_tfm;
+	desc.shash.flags = 0;
+
+	error = crypto_shash_init(&desc.shash);
+	if (error)
+		goto fail;
+	error = crypto_shash_update(&desc.shash, (u8 *) &le32_version, 4);
+	if (error)
+		goto fail;
+	error = crypto_shash_update(&desc.shash, (u8 *) start, len);
+	if (error)
+		goto fail;
+	error = crypto_shash_final(&desc.shash, profile->hash);
+	if (error)
+		goto fail;
+
+	return 0;
+
+fail:
+	kfree(profile->hash);
+	profile->hash = NULL;
+
+	return error;
+}
+
+static int __init init_profile_hash(void)
+{
+	struct crypto_shash *tfm;
+
+	if (!apparmor_initialized)
+		return 0;
+
+	tfm = crypto_alloc_shash("sha1", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm)) {
+		int error = PTR_ERR(tfm);
+		AA_ERROR("failed to setup profile sha1 hashing: %d\n", error);
+		return error;
+	}
+	apparmor_tfm = tfm;
+	apparmor_hash_size = crypto_shash_digestsize(apparmor_tfm);
+
+	aa_info_message("AppArmor sha1 policy hashing enabled");
+
+	return 0;
+}
+
+late_initcall(init_profile_hash);

security/apparmor/domain.c

@@ -0,0 +1,854 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy attachment and domain transitions
+ *
+ * Copyright (C) 2002-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/errno.h>
+#include <linux/fdtable.h>
+#include <linux/file.h>
+#include <linux/mount.h>
+#include <linux/syscalls.h>
+#include <linux/tracehook.h>
+#include <linux/personality.h>
+
+#include "include/audit.h"
+#include "include/apparmorfs.h"
+#include "include/context.h"
+#include "include/domain.h"
+#include "include/file.h"
+#include "include/ipc.h"
+#include "include/match.h"
+#include "include/path.h"
+#include "include/policy.h"
+
+/**
+ * aa_free_domain_entries - free entries in a domain table
+ * @domain: the domain table to free  (MAYBE NULL)
+ */
+void aa_free_domain_entries(struct aa_domain *domain)
+{
+	int i;
+	if (domain) {
+		if (!domain->table)
+			return;
+
+		for (i = 0; i < domain->size; i++)
+			kzfree(domain->table[i]);
+		kzfree(domain->table);
+		domain->table = NULL;
+	}
+}
+
+/**
+ * may_change_ptraced_domain - check if can change profile on ptraced task
+ * @to_profile: profile to change to  (NOT NULL)
+ *
+ * Check if current is ptraced and if so if the tracing task is allowed
+ * to trace the new domain
+ *
+ * Returns: %0 or error if change not allowed
+ */
+static int may_change_ptraced_domain(struct aa_profile *to_profile)
+{
+	struct task_struct *tracer;
+	struct aa_profile *tracerp = NULL;
+	int error = 0;
+
+	rcu_read_lock();
+	tracer = ptrace_parent(current);
+	if (tracer)
+		/* released below */
+		tracerp = aa_get_task_profile(tracer);
+
+	/* not ptraced */
+	if (!tracer || unconfined(tracerp))
+		goto out;
+
+	error = aa_may_ptrace(tracerp, to_profile, PTRACE_MODE_ATTACH);
+
+out:
+	rcu_read_unlock();
+	aa_put_profile(tracerp);
+
+	return error;
+}
+
+/**
+ * change_profile_perms - find permissions for change_profile
+ * @profile: the current profile  (NOT NULL)
+ * @ns: the namespace being switched to  (NOT NULL)
+ * @name: the name of the profile to change to  (NOT NULL)
+ * @request: requested perms
+ * @start: state to start matching in
+ *
+ * Returns: permission set
+ */
+static struct file_perms change_profile_perms(struct aa_profile *profile,
+					      struct aa_namespace *ns,
+					      const char *name, u32 request,
+					      unsigned int start)
+{
+	struct file_perms perms;
+	struct path_cond cond = { };
+	unsigned int state;
+
+	if (unconfined(profile)) {
+		perms.allow = AA_MAY_CHANGE_PROFILE | AA_MAY_ONEXEC;
+		perms.audit = perms.quiet = perms.kill = 0;
+		return perms;
+	} else if (!profile->file.dfa) {
+		return nullperms;
+	} else if ((ns == profile->ns)) {
+		/* try matching against rules with out namespace prepended */
+		aa_str_perms(profile->file.dfa, start, name, &cond, &perms);
+		if (COMBINED_PERM_MASK(perms) & request)
+			return perms;
+	}
+
+	/* try matching with namespace name and then profile */
+	state = aa_dfa_match(profile->file.dfa, start, ns->base.name);
+	state = aa_dfa_match_len(profile->file.dfa, state, ":", 1);
+	aa_str_perms(profile->file.dfa, state, name, &cond, &perms);
+
+	return perms;
+}
+
+/**
+ * __attach_match_ - find an attachment match
+ * @name - to match against  (NOT NULL)
+ * @head - profile list to walk  (NOT NULL)
+ *
+ * Do a linear search on the profiles in the list.  There is a matching
+ * preference where an exact match is preferred over a name which uses
+ * expressions to match, and matching expressions with the greatest
+ * xmatch_len are preferred.
+ *
+ * Requires: @head not be shared or have appropriate locks held
+ *
+ * Returns: profile or NULL if no match found
+ */
+static struct aa_profile *__attach_match(const char *name,
+					 struct list_head *head)
+{
+	int len = 0;
+	struct aa_profile *profile, *candidate = NULL;
+
+	list_for_each_entry_rcu(profile, head, base.list) {
+		if (profile->flags & PFLAG_NULL)
+			continue;
+		if (profile->xmatch && profile->xmatch_len > len) {
+			unsigned int state = aa_dfa_match(profile->xmatch,
+							  DFA_START, name);
+			u32 perm = dfa_user_allow(profile->xmatch, state);
+			/* any accepting state means a valid match. */
+			if (perm & MAY_EXEC) {
+				candidate = profile;
+				len = profile->xmatch_len;
+			}
+		} else if (!strcmp(profile->base.name, name))
+			/* exact non-re match, no more searching required */
+			return profile;
+	}
+
+	return candidate;
+}
+
+/**
+ * find_attach - do attachment search for unconfined processes
+ * @ns: the current namespace  (NOT NULL)
+ * @list: list to search  (NOT NULL)
+ * @name: the executable name to match against  (NOT NULL)
+ *
+ * Returns: profile or NULL if no match found
+ */
+static struct aa_profile *find_attach(struct aa_namespace *ns,
+				      struct list_head *list, const char *name)
+{
+	struct aa_profile *profile;
+
+	rcu_read_lock();
+	profile = aa_get_profile(__attach_match(name, list));
+	rcu_read_unlock();
+
+	return profile;
+}
+
+/**
+ * separate_fqname - separate the namespace and profile names
+ * @fqname: the fqname name to split  (NOT NULL)
+ * @ns_name: the namespace name if it exists  (NOT NULL)
+ *
+ * This is the xtable equivalent routine of aa_split_fqname.  It finds the
+ * split in an xtable fqname which contains an embedded \0 instead of a :
+ * if a namespace is specified.  This is done so the xtable is constant and
+ * isn't re-split on every lookup.
+ *
+ * Either the profile or namespace name may be optional but if the namespace
+ * is specified the profile name termination must be present.  This results
+ * in the following possible encodings:
+ * profile_name\0
+ * :ns_name\0profile_name\0
+ * :ns_name\0\0
+ *
+ * NOTE: the xtable fqname is pre-validated at load time in unpack_trans_table
+ *
+ * Returns: profile name if it is specified else NULL
+ */
+static const char *separate_fqname(const char *fqname, const char **ns_name)
+{
+	const char *name;
+
+	if (fqname[0] == ':') {
+		/* In this case there is guaranteed to be two \0 terminators
+		 * in the string.  They are verified at load time by
+		 * by unpack_trans_table
+		 */
+		*ns_name = fqname + 1;		/* skip : */
+		name = *ns_name + strlen(*ns_name) + 1;
+		if (!*name)
+			name = NULL;
+	} else {
+		*ns_name = NULL;
+		name = fqname;
+	}
+
+	return name;
+}
+
+static const char *next_name(int xtype, const char *name)
+{
+	return NULL;
+}
+
+/**
+ * x_table_lookup - lookup an x transition name via transition table
+ * @profile: current profile (NOT NULL)
+ * @xindex: index into x transition table
+ *
+ * Returns: refcounted profile, or NULL on failure (MAYBE NULL)
+ */
+static struct aa_profile *x_table_lookup(struct aa_profile *profile, u32 xindex)
+{
+	struct aa_profile *new_profile = NULL;
+	struct aa_namespace *ns = profile->ns;
+	u32 xtype = xindex & AA_X_TYPE_MASK;
+	int index = xindex & AA_X_INDEX_MASK;
+	const char *name;
+
+	/* index is guaranteed to be in range, validated at load time */
+	for (name = profile->file.trans.table[index]; !new_profile && name;
+	     name = next_name(xtype, name)) {
+		struct aa_namespace *new_ns;
+		const char *xname = NULL;
+
+		new_ns = NULL;
+		if (xindex & AA_X_CHILD) {
+			/* release by caller */
+			new_profile = aa_find_child(profile, name);
+			continue;
+		} else if (*name == ':') {
+			/* switching namespace */
+			const char *ns_name;
+			xname = name = separate_fqname(name, &ns_name);
+			if (!xname)
+				/* no name so use profile name */
+				xname = profile->base.hname;
+			if (*ns_name == '@') {
+				/* TODO: variable support */
+				;
+			}
+			/* released below */
+			new_ns = aa_find_namespace(ns, ns_name);
+			if (!new_ns)
+				continue;
+		} else if (*name == '@') {
+			/* TODO: variable support */
+			continue;
+		} else {
+			/* basic namespace lookup */
+			xname = name;
+		}
+
+		/* released by caller */
+		new_profile = aa_lookup_profile(new_ns ? new_ns : ns, xname);
+		aa_put_namespace(new_ns);
+	}
+
+	/* released by caller */
+	return new_profile;
+}
+
+/**
+ * x_to_profile - get target profile for a given xindex
+ * @profile: current profile  (NOT NULL)
+ * @name: name to lookup (NOT NULL)
+ * @xindex: index into x transition table
+ *
+ * find profile for a transition index
+ *
+ * Returns: refcounted profile or NULL if not found available
+ */
+static struct aa_profile *x_to_profile(struct aa_profile *profile,
+				       const char *name, u32 xindex)
+{
+	struct aa_profile *new_profile = NULL;
+	struct aa_namespace *ns = profile->ns;
+	u32 xtype = xindex & AA_X_TYPE_MASK;
+
+	switch (xtype) {
+	case AA_X_NONE:
+		/* fail exec unless ix || ux fallback - handled by caller */
+		return NULL;
+	case AA_X_NAME:
+		if (xindex & AA_X_CHILD)
+			/* released by caller */
+			new_profile = find_attach(ns, &profile->base.profiles,
+						  name);
+		else
+			/* released by caller */
+			new_profile = find_attach(ns, &ns->base.profiles,
+						  name);
+		break;
+	case AA_X_TABLE:
+		/* released by caller */
+		new_profile = x_table_lookup(profile, xindex);
+		break;
+	}
+
+	/* released by caller */
+	return new_profile;
+}
+
+/**
+ * apparmor_bprm_set_creds - set the new creds on the bprm struct
+ * @bprm: binprm for the exec  (NOT NULL)
+ *
+ * Returns: %0 or error on failure
+ */
+int apparmor_bprm_set_creds(struct linux_binprm *bprm)
+{
+	struct aa_task_cxt *cxt;
+	struct aa_profile *profile, *new_profile = NULL;
+	struct aa_namespace *ns;
+	char *buffer = NULL;
+	unsigned int state;
+	struct file_perms perms = {};
+	struct path_cond cond = {
+		file_inode(bprm->file)->i_uid,
+		file_inode(bprm->file)->i_mode
+	};
+	const char *name = NULL, *target = NULL, *info = NULL;
+	int error = cap_bprm_set_creds(bprm);
+	if (error)
+		return error;
+
+	if (bprm->cred_prepared)
+		return 0;
+
+	cxt = cred_cxt(bprm->cred);
+	BUG_ON(!cxt);
+
+	profile = aa_get_newest_profile(cxt->profile);
+	/*
+	 * get the namespace from the replacement profile as replacement
+	 * can change the namespace
+	 */
+	ns = profile->ns;
+	state = profile->file.start;
+
+	/* buffer freed below, name is pointer into buffer */
+	error = aa_path_name(&bprm->file->f_path, profile->path_flags, &buffer,
+			     &name, &info);
+	if (error) {
+		if (unconfined(profile) ||
+		    (profile->flags & PFLAG_IX_ON_NAME_ERROR))
+			error = 0;
+		name = bprm->filename;
+		goto audit;
+	}
+
+	/* Test for onexec first as onexec directives override other
+	 * x transitions.
+	 */
+	if (unconfined(profile)) {
+		/* unconfined task */
+		if (cxt->onexec)
+			/* change_profile on exec already been granted */
+			new_profile = aa_get_profile(cxt->onexec);
+		else
+			new_profile = find_attach(ns, &ns->base.profiles, name);
+		if (!new_profile)
+			goto cleanup;
+		/*
+		 * NOTE: Domain transitions from unconfined are allowed
+		 * even when no_new_privs is set because this aways results
+		 * in a further reduction of permissions.
+		 */
+		goto apply;
+	}
+
+	/* find exec permissions for name */
+	state = aa_str_perms(profile->file.dfa, state, name, &cond, &perms);
+	if (cxt->onexec) {
+		struct file_perms cp;
+		info = "change_profile onexec";
+		if (!(perms.allow & AA_MAY_ONEXEC))
+			goto audit;
+
+		/* test if this exec can be paired with change_profile onexec.
+		 * onexec permission is linked to exec with a standard pairing
+		 * exec\0change_profile
+		 */
+		state = aa_dfa_null_transition(profile->file.dfa, state);
+		cp = change_profile_perms(profile, cxt->onexec->ns,
+					  cxt->onexec->base.name,
+					  AA_MAY_ONEXEC, state);
+
+		if (!(cp.allow & AA_MAY_ONEXEC))
+			goto audit;
+		new_profile = aa_get_newest_profile(cxt->onexec);
+		goto apply;
+	}
+
+	if (perms.allow & MAY_EXEC) {
+		/* exec permission determine how to transition */
+		new_profile = x_to_profile(profile, name, perms.xindex);
+		if (!new_profile) {
+			if (perms.xindex & AA_X_INHERIT) {
+				/* (p|c|n)ix - don't change profile but do
+				 * use the newest version, which was picked
+				 * up above when getting profile
+				 */
+				info = "ix fallback";
+				new_profile = aa_get_profile(profile);
+				goto x_clear;
+			} else if (perms.xindex & AA_X_UNCONFINED) {
+				new_profile = aa_get_newest_profile(ns->unconfined);
+				info = "ux fallback";
+			} else {
+				error = -ENOENT;
+				info = "profile not found";
+				/* remove MAY_EXEC to audit as failure */
+				perms.allow &= ~MAY_EXEC;
+			}
+		}
+	} else if (COMPLAIN_MODE(profile)) {
+		/* no exec permission - are we in learning mode */
+		new_profile = aa_new_null_profile(profile, 0);
+		if (!new_profile) {
+			error = -ENOMEM;
+			info = "could not create null profile";
+		} else {
+			error = -EACCES;
+			target = new_profile->base.hname;
+		}
+		perms.xindex |= AA_X_UNSAFE;
+	} else
+		/* fail exec */
+		error = -EACCES;
+
+	/*
+	 * Policy has specified a domain transition, if no_new_privs then
+	 * fail the exec.
+	 */
+	if (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS) {
+		aa_put_profile(new_profile);
+		error = -EPERM;
+		goto cleanup;
+	}
+
+	if (!new_profile)
+		goto audit;
+
+	if (bprm->unsafe & LSM_UNSAFE_SHARE) {
+		/* FIXME: currently don't mediate shared state */
+		;
+	}
+
+	if (bprm->unsafe & (LSM_UNSAFE_PTRACE | LSM_UNSAFE_PTRACE_CAP)) {
+		error = may_change_ptraced_domain(new_profile);
+		if (error) {
+			aa_put_profile(new_profile);
+			goto audit;
+		}
+	}
+
+	/* Determine if secure exec is needed.
+	 * Can be at this point for the following reasons:
+	 * 1. unconfined switching to confined
+	 * 2. confined switching to different confinement
+	 * 3. confined switching to unconfined
+	 *
+	 * Cases 2 and 3 are marked as requiring secure exec
+	 * (unless policy specified "unsafe exec")
+	 *
+	 * bprm->unsafe is used to cache the AA_X_UNSAFE permission
+	 * to avoid having to recompute in secureexec
+	 */
+	if (!(perms.xindex & AA_X_UNSAFE)) {
+		AA_DEBUG("scrubbing environment variables for %s profile=%s\n",
+			 name, new_profile->base.hname);
+		bprm->unsafe |= AA_SECURE_X_NEEDED;
+	}
+apply:
+	target = new_profile->base.hname;
+	/* when transitioning profiles clear unsafe personality bits */
+	bprm->per_clear |= PER_CLEAR_ON_SETID;
+
+x_clear:
+	aa_put_profile(cxt->profile);
+	/* transfer new profile reference will be released when cxt is freed */
+	cxt->profile = new_profile;
+
+	/* clear out all temporary/transitional state from the context */
+	aa_clear_task_cxt_trans(cxt);
+
+audit:
+	error = aa_audit_file(profile, &perms, GFP_KERNEL, OP_EXEC, MAY_EXEC,
+			      name, target, cond.uid, info, error);
+
+cleanup:
+	aa_put_profile(profile);
+	kfree(buffer);
+
+	return error;
+}
+
+/**
+ * apparmor_bprm_secureexec - determine if secureexec is needed
+ * @bprm: binprm for exec  (NOT NULL)
+ *
+ * Returns: %1 if secureexec is needed else %0
+ */
+int apparmor_bprm_secureexec(struct linux_binprm *bprm)
+{
+	int ret = cap_bprm_secureexec(bprm);
+
+	/* the decision to use secure exec is computed in set_creds
+	 * and stored in bprm->unsafe.
+	 */
+	if (!ret && (bprm->unsafe & AA_SECURE_X_NEEDED))
+		ret = 1;
+
+	return ret;
+}
+
+/**
+ * apparmor_bprm_committing_creds - do task cleanup on committing new creds
+ * @bprm: binprm for the exec  (NOT NULL)
+ */
+void apparmor_bprm_committing_creds(struct linux_binprm *bprm)
+{
+	struct aa_profile *profile = __aa_current_profile();
+	struct aa_task_cxt *new_cxt = cred_cxt(bprm->cred);
+
+	/* bail out if unconfined or not changing profile */
+	if ((new_cxt->profile == profile) ||
+	    (unconfined(new_cxt->profile)))
+		return;
+
+	current->pdeath_signal = 0;
+
+	/* reset soft limits and set hard limits for the new profile */
+	__aa_transition_rlimits(profile, new_cxt->profile);
+}
+
+/**
+ * apparmor_bprm_commited_cred - do cleanup after new creds committed
+ * @bprm: binprm for the exec  (NOT NULL)
+ */
+void apparmor_bprm_committed_creds(struct linux_binprm *bprm)
+{
+	/* TODO: cleanup signals - ipc mediation */
+	return;
+}
+
+/*
+ * Functions for self directed profile change
+ */
+
+/**
+ * new_compound_name - create an hname with @n2 appended to @n1
+ * @n1: base of hname  (NOT NULL)
+ * @n2: name to append (NOT NULL)
+ *
+ * Returns: new name or NULL on error
+ */
+static char *new_compound_name(const char *n1, const char *n2)
+{
+	char *name = kmalloc(strlen(n1) + strlen(n2) + 3, GFP_KERNEL);
+	if (name)
+		sprintf(name, "%s//%s", n1, n2);
+	return name;
+}
+
+/**
+ * aa_change_hat - change hat to/from subprofile
+ * @hats: vector of hat names to try changing into (MAYBE NULL if @count == 0)
+ * @count: number of hat names in @hats
+ * @token: magic value to validate the hat change
+ * @permtest: true if this is just a permission test
+ *
+ * Change to the first profile specified in @hats that exists, and store
+ * the @hat_magic in the current task context.  If the count == 0 and the
+ * @token matches that stored in the current task context, return to the
+ * top level profile.
+ *
+ * Returns %0 on success, error otherwise.
+ */
+int aa_change_hat(const char *hats[], int count, u64 token, bool permtest)
+{
+	const struct cred *cred;
+	struct aa_task_cxt *cxt;
+	struct aa_profile *profile, *previous_profile, *hat = NULL;
+	char *name = NULL;
+	int i;
+	struct file_perms perms = {};
+	const char *target = NULL, *info = NULL;
+	int error = 0;
+
+	/*
+	 * Fail explicitly requested domain transitions if no_new_privs.
+	 * There is no exception for unconfined as change_hat is not
+	 * available.
+	 */
+	if (task_no_new_privs(current))
+		return -EPERM;
+
+	/* released below */
+	cred = get_current_cred();
+	cxt = cred_cxt(cred);
+	profile = aa_cred_profile(cred);
+	previous_profile = cxt->previous;
+
+	if (unconfined(profile)) {
+		info = "unconfined";
+		error = -EPERM;
+		goto audit;
+	}
+
+	if (count) {
+		/* attempting to change into a new hat or switch to a sibling */
+		struct aa_profile *root;
+		if (PROFILE_IS_HAT(profile))
+			root = aa_get_profile_rcu(&profile->parent);
+		else
+			root = aa_get_profile(profile);
+
+		/* find first matching hat */
+		for (i = 0; i < count && !hat; i++)
+			/* released below */
+			hat = aa_find_child(root, hats[i]);
+		if (!hat) {
+			if (!COMPLAIN_MODE(root) || permtest) {
+				if (list_empty(&root->base.profiles))
+					error = -ECHILD;
+				else
+					error = -ENOENT;
+				aa_put_profile(root);
+				goto out;
+			}
+
+			/*
+			 * In complain mode and failed to match any hats.
+			 * Audit the failure is based off of the first hat
+			 * supplied.  This is done due how userspace
+			 * interacts with change_hat.
+			 *
+			 * TODO: Add logging of all failed hats
+			 */
+
+			/* freed below */
+			name = new_compound_name(root->base.hname, hats[0]);
+			aa_put_profile(root);
+			target = name;
+			/* released below */
+			hat = aa_new_null_profile(profile, 1);
+			if (!hat) {
+				info = "failed null profile create";
+				error = -ENOMEM;
+				goto audit;
+			}
+		} else {
+			aa_put_profile(root);
+			target = hat->base.hname;
+			if (!PROFILE_IS_HAT(hat)) {
+				info = "target not hat";
+				error = -EPERM;
+				goto audit;
+			}
+		}
+
+		error = may_change_ptraced_domain(hat);
+		if (error) {
+			info = "ptraced";
+			error = -EPERM;
+			goto audit;
+		}
+
+		if (!permtest) {
+			error = aa_set_current_hat(hat, token);
+			if (error == -EACCES)
+				/* kill task in case of brute force attacks */
+				perms.kill = AA_MAY_CHANGEHAT;
+			else if (name && !error)
+				/* reset error for learning of new hats */
+				error = -ENOENT;
+		}
+	} else if (previous_profile) {
+		/* Return to saved profile.  Kill task if restore fails
+		 * to avoid brute force attacks
+		 */
+		target = previous_profile->base.hname;
+		error = aa_restore_previous_profile(token);
+		perms.kill = AA_MAY_CHANGEHAT;
+	} else
+		/* ignore restores when there is no saved profile */
+		goto out;
+
+audit:
+	if (!permtest)
+		error = aa_audit_file(profile, &perms, GFP_KERNEL,
+				      OP_CHANGE_HAT, AA_MAY_CHANGEHAT, NULL,
+				      target, GLOBAL_ROOT_UID, info, error);
+
+out:
+	aa_put_profile(hat);
+	kfree(name);
+	put_cred(cred);
+
+	return error;
+}
+
+/**
+ * aa_change_profile - perform a one-way profile transition
+ * @ns_name: name of the profile namespace to change to (MAYBE NULL)
+ * @hname: name of profile to change to (MAYBE NULL)
+ * @onexec: whether this transition is to take place immediately or at exec
+ * @permtest: true if this is just a permission test
+ *
+ * Change to new profile @name.  Unlike with hats, there is no way
+ * to change back.  If @name isn't specified the current profile name is
+ * used.
+ * If @onexec then the transition is delayed until
+ * the next exec.
+ *
+ * Returns %0 on success, error otherwise.
+ */
+int aa_change_profile(const char *ns_name, const char *hname, bool onexec,
+		      bool permtest)
+{
+	const struct cred *cred;
+	struct aa_profile *profile, *target = NULL;
+	struct aa_namespace *ns = NULL;
+	struct file_perms perms = {};
+	const char *name = NULL, *info = NULL;
+	int op, error = 0;
+	u32 request;
+
+	if (!hname && !ns_name)
+		return -EINVAL;
+
+	if (onexec) {
+		request = AA_MAY_ONEXEC;
+		op = OP_CHANGE_ONEXEC;
+	} else {
+		request = AA_MAY_CHANGE_PROFILE;
+		op = OP_CHANGE_PROFILE;
+	}
+
+	cred = get_current_cred();
+	profile = aa_cred_profile(cred);
+
+	/*
+	 * Fail explicitly requested domain transitions if no_new_privs
+	 * and not unconfined.
+	 * Domain transitions from unconfined are allowed even when
+	 * no_new_privs is set because this aways results in a reduction
+	 * of permissions.
+	 */
+	if (task_no_new_privs(current) && !unconfined(profile)) {
+		put_cred(cred);
+		return -EPERM;
+	}
+
+	if (ns_name) {
+		/* released below */
+		ns = aa_find_namespace(profile->ns, ns_name);
+		if (!ns) {
+			/* we don't create new namespace in complain mode */
+			name = ns_name;
+			info = "namespace not found";
+			error = -ENOENT;
+			goto audit;
+		}
+	} else
+		/* released below */
+		ns = aa_get_namespace(profile->ns);
+
+	/* if the name was not specified, use the name of the current profile */
+	if (!hname) {
+		if (unconfined(profile))
+			hname = ns->unconfined->base.hname;
+		else
+			hname = profile->base.hname;
+	}
+
+	perms = change_profile_perms(profile, ns, hname, request,
+				     profile->file.start);
+	if (!(perms.allow & request)) {
+		error = -EACCES;
+		goto audit;
+	}
+
+	/* released below */
+	target = aa_lookup_profile(ns, hname);
+	if (!target) {
+		info = "profile not found";
+		error = -ENOENT;
+		if (permtest || !COMPLAIN_MODE(profile))
+			goto audit;
+		/* released below */
+		target = aa_new_null_profile(profile, 0);
+		if (!target) {
+			info = "failed null profile create";
+			error = -ENOMEM;
+			goto audit;
+		}
+	}
+
+	/* check if tracing task is allowed to trace target domain */
+	error = may_change_ptraced_domain(target);
+	if (error) {
+		info = "ptrace prevents transition";
+		goto audit;
+	}
+
+	if (permtest)
+		goto audit;
+
+	if (onexec)
+		error = aa_set_current_onexec(target);
+	else
+		error = aa_replace_current_profile(target);
+
+audit:
+	if (!permtest)
+		error = aa_audit_file(profile, &perms, GFP_KERNEL, op, request,
+				      name, hname, GLOBAL_ROOT_UID, info, error);
+
+	aa_put_namespace(ns);
+	aa_put_profile(target);
+	put_cred(cred);
+
+	return error;
+}

security/apparmor/file.c

@@ -0,0 +1,458 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor mediation of files
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/file.h"
+#include "include/match.h"
+#include "include/path.h"
+#include "include/policy.h"
+
+struct file_perms nullperms;
+
+
+/**
+ * audit_file_mask - convert mask to permission string
+ * @buffer: buffer to write string to (NOT NULL)
+ * @mask: permission mask to convert
+ */
+static void audit_file_mask(struct audit_buffer *ab, u32 mask)
+{
+	char str[10];
+
+	char *m = str;
+
+	if (mask & AA_EXEC_MMAP)
+		*m++ = 'm';
+	if (mask & (MAY_READ | AA_MAY_META_READ))
+		*m++ = 'r';
+	if (mask & (MAY_WRITE | AA_MAY_META_WRITE | AA_MAY_CHMOD |
+		    AA_MAY_CHOWN))
+		*m++ = 'w';
+	else if (mask & MAY_APPEND)
+		*m++ = 'a';
+	if (mask & AA_MAY_CREATE)
+		*m++ = 'c';
+	if (mask & AA_MAY_DELETE)
+		*m++ = 'd';
+	if (mask & AA_MAY_LINK)
+		*m++ = 'l';
+	if (mask & AA_MAY_LOCK)
+		*m++ = 'k';
+	if (mask & MAY_EXEC)
+		*m++ = 'x';
+	*m = '\0';
+
+	audit_log_string(ab, str);
+}
+
+/**
+ * file_audit_cb - call back for file specific audit fields
+ * @ab: audit_buffer  (NOT NULL)
+ * @va: audit struct to audit values of  (NOT NULL)
+ */
+static void file_audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	kuid_t fsuid = current_fsuid();
+
+	if (sa->aad->fs.request & AA_AUDIT_FILE_MASK) {
+		audit_log_format(ab, " requested_mask=");
+		audit_file_mask(ab, sa->aad->fs.request);
+	}
+	if (sa->aad->fs.denied & AA_AUDIT_FILE_MASK) {
+		audit_log_format(ab, " denied_mask=");
+		audit_file_mask(ab, sa->aad->fs.denied);
+	}
+	if (sa->aad->fs.request & AA_AUDIT_FILE_MASK) {
+		audit_log_format(ab, " fsuid=%d",
+				 from_kuid(&init_user_ns, fsuid));
+		audit_log_format(ab, " ouid=%d",
+				 from_kuid(&init_user_ns, sa->aad->fs.ouid));
+	}
+
+	if (sa->aad->fs.target) {
+		audit_log_format(ab, " target=");
+		audit_log_untrustedstring(ab, sa->aad->fs.target);
+	}
+}
+
+/**
+ * aa_audit_file - handle the auditing of file operations
+ * @profile: the profile being enforced  (NOT NULL)
+ * @perms: the permissions computed for the request (NOT NULL)
+ * @gfp: allocation flags
+ * @op: operation being mediated
+ * @request: permissions requested
+ * @name: name of object being mediated (MAYBE NULL)
+ * @target: name of target (MAYBE NULL)
+ * @ouid: object uid
+ * @info: extra information message (MAYBE NULL)
+ * @error: 0 if operation allowed else failure error code
+ *
+ * Returns: %0 or error on failure
+ */
+int aa_audit_file(struct aa_profile *profile, struct file_perms *perms,
+		  gfp_t gfp, int op, u32 request, const char *name,
+		  const char *target, kuid_t ouid, const char *info, int error)
+{
+	int type = AUDIT_APPARMOR_AUTO;
+	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
+	sa.type = LSM_AUDIT_DATA_NONE;
+	sa.aad = &aad;
+	aad.op = op,
+	aad.fs.request = request;
+	aad.name = name;
+	aad.fs.target = target;
+	aad.fs.ouid = ouid;
+	aad.info = info;
+	aad.error = error;
+
+	if (likely(!sa.aad->error)) {
+		u32 mask = perms->audit;
+
+		if (unlikely(AUDIT_MODE(profile) == AUDIT_ALL))
+			mask = 0xffff;
+
+		/* mask off perms that are not being force audited */
+		sa.aad->fs.request &= mask;
+
+		if (likely(!sa.aad->fs.request))
+			return 0;
+		type = AUDIT_APPARMOR_AUDIT;
+	} else {
+		/* only report permissions that were denied */
+		sa.aad->fs.request = sa.aad->fs.request & ~perms->allow;
+
+		if (sa.aad->fs.request & perms->kill)
+			type = AUDIT_APPARMOR_KILL;
+
+		/* quiet known rejects, assumes quiet and kill do not overlap */
+		if ((sa.aad->fs.request & perms->quiet) &&
+		    AUDIT_MODE(profile) != AUDIT_NOQUIET &&
+		    AUDIT_MODE(profile) != AUDIT_ALL)
+			sa.aad->fs.request &= ~perms->quiet;
+
+		if (!sa.aad->fs.request)
+			return COMPLAIN_MODE(profile) ? 0 : sa.aad->error;
+	}
+
+	sa.aad->fs.denied = sa.aad->fs.request & ~perms->allow;
+	return aa_audit(type, profile, gfp, &sa, file_audit_cb);
+}
+
+/**
+ * map_old_perms - map old file perms layout to the new layout
+ * @old: permission set in old mapping
+ *
+ * Returns: new permission mapping
+ */
+static u32 map_old_perms(u32 old)
+{
+	u32 new = old & 0xf;
+	if (old & MAY_READ)
+		new |= AA_MAY_META_READ;
+	if (old & MAY_WRITE)
+		new |= AA_MAY_META_WRITE | AA_MAY_CREATE | AA_MAY_DELETE |
+			AA_MAY_CHMOD | AA_MAY_CHOWN;
+	if (old & 0x10)
+		new |= AA_MAY_LINK;
+	/* the old mapping lock and link_subset flags where overlaid
+	 * and use was determined by part of a pair that they were in
+	 */
+	if (old & 0x20)
+		new |= AA_MAY_LOCK | AA_LINK_SUBSET;
+	if (old & 0x40)	/* AA_EXEC_MMAP */
+		new |= AA_EXEC_MMAP;
+
+	return new;
+}
+
+/**
+ * compute_perms - convert dfa compressed perms to internal perms
+ * @dfa: dfa to compute perms for   (NOT NULL)
+ * @state: state in dfa
+ * @cond:  conditions to consider  (NOT NULL)
+ *
+ * TODO: convert from dfa + state to permission entry, do computation conversion
+ *       at load time.
+ *
+ * Returns: computed permission set
+ */
+static struct file_perms compute_perms(struct aa_dfa *dfa, unsigned int state,
+				       struct path_cond *cond)
+{
+	struct file_perms perms;
+
+	/* FIXME: change over to new dfa format
+	 * currently file perms are encoded in the dfa, new format
+	 * splits the permissions from the dfa.  This mapping can be
+	 * done at profile load
+	 */
+	perms.kill = 0;
+
+	if (uid_eq(current_fsuid(), cond->uid)) {
+		perms.allow = map_old_perms(dfa_user_allow(dfa, state));
+		perms.audit = map_old_perms(dfa_user_audit(dfa, state));
+		perms.quiet = map_old_perms(dfa_user_quiet(dfa, state));
+		perms.xindex = dfa_user_xindex(dfa, state);
+	} else {
+		perms.allow = map_old_perms(dfa_other_allow(dfa, state));
+		perms.audit = map_old_perms(dfa_other_audit(dfa, state));
+		perms.quiet = map_old_perms(dfa_other_quiet(dfa, state));
+		perms.xindex = dfa_other_xindex(dfa, state);
+	}
+	perms.allow |= AA_MAY_META_READ;
+
+	/* change_profile wasn't determined by ownership in old mapping */
+	if (ACCEPT_TABLE(dfa)[state] & 0x80000000)
+		perms.allow |= AA_MAY_CHANGE_PROFILE;
+	if (ACCEPT_TABLE(dfa)[state] & 0x40000000)
+		perms.allow |= AA_MAY_ONEXEC;
+
+	return perms;
+}
+
+/**
+ * aa_str_perms - find permission that match @name
+ * @dfa: to match against  (MAYBE NULL)
+ * @state: state to start matching in
+ * @name: string to match against dfa  (NOT NULL)
+ * @cond: conditions to consider for permission set computation  (NOT NULL)
+ * @perms: Returns - the permissions found when matching @name
+ *
+ * Returns: the final state in @dfa when beginning @start and walking @name
+ */
+unsigned int aa_str_perms(struct aa_dfa *dfa, unsigned int start,
+			  const char *name, struct path_cond *cond,
+			  struct file_perms *perms)
+{
+	unsigned int state;
+	if (!dfa) {
+		*perms = nullperms;
+		return DFA_NOMATCH;
+	}
+
+	state = aa_dfa_match(dfa, start, name);
+	*perms = compute_perms(dfa, state, cond);
+
+	return state;
+}
+
+/**
+ * is_deleted - test if a file has been completely unlinked
+ * @dentry: dentry of file to test for deletion  (NOT NULL)
+ *
+ * Returns: %1 if deleted else %0
+ */
+static inline bool is_deleted(struct dentry *dentry)
+{
+	if (d_unlinked(dentry) && dentry->d_inode->i_nlink == 0)
+		return 1;
+	return 0;
+}
+
+/**
+ * aa_path_perm - do permissions check & audit for @path
+ * @op: operation being checked
+ * @profile: profile being enforced  (NOT NULL)
+ * @path: path to check permissions of  (NOT NULL)
+ * @flags: any additional path flags beyond what the profile specifies
+ * @request: requested permissions
+ * @cond: conditional info for this request  (NOT NULL)
+ *
+ * Returns: %0 else error if access denied or other error
+ */
+int aa_path_perm(int op, struct aa_profile *profile, struct path *path,
+		 int flags, u32 request, struct path_cond *cond)
+{
+	char *buffer = NULL;
+	struct file_perms perms = {};
+	const char *name, *info = NULL;
+	int error;
+
+	flags |= profile->path_flags | (S_ISDIR(cond->mode) ? PATH_IS_DIR : 0);
+	error = aa_path_name(path, flags, &buffer, &name, &info);
+	if (error) {
+		if (error == -ENOENT && is_deleted(path->dentry)) {
+			/* Access to open files that are deleted are
+			 * give a pass (implicit delegation)
+			 */
+			error = 0;
+			info = NULL;
+			perms.allow = request;
+		}
+	} else {
+		aa_str_perms(profile->file.dfa, profile->file.start, name, cond,
+			     &perms);
+		if (request & ~perms.allow)
+			error = -EACCES;
+	}
+	error = aa_audit_file(profile, &perms, GFP_KERNEL, op, request, name,
+			      NULL, cond->uid, info, error);
+	kfree(buffer);
+
+	return error;
+}
+
+/**
+ * xindex_is_subset - helper for aa_path_link
+ * @link: link permission set
+ * @target: target permission set
+ *
+ * test target x permissions are equal OR a subset of link x permissions
+ * this is done as part of the subset test, where a hardlink must have
+ * a subset of permissions that the target has.
+ *
+ * Returns: %1 if subset else %0
+ */
+static inline bool xindex_is_subset(u32 link, u32 target)
+{
+	if (((link & ~AA_X_UNSAFE) != (target & ~AA_X_UNSAFE)) ||
+	    ((link & AA_X_UNSAFE) && !(target & AA_X_UNSAFE)))
+		return 0;
+
+	return 1;
+}
+
+/**
+ * aa_path_link - Handle hard link permission check
+ * @profile: the profile being enforced  (NOT NULL)
+ * @old_dentry: the target dentry  (NOT NULL)
+ * @new_dir: directory the new link will be created in  (NOT NULL)
+ * @new_dentry: the link being created  (NOT NULL)
+ *
+ * Handle the permission test for a link & target pair.  Permission
+ * is encoded as a pair where the link permission is determined
+ * first, and if allowed, the target is tested.  The target test
+ * is done from the point of the link match (not start of DFA)
+ * making the target permission dependent on the link permission match.
+ *
+ * The subset test if required forces that permissions granted
+ * on link are a subset of the permission granted to target.
+ *
+ * Returns: %0 if allowed else error
+ */
+int aa_path_link(struct aa_profile *profile, struct dentry *old_dentry,
+		 struct path *new_dir, struct dentry *new_dentry)
+{
+	struct path link = { new_dir->mnt, new_dentry };
+	struct path target = { new_dir->mnt, old_dentry };
+	struct path_cond cond = {
+		old_dentry->d_inode->i_uid,
+		old_dentry->d_inode->i_mode
+	};
+	char *buffer = NULL, *buffer2 = NULL;
+	const char *lname, *tname = NULL, *info = NULL;
+	struct file_perms lperms, perms;
+	u32 request = AA_MAY_LINK;
+	unsigned int state;
+	int error;
+
+	lperms = nullperms;
+
+	/* buffer freed below, lname is pointer in buffer */
+	error = aa_path_name(&link, profile->path_flags, &buffer, &lname,
+			     &info);
+	if (error)
+		goto audit;
+
+	/* buffer2 freed below, tname is pointer in buffer2 */
+	error = aa_path_name(&target, profile->path_flags, &buffer2, &tname,
+			     &info);
+	if (error)
+		goto audit;
+
+	error = -EACCES;
+	/* aa_str_perms - handles the case of the dfa being NULL */
+	state = aa_str_perms(profile->file.dfa, profile->file.start, lname,
+			     &cond, &lperms);
+
+	if (!(lperms.allow & AA_MAY_LINK))
+		goto audit;
+
+	/* test to see if target can be paired with link */
+	state = aa_dfa_null_transition(profile->file.dfa, state);
+	aa_str_perms(profile->file.dfa, state, tname, &cond, &perms);
+
+	/* force audit/quiet masks for link are stored in the second entry
+	 * in the link pair.
+	 */
+	lperms.audit = perms.audit;
+	lperms.quiet = perms.quiet;
+	lperms.kill = perms.kill;
+
+	if (!(perms.allow & AA_MAY_LINK)) {
+		info = "target restricted";
+		goto audit;
+	}
+
+	/* done if link subset test is not required */
+	if (!(perms.allow & AA_LINK_SUBSET))
+		goto done_tests;
+
+	/* Do link perm subset test requiring allowed permission on link are a
+	 * subset of the allowed permissions on target.
+	 */
+	aa_str_perms(profile->file.dfa, profile->file.start, tname, &cond,
+		     &perms);
+
+	/* AA_MAY_LINK is not considered in the subset test */
+	request = lperms.allow & ~AA_MAY_LINK;
+	lperms.allow &= perms.allow | AA_MAY_LINK;
+
+	request |= AA_AUDIT_FILE_MASK & (lperms.allow & ~perms.allow);
+	if (request & ~lperms.allow) {
+		goto audit;
+	} else if ((lperms.allow & MAY_EXEC) &&
+		   !xindex_is_subset(lperms.xindex, perms.xindex)) {
+		lperms.allow &= ~MAY_EXEC;
+		request |= MAY_EXEC;
+		info = "link not subset of target";
+		goto audit;
+	}
+
+done_tests:
+	error = 0;
+
+audit:
+	error = aa_audit_file(profile, &lperms, GFP_KERNEL, OP_LINK, request,
+			      lname, tname, cond.uid, info, error);
+	kfree(buffer);
+	kfree(buffer2);
+
+	return error;
+}
+
+/**
+ * aa_file_perm - do permission revalidation check & audit for @file
+ * @op: operation being checked
+ * @profile: profile being enforced   (NOT NULL)
+ * @file: file to revalidate access permissions on  (NOT NULL)
+ * @request: requested permissions
+ *
+ * Returns: %0 if access allowed else error
+ */
+int aa_file_perm(int op, struct aa_profile *profile, struct file *file,
+		 u32 request)
+{
+	struct path_cond cond = {
+		.uid = file_inode(file)->i_uid,
+		.mode = file_inode(file)->i_mode
+	};
+
+	return aa_path_perm(op, profile, &file->f_path, PATH_DELEGATE_DELETED,
+			    request, &cond);
+}

security/apparmor/include/apparmor.h

@@ -0,0 +1,120 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor basic global and lib definitions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __APPARMOR_H
+#define __APPARMOR_H
+
+#include <linux/slab.h>
+#include <linux/fs.h>
+
+#include "match.h"
+
+/*
+ * Class of mediation types in the AppArmor policy db
+ */
+#define AA_CLASS_ENTRY		0
+#define AA_CLASS_UNKNOWN	1
+#define AA_CLASS_FILE		2
+#define AA_CLASS_CAP		3
+#define AA_CLASS_NET		4
+#define AA_CLASS_RLIMITS	5
+#define AA_CLASS_DOMAIN		6
+
+#define AA_CLASS_LAST		AA_CLASS_DOMAIN
+
+/* Control parameters settable through module/boot flags */
+extern enum audit_mode aa_g_audit;
+extern bool aa_g_audit_header;
+extern bool aa_g_debug;
+extern bool aa_g_lock_policy;
+extern bool aa_g_logsyscall;
+extern bool aa_g_paranoid_load;
+extern unsigned int aa_g_path_max;
+
+/*
+ * DEBUG remains global (no per profile flag) since it is mostly used in sysctl
+ * which is not related to profile accesses.
+ */
+
+#define AA_DEBUG(fmt, args...)						\
+	do {								\
+		if (aa_g_debug && printk_ratelimit())			\
+			printk(KERN_DEBUG "AppArmor: " fmt, ##args);	\
+	} while (0)
+
+#define AA_ERROR(fmt, args...)						\
+	do {								\
+		if (printk_ratelimit())					\
+			printk(KERN_ERR "AppArmor: " fmt, ##args);	\
+	} while (0)
+
+/* Flag indicating whether initialization completed */
+extern int apparmor_initialized __initdata;
+
+/* fn's in lib */
+char *aa_split_fqname(char *args, char **ns_name);
+void aa_info_message(const char *str);
+void *__aa_kvmalloc(size_t size, gfp_t flags);
+
+static inline void *kvmalloc(size_t size)
+{
+	return __aa_kvmalloc(size, 0);
+}
+
+static inline void *kvzalloc(size_t size)
+{
+	return __aa_kvmalloc(size, __GFP_ZERO);
+}
+
+/* returns 0 if kref not incremented */
+static inline int kref_get_not0(struct kref *kref)
+{
+	return atomic_inc_not_zero(&kref->refcount);
+}
+
+/**
+ * aa_strneq - compare null terminated @str to a non null terminated substring
+ * @str: a null terminated string
+ * @sub: a substring, not necessarily null terminated
+ * @len: length of @sub to compare
+ *
+ * The @str string must be full consumed for this to be considered a match
+ */
+static inline bool aa_strneq(const char *str, const char *sub, int len)
+{
+	return !strncmp(str, sub, len) && !str[len];
+}
+
+/**
+ * aa_dfa_null_transition - step to next state after null character
+ * @dfa: the dfa to match against
+ * @start: the state of the dfa to start matching in
+ *
+ * aa_dfa_null_transition transitions to the next state after a null
+ * character which is not used in standard matching and is only
+ * used to separate pairs.
+ */
+static inline unsigned int aa_dfa_null_transition(struct aa_dfa *dfa,
+						  unsigned int start)
+{
+	/* the null transition only needs the string's null terminator byte */
+	return aa_dfa_next(dfa, start, 0);
+}
+
+static inline bool mediated_filesystem(struct inode *inode)
+{
+	return !(inode->i_sb->s_flags & MS_NOUSER);
+}
+
+#endif /* __APPARMOR_H */

security/apparmor/include/apparmorfs.h

@@ -0,0 +1,104 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor filesystem definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_APPARMORFS_H
+#define __AA_APPARMORFS_H
+
+enum aa_fs_type {
+	AA_FS_TYPE_BOOLEAN,
+	AA_FS_TYPE_STRING,
+	AA_FS_TYPE_U64,
+	AA_FS_TYPE_FOPS,
+	AA_FS_TYPE_DIR,
+};
+
+struct aa_fs_entry;
+
+struct aa_fs_entry {
+	const char *name;
+	struct dentry *dentry;
+	umode_t mode;
+	enum aa_fs_type v_type;
+	union {
+		bool boolean;
+		char *string;
+		unsigned long u64;
+		struct aa_fs_entry *files;
+	} v;
+	const struct file_operations *file_ops;
+};
+
+extern const struct file_operations aa_fs_seq_file_ops;
+
+#define AA_FS_FILE_BOOLEAN(_name, _value) \
+	{ .name = (_name), .mode = 0444, \
+	  .v_type = AA_FS_TYPE_BOOLEAN, .v.boolean = (_value), \
+	  .file_ops = &aa_fs_seq_file_ops }
+#define AA_FS_FILE_STRING(_name, _value) \
+	{ .name = (_name), .mode = 0444, \
+	  .v_type = AA_FS_TYPE_STRING, .v.string = (_value), \
+	  .file_ops = &aa_fs_seq_file_ops }
+#define AA_FS_FILE_U64(_name, _value) \
+	{ .name = (_name), .mode = 0444, \
+	  .v_type = AA_FS_TYPE_U64, .v.u64 = (_value), \
+	  .file_ops = &aa_fs_seq_file_ops }
+#define AA_FS_FILE_FOPS(_name, _mode, _fops) \
+	{ .name = (_name), .v_type = AA_FS_TYPE_FOPS, \
+	  .mode = (_mode), .file_ops = (_fops) }
+#define AA_FS_DIR(_name, _value) \
+	{ .name = (_name), .v_type = AA_FS_TYPE_DIR, .v.files = (_value) }
+
+extern void __init aa_destroy_aafs(void);
+
+struct aa_profile;
+struct aa_namespace;
+
+enum aafs_ns_type {
+	AAFS_NS_DIR,
+	AAFS_NS_PROFS,
+	AAFS_NS_NS,
+	AAFS_NS_COUNT,
+	AAFS_NS_MAX_COUNT,
+	AAFS_NS_SIZE,
+	AAFS_NS_MAX_SIZE,
+	AAFS_NS_OWNER,
+	AAFS_NS_SIZEOF,
+};
+
+enum aafs_prof_type {
+	AAFS_PROF_DIR,
+	AAFS_PROF_PROFS,
+	AAFS_PROF_NAME,
+	AAFS_PROF_MODE,
+	AAFS_PROF_ATTACH,
+	AAFS_PROF_HASH,
+	AAFS_PROF_SIZEOF,
+};
+
+#define ns_dir(X) ((X)->dents[AAFS_NS_DIR])
+#define ns_subns_dir(X) ((X)->dents[AAFS_NS_NS])
+#define ns_subprofs_dir(X) ((X)->dents[AAFS_NS_PROFS])
+
+#define prof_dir(X) ((X)->dents[AAFS_PROF_DIR])
+#define prof_child_dir(X) ((X)->dents[AAFS_PROF_PROFS])
+
+void __aa_fs_profile_rmdir(struct aa_profile *profile);
+void __aa_fs_profile_migrate_dents(struct aa_profile *old,
+				   struct aa_profile *new);
+int __aa_fs_profile_mkdir(struct aa_profile *profile, struct dentry *parent);
+void __aa_fs_namespace_rmdir(struct aa_namespace *ns);
+int __aa_fs_namespace_mkdir(struct aa_namespace *ns, struct dentry *parent,
+			    const char *name);
+
+#endif /* __AA_APPARMORFS_H */

security/apparmor/include/audit.h

@@ -0,0 +1,147 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor auditing function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_AUDIT_H
+#define __AA_AUDIT_H
+
+#include <linux/audit.h>
+#include <linux/fs.h>
+#include <linux/lsm_audit.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include "file.h"
+
+struct aa_profile;
+
+extern const char *const audit_mode_names[];
+#define AUDIT_MAX_INDEX 5
+enum audit_mode {
+	AUDIT_NORMAL,		/* follow normal auditing of accesses */
+	AUDIT_QUIET_DENIED,	/* quiet all denied access messages */
+	AUDIT_QUIET,		/* quiet all messages */
+	AUDIT_NOQUIET,		/* do not quiet audit messages */
+	AUDIT_ALL		/* audit all accesses */
+};
+
+enum audit_type {
+	AUDIT_APPARMOR_AUDIT,
+	AUDIT_APPARMOR_ALLOWED,
+	AUDIT_APPARMOR_DENIED,
+	AUDIT_APPARMOR_HINT,
+	AUDIT_APPARMOR_STATUS,
+	AUDIT_APPARMOR_ERROR,
+	AUDIT_APPARMOR_KILL,
+	AUDIT_APPARMOR_AUTO
+};
+
+extern const char *const op_table[];
+enum aa_ops {
+	OP_NULL,
+
+	OP_SYSCTL,
+	OP_CAPABLE,
+
+	OP_UNLINK,
+	OP_MKDIR,
+	OP_RMDIR,
+	OP_MKNOD,
+	OP_TRUNC,
+	OP_LINK,
+	OP_SYMLINK,
+	OP_RENAME_SRC,
+	OP_RENAME_DEST,
+	OP_CHMOD,
+	OP_CHOWN,
+	OP_GETATTR,
+	OP_OPEN,
+
+	OP_FPERM,
+	OP_FLOCK,
+	OP_FMMAP,
+	OP_FMPROT,
+
+	OP_CREATE,
+	OP_POST_CREATE,
+	OP_BIND,
+	OP_CONNECT,
+	OP_LISTEN,
+	OP_ACCEPT,
+	OP_SENDMSG,
+	OP_RECVMSG,
+	OP_GETSOCKNAME,
+	OP_GETPEERNAME,
+	OP_GETSOCKOPT,
+	OP_SETSOCKOPT,
+	OP_SOCK_SHUTDOWN,
+
+	OP_PTRACE,
+
+	OP_EXEC,
+	OP_CHANGE_HAT,
+	OP_CHANGE_PROFILE,
+	OP_CHANGE_ONEXEC,
+
+	OP_SETPROCATTR,
+	OP_SETRLIMIT,
+
+	OP_PROF_REPL,
+	OP_PROF_LOAD,
+	OP_PROF_RM,
+};
+
+
+struct apparmor_audit_data {
+	int error;
+	int op;
+	int type;
+	void *profile;
+	const char *name;
+	const char *info;
+	union {
+		void *target;
+		struct {
+			long pos;
+			void *target;
+		} iface;
+		struct {
+			int rlim;
+			unsigned long max;
+		} rlim;
+		struct {
+			const char *target;
+			u32 request;
+			u32 denied;
+			kuid_t ouid;
+		} fs;
+	};
+};
+
+/* define a short hand for apparmor_audit_data structure */
+#define aad apparmor_audit_data
+
+void aa_audit_msg(int type, struct common_audit_data *sa,
+		  void (*cb) (struct audit_buffer *, void *));
+int aa_audit(int type, struct aa_profile *profile, gfp_t gfp,
+	     struct common_audit_data *sa,
+	     void (*cb) (struct audit_buffer *, void *));
+
+static inline int complain_error(int error)
+{
+	if (error == -EPERM || error == -EACCES)
+		return 0;
+	return error;
+}
+
+#endif /* __AA_AUDIT_H */

security/apparmor/include/capability.h

@@ -0,0 +1,48 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor capability mediation definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2013 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_CAPABILITY_H
+#define __AA_CAPABILITY_H
+
+#include <linux/sched.h>
+
+#include "apparmorfs.h"
+
+struct aa_profile;
+
+/* aa_caps - confinement data for capabilities
+ * @allowed: capabilities mask
+ * @audit: caps that are to be audited
+ * @quiet: caps that should not be audited
+ * @kill: caps that when requested will result in the task being killed
+ * @extended: caps that are subject finer grained mediation
+ */
+struct aa_caps {
+	kernel_cap_t allow;
+	kernel_cap_t audit;
+	kernel_cap_t quiet;
+	kernel_cap_t kill;
+	kernel_cap_t extended;
+};
+
+extern struct aa_fs_entry aa_fs_entry_caps[];
+
+int aa_capable(struct aa_profile *profile, int cap, int audit);
+
+static inline void aa_free_cap_rules(struct aa_caps *caps)
+{
+	/* NOP */
+}
+
+#endif /* __AA_CAPBILITY_H */

security/apparmor/include/context.h

@@ -0,0 +1,178 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor contexts used to associate "labels" to objects.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_CONTEXT_H
+#define __AA_CONTEXT_H
+
+#include <linux/cred.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+
+#include "policy.h"
+
+#define cred_cxt(X) (X)->security
+#define current_cxt() cred_cxt(current_cred())
+
+/* struct aa_file_cxt - the AppArmor context the file was opened in
+ * @perms: the permission the file was opened with
+ *
+ * The file_cxt could currently be directly stored in file->f_security
+ * as the profile reference is now stored in the f_cred.  However the
+ * cxt struct will expand in the future so we keep the struct.
+ */
+struct aa_file_cxt {
+	u16 allow;
+};
+
+/**
+ * aa_alloc_file_context - allocate file_cxt
+ * @gfp: gfp flags for allocation
+ *
+ * Returns: file_cxt or NULL on failure
+ */
+static inline struct aa_file_cxt *aa_alloc_file_context(gfp_t gfp)
+{
+	return kzalloc(sizeof(struct aa_file_cxt), gfp);
+}
+
+/**
+ * aa_free_file_context - free a file_cxt
+ * @cxt: file_cxt to free  (MAYBE_NULL)
+ */
+static inline void aa_free_file_context(struct aa_file_cxt *cxt)
+{
+	if (cxt)
+		kzfree(cxt);
+}
+
+/**
+ * struct aa_task_cxt - primary label for confined tasks
+ * @profile: the current profile   (NOT NULL)
+ * @exec: profile to transition to on next exec  (MAYBE NULL)
+ * @previous: profile the task may return to     (MAYBE NULL)
+ * @token: magic value the task must know for returning to @previous_profile
+ *
+ * Contains the task's current profile (which could change due to
+ * change_hat).  Plus the hat_magic needed during change_hat.
+ *
+ * TODO: make so a task can be confined by a stack of contexts
+ */
+struct aa_task_cxt {
+	struct aa_profile *profile;
+	struct aa_profile *onexec;
+	struct aa_profile *previous;
+	u64 token;
+};
+
+struct aa_task_cxt *aa_alloc_task_context(gfp_t flags);
+void aa_free_task_context(struct aa_task_cxt *cxt);
+void aa_dup_task_context(struct aa_task_cxt *new,
+			 const struct aa_task_cxt *old);
+int aa_replace_current_profile(struct aa_profile *profile);
+int aa_set_current_onexec(struct aa_profile *profile);
+int aa_set_current_hat(struct aa_profile *profile, u64 token);
+int aa_restore_previous_profile(u64 cookie);
+struct aa_profile *aa_get_task_profile(struct task_struct *task);
+
+
+/**
+ * aa_cred_profile - obtain cred's profiles
+ * @cred: cred to obtain profiles from  (NOT NULL)
+ *
+ * Returns: confining profile
+ *
+ * does NOT increment reference count
+ */
+static inline struct aa_profile *aa_cred_profile(const struct cred *cred)
+{
+	struct aa_task_cxt *cxt = cred_cxt(cred);
+	BUG_ON(!cxt || !cxt->profile);
+	return cxt->profile;
+}
+
+/**
+ * __aa_task_profile - retrieve another task's profile
+ * @task: task to query  (NOT NULL)
+ *
+ * Returns: @task's profile without incrementing its ref count
+ *
+ * If @task != current needs to be called in RCU safe critical section
+ */
+static inline struct aa_profile *__aa_task_profile(struct task_struct *task)
+{
+	return aa_cred_profile(__task_cred(task));
+}
+
+/**
+ * __aa_task_is_confined - determine if @task has any confinement
+ * @task: task to check confinement of  (NOT NULL)
+ *
+ * If @task != current needs to be called in RCU safe critical section
+ */
+static inline bool __aa_task_is_confined(struct task_struct *task)
+{
+	return !unconfined(__aa_task_profile(task));
+}
+
+/**
+ * __aa_current_profile - find the current tasks confining profile
+ *
+ * Returns: up to date confining profile or the ns unconfined profile (NOT NULL)
+ *
+ * This fn will not update the tasks cred to the most up to date version
+ * of the profile so it is safe to call when inside of locks.
+ */
+static inline struct aa_profile *__aa_current_profile(void)
+{
+	return aa_cred_profile(current_cred());
+}
+
+/**
+ * aa_current_profile - find the current tasks confining profile and do updates
+ *
+ * Returns: up to date confining profile or the ns unconfined profile (NOT NULL)
+ *
+ * This fn will update the tasks cred structure if the profile has been
+ * replaced.  Not safe to call inside locks
+ */
+static inline struct aa_profile *aa_current_profile(void)
+{
+	const struct aa_task_cxt *cxt = current_cxt();
+	struct aa_profile *profile;
+	BUG_ON(!cxt || !cxt->profile);
+
+	if (PROFILE_INVALID(cxt->profile)) {
+		profile = aa_get_newest_profile(cxt->profile);
+		aa_replace_current_profile(profile);
+		aa_put_profile(profile);
+		cxt = current_cxt();
+	}
+
+	return cxt->profile;
+}
+
+/**
+ * aa_clear_task_cxt_trans - clear transition tracking info from the cxt
+ * @cxt: task context to clear (NOT NULL)
+ */
+static inline void aa_clear_task_cxt_trans(struct aa_task_cxt *cxt)
+{
+	aa_put_profile(cxt->previous);
+	aa_put_profile(cxt->onexec);
+	cxt->previous = NULL;
+	cxt->onexec = NULL;
+	cxt->token = 0;
+}
+
+#endif /* __AA_CONTEXT_H */

security/apparmor/include/crypto.h

@@ -0,0 +1,36 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy loading interface function definitions.
+ *
+ * Copyright 2013 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __APPARMOR_CRYPTO_H
+#define __APPARMOR_CRYPTO_H
+
+#include "policy.h"
+
+#ifdef CONFIG_SECURITY_APPARMOR_HASH
+unsigned int aa_hash_size(void);
+int aa_calc_profile_hash(struct aa_profile *profile, u32 version, void *start,
+			 size_t len);
+#else
+static inline int aa_calc_profile_hash(struct aa_profile *profile, u32 version,
+				       void *start, size_t len)
+{
+	return 0;
+}
+
+static inline unsigned int aa_hash_size(void)
+{
+	return 0;
+}
+#endif
+
+#endif /* __APPARMOR_CRYPTO_H */

security/apparmor/include/domain.h

@@ -0,0 +1,36 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor security domain transition function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/binfmts.h>
+#include <linux/types.h>
+
+#ifndef __AA_DOMAIN_H
+#define __AA_DOMAIN_H
+
+struct aa_domain {
+	int size;
+	char **table;
+};
+
+int apparmor_bprm_set_creds(struct linux_binprm *bprm);
+int apparmor_bprm_secureexec(struct linux_binprm *bprm);
+void apparmor_bprm_committing_creds(struct linux_binprm *bprm);
+void apparmor_bprm_committed_creds(struct linux_binprm *bprm);
+
+void aa_free_domain_entries(struct aa_domain *domain);
+int aa_change_hat(const char *hats[], int count, u64 token, bool permtest);
+int aa_change_profile(const char *ns_name, const char *name, bool onexec,
+		      bool permtest);
+
+#endif /* __AA_DOMAIN_H */

security/apparmor/include/file.h

@@ -0,0 +1,216 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor file mediation function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_FILE_H
+#define __AA_FILE_H
+
+#include "domain.h"
+#include "match.h"
+
+struct aa_profile;
+struct path;
+
+/*
+ * We use MAY_EXEC, MAY_WRITE, MAY_READ, MAY_APPEND and the following flags
+ * for profile permissions
+ */
+#define AA_MAY_CREATE                  0x0010
+#define AA_MAY_DELETE                  0x0020
+#define AA_MAY_META_WRITE              0x0040
+#define AA_MAY_META_READ               0x0080
+
+#define AA_MAY_CHMOD                   0x0100
+#define AA_MAY_CHOWN                   0x0200
+#define AA_MAY_LOCK                    0x0400
+#define AA_EXEC_MMAP                   0x0800
+
+#define AA_MAY_LINK			0x1000
+#define AA_LINK_SUBSET			AA_MAY_LOCK	/* overlaid */
+#define AA_MAY_ONEXEC			0x40000000	/* exec allows onexec */
+#define AA_MAY_CHANGE_PROFILE		0x80000000
+#define AA_MAY_CHANGEHAT		0x80000000	/* ctrl auditing only */
+
+#define AA_AUDIT_FILE_MASK	(MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND |\
+				 AA_MAY_CREATE | AA_MAY_DELETE |	\
+				 AA_MAY_META_READ | AA_MAY_META_WRITE | \
+				 AA_MAY_CHMOD | AA_MAY_CHOWN | AA_MAY_LOCK | \
+				 AA_EXEC_MMAP | AA_MAY_LINK)
+
+/*
+ * The xindex is broken into 3 parts
+ * - index - an index into either the exec name table or the variable table
+ * - exec type - which determines how the executable name and index are used
+ * - flags - which modify how the destination name is applied
+ */
+#define AA_X_INDEX_MASK		0x03ff
+
+#define AA_X_TYPE_MASK		0x0c00
+#define AA_X_TYPE_SHIFT		10
+#define AA_X_NONE		0x0000
+#define AA_X_NAME		0x0400	/* use executable name px */
+#define AA_X_TABLE		0x0800	/* use a specified name ->n# */
+
+#define AA_X_UNSAFE		0x1000
+#define AA_X_CHILD		0x2000	/* make >AA_X_NONE apply to children */
+#define AA_X_INHERIT		0x4000
+#define AA_X_UNCONFINED		0x8000
+
+/* AA_SECURE_X_NEEDED - is passed in the bprm->unsafe field */
+#define AA_SECURE_X_NEEDED	0x8000
+
+/* need to make conditional which ones are being set */
+struct path_cond {
+	kuid_t uid;
+	umode_t mode;
+};
+
+/* struct file_perms - file permission
+ * @allow: mask of permissions that are allowed
+ * @audit: mask of permissions to force an audit message for
+ * @quiet: mask of permissions to quiet audit messages for
+ * @kill: mask of permissions that when matched will kill the task
+ * @xindex: exec transition index if @allow contains MAY_EXEC
+ *
+ * The @audit and @queit mask should be mutually exclusive.
+ */
+struct file_perms {
+	u32 allow;
+	u32 audit;
+	u32 quiet;
+	u32 kill;
+	u16 xindex;
+};
+
+extern struct file_perms nullperms;
+
+#define COMBINED_PERM_MASK(X) ((X).allow | (X).audit | (X).quiet | (X).kill)
+
+/* FIXME: split perms from dfa and match this to description
+ *        also add delegation info.
+ */
+static inline u16 dfa_map_xindex(u16 mask)
+{
+	u16 old_index = (mask >> 10) & 0xf;
+	u16 index = 0;
+
+	if (mask & 0x100)
+		index |= AA_X_UNSAFE;
+	if (mask & 0x200)
+		index |= AA_X_INHERIT;
+	if (mask & 0x80)
+		index |= AA_X_UNCONFINED;
+
+	if (old_index == 1) {
+		index |= AA_X_UNCONFINED;
+	} else if (old_index == 2) {
+		index |= AA_X_NAME;
+	} else if (old_index == 3) {
+		index |= AA_X_NAME | AA_X_CHILD;
+	} else if (old_index) {
+		index |= AA_X_TABLE;
+		index |= old_index - 4;
+	}
+
+	return index;
+}
+
+/*
+ * map old dfa inline permissions to new format
+ */
+#define dfa_user_allow(dfa, state) (((ACCEPT_TABLE(dfa)[state]) & 0x7f) | \
+				    ((ACCEPT_TABLE(dfa)[state]) & 0x80000000))
+#define dfa_user_audit(dfa, state) ((ACCEPT_TABLE2(dfa)[state]) & 0x7f)
+#define dfa_user_quiet(dfa, state) (((ACCEPT_TABLE2(dfa)[state]) >> 7) & 0x7f)
+#define dfa_user_xindex(dfa, state) \
+	(dfa_map_xindex(ACCEPT_TABLE(dfa)[state] & 0x3fff))
+
+#define dfa_other_allow(dfa, state) ((((ACCEPT_TABLE(dfa)[state]) >> 14) & \
+				      0x7f) |				\
+				     ((ACCEPT_TABLE(dfa)[state]) & 0x80000000))
+#define dfa_other_audit(dfa, state) (((ACCEPT_TABLE2(dfa)[state]) >> 14) & 0x7f)
+#define dfa_other_quiet(dfa, state) \
+	((((ACCEPT_TABLE2(dfa)[state]) >> 7) >> 14) & 0x7f)
+#define dfa_other_xindex(dfa, state) \
+	dfa_map_xindex((ACCEPT_TABLE(dfa)[state] >> 14) & 0x3fff)
+
+int aa_audit_file(struct aa_profile *profile, struct file_perms *perms,
+		  gfp_t gfp, int op, u32 request, const char *name,
+		  const char *target, kuid_t ouid, const char *info, int error);
+
+/**
+ * struct aa_file_rules - components used for file rule permissions
+ * @dfa: dfa to match path names and conditionals against
+ * @perms: permission table indexed by the matched state accept entry of @dfa
+ * @trans: transition table for indexed by named x transitions
+ *
+ * File permission are determined by matching a path against @dfa and then
+ * then using the value of the accept entry for the matching state as
+ * an index into @perms.  If a named exec transition is required it is
+ * looked up in the transition table.
+ */
+struct aa_file_rules {
+	unsigned int start;
+	struct aa_dfa *dfa;
+	/* struct perms perms; */
+	struct aa_domain trans;
+	/* TODO: add delegate table */
+};
+
+unsigned int aa_str_perms(struct aa_dfa *dfa, unsigned int start,
+			  const char *name, struct path_cond *cond,
+			  struct file_perms *perms);
+
+int aa_path_perm(int op, struct aa_profile *profile, struct path *path,
+		 int flags, u32 request, struct path_cond *cond);
+
+int aa_path_link(struct aa_profile *profile, struct dentry *old_dentry,
+		 struct path *new_dir, struct dentry *new_dentry);
+
+int aa_file_perm(int op, struct aa_profile *profile, struct file *file,
+		 u32 request);
+
+static inline void aa_free_file_rules(struct aa_file_rules *rules)
+{
+	aa_put_dfa(rules->dfa);
+	aa_free_domain_entries(&rules->trans);
+}
+
+/**
+ * aa_map_file_perms - map file flags to AppArmor permissions
+ * @file: open file to map flags to AppArmor permissions
+ *
+ * Returns: apparmor permission set for the file
+ */
+static inline u32 aa_map_file_to_perms(struct file *file)
+{
+	int flags = file->f_flags;
+	u32 perms = 0;
+
+	if (file->f_mode & FMODE_WRITE)
+		perms |= MAY_WRITE;
+	if (file->f_mode & FMODE_READ)
+		perms |= MAY_READ;
+
+	if ((flags & O_APPEND) && (perms & MAY_WRITE))
+		perms = (perms & ~MAY_WRITE) | MAY_APPEND;
+	/* trunc implies write permission */
+	if (flags & O_TRUNC)
+		perms |= MAY_WRITE;
+	if (flags & O_CREAT)
+		perms |= AA_MAY_CREATE;
+
+	return perms;
+}
+
+#endif /* __AA_FILE_H */

security/apparmor/include/ipc.h

@@ -0,0 +1,28 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor ipc mediation function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_IPC_H
+#define __AA_IPC_H
+
+#include <linux/sched.h>
+
+struct aa_profile;
+
+int aa_may_ptrace(struct aa_profile *tracer, struct aa_profile *tracee,
+		  unsigned int mode);
+
+int aa_ptrace(struct task_struct *tracer, struct task_struct *tracee,
+	      unsigned int mode);
+
+#endif /* __AA_IPC_H */

security/apparmor/include/match.h

@@ -0,0 +1,141 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy dfa matching engine definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2012 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_MATCH_H
+#define __AA_MATCH_H
+
+#include <linux/kref.h>
+
+#define DFA_NOMATCH			0
+#define DFA_START			1
+
+
+/**
+ * The format used for transition tables is based on the GNU flex table
+ * file format (--tables-file option; see Table File Format in the flex
+ * info pages and the flex sources for documentation). The magic number
+ * used in the header is 0x1B5E783D instead of 0xF13C57B1 though, because
+ * new tables have been defined and others YY_ID_CHK (check) and YY_ID_DEF
+ * (default) tables are used slightly differently (see the apparmor-parser
+ * package).
+ *
+ *
+ * The data in the packed dfa is stored in network byte order, and the tables
+ * are arranged for flexibility.  We convert the table data to host native
+ * byte order.
+ *
+ * The dfa begins with a table set header, and is followed by the actual
+ * tables.
+ */
+
+#define YYTH_MAGIC	0x1B5E783D
+
+struct table_set_header {
+	u32 th_magic;		/* YYTH_MAGIC */
+	u32 th_hsize;
+	u32 th_ssize;
+	u16 th_flags;
+	char th_version[];
+};
+
+/* The YYTD_ID are one less than flex table mappings.  The flex id
+ * has 1 subtracted at table load time, this allows us to directly use the
+ * ID's as indexes.
+ */
+#define	YYTD_ID_ACCEPT	0
+#define YYTD_ID_BASE	1
+#define YYTD_ID_CHK	2
+#define YYTD_ID_DEF	3
+#define YYTD_ID_EC	4
+#define YYTD_ID_META	5
+#define YYTD_ID_ACCEPT2 6
+#define YYTD_ID_NXT	7
+#define YYTD_ID_TSIZE	8
+
+#define YYTD_DATA8	1
+#define YYTD_DATA16	2
+#define YYTD_DATA32	4
+#define YYTD_DATA64	8
+
+/* ACCEPT & ACCEPT2 tables gets 6 dedicated flags, YYTD_DATAX define the
+ * first flags
+ */
+#define ACCEPT1_FLAGS(X) ((X) & 0x3f)
+#define ACCEPT2_FLAGS(X) ACCEPT1_FLAGS((X) >> YYTD_ID_ACCEPT2)
+#define TO_ACCEPT1_FLAG(X) ACCEPT1_FLAGS(X)
+#define TO_ACCEPT2_FLAG(X) (ACCEPT1_FLAGS(X) << YYTD_ID_ACCEPT2)
+#define DFA_FLAG_VERIFY_STATES 0x1000
+
+struct table_header {
+	u16 td_id;
+	u16 td_flags;
+	u32 td_hilen;
+	u32 td_lolen;
+	char td_data[];
+};
+
+#define DEFAULT_TABLE(DFA) ((u16 *)((DFA)->tables[YYTD_ID_DEF]->td_data))
+#define BASE_TABLE(DFA) ((u32 *)((DFA)->tables[YYTD_ID_BASE]->td_data))
+#define NEXT_TABLE(DFA) ((u16 *)((DFA)->tables[YYTD_ID_NXT]->td_data))
+#define CHECK_TABLE(DFA) ((u16 *)((DFA)->tables[YYTD_ID_CHK]->td_data))
+#define EQUIV_TABLE(DFA) ((u8 *)((DFA)->tables[YYTD_ID_EC]->td_data))
+#define ACCEPT_TABLE(DFA) ((u32 *)((DFA)->tables[YYTD_ID_ACCEPT]->td_data))
+#define ACCEPT_TABLE2(DFA) ((u32 *)((DFA)->tables[YYTD_ID_ACCEPT2]->td_data))
+
+struct aa_dfa {
+	struct kref count;
+	u16 flags;
+	struct table_header *tables[YYTD_ID_TSIZE];
+};
+
+#define byte_to_byte(X) (X)
+
+#define UNPACK_ARRAY(TABLE, BLOB, LEN, TYPE, NTOHX) \
+	do { \
+		typeof(LEN) __i; \
+		TYPE *__t = (TYPE *) TABLE; \
+		TYPE *__b = (TYPE *) BLOB; \
+		for (__i = 0; __i < LEN; __i++) { \
+			__t[__i] = NTOHX(__b[__i]); \
+		} \
+	} while (0)
+
+static inline size_t table_size(size_t len, size_t el_size)
+{
+	return ALIGN(sizeof(struct table_header) + len * el_size, 8);
+}
+
+struct aa_dfa *aa_dfa_unpack(void *blob, size_t size, int flags);
+unsigned int aa_dfa_match_len(struct aa_dfa *dfa, unsigned int start,
+			      const char *str, int len);
+unsigned int aa_dfa_match(struct aa_dfa *dfa, unsigned int start,
+			  const char *str);
+unsigned int aa_dfa_next(struct aa_dfa *dfa, unsigned int state,
+			 const char c);
+
+void aa_dfa_free_kref(struct kref *kref);
+
+/**
+ * aa_put_dfa - put a dfa refcount
+ * @dfa: dfa to put refcount   (MAYBE NULL)
+ *
+ * Requires: if @dfa != NULL that a valid refcount be held
+ */
+static inline void aa_put_dfa(struct aa_dfa *dfa)
+{
+	if (dfa)
+		kref_put(&dfa->count, aa_dfa_free_kref);
+}
+
+#endif /* __AA_MATCH_H */

security/apparmor/include/path.h

@@ -0,0 +1,32 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor basic path manipulation function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_PATH_H
+#define __AA_PATH_H
+
+
+enum path_flags {
+	PATH_IS_DIR = 0x1,		/* path is a directory */
+	PATH_CONNECT_PATH = 0x4,	/* connect disconnected paths to / */
+	PATH_CHROOT_REL = 0x8,		/* do path lookup relative to chroot */
+	PATH_CHROOT_NSCONNECT = 0x10,	/* connect paths that are at ns root */
+
+	PATH_DELEGATE_DELETED = 0x08000, /* delegate deleted files */
+	PATH_MEDIATE_DELETED = 0x10000,	/* mediate deleted paths */
+};
+
+int aa_path_name(struct path *path, int flags, char **buffer,
+		 const char **name, const char **info);
+
+#endif /* __AA_PATH_H */

security/apparmor/include/policy.h

@@ -0,0 +1,408 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_POLICY_H
+#define __AA_POLICY_H
+
+#include <linux/capability.h>
+#include <linux/cred.h>
+#include <linux/kref.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+
+#include "apparmor.h"
+#include "audit.h"
+#include "capability.h"
+#include "domain.h"
+#include "file.h"
+#include "resource.h"
+
+extern const char *const aa_profile_mode_names[];
+#define APPARMOR_MODE_NAMES_MAX_INDEX 4
+
+#define PROFILE_MODE(_profile, _mode)		\
+	((aa_g_profile_mode == (_mode)) ||	\
+	 ((_profile)->mode == (_mode)))
+
+#define COMPLAIN_MODE(_profile)	PROFILE_MODE((_profile), APPARMOR_COMPLAIN)
+
+#define KILL_MODE(_profile) PROFILE_MODE((_profile), APPARMOR_KILL)
+
+#define PROFILE_IS_HAT(_profile) ((_profile)->flags & PFLAG_HAT)
+
+#define PROFILE_INVALID(_profile) ((_profile)->flags & PFLAG_INVALID)
+
+#define on_list_rcu(X) (!list_empty(X) && (X)->prev != LIST_POISON2)
+
+/*
+ * FIXME: currently need a clean way to replace and remove profiles as a
+ * set.  It should be done at the namespace level.
+ * Either, with a set of profiles loaded at the namespace level or via
+ * a mark and remove marked interface.
+ */
+enum profile_mode {
+	APPARMOR_ENFORCE,	/* enforce access rules */
+	APPARMOR_COMPLAIN,	/* allow and log access violations */
+	APPARMOR_KILL,		/* kill task on access violation */
+	APPARMOR_UNCONFINED,	/* profile set to unconfined */
+};
+
+enum profile_flags {
+	PFLAG_HAT = 1,			/* profile is a hat */
+	PFLAG_NULL = 4,			/* profile is null learning profile */
+	PFLAG_IX_ON_NAME_ERROR = 8,	/* fallback to ix on name lookup fail */
+	PFLAG_IMMUTABLE = 0x10,		/* don't allow changes/replacement */
+	PFLAG_USER_DEFINED = 0x20,	/* user based profile - lower privs */
+	PFLAG_NO_LIST_REF = 0x40,	/* list doesn't keep profile ref */
+	PFLAG_OLD_NULL_TRANS = 0x100,	/* use // as the null transition */
+	PFLAG_INVALID = 0x200,		/* profile replaced/removed */
+	PFLAG_NS_COUNT = 0x400,		/* carries NS ref count */
+
+	/* These flags must correspond with PATH_flags */
+	PFLAG_MEDIATE_DELETED = 0x10000, /* mediate instead delegate deleted */
+};
+
+struct aa_profile;
+
+/* struct aa_policy - common part of both namespaces and profiles
+ * @name: name of the object
+ * @hname - The hierarchical name
+ * @list: list policy object is on
+ * @profiles: head of the profiles list contained in the object
+ */
+struct aa_policy {
+	char *name;
+	char *hname;
+	struct list_head list;
+	struct list_head profiles;
+};
+
+/* struct aa_ns_acct - accounting of profiles in namespace
+ * @max_size: maximum space allowed for all profiles in namespace
+ * @max_count: maximum number of profiles that can be in this namespace
+ * @size: current size of profiles
+ * @count: current count of profiles (includes null profiles)
+ */
+struct aa_ns_acct {
+	int max_size;
+	int max_count;
+	int size;
+	int count;
+};
+
+/* struct aa_namespace - namespace for a set of profiles
+ * @base: common policy
+ * @parent: parent of namespace
+ * @lock: lock for modifying the object
+ * @acct: accounting for the namespace
+ * @unconfined: special unconfined profile for the namespace
+ * @sub_ns: list of namespaces under the current namespace.
+ * @uniq_null: uniq value used for null learning profiles
+ * @uniq_id: a unique id count for the profiles in the namespace
+ * @dents: dentries for the namespaces file entries in apparmorfs
+ *
+ * An aa_namespace defines the set profiles that are searched to determine
+ * which profile to attach to a task.  Profiles can not be shared between
+ * aa_namespaces and profile names within a namespace are guaranteed to be
+ * unique.  When profiles in separate namespaces have the same name they
+ * are NOT considered to be equivalent.
+ *
+ * Namespaces are hierarchical and only namespaces and profiles below the
+ * current namespace are visible.
+ *
+ * Namespace names must be unique and can not contain the characters :/\0
+ *
+ * FIXME TODO: add vserver support of namespaces (can it all be done in
+ *             userspace?)
+ */
+struct aa_namespace {
+	struct aa_policy base;
+	struct aa_namespace *parent;
+	struct mutex lock;
+	struct aa_ns_acct acct;
+	struct aa_profile *unconfined;
+	struct list_head sub_ns;
+	atomic_t uniq_null;
+	long uniq_id;
+
+	struct dentry *dents[AAFS_NS_SIZEOF];
+};
+
+/* struct aa_policydb - match engine for a policy
+ * dfa: dfa pattern match
+ * start: set of start states for the different classes of data
+ */
+struct aa_policydb {
+	/* Generic policy DFA specific rule types will be subsections of it */
+	struct aa_dfa *dfa;
+	unsigned int start[AA_CLASS_LAST + 1];
+
+};
+
+struct aa_replacedby {
+	struct kref count;
+	struct aa_profile __rcu *profile;
+};
+
+
+/* struct aa_profile - basic confinement data
+ * @base - base components of the profile (name, refcount, lists, lock ...)
+ * @count: reference count of the obj
+ * @rcu: rcu head used when removing from @list
+ * @parent: parent of profile
+ * @ns: namespace the profile is in
+ * @replacedby: is set to the profile that replaced this profile
+ * @rename: optional profile name that this profile renamed
+ * @attach: human readable attachment string
+ * @xmatch: optional extended matching for unconfined executables names
+ * @xmatch_len: xmatch prefix len, used to determine xmatch priority
+ * @audit: the auditing mode of the profile
+ * @mode: the enforcement mode of the profile
+ * @flags: flags controlling profile behavior
+ * @path_flags: flags controlling path generation behavior
+ * @size: the memory consumed by this profiles rules
+ * @policy: general match rules governing policy
+ * @file: The set of rules governing basic file access and domain transitions
+ * @caps: capabilities for the profile
+ * @rlimits: rlimits for the profile
+ *
+ * @dents: dentries for the profiles file entries in apparmorfs
+ * @dirname: name of the profile dir in apparmorfs
+ *
+ * The AppArmor profile contains the basic confinement data.  Each profile
+ * has a name, and exists in a namespace.  The @name and @exec_match are
+ * used to determine profile attachment against unconfined tasks.  All other
+ * attachments are determined by profile X transition rules.
+ *
+ * The @replacedby struct is write protected by the profile lock.
+ *
+ * Profiles have a hierarchy where hats and children profiles keep
+ * a reference to their parent.
+ *
+ * Profile names can not begin with a : and can not contain the \0
+ * character.  If a profile name begins with / it will be considered when
+ * determining profile attachment on "unconfined" tasks.
+ */
+struct aa_profile {
+	struct aa_policy base;
+	struct kref count;
+	struct rcu_head rcu;
+	struct aa_profile __rcu *parent;
+
+	struct aa_namespace *ns;
+	struct aa_replacedby *replacedby;
+	const char *rename;
+
+	const char *attach;
+	struct aa_dfa *xmatch;
+	int xmatch_len;
+	enum audit_mode audit;
+	long mode;
+	long flags;
+	u32 path_flags;
+	int size;
+
+	struct aa_policydb policy;
+	struct aa_file_rules file;
+	struct aa_caps caps;
+	struct aa_rlimit rlimits;
+
+	unsigned char *hash;
+	char *dirname;
+	struct dentry *dents[AAFS_PROF_SIZEOF];
+};
+
+extern struct aa_namespace *root_ns;
+extern enum profile_mode aa_g_profile_mode;
+
+void aa_add_profile(struct aa_policy *common, struct aa_profile *profile);
+
+bool aa_ns_visible(struct aa_namespace *curr, struct aa_namespace *view);
+const char *aa_ns_name(struct aa_namespace *parent, struct aa_namespace *child);
+int aa_alloc_root_ns(void);
+void aa_free_root_ns(void);
+void aa_free_namespace_kref(struct kref *kref);
+
+struct aa_namespace *aa_find_namespace(struct aa_namespace *root,
+				       const char *name);
+
+
+void aa_free_replacedby_kref(struct kref *kref);
+struct aa_profile *aa_alloc_profile(const char *name);
+struct aa_profile *aa_new_null_profile(struct aa_profile *parent, int hat);
+void aa_free_profile(struct aa_profile *profile);
+void aa_free_profile_kref(struct kref *kref);
+struct aa_profile *aa_find_child(struct aa_profile *parent, const char *name);
+struct aa_profile *aa_lookup_profile(struct aa_namespace *ns, const char *name);
+struct aa_profile *aa_match_profile(struct aa_namespace *ns, const char *name);
+
+ssize_t aa_replace_profiles(void *udata, size_t size, bool noreplace);
+ssize_t aa_remove_profiles(char *name, size_t size);
+
+#define PROF_ADD 1
+#define PROF_REPLACE 0
+
+#define unconfined(X) ((X)->mode == APPARMOR_UNCONFINED)
+
+
+static inline struct aa_profile *aa_deref_parent(struct aa_profile *p)
+{
+	return rcu_dereference_protected(p->parent,
+					 mutex_is_locked(&p->ns->lock));
+}
+
+/**
+ * aa_get_profile - increment refcount on profile @p
+ * @p: profile  (MAYBE NULL)
+ *
+ * Returns: pointer to @p if @p is NULL will return NULL
+ * Requires: @p must be held with valid refcount when called
+ */
+static inline struct aa_profile *aa_get_profile(struct aa_profile *p)
+{
+	if (p)
+		kref_get(&(p->count));
+
+	return p;
+}
+
+/**
+ * aa_get_profile_not0 - increment refcount on profile @p found via lookup
+ * @p: profile  (MAYBE NULL)
+ *
+ * Returns: pointer to @p if @p is NULL will return NULL
+ * Requires: @p must be held with valid refcount when called
+ */
+static inline struct aa_profile *aa_get_profile_not0(struct aa_profile *p)
+{
+	if (p && kref_get_not0(&p->count))
+		return p;
+
+	return NULL;
+}
+
+/**
+ * aa_get_profile_rcu - increment a refcount profile that can be replaced
+ * @p: pointer to profile that can be replaced (NOT NULL)
+ *
+ * Returns: pointer to a refcounted profile.
+ *     else NULL if no profile
+ */
+static inline struct aa_profile *aa_get_profile_rcu(struct aa_profile __rcu **p)
+{
+	struct aa_profile *c;
+
+	rcu_read_lock();
+	do {
+		c = rcu_dereference(*p);
+	} while (c && !kref_get_not0(&c->count));
+	rcu_read_unlock();
+
+	return c;
+}
+
+/**
+ * aa_get_newest_profile - find the newest version of @profile
+ * @profile: the profile to check for newer versions of
+ *
+ * Returns: refcounted newest version of @profile taking into account
+ *          replacement, renames and removals
+ *          return @profile.
+ */
+static inline struct aa_profile *aa_get_newest_profile(struct aa_profile *p)
+{
+	if (!p)
+		return NULL;
+
+	if (PROFILE_INVALID(p))
+		return aa_get_profile_rcu(&p->replacedby->profile);
+
+	return aa_get_profile(p);
+}
+
+/**
+ * aa_put_profile - decrement refcount on profile @p
+ * @p: profile  (MAYBE NULL)
+ */
+static inline void aa_put_profile(struct aa_profile *p)
+{
+	if (p)
+		kref_put(&p->count, aa_free_profile_kref);
+}
+
+static inline struct aa_replacedby *aa_get_replacedby(struct aa_replacedby *p)
+{
+	if (p)
+		kref_get(&(p->count));
+
+	return p;
+}
+
+static inline void aa_put_replacedby(struct aa_replacedby *p)
+{
+	if (p)
+		kref_put(&p->count, aa_free_replacedby_kref);
+}
+
+/* requires profile list write lock held */
+static inline void __aa_update_replacedby(struct aa_profile *orig,
+					  struct aa_profile *new)
+{
+	struct aa_profile *tmp;
+	tmp = rcu_dereference_protected(orig->replacedby->profile,
+					mutex_is_locked(&orig->ns->lock));
+	rcu_assign_pointer(orig->replacedby->profile, aa_get_profile(new));
+	orig->flags |= PFLAG_INVALID;
+	aa_put_profile(tmp);
+}
+
+/**
+ * aa_get_namespace - increment references count on @ns
+ * @ns: namespace to increment reference count of (MAYBE NULL)
+ *
+ * Returns: pointer to @ns, if @ns is NULL returns NULL
+ * Requires: @ns must be held with valid refcount when called
+ */
+static inline struct aa_namespace *aa_get_namespace(struct aa_namespace *ns)
+{
+	if (ns)
+		aa_get_profile(ns->unconfined);
+
+	return ns;
+}
+
+/**
+ * aa_put_namespace - decrement refcount on @ns
+ * @ns: namespace to put reference of
+ *
+ * Decrement reference count of @ns and if no longer in use free it
+ */
+static inline void aa_put_namespace(struct aa_namespace *ns)
+{
+	if (ns)
+		aa_put_profile(ns->unconfined);
+}
+
+static inline int AUDIT_MODE(struct aa_profile *profile)
+{
+	if (aa_g_audit != AUDIT_NORMAL)
+		return aa_g_audit;
+
+	return profile->audit;
+}
+
+bool aa_may_manage_policy(int op);
+
+#endif /* __AA_POLICY_H */

security/apparmor/include/policy_unpack.h

@@ -0,0 +1,39 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor policy loading interface function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __POLICY_INTERFACE_H
+#define __POLICY_INTERFACE_H
+
+#include <linux/list.h>
+
+struct aa_load_ent {
+	struct list_head list;
+	struct aa_profile *new;
+	struct aa_profile *old;
+	struct aa_profile *rename;
+};
+
+void aa_load_ent_free(struct aa_load_ent *ent);
+struct aa_load_ent *aa_load_ent_alloc(void);
+
+#define PACKED_FLAG_HAT		1
+
+#define PACKED_MODE_ENFORCE	0
+#define PACKED_MODE_COMPLAIN	1
+#define PACKED_MODE_KILL	2
+#define PACKED_MODE_UNCONFINED	3
+
+int aa_unpack(void *udata, size_t size, struct list_head *lh, const char **ns);
+
+#endif /* __POLICY_INTERFACE_H */

security/apparmor/include/procattr.h

@@ -0,0 +1,25 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor /proc/<pid>/attr/ interface function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_PROCATTR_H
+#define __AA_PROCATTR_H
+
+#define AA_DO_TEST 1
+#define AA_ONEXEC  1
+
+int aa_getprocattr(struct aa_profile *profile, char **string);
+int aa_setprocattr_changehat(char *args, size_t size, int test);
+int aa_setprocattr_changeprofile(char *fqname, bool onexec, int test);
+
+#endif /* __AA_PROCATTR_H */

security/apparmor/include/resource.h

@@ -0,0 +1,50 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor resource limits function definitions.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_RESOURCE_H
+#define __AA_RESOURCE_H
+
+#include <linux/resource.h>
+#include <linux/sched.h>
+
+#include "apparmorfs.h"
+
+struct aa_profile;
+
+/* struct aa_rlimit - rlimit settings for the profile
+ * @mask: which hard limits to set
+ * @limits: rlimit values that override task limits
+ *
+ * AppArmor rlimits are used to set confined task rlimits.  Only the
+ * limits specified in @mask will be controlled by apparmor.
+ */
+struct aa_rlimit {
+	unsigned int mask;
+	struct rlimit limits[RLIM_NLIMITS];
+};
+
+extern struct aa_fs_entry aa_fs_entry_rlimit[];
+
+int aa_map_resource(int resource);
+int aa_task_setrlimit(struct aa_profile *profile, struct task_struct *,
+		      unsigned int resource, struct rlimit *new_rlim);
+
+void __aa_transition_rlimits(struct aa_profile *old, struct aa_profile *new);
+
+static inline void aa_free_rlimit_rules(struct aa_rlimit *rlims)
+{
+	/* NOP */
+}
+
+#endif /* __AA_RESOURCE_H */

security/apparmor/include/sid.h

@@ -0,0 +1,26 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor security identifier (sid) definitions
+ *
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#ifndef __AA_SID_H
+#define __AA_SID_H
+
+#include <linux/types.h>
+
+/* sid value that will not be allocated */
+#define AA_SID_INVALID 0
+#define AA_SID_ALLOC AA_SID_INVALID
+
+u32 aa_alloc_sid(void);
+void aa_free_sid(u32 sid);
+
+#endif /* __AA_SID_H */

security/apparmor/ipc.c

@@ -0,0 +1,111 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor ipc mediation
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/gfp.h>
+#include <linux/ptrace.h>
+
+#include "include/audit.h"
+#include "include/capability.h"
+#include "include/context.h"
+#include "include/policy.h"
+#include "include/ipc.h"
+
+/* call back to audit ptrace fields */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	audit_log_format(ab, " target=");
+	audit_log_untrustedstring(ab, sa->aad->target);
+}
+
+/**
+ * aa_audit_ptrace - do auditing for ptrace
+ * @profile: profile being enforced  (NOT NULL)
+ * @target: profile being traced (NOT NULL)
+ * @error: error condition
+ *
+ * Returns: %0 or error code
+ */
+static int aa_audit_ptrace(struct aa_profile *profile,
+			   struct aa_profile *target, int error)
+{
+	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
+	sa.type = LSM_AUDIT_DATA_NONE;
+	sa.aad = &aad;
+	aad.op = OP_PTRACE;
+	aad.target = target;
+	aad.error = error;
+
+	return aa_audit(AUDIT_APPARMOR_AUTO, profile, GFP_ATOMIC, &sa,
+			audit_cb);
+}
+
+/**
+ * aa_may_ptrace - test if tracer task can trace the tracee
+ * @tracer: profile of the task doing the tracing  (NOT NULL)
+ * @tracee: task to be traced
+ * @mode: whether PTRACE_MODE_READ || PTRACE_MODE_ATTACH
+ *
+ * Returns: %0 else error code if permission denied or error
+ */
+int aa_may_ptrace(struct aa_profile *tracer, struct aa_profile *tracee,
+		  unsigned int mode)
+{
+	/* TODO: currently only based on capability, not extended ptrace
+	 *       rules,
+	 *       Test mode for PTRACE_MODE_READ || PTRACE_MODE_ATTACH
+	 */
+
+	if (unconfined(tracer) || tracer == tracee)
+		return 0;
+	/* log this capability request */
+	return aa_capable(tracer, CAP_SYS_PTRACE, 1);
+}
+
+/**
+ * aa_ptrace - do ptrace permission check and auditing
+ * @tracer: task doing the tracing (NOT NULL)
+ * @tracee: task being traced (NOT NULL)
+ * @mode: ptrace mode either PTRACE_MODE_READ || PTRACE_MODE_ATTACH
+ *
+ * Returns: %0 else error code if permission denied or error
+ */
+int aa_ptrace(struct task_struct *tracer, struct task_struct *tracee,
+	      unsigned int mode)
+{
+	/*
+	 * tracer can ptrace tracee when
+	 * - tracer is unconfined ||
+	 *   - tracer is in complain mode
+	 *   - tracer has rules allowing it to trace tracee currently this is:
+	 *       - confined by the same profile ||
+	 *       - tracer profile has CAP_SYS_PTRACE
+	 */
+
+	struct aa_profile *tracer_p = aa_get_task_profile(tracer);
+	int error = 0;
+
+	if (!unconfined(tracer_p)) {
+		struct aa_profile *tracee_p = aa_get_task_profile(tracee);
+
+		error = aa_may_ptrace(tracer_p, tracee_p, mode);
+		error = aa_audit_ptrace(tracer_p, tracee_p, error);
+
+		aa_put_profile(tracee_p);
+	}
+	aa_put_profile(tracer_p);
+
+	return error;
+}

security/apparmor/lib.c

@@ -0,0 +1,106 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains basic common functions used in AppArmor
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/vmalloc.h>
+
+#include "include/audit.h"
+#include "include/apparmor.h"
+
+
+/**
+ * aa_split_fqname - split a fqname into a profile and namespace name
+ * @fqname: a full qualified name in namespace profile format (NOT NULL)
+ * @ns_name: pointer to portion of the string containing the ns name (NOT NULL)
+ *
+ * Returns: profile name or NULL if one is not specified
+ *
+ * Split a namespace name from a profile name (see policy.c for naming
+ * description).  If a portion of the name is missing it returns NULL for
+ * that portion.
+ *
+ * NOTE: may modify the @fqname string.  The pointers returned point
+ *       into the @fqname string.
+ */
+char *aa_split_fqname(char *fqname, char **ns_name)
+{
+	char *name = strim(fqname);
+
+	*ns_name = NULL;
+	if (name[0] == ':') {
+		char *split = strchr(&name[1], ':');
+		*ns_name = skip_spaces(&name[1]);
+		if (split) {
+			/* overwrite ':' with \0 */
+			*split++ = 0;
+			if (strncmp(split, "//", 2) == 0)
+				split += 2;
+			name = skip_spaces(split);
+		} else
+			/* a ns name without a following profile is allowed */
+			name = NULL;
+	}
+	if (name && *name == 0)
+		name = NULL;
+
+	return name;
+}
+
+/**
+ * aa_info_message - log a none profile related status message
+ * @str: message to log
+ */
+void aa_info_message(const char *str)
+{
+	if (audit_enabled) {
+		struct common_audit_data sa;
+		struct apparmor_audit_data aad = {0,};
+		sa.type = LSM_AUDIT_DATA_NONE;
+		sa.aad = &aad;
+		aad.info = str;
+		aa_audit_msg(AUDIT_APPARMOR_STATUS, &sa, NULL);
+	}
+	printk(KERN_INFO "AppArmor: %s\n", str);
+}
+
+/**
+ * __aa_kvmalloc - do allocation preferring kmalloc but falling back to vmalloc
+ * @size: how many bytes of memory are required
+ * @flags: the type of memory to allocate (see kmalloc).
+ *
+ * Return: allocated buffer or NULL if failed
+ *
+ * It is possible that policy being loaded from the user is larger than
+ * what can be allocated by kmalloc, in those cases fall back to vmalloc.
+ */
+void *__aa_kvmalloc(size_t size, gfp_t flags)
+{
+	void *buffer = NULL;
+
+	if (size == 0)
+		return NULL;
+
+	/* do not attempt kmalloc if we need more than 16 pages at once */
+	if (size <= (16*PAGE_SIZE))
+		buffer = kmalloc(size, flags | GFP_NOIO | __GFP_NOWARN);
+	if (!buffer) {
+		if (flags & __GFP_ZERO)
+			buffer = vzalloc(size);
+		else
+			buffer = vmalloc(size);
+	}
+	return buffer;
+}

security/apparmor/lsm.c

@@ -0,0 +1,949 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor LSM hooks.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/security.h>
+#include <linux/moduleparam.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/ptrace.h>
+#include <linux/ctype.h>
+#include <linux/sysctl.h>
+#include <linux/audit.h>
+#include <linux/user_namespace.h>
+#include <net/sock.h>
+
+#include "include/apparmor.h"
+#include "include/apparmorfs.h"
+#include "include/audit.h"
+#include "include/capability.h"
+#include "include/context.h"
+#include "include/file.h"
+#include "include/ipc.h"
+#include "include/path.h"
+#include "include/policy.h"
+#include "include/procattr.h"
+
+/* Flag indicating whether initialization completed */
+int apparmor_initialized __initdata;
+
+/*
+ * LSM hook functions
+ */
+
+/*
+ * free the associated aa_task_cxt and put its profiles
+ */
+static void apparmor_cred_free(struct cred *cred)
+{
+	aa_free_task_context(cred_cxt(cred));
+	cred_cxt(cred) = NULL;
+}
+
+/*
+ * allocate the apparmor part of blank credentials
+ */
+static int apparmor_cred_alloc_blank(struct cred *cred, gfp_t gfp)
+{
+	/* freed by apparmor_cred_free */
+	struct aa_task_cxt *cxt = aa_alloc_task_context(gfp);
+	if (!cxt)
+		return -ENOMEM;
+
+	cred_cxt(cred) = cxt;
+	return 0;
+}
+
+/*
+ * prepare new aa_task_cxt for modification by prepare_cred block
+ */
+static int apparmor_cred_prepare(struct cred *new, const struct cred *old,
+				 gfp_t gfp)
+{
+	/* freed by apparmor_cred_free */
+	struct aa_task_cxt *cxt = aa_alloc_task_context(gfp);
+	if (!cxt)
+		return -ENOMEM;
+
+	aa_dup_task_context(cxt, cred_cxt(old));
+	cred_cxt(new) = cxt;
+	return 0;
+}
+
+/*
+ * transfer the apparmor data to a blank set of creds
+ */
+static void apparmor_cred_transfer(struct cred *new, const struct cred *old)
+{
+	const struct aa_task_cxt *old_cxt = cred_cxt(old);
+	struct aa_task_cxt *new_cxt = cred_cxt(new);
+
+	aa_dup_task_context(new_cxt, old_cxt);
+}
+
+static int apparmor_ptrace_access_check(struct task_struct *child,
+					unsigned int mode)
+{
+	int error = cap_ptrace_access_check(child, mode);
+	if (error)
+		return error;
+
+	return aa_ptrace(current, child, mode);
+}
+
+static int apparmor_ptrace_traceme(struct task_struct *parent)
+{
+	int error = cap_ptrace_traceme(parent);
+	if (error)
+		return error;
+
+	return aa_ptrace(parent, current, PTRACE_MODE_ATTACH);
+}
+
+/* Derived from security/commoncap.c:cap_capget */
+static int apparmor_capget(struct task_struct *target, kernel_cap_t *effective,
+			   kernel_cap_t *inheritable, kernel_cap_t *permitted)
+{
+	struct aa_profile *profile;
+	const struct cred *cred;
+
+	rcu_read_lock();
+	cred = __task_cred(target);
+	profile = aa_cred_profile(cred);
+
+	*effective = cred->cap_effective;
+	*inheritable = cred->cap_inheritable;
+	*permitted = cred->cap_permitted;
+
+	if (!unconfined(profile) && !COMPLAIN_MODE(profile)) {
+		*effective = cap_intersect(*effective, profile->caps.allow);
+		*permitted = cap_intersect(*permitted, profile->caps.allow);
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int apparmor_capable(const struct cred *cred, struct user_namespace *ns,
+			    int cap, int audit)
+{
+	struct aa_profile *profile;
+	/* cap_capable returns 0 on success, else -EPERM */
+	int error = cap_capable(cred, ns, cap, audit);
+	if (!error) {
+		profile = aa_cred_profile(cred);
+		if (!unconfined(profile))
+			error = aa_capable(profile, cap, audit);
+	}
+	return error;
+}
+
+/**
+ * common_perm - basic common permission check wrapper fn for paths
+ * @op: operation being checked
+ * @path: path to check permission of  (NOT NULL)
+ * @mask: requested permissions mask
+ * @cond: conditional info for the permission request  (NOT NULL)
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm(int op, struct path *path, u32 mask,
+		       struct path_cond *cond)
+{
+	struct aa_profile *profile;
+	int error = 0;
+
+	profile = __aa_current_profile();
+	if (!unconfined(profile))
+		error = aa_path_perm(op, profile, path, 0, mask, cond);
+
+	return error;
+}
+
+/**
+ * common_perm_dir_dentry - common permission wrapper when path is dir, dentry
+ * @op: operation being checked
+ * @dir: directory of the dentry  (NOT NULL)
+ * @dentry: dentry to check  (NOT NULL)
+ * @mask: requested permissions mask
+ * @cond: conditional info for the permission request  (NOT NULL)
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm_dir_dentry(int op, struct path *dir,
+				  struct dentry *dentry, u32 mask,
+				  struct path_cond *cond)
+{
+	struct path path = { dir->mnt, dentry };
+
+	return common_perm(op, &path, mask, cond);
+}
+
+/**
+ * common_perm_mnt_dentry - common permission wrapper when mnt, dentry
+ * @op: operation being checked
+ * @mnt: mount point of dentry (NOT NULL)
+ * @dentry: dentry to check  (NOT NULL)
+ * @mask: requested permissions mask
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm_mnt_dentry(int op, struct vfsmount *mnt,
+				  struct dentry *dentry, u32 mask)
+{
+	struct path path = { mnt, dentry };
+	struct path_cond cond = { dentry->d_inode->i_uid,
+				  dentry->d_inode->i_mode
+	};
+
+	return common_perm(op, &path, mask, &cond);
+}
+
+/**
+ * common_perm_rm - common permission wrapper for operations doing rm
+ * @op: operation being checked
+ * @dir: directory that the dentry is in  (NOT NULL)
+ * @dentry: dentry being rm'd  (NOT NULL)
+ * @mask: requested permission mask
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm_rm(int op, struct path *dir,
+			  struct dentry *dentry, u32 mask)
+{
+	struct inode *inode = dentry->d_inode;
+	struct path_cond cond = { };
+
+	if (!inode || !dir->mnt || !mediated_filesystem(inode))
+		return 0;
+
+	cond.uid = inode->i_uid;
+	cond.mode = inode->i_mode;
+
+	return common_perm_dir_dentry(op, dir, dentry, mask, &cond);
+}
+
+/**
+ * common_perm_create - common permission wrapper for operations doing create
+ * @op: operation being checked
+ * @dir: directory that dentry will be created in  (NOT NULL)
+ * @dentry: dentry to create   (NOT NULL)
+ * @mask: request permission mask
+ * @mode: created file mode
+ *
+ * Returns: %0 else error code if error or permission denied
+ */
+static int common_perm_create(int op, struct path *dir, struct dentry *dentry,
+			      u32 mask, umode_t mode)
+{
+	struct path_cond cond = { current_fsuid(), mode };
+
+	if (!dir->mnt || !mediated_filesystem(dir->dentry->d_inode))
+		return 0;
+
+	return common_perm_dir_dentry(op, dir, dentry, mask, &cond);
+}
+
+static int apparmor_path_unlink(struct path *dir, struct dentry *dentry)
+{
+	return common_perm_rm(OP_UNLINK, dir, dentry, AA_MAY_DELETE);
+}
+
+static int apparmor_path_mkdir(struct path *dir, struct dentry *dentry,
+			       umode_t mode)
+{
+	return common_perm_create(OP_MKDIR, dir, dentry, AA_MAY_CREATE,
+				  S_IFDIR);
+}
+
+static int apparmor_path_rmdir(struct path *dir, struct dentry *dentry)
+{
+	return common_perm_rm(OP_RMDIR, dir, dentry, AA_MAY_DELETE);
+}
+
+static int apparmor_path_mknod(struct path *dir, struct dentry *dentry,
+			       umode_t mode, unsigned int dev)
+{
+	return common_perm_create(OP_MKNOD, dir, dentry, AA_MAY_CREATE, mode);
+}
+
+static int apparmor_path_truncate(struct path *path)
+{
+	struct path_cond cond = { path->dentry->d_inode->i_uid,
+				  path->dentry->d_inode->i_mode
+	};
+
+	if (!path->mnt || !mediated_filesystem(path->dentry->d_inode))
+		return 0;
+
+	return common_perm(OP_TRUNC, path, MAY_WRITE | AA_MAY_META_WRITE,
+			   &cond);
+}
+
+static int apparmor_path_symlink(struct path *dir, struct dentry *dentry,
+				 const char *old_name)
+{
+	return common_perm_create(OP_SYMLINK, dir, dentry, AA_MAY_CREATE,
+				  S_IFLNK);
+}
+
+static int apparmor_path_link(struct dentry *old_dentry, struct path *new_dir,
+			      struct dentry *new_dentry)
+{
+	struct aa_profile *profile;
+	int error = 0;
+
+	if (!mediated_filesystem(old_dentry->d_inode))
+		return 0;
+
+	profile = aa_current_profile();
+	if (!unconfined(profile))
+		error = aa_path_link(profile, old_dentry, new_dir, new_dentry);
+	return error;
+}
+
+static int apparmor_path_rename(struct path *old_dir, struct dentry *old_dentry,
+				struct path *new_dir, struct dentry *new_dentry)
+{
+	struct aa_profile *profile;
+	int error = 0;
+
+	if (!mediated_filesystem(old_dentry->d_inode))
+		return 0;
+
+	profile = aa_current_profile();
+	if (!unconfined(profile)) {
+		struct path old_path = { old_dir->mnt, old_dentry };
+		struct path new_path = { new_dir->mnt, new_dentry };
+		struct path_cond cond = { old_dentry->d_inode->i_uid,
+					  old_dentry->d_inode->i_mode
+		};
+
+		error = aa_path_perm(OP_RENAME_SRC, profile, &old_path, 0,
+				     MAY_READ | AA_MAY_META_READ | MAY_WRITE |
+				     AA_MAY_META_WRITE | AA_MAY_DELETE,
+				     &cond);
+		if (!error)
+			error = aa_path_perm(OP_RENAME_DEST, profile, &new_path,
+					     0, MAY_WRITE | AA_MAY_META_WRITE |
+					     AA_MAY_CREATE, &cond);
+
+	}
+	return error;
+}
+
+static int apparmor_path_chmod(struct path *path, umode_t mode)
+{
+	if (!mediated_filesystem(path->dentry->d_inode))
+		return 0;
+
+	return common_perm_mnt_dentry(OP_CHMOD, path->mnt, path->dentry, AA_MAY_CHMOD);
+}
+
+static int apparmor_path_chown(struct path *path, kuid_t uid, kgid_t gid)
+{
+	struct path_cond cond =  { path->dentry->d_inode->i_uid,
+				   path->dentry->d_inode->i_mode
+	};
+
+	if (!mediated_filesystem(path->dentry->d_inode))
+		return 0;
+
+	return common_perm(OP_CHOWN, path, AA_MAY_CHOWN, &cond);
+}
+
+static int apparmor_inode_getattr(struct vfsmount *mnt, struct dentry *dentry)
+{
+	if (!mediated_filesystem(dentry->d_inode))
+		return 0;
+
+	return common_perm_mnt_dentry(OP_GETATTR, mnt, dentry,
+				      AA_MAY_META_READ);
+}
+
+static int apparmor_file_open(struct file *file, const struct cred *cred)
+{
+	struct aa_file_cxt *fcxt = file->f_security;
+	struct aa_profile *profile;
+	int error = 0;
+
+	if (!mediated_filesystem(file_inode(file)))
+		return 0;
+
+	/* If in exec, permission is handled by bprm hooks.
+	 * Cache permissions granted by the previous exec check, with
+	 * implicit read and executable mmap which are required to
+	 * actually execute the image.
+	 */
+	if (current->in_execve) {
+		fcxt->allow = MAY_EXEC | MAY_READ | AA_EXEC_MMAP;
+		return 0;
+	}
+
+	profile = aa_cred_profile(cred);
+	if (!unconfined(profile)) {
+		struct inode *inode = file_inode(file);
+		struct path_cond cond = { inode->i_uid, inode->i_mode };
+
+		error = aa_path_perm(OP_OPEN, profile, &file->f_path, 0,
+				     aa_map_file_to_perms(file), &cond);
+		/* todo cache full allowed permissions set and state */
+		fcxt->allow = aa_map_file_to_perms(file);
+	}
+
+	return error;
+}
+
+static int apparmor_file_alloc_security(struct file *file)
+{
+	/* freed by apparmor_file_free_security */
+	file->f_security = aa_alloc_file_context(GFP_KERNEL);
+	if (!file->f_security)
+		return -ENOMEM;
+	return 0;
+
+}
+
+static void apparmor_file_free_security(struct file *file)
+{
+	struct aa_file_cxt *cxt = file->f_security;
+
+	aa_free_file_context(cxt);
+}
+
+static int common_file_perm(int op, struct file *file, u32 mask)
+{
+	struct aa_file_cxt *fcxt = file->f_security;
+	struct aa_profile *profile, *fprofile = aa_cred_profile(file->f_cred);
+	int error = 0;
+
+	BUG_ON(!fprofile);
+
+	if (!file->f_path.mnt ||
+	    !mediated_filesystem(file_inode(file)))
+		return 0;
+
+	profile = __aa_current_profile();
+
+	/* revalidate access, if task is unconfined, or the cached cred
+	 * doesn't match or if the request is for more permissions than
+	 * was granted.
+	 *
+	 * Note: the test for !unconfined(fprofile) is to handle file
+	 *       delegation from unconfined tasks
+	 */
+	if (!unconfined(profile) && !unconfined(fprofile) &&
+	    ((fprofile != profile) || (mask & ~fcxt->allow)))
+		error = aa_file_perm(op, profile, file, mask);
+
+	return error;
+}
+
+static int apparmor_file_permission(struct file *file, int mask)
+{
+	return common_file_perm(OP_FPERM, file, mask);
+}
+
+static int apparmor_file_lock(struct file *file, unsigned int cmd)
+{
+	u32 mask = AA_MAY_LOCK;
+
+	if (cmd == F_WRLCK)
+		mask |= MAY_WRITE;
+
+	return common_file_perm(OP_FLOCK, file, mask);
+}
+
+static int common_mmap(int op, struct file *file, unsigned long prot,
+		       unsigned long flags)
+{
+	int mask = 0;
+
+	if (!file || !file->f_security)
+		return 0;
+
+	if (prot & PROT_READ)
+		mask |= MAY_READ;
+	/*
+	 * Private mappings don't require write perms since they don't
+	 * write back to the files
+	 */
+	if ((prot & PROT_WRITE) && !(flags & MAP_PRIVATE))
+		mask |= MAY_WRITE;
+	if (prot & PROT_EXEC)
+		mask |= AA_EXEC_MMAP;
+
+	return common_file_perm(op, file, mask);
+}
+
+static int apparmor_mmap_file(struct file *file, unsigned long reqprot,
+			      unsigned long prot, unsigned long flags)
+{
+	return common_mmap(OP_FMMAP, file, prot, flags);
+}
+
+static int apparmor_file_mprotect(struct vm_area_struct *vma,
+				  unsigned long reqprot, unsigned long prot)
+{
+	return common_mmap(OP_FMPROT, vma->vm_file, prot,
+			   !(vma->vm_flags & VM_SHARED) ? MAP_PRIVATE : 0);
+}
+
+static int apparmor_getprocattr(struct task_struct *task, char *name,
+				char **value)
+{
+	int error = -ENOENT;
+	/* released below */
+	const struct cred *cred = get_task_cred(task);
+	struct aa_task_cxt *cxt = cred_cxt(cred);
+	struct aa_profile *profile = NULL;
+
+	if (strcmp(name, "current") == 0)
+		profile = aa_get_newest_profile(cxt->profile);
+	else if (strcmp(name, "prev") == 0  && cxt->previous)
+		profile = aa_get_newest_profile(cxt->previous);
+	else if (strcmp(name, "exec") == 0 && cxt->onexec)
+		profile = aa_get_newest_profile(cxt->onexec);
+	else
+		error = -EINVAL;
+
+	if (profile)
+		error = aa_getprocattr(profile, value);
+
+	aa_put_profile(profile);
+	put_cred(cred);
+
+	return error;
+}
+
+static int apparmor_setprocattr(struct task_struct *task, char *name,
+				void *value, size_t size)
+{
+	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
+	char *command, *args = value;
+	size_t arg_size;
+	int error;
+
+	if (size == 0)
+		return -EINVAL;
+	/* args points to a PAGE_SIZE buffer, AppArmor requires that
+	 * the buffer must be null terminated or have size <= PAGE_SIZE -1
+	 * so that AppArmor can null terminate them
+	 */
+	if (args[size - 1] != '\0') {
+		if (size == PAGE_SIZE)
+			return -EINVAL;
+		args[size] = '\0';
+	}
+
+	/* task can only write its own attributes */
+	if (current != task)
+		return -EACCES;
+
+	args = value;
+	args = strim(args);
+	command = strsep(&args, " ");
+	if (!args)
+		return -EINVAL;
+	args = skip_spaces(args);
+	if (!*args)
+		return -EINVAL;
+
+	arg_size = size - (args - (char *) value);
+	if (strcmp(name, "current") == 0) {
+		if (strcmp(command, "changehat") == 0) {
+			error = aa_setprocattr_changehat(args, arg_size,
+							 !AA_DO_TEST);
+		} else if (strcmp(command, "permhat") == 0) {
+			error = aa_setprocattr_changehat(args, arg_size,
+							 AA_DO_TEST);
+		} else if (strcmp(command, "changeprofile") == 0) {
+			error = aa_setprocattr_changeprofile(args, !AA_ONEXEC,
+							     !AA_DO_TEST);
+		} else if (strcmp(command, "permprofile") == 0) {
+			error = aa_setprocattr_changeprofile(args, !AA_ONEXEC,
+							     AA_DO_TEST);
+		} else
+			goto fail;
+	} else if (strcmp(name, "exec") == 0) {
+		if (strcmp(command, "exec") == 0)
+			error = aa_setprocattr_changeprofile(args, AA_ONEXEC,
+							     !AA_DO_TEST);
+		else
+			goto fail;
+	} else
+		/* only support the "current" and "exec" process attributes */
+		return -EINVAL;
+
+	if (!error)
+		error = size;
+	return error;
+
+fail:
+	sa.type = LSM_AUDIT_DATA_NONE;
+	sa.aad = &aad;
+	aad.profile = aa_current_profile();
+	aad.op = OP_SETPROCATTR;
+	aad.info = name;
+	aad.error = -EINVAL;
+	aa_audit_msg(AUDIT_APPARMOR_DENIED, &sa, NULL);
+	return -EINVAL;
+}
+
+static int apparmor_task_setrlimit(struct task_struct *task,
+		unsigned int resource, struct rlimit *new_rlim)
+{
+	struct aa_profile *profile = __aa_current_profile();
+	int error = 0;
+
+	if (!unconfined(profile))
+		error = aa_task_setrlimit(profile, task, resource, new_rlim);
+
+	return error;
+}
+
+static struct security_operations apparmor_ops = {
+	.name =				"apparmor",
+
+	.ptrace_access_check =		apparmor_ptrace_access_check,
+	.ptrace_traceme =		apparmor_ptrace_traceme,
+	.capget =			apparmor_capget,
+	.capable =			apparmor_capable,
+
+	.path_link =			apparmor_path_link,
+	.path_unlink =			apparmor_path_unlink,
+	.path_symlink =			apparmor_path_symlink,
+	.path_mkdir =			apparmor_path_mkdir,
+	.path_rmdir =			apparmor_path_rmdir,
+	.path_mknod =			apparmor_path_mknod,
+	.path_rename =			apparmor_path_rename,
+	.path_chmod =			apparmor_path_chmod,
+	.path_chown =			apparmor_path_chown,
+	.path_truncate =		apparmor_path_truncate,
+	.inode_getattr =                apparmor_inode_getattr,
+
+	.file_open =			apparmor_file_open,
+	.file_permission =		apparmor_file_permission,
+	.file_alloc_security =		apparmor_file_alloc_security,
+	.file_free_security =		apparmor_file_free_security,
+	.mmap_file =			apparmor_mmap_file,
+	.mmap_addr =			cap_mmap_addr,
+	.file_mprotect =		apparmor_file_mprotect,
+	.file_lock =			apparmor_file_lock,
+
+	.getprocattr =			apparmor_getprocattr,
+	.setprocattr =			apparmor_setprocattr,
+
+	.cred_alloc_blank =		apparmor_cred_alloc_blank,
+	.cred_free =			apparmor_cred_free,
+	.cred_prepare =			apparmor_cred_prepare,
+	.cred_transfer =		apparmor_cred_transfer,
+
+	.bprm_set_creds =		apparmor_bprm_set_creds,
+	.bprm_committing_creds =	apparmor_bprm_committing_creds,
+	.bprm_committed_creds =		apparmor_bprm_committed_creds,
+	.bprm_secureexec =		apparmor_bprm_secureexec,
+
+	.task_setrlimit =		apparmor_task_setrlimit,
+};
+
+/*
+ * AppArmor sysfs module parameters
+ */
+
+static int param_set_aabool(const char *val, const struct kernel_param *kp);
+static int param_get_aabool(char *buffer, const struct kernel_param *kp);
+#define param_check_aabool param_check_bool
+static struct kernel_param_ops param_ops_aabool = {
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
+	.set = param_set_aabool,
+	.get = param_get_aabool
+};
+
+static int param_set_aauint(const char *val, const struct kernel_param *kp);
+static int param_get_aauint(char *buffer, const struct kernel_param *kp);
+#define param_check_aauint param_check_uint
+static struct kernel_param_ops param_ops_aauint = {
+	.set = param_set_aauint,
+	.get = param_get_aauint
+};
+
+static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp);
+static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp);
+#define param_check_aalockpolicy param_check_bool
+static struct kernel_param_ops param_ops_aalockpolicy = {
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
+	.set = param_set_aalockpolicy,
+	.get = param_get_aalockpolicy
+};
+
+static int param_set_audit(const char *val, struct kernel_param *kp);
+static int param_get_audit(char *buffer, struct kernel_param *kp);
+
+static int param_set_mode(const char *val, struct kernel_param *kp);
+static int param_get_mode(char *buffer, struct kernel_param *kp);
+
+/* Flag values, also controllable via /sys/module/apparmor/parameters
+ * We define special types as we want to do additional mediation.
+ */
+
+/* AppArmor global enforcement switch - complain, enforce, kill */
+enum profile_mode aa_g_profile_mode = APPARMOR_ENFORCE;
+module_param_call(mode, param_set_mode, param_get_mode,
+		  &aa_g_profile_mode, S_IRUSR | S_IWUSR);
+
+/* Debug mode */
+bool aa_g_debug;
+module_param_named(debug, aa_g_debug, aabool, S_IRUSR | S_IWUSR);
+
+/* Audit mode */
+enum audit_mode aa_g_audit;
+module_param_call(audit, param_set_audit, param_get_audit,
+		  &aa_g_audit, S_IRUSR | S_IWUSR);
+
+/* Determines if audit header is included in audited messages.  This
+ * provides more context if the audit daemon is not running
+ */
+bool aa_g_audit_header = 1;
+module_param_named(audit_header, aa_g_audit_header, aabool,
+		   S_IRUSR | S_IWUSR);
+
+/* lock out loading/removal of policy
+ * TODO: add in at boot loading of policy, which is the only way to
+ *       load policy, if lock_policy is set
+ */
+bool aa_g_lock_policy;
+module_param_named(lock_policy, aa_g_lock_policy, aalockpolicy,
+		   S_IRUSR | S_IWUSR);
+
+/* Syscall logging mode */
+bool aa_g_logsyscall;
+module_param_named(logsyscall, aa_g_logsyscall, aabool, S_IRUSR | S_IWUSR);
+
+/* Maximum pathname length before accesses will start getting rejected */
+unsigned int aa_g_path_max = 2 * PATH_MAX;
+module_param_named(path_max, aa_g_path_max, aauint, S_IRUSR | S_IWUSR);
+
+/* Determines how paranoid loading of policy is and how much verification
+ * on the loaded policy is done.
+ */
+bool aa_g_paranoid_load = 1;
+module_param_named(paranoid_load, aa_g_paranoid_load, aabool,
+		   S_IRUSR | S_IWUSR);
+
+/* Boot time disable flag */
+static bool apparmor_enabled = CONFIG_SECURITY_APPARMOR_BOOTPARAM_VALUE;
+module_param_named(enabled, apparmor_enabled, bool, S_IRUGO);
+
+static int __init apparmor_enabled_setup(char *str)
+{
+	unsigned long enabled;
+	int error = kstrtoul(str, 0, &enabled);
+	if (!error)
+		apparmor_enabled = enabled ? 1 : 0;
+	return 1;
+}
+
+__setup("apparmor=", apparmor_enabled_setup);
+
+/* set global flag turning off the ability to load policy */
+static int param_set_aalockpolicy(const char *val, const struct kernel_param *kp)
+{
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+	if (aa_g_lock_policy)
+		return -EACCES;
+	return param_set_bool(val, kp);
+}
+
+static int param_get_aalockpolicy(char *buffer, const struct kernel_param *kp)
+{
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+	return param_get_bool(buffer, kp);
+}
+
+static int param_set_aabool(const char *val, const struct kernel_param *kp)
+{
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+	return param_set_bool(val, kp);
+}
+
+static int param_get_aabool(char *buffer, const struct kernel_param *kp)
+{
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+	return param_get_bool(buffer, kp);
+}
+
+static int param_set_aauint(const char *val, const struct kernel_param *kp)
+{
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+	return param_set_uint(val, kp);
+}
+
+static int param_get_aauint(char *buffer, const struct kernel_param *kp)
+{
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+	return param_get_uint(buffer, kp);
+}
+
+static int param_get_audit(char *buffer, struct kernel_param *kp)
+{
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (!apparmor_enabled)
+		return -EINVAL;
+
+	return sprintf(buffer, "%s", audit_mode_names[aa_g_audit]);
+}
+
+static int param_set_audit(const char *val, struct kernel_param *kp)
+{
+	int i;
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (!apparmor_enabled)
+		return -EINVAL;
+
+	if (!val)
+		return -EINVAL;
+
+	for (i = 0; i < AUDIT_MAX_INDEX; i++) {
+		if (strcmp(val, audit_mode_names[i]) == 0) {
+			aa_g_audit = i;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int param_get_mode(char *buffer, struct kernel_param *kp)
+{
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (!apparmor_enabled)
+		return -EINVAL;
+
+	return sprintf(buffer, "%s", aa_profile_mode_names[aa_g_profile_mode]);
+}
+
+static int param_set_mode(const char *val, struct kernel_param *kp)
+{
+	int i;
+	if (!capable(CAP_MAC_ADMIN))
+		return -EPERM;
+
+	if (!apparmor_enabled)
+		return -EINVAL;
+
+	if (!val)
+		return -EINVAL;
+
+	for (i = 0; i < APPARMOR_MODE_NAMES_MAX_INDEX; i++) {
+		if (strcmp(val, aa_profile_mode_names[i]) == 0) {
+			aa_g_profile_mode = i;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+/*
+ * AppArmor init functions
+ */
+
+/**
+ * set_init_cxt - set a task context and profile on the first task.
+ *
+ * TODO: allow setting an alternate profile than unconfined
+ */
+static int __init set_init_cxt(void)
+{
+	struct cred *cred = (struct cred *)current->real_cred;
+	struct aa_task_cxt *cxt;
+
+	cxt = aa_alloc_task_context(GFP_KERNEL);
+	if (!cxt)
+		return -ENOMEM;
+
+	cxt->profile = aa_get_profile(root_ns->unconfined);
+	cred_cxt(cred) = cxt;
+
+	return 0;
+}
+
+static int __init apparmor_init(void)
+{
+	int error;
+
+	if (!apparmor_enabled || !security_module_enable(&apparmor_ops)) {
+		aa_info_message("AppArmor disabled by boot time parameter");
+		apparmor_enabled = 0;
+		return 0;
+	}
+
+	error = aa_alloc_root_ns();
+	if (error) {
+		AA_ERROR("Unable to allocate default profile namespace\n");
+		goto alloc_out;
+	}
+
+	error = set_init_cxt();
+	if (error) {
+		AA_ERROR("Failed to set context on init task\n");
+		goto register_security_out;
+	}
+
+	error = register_security(&apparmor_ops);
+	if (error) {
+		struct cred *cred = (struct cred *)current->real_cred;
+		aa_free_task_context(cred_cxt(cred));
+		cred_cxt(cred) = NULL;
+		AA_ERROR("Unable to register AppArmor\n");
+		goto register_security_out;
+	}
+
+	/* Report that AppArmor successfully initialized */
+	apparmor_initialized = 1;
+	if (aa_g_profile_mode == APPARMOR_COMPLAIN)
+		aa_info_message("AppArmor initialized: complain mode enabled");
+	else if (aa_g_profile_mode == APPARMOR_KILL)
+		aa_info_message("AppArmor initialized: kill mode enabled");
+	else
+		aa_info_message("AppArmor initialized");
+
+	return error;
+
+register_security_out:
+	aa_free_root_ns();
+
+alloc_out:
+	aa_destroy_aafs();
+
+	apparmor_enabled = 0;
+	return error;
+}
+
+security_initcall(apparmor_init);

security/apparmor/match.c

@@ -0,0 +1,428 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor dfa based regular expression matching engine
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2012 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/err.h>
+#include <linux/kref.h>
+
+#include "include/apparmor.h"
+#include "include/match.h"
+
+#define base_idx(X) ((X) & 0xffffff)
+
+/**
+ * unpack_table - unpack a dfa table (one of accept, default, base, next check)
+ * @blob: data to unpack (NOT NULL)
+ * @bsize: size of blob
+ *
+ * Returns: pointer to table else NULL on failure
+ *
+ * NOTE: must be freed by kvfree (not kfree)
+ */
+static struct table_header *unpack_table(char *blob, size_t bsize)
+{
+	struct table_header *table = NULL;
+	struct table_header th;
+	size_t tsize;
+
+	if (bsize < sizeof(struct table_header))
+		goto out;
+
+	/* loaded td_id's start at 1, subtract 1 now to avoid doing
+	 * it every time we use td_id as an index
+	 */
+	th.td_id = be16_to_cpu(*(u16 *) (blob)) - 1;
+	th.td_flags = be16_to_cpu(*(u16 *) (blob + 2));
+	th.td_lolen = be32_to_cpu(*(u32 *) (blob + 8));
+	blob += sizeof(struct table_header);
+
+	if (!(th.td_flags == YYTD_DATA16 || th.td_flags == YYTD_DATA32 ||
+	      th.td_flags == YYTD_DATA8))
+		goto out;
+
+	tsize = table_size(th.td_lolen, th.td_flags);
+	if (bsize < tsize)
+		goto out;
+
+	table = kvzalloc(tsize);
+	if (table) {
+		*table = th;
+		if (th.td_flags == YYTD_DATA8)
+			UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
+				     u8, byte_to_byte);
+		else if (th.td_flags == YYTD_DATA16)
+			UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
+				     u16, be16_to_cpu);
+		else if (th.td_flags == YYTD_DATA32)
+			UNPACK_ARRAY(table->td_data, blob, th.td_lolen,
+				     u32, be32_to_cpu);
+		else
+			goto fail;
+	}
+
+out:
+	/* if table was vmalloced make sure the page tables are synced
+	 * before it is used, as it goes live to all cpus.
+	 */
+	if (is_vmalloc_addr(table))
+		vm_unmap_aliases();
+	return table;
+fail:
+	kvfree(table);
+	return NULL;
+}
+
+/**
+ * verify_dfa - verify that transitions and states in the tables are in bounds.
+ * @dfa: dfa to test  (NOT NULL)
+ * @flags: flags controlling what type of accept table are acceptable
+ *
+ * Assumes dfa has gone through the first pass verification done by unpacking
+ * NOTE: this does not valid accept table values
+ *
+ * Returns: %0 else error code on failure to verify
+ */
+static int verify_dfa(struct aa_dfa *dfa, int flags)
+{
+	size_t i, state_count, trans_count;
+	int error = -EPROTO;
+
+	/* check that required tables exist */
+	if (!(dfa->tables[YYTD_ID_DEF] &&
+	      dfa->tables[YYTD_ID_BASE] &&
+	      dfa->tables[YYTD_ID_NXT] && dfa->tables[YYTD_ID_CHK]))
+		goto out;
+
+	/* accept.size == default.size == base.size */
+	state_count = dfa->tables[YYTD_ID_BASE]->td_lolen;
+	if (ACCEPT1_FLAGS(flags)) {
+		if (!dfa->tables[YYTD_ID_ACCEPT])
+			goto out;
+		if (state_count != dfa->tables[YYTD_ID_ACCEPT]->td_lolen)
+			goto out;
+	}
+	if (ACCEPT2_FLAGS(flags)) {
+		if (!dfa->tables[YYTD_ID_ACCEPT2])
+			goto out;
+		if (state_count != dfa->tables[YYTD_ID_ACCEPT2]->td_lolen)
+			goto out;
+	}
+	if (state_count != dfa->tables[YYTD_ID_DEF]->td_lolen)
+		goto out;
+
+	/* next.size == chk.size */
+	trans_count = dfa->tables[YYTD_ID_NXT]->td_lolen;
+	if (trans_count != dfa->tables[YYTD_ID_CHK]->td_lolen)
+		goto out;
+
+	/* if equivalence classes then its table size must be 256 */
+	if (dfa->tables[YYTD_ID_EC] &&
+	    dfa->tables[YYTD_ID_EC]->td_lolen != 256)
+		goto out;
+
+	if (flags & DFA_FLAG_VERIFY_STATES) {
+		for (i = 0; i < state_count; i++) {
+			if (DEFAULT_TABLE(dfa)[i] >= state_count)
+				goto out;
+			if (base_idx(BASE_TABLE(dfa)[i]) + 255 >= trans_count) {
+				printk(KERN_ERR "AppArmor DFA next/check upper "
+				       "bounds error\n");
+				goto out;
+			}
+		}
+
+		for (i = 0; i < trans_count; i++) {
+			if (NEXT_TABLE(dfa)[i] >= state_count)
+				goto out;
+			if (CHECK_TABLE(dfa)[i] >= state_count)
+				goto out;
+		}
+	}
+
+	error = 0;
+out:
+	return error;
+}
+
+/**
+ * dfa_free - free a dfa allocated by aa_dfa_unpack
+ * @dfa: the dfa to free  (MAYBE NULL)
+ *
+ * Requires: reference count to dfa == 0
+ */
+static void dfa_free(struct aa_dfa *dfa)
+{
+	if (dfa) {
+		int i;
+
+		for (i = 0; i < ARRAY_SIZE(dfa->tables); i++) {
+			kvfree(dfa->tables[i]);
+			dfa->tables[i] = NULL;
+		}
+		kfree(dfa);
+	}
+}
+
+/**
+ * aa_dfa_free_kref - free aa_dfa by kref (called by aa_put_dfa)
+ * @kr: kref callback for freeing of a dfa  (NOT NULL)
+ */
+void aa_dfa_free_kref(struct kref *kref)
+{
+	struct aa_dfa *dfa = container_of(kref, struct aa_dfa, count);
+	dfa_free(dfa);
+}
+
+/**
+ * aa_dfa_unpack - unpack the binary tables of a serialized dfa
+ * @blob: aligned serialized stream of data to unpack  (NOT NULL)
+ * @size: size of data to unpack
+ * @flags: flags controlling what type of accept tables are acceptable
+ *
+ * Unpack a dfa that has been serialized.  To find information on the dfa
+ * format look in Documentation/security/apparmor.txt
+ * Assumes the dfa @blob stream has been aligned on a 8 byte boundary
+ *
+ * Returns: an unpacked dfa ready for matching or ERR_PTR on failure
+ */
+struct aa_dfa *aa_dfa_unpack(void *blob, size_t size, int flags)
+{
+	int hsize;
+	int error = -ENOMEM;
+	char *data = blob;
+	struct table_header *table = NULL;
+	struct aa_dfa *dfa = kzalloc(sizeof(struct aa_dfa), GFP_KERNEL);
+	if (!dfa)
+		goto fail;
+
+	kref_init(&dfa->count);
+
+	error = -EPROTO;
+
+	/* get dfa table set header */
+	if (size < sizeof(struct table_set_header))
+		goto fail;
+
+	if (ntohl(*(u32 *) data) != YYTH_MAGIC)
+		goto fail;
+
+	hsize = ntohl(*(u32 *) (data + 4));
+	if (size < hsize)
+		goto fail;
+
+	dfa->flags = ntohs(*(u16 *) (data + 12));
+	data += hsize;
+	size -= hsize;
+
+	while (size > 0) {
+		table = unpack_table(data, size);
+		if (!table)
+			goto fail;
+
+		switch (table->td_id) {
+		case YYTD_ID_ACCEPT:
+			if (!(table->td_flags & ACCEPT1_FLAGS(flags)))
+				goto fail;
+			break;
+		case YYTD_ID_ACCEPT2:
+			if (!(table->td_flags & ACCEPT2_FLAGS(flags)))
+				goto fail;
+			break;
+		case YYTD_ID_BASE:
+			if (table->td_flags != YYTD_DATA32)
+				goto fail;
+			break;
+		case YYTD_ID_DEF:
+		case YYTD_ID_NXT:
+		case YYTD_ID_CHK:
+			if (table->td_flags != YYTD_DATA16)
+				goto fail;
+			break;
+		case YYTD_ID_EC:
+			if (table->td_flags != YYTD_DATA8)
+				goto fail;
+			break;
+		default:
+			goto fail;
+		}
+		/* check for duplicate table entry */
+		if (dfa->tables[table->td_id])
+			goto fail;
+		dfa->tables[table->td_id] = table;
+		data += table_size(table->td_lolen, table->td_flags);
+		size -= table_size(table->td_lolen, table->td_flags);
+		table = NULL;
+	}
+
+	error = verify_dfa(dfa, flags);
+	if (error)
+		goto fail;
+
+	return dfa;
+
+fail:
+	kvfree(table);
+	dfa_free(dfa);
+	return ERR_PTR(error);
+}
+
+/**
+ * aa_dfa_match_len - traverse @dfa to find state @str stops at
+ * @dfa: the dfa to match @str against  (NOT NULL)
+ * @start: the state of the dfa to start matching in
+ * @str: the string of bytes to match against the dfa  (NOT NULL)
+ * @len: length of the string of bytes to match
+ *
+ * aa_dfa_match_len will match @str against the dfa and return the state it
+ * finished matching in. The final state can be used to look up the accepting
+ * label, or as the start state of a continuing match.
+ *
+ * This function will happily match again the 0 byte and only finishes
+ * when @len input is consumed.
+ *
+ * Returns: final state reached after input is consumed
+ */
+unsigned int aa_dfa_match_len(struct aa_dfa *dfa, unsigned int start,
+			      const char *str, int len)
+{
+	u16 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u16 *next = NEXT_TABLE(dfa);
+	u16 *check = CHECK_TABLE(dfa);
+	unsigned int state = start, pos;
+
+	if (state == 0)
+		return 0;
+
+	/* current state is <state>, matching character *str */
+	if (dfa->tables[YYTD_ID_EC]) {
+		/* Equivalence class table defined */
+		u8 *equiv = EQUIV_TABLE(dfa);
+		/* default is direct to next state */
+		for (; len; len--) {
+			pos = base_idx(base[state]) + equiv[(u8) *str++];
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+		}
+	} else {
+		/* default is direct to next state */
+		for (; len; len--) {
+			pos = base_idx(base[state]) + (u8) *str++;
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+		}
+	}
+
+	return state;
+}
+
+/**
+ * aa_dfa_match - traverse @dfa to find state @str stops at
+ * @dfa: the dfa to match @str against  (NOT NULL)
+ * @start: the state of the dfa to start matching in
+ * @str: the null terminated string of bytes to match against the dfa (NOT NULL)
+ *
+ * aa_dfa_match will match @str against the dfa and return the state it
+ * finished matching in. The final state can be used to look up the accepting
+ * label, or as the start state of a continuing match.
+ *
+ * Returns: final state reached after input is consumed
+ */
+unsigned int aa_dfa_match(struct aa_dfa *dfa, unsigned int start,
+			  const char *str)
+{
+	u16 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u16 *next = NEXT_TABLE(dfa);
+	u16 *check = CHECK_TABLE(dfa);
+	unsigned int state = start, pos;
+
+	if (state == 0)
+		return 0;
+
+	/* current state is <state>, matching character *str */
+	if (dfa->tables[YYTD_ID_EC]) {
+		/* Equivalence class table defined */
+		u8 *equiv = EQUIV_TABLE(dfa);
+		/* default is direct to next state */
+		while (*str) {
+			pos = base_idx(base[state]) + equiv[(u8) *str++];
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+		}
+	} else {
+		/* default is direct to next state */
+		while (*str) {
+			pos = base_idx(base[state]) + (u8) *str++;
+			if (check[pos] == state)
+				state = next[pos];
+			else
+				state = def[state];
+		}
+	}
+
+	return state;
+}
+
+/**
+ * aa_dfa_next - step one character to the next state in the dfa
+ * @dfa: the dfa to tranverse (NOT NULL)
+ * @state: the state to start in
+ * @c: the input character to transition on
+ *
+ * aa_dfa_match will step through the dfa by one input character @c
+ *
+ * Returns: state reach after input @c
+ */
+unsigned int aa_dfa_next(struct aa_dfa *dfa, unsigned int state,
+			  const char c)
+{
+	u16 *def = DEFAULT_TABLE(dfa);
+	u32 *base = BASE_TABLE(dfa);
+	u16 *next = NEXT_TABLE(dfa);
+	u16 *check = CHECK_TABLE(dfa);
+	unsigned int pos;
+
+	/* current state is <state>, matching character *str */
+	if (dfa->tables[YYTD_ID_EC]) {
+		/* Equivalence class table defined */
+		u8 *equiv = EQUIV_TABLE(dfa);
+		/* default is direct to next state */
+
+		pos = base_idx(base[state]) + equiv[(u8) c];
+		if (check[pos] == state)
+			state = next[pos];
+		else
+			state = def[state];
+	} else {
+		/* default is direct to next state */
+		pos = base_idx(base[state]) + (u8) c;
+		if (check[pos] == state)
+			state = next[pos];
+		else
+			state = def[state];
+	}
+
+	return state;
+}

security/apparmor/path.c

@@ -0,0 +1,236 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor function for pathnames
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/magic.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/nsproxy.h>
+#include <linux/path.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/fs_struct.h>
+
+#include "include/apparmor.h"
+#include "include/path.h"
+#include "include/policy.h"
+
+
+/* modified from dcache.c */
+static int prepend(char **buffer, int buflen, const char *str, int namelen)
+{
+	buflen -= namelen;
+	if (buflen < 0)
+		return -ENAMETOOLONG;
+	*buffer -= namelen;
+	memcpy(*buffer, str, namelen);
+	return 0;
+}
+
+#define CHROOT_NSCONNECT (PATH_CHROOT_REL | PATH_CHROOT_NSCONNECT)
+
+/**
+ * d_namespace_path - lookup a name associated with a given path
+ * @path: path to lookup  (NOT NULL)
+ * @buf:  buffer to store path to  (NOT NULL)
+ * @buflen: length of @buf
+ * @name: Returns - pointer for start of path name with in @buf (NOT NULL)
+ * @flags: flags controlling path lookup
+ *
+ * Handle path name lookup.
+ *
+ * Returns: %0 else error code if path lookup fails
+ *          When no error the path name is returned in @name which points to
+ *          to a position in @buf
+ */
+static int d_namespace_path(struct path *path, char *buf, int buflen,
+			    char **name, int flags)
+{
+	char *res;
+	int error = 0;
+	int connected = 1;
+
+	if (path->mnt->mnt_flags & MNT_INTERNAL) {
+		/* it's not mounted anywhere */
+		res = dentry_path(path->dentry, buf, buflen);
+		*name = res;
+		if (IS_ERR(res)) {
+			*name = buf;
+			return PTR_ERR(res);
+		}
+		if (path->dentry->d_sb->s_magic == PROC_SUPER_MAGIC &&
+		    strncmp(*name, "/sys/", 5) == 0) {
+			/* TODO: convert over to using a per namespace
+			 * control instead of hard coded /proc
+			 */
+			return prepend(name, *name - buf, "/proc", 5);
+		}
+		return 0;
+	}
+
+	/* resolve paths relative to chroot?*/
+	if (flags & PATH_CHROOT_REL) {
+		struct path root;
+		get_fs_root(current->fs, &root);
+		res = __d_path(path, &root, buf, buflen);
+		path_put(&root);
+	} else {
+		res = d_absolute_path(path, buf, buflen);
+		if (!our_mnt(path->mnt))
+			connected = 0;
+	}
+
+	/* handle error conditions - and still allow a partial path to
+	 * be returned.
+	 */
+	if (!res || IS_ERR(res)) {
+		if (PTR_ERR(res) == -ENAMETOOLONG)
+			return -ENAMETOOLONG;
+		connected = 0;
+		res = dentry_path_raw(path->dentry, buf, buflen);
+		if (IS_ERR(res)) {
+			error = PTR_ERR(res);
+			*name = buf;
+			goto out;
+		};
+	} else if (!our_mnt(path->mnt))
+		connected = 0;
+
+	*name = res;
+
+	/* Handle two cases:
+	 * 1. A deleted dentry && profile is not allowing mediation of deleted
+	 * 2. On some filesystems, newly allocated dentries appear to the
+	 *    security_path hooks as a deleted dentry except without an inode
+	 *    allocated.
+	 */
+	if (d_unlinked(path->dentry) && path->dentry->d_inode &&
+	    !(flags & PATH_MEDIATE_DELETED)) {
+			error = -ENOENT;
+			goto out;
+	}
+
+	/* If the path is not connected to the expected root,
+	 * check if it is a sysctl and handle specially else remove any
+	 * leading / that __d_path may have returned.
+	 * Unless
+	 *     specifically directed to connect the path,
+	 * OR
+	 *     if in a chroot and doing chroot relative paths and the path
+	 *     resolves to the namespace root (would be connected outside
+	 *     of chroot) and specifically directed to connect paths to
+	 *     namespace root.
+	 */
+	if (!connected) {
+		if (!(flags & PATH_CONNECT_PATH) &&
+			   !(((flags & CHROOT_NSCONNECT) == CHROOT_NSCONNECT) &&
+			     our_mnt(path->mnt))) {
+			/* disconnected path, don't return pathname starting
+			 * with '/'
+			 */
+			error = -EACCES;
+			if (*res == '/')
+				*name = res + 1;
+		}
+	}
+
+out:
+	return error;
+}
+
+/**
+ * get_name_to_buffer - get the pathname to a buffer ensure dir / is appended
+ * @path: path to get name for  (NOT NULL)
+ * @flags: flags controlling path lookup
+ * @buffer: buffer to put name in  (NOT NULL)
+ * @size: size of buffer
+ * @name: Returns - contains position of path name in @buffer (NOT NULL)
+ *
+ * Returns: %0 else error on failure
+ */
+static int get_name_to_buffer(struct path *path, int flags, char *buffer,
+			      int size, char **name, const char **info)
+{
+	int adjust = (flags & PATH_IS_DIR) ? 1 : 0;
+	int error = d_namespace_path(path, buffer, size - adjust, name, flags);
+
+	if (!error && (flags & PATH_IS_DIR) && (*name)[1] != '\0')
+		/*
+		 * Append "/" to the pathname.  The root directory is a special
+		 * case; it already ends in slash.
+		 */
+		strcpy(&buffer[size - 2], "/");
+
+	if (info && error) {
+		if (error == -ENOENT)
+			*info = "Failed name lookup - deleted entry";
+		else if (error == -EACCES)
+			*info = "Failed name lookup - disconnected path";
+		else if (error == -ENAMETOOLONG)
+			*info = "Failed name lookup - name too long";
+		else
+			*info = "Failed name lookup";
+	}
+
+	return error;
+}
+
+/**
+ * aa_path_name - compute the pathname of a file
+ * @path: path the file  (NOT NULL)
+ * @flags: flags controlling path name generation
+ * @buffer: buffer that aa_get_name() allocated  (NOT NULL)
+ * @name: Returns - the generated path name if !error (NOT NULL)
+ * @info: Returns - information on why the path lookup failed (MAYBE NULL)
+ *
+ * @name is a pointer to the beginning of the pathname (which usually differs
+ * from the beginning of the buffer), or NULL.  If there is an error @name
+ * may contain a partial or invalid name that can be used for audit purposes,
+ * but it can not be used for mediation.
+ *
+ * We need PATH_IS_DIR to indicate whether the file is a directory or not
+ * because the file may not yet exist, and so we cannot check the inode's
+ * file type.
+ *
+ * Returns: %0 else error code if could retrieve name
+ */
+int aa_path_name(struct path *path, int flags, char **buffer, const char **name,
+		 const char **info)
+{
+	char *buf, *str = NULL;
+	int size = 256;
+	int error;
+
+	*name = NULL;
+	*buffer = NULL;
+	for (;;) {
+		/* freed by caller */
+		buf = kmalloc(size, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		error = get_name_to_buffer(path, flags, buf, size, &str, info);
+		if (error != -ENAMETOOLONG)
+			break;
+
+		kfree(buf);
+		size <<= 1;
+		if (size > aa_g_path_max)
+			return -ENAMETOOLONG;
+		*info = NULL;
+	}
+	*buffer = buf;
+	*name = str;
+
+	return error;
+}

security/apparmor/policy_unpack.c

@@ -0,0 +1,805 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor functions for unpacking policy loaded from
+ * userspace.
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * AppArmor uses a serialized binary format for loading policy. To find
+ * policy format documentation look in Documentation/security/apparmor.txt
+ * All policy is validated before it is used.
+ */
+
+#include <asm/unaligned.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+
+#include "include/apparmor.h"
+#include "include/audit.h"
+#include "include/context.h"
+#include "include/crypto.h"
+#include "include/match.h"
+#include "include/policy.h"
+#include "include/policy_unpack.h"
+
+/*
+ * The AppArmor interface treats data as a type byte followed by the
+ * actual data.  The interface has the notion of a a named entry
+ * which has a name (AA_NAME typecode followed by name string) followed by
+ * the entries typecode and data.  Named types allow for optional
+ * elements and extensions to be added and tested for without breaking
+ * backwards compatibility.
+ */
+
+enum aa_code {
+	AA_U8,
+	AA_U16,
+	AA_U32,
+	AA_U64,
+	AA_NAME,		/* same as string except it is items name */
+	AA_STRING,
+	AA_BLOB,
+	AA_STRUCT,
+	AA_STRUCTEND,
+	AA_LIST,
+	AA_LISTEND,
+	AA_ARRAY,
+	AA_ARRAYEND,
+};
+
+/*
+ * aa_ext is the read of the buffer containing the serialized profile.  The
+ * data is copied into a kernel buffer in apparmorfs and then handed off to
+ * the unpack routines.
+ */
+struct aa_ext {
+	void *start;
+	void *end;
+	void *pos;		/* pointer to current position in the buffer */
+	u32 version;
+};
+
+/* audit callback for unpack fields */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+	if (sa->aad->iface.target) {
+		struct aa_profile *name = sa->aad->iface.target;
+		audit_log_format(ab, " name=");
+		audit_log_untrustedstring(ab, name->base.hname);
+	}
+	if (sa->aad->iface.pos)
+		audit_log_format(ab, " offset=%ld", sa->aad->iface.pos);
+}
+
+/**
+ * audit_iface - do audit message for policy unpacking/load/replace/remove
+ * @new: profile if it has been allocated (MAYBE NULL)
+ * @name: name of the profile being manipulated (MAYBE NULL)
+ * @info: any extra info about the failure (MAYBE NULL)
+ * @e: buffer position info
+ * @error: error code
+ *
+ * Returns: %0 or error
+ */
+static int audit_iface(struct aa_profile *new, const char *name,
+		       const char *info, struct aa_ext *e, int error)
+{
+	struct aa_profile *profile = __aa_current_profile();
+	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
+	sa.type = LSM_AUDIT_DATA_NONE;
+	sa.aad = &aad;
+	if (e)
+		aad.iface.pos = e->pos - e->start;
+	aad.iface.target = new;
+	aad.name = name;
+	aad.info = info;
+	aad.error = error;
+
+	return aa_audit(AUDIT_APPARMOR_STATUS, profile, GFP_KERNEL, &sa,
+			audit_cb);
+}
+
+/* test if read will be in packed data bounds */
+static bool inbounds(struct aa_ext *e, size_t size)
+{
+	return (size <= e->end - e->pos);
+}
+
+/**
+ * aa_u16_chunck - test and do bounds checking for a u16 size based chunk
+ * @e: serialized data read head (NOT NULL)
+ * @chunk: start address for chunk of data (NOT NULL)
+ *
+ * Returns: the size of chunk found with the read head at the end of the chunk.
+ */
+static size_t unpack_u16_chunk(struct aa_ext *e, char **chunk)
+{
+	size_t size = 0;
+
+	if (!inbounds(e, sizeof(u16)))
+		return 0;
+	size = le16_to_cpu(get_unaligned((u16 *) e->pos));
+	e->pos += sizeof(u16);
+	if (!inbounds(e, size))
+		return 0;
+	*chunk = e->pos;
+	e->pos += size;
+	return size;
+}
+
+/* unpack control byte */
+static bool unpack_X(struct aa_ext *e, enum aa_code code)
+{
+	if (!inbounds(e, 1))
+		return 0;
+	if (*(u8 *) e->pos != code)
+		return 0;
+	e->pos++;
+	return 1;
+}
+
+/**
+ * unpack_nameX - check is the next element is of type X with a name of @name
+ * @e: serialized data extent information  (NOT NULL)
+ * @code: type code
+ * @name: name to match to the serialized element.  (MAYBE NULL)
+ *
+ * check that the next serialized data element is of type X and has a tag
+ * name @name.  If @name is specified then there must be a matching
+ * name element in the stream.  If @name is NULL any name element will be
+ * skipped and only the typecode will be tested.
+ *
+ * Returns 1 on success (both type code and name tests match) and the read
+ * head is advanced past the headers
+ *
+ * Returns: 0 if either match fails, the read head does not move
+ */
+static bool unpack_nameX(struct aa_ext *e, enum aa_code code, const char *name)
+{
+	/*
+	 * May need to reset pos if name or type doesn't match
+	 */
+	void *pos = e->pos;
+	/*
+	 * Check for presence of a tagname, and if present name size
+	 * AA_NAME tag value is a u16.
+	 */
+	if (unpack_X(e, AA_NAME)) {
+		char *tag = NULL;
+		size_t size = unpack_u16_chunk(e, &tag);
+		/* if a name is specified it must match. otherwise skip tag */
+		if (name && (!size || strcmp(name, tag)))
+			goto fail;
+	} else if (name) {
+		/* if a name is specified and there is no name tag fail */
+		goto fail;
+	}
+
+	/* now check if type code matches */
+	if (unpack_X(e, code))
+		return 1;
+
+fail:
+	e->pos = pos;
+	return 0;
+}
+
+static bool unpack_u32(struct aa_ext *e, u32 *data, const char *name)
+{
+	if (unpack_nameX(e, AA_U32, name)) {
+		if (!inbounds(e, sizeof(u32)))
+			return 0;
+		if (data)
+			*data = le32_to_cpu(get_unaligned((u32 *) e->pos));
+		e->pos += sizeof(u32);
+		return 1;
+	}
+	return 0;
+}
+
+static bool unpack_u64(struct aa_ext *e, u64 *data, const char *name)
+{
+	if (unpack_nameX(e, AA_U64, name)) {
+		if (!inbounds(e, sizeof(u64)))
+			return 0;
+		if (data)
+			*data = le64_to_cpu(get_unaligned((u64 *) e->pos));
+		e->pos += sizeof(u64);
+		return 1;
+	}
+	return 0;
+}
+
+static size_t unpack_array(struct aa_ext *e, const char *name)
+{
+	if (unpack_nameX(e, AA_ARRAY, name)) {
+		int size;
+		if (!inbounds(e, sizeof(u16)))
+			return 0;
+		size = (int)le16_to_cpu(get_unaligned((u16 *) e->pos));
+		e->pos += sizeof(u16);
+		return size;
+	}
+	return 0;
+}
+
+static size_t unpack_blob(struct aa_ext *e, char **blob, const char *name)
+{
+	if (unpack_nameX(e, AA_BLOB, name)) {
+		u32 size;
+		if (!inbounds(e, sizeof(u32)))
+			return 0;
+		size = le32_to_cpu(get_unaligned((u32 *) e->pos));
+		e->pos += sizeof(u32);
+		if (inbounds(e, (size_t) size)) {
+			*blob = e->pos;
+			e->pos += size;
+			return size;
+		}
+	}
+	return 0;
+}
+
+static int unpack_str(struct aa_ext *e, const char **string, const char *name)
+{
+	char *src_str;
+	size_t size = 0;
+	void *pos = e->pos;
+	*string = NULL;
+	if (unpack_nameX(e, AA_STRING, name)) {
+		size = unpack_u16_chunk(e, &src_str);
+		if (size) {
+			/* strings are null terminated, length is size - 1 */
+			if (src_str[size - 1] != 0)
+				goto fail;
+			*string = src_str;
+		}
+	}
+	return size;
+
+fail:
+	e->pos = pos;
+	return 0;
+}
+
+static int unpack_strdup(struct aa_ext *e, char **string, const char *name)
+{
+	const char *tmp;
+	void *pos = e->pos;
+	int res = unpack_str(e, &tmp, name);
+	*string = NULL;
+
+	if (!res)
+		return 0;
+
+	*string = kmemdup(tmp, res, GFP_KERNEL);
+	if (!*string) {
+		e->pos = pos;
+		return 0;
+	}
+
+	return res;
+}
+
+#define DFA_VALID_PERM_MASK		0xffffffff
+#define DFA_VALID_PERM2_MASK		0xffffffff
+
+/**
+ * verify_accept - verify the accept tables of a dfa
+ * @dfa: dfa to verify accept tables of (NOT NULL)
+ * @flags: flags governing dfa
+ *
+ * Returns: 1 if valid accept tables else 0 if error
+ */
+static bool verify_accept(struct aa_dfa *dfa, int flags)
+{
+	int i;
+
+	/* verify accept permissions */
+	for (i = 0; i < dfa->tables[YYTD_ID_ACCEPT]->td_lolen; i++) {
+		int mode = ACCEPT_TABLE(dfa)[i];
+
+		if (mode & ~DFA_VALID_PERM_MASK)
+			return 0;
+
+		if (ACCEPT_TABLE2(dfa)[i] & ~DFA_VALID_PERM2_MASK)
+			return 0;
+	}
+	return 1;
+}
+
+/**
+ * unpack_dfa - unpack a file rule dfa
+ * @e: serialized data extent information (NOT NULL)
+ *
+ * returns dfa or ERR_PTR or NULL if no dfa
+ */
+static struct aa_dfa *unpack_dfa(struct aa_ext *e)
+{
+	char *blob = NULL;
+	size_t size;
+	struct aa_dfa *dfa = NULL;
+
+	size = unpack_blob(e, &blob, "aadfa");
+	if (size) {
+		/*
+		 * The dfa is aligned with in the blob to 8 bytes
+		 * from the beginning of the stream.
+		 * alignment adjust needed by dfa unpack
+		 */
+		size_t sz = blob - (char *) e->start -
+			((e->pos - e->start) & 7);
+		size_t pad = ALIGN(sz, 8) - sz;
+		int flags = TO_ACCEPT1_FLAG(YYTD_DATA32) |
+			TO_ACCEPT2_FLAG(YYTD_DATA32);
+
+
+		if (aa_g_paranoid_load)
+			flags |= DFA_FLAG_VERIFY_STATES;
+
+		dfa = aa_dfa_unpack(blob + pad, size - pad, flags);
+
+		if (IS_ERR(dfa))
+			return dfa;
+
+		if (!verify_accept(dfa, flags))
+			goto fail;
+	}
+
+	return dfa;
+
+fail:
+	aa_put_dfa(dfa);
+	return ERR_PTR(-EPROTO);
+}
+
+/**
+ * unpack_trans_table - unpack a profile transition table
+ * @e: serialized data extent information  (NOT NULL)
+ * @profile: profile to add the accept table to (NOT NULL)
+ *
+ * Returns: 1 if table successfully unpacked
+ */
+static bool unpack_trans_table(struct aa_ext *e, struct aa_profile *profile)
+{
+	void *pos = e->pos;
+
+	/* exec table is optional */
+	if (unpack_nameX(e, AA_STRUCT, "xtable")) {
+		int i, size;
+
+		size = unpack_array(e, NULL);
+		/* currently 4 exec bits and entries 0-3 are reserved iupcx */
+		if (size > 16 - 4)
+			goto fail;
+		profile->file.trans.table = kzalloc(sizeof(char *) * size,
+						    GFP_KERNEL);
+		if (!profile->file.trans.table)
+			goto fail;
+
+		profile->file.trans.size = size;
+		for (i = 0; i < size; i++) {
+			char *str;
+			int c, j, size2 = unpack_strdup(e, &str, NULL);
+			/* unpack_strdup verifies that the last character is
+			 * null termination byte.
+			 */
+			if (!size2)
+				goto fail;
+			profile->file.trans.table[i] = str;
+			/* verify that name doesn't start with space */
+			if (isspace(*str))
+				goto fail;
+
+			/* count internal #  of internal \0 */
+			for (c = j = 0; j < size2 - 2; j++) {
+				if (!str[j])
+					c++;
+			}
+			if (*str == ':') {
+				/* beginning with : requires an embedded \0,
+				 * verify that exactly 1 internal \0 exists
+				 * trailing \0 already verified by unpack_strdup
+				 */
+				if (c != 1)
+					goto fail;
+				/* first character after : must be valid */
+				if (!str[1])
+					goto fail;
+			} else if (c)
+				/* fail - all other cases with embedded \0 */
+				goto fail;
+		}
+		if (!unpack_nameX(e, AA_ARRAYEND, NULL))
+			goto fail;
+		if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+	return 1;
+
+fail:
+	aa_free_domain_entries(&profile->file.trans);
+	e->pos = pos;
+	return 0;
+}
+
+static bool unpack_rlimits(struct aa_ext *e, struct aa_profile *profile)
+{
+	void *pos = e->pos;
+
+	/* rlimits are optional */
+	if (unpack_nameX(e, AA_STRUCT, "rlimits")) {
+		int i, size;
+		u32 tmp = 0;
+		if (!unpack_u32(e, &tmp, NULL))
+			goto fail;
+		profile->rlimits.mask = tmp;
+
+		size = unpack_array(e, NULL);
+		if (size > RLIM_NLIMITS)
+			goto fail;
+		for (i = 0; i < size; i++) {
+			u64 tmp2 = 0;
+			int a = aa_map_resource(i);
+			if (!unpack_u64(e, &tmp2, NULL))
+				goto fail;
+			profile->rlimits.limits[a].rlim_max = tmp2;
+		}
+		if (!unpack_nameX(e, AA_ARRAYEND, NULL))
+			goto fail;
+		if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+	return 1;
+
+fail:
+	e->pos = pos;
+	return 0;
+}
+
+/**
+ * unpack_profile - unpack a serialized profile
+ * @e: serialized data extent information (NOT NULL)
+ *
+ * NOTE: unpack profile sets audit struct if there is a failure
+ */
+static struct aa_profile *unpack_profile(struct aa_ext *e)
+{
+	struct aa_profile *profile = NULL;
+	const char *name = NULL;
+	int i, error = -EPROTO;
+	kernel_cap_t tmpcap;
+	u32 tmp;
+
+	/* check that we have the right struct being passed */
+	if (!unpack_nameX(e, AA_STRUCT, "profile"))
+		goto fail;
+	if (!unpack_str(e, &name, NULL))
+		goto fail;
+
+	profile = aa_alloc_profile(name);
+	if (!profile)
+		return ERR_PTR(-ENOMEM);
+
+	/* profile renaming is optional */
+	(void) unpack_str(e, &profile->rename, "rename");
+
+	/* attachment string is optional */
+	(void) unpack_str(e, &profile->attach, "attach");
+
+	/* xmatch is optional and may be NULL */
+	profile->xmatch = unpack_dfa(e);
+	if (IS_ERR(profile->xmatch)) {
+		error = PTR_ERR(profile->xmatch);
+		profile->xmatch = NULL;
+		goto fail;
+	}
+	/* xmatch_len is not optional if xmatch is set */
+	if (profile->xmatch) {
+		if (!unpack_u32(e, &tmp, NULL))
+			goto fail;
+		profile->xmatch_len = tmp;
+	}
+
+	/* per profile debug flags (complain, audit) */
+	if (!unpack_nameX(e, AA_STRUCT, "flags"))
+		goto fail;
+	if (!unpack_u32(e, &tmp, NULL))
+		goto fail;
+	if (tmp & PACKED_FLAG_HAT)
+		profile->flags |= PFLAG_HAT;
+	if (!unpack_u32(e, &tmp, NULL))
+		goto fail;
+	if (tmp == PACKED_MODE_COMPLAIN)
+		profile->mode = APPARMOR_COMPLAIN;
+	else if (tmp == PACKED_MODE_KILL)
+		profile->mode = APPARMOR_KILL;
+	else if (tmp == PACKED_MODE_UNCONFINED)
+		profile->mode = APPARMOR_UNCONFINED;
+	if (!unpack_u32(e, &tmp, NULL))
+		goto fail;
+	if (tmp)
+		profile->audit = AUDIT_ALL;
+
+	if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+		goto fail;
+
+	/* path_flags is optional */
+	if (unpack_u32(e, &profile->path_flags, "path_flags"))
+		profile->path_flags |= profile->flags & PFLAG_MEDIATE_DELETED;
+	else
+		/* set a default value if path_flags field is not present */
+		profile->path_flags = PFLAG_MEDIATE_DELETED;
+
+	if (!unpack_u32(e, &(profile->caps.allow.cap[0]), NULL))
+		goto fail;
+	if (!unpack_u32(e, &(profile->caps.audit.cap[0]), NULL))
+		goto fail;
+	if (!unpack_u32(e, &(profile->caps.quiet.cap[0]), NULL))
+		goto fail;
+	if (!unpack_u32(e, &tmpcap.cap[0], NULL))
+		goto fail;
+
+	if (unpack_nameX(e, AA_STRUCT, "caps64")) {
+		/* optional upper half of 64 bit caps */
+		if (!unpack_u32(e, &(profile->caps.allow.cap[1]), NULL))
+			goto fail;
+		if (!unpack_u32(e, &(profile->caps.audit.cap[1]), NULL))
+			goto fail;
+		if (!unpack_u32(e, &(profile->caps.quiet.cap[1]), NULL))
+			goto fail;
+		if (!unpack_u32(e, &(tmpcap.cap[1]), NULL))
+			goto fail;
+		if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+
+	if (unpack_nameX(e, AA_STRUCT, "capsx")) {
+		/* optional extended caps mediation mask */
+		if (!unpack_u32(e, &(profile->caps.extended.cap[0]), NULL))
+			goto fail;
+		if (!unpack_u32(e, &(profile->caps.extended.cap[1]), NULL))
+			goto fail;
+		if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+
+	if (!unpack_rlimits(e, profile))
+		goto fail;
+
+	if (unpack_nameX(e, AA_STRUCT, "policydb")) {
+		/* generic policy dfa - optional and may be NULL */
+		profile->policy.dfa = unpack_dfa(e);
+		if (IS_ERR(profile->policy.dfa)) {
+			error = PTR_ERR(profile->policy.dfa);
+			profile->policy.dfa = NULL;
+			goto fail;
+		}
+		if (!unpack_u32(e, &profile->policy.start[0], "start"))
+			/* default start state */
+			profile->policy.start[0] = DFA_START;
+		/* setup class index */
+		for (i = AA_CLASS_FILE; i <= AA_CLASS_LAST; i++) {
+			profile->policy.start[i] =
+				aa_dfa_next(profile->policy.dfa,
+					    profile->policy.start[0],
+					    i);
+		}
+		if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+			goto fail;
+	}
+
+	/* get file rules */
+	profile->file.dfa = unpack_dfa(e);
+	if (IS_ERR(profile->file.dfa)) {
+		error = PTR_ERR(profile->file.dfa);
+		profile->file.dfa = NULL;
+		goto fail;
+	}
+
+	if (!unpack_u32(e, &profile->file.start, "dfa_start"))
+		/* default start state */
+		profile->file.start = DFA_START;
+
+	if (!unpack_trans_table(e, profile))
+		goto fail;
+
+	if (!unpack_nameX(e, AA_STRUCTEND, NULL))
+		goto fail;
+
+	return profile;
+
+fail:
+	if (profile)
+		name = NULL;
+	else if (!name)
+		name = "unknown";
+	audit_iface(profile, name, "failed to unpack profile", e, error);
+	aa_free_profile(profile);
+
+	return ERR_PTR(error);
+}
+
+/**
+ * verify_head - unpack serialized stream header
+ * @e: serialized data read head (NOT NULL)
+ * @required: whether the header is required or optional
+ * @ns: Returns - namespace if one is specified else NULL (NOT NULL)
+ *
+ * Returns: error or 0 if header is good
+ */
+static int verify_header(struct aa_ext *e, int required, const char **ns)
+{
+	int error = -EPROTONOSUPPORT;
+	const char *name = NULL;
+	*ns = NULL;
+
+	/* get the interface version */
+	if (!unpack_u32(e, &e->version, "version")) {
+		if (required) {
+			audit_iface(NULL, NULL, "invalid profile format", e,
+				    error);
+			return error;
+		}
+
+		/* check that the interface version is currently supported */
+		if (e->version != 5) {
+			audit_iface(NULL, NULL, "unsupported interface version",
+				    e, error);
+			return error;
+		}
+	}
+
+
+	/* read the namespace if present */
+	if (unpack_str(e, &name, "namespace")) {
+		if (*ns && strcmp(*ns, name))
+			audit_iface(NULL, NULL, "invalid ns change", e, error);
+		else if (!*ns)
+			*ns = name;
+	}
+
+	return 0;
+}
+
+static bool verify_xindex(int xindex, int table_size)
+{
+	int index, xtype;
+	xtype = xindex & AA_X_TYPE_MASK;
+	index = xindex & AA_X_INDEX_MASK;
+	if (xtype == AA_X_TABLE && index > table_size)
+		return 0;
+	return 1;
+}
+
+/* verify dfa xindexes are in range of transition tables */
+static bool verify_dfa_xindex(struct aa_dfa *dfa, int table_size)
+{
+	int i;
+	for (i = 0; i < dfa->tables[YYTD_ID_ACCEPT]->td_lolen; i++) {
+		if (!verify_xindex(dfa_user_xindex(dfa, i), table_size))
+			return 0;
+		if (!verify_xindex(dfa_other_xindex(dfa, i), table_size))
+			return 0;
+	}
+	return 1;
+}
+
+/**
+ * verify_profile - Do post unpack analysis to verify profile consistency
+ * @profile: profile to verify (NOT NULL)
+ *
+ * Returns: 0 if passes verification else error
+ */
+static int verify_profile(struct aa_profile *profile)
+{
+	if (aa_g_paranoid_load) {
+		if (profile->file.dfa &&
+		    !verify_dfa_xindex(profile->file.dfa,
+				       profile->file.trans.size)) {
+			audit_iface(profile, NULL, "Invalid named transition",
+				    NULL, -EPROTO);
+			return -EPROTO;
+		}
+	}
+
+	return 0;
+}
+
+void aa_load_ent_free(struct aa_load_ent *ent)
+{
+	if (ent) {
+		aa_put_profile(ent->rename);
+		aa_put_profile(ent->old);
+		aa_put_profile(ent->new);
+		kzfree(ent);
+	}
+}
+
+struct aa_load_ent *aa_load_ent_alloc(void)
+{
+	struct aa_load_ent *ent = kzalloc(sizeof(*ent), GFP_KERNEL);
+	if (ent)
+		INIT_LIST_HEAD(&ent->list);
+	return ent;
+}
+
+/**
+ * aa_unpack - unpack packed binary profile(s) data loaded from user space
+ * @udata: user data copied to kmem  (NOT NULL)
+ * @size: the size of the user data
+ * @lh: list to place unpacked profiles in a aa_repl_ws
+ * @ns: Returns namespace profile is in if specified else NULL (NOT NULL)
+ *
+ * Unpack user data and return refcounted allocated profile(s) stored in
+ * @lh in order of discovery, with the list chain stored in base.list
+ * or error
+ *
+ * Returns: profile(s) on @lh else error pointer if fails to unpack
+ */
+int aa_unpack(void *udata, size_t size, struct list_head *lh, const char **ns)
+{
+	struct aa_load_ent *tmp, *ent;
+	struct aa_profile *profile = NULL;
+	int error;
+	struct aa_ext e = {
+		.start = udata,
+		.end = udata + size,
+		.pos = udata,
+	};
+
+	*ns = NULL;
+	while (e.pos < e.end) {
+		void *start;
+		error = verify_header(&e, e.pos == e.start, ns);
+		if (error)
+			goto fail;
+
+		start = e.pos;
+		profile = unpack_profile(&e);
+		if (IS_ERR(profile)) {
+			error = PTR_ERR(profile);
+			goto fail;
+		}
+
+		error = verify_profile(profile);
+		if (error)
+			goto fail_profile;
+
+		error = aa_calc_profile_hash(profile, e.version, start,
+					     e.pos - start);
+		if (error)
+			goto fail_profile;
+
+		ent = aa_load_ent_alloc();
+		if (!ent) {
+			error = -ENOMEM;
+			goto fail_profile;
+		}
+
+		ent->new = profile;
+		list_add_tail(&ent->list, lh);
+	}
+
+	return 0;
+
+fail_profile:
+	aa_put_profile(profile);
+
+fail:
+	list_for_each_entry_safe(ent, tmp, lh, list) {
+		list_del_init(&ent->list);
+		aa_load_ent_free(ent);
+	}
+
+	return error;
+}

security/apparmor/procattr.c

@@ -0,0 +1,165 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor /proc/<pid>/attr/ interface functions
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include "include/apparmor.h"
+#include "include/context.h"
+#include "include/policy.h"
+#include "include/domain.h"
+#include "include/procattr.h"
+
+
+/**
+ * aa_getprocattr - Return the profile information for @profile
+ * @profile: the profile to print profile info about  (NOT NULL)
+ * @string: Returns - string containing the profile info (NOT NULL)
+ *
+ * Returns: length of @string on success else error on failure
+ *
+ * Requires: profile != NULL
+ *
+ * Creates a string containing the namespace_name://profile_name for
+ * @profile.
+ *
+ * Returns: size of string placed in @string else error code on failure
+ */
+int aa_getprocattr(struct aa_profile *profile, char **string)
+{
+	char *str;
+	int len = 0, mode_len = 0, ns_len = 0, name_len;
+	const char *mode_str = aa_profile_mode_names[profile->mode];
+	const char *ns_name = NULL;
+	struct aa_namespace *ns = profile->ns;
+	struct aa_namespace *current_ns = __aa_current_profile()->ns;
+	char *s;
+
+	if (!aa_ns_visible(current_ns, ns))
+		return -EACCES;
+
+	ns_name = aa_ns_name(current_ns, ns);
+	ns_len = strlen(ns_name);
+
+	/* if the visible ns_name is > 0 increase size for : :// seperator */
+	if (ns_len)
+		ns_len += 4;
+
+	/* unconfined profiles don't have a mode string appended */
+	if (!unconfined(profile))
+		mode_len = strlen(mode_str) + 3;	/* + 3 for _() */
+
+	name_len = strlen(profile->base.hname);
+	len = mode_len + ns_len + name_len + 1;	    /* + 1 for \n */
+	s = str = kmalloc(len + 1, GFP_KERNEL);	    /* + 1 \0 */
+	if (!str)
+		return -ENOMEM;
+
+	if (ns_len) {
+		/* skip over prefix current_ns->base.hname and separating // */
+		sprintf(s, ":%s://", ns_name);
+		s += ns_len;
+	}
+	if (unconfined(profile))
+		/* mode string not being appended */
+		sprintf(s, "%s\n", profile->base.hname);
+	else
+		sprintf(s, "%s (%s)\n", profile->base.hname, mode_str);
+	*string = str;
+
+	/* NOTE: len does not include \0 of string, not saved as part of file */
+	return len;
+}
+
+/**
+ * split_token_from_name - separate a string of form  <token>^<name>
+ * @op: operation being checked
+ * @args: string to parse  (NOT NULL)
+ * @token: stores returned parsed token value  (NOT NULL)
+ *
+ * Returns: start position of name after token else NULL on failure
+ */
+static char *split_token_from_name(int op, char *args, u64 * token)
+{
+	char *name;
+
+	*token = simple_strtoull(args, &name, 16);
+	if ((name == args) || *name != '^') {
+		AA_ERROR("%s: Invalid input '%s'", op_table[op], args);
+		return ERR_PTR(-EINVAL);
+	}
+
+	name++;			/* skip ^ */
+	if (!*name)
+		name = NULL;
+	return name;
+}
+
+/**
+ * aa_setprocattr_chagnehat - handle procattr interface to change_hat
+ * @args: args received from writing to /proc/<pid>/attr/current (NOT NULL)
+ * @size: size of the args
+ * @test: true if this is a test of change_hat permissions
+ *
+ * Returns: %0 or error code if change_hat fails
+ */
+int aa_setprocattr_changehat(char *args, size_t size, int test)
+{
+	char *hat;
+	u64 token;
+	const char *hats[16];		/* current hard limit on # of names */
+	int count = 0;
+
+	hat = split_token_from_name(OP_CHANGE_HAT, args, &token);
+	if (IS_ERR(hat))
+		return PTR_ERR(hat);
+
+	if (!hat && !token) {
+		AA_ERROR("change_hat: Invalid input, NULL hat and NULL magic");
+		return -EINVAL;
+	}
+
+	if (hat) {
+		/* set up hat name vector, args guaranteed null terminated
+		 * at args[size] by setprocattr.
+		 *
+		 * If there are multiple hat names in the buffer each is
+		 * separated by a \0.  Ie. userspace writes them pre tokenized
+		 */
+		char *end = args + size;
+		for (count = 0; (hat < end) && count < 16; ++count) {
+			char *next = hat + strlen(hat) + 1;
+			hats[count] = hat;
+			hat = next;
+		}
+	}
+
+	AA_DEBUG("%s: Magic 0x%llx Hat '%s'\n",
+		 __func__, token, hat ? hat : NULL);
+
+	return aa_change_hat(hats, count, token, test);
+}
+
+/**
+ * aa_setprocattr_changeprofile - handle procattr interface to changeprofile
+ * @fqname: args received from writting to /proc/<pid>/attr/current (NOT NULL)
+ * @onexec: true if change_profile should be delayed until exec
+ * @test: true if this is a test of change_profile permissions
+ *
+ * Returns: %0 or error code if change_profile fails
+ */
+int aa_setprocattr_changeprofile(char *fqname, bool onexec, int test)
+{
+	char *name, *ns_name;
+
+	name = aa_split_fqname(fqname, &ns_name);
+	return aa_change_profile(ns_name, name, onexec, test);
+}

security/apparmor/resource.c

@@ -0,0 +1,154 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor resource mediation and attachment
+ *
+ * Copyright (C) 1998-2008 Novell/SUSE
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ */
+
+#include <linux/audit.h>
+
+#include "include/audit.h"
+#include "include/context.h"
+#include "include/resource.h"
+#include "include/policy.h"
+
+/*
+ * Table of rlimit names: we generate it from resource.h.
+ */
+#include "rlim_names.h"
+
+struct aa_fs_entry aa_fs_entry_rlimit[] = {
+	AA_FS_FILE_STRING("mask", AA_FS_RLIMIT_MASK),
+	{ }
+};
+
+/* audit callback for resource specific fields */
+static void audit_cb(struct audit_buffer *ab, void *va)
+{
+	struct common_audit_data *sa = va;
+
+	audit_log_format(ab, " rlimit=%s value=%lu",
+			 rlim_names[sa->aad->rlim.rlim], sa->aad->rlim.max);
+}
+
+/**
+ * audit_resource - audit setting resource limit
+ * @profile: profile being enforced  (NOT NULL)
+ * @resoure: rlimit being auditing
+ * @value: value being set
+ * @error: error value
+ *
+ * Returns: 0 or sa->error else other error code on failure
+ */
+static int audit_resource(struct aa_profile *profile, unsigned int resource,
+			  unsigned long value, int error)
+{
+	struct common_audit_data sa;
+	struct apparmor_audit_data aad = {0,};
+
+	sa.type = LSM_AUDIT_DATA_NONE;
+	sa.aad = &aad;
+	aad.op = OP_SETRLIMIT,
+	aad.rlim.rlim = resource;
+	aad.rlim.max = value;
+	aad.error = error;
+	return aa_audit(AUDIT_APPARMOR_AUTO, profile, GFP_KERNEL, &sa,
+			audit_cb);
+}
+
+/**
+ * aa_map_resouce - map compiled policy resource to internal #
+ * @resource: flattened policy resource number
+ *
+ * Returns: resource # for the current architecture.
+ *
+ * rlimit resource can vary based on architecture, map the compiled policy
+ * resource # to the internal representation for the architecture.
+ */
+int aa_map_resource(int resource)
+{
+	return rlim_map[resource];
+}
+
+/**
+ * aa_task_setrlimit - test permission to set an rlimit
+ * @profile - profile confining the task  (NOT NULL)
+ * @task - task the resource is being set on
+ * @resource - the resource being set
+ * @new_rlim - the new resource limit  (NOT NULL)
+ *
+ * Control raising the processes hard limit.
+ *
+ * Returns: 0 or error code if setting resource failed
+ */
+int aa_task_setrlimit(struct aa_profile *profile, struct task_struct *task,
+		      unsigned int resource, struct rlimit *new_rlim)
+{
+	struct aa_profile *task_profile;
+	int error = 0;
+
+	rcu_read_lock();
+	task_profile = aa_get_profile(aa_cred_profile(__task_cred(task)));
+	rcu_read_unlock();
+
+	/* TODO: extend resource control to handle other (non current)
+	 * profiles.  AppArmor rules currently have the implicit assumption
+	 * that the task is setting the resource of a task confined with
+	 * the same profile.
+	 */
+	if (profile != task_profile ||
+	    (profile->rlimits.mask & (1 << resource) &&
+	     new_rlim->rlim_max > profile->rlimits.limits[resource].rlim_max))
+		error = -EACCES;
+
+	aa_put_profile(task_profile);
+
+	return audit_resource(profile, resource, new_rlim->rlim_max, error);
+}
+
+/**
+ * __aa_transition_rlimits - apply new profile rlimits
+ * @old: old profile on task  (NOT NULL)
+ * @new: new profile with rlimits to apply  (NOT NULL)
+ */
+void __aa_transition_rlimits(struct aa_profile *old, struct aa_profile *new)
+{
+	unsigned int mask = 0;
+	struct rlimit *rlim, *initrlim;
+	int i;
+
+	/* for any rlimits the profile controlled reset the soft limit
+	 * to the less of the tasks hard limit and the init tasks soft limit
+	 */
+	if (old->rlimits.mask) {
+		for (i = 0, mask = 1; i < RLIM_NLIMITS; i++, mask <<= 1) {
+			if (old->rlimits.mask & mask) {
+				rlim = current->signal->rlim + i;
+				initrlim = init_task.signal->rlim + i;
+				rlim->rlim_cur = min(rlim->rlim_max,
+						     initrlim->rlim_cur);
+			}
+		}
+	}
+
+	/* set any new hard limits as dictated by the new profile */
+	if (!new->rlimits.mask)
+		return;
+	for (i = 0, mask = 1; i < RLIM_NLIMITS; i++, mask <<= 1) {
+		if (!(new->rlimits.mask & mask))
+			continue;
+
+		rlim = current->signal->rlim + i;
+		rlim->rlim_max = min(rlim->rlim_max,
+				     new->rlimits.limits[i].rlim_max);
+		/* soft limit should not exceed hard limit */
+		rlim->rlim_cur = min(rlim->rlim_cur, rlim->rlim_max);
+	}
+}

security/apparmor/sid.c

@@ -0,0 +1,55 @@
+/*
+ * AppArmor security module
+ *
+ * This file contains AppArmor security identifier (sid) manipulation fns
+ *
+ * Copyright 2009-2010 Canonical Ltd.
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ *
+ * AppArmor allocates a unique sid for every profile loaded.  If a profile
+ * is replaced it receives the sid of the profile it is replacing.
+ *
+ * The sid value of 0 is invalid.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+
+#include "include/sid.h"
+
+/* global counter from which sids are allocated */
+static u32 global_sid;
+static DEFINE_SPINLOCK(sid_lock);
+
+/* TODO FIXME: add sid to profile mapping, and sid recycling */
+
+/**
+ * aa_alloc_sid - allocate a new sid for a profile
+ */
+u32 aa_alloc_sid(void)
+{
+	u32 sid;
+
+	/*
+	 * TODO FIXME: sid recycling - part of profile mapping table
+	 */
+	spin_lock(&sid_lock);
+	sid = (++global_sid);
+	spin_unlock(&sid_lock);
+	return sid;
+}
+
+/**
+ * aa_free_sid - free a sid
+ * @sid: sid to free
+ */
+void aa_free_sid(u32 sid)
+{
+	;			/* NOP ATM */
+}

security/commoncap.c

@@ -0,0 +1,998 @@
+/* Common capabilities, needed by capability.o.
+ *
+ *	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.
+ *
+ */
+
+#include <linux/capability.h>
+#include <linux/audit.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/security.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/ptrace.h>
+#include <linux/xattr.h>
+#include <linux/hugetlb.h>
+#include <linux/mount.h>
+#include <linux/sched.h>
+#include <linux/prctl.h>
+#include <linux/securebits.h>
+#include <linux/user_namespace.h>
+#include <linux/binfmts.h>
+#include <linux/personality.h>
+
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+#include <linux/android_aid.h>
+#endif
+
+/*
+ * If a non-root user executes a setuid-root binary in
+ * !secure(SECURE_NOROOT) mode, then we raise capabilities.
+ * However if fE is also set, then the intent is for only
+ * the file capabilities to be applied, and the setuid-root
+ * bit is left on either to change the uid (plausible) or
+ * to get full privilege on a kernel without file capabilities
+ * support.  So in that case we do not raise capabilities.
+ *
+ * Warn if that happens, once per boot.
+ */
+static void warn_setuid_and_fcaps_mixed(const char *fname)
+{
+	static int warned;
+	if (!warned) {
+		printk(KERN_INFO "warning: `%s' has both setuid-root and"
+			" effective capabilities. Therefore not raising all"
+			" capabilities.\n", fname);
+		warned = 1;
+	}
+}
+
+int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
+{
+	return 0;
+}
+
+/**
+ * cap_capable - Determine whether a task has a particular effective capability
+ * @cred: The credentials to use
+ * @ns:  The user namespace in which we need the capability
+ * @cap: The capability to check for
+ * @audit: Whether to write an audit message or not
+ *
+ * Determine whether the nominated task has the specified capability amongst
+ * its effective set, returning 0 if it does, -ve if it does not.
+ *
+ * NOTE WELL: cap_has_capability() cannot be used like the kernel's capable()
+ * and has_capability() functions.  That is, it has the reverse semantics:
+ * cap_has_capability() returns 0 when a task has a capability, but the
+ * kernel's capable() and has_capability() returns 1 for this case.
+ */
+int cap_capable(const struct cred *cred, struct user_namespace *targ_ns,
+		int cap, int audit)
+{
+	struct user_namespace *ns = targ_ns;
+
+#ifdef CONFIG_ANDROID_PARANOID_NETWORK
+	if (cap == CAP_NET_RAW && in_egroup_p(AID_NET_RAW))
+		return 0;
+	if (cap == CAP_NET_ADMIN && in_egroup_p(AID_NET_ADMIN))
+		return 0;
+#endif
+
+	/* See if cred has the capability in the target user namespace
+	 * by examining the target user namespace and all of the target
+	 * user namespace's parents.
+	 */
+	for (;;) {
+		/* Do we have the necessary capabilities? */
+		if (ns == cred->user_ns)
+			return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
+
+		/* Have we tried all of the parent namespaces? */
+		if (ns == &init_user_ns)
+			return -EPERM;
+
+		/* 
+		 * The owner of the user namespace in the parent of the
+		 * user namespace has all caps.
+		 */
+		if ((ns->parent == cred->user_ns) && uid_eq(ns->owner, cred->euid))
+			return 0;
+
+		/*
+		 * If you have a capability in a parent user ns, then you have
+		 * it over all children user namespaces as well.
+		 */
+		ns = ns->parent;
+	}
+
+	/* We never get here */
+}
+
+/**
+ * cap_settime - Determine whether the current process may set the system clock
+ * @ts: The time to set
+ * @tz: The timezone to set
+ *
+ * Determine whether the current process may set the system clock and timezone
+ * information, returning 0 if permission granted, -ve if denied.
+ */
+int cap_settime(const struct timespec *ts, const struct timezone *tz)
+{
+	if (!capable(CAP_SYS_TIME))
+		return -EPERM;
+	return 0;
+}
+
+/**
+ * cap_ptrace_access_check - Determine whether the current process may access
+ *			   another
+ * @child: The process to be accessed
+ * @mode: The mode of attachment.
+ *
+ * If we are in the same or an ancestor user_ns and have all the target
+ * task's capabilities, then ptrace access is allowed.
+ * If we have the ptrace capability to the target user_ns, then ptrace
+ * access is allowed.
+ * Else denied.
+ *
+ * Determine whether a process may access another, returning 0 if permission
+ * granted, -ve if denied.
+ */
+int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
+{
+	int ret = 0;
+	const struct cred *cred, *child_cred;
+
+	rcu_read_lock();
+	cred = current_cred();
+	child_cred = __task_cred(child);
+	if (cred->user_ns == child_cred->user_ns &&
+	    cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
+		goto out;
+	if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE))
+		goto out;
+	ret = -EPERM;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * cap_ptrace_traceme - Determine whether another process may trace the current
+ * @parent: The task proposed to be the tracer
+ *
+ * If parent is in the same or an ancestor user_ns and has all current's
+ * capabilities, then ptrace access is allowed.
+ * If parent has the ptrace capability to current's user_ns, then ptrace
+ * access is allowed.
+ * Else denied.
+ *
+ * Determine whether the nominated task is permitted to trace the current
+ * process, returning 0 if permission is granted, -ve if denied.
+ */
+int cap_ptrace_traceme(struct task_struct *parent)
+{
+	int ret = 0;
+	const struct cred *cred, *child_cred;
+
+	rcu_read_lock();
+	cred = __task_cred(parent);
+	child_cred = current_cred();
+	if (cred->user_ns == child_cred->user_ns &&
+	    cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
+		goto out;
+	if (has_ns_capability(parent, child_cred->user_ns, CAP_SYS_PTRACE))
+		goto out;
+	ret = -EPERM;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * cap_capget - Retrieve a task's capability sets
+ * @target: The task from which to retrieve the capability sets
+ * @effective: The place to record the effective set
+ * @inheritable: The place to record the inheritable set
+ * @permitted: The place to record the permitted set
+ *
+ * This function retrieves the capabilities of the nominated task and returns
+ * them to the caller.
+ */
+int cap_capget(struct task_struct *target, kernel_cap_t *effective,
+	       kernel_cap_t *inheritable, kernel_cap_t *permitted)
+{
+	const struct cred *cred;
+
+	/* Derived from kernel/capability.c:sys_capget. */
+	rcu_read_lock();
+	cred = __task_cred(target);
+	*effective   = cred->cap_effective;
+	*inheritable = cred->cap_inheritable;
+	*permitted   = cred->cap_permitted;
+	rcu_read_unlock();
+	return 0;
+}
+
+/*
+ * Determine whether the inheritable capabilities are limited to the old
+ * permitted set.  Returns 1 if they are limited, 0 if they are not.
+ */
+static inline int cap_inh_is_capped(void)
+{
+
+	/* they are so limited unless the current task has the CAP_SETPCAP
+	 * capability
+	 */
+	if (cap_capable(current_cred(), current_cred()->user_ns,
+			CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0)
+		return 0;
+	return 1;
+}
+
+/**
+ * cap_capset - Validate and apply proposed changes to current's capabilities
+ * @new: The proposed new credentials; alterations should be made here
+ * @old: The current task's current credentials
+ * @effective: A pointer to the proposed new effective capabilities set
+ * @inheritable: A pointer to the proposed new inheritable capabilities set
+ * @permitted: A pointer to the proposed new permitted capabilities set
+ *
+ * This function validates and applies a proposed mass change to the current
+ * process's capability sets.  The changes are made to the proposed new
+ * credentials, and assuming no error, will be committed by the caller of LSM.
+ */
+int cap_capset(struct cred *new,
+	       const struct cred *old,
+	       const kernel_cap_t *effective,
+	       const kernel_cap_t *inheritable,
+	       const kernel_cap_t *permitted)
+{
+	if (cap_inh_is_capped() &&
+	    !cap_issubset(*inheritable,
+			  cap_combine(old->cap_inheritable,
+				      old->cap_permitted)))
+		/* incapable of using this inheritable set */
+		return -EPERM;
+
+	if (!cap_issubset(*inheritable,
+			  cap_combine(old->cap_inheritable,
+				      old->cap_bset)))
+		/* no new pI capabilities outside bounding set */
+		return -EPERM;
+
+	/* verify restrictions on target's new Permitted set */
+	if (!cap_issubset(*permitted, old->cap_permitted))
+		return -EPERM;
+
+	/* verify the _new_Effective_ is a subset of the _new_Permitted_ */
+	if (!cap_issubset(*effective, *permitted))
+		return -EPERM;
+
+	new->cap_effective   = *effective;
+	new->cap_inheritable = *inheritable;
+	new->cap_permitted   = *permitted;
+	return 0;
+}
+
+/*
+ * Clear proposed capability sets for execve().
+ */
+static inline void bprm_clear_caps(struct linux_binprm *bprm)
+{
+	cap_clear(bprm->cred->cap_permitted);
+	bprm->cap_effective = false;
+}
+
+/**
+ * cap_inode_need_killpriv - Determine if inode change affects privileges
+ * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV
+ *
+ * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV
+ * affects the security markings on that inode, and if it is, should
+ * inode_killpriv() be invoked or the change rejected?
+ *
+ * Returns 0 if granted; +ve if granted, but inode_killpriv() is required; and
+ * -ve to deny the change.
+ */
+int cap_inode_need_killpriv(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	int error;
+
+	if (!inode->i_op->getxattr)
+	       return 0;
+
+	error = inode->i_op->getxattr(dentry, XATTR_NAME_CAPS, NULL, 0);
+	if (error <= 0)
+		return 0;
+	return 1;
+}
+
+/**
+ * cap_inode_killpriv - Erase the security markings on an inode
+ * @dentry: The inode/dentry to alter
+ *
+ * Erase the privilege-enhancing security markings on an inode.
+ *
+ * Returns 0 if successful, -ve on error.
+ */
+int cap_inode_killpriv(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+
+	if (!inode->i_op->removexattr)
+	       return 0;
+
+	return inode->i_op->removexattr(dentry, XATTR_NAME_CAPS);
+}
+
+/*
+ * Calculate the new process capability sets from the capability sets attached
+ * to a file.
+ */
+static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
+					  struct linux_binprm *bprm,
+					  bool *effective,
+					  bool *has_cap)
+{
+	struct cred *new = bprm->cred;
+	unsigned i;
+	int ret = 0;
+
+	if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE)
+		*effective = true;
+
+	if (caps->magic_etc & VFS_CAP_REVISION_MASK)
+		*has_cap = true;
+
+	CAP_FOR_EACH_U32(i) {
+		__u32 permitted = caps->permitted.cap[i];
+		__u32 inheritable = caps->inheritable.cap[i];
+
+		/*
+		 * pP' = (X & fP) | (pI & fI)
+		 */
+		new->cap_permitted.cap[i] =
+			(new->cap_bset.cap[i] & permitted) |
+			(new->cap_inheritable.cap[i] & inheritable);
+
+		if (permitted & ~new->cap_permitted.cap[i])
+			/* insufficient to execute correctly */
+			ret = -EPERM;
+	}
+
+	/*
+	 * For legacy apps, with no internal support for recognizing they
+	 * do not have enough capabilities, we return an error if they are
+	 * missing some "forced" (aka file-permitted) capabilities.
+	 */
+	return *effective ? ret : 0;
+}
+
+/*
+ * Extract the on-exec-apply capability sets for an executable file.
+ */
+int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps)
+{
+	struct inode *inode = dentry->d_inode;
+	__u32 magic_etc;
+	unsigned tocopy, i;
+	int size;
+	struct vfs_cap_data caps;
+
+	memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data));
+
+	if (!inode || !inode->i_op->getxattr)
+		return -ENODATA;
+
+	size = inode->i_op->getxattr((struct dentry *)dentry, XATTR_NAME_CAPS, &caps,
+				   XATTR_CAPS_SZ);
+	if (size == -ENODATA || size == -EOPNOTSUPP)
+		/* no data, that's ok */
+		return -ENODATA;
+	if (size < 0)
+		return size;
+
+	if (size < sizeof(magic_etc))
+		return -EINVAL;
+
+	cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps.magic_etc);
+
+	switch (magic_etc & VFS_CAP_REVISION_MASK) {
+	case VFS_CAP_REVISION_1:
+		if (size != XATTR_CAPS_SZ_1)
+			return -EINVAL;
+		tocopy = VFS_CAP_U32_1;
+		break;
+	case VFS_CAP_REVISION_2:
+		if (size != XATTR_CAPS_SZ_2)
+			return -EINVAL;
+		tocopy = VFS_CAP_U32_2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	CAP_FOR_EACH_U32(i) {
+		if (i >= tocopy)
+			break;
+		cpu_caps->permitted.cap[i] = le32_to_cpu(caps.data[i].permitted);
+		cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable);
+	}
+
+	cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+
+	return 0;
+}
+
+/*
+ * Attempt to get the on-exec apply capability sets for an executable file from
+ * its xattrs and, if present, apply them to the proposed credentials being
+ * constructed by execve().
+ */
+static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_cap)
+{
+	struct dentry *dentry;
+	int rc = 0;
+	struct cpu_vfs_cap_data vcaps;
+
+	bprm_clear_caps(bprm);
+
+	if (!file_caps_enabled)
+		return 0;
+
+	if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
+		return 0;
+
+	dentry = dget(bprm->file->f_dentry);
+
+	rc = get_vfs_caps_from_disk(dentry, &vcaps);
+	if (rc < 0) {
+		if (rc == -EINVAL)
+			printk(KERN_NOTICE "%s: get_vfs_caps_from_disk returned %d for %s\n",
+				__func__, rc, bprm->filename);
+		else if (rc == -ENODATA)
+			rc = 0;
+		goto out;
+	}
+
+	rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective, has_cap);
+	if (rc == -EINVAL)
+		printk(KERN_NOTICE "%s: cap_from_disk returned %d for %s\n",
+		       __func__, rc, bprm->filename);
+
+out:
+	dput(dentry);
+	if (rc)
+		bprm_clear_caps(bprm);
+
+	return rc;
+}
+
+/**
+ * cap_bprm_set_creds - Set up the proposed credentials for execve().
+ * @bprm: The execution parameters, including the proposed creds
+ *
+ * Set up the proposed credentials for a new execution context being
+ * constructed by execve().  The proposed creds in @bprm->cred is altered,
+ * which won't take effect immediately.  Returns 0 if successful, -ve on error.
+ */
+int cap_bprm_set_creds(struct linux_binprm *bprm)
+{
+	const struct cred *old = current_cred();
+	struct cred *new = bprm->cred;
+	bool effective, has_cap = false;
+	int ret;
+	kuid_t root_uid;
+
+	effective = false;
+	ret = get_file_caps(bprm, &effective, &has_cap);
+	if (ret < 0)
+		return ret;
+
+	root_uid = make_kuid(new->user_ns, 0);
+
+	if (!issecure(SECURE_NOROOT)) {
+		/*
+		 * If the legacy file capability is set, then don't set privs
+		 * for a setuid root binary run by a non-root user.  Do set it
+		 * for a root user just to cause least surprise to an admin.
+		 */
+		if (has_cap && !uid_eq(new->uid, root_uid) && uid_eq(new->euid, root_uid)) {
+			warn_setuid_and_fcaps_mixed(bprm->filename);
+			goto skip;
+		}
+		/*
+		 * To support inheritance of root-permissions and suid-root
+		 * executables under compatibility mode, we override the
+		 * capability sets for the file.
+		 *
+		 * If only the real uid is 0, we do not set the effective bit.
+		 */
+		if (uid_eq(new->euid, root_uid) || uid_eq(new->uid, root_uid)) {
+			/* pP' = (cap_bset & ~0) | (pI & ~0) */
+			new->cap_permitted = cap_combine(old->cap_bset,
+							 old->cap_inheritable);
+		}
+		if (uid_eq(new->euid, root_uid))
+			effective = true;
+	}
+skip:
+
+	/* if we have fs caps, clear dangerous personality flags */
+	if (!cap_issubset(new->cap_permitted, old->cap_permitted))
+		bprm->per_clear |= PER_CLEAR_ON_SETID;
+
+
+	/* Don't let someone trace a set[ug]id/setpcap binary with the revised
+	 * credentials unless they have the appropriate permit.
+	 *
+	 * In addition, if NO_NEW_PRIVS, then ensure we get no new privs.
+	 */
+	if ((!uid_eq(new->euid, old->uid) ||
+	     !gid_eq(new->egid, old->gid) ||
+	     !cap_issubset(new->cap_permitted, old->cap_permitted)) &&
+	    bprm->unsafe & ~LSM_UNSAFE_PTRACE_CAP) {
+		/* downgrade; they get no more than they had, and maybe less */
+		if (!capable(CAP_SETUID) ||
+		    (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) {
+			new->euid = new->uid;
+			new->egid = new->gid;
+		}
+		new->cap_permitted = cap_intersect(new->cap_permitted,
+						   old->cap_permitted);
+	}
+
+	new->suid = new->fsuid = new->euid;
+	new->sgid = new->fsgid = new->egid;
+
+	if (effective)
+		new->cap_effective = new->cap_permitted;
+	else
+		cap_clear(new->cap_effective);
+	bprm->cap_effective = effective;
+
+	/*
+	 * Audit candidate if current->cap_effective is set
+	 *
+	 * We do not bother to audit if 3 things are true:
+	 *   1) cap_effective has all caps
+	 *   2) we are root
+	 *   3) root is supposed to have all caps (SECURE_NOROOT)
+	 * Since this is just a normal root execing a process.
+	 *
+	 * Number 1 above might fail if you don't have a full bset, but I think
+	 * that is interesting information to audit.
+	 */
+	if (!cap_isclear(new->cap_effective)) {
+		if (!cap_issubset(CAP_FULL_SET, new->cap_effective) ||
+		    !uid_eq(new->euid, root_uid) || !uid_eq(new->uid, root_uid) ||
+		    issecure(SECURE_NOROOT)) {
+			ret = audit_log_bprm_fcaps(bprm, new, old);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
+	return 0;
+}
+
+/**
+ * cap_bprm_secureexec - Determine whether a secure execution is required
+ * @bprm: The execution parameters
+ *
+ * Determine whether a secure execution is required, return 1 if it is, and 0
+ * if it is not.
+ *
+ * The credentials have been committed by this point, and so are no longer
+ * available through @bprm->cred.
+ */
+int cap_bprm_secureexec(struct linux_binprm *bprm)
+{
+	const struct cred *cred = current_cred();
+	kuid_t root_uid = make_kuid(cred->user_ns, 0);
+
+	if (!uid_eq(cred->uid, root_uid)) {
+		if (bprm->cap_effective)
+			return 1;
+		if (!cap_isclear(cred->cap_permitted))
+			return 1;
+	}
+
+	return (!uid_eq(cred->euid, cred->uid) ||
+		!gid_eq(cred->egid, cred->gid));
+}
+
+/**
+ * cap_inode_setxattr - Determine whether an xattr may be altered
+ * @dentry: The inode/dentry being altered
+ * @name: The name of the xattr to be changed
+ * @value: The value that the xattr will be changed to
+ * @size: The size of value
+ * @flags: The replacement flag
+ *
+ * Determine whether an xattr may be altered or set on an inode, returning 0 if
+ * permission is granted, -ve if denied.
+ *
+ * This is used to make sure security xattrs don't get updated or set by those
+ * who aren't privileged to do so.
+ */
+int cap_inode_setxattr(struct dentry *dentry, const char *name,
+		       const void *value, size_t size, int flags)
+{
+	if (!strcmp(name, XATTR_NAME_CAPS)) {
+		if (!capable(CAP_SETFCAP))
+			return -EPERM;
+		return 0;
+	}
+
+	if (!strncmp(name, XATTR_SECURITY_PREFIX,
+		     sizeof(XATTR_SECURITY_PREFIX) - 1) &&
+	    !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	return 0;
+}
+
+/**
+ * cap_inode_removexattr - Determine whether an xattr may be removed
+ * @dentry: The inode/dentry being altered
+ * @name: The name of the xattr to be changed
+ *
+ * Determine whether an xattr may be removed from an inode, returning 0 if
+ * permission is granted, -ve if denied.
+ *
+ * This is used to make sure security xattrs don't get removed by those who
+ * aren't privileged to remove them.
+ */
+int cap_inode_removexattr(struct dentry *dentry, const char *name)
+{
+	if (!strcmp(name, XATTR_NAME_CAPS)) {
+		if (!capable(CAP_SETFCAP))
+			return -EPERM;
+		return 0;
+	}
+
+	if (!strncmp(name, XATTR_SECURITY_PREFIX,
+		     sizeof(XATTR_SECURITY_PREFIX) - 1) &&
+	    !capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	return 0;
+}
+
+/*
+ * cap_emulate_setxuid() fixes the effective / permitted capabilities of
+ * a process after a call to setuid, setreuid, or setresuid.
+ *
+ *  1) When set*uiding _from_ one of {r,e,s}uid == 0 _to_ all of
+ *  {r,e,s}uid != 0, the permitted and effective capabilities are
+ *  cleared.
+ *
+ *  2) When set*uiding _from_ euid == 0 _to_ euid != 0, the effective
+ *  capabilities of the process are cleared.
+ *
+ *  3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective
+ *  capabilities are set to the permitted capabilities.
+ *
+ *  fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should
+ *  never happen.
+ *
+ *  -astor
+ *
+ * cevans - New behaviour, Oct '99
+ * A process may, via prctl(), elect to keep its capabilities when it
+ * calls setuid() and switches away from uid==0. Both permitted and
+ * effective sets will be retained.
+ * Without this change, it was impossible for a daemon to drop only some
+ * of its privilege. The call to setuid(!=0) would drop all privileges!
+ * Keeping uid 0 is not an option because uid 0 owns too many vital
+ * files..
+ * Thanks to Olaf Kirch and Peter Benie for spotting this.
+ */
+static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old)
+{
+	kuid_t root_uid = make_kuid(old->user_ns, 0);
+
+	if ((uid_eq(old->uid, root_uid) ||
+	     uid_eq(old->euid, root_uid) ||
+	     uid_eq(old->suid, root_uid)) &&
+	    (!uid_eq(new->uid, root_uid) &&
+	     !uid_eq(new->euid, root_uid) &&
+	     !uid_eq(new->suid, root_uid)) &&
+	    !issecure(SECURE_KEEP_CAPS)) {
+		cap_clear(new->cap_permitted);
+		cap_clear(new->cap_effective);
+	}
+	if (uid_eq(old->euid, root_uid) && !uid_eq(new->euid, root_uid))
+		cap_clear(new->cap_effective);
+	if (!uid_eq(old->euid, root_uid) && uid_eq(new->euid, root_uid))
+		new->cap_effective = new->cap_permitted;
+}
+
+/**
+ * cap_task_fix_setuid - Fix up the results of setuid() call
+ * @new: The proposed credentials
+ * @old: The current task's current credentials
+ * @flags: Indications of what has changed
+ *
+ * Fix up the results of setuid() call before the credential changes are
+ * actually applied, returning 0 to grant the changes, -ve to deny them.
+ */
+int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags)
+{
+	switch (flags) {
+	case LSM_SETID_RE:
+	case LSM_SETID_ID:
+	case LSM_SETID_RES:
+		/* juggle the capabilities to follow [RES]UID changes unless
+		 * otherwise suppressed */
+		if (!issecure(SECURE_NO_SETUID_FIXUP))
+			cap_emulate_setxuid(new, old);
+		break;
+
+	case LSM_SETID_FS:
+		/* juggle the capabilties to follow FSUID changes, unless
+		 * otherwise suppressed
+		 *
+		 * FIXME - is fsuser used for all CAP_FS_MASK capabilities?
+		 *          if not, we might be a bit too harsh here.
+		 */
+		if (!issecure(SECURE_NO_SETUID_FIXUP)) {
+			kuid_t root_uid = make_kuid(old->user_ns, 0);
+			if (uid_eq(old->fsuid, root_uid) && !uid_eq(new->fsuid, root_uid))
+				new->cap_effective =
+					cap_drop_fs_set(new->cap_effective);
+
+			if (!uid_eq(old->fsuid, root_uid) && uid_eq(new->fsuid, root_uid))
+				new->cap_effective =
+					cap_raise_fs_set(new->cap_effective,
+							 new->cap_permitted);
+		}
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/*
+ * Rationale: code calling task_setscheduler, task_setioprio, and
+ * task_setnice, assumes that
+ *   . if capable(cap_sys_nice), then those actions should be allowed
+ *   . if not capable(cap_sys_nice), but acting on your own processes,
+ *   	then those actions should be allowed
+ * This is insufficient now since you can call code without suid, but
+ * yet with increased caps.
+ * So we check for increased caps on the target process.
+ */
+static int cap_safe_nice(struct task_struct *p)
+{
+	int is_subset, ret = 0;
+
+	rcu_read_lock();
+	is_subset = cap_issubset(__task_cred(p)->cap_permitted,
+				 current_cred()->cap_permitted);
+	if (!is_subset && !ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
+		ret = -EPERM;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/**
+ * cap_task_setscheduler - Detemine if scheduler policy change is permitted
+ * @p: The task to affect
+ *
+ * Detemine if the requested scheduler policy change is permitted for the
+ * specified task, returning 0 if permission is granted, -ve if denied.
+ */
+int cap_task_setscheduler(struct task_struct *p)
+{
+	return cap_safe_nice(p);
+}
+
+/**
+ * cap_task_ioprio - Detemine if I/O priority change is permitted
+ * @p: The task to affect
+ * @ioprio: The I/O priority to set
+ *
+ * Detemine if the requested I/O priority change is permitted for the specified
+ * task, returning 0 if permission is granted, -ve if denied.
+ */
+int cap_task_setioprio(struct task_struct *p, int ioprio)
+{
+	return cap_safe_nice(p);
+}
+
+/**
+ * cap_task_ioprio - Detemine if task priority change is permitted
+ * @p: The task to affect
+ * @nice: The nice value to set
+ *
+ * Detemine if the requested task priority change is permitted for the
+ * specified task, returning 0 if permission is granted, -ve if denied.
+ */
+int cap_task_setnice(struct task_struct *p, int nice)
+{
+	return cap_safe_nice(p);
+}
+
+/*
+ * Implement PR_CAPBSET_DROP.  Attempt to remove the specified capability from
+ * the current task's bounding set.  Returns 0 on success, -ve on error.
+ */
+static int cap_prctl_drop(unsigned long cap)
+{
+	struct cred *new;
+
+	if (!ns_capable(current_user_ns(), CAP_SETPCAP))
+		return -EPERM;
+	if (!cap_valid(cap))
+		return -EINVAL;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+	cap_lower(new->cap_bset, cap);
+	return commit_creds(new);
+}
+
+/**
+ * cap_task_prctl - Implement process control functions for this security module
+ * @option: The process control function requested
+ * @arg2, @arg3, @arg4, @arg5: The argument data for this function
+ *
+ * Allow process control functions (sys_prctl()) to alter capabilities; may
+ * also deny access to other functions not otherwise implemented here.
+ *
+ * Returns 0 or +ve on success, -ENOSYS if this function is not implemented
+ * here, other -ve on error.  If -ENOSYS is returned, sys_prctl() and other LSM
+ * modules will consider performing the function.
+ */
+int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
+		   unsigned long arg4, unsigned long arg5)
+{
+	const struct cred *old = current_cred();
+	struct cred *new;
+
+	switch (option) {
+	case PR_CAPBSET_READ:
+		if (!cap_valid(arg2))
+			return -EINVAL;
+		return !!cap_raised(old->cap_bset, arg2);
+
+	case PR_CAPBSET_DROP:
+		return cap_prctl_drop(arg2);
+
+	/*
+	 * The next four prctl's remain to assist with transitioning a
+	 * system from legacy UID=0 based privilege (when filesystem
+	 * capabilities are not in use) to a system using filesystem
+	 * capabilities only - as the POSIX.1e draft intended.
+	 *
+	 * Note:
+	 *
+	 *  PR_SET_SECUREBITS =
+	 *      issecure_mask(SECURE_KEEP_CAPS_LOCKED)
+	 *    | issecure_mask(SECURE_NOROOT)
+	 *    | issecure_mask(SECURE_NOROOT_LOCKED)
+	 *    | issecure_mask(SECURE_NO_SETUID_FIXUP)
+	 *    | issecure_mask(SECURE_NO_SETUID_FIXUP_LOCKED)
+	 *
+	 * will ensure that the current process and all of its
+	 * children will be locked into a pure
+	 * capability-based-privilege environment.
+	 */
+	case PR_SET_SECUREBITS:
+		if ((((old->securebits & SECURE_ALL_LOCKS) >> 1)
+		     & (old->securebits ^ arg2))			/*[1]*/
+		    || ((old->securebits & SECURE_ALL_LOCKS & ~arg2))	/*[2]*/
+		    || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS))	/*[3]*/
+		    || (cap_capable(current_cred(),
+				    current_cred()->user_ns, CAP_SETPCAP,
+				    SECURITY_CAP_AUDIT) != 0)		/*[4]*/
+			/*
+			 * [1] no changing of bits that are locked
+			 * [2] no unlocking of locks
+			 * [3] no setting of unsupported bits
+			 * [4] doing anything requires privilege (go read about
+			 *     the "sendmail capabilities bug")
+			 */
+		    )
+			/* cannot change a locked bit */
+			return -EPERM;
+
+		new = prepare_creds();
+		if (!new)
+			return -ENOMEM;
+		new->securebits = arg2;
+		return commit_creds(new);
+
+	case PR_GET_SECUREBITS:
+		return old->securebits;
+
+	case PR_GET_KEEPCAPS:
+		return !!issecure(SECURE_KEEP_CAPS);
+
+	case PR_SET_KEEPCAPS:
+		if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */
+			return -EINVAL;
+		if (issecure(SECURE_KEEP_CAPS_LOCKED))
+			return -EPERM;
+
+		new = prepare_creds();
+		if (!new)
+			return -ENOMEM;
+		if (arg2)
+			new->securebits |= issecure_mask(SECURE_KEEP_CAPS);
+		else
+			new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
+		return commit_creds(new);
+
+	default:
+		/* No functionality available - continue with default */
+		return -ENOSYS;
+	}
+}
+
+/**
+ * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted
+ * @mm: The VM space in which the new mapping is to be made
+ * @pages: The size of the mapping
+ *
+ * Determine whether the allocation of a new virtual mapping by the current
+ * task is permitted, returning 0 if permission is granted, -ve if not.
+ */
+int cap_vm_enough_memory(struct mm_struct *mm, long pages)
+{
+	int cap_sys_admin = 0;
+
+	if (cap_capable(current_cred(), &init_user_ns, CAP_SYS_ADMIN,
+			SECURITY_CAP_NOAUDIT) == 0)
+		cap_sys_admin = 1;
+	return __vm_enough_memory(mm, pages, cap_sys_admin);
+}
+
+/*
+ * cap_mmap_addr - check if able to map given addr
+ * @addr: address attempting to be mapped
+ *
+ * If the process is attempting to map memory below dac_mmap_min_addr they need
+ * CAP_SYS_RAWIO.  The other parameters to this function are unused by the
+ * capability security module.  Returns 0 if this mapping should be allowed
+ * -EPERM if not.
+ */
+int cap_mmap_addr(unsigned long addr)
+{
+	int ret = 0;
+
+	if (addr < dac_mmap_min_addr) {
+		ret = cap_capable(current_cred(), &init_user_ns, CAP_SYS_RAWIO,
+				  SECURITY_CAP_AUDIT);
+		/* set PF_SUPERPRIV if it turns out we allow the low mmap */
+		if (ret == 0)
+			current->flags |= PF_SUPERPRIV;
+	}
+	return ret;
+}
+
+int cap_mmap_file(struct file *file, unsigned long reqprot,
+		  unsigned long prot, unsigned long flags)
+{
+	return 0;
+}

security/device_cgroup.c

@@ -0,0 +1,868 @@
+/*
+ * device_cgroup.c - device cgroup subsystem
+ *
+ * Copyright 2007 IBM Corp
+ */
+
+#include <linux/device_cgroup.h>
+#include <linux/cgroup.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+#include <linux/mutex.h>
+
+#define ACC_MKNOD 1
+#define ACC_READ  2
+#define ACC_WRITE 4
+#define ACC_MASK (ACC_MKNOD | ACC_READ | ACC_WRITE)
+
+#define DEV_BLOCK 1
+#define DEV_CHAR  2
+#define DEV_ALL   4  /* this represents all devices */
+
+static DEFINE_MUTEX(devcgroup_mutex);
+
+enum devcg_behavior {
+	DEVCG_DEFAULT_NONE,
+	DEVCG_DEFAULT_ALLOW,
+	DEVCG_DEFAULT_DENY,
+};
+
+/*
+ * exception list locking rules:
+ * hold devcgroup_mutex for update/read.
+ * hold rcu_read_lock() for read.
+ */
+
+struct dev_exception_item {
+	u32 major, minor;
+	short type;
+	short access;
+	struct list_head list;
+	struct rcu_head rcu;
+};
+
+struct dev_cgroup {
+	struct cgroup_subsys_state css;
+	struct list_head exceptions;
+	enum devcg_behavior behavior;
+};
+
+static inline struct dev_cgroup *css_to_devcgroup(struct cgroup_subsys_state *s)
+{
+	return s ? container_of(s, struct dev_cgroup, css) : NULL;
+}
+
+static inline struct dev_cgroup *task_devcgroup(struct task_struct *task)
+{
+	return css_to_devcgroup(task_css(task, devices_cgrp_id));
+}
+
+/*
+ * called under devcgroup_mutex
+ */
+static int dev_exceptions_copy(struct list_head *dest, struct list_head *orig)
+{
+	struct dev_exception_item *ex, *tmp, *new;
+
+	lockdep_assert_held(&devcgroup_mutex);
+
+	list_for_each_entry(ex, orig, list) {
+		new = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
+		if (!new)
+			goto free_and_exit;
+		list_add_tail(&new->list, dest);
+	}
+
+	return 0;
+
+free_and_exit:
+	list_for_each_entry_safe(ex, tmp, dest, list) {
+		list_del(&ex->list);
+		kfree(ex);
+	}
+	return -ENOMEM;
+}
+
+/*
+ * called under devcgroup_mutex
+ */
+static int dev_exception_add(struct dev_cgroup *dev_cgroup,
+			     struct dev_exception_item *ex)
+{
+	struct dev_exception_item *excopy, *walk;
+
+	lockdep_assert_held(&devcgroup_mutex);
+
+	excopy = kmemdup(ex, sizeof(*ex), GFP_KERNEL);
+	if (!excopy)
+		return -ENOMEM;
+
+	list_for_each_entry(walk, &dev_cgroup->exceptions, list) {
+		if (walk->type != ex->type)
+			continue;
+		if (walk->major != ex->major)
+			continue;
+		if (walk->minor != ex->minor)
+			continue;
+
+		walk->access |= ex->access;
+		kfree(excopy);
+		excopy = NULL;
+	}
+
+	if (excopy != NULL)
+		list_add_tail_rcu(&excopy->list, &dev_cgroup->exceptions);
+	return 0;
+}
+
+/*
+ * called under devcgroup_mutex
+ */
+static void dev_exception_rm(struct dev_cgroup *dev_cgroup,
+			     struct dev_exception_item *ex)
+{
+	struct dev_exception_item *walk, *tmp;
+
+	lockdep_assert_held(&devcgroup_mutex);
+
+	list_for_each_entry_safe(walk, tmp, &dev_cgroup->exceptions, list) {
+		if (walk->type != ex->type)
+			continue;
+		if (walk->major != ex->major)
+			continue;
+		if (walk->minor != ex->minor)
+			continue;
+
+		walk->access &= ~ex->access;
+		if (!walk->access) {
+			list_del_rcu(&walk->list);
+			kfree_rcu(walk, rcu);
+		}
+	}
+}
+
+static void __dev_exception_clean(struct dev_cgroup *dev_cgroup)
+{
+	struct dev_exception_item *ex, *tmp;
+
+	list_for_each_entry_safe(ex, tmp, &dev_cgroup->exceptions, list) {
+		list_del_rcu(&ex->list);
+		kfree_rcu(ex, rcu);
+	}
+}
+
+/**
+ * dev_exception_clean - frees all entries of the exception list
+ * @dev_cgroup: dev_cgroup with the exception list to be cleaned
+ *
+ * called under devcgroup_mutex
+ */
+static void dev_exception_clean(struct dev_cgroup *dev_cgroup)
+{
+	lockdep_assert_held(&devcgroup_mutex);
+
+	__dev_exception_clean(dev_cgroup);
+}
+
+static inline bool is_devcg_online(const struct dev_cgroup *devcg)
+{
+	return (devcg->behavior != DEVCG_DEFAULT_NONE);
+}
+
+/**
+ * devcgroup_online - initializes devcgroup's behavior and exceptions based on
+ * 		      parent's
+ * @css: css getting online
+ * returns 0 in case of success, error code otherwise
+ */
+static int devcgroup_online(struct cgroup_subsys_state *css)
+{
+	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
+	struct dev_cgroup *parent_dev_cgroup = css_to_devcgroup(css->parent);
+	int ret = 0;
+
+	mutex_lock(&devcgroup_mutex);
+
+	if (parent_dev_cgroup == NULL)
+		dev_cgroup->behavior = DEVCG_DEFAULT_ALLOW;
+	else {
+		ret = dev_exceptions_copy(&dev_cgroup->exceptions,
+					  &parent_dev_cgroup->exceptions);
+		if (!ret)
+			dev_cgroup->behavior = parent_dev_cgroup->behavior;
+	}
+	mutex_unlock(&devcgroup_mutex);
+
+	return ret;
+}
+
+static void devcgroup_offline(struct cgroup_subsys_state *css)
+{
+	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
+
+	mutex_lock(&devcgroup_mutex);
+	dev_cgroup->behavior = DEVCG_DEFAULT_NONE;
+	mutex_unlock(&devcgroup_mutex);
+}
+
+/*
+ * called from kernel/cgroup.c with cgroup_lock() held.
+ */
+static struct cgroup_subsys_state *
+devcgroup_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct dev_cgroup *dev_cgroup;
+
+	dev_cgroup = kzalloc(sizeof(*dev_cgroup), GFP_KERNEL);
+	if (!dev_cgroup)
+		return ERR_PTR(-ENOMEM);
+	INIT_LIST_HEAD(&dev_cgroup->exceptions);
+	dev_cgroup->behavior = DEVCG_DEFAULT_NONE;
+
+	return &dev_cgroup->css;
+}
+
+static void devcgroup_css_free(struct cgroup_subsys_state *css)
+{
+	struct dev_cgroup *dev_cgroup = css_to_devcgroup(css);
+
+	__dev_exception_clean(dev_cgroup);
+	kfree(dev_cgroup);
+}
+
+#define DEVCG_ALLOW 1
+#define DEVCG_DENY 2
+#define DEVCG_LIST 3
+
+#define MAJMINLEN 13
+#define ACCLEN 4
+
+static void set_access(char *acc, short access)
+{
+	int idx = 0;
+	memset(acc, 0, ACCLEN);
+	if (access & ACC_READ)
+		acc[idx++] = 'r';
+	if (access & ACC_WRITE)
+		acc[idx++] = 'w';
+	if (access & ACC_MKNOD)
+		acc[idx++] = 'm';
+}
+
+static char type_to_char(short type)
+{
+	if (type == DEV_ALL)
+		return 'a';
+	if (type == DEV_CHAR)
+		return 'c';
+	if (type == DEV_BLOCK)
+		return 'b';
+	return 'X';
+}
+
+static void set_majmin(char *str, unsigned m)
+{
+	if (m == ~0)
+		strcpy(str, "*");
+	else
+		sprintf(str, "%u", m);
+}
+
+static int devcgroup_seq_show(struct seq_file *m, void *v)
+{
+	struct dev_cgroup *devcgroup = css_to_devcgroup(seq_css(m));
+	struct dev_exception_item *ex;
+	char maj[MAJMINLEN], min[MAJMINLEN], acc[ACCLEN];
+
+	rcu_read_lock();
+	/*
+	 * To preserve the compatibility:
+	 * - Only show the "all devices" when the default policy is to allow
+	 * - List the exceptions in case the default policy is to deny
+	 * This way, the file remains as a "whitelist of devices"
+	 */
+	if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
+		set_access(acc, ACC_MASK);
+		set_majmin(maj, ~0);
+		set_majmin(min, ~0);
+		seq_printf(m, "%c %s:%s %s\n", type_to_char(DEV_ALL),
+			   maj, min, acc);
+	} else {
+		list_for_each_entry_rcu(ex, &devcgroup->exceptions, list) {
+			set_access(acc, ex->access);
+			set_majmin(maj, ex->major);
+			set_majmin(min, ex->minor);
+			seq_printf(m, "%c %s:%s %s\n", type_to_char(ex->type),
+				   maj, min, acc);
+		}
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+
+/**
+ * match_exception	- iterates the exception list trying to find a complete match
+ * @exceptions: list of exceptions
+ * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ *
+ * It is considered a complete match if an exception is found that will
+ * contain the entire range of provided parameters.
+ *
+ * Return: true in case it matches an exception completely
+ */
+static bool match_exception(struct list_head *exceptions, short type,
+			    u32 major, u32 minor, short access)
+{
+	struct dev_exception_item *ex;
+
+	list_for_each_entry_rcu(ex, exceptions, list) {
+		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+			continue;
+		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+			continue;
+		if (ex->major != ~0 && ex->major != major)
+			continue;
+		if (ex->minor != ~0 && ex->minor != minor)
+			continue;
+		/* provided access cannot have more than the exception rule */
+		if (access & (~ex->access))
+			continue;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * match_exception_partial - iterates the exception list trying to find a partial match
+ * @exceptions: list of exceptions
+ * @type: device type (DEV_BLOCK or DEV_CHAR)
+ * @major: device file major number, ~0 to match all
+ * @minor: device file minor number, ~0 to match all
+ * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD)
+ *
+ * It is considered a partial match if an exception's range is found to
+ * contain *any* of the devices specified by provided parameters. This is
+ * used to make sure no extra access is being granted that is forbidden by
+ * any of the exception list.
+ *
+ * Return: true in case the provided range mat matches an exception completely
+ */
+static bool match_exception_partial(struct list_head *exceptions, short type,
+				    u32 major, u32 minor, short access)
+{
+	struct dev_exception_item *ex;
+
+	list_for_each_entry_rcu(ex, exceptions, list) {
+		if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK))
+			continue;
+		if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR))
+			continue;
+		/*
+		 * We must be sure that both the exception and the provided
+		 * range aren't masking all devices
+		 */
+		if (ex->major != ~0 && major != ~0 && ex->major != major)
+			continue;
+		if (ex->minor != ~0 && minor != ~0 && ex->minor != minor)
+			continue;
+		/*
+		 * In order to make sure the provided range isn't matching
+		 * an exception, all its access bits shouldn't match the
+		 * exception's access bits
+		 */
+		if (!(access & ex->access))
+			continue;
+		return true;
+	}
+	return false;
+}
+
+/**
+ * verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions
+ * @dev_cgroup: dev cgroup to be tested against
+ * @refex: new exception
+ * @behavior: behavior of the exception's dev_cgroup
+ *
+ * This is used to make sure a child cgroup won't have more privileges
+ * than its parent
+ */
+static bool verify_new_ex(struct dev_cgroup *dev_cgroup,
+		          struct dev_exception_item *refex,
+		          enum devcg_behavior behavior)
+{
+	bool match = false;
+
+	rcu_lockdep_assert(rcu_read_lock_held() ||
+			   lockdep_is_held(&devcgroup_mutex),
+			   "device_cgroup:verify_new_ex called without proper synchronization");
+
+	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) {
+		if (behavior == DEVCG_DEFAULT_ALLOW) {
+			/*
+			 * new exception in the child doesn't matter, only
+			 * adding extra restrictions
+			 */ 
+			return true;
+		} else {
+			/*
+			 * new exception in the child will add more devices
+			 * that can be acessed, so it can't match any of
+			 * parent's exceptions, even slightly
+			 */ 
+			match = match_exception_partial(&dev_cgroup->exceptions,
+							refex->type,
+							refex->major,
+							refex->minor,
+							refex->access);
+
+			if (match)
+				return false;
+			return true;
+		}
+	} else {
+		/*
+		 * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore
+		 * the new exception will add access to more devices and must
+		 * be contained completely in an parent's exception to be
+		 * allowed
+		 */
+		match = match_exception(&dev_cgroup->exceptions, refex->type,
+					refex->major, refex->minor,
+					refex->access);
+
+		if (match)
+			/* parent has an exception that matches the proposed */
+			return true;
+		else
+			return false;
+	}
+	return false;
+}
+
+/*
+ * parent_has_perm:
+ * when adding a new allow rule to a device exception list, the rule
+ * must be allowed in the parent device
+ */
+static int parent_has_perm(struct dev_cgroup *childcg,
+				  struct dev_exception_item *ex)
+{
+	struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
+
+	if (!parent)
+		return 1;
+	return verify_new_ex(parent, ex, childcg->behavior);
+}
+
+/**
+ * parent_allows_removal - verify if it's ok to remove an exception
+ * @childcg: child cgroup from where the exception will be removed
+ * @ex: exception being removed
+ *
+ * When removing an exception in cgroups with default ALLOW policy, it must
+ * be checked if removing it will give the child cgroup more access than the
+ * parent.
+ *
+ * Return: true if it's ok to remove exception, false otherwise
+ */
+static bool parent_allows_removal(struct dev_cgroup *childcg,
+				  struct dev_exception_item *ex)
+{
+	struct dev_cgroup *parent = css_to_devcgroup(childcg->css.parent);
+
+	if (!parent)
+		return true;
+
+	/* It's always allowed to remove access to devices */
+	if (childcg->behavior == DEVCG_DEFAULT_DENY)
+		return true;
+
+	/*
+	 * Make sure you're not removing part or a whole exception existing in
+	 * the parent cgroup
+	 */
+	return !match_exception_partial(&parent->exceptions, ex->type,
+					ex->major, ex->minor, ex->access);
+}
+
+/**
+ * may_allow_all - checks if it's possible to change the behavior to
+ *		   allow based on parent's rules.
+ * @parent: device cgroup's parent
+ * returns: != 0 in case it's allowed, 0 otherwise
+ */
+static inline int may_allow_all(struct dev_cgroup *parent)
+{
+	if (!parent)
+		return 1;
+	return parent->behavior == DEVCG_DEFAULT_ALLOW;
+}
+
+/**
+ * revalidate_active_exceptions - walks through the active exception list and
+ * 				  revalidates the exceptions based on parent's
+ * 				  behavior and exceptions. The exceptions that
+ * 				  are no longer valid will be removed.
+ * 				  Called with devcgroup_mutex held.
+ * @devcg: cgroup which exceptions will be checked
+ *
+ * This is one of the three key functions for hierarchy implementation.
+ * This function is responsible for re-evaluating all the cgroup's active
+ * exceptions due to a parent's exception change.
+ * Refer to Documentation/cgroups/devices.txt for more details.
+ */
+static void revalidate_active_exceptions(struct dev_cgroup *devcg)
+{
+	struct dev_exception_item *ex;
+	struct list_head *this, *tmp;
+
+	list_for_each_safe(this, tmp, &devcg->exceptions) {
+		ex = container_of(this, struct dev_exception_item, list);
+		if (!parent_has_perm(devcg, ex))
+			dev_exception_rm(devcg, ex);
+	}
+}
+
+/**
+ * propagate_exception - propagates a new exception to the children
+ * @devcg_root: device cgroup that added a new exception
+ * @ex: new exception to be propagated
+ *
+ * returns: 0 in case of success, != 0 in case of error
+ */
+static int propagate_exception(struct dev_cgroup *devcg_root,
+			       struct dev_exception_item *ex)
+{
+	struct cgroup_subsys_state *pos;
+	int rc = 0;
+
+	rcu_read_lock();
+
+	css_for_each_descendant_pre(pos, &devcg_root->css) {
+		struct dev_cgroup *devcg = css_to_devcgroup(pos);
+
+		/*
+		 * Because devcgroup_mutex is held, no devcg will become
+		 * online or offline during the tree walk (see on/offline
+		 * methods), and online ones are safe to access outside RCU
+		 * read lock without bumping refcnt.
+		 */
+		if (pos == &devcg_root->css || !is_devcg_online(devcg))
+			continue;
+
+		rcu_read_unlock();
+
+		/*
+		 * in case both root's behavior and devcg is allow, a new
+		 * restriction means adding to the exception list
+		 */
+		if (devcg_root->behavior == DEVCG_DEFAULT_ALLOW &&
+		    devcg->behavior == DEVCG_DEFAULT_ALLOW) {
+			rc = dev_exception_add(devcg, ex);
+			if (rc)
+				break;
+		} else {
+			/*
+			 * in the other possible cases:
+			 * root's behavior: allow, devcg's: deny
+			 * root's behavior: deny, devcg's: deny
+			 * the exception will be removed
+			 */
+			dev_exception_rm(devcg, ex);
+		}
+		revalidate_active_exceptions(devcg);
+
+		rcu_read_lock();
+	}
+
+	rcu_read_unlock();
+	return rc;
+}
+
+/*
+ * Modify the exception list using allow/deny rules.
+ * CAP_SYS_ADMIN is needed for this.  It's at least separate from CAP_MKNOD
+ * so we can give a container CAP_MKNOD to let it create devices but not
+ * modify the exception list.
+ * It seems likely we'll want to add a CAP_CONTAINER capability to allow
+ * us to also grant CAP_SYS_ADMIN to containers without giving away the
+ * device exception list controls, but for now we'll stick with CAP_SYS_ADMIN
+ *
+ * Taking rules away is always allowed (given CAP_SYS_ADMIN).  Granting
+ * new access is only allowed if you're in the top-level cgroup, or your
+ * parent cgroup has the access you're asking for.
+ */
+static int devcgroup_update_access(struct dev_cgroup *devcgroup,
+				   int filetype, char *buffer)
+{
+	const char *b;
+	char temp[12];		/* 11 + 1 characters needed for a u32 */
+	int count, rc = 0;
+	struct dev_exception_item ex;
+	struct dev_cgroup *parent = css_to_devcgroup(devcgroup->css.parent);
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	memset(&ex, 0, sizeof(ex));
+	b = buffer;
+
+	switch (*b) {
+	case 'a':
+		switch (filetype) {
+		case DEVCG_ALLOW:
+			if (css_has_online_children(&devcgroup->css))
+				return -EINVAL;
+
+			if (!may_allow_all(parent))
+				return -EPERM;
+			dev_exception_clean(devcgroup);
+			devcgroup->behavior = DEVCG_DEFAULT_ALLOW;
+			if (!parent)
+				break;
+
+			rc = dev_exceptions_copy(&devcgroup->exceptions,
+						 &parent->exceptions);
+			if (rc)
+				return rc;
+			break;
+		case DEVCG_DENY:
+			if (css_has_online_children(&devcgroup->css))
+				return -EINVAL;
+
+			dev_exception_clean(devcgroup);
+			devcgroup->behavior = DEVCG_DEFAULT_DENY;
+			break;
+		default:
+			return -EINVAL;
+		}
+		return 0;
+	case 'b':
+		ex.type = DEV_BLOCK;
+		break;
+	case 'c':
+		ex.type = DEV_CHAR;
+		break;
+	default:
+		return -EINVAL;
+	}
+	b++;
+	if (!isspace(*b))
+		return -EINVAL;
+	b++;
+	if (*b == '*') {
+		ex.major = ~0;
+		b++;
+	} else if (isdigit(*b)) {
+		memset(temp, 0, sizeof(temp));
+		for (count = 0; count < sizeof(temp) - 1; count++) {
+			temp[count] = *b;
+			b++;
+			if (!isdigit(*b))
+				break;
+		}
+		rc = kstrtou32(temp, 10, &ex.major);
+		if (rc)
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+	if (*b != ':')
+		return -EINVAL;
+	b++;
+
+	/* read minor */
+	if (*b == '*') {
+		ex.minor = ~0;
+		b++;
+	} else if (isdigit(*b)) {
+		memset(temp, 0, sizeof(temp));
+		for (count = 0; count < sizeof(temp) - 1; count++) {
+			temp[count] = *b;
+			b++;
+			if (!isdigit(*b))
+				break;
+		}
+		rc = kstrtou32(temp, 10, &ex.minor);
+		if (rc)
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+	if (!isspace(*b))
+		return -EINVAL;
+	for (b++, count = 0; count < 3; count++, b++) {
+		switch (*b) {
+		case 'r':
+			ex.access |= ACC_READ;
+			break;
+		case 'w':
+			ex.access |= ACC_WRITE;
+			break;
+		case 'm':
+			ex.access |= ACC_MKNOD;
+			break;
+		case '\n':
+		case '\0':
+			count = 3;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	switch (filetype) {
+	case DEVCG_ALLOW:
+		/*
+		 * If the default policy is to allow by default, try to remove
+		 * an matching exception instead. And be silent about it: we
+		 * don't want to break compatibility
+		 */
+		if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) {
+			/* Check if the parent allows removing it first */
+			if (!parent_allows_removal(devcgroup, &ex))
+				return -EPERM;
+			dev_exception_rm(devcgroup, &ex);
+			break;
+		}
+
+		if (!parent_has_perm(devcgroup, &ex))
+			return -EPERM;
+		rc = dev_exception_add(devcgroup, &ex);
+		break;
+	case DEVCG_DENY:
+		/*
+		 * If the default policy is to deny by default, try to remove
+		 * an matching exception instead. And be silent about it: we
+		 * don't want to break compatibility
+		 */
+		if (devcgroup->behavior == DEVCG_DEFAULT_DENY)
+			dev_exception_rm(devcgroup, &ex);
+		else
+			rc = dev_exception_add(devcgroup, &ex);
+
+		if (rc)
+			break;
+		/* we only propagate new restrictions */
+		rc = propagate_exception(devcgroup, &ex);
+		break;
+	default:
+		rc = -EINVAL;
+	}
+	return rc;
+}
+
+static ssize_t devcgroup_access_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
+{
+	int retval;
+
+	mutex_lock(&devcgroup_mutex);
+	retval = devcgroup_update_access(css_to_devcgroup(of_css(of)),
+					 of_cft(of)->private, strstrip(buf));
+	mutex_unlock(&devcgroup_mutex);
+	return retval ?: nbytes;
+}
+
+static struct cftype dev_cgroup_files[] = {
+	{
+		.name = "allow",
+		.write = devcgroup_access_write,
+		.private = DEVCG_ALLOW,
+	},
+	{
+		.name = "deny",
+		.write = devcgroup_access_write,
+		.private = DEVCG_DENY,
+	},
+	{
+		.name = "list",
+		.seq_show = devcgroup_seq_show,
+		.private = DEVCG_LIST,
+	},
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys devices_cgrp_subsys = {
+	.css_alloc = devcgroup_css_alloc,
+	.css_free = devcgroup_css_free,
+	.css_online = devcgroup_online,
+	.css_offline = devcgroup_offline,
+	.legacy_cftypes = dev_cgroup_files,
+};
+
+/**
+ * __devcgroup_check_permission - checks if an inode operation is permitted
+ * @dev_cgroup: the dev cgroup to be tested against
+ * @type: device type
+ * @major: device major number
+ * @minor: device minor number
+ * @access: combination of ACC_WRITE, ACC_READ and ACC_MKNOD
+ *
+ * returns 0 on success, -EPERM case the operation is not permitted
+ */
+static int __devcgroup_check_permission(short type, u32 major, u32 minor,
+				        short access)
+{
+	struct dev_cgroup *dev_cgroup;
+	bool rc;
+
+	rcu_read_lock();
+	dev_cgroup = task_devcgroup(current);
+	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW)
+		/* Can't match any of the exceptions, even partially */
+		rc = !match_exception_partial(&dev_cgroup->exceptions,
+					      type, major, minor, access);
+	else
+		/* Need to match completely one exception to be allowed */
+		rc = match_exception(&dev_cgroup->exceptions, type, major,
+				     minor, access);
+	rcu_read_unlock();
+
+	if (!rc)
+		return -EPERM;
+
+	return 0;
+}
+
+int __devcgroup_inode_permission(struct inode *inode, int mask)
+{
+	short type, access = 0;
+
+	if (S_ISBLK(inode->i_mode))
+		type = DEV_BLOCK;
+	if (S_ISCHR(inode->i_mode))
+		type = DEV_CHAR;
+	if (mask & MAY_WRITE)
+		access |= ACC_WRITE;
+	if (mask & MAY_READ)
+		access |= ACC_READ;
+
+	return __devcgroup_check_permission(type, imajor(inode), iminor(inode),
+			access);
+}
+
+int devcgroup_inode_mknod(int mode, dev_t dev)
+{
+	short type;
+
+	if (!S_ISBLK(mode) && !S_ISCHR(mode))
+		return 0;
+
+	if (S_ISBLK(mode))
+		type = DEV_BLOCK;
+	else
+		type = DEV_CHAR;
+
+	return __devcgroup_check_permission(type, MAJOR(dev), MINOR(dev),
+			ACC_MKNOD);
+
+}

security/inode.c

@@ -0,0 +1,236 @@
+/*
+ *  inode.c - securityfs
+ *
+ *  Copyright (C) 2005 Greg Kroah-Hartman <gregkh@suse.de>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License version
+ *	2 as published by the Free Software Foundation.
+ *
+ *  Based on fs/debugfs/inode.c which had the following copyright notice:
+ *    Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com>
+ *    Copyright (C) 2004 IBM Inc.
+ */
+
+/* #define DEBUG */
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/pagemap.h>
+#include <linux/init.h>
+#include <linux/namei.h>
+#include <linux/security.h>
+#include <linux/magic.h>
+
+static struct vfsmount *mount;
+static int mount_count;
+
+static inline int positive(struct dentry *dentry)
+{
+	return dentry->d_inode && !d_unhashed(dentry);
+}
+
+static int fill_super(struct super_block *sb, void *data, int silent)
+{
+	static struct tree_descr files[] = {{""}};
+
+	return simple_fill_super(sb, SECURITYFS_MAGIC, files);
+}
+
+static struct dentry *get_sb(struct file_system_type *fs_type,
+		  int flags, const char *dev_name,
+		  void *data)
+{
+	return mount_single(fs_type, flags, data, fill_super);
+}
+
+static struct file_system_type fs_type = {
+	.owner =	THIS_MODULE,
+	.name =		"securityfs",
+	.mount =	get_sb,
+	.kill_sb =	kill_litter_super,
+};
+
+/**
+ * securityfs_create_file - create a file in the securityfs filesystem
+ *
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is %NULL, then the
+ *          file will be created in the root of the securityfs filesystem.
+ * @data: a pointer to something that the caller will want to get to later
+ *        on.  The inode.i_private pointer will point to this value on
+ *        the open() call.
+ * @fops: a pointer to a struct file_operations that should be used for
+ *        this file.
+ *
+ * This is the basic "create a file" function for securityfs.  It allows for a
+ * wide range of flexibility in creating a file, or a directory (if you
+ * want to create a directory, the securityfs_create_dir() function is
+ * recommended to be used instead).
+ *
+ * This function returns a pointer to a dentry if it succeeds.  This
+ * pointer must be passed to the securityfs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here).  If an error occurs, the function will return
+ * the error value (via ERR_PTR).
+ *
+ * If securityfs is not enabled in the kernel, the value %-ENODEV is
+ * returned.
+ */
+struct dentry *securityfs_create_file(const char *name, umode_t mode,
+				   struct dentry *parent, void *data,
+				   const struct file_operations *fops)
+{
+	struct dentry *dentry;
+	int is_dir = S_ISDIR(mode);
+	struct inode *dir, *inode;
+	int error;
+
+	if (!is_dir) {
+		BUG_ON(!fops);
+		mode = (mode & S_IALLUGO) | S_IFREG;
+	}
+
+	pr_debug("securityfs: creating file '%s'\n",name);
+
+	error = simple_pin_fs(&fs_type, &mount, &mount_count);
+	if (error)
+		return ERR_PTR(error);
+
+	if (!parent)
+		parent = mount->mnt_root;
+
+	dir = parent->d_inode;
+
+	mutex_lock(&dir->i_mutex);
+	dentry = lookup_one_len(name, parent, strlen(name));
+	if (IS_ERR(dentry))
+		goto out;
+
+	if (dentry->d_inode) {
+		error = -EEXIST;
+		goto out1;
+	}
+
+	inode = new_inode(dir->i_sb);
+	if (!inode) {
+		error = -ENOMEM;
+		goto out1;
+	}
+
+	inode->i_ino = get_next_ino();
+	inode->i_mode = mode;
+	inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	inode->i_private = data;
+	if (is_dir) {
+		inode->i_op = &simple_dir_inode_operations;
+		inode->i_fop = &simple_dir_operations;
+		inc_nlink(inode);
+		inc_nlink(dir);
+	} else {
+		inode->i_fop = fops;
+	}
+	d_instantiate(dentry, inode);
+	dget(dentry);
+	mutex_unlock(&dir->i_mutex);
+	return dentry;
+
+out1:
+	dput(dentry);
+	dentry = ERR_PTR(error);
+out:
+	mutex_unlock(&dir->i_mutex);
+	simple_release_fs(&mount, &mount_count);
+	return dentry;
+}
+EXPORT_SYMBOL_GPL(securityfs_create_file);
+
+/**
+ * securityfs_create_dir - create a directory in the securityfs filesystem
+ *
+ * @name: a pointer to a string containing the name of the directory to
+ *        create.
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is %NULL, then the
+ *          directory will be created in the root of the securityfs filesystem.
+ *
+ * This function creates a directory in securityfs with the given @name.
+ *
+ * This function returns a pointer to a dentry if it succeeds.  This
+ * pointer must be passed to the securityfs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here).  If an error occurs, %NULL will be returned.
+ *
+ * If securityfs is not enabled in the kernel, the value %-ENODEV is
+ * returned.  It is not wise to check for this value, but rather, check for
+ * %NULL or !%NULL instead as to eliminate the need for #ifdef in the calling
+ * code.
+ */
+struct dentry *securityfs_create_dir(const char *name, struct dentry *parent)
+{
+	return securityfs_create_file(name,
+				      S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO,
+				      parent, NULL, NULL);
+}
+EXPORT_SYMBOL_GPL(securityfs_create_dir);
+
+/**
+ * securityfs_remove - removes a file or directory from the securityfs filesystem
+ *
+ * @dentry: a pointer to a the dentry of the file or directory to be removed.
+ *
+ * This function removes a file or directory in securityfs that was previously
+ * created with a call to another securityfs function (like
+ * securityfs_create_file() or variants thereof.)
+ *
+ * This function is required to be called in order for the file to be
+ * removed. No automatic cleanup of files will happen when a module is
+ * removed; you are responsible here.
+ */
+void securityfs_remove(struct dentry *dentry)
+{
+	struct dentry *parent;
+
+	if (!dentry || IS_ERR(dentry))
+		return;
+
+	parent = dentry->d_parent;
+	if (!parent || !parent->d_inode)
+		return;
+
+	mutex_lock(&parent->d_inode->i_mutex);
+	if (positive(dentry)) {
+		if (dentry->d_inode) {
+			if (S_ISDIR(dentry->d_inode->i_mode))
+				simple_rmdir(parent->d_inode, dentry);
+			else
+				simple_unlink(parent->d_inode, dentry);
+			dput(dentry);
+		}
+	}
+	mutex_unlock(&parent->d_inode->i_mutex);
+	simple_release_fs(&mount, &mount_count);
+}
+EXPORT_SYMBOL_GPL(securityfs_remove);
+
+static struct kobject *security_kobj;
+
+static int __init securityfs_init(void)
+{
+	int retval;
+
+	security_kobj = kobject_create_and_add("security", kernel_kobj);
+	if (!security_kobj)
+		return -EINVAL;
+
+	retval = register_filesystem(&fs_type);
+	if (retval)
+		kobject_put(security_kobj);
+	return retval;
+}
+
+core_initcall(securityfs_init);
+MODULE_LICENSE("GPL");
+

security/integrity/Kconfig

@@ -0,0 +1,62 @@
+#
+config INTEGRITY
+	bool "Integrity subsystem"
+	depends on SECURITY
+	default y
+	help
+	  This option enables the integrity subsystem, which is comprised
+	  of a number of different components including the Integrity
+	  Measurement Architecture (IMA), Extended Verification Module
+	  (EVM), IMA-appraisal extension, digital signature verification
+	  extension and audit measurement log support.
+
+	  Each of these components can be enabled/disabled separately.
+	  Refer to the individual components for additional details.
+
+if INTEGRITY
+
+config INTEGRITY_SIGNATURE
+	boolean "Digital signature verification using multiple keyrings"
+	depends on KEYS
+	default n
+	select SIGNATURE
+	help
+	  This option enables digital signature verification support
+	  using multiple keyrings. It defines separate keyrings for each
+	  of the different use cases - evm, ima, and modules.
+	  Different keyrings improves search performance, but also allow
+	  to "lock" certain keyring to prevent adding new keys.
+	  This is useful for evm and module keyrings, when keys are
+	  usually only added from initramfs.
+
+config INTEGRITY_ASYMMETRIC_KEYS
+	boolean "Enable asymmetric keys support"
+	depends on INTEGRITY_SIGNATURE
+	default n
+        select ASYMMETRIC_KEY_TYPE
+        select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
+        select PUBLIC_KEY_ALGO_RSA
+        select X509_CERTIFICATE_PARSER
+	help
+	  This option enables digital signature verification using
+	  asymmetric keys.
+
+config INTEGRITY_AUDIT
+	bool "Enables integrity auditing support "
+	depends on AUDIT
+	default y
+	help
+	  In addition to enabling integrity auditing support, this
+	  option adds a kernel parameter 'integrity_audit', which
+	  controls the level of integrity auditing messages.
+	  0 - basic integrity auditing messages (default)
+	  1 - additional integrity auditing messages
+
+	  Additional informational integrity auditing messages would
+	  be enabled by specifying 'integrity_audit=1' on the kernel
+	  command line.
+
+source security/integrity/ima/Kconfig
+source security/integrity/evm/Kconfig
+
+endif   # if INTEGRITY

security/integrity/Makefile

@@ -0,0 +1,15 @@
+#
+# Makefile for caching inode integrity data (iint)
+#
+
+obj-$(CONFIG_INTEGRITY) += integrity.o
+
+integrity-y := iint.o
+integrity-$(CONFIG_INTEGRITY_AUDIT) += integrity_audit.o
+integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o
+integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o
+
+subdir-$(CONFIG_IMA)			+= ima
+obj-$(CONFIG_IMA)			+= ima/
+subdir-$(CONFIG_EVM)			+= evm
+obj-$(CONFIG_EVM)			+= evm/

security/integrity/digsig.c

@@ -0,0 +1,86 @@
+/*
+ * Copyright (C) 2011 Intel Corporation
+ *
+ * Author:
+ * Dmitry Kasatkin <dmitry.kasatkin@intel.com>
+ *
+ * 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, version 2 of the License.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/err.h>
+#include <linux/sched.h>
+#include <linux/rbtree.h>
+#include <linux/cred.h>
+#include <linux/key-type.h>
+#include <linux/digsig.h>
+
+#include "integrity.h"
+
+static struct key *keyring[INTEGRITY_KEYRING_MAX];
+
+static const char *keyring_name[INTEGRITY_KEYRING_MAX] = {
+	"_evm",
+	"_module",
+#ifndef CONFIG_IMA_TRUSTED_KEYRING
+	"_ima",
+#else
+	".ima",
+#endif
+};
+
+int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
+			    const char *digest, int digestlen)
+{
+	if (id >= INTEGRITY_KEYRING_MAX)
+		return -EINVAL;
+
+	if (!keyring[id]) {
+		keyring[id] =
+			request_key(&key_type_keyring, keyring_name[id], NULL);
+		if (IS_ERR(keyring[id])) {
+			int err = PTR_ERR(keyring[id]);
+			pr_err("no %s keyring: %d\n", keyring_name[id], err);
+			keyring[id] = NULL;
+			return err;
+		}
+	}
+
+	switch (sig[1]) {
+	case 1:
+		/* v1 API expect signature without xattr type */
+		return digsig_verify(keyring[id], sig + 1, siglen - 1,
+				     digest, digestlen);
+	case 2:
+		return asymmetric_verify(keyring[id], sig, siglen,
+					 digest, digestlen);
+	}
+
+	return -EOPNOTSUPP;
+}
+
+int integrity_init_keyring(const unsigned int id)
+{
+	const struct cred *cred = current_cred();
+	int err = 0;
+
+	keyring[id] = keyring_alloc(keyring_name[id], KUIDT_INIT(0),
+				    KGIDT_INIT(0), cred,
+				    ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+				     KEY_USR_VIEW | KEY_USR_READ |
+				     KEY_USR_WRITE | KEY_USR_SEARCH),
+				    KEY_ALLOC_NOT_IN_QUOTA, NULL);
+	if (!IS_ERR(keyring[id]))
+		set_bit(KEY_FLAG_TRUSTED_ONLY, &keyring[id]->flags);
+	else {
+		err = PTR_ERR(keyring[id]);
+		pr_info("Can't allocate %s keyring (%d)\n",
+			keyring_name[id], err);
+		keyring[id] = NULL;
+	}
+	return err;
+}

security/integrity/digsig_asymmetric.c

@@ -0,0 +1,105 @@
+/*
+ * Copyright (C) 2013 Intel Corporation
+ *
+ * Author:
+ * Dmitry Kasatkin <dmitry.kasatkin@intel.com>
+ *
+ * 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, version 2 of the License.
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/err.h>
+#include <linux/ratelimit.h>
+#include <linux/key-type.h>
+#include <crypto/public_key.h>
+#include <keys/asymmetric-type.h>
+
+#include "integrity.h"
+
+/*
+ * Request an asymmetric key.
+ */
+static struct key *request_asymmetric_key(struct key *keyring, uint32_t keyid)
+{
+	struct key *key;
+	char name[12];
+
+	sprintf(name, "id:%08x", keyid);
+
+	pr_debug("key search: \"%s\"\n", name);
+
+	if (keyring) {
+		/* search in specific keyring */
+		key_ref_t kref;
+		kref = keyring_search(make_key_ref(keyring, 1),
+				      &key_type_asymmetric, name);
+		if (IS_ERR(kref))
+			key = ERR_CAST(kref);
+		else
+			key = key_ref_to_ptr(kref);
+	} else {
+		key = request_key(&key_type_asymmetric, name, NULL);
+	}
+
+	if (IS_ERR(key)) {
+		pr_err_ratelimited("Request for unknown key '%s' err %ld\n",
+				   name, PTR_ERR(key));
+		switch (PTR_ERR(key)) {
+			/* Hide some search errors */
+		case -EACCES:
+		case -ENOTDIR:
+		case -EAGAIN:
+			return ERR_PTR(-ENOKEY);
+		default:
+			return key;
+		}
+	}
+
+	pr_debug("%s() = 0 [%x]\n", __func__, key_serial(key));
+
+	return key;
+}
+
+int asymmetric_verify(struct key *keyring, const char *sig,
+		      int siglen, const char *data, int datalen)
+{
+	struct public_key_signature pks;
+	struct signature_v2_hdr *hdr = (struct signature_v2_hdr *)sig;
+	struct key *key;
+	int ret = -ENOMEM;
+
+	if (siglen <= sizeof(*hdr))
+		return -EBADMSG;
+
+	siglen -= sizeof(*hdr);
+
+	if (siglen != __be16_to_cpu(hdr->sig_size))
+		return -EBADMSG;
+
+	if (hdr->hash_algo >= PKEY_HASH__LAST)
+		return -ENOPKG;
+
+	key = request_asymmetric_key(keyring, __be32_to_cpu(hdr->keyid));
+	if (IS_ERR(key))
+		return PTR_ERR(key);
+
+	memset(&pks, 0, sizeof(pks));
+
+	pks.pkey_hash_algo = hdr->hash_algo;
+	pks.digest = (u8 *)data;
+	pks.digest_size = datalen;
+	pks.nr_mpi = 1;
+	pks.rsa.s = mpi_read_raw_data(hdr->sig, siglen);
+
+	if (pks.rsa.s)
+		ret = verify_signature(key, &pks);
+
+	mpi_free(pks.rsa.s);
+	key_put(key);
+	pr_debug("%s() = %d\n", __func__, ret);
+	return ret;
+}

security/integrity/evm/Kconfig

@@ -0,0 +1,44 @@
+config EVM
+	boolean "EVM support"
+	select KEYS
+	select ENCRYPTED_KEYS
+	select CRYPTO_HMAC
+	select CRYPTO_SHA1
+	default n
+	help
+	  EVM protects a file's security extended attributes against
+	  integrity attacks.
+
+	  If you are unsure how to answer this question, answer N.
+
+config EVM_ATTR_FSUUID
+	bool "FSUUID (version 2)"
+	default y
+	depends on EVM
+	help
+	  Include filesystem UUID for HMAC calculation.
+
+	  Default value is 'selected', which is former version 2.
+	  if 'not selected', it is former version 1
+
+	  WARNING: changing the HMAC calculation method or adding
+	  additional info to the calculation, requires existing EVM
+	  labeled file systems to be relabeled.
+
+config EVM_EXTRA_SMACK_XATTRS
+	bool "Additional SMACK xattrs"
+	depends on EVM && SECURITY_SMACK
+	default n
+	help
+	  Include additional SMACK xattrs for HMAC calculation.
+
+	  In addition to the original security xattrs (eg. security.selinux,
+	  security.SMACK64, security.capability, and security.ima) included
+	  in the HMAC calculation, enabling this option includes newly defined
+	  Smack xattrs: security.SMACK64EXEC, security.SMACK64TRANSMUTE and
+	  security.SMACK64MMAP.
+
+	  WARNING: changing the HMAC calculation method or adding
+	  additional info to the calculation, requires existing EVM
+	  labeled file systems to be relabeled.
+

security/integrity/evm/Makefile

@@ -0,0 +1,7 @@
+#
+# Makefile for building the Extended Verification Module(EVM)
+#
+obj-$(CONFIG_EVM) += evm.o
+
+evm-y := evm_main.o evm_crypto.o evm_secfs.o
+evm-$(CONFIG_FS_POSIX_ACL) += evm_posix_acl.o

security/integrity/evm/evm.h

@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2005-2010 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * 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, version 2 of the License.
+ *
+ * File: evm.h
+ *
+ */
+
+#ifndef __INTEGRITY_EVM_H
+#define __INTEGRITY_EVM_H
+
+#include <linux/xattr.h>
+#include <linux/security.h>
+
+#include "../integrity.h"
+
+extern int evm_initialized;
+extern char *evm_hmac;
+extern char *evm_hash;
+
+#define EVM_ATTR_FSUUID		0x0001
+
+extern int evm_hmac_attrs;
+
+extern struct crypto_shash *hmac_tfm;
+extern struct crypto_shash *hash_tfm;
+
+/* List of EVM protected security xattrs */
+extern char *evm_config_xattrnames[];
+
+int evm_init_key(void);
+int evm_update_evmxattr(struct dentry *dentry,
+			const char *req_xattr_name,
+			const char *req_xattr_value,
+			size_t req_xattr_value_len);
+int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name,
+		  const char *req_xattr_value,
+		  size_t req_xattr_value_len, char *digest);
+int evm_calc_hash(struct dentry *dentry, const char *req_xattr_name,
+		  const char *req_xattr_value,
+		  size_t req_xattr_value_len, char *digest);
+int evm_init_hmac(struct inode *inode, const struct xattr *xattr,
+		  char *hmac_val);
+int evm_init_secfs(void);
+
+#endif

security/integrity/evm/evm_crypto.c

@@ -0,0 +1,262 @@
+/*
+ * Copyright (C) 2005-2010 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * 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, version 2 of the License.
+ *
+ * File: evm_crypto.c
+ *	 Using root's kernel master key (kmk), calculate the HMAC
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/xattr.h>
+#include <keys/encrypted-type.h>
+#include <crypto/hash.h>
+#include "evm.h"
+
+#define EVMKEY "evm-key"
+#define MAX_KEY_SIZE 128
+static unsigned char evmkey[MAX_KEY_SIZE];
+static int evmkey_len = MAX_KEY_SIZE;
+
+struct crypto_shash *hmac_tfm;
+struct crypto_shash *hash_tfm;
+
+static DEFINE_MUTEX(mutex);
+
+static struct shash_desc *init_desc(char type)
+{
+	long rc;
+	char *algo;
+	struct crypto_shash **tfm;
+	struct shash_desc *desc;
+
+	if (type == EVM_XATTR_HMAC) {
+		tfm = &hmac_tfm;
+		algo = evm_hmac;
+	} else {
+		tfm = &hash_tfm;
+		algo = evm_hash;
+	}
+
+	if (*tfm == NULL) {
+		mutex_lock(&mutex);
+		if (*tfm)
+			goto out;
+		*tfm = crypto_alloc_shash(algo, 0, CRYPTO_ALG_ASYNC);
+		if (IS_ERR(*tfm)) {
+			rc = PTR_ERR(*tfm);
+			pr_err("Can not allocate %s (reason: %ld)\n", algo, rc);
+			*tfm = NULL;
+			mutex_unlock(&mutex);
+			return ERR_PTR(rc);
+		}
+		if (type == EVM_XATTR_HMAC) {
+			rc = crypto_shash_setkey(*tfm, evmkey, evmkey_len);
+			if (rc) {
+				crypto_free_shash(*tfm);
+				*tfm = NULL;
+				mutex_unlock(&mutex);
+				return ERR_PTR(rc);
+			}
+		}
+out:
+		mutex_unlock(&mutex);
+	}
+
+	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(*tfm),
+			GFP_KERNEL);
+	if (!desc)
+		return ERR_PTR(-ENOMEM);
+
+	desc->tfm = *tfm;
+	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	rc = crypto_shash_init(desc);
+	if (rc) {
+		kfree(desc);
+		return ERR_PTR(rc);
+	}
+	return desc;
+}
+
+/* Protect against 'cutting & pasting' security.evm xattr, include inode
+ * specific info.
+ *
+ * (Additional directory/file metadata needs to be added for more complete
+ * protection.)
+ */
+static void hmac_add_misc(struct shash_desc *desc, struct inode *inode,
+			  char *digest)
+{
+	struct h_misc {
+		unsigned long ino;
+		__u32 generation;
+		uid_t uid;
+		gid_t gid;
+		umode_t mode;
+	} hmac_misc;
+
+	memset(&hmac_misc, 0, sizeof(hmac_misc));
+	hmac_misc.ino = inode->i_ino;
+	hmac_misc.generation = inode->i_generation;
+	hmac_misc.uid = from_kuid(&init_user_ns, inode->i_uid);
+	hmac_misc.gid = from_kgid(&init_user_ns, inode->i_gid);
+	hmac_misc.mode = inode->i_mode;
+	crypto_shash_update(desc, (const u8 *)&hmac_misc, sizeof(hmac_misc));
+	if (evm_hmac_attrs & EVM_ATTR_FSUUID)
+		crypto_shash_update(desc, inode->i_sb->s_uuid,
+				    sizeof(inode->i_sb->s_uuid));
+	crypto_shash_final(desc, digest);
+}
+
+/*
+ * Calculate the HMAC value across the set of protected security xattrs.
+ *
+ * Instead of retrieving the requested xattr, for performance, calculate
+ * the hmac using the requested xattr value. Don't alloc/free memory for
+ * each xattr, but attempt to re-use the previously allocated memory.
+ */
+static int evm_calc_hmac_or_hash(struct dentry *dentry,
+				const char *req_xattr_name,
+				const char *req_xattr_value,
+				size_t req_xattr_value_len,
+				char type, char *digest)
+{
+	struct inode *inode = dentry->d_inode;
+	struct shash_desc *desc;
+	char **xattrname;
+	size_t xattr_size = 0;
+	char *xattr_value = NULL;
+	int error;
+	int size;
+
+	if (!inode->i_op->getxattr)
+		return -EOPNOTSUPP;
+	desc = init_desc(type);
+	if (IS_ERR(desc))
+		return PTR_ERR(desc);
+
+	error = -ENODATA;
+	for (xattrname = evm_config_xattrnames; *xattrname != NULL; xattrname++) {
+		if ((req_xattr_name && req_xattr_value)
+		    && !strcmp(*xattrname, req_xattr_name)) {
+			error = 0;
+			crypto_shash_update(desc, (const u8 *)req_xattr_value,
+					     req_xattr_value_len);
+			continue;
+		}
+		size = vfs_getxattr_alloc(dentry, *xattrname,
+					  &xattr_value, xattr_size, GFP_NOFS);
+		if (size == -ENOMEM) {
+			error = -ENOMEM;
+			goto out;
+		}
+		if (size < 0)
+			continue;
+
+		error = 0;
+		xattr_size = size;
+		crypto_shash_update(desc, (const u8 *)xattr_value, xattr_size);
+	}
+	hmac_add_misc(desc, inode, digest);
+
+out:
+	kfree(xattr_value);
+	kfree(desc);
+	return error;
+}
+
+int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name,
+		  const char *req_xattr_value, size_t req_xattr_value_len,
+		  char *digest)
+{
+	return evm_calc_hmac_or_hash(dentry, req_xattr_name, req_xattr_value,
+				req_xattr_value_len, EVM_XATTR_HMAC, digest);
+}
+
+int evm_calc_hash(struct dentry *dentry, const char *req_xattr_name,
+		  const char *req_xattr_value, size_t req_xattr_value_len,
+		  char *digest)
+{
+	return evm_calc_hmac_or_hash(dentry, req_xattr_name, req_xattr_value,
+				req_xattr_value_len, IMA_XATTR_DIGEST, digest);
+}
+
+/*
+ * Calculate the hmac and update security.evm xattr
+ *
+ * Expects to be called with i_mutex locked.
+ */
+int evm_update_evmxattr(struct dentry *dentry, const char *xattr_name,
+			const char *xattr_value, size_t xattr_value_len)
+{
+	struct inode *inode = dentry->d_inode;
+	struct evm_ima_xattr_data xattr_data;
+	int rc = 0;
+
+	rc = evm_calc_hmac(dentry, xattr_name, xattr_value,
+			   xattr_value_len, xattr_data.digest);
+	if (rc == 0) {
+		xattr_data.type = EVM_XATTR_HMAC;
+		rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_EVM,
+					   &xattr_data,
+					   sizeof(xattr_data), 0);
+	} else if (rc == -ENODATA && inode->i_op->removexattr) {
+		rc = inode->i_op->removexattr(dentry, XATTR_NAME_EVM);
+	}
+	return rc;
+}
+
+int evm_init_hmac(struct inode *inode, const struct xattr *lsm_xattr,
+		  char *hmac_val)
+{
+	struct shash_desc *desc;
+
+	desc = init_desc(EVM_XATTR_HMAC);
+	if (IS_ERR(desc)) {
+		pr_info("init_desc failed\n");
+		return PTR_ERR(desc);
+	}
+
+	crypto_shash_update(desc, lsm_xattr->value, lsm_xattr->value_len);
+	hmac_add_misc(desc, inode, hmac_val);
+	kfree(desc);
+	return 0;
+}
+
+/*
+ * Get the key from the TPM for the SHA1-HMAC
+ */
+int evm_init_key(void)
+{
+	struct key *evm_key;
+	struct encrypted_key_payload *ekp;
+	int rc = 0;
+
+	evm_key = request_key(&key_type_encrypted, EVMKEY, NULL);
+	if (IS_ERR(evm_key))
+		return -ENOENT;
+
+	down_read(&evm_key->sem);
+	ekp = evm_key->payload.data;
+	if (ekp->decrypted_datalen > MAX_KEY_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+	memcpy(evmkey, ekp->decrypted_data, ekp->decrypted_datalen);
+out:
+	/* burn the original key contents */
+	memset(ekp->decrypted_data, 0, ekp->decrypted_datalen);
+	up_read(&evm_key->sem);
+	key_put(evm_key);
+	return rc;
+}

security/integrity/evm/evm_main.c

@@ -0,0 +1,494 @@
+/*
+ * Copyright (C) 2005-2010 IBM Corporation
+ *
+ * Author:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * 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, version 2 of the License.
+ *
+ * File: evm_main.c
+ *	implements evm_inode_setxattr, evm_inode_post_setxattr,
+ *	evm_inode_removexattr, and evm_verifyxattr
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <linux/audit.h>
+#include <linux/xattr.h>
+#include <linux/integrity.h>
+#include <linux/evm.h>
+#include <crypto/hash.h>
+#include <crypto/algapi.h>
+#include "evm.h"
+
+int evm_initialized;
+
+static char *integrity_status_msg[] = {
+	"pass", "fail", "no_label", "no_xattrs", "unknown"
+};
+char *evm_hmac = "hmac(sha1)";
+char *evm_hash = "sha1";
+int evm_hmac_attrs;
+
+char *evm_config_xattrnames[] = {
+#ifdef CONFIG_SECURITY_SELINUX
+	XATTR_NAME_SELINUX,
+#endif
+#ifdef CONFIG_SECURITY_SMACK
+	XATTR_NAME_SMACK,
+#ifdef CONFIG_EVM_EXTRA_SMACK_XATTRS
+	XATTR_NAME_SMACKEXEC,
+	XATTR_NAME_SMACKTRANSMUTE,
+	XATTR_NAME_SMACKMMAP,
+#endif
+#endif
+#ifdef CONFIG_IMA_APPRAISE
+	XATTR_NAME_IMA,
+#endif
+	XATTR_NAME_CAPS,
+	NULL
+};
+
+static int evm_fixmode;
+static int __init evm_set_fixmode(char *str)
+{
+	if (strncmp(str, "fix", 3) == 0)
+		evm_fixmode = 1;
+	return 0;
+}
+__setup("evm=", evm_set_fixmode);
+
+static void __init evm_init_config(void)
+{
+#ifdef CONFIG_EVM_ATTR_FSUUID
+	evm_hmac_attrs |= EVM_ATTR_FSUUID;
+#endif
+	pr_info("HMAC attrs: 0x%x\n", evm_hmac_attrs);
+}
+
+static int evm_find_protected_xattrs(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	char **xattr;
+	int error;
+	int count = 0;
+
+	if (!inode->i_op->getxattr)
+		return -EOPNOTSUPP;
+
+	for (xattr = evm_config_xattrnames; *xattr != NULL; xattr++) {
+		error = inode->i_op->getxattr(dentry, *xattr, NULL, 0);
+		if (error < 0) {
+			if (error == -ENODATA)
+				continue;
+			return error;
+		}
+		count++;
+	}
+
+	return count;
+}
+
+/*
+ * evm_verify_hmac - calculate and compare the HMAC with the EVM xattr
+ *
+ * Compute the HMAC on the dentry's protected set of extended attributes
+ * and compare it against the stored security.evm xattr.
+ *
+ * For performance:
+ * - use the previoulsy retrieved xattr value and length to calculate the
+ *   HMAC.)
+ * - cache the verification result in the iint, when available.
+ *
+ * Returns integrity status
+ */
+static enum integrity_status evm_verify_hmac(struct dentry *dentry,
+					     const char *xattr_name,
+					     char *xattr_value,
+					     size_t xattr_value_len,
+					     struct integrity_iint_cache *iint)
+{
+	struct evm_ima_xattr_data *xattr_data = NULL;
+	struct evm_ima_xattr_data calc;
+	enum integrity_status evm_status = INTEGRITY_PASS;
+	int rc, xattr_len;
+
+	if (iint && iint->evm_status == INTEGRITY_PASS)
+		return iint->evm_status;
+
+	/* if status is not PASS, try to check again - against -ENOMEM */
+
+	/* first need to know the sig type */
+	rc = vfs_getxattr_alloc(dentry, XATTR_NAME_EVM, (char **)&xattr_data, 0,
+				GFP_NOFS);
+	if (rc <= 0) {
+		evm_status = INTEGRITY_FAIL;
+		if (rc == -ENODATA) {
+			rc = evm_find_protected_xattrs(dentry);
+			if (rc > 0)
+				evm_status = INTEGRITY_NOLABEL;
+			else if (rc == 0)
+				evm_status = INTEGRITY_NOXATTRS; /* new file */
+		} else if (rc == -EOPNOTSUPP) {
+			evm_status = INTEGRITY_UNKNOWN;
+		}
+		goto out;
+	}
+
+	xattr_len = rc;
+
+	/* check value type */
+	switch (xattr_data->type) {
+	case EVM_XATTR_HMAC:
+		rc = evm_calc_hmac(dentry, xattr_name, xattr_value,
+				   xattr_value_len, calc.digest);
+		if (rc)
+			break;
+		rc = crypto_memneq(xattr_data->digest, calc.digest,
+			    sizeof(calc.digest));
+		if (rc)
+			rc = -EINVAL;
+		break;
+	case EVM_IMA_XATTR_DIGSIG:
+		rc = evm_calc_hash(dentry, xattr_name, xattr_value,
+				xattr_value_len, calc.digest);
+		if (rc)
+			break;
+		rc = integrity_digsig_verify(INTEGRITY_KEYRING_EVM,
+					(const char *)xattr_data, xattr_len,
+					calc.digest, sizeof(calc.digest));
+		if (!rc) {
+			/* we probably want to replace rsa with hmac here */
+			evm_update_evmxattr(dentry, xattr_name, xattr_value,
+				   xattr_value_len);
+		}
+		break;
+	default:
+		rc = -EINVAL;
+		break;
+	}
+
+	if (rc)
+		evm_status = (rc == -ENODATA) ?
+				INTEGRITY_NOXATTRS : INTEGRITY_FAIL;
+out:
+	if (iint)
+		iint->evm_status = evm_status;
+	kfree(xattr_data);
+	return evm_status;
+}
+
+static int evm_protected_xattr(const char *req_xattr_name)
+{
+	char **xattrname;
+	int namelen;
+	int found = 0;
+
+	namelen = strlen(req_xattr_name);
+	for (xattrname = evm_config_xattrnames; *xattrname != NULL; xattrname++) {
+		if ((strlen(*xattrname) == namelen)
+		    && (strncmp(req_xattr_name, *xattrname, namelen) == 0)) {
+			found = 1;
+			break;
+		}
+		if (strncmp(req_xattr_name,
+			    *xattrname + XATTR_SECURITY_PREFIX_LEN,
+			    strlen(req_xattr_name)) == 0) {
+			found = 1;
+			break;
+		}
+	}
+	return found;
+}
+
+/**
+ * evm_verifyxattr - verify the integrity of the requested xattr
+ * @dentry: object of the verify xattr
+ * @xattr_name: requested xattr
+ * @xattr_value: requested xattr value
+ * @xattr_value_len: requested xattr value length
+ *
+ * Calculate the HMAC for the given dentry and verify it against the stored
+ * security.evm xattr. For performance, use the xattr value and length
+ * previously retrieved to calculate the HMAC.
+ *
+ * Returns the xattr integrity status.
+ *
+ * This function requires the caller to lock the inode's i_mutex before it
+ * is executed.
+ */
+enum integrity_status evm_verifyxattr(struct dentry *dentry,
+				      const char *xattr_name,
+				      void *xattr_value, size_t xattr_value_len,
+				      struct integrity_iint_cache *iint)
+{
+	if (!evm_initialized || !evm_protected_xattr(xattr_name))
+		return INTEGRITY_UNKNOWN;
+
+	if (!iint) {
+		iint = integrity_iint_find(dentry->d_inode);
+		if (!iint)
+			return INTEGRITY_UNKNOWN;
+	}
+	return evm_verify_hmac(dentry, xattr_name, xattr_value,
+				 xattr_value_len, iint);
+}
+EXPORT_SYMBOL_GPL(evm_verifyxattr);
+
+/*
+ * evm_verify_current_integrity - verify the dentry's metadata integrity
+ * @dentry: pointer to the affected dentry
+ *
+ * Verify and return the dentry's metadata integrity. The exceptions are
+ * before EVM is initialized or in 'fix' mode.
+ */
+static enum integrity_status evm_verify_current_integrity(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+
+	if (!evm_initialized || !S_ISREG(inode->i_mode) || evm_fixmode)
+		return 0;
+	return evm_verify_hmac(dentry, NULL, NULL, 0, NULL);
+}
+
+/*
+ * evm_protect_xattr - protect the EVM extended attribute
+ *
+ * Prevent security.evm from being modified or removed without the
+ * necessary permissions or when the existing value is invalid.
+ *
+ * The posix xattr acls are 'system' prefixed, which normally would not
+ * affect security.evm.  An interesting side affect of writing posix xattr
+ * acls is their modifying of the i_mode, which is included in security.evm.
+ * For posix xattr acls only, permit security.evm, even if it currently
+ * doesn't exist, to be updated.
+ */
+static int evm_protect_xattr(struct dentry *dentry, const char *xattr_name,
+			     const void *xattr_value, size_t xattr_value_len)
+{
+	enum integrity_status evm_status;
+
+	if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+	} else if (!evm_protected_xattr(xattr_name)) {
+		if (!posix_xattr_acl(xattr_name))
+			return 0;
+		evm_status = evm_verify_current_integrity(dentry);
+		if ((evm_status == INTEGRITY_PASS) ||
+		    (evm_status == INTEGRITY_NOXATTRS))
+			return 0;
+		goto out;
+	}
+	evm_status = evm_verify_current_integrity(dentry);
+	if (evm_status == INTEGRITY_NOXATTRS) {
+		struct integrity_iint_cache *iint;
+
+		iint = integrity_iint_find(dentry->d_inode);
+		if (iint && (iint->flags & IMA_NEW_FILE))
+			return 0;
+	}
+out:
+	if (evm_status != INTEGRITY_PASS)
+		integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode,
+				    dentry->d_name.name, "appraise_metadata",
+				    integrity_status_msg[evm_status],
+				    -EPERM, 0);
+	return evm_status == INTEGRITY_PASS ? 0 : -EPERM;
+}
+
+/**
+ * evm_inode_setxattr - protect the EVM extended attribute
+ * @dentry: pointer to the affected dentry
+ * @xattr_name: pointer to the affected extended attribute name
+ * @xattr_value: pointer to the new extended attribute value
+ * @xattr_value_len: pointer to the new extended attribute value length
+ *
+ * Before allowing the 'security.evm' protected xattr to be updated,
+ * verify the existing value is valid.  As only the kernel should have
+ * access to the EVM encrypted key needed to calculate the HMAC, prevent
+ * userspace from writing HMAC value.  Writing 'security.evm' requires
+ * requires CAP_SYS_ADMIN privileges.
+ */
+int evm_inode_setxattr(struct dentry *dentry, const char *xattr_name,
+		       const void *xattr_value, size_t xattr_value_len)
+{
+	const struct evm_ima_xattr_data *xattr_data = xattr_value;
+
+	if (strcmp(xattr_name, XATTR_NAME_EVM) == 0) {
+		if (!xattr_value_len)
+			return -EINVAL;
+		if (xattr_data->type != EVM_IMA_XATTR_DIGSIG)
+			return -EPERM;
+	}
+	return evm_protect_xattr(dentry, xattr_name, xattr_value,
+				 xattr_value_len);
+}
+
+/**
+ * evm_inode_removexattr - protect the EVM extended attribute
+ * @dentry: pointer to the affected dentry
+ * @xattr_name: pointer to the affected extended attribute name
+ *
+ * Removing 'security.evm' requires CAP_SYS_ADMIN privileges and that
+ * the current value is valid.
+ */
+int evm_inode_removexattr(struct dentry *dentry, const char *xattr_name)
+{
+	return evm_protect_xattr(dentry, xattr_name, NULL, 0);
+}
+
+/**
+ * evm_inode_post_setxattr - update 'security.evm' to reflect the changes
+ * @dentry: pointer to the affected dentry
+ * @xattr_name: pointer to the affected extended attribute name
+ * @xattr_value: pointer to the new extended attribute value
+ * @xattr_value_len: pointer to the new extended attribute value length
+ *
+ * Update the HMAC stored in 'security.evm' to reflect the change.
+ *
+ * No need to take the i_mutex lock here, as this function is called from
+ * __vfs_setxattr_noperm().  The caller of which has taken the inode's
+ * i_mutex lock.
+ */
+void evm_inode_post_setxattr(struct dentry *dentry, const char *xattr_name,
+			     const void *xattr_value, size_t xattr_value_len)
+{
+	if (!evm_initialized || (!evm_protected_xattr(xattr_name)
+				 && !posix_xattr_acl(xattr_name)))
+		return;
+
+	evm_update_evmxattr(dentry, xattr_name, xattr_value, xattr_value_len);
+}
+
+/**
+ * evm_inode_post_removexattr - update 'security.evm' after removing the xattr
+ * @dentry: pointer to the affected dentry
+ * @xattr_name: pointer to the affected extended attribute name
+ *
+ * Update the HMAC stored in 'security.evm' to reflect removal of the xattr.
+ */
+void evm_inode_post_removexattr(struct dentry *dentry, const char *xattr_name)
+{
+	struct inode *inode = dentry->d_inode;
+
+	if (!evm_initialized || !evm_protected_xattr(xattr_name))
+		return;
+
+	mutex_lock(&inode->i_mutex);
+	evm_update_evmxattr(dentry, xattr_name, NULL, 0);
+	mutex_unlock(&inode->i_mutex);
+}
+
+/**
+ * evm_inode_setattr - prevent updating an invalid EVM extended attribute
+ * @dentry: pointer to the affected dentry
+ */
+int evm_inode_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	unsigned int ia_valid = attr->ia_valid;
+	enum integrity_status evm_status;
+
+	if (!(ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)))
+		return 0;
+	evm_status = evm_verify_current_integrity(dentry);
+	if ((evm_status == INTEGRITY_PASS) ||
+	    (evm_status == INTEGRITY_NOXATTRS))
+		return 0;
+	integrity_audit_msg(AUDIT_INTEGRITY_METADATA, dentry->d_inode,
+			    dentry->d_name.name, "appraise_metadata",
+			    integrity_status_msg[evm_status], -EPERM, 0);
+	return -EPERM;
+}
+
+/**
+ * evm_inode_post_setattr - update 'security.evm' after modifying metadata
+ * @dentry: pointer to the affected dentry
+ * @ia_valid: for the UID and GID status
+ *
+ * For now, update the HMAC stored in 'security.evm' to reflect UID/GID
+ * changes.
+ *
+ * This function is called from notify_change(), which expects the caller
+ * to lock the inode's i_mutex.
+ */
+void evm_inode_post_setattr(struct dentry *dentry, int ia_valid)
+{
+	if (!evm_initialized)
+		return;
+
+	if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID))
+		evm_update_evmxattr(dentry, NULL, NULL, 0);
+}
+
+/*
+ * evm_inode_init_security - initializes security.evm
+ */
+int evm_inode_init_security(struct inode *inode,
+				 const struct xattr *lsm_xattr,
+				 struct xattr *evm_xattr)
+{
+	struct evm_ima_xattr_data *xattr_data;
+	int rc;
+
+	if (!evm_initialized || !evm_protected_xattr(lsm_xattr->name))
+		return 0;
+
+	xattr_data = kzalloc(sizeof(*xattr_data), GFP_NOFS);
+	if (!xattr_data)
+		return -ENOMEM;
+
+	xattr_data->type = EVM_XATTR_HMAC;
+	rc = evm_init_hmac(inode, lsm_xattr, xattr_data->digest);
+	if (rc < 0)
+		goto out;
+
+	evm_xattr->value = xattr_data;
+	evm_xattr->value_len = sizeof(*xattr_data);
+	evm_xattr->name = XATTR_EVM_SUFFIX;
+	return 0;
+out:
+	kfree(xattr_data);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(evm_inode_init_security);
+
+static int __init init_evm(void)
+{
+	int error;
+
+	evm_init_config();
+
+	error = evm_init_secfs();
+	if (error < 0) {
+		pr_info("Error registering secfs\n");
+		goto err;
+	}
+
+	return 0;
+err:
+	return error;
+}
+
+/*
+ * evm_display_config - list the EVM protected security extended attributes
+ */
+static int __init evm_display_config(void)
+{
+	char **xattrname;
+
+	for (xattrname = evm_config_xattrnames; *xattrname != NULL; xattrname++)
+		pr_info("%s\n", *xattrname);
+	return 0;
+}
+
+pure_initcall(evm_display_config);
+late_initcall(init_evm);
+
+MODULE_DESCRIPTION("Extended Verification Module");
+MODULE_LICENSE("GPL");

security/integrity/evm/evm_posix_acl.c

@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2011 IBM Corporation
+ *
+ * Author:
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the License.
+ */
+
+#include <linux/module.h>
+#include <linux/xattr.h>
+#include <linux/evm.h>
+
+int posix_xattr_acl(const char *xattr)
+{
+	int xattr_len = strlen(xattr);
+
+	if ((strlen(XATTR_NAME_POSIX_ACL_ACCESS) == xattr_len)
+	     && (strncmp(XATTR_NAME_POSIX_ACL_ACCESS, xattr, xattr_len) == 0))
+		return 1;
+	if ((strlen(XATTR_NAME_POSIX_ACL_DEFAULT) == xattr_len)
+	     && (strncmp(XATTR_NAME_POSIX_ACL_DEFAULT, xattr, xattr_len) == 0))
+		return 1;
+	return 0;
+}

security/integrity/evm/evm_secfs.c

@@ -0,0 +1,104 @@
+/*
+ * Copyright (C) 2010 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the License.
+ *
+ * File: evm_secfs.c
+ *	- Used to signal when key is on keyring
+ *	- Get the key and enable EVM
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include "evm.h"
+
+static struct dentry *evm_init_tpm;
+
+/**
+ * evm_read_key - read() for <securityfs>/evm
+ *
+ * @filp: file pointer, not actually used
+ * @buf: where to put the result
+ * @count: maximum to send along
+ * @ppos: where to start
+ *
+ * Returns number of bytes read or error code, as appropriate
+ */
+static ssize_t evm_read_key(struct file *filp, char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	char temp[80];
+	ssize_t rc;
+
+	if (*ppos != 0)
+		return 0;
+
+	sprintf(temp, "%d", evm_initialized);
+	rc = simple_read_from_buffer(buf, count, ppos, temp, strlen(temp));
+
+	return rc;
+}
+
+/**
+ * evm_write_key - write() for <securityfs>/evm
+ * @file: file pointer, not actually used
+ * @buf: where to get the data from
+ * @count: bytes sent
+ * @ppos: where to start
+ *
+ * Used to signal that key is on the kernel key ring.
+ * - get the integrity hmac key from the kernel key ring
+ * - create list of hmac protected extended attributes
+ * Returns number of bytes written or error code, as appropriate
+ */
+static ssize_t evm_write_key(struct file *file, const char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	char temp[80];
+	int i, error;
+
+	if (!capable(CAP_SYS_ADMIN) || evm_initialized)
+		return -EPERM;
+
+	if (count >= sizeof(temp) || count == 0)
+		return -EINVAL;
+
+	if (copy_from_user(temp, buf, count) != 0)
+		return -EFAULT;
+
+	temp[count] = '\0';
+
+	if ((sscanf(temp, "%d", &i) != 1) || (i != 1))
+		return -EINVAL;
+
+	error = evm_init_key();
+	if (!error) {
+		evm_initialized = 1;
+		pr_info("initialized\n");
+	} else
+		pr_err("initialization failed\n");
+	return count;
+}
+
+static const struct file_operations evm_key_ops = {
+	.read		= evm_read_key,
+	.write		= evm_write_key,
+};
+
+int __init evm_init_secfs(void)
+{
+	int error = 0;
+
+	evm_init_tpm = securityfs_create_file("evm", S_IRUSR | S_IRGRP,
+					      NULL, NULL, &evm_key_ops);
+	if (!evm_init_tpm || IS_ERR(evm_init_tpm))
+		error = -EFAULT;
+	return error;
+}

security/integrity/iint.c

@@ -0,0 +1,172 @@
+/*
+ * Copyright (C) 2008 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: integrity_iint.c
+ *	- implements the integrity hooks: integrity_inode_alloc,
+ *	  integrity_inode_free
+ *	- cache integrity information associated with an inode
+ *	  using a rbtree tree.
+ */
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/rbtree.h>
+#include "integrity.h"
+
+static struct rb_root integrity_iint_tree = RB_ROOT;
+static DEFINE_RWLOCK(integrity_iint_lock);
+static struct kmem_cache *iint_cache __read_mostly;
+
+int iint_initialized;
+
+/*
+ * __integrity_iint_find - return the iint associated with an inode
+ */
+static struct integrity_iint_cache *__integrity_iint_find(struct inode *inode)
+{
+	struct integrity_iint_cache *iint;
+	struct rb_node *n = integrity_iint_tree.rb_node;
+
+	while (n) {
+		iint = rb_entry(n, struct integrity_iint_cache, rb_node);
+
+		if (inode < iint->inode)
+			n = n->rb_left;
+		else if (inode > iint->inode)
+			n = n->rb_right;
+		else
+			break;
+	}
+	if (!n)
+		return NULL;
+
+	return iint;
+}
+
+/*
+ * integrity_iint_find - return the iint associated with an inode
+ */
+struct integrity_iint_cache *integrity_iint_find(struct inode *inode)
+{
+	struct integrity_iint_cache *iint;
+
+	if (!IS_IMA(inode))
+		return NULL;
+
+	read_lock(&integrity_iint_lock);
+	iint = __integrity_iint_find(inode);
+	read_unlock(&integrity_iint_lock);
+
+	return iint;
+}
+
+static void iint_free(struct integrity_iint_cache *iint)
+{
+	kfree(iint->ima_hash);
+	iint->ima_hash = NULL;
+	iint->version = 0;
+	iint->flags = 0UL;
+	iint->ima_file_status = INTEGRITY_UNKNOWN;
+	iint->ima_mmap_status = INTEGRITY_UNKNOWN;
+	iint->ima_bprm_status = INTEGRITY_UNKNOWN;
+	iint->ima_module_status = INTEGRITY_UNKNOWN;
+	iint->evm_status = INTEGRITY_UNKNOWN;
+	kmem_cache_free(iint_cache, iint);
+}
+
+/**
+ * integrity_inode_get - find or allocate an iint associated with an inode
+ * @inode: pointer to the inode
+ * @return: allocated iint
+ *
+ * Caller must lock i_mutex
+ */
+struct integrity_iint_cache *integrity_inode_get(struct inode *inode)
+{
+	struct rb_node **p;
+	struct rb_node *node, *parent = NULL;
+	struct integrity_iint_cache *iint, *test_iint;
+
+	iint = integrity_iint_find(inode);
+	if (iint)
+		return iint;
+
+	iint = kmem_cache_alloc(iint_cache, GFP_NOFS);
+	if (!iint)
+		return NULL;
+
+	write_lock(&integrity_iint_lock);
+
+	p = &integrity_iint_tree.rb_node;
+	while (*p) {
+		parent = *p;
+		test_iint = rb_entry(parent, struct integrity_iint_cache,
+				     rb_node);
+		if (inode < test_iint->inode)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	iint->inode = inode;
+	node = &iint->rb_node;
+	inode->i_flags |= S_IMA;
+	rb_link_node(node, parent, p);
+	rb_insert_color(node, &integrity_iint_tree);
+
+	write_unlock(&integrity_iint_lock);
+	return iint;
+}
+
+/**
+ * integrity_inode_free - called on security_inode_free
+ * @inode: pointer to the inode
+ *
+ * Free the integrity information(iint) associated with an inode.
+ */
+void integrity_inode_free(struct inode *inode)
+{
+	struct integrity_iint_cache *iint;
+
+	if (!IS_IMA(inode))
+		return;
+
+	write_lock(&integrity_iint_lock);
+	iint = __integrity_iint_find(inode);
+	rb_erase(&iint->rb_node, &integrity_iint_tree);
+	write_unlock(&integrity_iint_lock);
+
+	iint_free(iint);
+}
+
+static void init_once(void *foo)
+{
+	struct integrity_iint_cache *iint = foo;
+
+	memset(iint, 0, sizeof(*iint));
+	iint->version = 0;
+	iint->flags = 0UL;
+	iint->ima_file_status = INTEGRITY_UNKNOWN;
+	iint->ima_mmap_status = INTEGRITY_UNKNOWN;
+	iint->ima_bprm_status = INTEGRITY_UNKNOWN;
+	iint->ima_module_status = INTEGRITY_UNKNOWN;
+	iint->evm_status = INTEGRITY_UNKNOWN;
+}
+
+static int __init integrity_iintcache_init(void)
+{
+	iint_cache =
+	    kmem_cache_create("iint_cache", sizeof(struct integrity_iint_cache),
+			      0, SLAB_PANIC, init_once);
+	iint_initialized = 1;
+	return 0;
+}
+security_initcall(integrity_iintcache_init);

security/integrity/ima/Kconfig

@@ -0,0 +1,133 @@
+# IBM Integrity Measurement Architecture
+#
+config IMA
+	bool "Integrity Measurement Architecture(IMA)"
+	select SECURITYFS
+	select CRYPTO
+	select CRYPTO_HMAC
+	select CRYPTO_MD5
+	select CRYPTO_SHA1
+	select CRYPTO_HASH_INFO
+	select TCG_TPM if HAS_IOMEM && !UML
+	select TCG_TIS if TCG_TPM && X86
+	select TCG_IBMVTPM if TCG_TPM && PPC64
+	help
+	  The Trusted Computing Group(TCG) runtime Integrity
+	  Measurement Architecture(IMA) maintains a list of hash
+	  values of executables and other sensitive system files,
+	  as they are read or executed. If an attacker manages
+	  to change the contents of an important system file
+	  being measured, we can tell.
+
+	  If your system has a TPM chip, then IMA also maintains
+	  an aggregate integrity value over this list inside the
+	  TPM hardware, so that the TPM can prove to a third party
+	  whether or not critical system files have been modified.
+	  Read <http://www.usenix.org/events/sec04/tech/sailer.html>
+	  to learn more about IMA.
+	  If unsure, say N.
+
+config IMA_MEASURE_PCR_IDX
+	int
+	depends on IMA
+	range 8 14
+	default 10
+	help
+	  IMA_MEASURE_PCR_IDX determines the TPM PCR register index
+	  that IMA uses to maintain the integrity aggregate of the
+	  measurement list.  If unsure, use the default 10.
+
+config IMA_LSM_RULES
+	bool
+	depends on IMA && AUDIT && (SECURITY_SELINUX || SECURITY_SMACK)
+	default y
+	help
+	  Disabling this option will disregard LSM based policy rules.
+
+choice
+	prompt "Default template"
+	default IMA_NG_TEMPLATE
+	depends on IMA
+	help
+	  Select the default IMA measurement template.
+
+	  The original 'ima' measurement list template contains a
+	  hash, defined as 20 bytes, and a null terminated pathname,
+	  limited to 255 characters.  The 'ima-ng' measurement list
+	  template permits both larger hash digests and longer
+	  pathnames.
+
+	config IMA_TEMPLATE
+		bool "ima"
+	config IMA_NG_TEMPLATE
+		bool "ima-ng (default)"
+	config IMA_SIG_TEMPLATE
+		bool "ima-sig"
+endchoice
+
+config IMA_DEFAULT_TEMPLATE
+	string
+	depends on IMA
+	default "ima" if IMA_TEMPLATE
+	default "ima-ng" if IMA_NG_TEMPLATE
+	default "ima-sig" if IMA_SIG_TEMPLATE
+
+choice
+	prompt "Default integrity hash algorithm"
+	default IMA_DEFAULT_HASH_SHA1
+	depends on IMA
+	help
+	   Select the default hash algorithm used for the measurement
+	   list, integrity appraisal and audit log.  The compiled default
+	   hash algorithm can be overwritten using the kernel command
+	   line 'ima_hash=' option.
+
+	config IMA_DEFAULT_HASH_SHA1
+		bool "SHA1 (default)"
+		depends on CRYPTO_SHA1
+
+	config IMA_DEFAULT_HASH_SHA256
+		bool "SHA256"
+		depends on CRYPTO_SHA256 && !IMA_TEMPLATE
+
+	config IMA_DEFAULT_HASH_SHA512
+		bool "SHA512"
+		depends on CRYPTO_SHA512 && !IMA_TEMPLATE
+
+	config IMA_DEFAULT_HASH_WP512
+		bool "WP512"
+		depends on CRYPTO_WP512 && !IMA_TEMPLATE
+endchoice
+
+config IMA_DEFAULT_HASH
+	string
+	depends on IMA
+	default "sha1" if IMA_DEFAULT_HASH_SHA1
+	default "sha256" if IMA_DEFAULT_HASH_SHA256
+	default "sha512" if IMA_DEFAULT_HASH_SHA512
+	default "wp512" if IMA_DEFAULT_HASH_WP512
+
+config IMA_APPRAISE
+	bool "Appraise integrity measurements"
+	depends on IMA
+	default n
+	help
+	  This option enables local measurement integrity appraisal.
+	  It requires the system to be labeled with a security extended
+	  attribute containing the file hash measurement.  To protect
+	  the security extended attributes from offline attack, enable
+	  and configure EVM.
+
+	  For more information on integrity appraisal refer to:
+	  <http://linux-ima.sourceforge.net>
+	  If unsure, say N.
+
+config IMA_TRUSTED_KEYRING
+	bool "Require all keys on the .ima keyring be signed"
+	depends on IMA_APPRAISE && SYSTEM_TRUSTED_KEYRING
+	depends on INTEGRITY_ASYMMETRIC_KEYS
+	select KEYS_DEBUG_PROC_KEYS
+	default y
+	help
+	   This option requires that all keys added to the .ima
+	   keyring be signed by a key on the system trusted keyring.

security/integrity/ima/Makefile

@@ -0,0 +1,10 @@
+#
+# Makefile for building Trusted Computing Group's(TCG) runtime Integrity
+# Measurement Architecture(IMA).
+#
+
+obj-$(CONFIG_IMA) += ima.o
+
+ima-y := ima_fs.o ima_queue.o ima_init.o ima_main.o ima_crypto.o ima_api.o \
+	 ima_policy.o ima_template.o ima_template_lib.o
+ima-$(CONFIG_IMA_APPRAISE) += ima_appraise.o

security/integrity/ima/ima.h

@@ -0,0 +1,259 @@
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Reiner Sailer <sailer@watson.ibm.com>
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima.h
+ *	internal Integrity Measurement Architecture (IMA) definitions
+ */
+
+#ifndef __LINUX_IMA_H
+#define __LINUX_IMA_H
+
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/security.h>
+#include <linux/hash.h>
+#include <linux/tpm.h>
+#include <linux/audit.h>
+
+#include "../integrity.h"
+
+enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN,
+		     IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII };
+enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
+
+/* digest size for IMA, fits SHA1 or MD5 */
+#define IMA_DIGEST_SIZE		SHA1_DIGEST_SIZE
+#define IMA_EVENT_NAME_LEN_MAX	255
+
+#define IMA_HASH_BITS 9
+#define IMA_MEASURE_HTABLE_SIZE (1 << IMA_HASH_BITS)
+
+#define IMA_TEMPLATE_FIELD_ID_MAX_LEN	16
+#define IMA_TEMPLATE_NUM_FIELDS_MAX	15
+
+#define IMA_TEMPLATE_IMA_NAME "ima"
+#define IMA_TEMPLATE_IMA_FMT "d|n"
+
+/* current content of the policy */
+extern int ima_policy_flag;
+
+/* set during initialization */
+extern int ima_initialized;
+extern int ima_used_chip;
+extern int ima_hash_algo;
+extern int ima_appraise;
+
+/* IMA template field data definition */
+struct ima_field_data {
+	u8 *data;
+	u32 len;
+};
+
+/* IMA template field definition */
+struct ima_template_field {
+	const char field_id[IMA_TEMPLATE_FIELD_ID_MAX_LEN];
+	int (*field_init) (struct integrity_iint_cache *iint, struct file *file,
+			   const unsigned char *filename,
+			   struct evm_ima_xattr_data *xattr_value,
+			   int xattr_len, struct ima_field_data *field_data);
+	void (*field_show) (struct seq_file *m, enum ima_show_type show,
+			    struct ima_field_data *field_data);
+};
+
+/* IMA template descriptor definition */
+struct ima_template_desc {
+	char *name;
+	char *fmt;
+	int num_fields;
+	struct ima_template_field **fields;
+};
+
+struct ima_template_entry {
+	u8 digest[TPM_DIGEST_SIZE];	/* sha1 or md5 measurement hash */
+	struct ima_template_desc *template_desc; /* template descriptor */
+	u32 template_data_len;
+	struct ima_field_data template_data[0];	/* template related data */
+};
+
+struct ima_queue_entry {
+	struct hlist_node hnext;	/* place in hash collision list */
+	struct list_head later;		/* place in ima_measurements list */
+	struct ima_template_entry *entry;
+};
+extern struct list_head ima_measurements;	/* list of all measurements */
+
+/* Internal IMA function definitions */
+int ima_init(void);
+int ima_fs_init(void);
+int ima_add_template_entry(struct ima_template_entry *entry, int violation,
+			   const char *op, struct inode *inode,
+			   const unsigned char *filename);
+int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash);
+int ima_calc_field_array_hash(struct ima_field_data *field_data,
+			      struct ima_template_desc *desc, int num_fields,
+			      struct ima_digest_data *hash);
+int __init ima_calc_boot_aggregate(struct ima_digest_data *hash);
+void ima_add_violation(struct file *file, const unsigned char *filename,
+		       const char *op, const char *cause);
+int ima_init_crypto(void);
+void ima_putc(struct seq_file *m, void *data, int datalen);
+void ima_print_digest(struct seq_file *m, u8 *digest, int size);
+struct ima_template_desc *ima_template_desc_current(void);
+int ima_init_template(void);
+
+/*
+ * used to protect h_table and sha_table
+ */
+extern spinlock_t ima_queue_lock;
+
+struct ima_h_table {
+	atomic_long_t len;	/* number of stored measurements in the list */
+	atomic_long_t violations;
+	struct hlist_head queue[IMA_MEASURE_HTABLE_SIZE];
+};
+extern struct ima_h_table ima_htable;
+
+static inline unsigned long ima_hash_key(u8 *digest)
+{
+	return hash_long(*digest, IMA_HASH_BITS);
+}
+
+/* LIM API function definitions */
+int ima_get_action(struct inode *inode, int mask, int function);
+int ima_must_measure(struct inode *inode, int mask, int function);
+int ima_collect_measurement(struct integrity_iint_cache *iint,
+			    struct file *file,
+			    struct evm_ima_xattr_data **xattr_value,
+			    int *xattr_len);
+void ima_store_measurement(struct integrity_iint_cache *iint, struct file *file,
+			   const unsigned char *filename,
+			   struct evm_ima_xattr_data *xattr_value,
+			   int xattr_len);
+void ima_audit_measurement(struct integrity_iint_cache *iint,
+			   const unsigned char *filename);
+int ima_alloc_init_template(struct integrity_iint_cache *iint,
+			    struct file *file, const unsigned char *filename,
+			    struct evm_ima_xattr_data *xattr_value,
+			    int xattr_len, struct ima_template_entry **entry);
+int ima_store_template(struct ima_template_entry *entry, int violation,
+		       struct inode *inode, const unsigned char *filename);
+void ima_free_template_entry(struct ima_template_entry *entry);
+const char *ima_d_path(struct path *path, char **pathbuf);
+
+/* IMA policy related functions */
+enum ima_hooks { FILE_CHECK = 1, MMAP_CHECK, BPRM_CHECK, MODULE_CHECK, FIRMWARE_CHECK, POST_SETATTR };
+
+int ima_match_policy(struct inode *inode, enum ima_hooks func, int mask,
+		     int flags);
+void ima_init_policy(void);
+void ima_update_policy(void);
+void ima_update_policy_flag(void);
+ssize_t ima_parse_add_rule(char *);
+void ima_delete_rules(void);
+
+/* Appraise integrity measurements */
+#define IMA_APPRAISE_ENFORCE	0x01
+#define IMA_APPRAISE_FIX	0x02
+#define IMA_APPRAISE_LOG	0x04
+#define IMA_APPRAISE_MODULES	0x08
+#define IMA_APPRAISE_FIRMWARE	0x10
+
+#ifdef CONFIG_IMA_APPRAISE
+int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
+			     struct file *file, const unsigned char *filename,
+			     struct evm_ima_xattr_data *xattr_value,
+			     int xattr_len, int opened);
+int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
+void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
+enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
+					   int func);
+void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		       struct ima_digest_data *hash);
+int ima_read_xattr(struct dentry *dentry,
+		   struct evm_ima_xattr_data **xattr_value);
+
+#else
+static inline int ima_appraise_measurement(int func,
+					   struct integrity_iint_cache *iint,
+					   struct file *file,
+					   const unsigned char *filename,
+					   struct evm_ima_xattr_data *xattr_value,
+					   int xattr_len, int opened)
+{
+	return INTEGRITY_UNKNOWN;
+}
+
+static inline int ima_must_appraise(struct inode *inode, int mask,
+				    enum ima_hooks func)
+{
+	return 0;
+}
+
+static inline void ima_update_xattr(struct integrity_iint_cache *iint,
+				    struct file *file)
+{
+}
+
+static inline enum integrity_status ima_get_cache_status(struct integrity_iint_cache
+							 *iint, int func)
+{
+	return INTEGRITY_UNKNOWN;
+}
+
+static inline void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value,
+				     int xattr_len,
+				     struct ima_digest_data *hash)
+{
+}
+
+static inline int ima_read_xattr(struct dentry *dentry,
+				 struct evm_ima_xattr_data **xattr_value)
+{
+	return 0;
+}
+
+#endif
+
+/* LSM based policy rules require audit */
+#ifdef CONFIG_IMA_LSM_RULES
+
+#define security_filter_rule_init security_audit_rule_init
+#define security_filter_rule_match security_audit_rule_match
+
+#else
+
+static inline int security_filter_rule_init(u32 field, u32 op, char *rulestr,
+					    void **lsmrule)
+{
+	return -EINVAL;
+}
+
+static inline int security_filter_rule_match(u32 secid, u32 field, u32 op,
+					     void *lsmrule,
+					     struct audit_context *actx)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_IMA_LSM_RULES */
+
+#ifdef CONFIG_IMA_TRUSTED_KEYRING
+static inline int ima_init_keyring(const unsigned int id)
+{
+	return integrity_init_keyring(id);
+}
+#else
+static inline int ima_init_keyring(const unsigned int id)
+{
+	return 0;
+}
+#endif /* CONFIG_IMA_TRUSTED_KEYRING */
+#endif

security/integrity/ima/ima_api.c

@@ -0,0 +1,338 @@
+/*
+ * Copyright (C) 2008 IBM Corporation
+ *
+ * Author: Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_api.c
+ *	Implements must_appraise_or_measure, collect_measurement,
+ *	appraise_measurement, store_measurement and store_template.
+ */
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/xattr.h>
+#include <linux/evm.h>
+#include <crypto/hash_info.h>
+#include "ima.h"
+
+/*
+ * ima_free_template_entry - free an existing template entry
+ */
+void ima_free_template_entry(struct ima_template_entry *entry)
+{
+	int i;
+
+	for (i = 0; i < entry->template_desc->num_fields; i++)
+		kfree(entry->template_data[i].data);
+
+	kfree(entry);
+}
+
+/*
+ * ima_alloc_init_template - create and initialize a new template entry
+ */
+int ima_alloc_init_template(struct integrity_iint_cache *iint,
+			    struct file *file, const unsigned char *filename,
+			    struct evm_ima_xattr_data *xattr_value,
+			    int xattr_len, struct ima_template_entry **entry)
+{
+	struct ima_template_desc *template_desc = ima_template_desc_current();
+	int i, result = 0;
+
+	*entry = kzalloc(sizeof(**entry) + template_desc->num_fields *
+			 sizeof(struct ima_field_data), GFP_NOFS);
+	if (!*entry)
+		return -ENOMEM;
+
+	(*entry)->template_desc = template_desc;
+	for (i = 0; i < template_desc->num_fields; i++) {
+		struct ima_template_field *field = template_desc->fields[i];
+		u32 len;
+
+		result = field->field_init(iint, file, filename,
+					   xattr_value, xattr_len,
+					   &((*entry)->template_data[i]));
+		if (result != 0)
+			goto out;
+
+		len = (*entry)->template_data[i].len;
+		(*entry)->template_data_len += sizeof(len);
+		(*entry)->template_data_len += len;
+	}
+	return 0;
+out:
+	ima_free_template_entry(*entry);
+	*entry = NULL;
+	return result;
+}
+
+/*
+ * ima_store_template - store ima template measurements
+ *
+ * Calculate the hash of a template entry, add the template entry
+ * to an ordered list of measurement entries maintained inside the kernel,
+ * and also update the aggregate integrity value (maintained inside the
+ * configured TPM PCR) over the hashes of the current list of measurement
+ * entries.
+ *
+ * Applications retrieve the current kernel-held measurement list through
+ * the securityfs entries in /sys/kernel/security/ima. The signed aggregate
+ * TPM PCR (called quote) can be retrieved using a TPM user space library
+ * and is used to validate the measurement list.
+ *
+ * Returns 0 on success, error code otherwise
+ */
+int ima_store_template(struct ima_template_entry *entry,
+		       int violation, struct inode *inode,
+		       const unsigned char *filename)
+{
+	static const char op[] = "add_template_measure";
+	static const char audit_cause[] = "hashing_error";
+	char *template_name = entry->template_desc->name;
+	int result;
+	struct {
+		struct ima_digest_data hdr;
+		char digest[TPM_DIGEST_SIZE];
+	} hash;
+
+	if (!violation) {
+		int num_fields = entry->template_desc->num_fields;
+
+		/* this function uses default algo */
+		hash.hdr.algo = HASH_ALGO_SHA1;
+		result = ima_calc_field_array_hash(&entry->template_data[0],
+						   entry->template_desc,
+						   num_fields, &hash.hdr);
+		if (result < 0) {
+			integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode,
+					    template_name, op,
+					    audit_cause, result, 0);
+			return result;
+		}
+		memcpy(entry->digest, hash.hdr.digest, hash.hdr.length);
+	}
+	result = ima_add_template_entry(entry, violation, op, inode, filename);
+	return result;
+}
+
+/*
+ * ima_add_violation - add violation to measurement list.
+ *
+ * Violations are flagged in the measurement list with zero hash values.
+ * By extending the PCR with 0xFF's instead of with zeroes, the PCR
+ * value is invalidated.
+ */
+void ima_add_violation(struct file *file, const unsigned char *filename,
+		       const char *op, const char *cause)
+{
+	struct ima_template_entry *entry;
+	struct inode *inode = file_inode(file);
+	int violation = 1;
+	int result;
+
+	/* can overflow, only indicator */
+	atomic_long_inc(&ima_htable.violations);
+
+	result = ima_alloc_init_template(NULL, file, filename,
+					 NULL, 0, &entry);
+	if (result < 0) {
+		result = -ENOMEM;
+		goto err_out;
+	}
+	result = ima_store_template(entry, violation, inode, filename);
+	if (result < 0)
+		ima_free_template_entry(entry);
+err_out:
+	integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
+			    op, cause, result, 0);
+}
+
+/**
+ * ima_get_action - appraise & measure decision based on policy.
+ * @inode: pointer to inode to measure
+ * @mask: contains the permission mask (MAY_READ, MAY_WRITE, MAY_EXECUTE)
+ * @function: calling function (FILE_CHECK, BPRM_CHECK, MMAP_CHECK, MODULE_CHECK)
+ *
+ * The policy is defined in terms of keypairs:
+ *		subj=, obj=, type=, func=, mask=, fsmagic=
+ *	subj,obj, and type: are LSM specific.
+ *	func: FILE_CHECK | BPRM_CHECK | MMAP_CHECK | MODULE_CHECK
+ *	mask: contains the permission mask
+ *	fsmagic: hex value
+ *
+ * Returns IMA_MEASURE, IMA_APPRAISE mask.
+ *
+ */
+int ima_get_action(struct inode *inode, int mask, int function)
+{
+	int flags = IMA_MEASURE | IMA_AUDIT | IMA_APPRAISE;
+
+	if (!ima_appraise)
+		flags &= ~IMA_APPRAISE;
+
+	return ima_match_policy(inode, function, mask, flags);
+}
+
+/*
+ * ima_collect_measurement - collect file measurement
+ *
+ * Calculate the file hash, if it doesn't already exist,
+ * storing the measurement and i_version in the iint.
+ *
+ * Must be called with iint->mutex held.
+ *
+ * Return 0 on success, error code otherwise
+ */
+int ima_collect_measurement(struct integrity_iint_cache *iint,
+			    struct file *file,
+			    struct evm_ima_xattr_data **xattr_value,
+			    int *xattr_len)
+{
+	const char *audit_cause = "failed";
+	struct inode *inode = file_inode(file);
+	const char *filename = file->f_dentry->d_name.name;
+	int result = 0;
+	struct {
+		struct ima_digest_data hdr;
+		char digest[IMA_MAX_DIGEST_SIZE];
+	} hash;
+
+	if (xattr_value)
+		*xattr_len = ima_read_xattr(file->f_dentry, xattr_value);
+
+	if (!(iint->flags & IMA_COLLECTED)) {
+		u64 i_version = file_inode(file)->i_version;
+
+		if (file->f_flags & O_DIRECT) {
+			audit_cause = "failed(directio)";
+			result = -EACCES;
+			goto out;
+		}
+
+		/* use default hash algorithm */
+		hash.hdr.algo = ima_hash_algo;
+
+		if (xattr_value)
+			ima_get_hash_algo(*xattr_value, *xattr_len, &hash.hdr);
+
+		result = ima_calc_file_hash(file, &hash.hdr);
+		if (!result) {
+			int length = sizeof(hash.hdr) + hash.hdr.length;
+			void *tmpbuf = krealloc(iint->ima_hash, length,
+						GFP_NOFS);
+			if (tmpbuf) {
+				iint->ima_hash = tmpbuf;
+				memcpy(iint->ima_hash, &hash, length);
+				iint->version = i_version;
+				iint->flags |= IMA_COLLECTED;
+			} else
+				result = -ENOMEM;
+		}
+	}
+out:
+	if (result)
+		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
+				    filename, "collect_data", audit_cause,
+				    result, 0);
+	return result;
+}
+
+/*
+ * ima_store_measurement - store file measurement
+ *
+ * Create an "ima" template and then store the template by calling
+ * ima_store_template.
+ *
+ * We only get here if the inode has not already been measured,
+ * but the measurement could already exist:
+ *	- multiple copies of the same file on either the same or
+ *	  different filesystems.
+ *	- the inode was previously flushed as well as the iint info,
+ *	  containing the hashing info.
+ *
+ * Must be called with iint->mutex held.
+ */
+void ima_store_measurement(struct integrity_iint_cache *iint,
+			   struct file *file, const unsigned char *filename,
+			   struct evm_ima_xattr_data *xattr_value,
+			   int xattr_len)
+{
+	static const char op[] = "add_template_measure";
+	static const char audit_cause[] = "ENOMEM";
+	int result = -ENOMEM;
+	struct inode *inode = file_inode(file);
+	struct ima_template_entry *entry;
+	int violation = 0;
+
+	if (iint->flags & IMA_MEASURED)
+		return;
+
+	result = ima_alloc_init_template(iint, file, filename,
+					 xattr_value, xattr_len, &entry);
+	if (result < 0) {
+		integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
+				    op, audit_cause, result, 0);
+		return;
+	}
+
+	result = ima_store_template(entry, violation, inode, filename);
+	if (!result || result == -EEXIST)
+		iint->flags |= IMA_MEASURED;
+	if (result < 0)
+		ima_free_template_entry(entry);
+}
+
+void ima_audit_measurement(struct integrity_iint_cache *iint,
+			   const unsigned char *filename)
+{
+	struct audit_buffer *ab;
+	char hash[(iint->ima_hash->length * 2) + 1];
+	const char *algo_name = hash_algo_name[iint->ima_hash->algo];
+	char algo_hash[sizeof(hash) + strlen(algo_name) + 2];
+	int i;
+
+	if (iint->flags & IMA_AUDITED)
+		return;
+
+	for (i = 0; i < iint->ima_hash->length; i++)
+		hex_byte_pack(hash + (i * 2), iint->ima_hash->digest[i]);
+	hash[i * 2] = '\0';
+
+	ab = audit_log_start(current->audit_context, GFP_KERNEL,
+			     AUDIT_INTEGRITY_RULE);
+	if (!ab)
+		return;
+
+	audit_log_format(ab, "file=");
+	audit_log_untrustedstring(ab, filename);
+	audit_log_format(ab, " hash=");
+	snprintf(algo_hash, sizeof(algo_hash), "%s:%s", algo_name, hash);
+	audit_log_untrustedstring(ab, algo_hash);
+
+	audit_log_task_info(ab, current);
+	audit_log_end(ab);
+
+	iint->flags |= IMA_AUDITED;
+}
+
+const char *ima_d_path(struct path *path, char **pathbuf)
+{
+	char *pathname = NULL;
+
+	*pathbuf = kmalloc(PATH_MAX, GFP_KERNEL);
+	if (*pathbuf) {
+		pathname = d_absolute_path(path, *pathbuf, PATH_MAX);
+		if (IS_ERR(pathname)) {
+			kfree(*pathbuf);
+			*pathbuf = NULL;
+			pathname = NULL;
+		}
+	}
+	return pathname ?: (const char *)path->dentry->d_name.name;
+}

security/integrity/ima/ima_appraise.c

@@ -0,0 +1,400 @@
+/*
+ * Copyright (C) 2011 IBM Corporation
+ *
+ * Author:
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the License.
+ */
+#include <linux/module.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/xattr.h>
+#include <linux/magic.h>
+#include <linux/ima.h>
+#include <linux/evm.h>
+#include <crypto/hash_info.h>
+
+#include "ima.h"
+
+static int __init default_appraise_setup(char *str)
+{
+	if (strncmp(str, "off", 3) == 0)
+		ima_appraise = 0;
+	else if (strncmp(str, "log", 3) == 0)
+		ima_appraise = IMA_APPRAISE_LOG;
+	else if (strncmp(str, "fix", 3) == 0)
+		ima_appraise = IMA_APPRAISE_FIX;
+	return 1;
+}
+
+__setup("ima_appraise=", default_appraise_setup);
+
+/*
+ * ima_must_appraise - set appraise flag
+ *
+ * Return 1 to appraise
+ */
+int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func)
+{
+	if (!ima_appraise)
+		return 0;
+
+	return ima_match_policy(inode, func, mask, IMA_APPRAISE);
+}
+
+static int ima_fix_xattr(struct dentry *dentry,
+			 struct integrity_iint_cache *iint)
+{
+	int rc, offset;
+	u8 algo = iint->ima_hash->algo;
+
+	if (algo <= HASH_ALGO_SHA1) {
+		offset = 1;
+		iint->ima_hash->xattr.sha1.type = IMA_XATTR_DIGEST;
+	} else {
+		offset = 0;
+		iint->ima_hash->xattr.ng.type = IMA_XATTR_DIGEST_NG;
+		iint->ima_hash->xattr.ng.algo = algo;
+	}
+	rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_IMA,
+				   &iint->ima_hash->xattr.data[offset],
+				   (sizeof(iint->ima_hash->xattr) - offset) +
+				   iint->ima_hash->length, 0);
+	return rc;
+}
+
+/* Return specific func appraised cached result */
+enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
+					   int func)
+{
+	switch (func) {
+	case MMAP_CHECK:
+		return iint->ima_mmap_status;
+	case BPRM_CHECK:
+		return iint->ima_bprm_status;
+	case MODULE_CHECK:
+		return iint->ima_module_status;
+	case FIRMWARE_CHECK:
+		return iint->ima_firmware_status;
+	case FILE_CHECK:
+	default:
+		return iint->ima_file_status;
+	}
+}
+
+static void ima_set_cache_status(struct integrity_iint_cache *iint,
+				 int func, enum integrity_status status)
+{
+	switch (func) {
+	case MMAP_CHECK:
+		iint->ima_mmap_status = status;
+		break;
+	case BPRM_CHECK:
+		iint->ima_bprm_status = status;
+		break;
+	case MODULE_CHECK:
+		iint->ima_module_status = status;
+		break;
+	case FIRMWARE_CHECK:
+		iint->ima_firmware_status = status;
+		break;
+	case FILE_CHECK:
+	default:
+		iint->ima_file_status = status;
+		break;
+	}
+}
+
+static void ima_cache_flags(struct integrity_iint_cache *iint, int func)
+{
+	switch (func) {
+	case MMAP_CHECK:
+		iint->flags |= (IMA_MMAP_APPRAISED | IMA_APPRAISED);
+		break;
+	case BPRM_CHECK:
+		iint->flags |= (IMA_BPRM_APPRAISED | IMA_APPRAISED);
+		break;
+	case MODULE_CHECK:
+		iint->flags |= (IMA_MODULE_APPRAISED | IMA_APPRAISED);
+		break;
+	case FIRMWARE_CHECK:
+		iint->flags |= (IMA_FIRMWARE_APPRAISED | IMA_APPRAISED);
+		break;
+	case FILE_CHECK:
+	default:
+		iint->flags |= (IMA_FILE_APPRAISED | IMA_APPRAISED);
+		break;
+	}
+}
+
+void ima_get_hash_algo(struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		       struct ima_digest_data *hash)
+{
+	struct signature_v2_hdr *sig;
+
+	if (!xattr_value || xattr_len < 2)
+		return;
+
+	switch (xattr_value->type) {
+	case EVM_IMA_XATTR_DIGSIG:
+		sig = (typeof(sig))xattr_value;
+		if (sig->version != 2 || xattr_len <= sizeof(*sig))
+			return;
+		hash->algo = sig->hash_algo;
+		break;
+	case IMA_XATTR_DIGEST_NG:
+		hash->algo = xattr_value->digest[0];
+		break;
+	case IMA_XATTR_DIGEST:
+		/* this is for backward compatibility */
+		if (xattr_len == 21) {
+			unsigned int zero = 0;
+			if (!memcmp(&xattr_value->digest[16], &zero, 4))
+				hash->algo = HASH_ALGO_MD5;
+			else
+				hash->algo = HASH_ALGO_SHA1;
+		} else if (xattr_len == 17)
+			hash->algo = HASH_ALGO_MD5;
+		break;
+	}
+}
+
+int ima_read_xattr(struct dentry *dentry,
+		   struct evm_ima_xattr_data **xattr_value)
+{
+	struct inode *inode = dentry->d_inode;
+
+	if (!inode->i_op->getxattr)
+		return 0;
+
+	return vfs_getxattr_alloc(dentry, XATTR_NAME_IMA, (char **)xattr_value,
+				  0, GFP_NOFS);
+}
+
+/*
+ * ima_appraise_measurement - appraise file measurement
+ *
+ * Call evm_verifyxattr() to verify the integrity of 'security.ima'.
+ * Assuming success, compare the xattr hash with the collected measurement.
+ *
+ * Return 0 on success, error code otherwise
+ */
+int ima_appraise_measurement(int func, struct integrity_iint_cache *iint,
+			     struct file *file, const unsigned char *filename,
+			     struct evm_ima_xattr_data *xattr_value,
+			     int xattr_len, int opened)
+{
+	static const char op[] = "appraise_data";
+	char *cause = "unknown";
+	struct dentry *dentry = file->f_dentry;
+	struct inode *inode = dentry->d_inode;
+	enum integrity_status status = INTEGRITY_UNKNOWN;
+	int rc = xattr_len, hash_start = 0;
+
+	if (!inode->i_op->getxattr)
+		return INTEGRITY_UNKNOWN;
+
+	if (rc <= 0) {
+		if (rc && rc != -ENODATA)
+			goto out;
+
+		cause = "missing-hash";
+		status = INTEGRITY_NOLABEL;
+		if (opened & FILE_CREATED) {
+			iint->flags |= IMA_NEW_FILE;
+			status = INTEGRITY_PASS;
+		}
+		goto out;
+	}
+
+	status = evm_verifyxattr(dentry, XATTR_NAME_IMA, xattr_value, rc, iint);
+	if ((status != INTEGRITY_PASS) && (status != INTEGRITY_UNKNOWN)) {
+		if ((status == INTEGRITY_NOLABEL)
+		    || (status == INTEGRITY_NOXATTRS))
+			cause = "missing-HMAC";
+		else if (status == INTEGRITY_FAIL)
+			cause = "invalid-HMAC";
+		goto out;
+	}
+	switch (xattr_value->type) {
+	case IMA_XATTR_DIGEST_NG:
+		/* first byte contains algorithm id */
+		hash_start = 1;
+	case IMA_XATTR_DIGEST:
+		if (iint->flags & IMA_DIGSIG_REQUIRED) {
+			cause = "IMA-signature-required";
+			status = INTEGRITY_FAIL;
+			break;
+		}
+		if (xattr_len - sizeof(xattr_value->type) - hash_start >=
+				iint->ima_hash->length)
+			/* xattr length may be longer. md5 hash in previous
+			   version occupied 20 bytes in xattr, instead of 16
+			 */
+			rc = memcmp(&xattr_value->digest[hash_start],
+				    iint->ima_hash->digest,
+				    iint->ima_hash->length);
+		else
+			rc = -EINVAL;
+		if (rc) {
+			cause = "invalid-hash";
+			status = INTEGRITY_FAIL;
+			break;
+		}
+		status = INTEGRITY_PASS;
+		break;
+	case EVM_IMA_XATTR_DIGSIG:
+		iint->flags |= IMA_DIGSIG;
+		rc = integrity_digsig_verify(INTEGRITY_KEYRING_IMA,
+					     (const char *)xattr_value, rc,
+					     iint->ima_hash->digest,
+					     iint->ima_hash->length);
+		if (rc == -EOPNOTSUPP) {
+			status = INTEGRITY_UNKNOWN;
+		} else if (rc) {
+			cause = "invalid-signature";
+			status = INTEGRITY_FAIL;
+		} else {
+			status = INTEGRITY_PASS;
+		}
+		break;
+	default:
+		status = INTEGRITY_UNKNOWN;
+		cause = "unknown-ima-data";
+		break;
+	}
+
+out:
+	if (status != INTEGRITY_PASS) {
+		if ((ima_appraise & IMA_APPRAISE_FIX) &&
+		    (!xattr_value ||
+		     xattr_value->type != EVM_IMA_XATTR_DIGSIG)) {
+			if (!ima_fix_xattr(dentry, iint))
+				status = INTEGRITY_PASS;
+		}
+		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, filename,
+				    op, cause, rc, 0);
+	} else {
+		ima_cache_flags(iint, func);
+	}
+	ima_set_cache_status(iint, func, status);
+	return status;
+}
+
+/*
+ * ima_update_xattr - update 'security.ima' hash value
+ */
+void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file)
+{
+	struct dentry *dentry = file->f_dentry;
+	int rc = 0;
+
+	/* do not collect and update hash for digital signatures */
+	if (iint->flags & IMA_DIGSIG)
+		return;
+
+	rc = ima_collect_measurement(iint, file, NULL, NULL);
+	if (rc < 0)
+		return;
+
+	ima_fix_xattr(dentry, iint);
+}
+
+/**
+ * ima_inode_post_setattr - reflect file metadata changes
+ * @dentry: pointer to the affected dentry
+ *
+ * Changes to a dentry's metadata might result in needing to appraise.
+ *
+ * This function is called from notify_change(), which expects the caller
+ * to lock the inode's i_mutex.
+ */
+void ima_inode_post_setattr(struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	struct integrity_iint_cache *iint;
+	int must_appraise, rc;
+
+	if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode)
+	    || !inode->i_op->removexattr)
+		return;
+
+	must_appraise = ima_must_appraise(inode, MAY_ACCESS, POST_SETATTR);
+	iint = integrity_iint_find(inode);
+	if (iint) {
+		iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED |
+				 IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK |
+				 IMA_ACTION_FLAGS);
+		if (must_appraise)
+			iint->flags |= IMA_APPRAISE;
+	}
+	if (!must_appraise)
+		rc = inode->i_op->removexattr(dentry, XATTR_NAME_IMA);
+	return;
+}
+
+/*
+ * ima_protect_xattr - protect 'security.ima'
+ *
+ * Ensure that not just anyone can modify or remove 'security.ima'.
+ */
+static int ima_protect_xattr(struct dentry *dentry, const char *xattr_name,
+			     const void *xattr_value, size_t xattr_value_len)
+{
+	if (strcmp(xattr_name, XATTR_NAME_IMA) == 0) {
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		return 1;
+	}
+	return 0;
+}
+
+static void ima_reset_appraise_flags(struct inode *inode, int digsig)
+{
+	struct integrity_iint_cache *iint;
+
+	if (!(ima_policy_flag & IMA_APPRAISE) || !S_ISREG(inode->i_mode))
+		return;
+
+	iint = integrity_iint_find(inode);
+	if (!iint)
+		return;
+
+	iint->flags &= ~IMA_DONE_MASK;
+	if (digsig)
+		iint->flags |= IMA_DIGSIG;
+	return;
+}
+
+int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name,
+		       const void *xattr_value, size_t xattr_value_len)
+{
+	const struct evm_ima_xattr_data *xvalue = xattr_value;
+	int result;
+
+	result = ima_protect_xattr(dentry, xattr_name, xattr_value,
+				   xattr_value_len);
+	if (result == 1) {
+		if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST))
+			return -EINVAL;
+		ima_reset_appraise_flags(dentry->d_inode,
+			 (xvalue->type == EVM_IMA_XATTR_DIGSIG) ? 1 : 0);
+		result = 0;
+	}
+	return result;
+}
+
+int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name)
+{
+	int result;
+
+	result = ima_protect_xattr(dentry, xattr_name, NULL, 0);
+	if (result == 1) {
+		ima_reset_appraise_flags(dentry->d_inode, 0);
+		result = 0;
+	}
+	return result;
+}

security/integrity/ima/ima_crypto.c

@@ -0,0 +1,603 @@
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Kylene Hall <kjhall@us.ibm.com>
+ *
+ * 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, version 2 of the License.
+ *
+ * File: ima_crypto.c
+ *	Calculates md5/sha1 file hash, template hash, boot-aggreate hash
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/ratelimit.h>
+#include <linux/file.h>
+#include <linux/crypto.h>
+#include <linux/scatterlist.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <crypto/hash.h>
+#include <crypto/hash_info.h>
+#include "ima.h"
+
+struct ahash_completion {
+	struct completion completion;
+	int err;
+};
+
+/* minimum file size for ahash use */
+static unsigned long ima_ahash_minsize;
+module_param_named(ahash_minsize, ima_ahash_minsize, ulong, 0644);
+MODULE_PARM_DESC(ahash_minsize, "Minimum file size for ahash use");
+
+/* default is 0 - 1 page. */
+static int ima_maxorder;
+static unsigned int ima_bufsize = PAGE_SIZE;
+
+static int param_set_bufsize(const char *val, const struct kernel_param *kp)
+{
+	unsigned long long size;
+	int order;
+
+	size = memparse(val, NULL);
+	order = get_order(size);
+	if (order >= MAX_ORDER)
+		return -EINVAL;
+	ima_maxorder = order;
+	ima_bufsize = PAGE_SIZE << order;
+	return 0;
+}
+
+static struct kernel_param_ops param_ops_bufsize = {
+	.set = param_set_bufsize,
+	.get = param_get_uint,
+};
+#define param_check_bufsize(name, p) __param_check(name, p, unsigned int)
+
+module_param_named(ahash_bufsize, ima_bufsize, bufsize, 0644);
+MODULE_PARM_DESC(ahash_bufsize, "Maximum ahash buffer size");
+
+static struct crypto_shash *ima_shash_tfm;
+static struct crypto_ahash *ima_ahash_tfm;
+
+/**
+ * ima_kernel_read - read file content
+ *
+ * This is a function for reading file content instead of kernel_read().
+ * It does not perform locking checks to ensure it cannot be blocked.
+ * It does not perform security checks because it is irrelevant for IMA.
+ *
+ */
+static int ima_kernel_read(struct file *file, loff_t offset,
+			   char *addr, unsigned long count)
+{
+	mm_segment_t old_fs;
+	char __user *buf = addr;
+	ssize_t ret = -EINVAL;
+
+	if (!(file->f_mode & FMODE_READ))
+		return -EBADF;
+
+	old_fs = get_fs();
+	set_fs(get_ds());
+	if (file->f_op->read)
+		ret = file->f_op->read(file, buf, count, &offset);
+	else if (file->f_op->aio_read)
+		ret = do_sync_read(file, buf, count, &offset);
+	else if (file->f_op->read_iter)
+		ret = new_sync_read(file, buf, count, &offset);
+	set_fs(old_fs);
+	return ret;
+}
+
+int __init ima_init_crypto(void)
+{
+	long rc;
+
+	ima_shash_tfm = crypto_alloc_shash(hash_algo_name[ima_hash_algo], 0, 0);
+	if (IS_ERR(ima_shash_tfm)) {
+		rc = PTR_ERR(ima_shash_tfm);
+		pr_err("Can not allocate %s (reason: %ld)\n",
+		       hash_algo_name[ima_hash_algo], rc);
+		return rc;
+	}
+	return 0;
+}
+
+static struct crypto_shash *ima_alloc_tfm(enum hash_algo algo)
+{
+	struct crypto_shash *tfm = ima_shash_tfm;
+	int rc;
+
+	if (algo < 0 || algo >= HASH_ALGO__LAST)
+		algo = ima_hash_algo;
+
+	if (algo != ima_hash_algo) {
+		tfm = crypto_alloc_shash(hash_algo_name[algo], 0, 0);
+		if (IS_ERR(tfm)) {
+			rc = PTR_ERR(tfm);
+			pr_err("Can not allocate %s (reason: %d)\n",
+			       hash_algo_name[algo], rc);
+		}
+	}
+	return tfm;
+}
+
+static void ima_free_tfm(struct crypto_shash *tfm)
+{
+	if (tfm != ima_shash_tfm)
+		crypto_free_shash(tfm);
+}
+
+/**
+ * ima_alloc_pages() - Allocate contiguous pages.
+ * @max_size:       Maximum amount of memory to allocate.
+ * @allocated_size: Returned size of actual allocation.
+ * @last_warn:      Should the min_size allocation warn or not.
+ *
+ * Tries to do opportunistic allocation for memory first trying to allocate
+ * max_size amount of memory and then splitting that until zero order is
+ * reached. Allocation is tried without generating allocation warnings unless
+ * last_warn is set. Last_warn set affects only last allocation of zero order.
+ *
+ * By default, ima_maxorder is 0 and it is equivalent to kmalloc(GFP_KERNEL)
+ *
+ * Return pointer to allocated memory, or NULL on failure.
+ */
+static void *ima_alloc_pages(loff_t max_size, size_t *allocated_size,
+			     int last_warn)
+{
+	void *ptr;
+	int order = ima_maxorder;
+	gfp_t gfp_mask = __GFP_WAIT | __GFP_NOWARN | __GFP_NORETRY;
+
+	if (order)
+		order = min(get_order(max_size), order);
+
+	for (; order; order--) {
+		ptr = (void *)__get_free_pages(gfp_mask, order);
+		if (ptr) {
+			*allocated_size = PAGE_SIZE << order;
+			return ptr;
+		}
+	}
+
+	/* order is zero - one page */
+
+	gfp_mask = GFP_KERNEL;
+
+	if (!last_warn)
+		gfp_mask |= __GFP_NOWARN;
+
+	ptr = (void *)__get_free_pages(gfp_mask, 0);
+	if (ptr) {
+		*allocated_size = PAGE_SIZE;
+		return ptr;
+	}
+
+	*allocated_size = 0;
+	return NULL;
+}
+
+/**
+ * ima_free_pages() - Free pages allocated by ima_alloc_pages().
+ * @ptr:  Pointer to allocated pages.
+ * @size: Size of allocated buffer.
+ */
+static void ima_free_pages(void *ptr, size_t size)
+{
+	if (!ptr)
+		return;
+	free_pages((unsigned long)ptr, get_order(size));
+}
+
+static struct crypto_ahash *ima_alloc_atfm(enum hash_algo algo)
+{
+	struct crypto_ahash *tfm = ima_ahash_tfm;
+	int rc;
+
+	if (algo < 0 || algo >= HASH_ALGO__LAST)
+		algo = ima_hash_algo;
+
+	if (algo != ima_hash_algo || !tfm) {
+		tfm = crypto_alloc_ahash(hash_algo_name[algo], 0, 0);
+		if (!IS_ERR(tfm)) {
+			if (algo == ima_hash_algo)
+				ima_ahash_tfm = tfm;
+		} else {
+			rc = PTR_ERR(tfm);
+			pr_err("Can not allocate %s (reason: %d)\n",
+			       hash_algo_name[algo], rc);
+		}
+	}
+	return tfm;
+}
+
+static void ima_free_atfm(struct crypto_ahash *tfm)
+{
+	if (tfm != ima_ahash_tfm)
+		crypto_free_ahash(tfm);
+}
+
+static void ahash_complete(struct crypto_async_request *req, int err)
+{
+	struct ahash_completion *res = req->data;
+
+	if (err == -EINPROGRESS)
+		return;
+	res->err = err;
+	complete(&res->completion);
+}
+
+static int ahash_wait(int err, struct ahash_completion *res)
+{
+	switch (err) {
+	case 0:
+		break;
+	case -EINPROGRESS:
+	case -EBUSY:
+		wait_for_completion(&res->completion);
+		reinit_completion(&res->completion);
+		err = res->err;
+		/* fall through */
+	default:
+		pr_crit_ratelimited("ahash calculation failed: err: %d\n", err);
+	}
+
+	return err;
+}
+
+static int ima_calc_file_hash_atfm(struct file *file,
+				   struct ima_digest_data *hash,
+				   struct crypto_ahash *tfm)
+{
+	loff_t i_size, offset;
+	char *rbuf[2] = { NULL, };
+	int rc, read = 0, rbuf_len, active = 0, ahash_rc = 0;
+	struct ahash_request *req;
+	struct scatterlist sg[1];
+	struct ahash_completion res;
+	size_t rbuf_size[2];
+
+	hash->length = crypto_ahash_digestsize(tfm);
+
+	req = ahash_request_alloc(tfm, GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	init_completion(&res.completion);
+	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
+				   CRYPTO_TFM_REQ_MAY_SLEEP,
+				   ahash_complete, &res);
+
+	rc = ahash_wait(crypto_ahash_init(req), &res);
+	if (rc)
+		goto out1;
+
+	i_size = i_size_read(file_inode(file));
+
+	if (i_size == 0)
+		goto out2;
+
+	/*
+	 * Try to allocate maximum size of memory.
+	 * Fail if even a single page cannot be allocated.
+	 */
+	rbuf[0] = ima_alloc_pages(i_size, &rbuf_size[0], 1);
+	if (!rbuf[0]) {
+		rc = -ENOMEM;
+		goto out1;
+	}
+
+	/* Only allocate one buffer if that is enough. */
+	if (i_size > rbuf_size[0]) {
+		/*
+		 * Try to allocate secondary buffer. If that fails fallback to
+		 * using single buffering. Use previous memory allocation size
+		 * as baseline for possible allocation size.
+		 */
+		rbuf[1] = ima_alloc_pages(i_size - rbuf_size[0],
+					  &rbuf_size[1], 0);
+	}
+
+	if (!(file->f_mode & FMODE_READ)) {
+		file->f_mode |= FMODE_READ;
+		read = 1;
+	}
+
+	for (offset = 0; offset < i_size; offset += rbuf_len) {
+		if (!rbuf[1] && offset) {
+			/* Not using two buffers, and it is not the first
+			 * read/request, wait for the completion of the
+			 * previous ahash_update() request.
+			 */
+			rc = ahash_wait(ahash_rc, &res);
+			if (rc)
+				goto out3;
+		}
+		/* read buffer */
+		rbuf_len = min_t(loff_t, i_size - offset, rbuf_size[active]);
+		rc = ima_kernel_read(file, offset, rbuf[active], rbuf_len);
+		if (rc != rbuf_len)
+			goto out3;
+
+		if (rbuf[1] && offset) {
+			/* Using two buffers, and it is not the first
+			 * read/request, wait for the completion of the
+			 * previous ahash_update() request.
+			 */
+			rc = ahash_wait(ahash_rc, &res);
+			if (rc)
+				goto out3;
+		}
+
+		sg_init_one(&sg[0], rbuf[active], rbuf_len);
+		ahash_request_set_crypt(req, sg, NULL, rbuf_len);
+
+		ahash_rc = crypto_ahash_update(req);
+
+		if (rbuf[1])
+			active = !active; /* swap buffers, if we use two */
+	}
+	/* wait for the last update request to complete */
+	rc = ahash_wait(ahash_rc, &res);
+out3:
+	if (read)
+		file->f_mode &= ~FMODE_READ;
+	ima_free_pages(rbuf[0], rbuf_size[0]);
+	ima_free_pages(rbuf[1], rbuf_size[1]);
+out2:
+	if (!rc) {
+		ahash_request_set_crypt(req, NULL, hash->digest, 0);
+		rc = ahash_wait(crypto_ahash_final(req), &res);
+	}
+out1:
+	ahash_request_free(req);
+	return rc;
+}
+
+static int ima_calc_file_ahash(struct file *file, struct ima_digest_data *hash)
+{
+	struct crypto_ahash *tfm;
+	int rc;
+
+	tfm = ima_alloc_atfm(hash->algo);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	rc = ima_calc_file_hash_atfm(file, hash, tfm);
+
+	ima_free_atfm(tfm);
+
+	return rc;
+}
+
+static int ima_calc_file_hash_tfm(struct file *file,
+				  struct ima_digest_data *hash,
+				  struct crypto_shash *tfm)
+{
+	loff_t i_size, offset = 0;
+	char *rbuf;
+	int rc, read = 0;
+	SHASH_DESC_ON_STACK(shash, tfm);
+
+	shash->tfm = tfm;
+	shash->flags = 0;
+
+	hash->length = crypto_shash_digestsize(tfm);
+
+	rc = crypto_shash_init(shash);
+	if (rc != 0)
+		return rc;
+
+	i_size = i_size_read(file_inode(file));
+
+	if (i_size == 0)
+		goto out;
+
+	rbuf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!rbuf)
+		return -ENOMEM;
+
+	if (!(file->f_mode & FMODE_READ)) {
+		file->f_mode |= FMODE_READ;
+		read = 1;
+	}
+
+	while (offset < i_size) {
+		int rbuf_len;
+
+		rbuf_len = ima_kernel_read(file, offset, rbuf, PAGE_SIZE);
+		if (rbuf_len < 0) {
+			rc = rbuf_len;
+			break;
+		}
+		if (rbuf_len == 0)
+			break;
+		offset += rbuf_len;
+
+		rc = crypto_shash_update(shash, rbuf, rbuf_len);
+		if (rc)
+			break;
+	}
+	if (read)
+		file->f_mode &= ~FMODE_READ;
+	kfree(rbuf);
+out:
+	if (!rc)
+		rc = crypto_shash_final(shash, hash->digest);
+	return rc;
+}
+
+static int ima_calc_file_shash(struct file *file, struct ima_digest_data *hash)
+{
+	struct crypto_shash *tfm;
+	int rc;
+
+	tfm = ima_alloc_tfm(hash->algo);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	rc = ima_calc_file_hash_tfm(file, hash, tfm);
+
+	ima_free_tfm(tfm);
+
+	return rc;
+}
+
+/*
+ * ima_calc_file_hash - calculate file hash
+ *
+ * Asynchronous hash (ahash) allows using HW acceleration for calculating
+ * a hash. ahash performance varies for different data sizes on different
+ * crypto accelerators. shash performance might be better for smaller files.
+ * The 'ima.ahash_minsize' module parameter allows specifying the best
+ * minimum file size for using ahash on the system.
+ *
+ * If the ima.ahash_minsize parameter is not specified, this function uses
+ * shash for the hash calculation.  If ahash fails, it falls back to using
+ * shash.
+ */
+int ima_calc_file_hash(struct file *file, struct ima_digest_data *hash)
+{
+	loff_t i_size;
+	int rc;
+
+	i_size = i_size_read(file_inode(file));
+
+	if (ima_ahash_minsize && i_size >= ima_ahash_minsize) {
+		rc = ima_calc_file_ahash(file, hash);
+		if (!rc)
+			return 0;
+	}
+
+	return ima_calc_file_shash(file, hash);
+}
+
+/*
+ * Calculate the hash of template data
+ */
+static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
+					 struct ima_template_desc *td,
+					 int num_fields,
+					 struct ima_digest_data *hash,
+					 struct crypto_shash *tfm)
+{
+	SHASH_DESC_ON_STACK(shash, tfm);
+	int rc, i;
+
+	shash->tfm = tfm;
+	shash->flags = 0;
+
+	hash->length = crypto_shash_digestsize(tfm);
+
+	rc = crypto_shash_init(shash);
+	if (rc != 0)
+		return rc;
+
+	for (i = 0; i < num_fields; i++) {
+		u8 buffer[IMA_EVENT_NAME_LEN_MAX + 1] = { 0 };
+		u8 *data_to_hash = field_data[i].data;
+		u32 datalen = field_data[i].len;
+
+		if (strcmp(td->name, IMA_TEMPLATE_IMA_NAME) != 0) {
+			rc = crypto_shash_update(shash,
+						(const u8 *) &field_data[i].len,
+						sizeof(field_data[i].len));
+			if (rc)
+				break;
+		} else if (strcmp(td->fields[i]->field_id, "n") == 0) {
+			memcpy(buffer, data_to_hash, datalen);
+			data_to_hash = buffer;
+			datalen = IMA_EVENT_NAME_LEN_MAX + 1;
+		}
+		rc = crypto_shash_update(shash, data_to_hash, datalen);
+		if (rc)
+			break;
+	}
+
+	if (!rc)
+		rc = crypto_shash_final(shash, hash->digest);
+
+	return rc;
+}
+
+int ima_calc_field_array_hash(struct ima_field_data *field_data,
+			      struct ima_template_desc *desc, int num_fields,
+			      struct ima_digest_data *hash)
+{
+	struct crypto_shash *tfm;
+	int rc;
+
+	tfm = ima_alloc_tfm(hash->algo);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	rc = ima_calc_field_array_hash_tfm(field_data, desc, num_fields,
+					   hash, tfm);
+
+	ima_free_tfm(tfm);
+
+	return rc;
+}
+
+static void __init ima_pcrread(int idx, u8 *pcr)
+{
+	if (!ima_used_chip)
+		return;
+
+	if (tpm_pcr_read(TPM_ANY_NUM, idx, pcr) != 0)
+		pr_err("Error Communicating to TPM chip\n");
+}
+
+/*
+ * Calculate the boot aggregate hash
+ */
+static int __init ima_calc_boot_aggregate_tfm(char *digest,
+					      struct crypto_shash *tfm)
+{
+	u8 pcr_i[TPM_DIGEST_SIZE];
+	int rc, i;
+	SHASH_DESC_ON_STACK(shash, tfm);
+
+	shash->tfm = tfm;
+	shash->flags = 0;
+
+	rc = crypto_shash_init(shash);
+	if (rc != 0)
+		return rc;
+
+	/* cumulative sha1 over tpm registers 0-7 */
+	for (i = TPM_PCR0; i < TPM_PCR8; i++) {
+		ima_pcrread(i, pcr_i);
+		/* now accumulate with current aggregate */
+		rc = crypto_shash_update(shash, pcr_i, TPM_DIGEST_SIZE);
+	}
+	if (!rc)
+		crypto_shash_final(shash, digest);
+	return rc;
+}
+
+int __init ima_calc_boot_aggregate(struct ima_digest_data *hash)
+{
+	struct crypto_shash *tfm;
+	int rc;
+
+	tfm = ima_alloc_tfm(hash->algo);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
+
+	hash->length = crypto_shash_digestsize(tfm);
+	rc = ima_calc_boot_aggregate_tfm(hash->digest, tfm);
+
+	ima_free_tfm(tfm);
+
+	return rc;
+}

security/integrity/ima/ima_fs.c

@@ -0,0 +1,382 @@
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Kylene Hall <kjhall@us.ibm.com>
+ * Reiner Sailer <sailer@us.ibm.com>
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_fs.c
+ *	implemenents security file system for reporting
+ *	current measurement list and IMA statistics
+ */
+#include <linux/fcntl.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/parser.h>
+
+#include "ima.h"
+
+static int valid_policy = 1;
+#define TMPBUFLEN 12
+static ssize_t ima_show_htable_value(char __user *buf, size_t count,
+				     loff_t *ppos, atomic_long_t *val)
+{
+	char tmpbuf[TMPBUFLEN];
+	ssize_t len;
+
+	len = scnprintf(tmpbuf, TMPBUFLEN, "%li\n", atomic_long_read(val));
+	return simple_read_from_buffer(buf, count, ppos, tmpbuf, len);
+}
+
+static ssize_t ima_show_htable_violations(struct file *filp,
+					  char __user *buf,
+					  size_t count, loff_t *ppos)
+{
+	return ima_show_htable_value(buf, count, ppos, &ima_htable.violations);
+}
+
+static const struct file_operations ima_htable_violations_ops = {
+	.read = ima_show_htable_violations,
+	.llseek = generic_file_llseek,
+};
+
+static ssize_t ima_show_measurements_count(struct file *filp,
+					   char __user *buf,
+					   size_t count, loff_t *ppos)
+{
+	return ima_show_htable_value(buf, count, ppos, &ima_htable.len);
+
+}
+
+static const struct file_operations ima_measurements_count_ops = {
+	.read = ima_show_measurements_count,
+	.llseek = generic_file_llseek,
+};
+
+/* returns pointer to hlist_node */
+static void *ima_measurements_start(struct seq_file *m, loff_t *pos)
+{
+	loff_t l = *pos;
+	struct ima_queue_entry *qe;
+
+	/* we need a lock since pos could point beyond last element */
+	rcu_read_lock();
+	list_for_each_entry_rcu(qe, &ima_measurements, later) {
+		if (!l--) {
+			rcu_read_unlock();
+			return qe;
+		}
+	}
+	rcu_read_unlock();
+	return NULL;
+}
+
+static void *ima_measurements_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct ima_queue_entry *qe = v;
+
+	/* lock protects when reading beyond last element
+	 * against concurrent list-extension
+	 */
+	rcu_read_lock();
+	qe = list_entry_rcu(qe->later.next, struct ima_queue_entry, later);
+	rcu_read_unlock();
+	(*pos)++;
+
+	return (&qe->later == &ima_measurements) ? NULL : qe;
+}
+
+static void ima_measurements_stop(struct seq_file *m, void *v)
+{
+}
+
+void ima_putc(struct seq_file *m, void *data, int datalen)
+{
+	while (datalen--)
+		seq_putc(m, *(char *)data++);
+}
+
+/* print format:
+ *       32bit-le=pcr#
+ *       char[20]=template digest
+ *       32bit-le=template name size
+ *       char[n]=template name
+ *       [eventdata length]
+ *       eventdata[n]=template specific data
+ */
+static int ima_measurements_show(struct seq_file *m, void *v)
+{
+	/* the list never shrinks, so we don't need a lock here */
+	struct ima_queue_entry *qe = v;
+	struct ima_template_entry *e;
+	int namelen;
+	u32 pcr = CONFIG_IMA_MEASURE_PCR_IDX;
+	bool is_ima_template = false;
+	int i;
+
+	/* get entry */
+	e = qe->entry;
+	if (e == NULL)
+		return -1;
+
+	/*
+	 * 1st: PCRIndex
+	 * PCR used is always the same (config option) in
+	 * little-endian format
+	 */
+	ima_putc(m, &pcr, sizeof(pcr));
+
+	/* 2nd: template digest */
+	ima_putc(m, e->digest, TPM_DIGEST_SIZE);
+
+	/* 3rd: template name size */
+	namelen = strlen(e->template_desc->name);
+	ima_putc(m, &namelen, sizeof(namelen));
+
+	/* 4th:  template name */
+	ima_putc(m, e->template_desc->name, namelen);
+
+	/* 5th:  template length (except for 'ima' template) */
+	if (strcmp(e->template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0)
+		is_ima_template = true;
+
+	if (!is_ima_template)
+		ima_putc(m, &e->template_data_len,
+			 sizeof(e->template_data_len));
+
+	/* 6th:  template specific data */
+	for (i = 0; i < e->template_desc->num_fields; i++) {
+		enum ima_show_type show = IMA_SHOW_BINARY;
+		struct ima_template_field *field = e->template_desc->fields[i];
+
+		if (is_ima_template && strcmp(field->field_id, "d") == 0)
+			show = IMA_SHOW_BINARY_NO_FIELD_LEN;
+		if (is_ima_template && strcmp(field->field_id, "n") == 0)
+			show = IMA_SHOW_BINARY_OLD_STRING_FMT;
+		field->field_show(m, show, &e->template_data[i]);
+	}
+	return 0;
+}
+
+static const struct seq_operations ima_measurments_seqops = {
+	.start = ima_measurements_start,
+	.next = ima_measurements_next,
+	.stop = ima_measurements_stop,
+	.show = ima_measurements_show
+};
+
+static int ima_measurements_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &ima_measurments_seqops);
+}
+
+static const struct file_operations ima_measurements_ops = {
+	.open = ima_measurements_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
+};
+
+void ima_print_digest(struct seq_file *m, u8 *digest, int size)
+{
+	int i;
+
+	for (i = 0; i < size; i++)
+		seq_printf(m, "%02x", *(digest + i));
+}
+
+/* print in ascii */
+static int ima_ascii_measurements_show(struct seq_file *m, void *v)
+{
+	/* the list never shrinks, so we don't need a lock here */
+	struct ima_queue_entry *qe = v;
+	struct ima_template_entry *e;
+	int i;
+
+	/* get entry */
+	e = qe->entry;
+	if (e == NULL)
+		return -1;
+
+	/* 1st: PCR used (config option) */
+	seq_printf(m, "%2d ", CONFIG_IMA_MEASURE_PCR_IDX);
+
+	/* 2nd: SHA1 template hash */
+	ima_print_digest(m, e->digest, TPM_DIGEST_SIZE);
+
+	/* 3th:  template name */
+	seq_printf(m, " %s", e->template_desc->name);
+
+	/* 4th:  template specific data */
+	for (i = 0; i < e->template_desc->num_fields; i++) {
+		seq_puts(m, " ");
+		if (e->template_data[i].len == 0)
+			continue;
+
+		e->template_desc->fields[i]->field_show(m, IMA_SHOW_ASCII,
+							&e->template_data[i]);
+	}
+	seq_puts(m, "\n");
+	return 0;
+}
+
+static const struct seq_operations ima_ascii_measurements_seqops = {
+	.start = ima_measurements_start,
+	.next = ima_measurements_next,
+	.stop = ima_measurements_stop,
+	.show = ima_ascii_measurements_show
+};
+
+static int ima_ascii_measurements_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &ima_ascii_measurements_seqops);
+}
+
+static const struct file_operations ima_ascii_measurements_ops = {
+	.open = ima_ascii_measurements_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
+};
+
+static ssize_t ima_write_policy(struct file *file, const char __user *buf,
+				size_t datalen, loff_t *ppos)
+{
+	char *data = NULL;
+	ssize_t result;
+
+	if (datalen >= PAGE_SIZE)
+		datalen = PAGE_SIZE - 1;
+
+	/* No partial writes. */
+	result = -EINVAL;
+	if (*ppos != 0)
+		goto out;
+
+	result = -ENOMEM;
+	data = kmalloc(datalen + 1, GFP_KERNEL);
+	if (!data)
+		goto out;
+
+	*(data + datalen) = '\0';
+
+	result = -EFAULT;
+	if (copy_from_user(data, buf, datalen))
+		goto out;
+
+	result = ima_parse_add_rule(data);
+out:
+	if (result < 0)
+		valid_policy = 0;
+	kfree(data);
+	return result;
+}
+
+static struct dentry *ima_dir;
+static struct dentry *binary_runtime_measurements;
+static struct dentry *ascii_runtime_measurements;
+static struct dentry *runtime_measurements_count;
+static struct dentry *violations;
+static struct dentry *ima_policy;
+
+static atomic_t policy_opencount = ATOMIC_INIT(1);
+/*
+ * ima_open_policy: sequentialize access to the policy file
+ */
+static int ima_open_policy(struct inode *inode, struct file *filp)
+{
+	/* No point in being allowed to open it if you aren't going to write */
+	if (!(filp->f_flags & O_WRONLY))
+		return -EACCES;
+	if (atomic_dec_and_test(&policy_opencount))
+		return 0;
+	return -EBUSY;
+}
+
+/*
+ * ima_release_policy - start using the new measure policy rules.
+ *
+ * Initially, ima_measure points to the default policy rules, now
+ * point to the new policy rules, and remove the securityfs policy file,
+ * assuming a valid policy.
+ */
+static int ima_release_policy(struct inode *inode, struct file *file)
+{
+	if (!valid_policy) {
+		ima_delete_rules();
+		valid_policy = 1;
+		atomic_set(&policy_opencount, 1);
+		return 0;
+	}
+	ima_update_policy();
+	securityfs_remove(ima_policy);
+	ima_policy = NULL;
+	return 0;
+}
+
+static const struct file_operations ima_measure_policy_ops = {
+	.open = ima_open_policy,
+	.write = ima_write_policy,
+	.release = ima_release_policy,
+	.llseek = generic_file_llseek,
+};
+
+int __init ima_fs_init(void)
+{
+	ima_dir = securityfs_create_dir("ima", NULL);
+	if (IS_ERR(ima_dir))
+		return -1;
+
+	binary_runtime_measurements =
+	    securityfs_create_file("binary_runtime_measurements",
+				   S_IRUSR | S_IRGRP, ima_dir, NULL,
+				   &ima_measurements_ops);
+	if (IS_ERR(binary_runtime_measurements))
+		goto out;
+
+	ascii_runtime_measurements =
+	    securityfs_create_file("ascii_runtime_measurements",
+				   S_IRUSR | S_IRGRP, ima_dir, NULL,
+				   &ima_ascii_measurements_ops);
+	if (IS_ERR(ascii_runtime_measurements))
+		goto out;
+
+	runtime_measurements_count =
+	    securityfs_create_file("runtime_measurements_count",
+				   S_IRUSR | S_IRGRP, ima_dir, NULL,
+				   &ima_measurements_count_ops);
+	if (IS_ERR(runtime_measurements_count))
+		goto out;
+
+	violations =
+	    securityfs_create_file("violations", S_IRUSR | S_IRGRP,
+				   ima_dir, NULL, &ima_htable_violations_ops);
+	if (IS_ERR(violations))
+		goto out;
+
+	ima_policy = securityfs_create_file("policy",
+					    S_IWUSR,
+					    ima_dir, NULL,
+					    &ima_measure_policy_ops);
+	if (IS_ERR(ima_policy))
+		goto out;
+
+	return 0;
+out:
+	securityfs_remove(violations);
+	securityfs_remove(runtime_measurements_count);
+	securityfs_remove(ascii_runtime_measurements);
+	securityfs_remove(binary_runtime_measurements);
+	securityfs_remove(ima_dir);
+	securityfs_remove(ima_policy);
+	return -1;
+}

security/integrity/ima/ima_init.c

@@ -0,0 +1,125 @@
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Reiner Sailer      <sailer@watson.ibm.com>
+ * Leendert van Doorn <leendert@watson.ibm.com>
+ * Mimi Zohar         <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_init.c
+ *             initialization and cleanup functions
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/scatterlist.h>
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <crypto/hash_info.h>
+#include "ima.h"
+
+/* name for boot aggregate entry */
+static const char *boot_aggregate_name = "boot_aggregate";
+int ima_used_chip;
+
+/* Add the boot aggregate to the IMA measurement list and extend
+ * the PCR register.
+ *
+ * Calculate the boot aggregate, a SHA1 over tpm registers 0-7,
+ * assuming a TPM chip exists, and zeroes if the TPM chip does not
+ * exist.  Add the boot aggregate measurement to the measurement
+ * list and extend the PCR register.
+ *
+ * If a tpm chip does not exist, indicate the core root of trust is
+ * not hardware based by invalidating the aggregate PCR value.
+ * (The aggregate PCR value is invalidated by adding one value to
+ * the measurement list and extending the aggregate PCR value with
+ * a different value.) Violations add a zero entry to the measurement
+ * list and extend the aggregate PCR value with ff...ff's.
+ */
+static int __init ima_add_boot_aggregate(void)
+{
+	static const char op[] = "add_boot_aggregate";
+	const char *audit_cause = "ENOMEM";
+	struct ima_template_entry *entry;
+	struct integrity_iint_cache tmp_iint, *iint = &tmp_iint;
+	int result = -ENOMEM;
+	int violation = 0;
+	struct {
+		struct ima_digest_data hdr;
+		char digest[TPM_DIGEST_SIZE];
+	} hash;
+
+	memset(iint, 0, sizeof(*iint));
+	memset(&hash, 0, sizeof(hash));
+	iint->ima_hash = &hash.hdr;
+	iint->ima_hash->algo = HASH_ALGO_SHA1;
+	iint->ima_hash->length = SHA1_DIGEST_SIZE;
+
+	if (ima_used_chip) {
+		result = ima_calc_boot_aggregate(&hash.hdr);
+		if (result < 0) {
+			audit_cause = "hashing_error";
+			goto err_out;
+		}
+	}
+
+	result = ima_alloc_init_template(iint, NULL, boot_aggregate_name,
+					 NULL, 0, &entry);
+	if (result < 0) {
+		audit_cause = "alloc_entry";
+		goto err_out;
+	}
+
+	result = ima_store_template(entry, violation, NULL,
+				    boot_aggregate_name);
+	if (result < 0) {
+		ima_free_template_entry(entry);
+		audit_cause = "store_entry";
+		goto err_out;
+	}
+	return 0;
+err_out:
+	integrity_audit_msg(AUDIT_INTEGRITY_PCR, NULL, boot_aggregate_name, op,
+			    audit_cause, result, 0);
+	return result;
+}
+
+int __init ima_init(void)
+{
+	u8 pcr_i[TPM_DIGEST_SIZE];
+	int rc;
+
+	ima_used_chip = 0;
+	rc = tpm_pcr_read(TPM_ANY_NUM, 0, pcr_i);
+	if (rc == 0)
+		ima_used_chip = 1;
+
+	if (!ima_used_chip)
+		pr_info("No TPM chip found, activating TPM-bypass!\n");
+
+	rc = ima_init_keyring(INTEGRITY_KEYRING_IMA);
+	if (rc)
+		return rc;
+
+	rc = ima_init_crypto();
+	if (rc)
+		return rc;
+	rc = ima_init_template();
+	if (rc != 0)
+		return rc;
+
+	rc = ima_add_boot_aggregate();	/* boot aggregate must be first entry */
+	if (rc != 0)
+		return rc;
+
+	ima_init_policy();
+
+	return ima_fs_init();
+}

security/integrity/ima/ima_main.c

@@ -0,0 +1,360 @@
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Reiner Sailer <sailer@watson.ibm.com>
+ * Serge Hallyn <serue@us.ibm.com>
+ * Kylene Hall <kylene@us.ibm.com>
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_main.c
+ *	implements the IMA hooks: ima_bprm_check, ima_file_mmap,
+ *	and ima_file_check.
+ */
+#include <linux/module.h>
+#include <linux/file.h>
+#include <linux/binfmts.h>
+#include <linux/mount.h>
+#include <linux/mman.h>
+#include <linux/slab.h>
+#include <linux/xattr.h>
+#include <linux/ima.h>
+#include <crypto/hash_info.h>
+
+#include "ima.h"
+
+int ima_initialized;
+
+#ifdef CONFIG_IMA_APPRAISE
+int ima_appraise = IMA_APPRAISE_ENFORCE;
+#else
+int ima_appraise;
+#endif
+
+int ima_hash_algo = HASH_ALGO_SHA1;
+static int hash_setup_done;
+
+static int __init hash_setup(char *str)
+{
+	struct ima_template_desc *template_desc = ima_template_desc_current();
+	int i;
+
+	if (hash_setup_done)
+		return 1;
+
+	if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) {
+		if (strncmp(str, "sha1", 4) == 0)
+			ima_hash_algo = HASH_ALGO_SHA1;
+		else if (strncmp(str, "md5", 3) == 0)
+			ima_hash_algo = HASH_ALGO_MD5;
+		goto out;
+	}
+
+	for (i = 0; i < HASH_ALGO__LAST; i++) {
+		if (strcmp(str, hash_algo_name[i]) == 0) {
+			ima_hash_algo = i;
+			break;
+		}
+	}
+out:
+	hash_setup_done = 1;
+	return 1;
+}
+__setup("ima_hash=", hash_setup);
+
+/*
+ * ima_rdwr_violation_check
+ *
+ * Only invalidate the PCR for measured files:
+ *	- Opening a file for write when already open for read,
+ *	  results in a time of measure, time of use (ToMToU) error.
+ *	- Opening a file for read when already open for write,
+ *	  could result in a file measurement error.
+ *
+ */
+static void ima_rdwr_violation_check(struct file *file,
+				     struct integrity_iint_cache *iint,
+				     int must_measure,
+				     char **pathbuf,
+				     const char **pathname)
+{
+	struct inode *inode = file_inode(file);
+	fmode_t mode = file->f_mode;
+	bool send_tomtou = false, send_writers = false;
+
+	if (mode & FMODE_WRITE) {
+		if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) {
+			if (!iint)
+				iint = integrity_iint_find(inode);
+			/* IMA_MEASURE is set from reader side */
+			if (iint && (iint->flags & IMA_MEASURE))
+				send_tomtou = true;
+		}
+	} else {
+		if ((atomic_read(&inode->i_writecount) > 0) && must_measure)
+			send_writers = true;
+	}
+
+	if (!send_tomtou && !send_writers)
+		return;
+
+	*pathname = ima_d_path(&file->f_path, pathbuf);
+
+	if (send_tomtou)
+		ima_add_violation(file, *pathname, "invalid_pcr", "ToMToU");
+	if (send_writers)
+		ima_add_violation(file, *pathname,
+				  "invalid_pcr", "open_writers");
+}
+
+static void ima_check_last_writer(struct integrity_iint_cache *iint,
+				  struct inode *inode, struct file *file)
+{
+	fmode_t mode = file->f_mode;
+
+	if (!(mode & FMODE_WRITE))
+		return;
+
+	mutex_lock(&inode->i_mutex);
+	if (atomic_read(&inode->i_writecount) == 1) {
+		if ((iint->version != inode->i_version) ||
+		    (iint->flags & IMA_NEW_FILE)) {
+			iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE);
+			if (iint->flags & IMA_APPRAISE)
+				ima_update_xattr(iint, file);
+		}
+	}
+	mutex_unlock(&inode->i_mutex);
+}
+
+/**
+ * ima_file_free - called on __fput()
+ * @file: pointer to file structure being freed
+ *
+ * Flag files that changed, based on i_version
+ */
+void ima_file_free(struct file *file)
+{
+	struct inode *inode = file_inode(file);
+	struct integrity_iint_cache *iint;
+
+	if (!iint_initialized || !S_ISREG(inode->i_mode))
+		return;
+
+	iint = integrity_iint_find(inode);
+	if (!iint)
+		return;
+
+	ima_check_last_writer(iint, inode, file);
+}
+
+static int process_measurement(struct file *file, int mask, int function,
+			       int opened)
+{
+	struct inode *inode = file_inode(file);
+	struct integrity_iint_cache *iint = NULL;
+	struct ima_template_desc *template_desc;
+	char *pathbuf = NULL;
+	const char *pathname = NULL;
+	int rc = -ENOMEM, action, must_appraise;
+	struct evm_ima_xattr_data *xattr_value = NULL, **xattr_ptr = NULL;
+	int xattr_len = 0;
+	bool violation_check;
+
+	if (!ima_policy_flag || !S_ISREG(inode->i_mode))
+		return 0;
+
+	/* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action
+	 * bitmask based on the appraise/audit/measurement policy.
+	 * Included is the appraise submask.
+	 */
+	action = ima_get_action(inode, mask, function);
+	violation_check = ((function == FILE_CHECK || function == MMAP_CHECK) &&
+			   (ima_policy_flag & IMA_MEASURE));
+	if (!action && !violation_check)
+		return 0;
+
+	must_appraise = action & IMA_APPRAISE;
+
+	/*  Is the appraise rule hook specific?  */
+	if (action & IMA_FILE_APPRAISE)
+		function = FILE_CHECK;
+
+	mutex_lock(&inode->i_mutex);
+
+	if (action) {
+		iint = integrity_inode_get(inode);
+		if (!iint)
+			goto out;
+	}
+
+	if (violation_check) {
+		ima_rdwr_violation_check(file, iint, action & IMA_MEASURE,
+					 &pathbuf, &pathname);
+		if (!action) {
+			rc = 0;
+			goto out_free;
+		}
+	}
+
+	/* Determine if already appraised/measured based on bitmask
+	 * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED,
+	 *  IMA_AUDIT, IMA_AUDITED)
+	 */
+	iint->flags |= action;
+	action &= IMA_DO_MASK;
+	action &= ~((iint->flags & IMA_DONE_MASK) >> 1);
+
+	/* Nothing to do, just return existing appraised status */
+	if (!action) {
+		if (must_appraise)
+			rc = ima_get_cache_status(iint, function);
+		goto out_digsig;
+	}
+
+	template_desc = ima_template_desc_current();
+	if ((action & IMA_APPRAISE_SUBMASK) ||
+		    strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0)
+		xattr_ptr = &xattr_value;
+
+	rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len);
+	if (rc != 0) {
+		if (file->f_flags & O_DIRECT)
+			rc = (iint->flags & IMA_PERMIT_DIRECTIO) ? 0 : -EACCES;
+		goto out_digsig;
+	}
+
+	if (!pathname)	/* ima_rdwr_violation possibly pre-fetched */
+		pathname = ima_d_path(&file->f_path, &pathbuf);
+
+	if (action & IMA_MEASURE)
+		ima_store_measurement(iint, file, pathname,
+				      xattr_value, xattr_len);
+	if (action & IMA_APPRAISE_SUBMASK)
+		rc = ima_appraise_measurement(function, iint, file, pathname,
+					      xattr_value, xattr_len, opened);
+	if (action & IMA_AUDIT)
+		ima_audit_measurement(iint, pathname);
+
+out_digsig:
+	if ((mask & MAY_WRITE) && (iint->flags & IMA_DIGSIG))
+		rc = -EACCES;
+	kfree(xattr_value);
+out_free:
+	kfree(pathbuf);
+out:
+	mutex_unlock(&inode->i_mutex);
+	if ((rc && must_appraise) && (ima_appraise & IMA_APPRAISE_ENFORCE))
+		return -EACCES;
+	return 0;
+}
+
+/**
+ * ima_file_mmap - based on policy, collect/store measurement.
+ * @file: pointer to the file to be measured (May be NULL)
+ * @prot: contains the protection that will be applied by the kernel.
+ *
+ * Measure files being mmapped executable based on the ima_must_measure()
+ * policy decision.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+int ima_file_mmap(struct file *file, unsigned long prot)
+{
+	if (file && (prot & PROT_EXEC))
+		return process_measurement(file, MAY_EXEC, MMAP_CHECK, 0);
+	return 0;
+}
+
+/**
+ * ima_bprm_check - based on policy, collect/store measurement.
+ * @bprm: contains the linux_binprm structure
+ *
+ * The OS protects against an executable file, already open for write,
+ * from being executed in deny_write_access() and an executable file,
+ * already open for execute, from being modified in get_write_access().
+ * So we can be certain that what we verify and measure here is actually
+ * what is being executed.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+int ima_bprm_check(struct linux_binprm *bprm)
+{
+	return process_measurement(bprm->file, MAY_EXEC, BPRM_CHECK, 0);
+}
+
+/**
+ * ima_path_check - based on policy, collect/store measurement.
+ * @file: pointer to the file to be measured
+ * @mask: contains MAY_READ, MAY_WRITE or MAY_EXECUTE
+ *
+ * Measure files based on the ima_must_measure() policy decision.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+int ima_file_check(struct file *file, int mask, int opened)
+{
+	return process_measurement(file,
+				   mask & (MAY_READ | MAY_WRITE | MAY_EXEC),
+				   FILE_CHECK, opened);
+}
+EXPORT_SYMBOL_GPL(ima_file_check);
+
+/**
+ * ima_module_check - based on policy, collect/store/appraise measurement.
+ * @file: pointer to the file to be measured/appraised
+ *
+ * Measure/appraise kernel modules based on policy.
+ *
+ * On success return 0.  On integrity appraisal error, assuming the file
+ * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
+ */
+int ima_module_check(struct file *file)
+{
+	if (!file) {
+#ifndef CONFIG_MODULE_SIG_FORCE
+		if ((ima_appraise & IMA_APPRAISE_MODULES) &&
+		    (ima_appraise & IMA_APPRAISE_ENFORCE))
+			return -EACCES;	/* INTEGRITY_UNKNOWN */
+#endif
+		return 0;	/* We rely on module signature checking */
+	}
+	return process_measurement(file, MAY_EXEC, MODULE_CHECK, 0);
+}
+
+int ima_fw_from_file(struct file *file, char *buf, size_t size)
+{
+	if (!file) {
+		if ((ima_appraise & IMA_APPRAISE_FIRMWARE) &&
+		    (ima_appraise & IMA_APPRAISE_ENFORCE))
+			return -EACCES;	/* INTEGRITY_UNKNOWN */
+		return 0;
+	}
+	return process_measurement(file, MAY_EXEC, FIRMWARE_CHECK, 0);
+}
+
+static int __init init_ima(void)
+{
+	int error;
+
+	hash_setup(CONFIG_IMA_DEFAULT_HASH);
+	error = ima_init();
+	if (!error) {
+		ima_initialized = 1;
+		ima_update_policy_flag();
+	}
+	return error;
+}
+
+late_initcall(init_ima);	/* Start IMA after the TPM is available */
+
+MODULE_DESCRIPTION("Integrity Measurement Architecture");
+MODULE_LICENSE("GPL");

security/integrity/ima/ima_policy.c

@@ -0,0 +1,745 @@
+/*
+ * Copyright (C) 2008 IBM Corporation
+ * Author: Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the License.
+ *
+ * ima_policy.c
+ *	- initialize default measure policy rules
+ *
+ */
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/security.h>
+#include <linux/magic.h>
+#include <linux/parser.h>
+#include <linux/slab.h>
+#include <linux/genhd.h>
+
+#include "ima.h"
+
+/* flags definitions */
+#define IMA_FUNC	0x0001
+#define IMA_MASK	0x0002
+#define IMA_FSMAGIC	0x0004
+#define IMA_UID		0x0008
+#define IMA_FOWNER	0x0010
+#define IMA_FSUUID	0x0020
+
+#define UNKNOWN		0
+#define MEASURE		0x0001	/* same as IMA_MEASURE */
+#define DONT_MEASURE	0x0002
+#define APPRAISE	0x0004	/* same as IMA_APPRAISE */
+#define DONT_APPRAISE	0x0008
+#define AUDIT		0x0040
+
+int ima_policy_flag;
+
+#define MAX_LSM_RULES 6
+enum lsm_rule_types { LSM_OBJ_USER, LSM_OBJ_ROLE, LSM_OBJ_TYPE,
+	LSM_SUBJ_USER, LSM_SUBJ_ROLE, LSM_SUBJ_TYPE
+};
+
+struct ima_rule_entry {
+	struct list_head list;
+	int action;
+	unsigned int flags;
+	enum ima_hooks func;
+	int mask;
+	unsigned long fsmagic;
+	u8 fsuuid[16];
+	kuid_t uid;
+	kuid_t fowner;
+	struct {
+		void *rule;	/* LSM file metadata specific */
+		void *args_p;	/* audit value */
+		int type;	/* audit type */
+	} lsm[MAX_LSM_RULES];
+};
+
+/*
+ * Without LSM specific knowledge, the default policy can only be
+ * written in terms of .action, .func, .mask, .fsmagic, .uid, and .fowner
+ */
+
+/*
+ * The minimum rule set to allow for full TCB coverage.  Measures all files
+ * opened or mmap for exec and everything read by root.  Dangerous because
+ * normal users can easily run the machine out of memory simply building
+ * and running executables.
+ */
+static struct ima_rule_entry default_rules[] = {
+	{.action = DONT_MEASURE, .fsmagic = PROC_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = SYSFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = DEBUGFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = TMPFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = DEVPTS_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = BINFMTFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = SECURITYFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_MEASURE, .fsmagic = SELINUX_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = MEASURE, .func = MMAP_CHECK, .mask = MAY_EXEC,
+	 .flags = IMA_FUNC | IMA_MASK},
+	{.action = MEASURE, .func = BPRM_CHECK, .mask = MAY_EXEC,
+	 .flags = IMA_FUNC | IMA_MASK},
+	{.action = MEASURE, .func = FILE_CHECK, .mask = MAY_READ, .uid = GLOBAL_ROOT_UID,
+	 .flags = IMA_FUNC | IMA_MASK | IMA_UID},
+	{.action = MEASURE, .func = MODULE_CHECK, .flags = IMA_FUNC},
+	{.action = MEASURE, .func = FIRMWARE_CHECK, .flags = IMA_FUNC},
+};
+
+static struct ima_rule_entry default_appraise_rules[] = {
+	{.action = DONT_APPRAISE, .fsmagic = PROC_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = SYSFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = DEBUGFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = TMPFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = RAMFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = DEVPTS_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = BINFMTFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = SECURITYFS_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = SELINUX_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = DONT_APPRAISE, .fsmagic = CGROUP_SUPER_MAGIC, .flags = IMA_FSMAGIC},
+	{.action = APPRAISE, .fowner = GLOBAL_ROOT_UID, .flags = IMA_FOWNER},
+};
+
+static LIST_HEAD(ima_default_rules);
+static LIST_HEAD(ima_policy_rules);
+static struct list_head *ima_rules;
+
+static DEFINE_MUTEX(ima_rules_mutex);
+
+static bool ima_use_tcb __initdata;
+static int __init default_measure_policy_setup(char *str)
+{
+	ima_use_tcb = 1;
+	return 1;
+}
+__setup("ima_tcb", default_measure_policy_setup);
+
+static bool ima_use_appraise_tcb __initdata;
+static int __init default_appraise_policy_setup(char *str)
+{
+	ima_use_appraise_tcb = 1;
+	return 1;
+}
+__setup("ima_appraise_tcb", default_appraise_policy_setup);
+
+/*
+ * Although the IMA policy does not change, the LSM policy can be
+ * reloaded, leaving the IMA LSM based rules referring to the old,
+ * stale LSM policy.
+ *
+ * Update the IMA LSM based rules to reflect the reloaded LSM policy.
+ * We assume the rules still exist; and BUG_ON() if they don't.
+ */
+static void ima_lsm_update_rules(void)
+{
+	struct ima_rule_entry *entry, *tmp;
+	int result;
+	int i;
+
+	mutex_lock(&ima_rules_mutex);
+	list_for_each_entry_safe(entry, tmp, &ima_policy_rules, list) {
+		for (i = 0; i < MAX_LSM_RULES; i++) {
+			if (!entry->lsm[i].rule)
+				continue;
+			result = security_filter_rule_init(entry->lsm[i].type,
+							   Audit_equal,
+							   entry->lsm[i].args_p,
+							   &entry->lsm[i].rule);
+			BUG_ON(!entry->lsm[i].rule);
+		}
+	}
+	mutex_unlock(&ima_rules_mutex);
+}
+
+/**
+ * ima_match_rules - determine whether an inode matches the measure rule.
+ * @rule: a pointer to a rule
+ * @inode: a pointer to an inode
+ * @func: LIM hook identifier
+ * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC)
+ *
+ * Returns true on rule match, false on failure.
+ */
+static bool ima_match_rules(struct ima_rule_entry *rule,
+			    struct inode *inode, enum ima_hooks func, int mask)
+{
+	struct task_struct *tsk = current;
+	const struct cred *cred = current_cred();
+	int i;
+
+	if ((rule->flags & IMA_FUNC) &&
+	    (rule->func != func && func != POST_SETATTR))
+		return false;
+	if ((rule->flags & IMA_MASK) &&
+	    (rule->mask != mask && func != POST_SETATTR))
+		return false;
+	if ((rule->flags & IMA_FSMAGIC)
+	    && rule->fsmagic != inode->i_sb->s_magic)
+		return false;
+	if ((rule->flags & IMA_FSUUID) &&
+	    memcmp(rule->fsuuid, inode->i_sb->s_uuid, sizeof(rule->fsuuid)))
+		return false;
+	if ((rule->flags & IMA_UID) && !uid_eq(rule->uid, cred->uid))
+		return false;
+	if ((rule->flags & IMA_FOWNER) && !uid_eq(rule->fowner, inode->i_uid))
+		return false;
+	for (i = 0; i < MAX_LSM_RULES; i++) {
+		int rc = 0;
+		u32 osid, sid;
+		int retried = 0;
+
+		if (!rule->lsm[i].rule)
+			continue;
+retry:
+		switch (i) {
+		case LSM_OBJ_USER:
+		case LSM_OBJ_ROLE:
+		case LSM_OBJ_TYPE:
+			security_inode_getsecid(inode, &osid);
+			rc = security_filter_rule_match(osid,
+							rule->lsm[i].type,
+							Audit_equal,
+							rule->lsm[i].rule,
+							NULL);
+			break;
+		case LSM_SUBJ_USER:
+		case LSM_SUBJ_ROLE:
+		case LSM_SUBJ_TYPE:
+			security_task_getsecid(tsk, &sid);
+			rc = security_filter_rule_match(sid,
+							rule->lsm[i].type,
+							Audit_equal,
+							rule->lsm[i].rule,
+							NULL);
+		default:
+			break;
+		}
+		if ((rc < 0) && (!retried)) {
+			retried = 1;
+			ima_lsm_update_rules();
+			goto retry;
+		}
+		if (!rc)
+			return false;
+	}
+	return true;
+}
+
+/*
+ * In addition to knowing that we need to appraise the file in general,
+ * we need to differentiate between calling hooks, for hook specific rules.
+ */
+static int get_subaction(struct ima_rule_entry *rule, int func)
+{
+	if (!(rule->flags & IMA_FUNC))
+		return IMA_FILE_APPRAISE;
+
+	switch (func) {
+	case MMAP_CHECK:
+		return IMA_MMAP_APPRAISE;
+	case BPRM_CHECK:
+		return IMA_BPRM_APPRAISE;
+	case MODULE_CHECK:
+		return IMA_MODULE_APPRAISE;
+	case FIRMWARE_CHECK:
+		return IMA_FIRMWARE_APPRAISE;
+	case FILE_CHECK:
+	default:
+		return IMA_FILE_APPRAISE;
+	}
+}
+
+/**
+ * ima_match_policy - decision based on LSM and other conditions
+ * @inode: pointer to an inode for which the policy decision is being made
+ * @func: IMA hook identifier
+ * @mask: requested action (MAY_READ | MAY_WRITE | MAY_APPEND | MAY_EXEC)
+ *
+ * Measure decision based on func/mask/fsmagic and LSM(subj/obj/type)
+ * conditions.
+ *
+ * (There is no need for locking when walking the policy list,
+ * as elements in the list are never deleted, nor does the list
+ * change.)
+ */
+int ima_match_policy(struct inode *inode, enum ima_hooks func, int mask,
+		     int flags)
+{
+	struct ima_rule_entry *entry;
+	int action = 0, actmask = flags | (flags << 1);
+
+	list_for_each_entry(entry, ima_rules, list) {
+
+		if (!(entry->action & actmask))
+			continue;
+
+		if (!ima_match_rules(entry, inode, func, mask))
+			continue;
+
+		action |= entry->flags & IMA_ACTION_FLAGS;
+
+		action |= entry->action & IMA_DO_MASK;
+		if (entry->action & IMA_APPRAISE)
+			action |= get_subaction(entry, func);
+
+		if (entry->action & IMA_DO_MASK)
+			actmask &= ~(entry->action | entry->action << 1);
+		else
+			actmask &= ~(entry->action | entry->action >> 1);
+
+		if (!actmask)
+			break;
+	}
+
+	return action;
+}
+
+/*
+ * Initialize the ima_policy_flag variable based on the currently
+ * loaded policy.  Based on this flag, the decision to short circuit
+ * out of a function or not call the function in the first place
+ * can be made earlier.
+ */
+void ima_update_policy_flag(void)
+{
+	struct ima_rule_entry *entry;
+
+	ima_policy_flag = 0;
+	list_for_each_entry(entry, ima_rules, list) {
+		if (entry->action & IMA_DO_MASK)
+			ima_policy_flag |= entry->action;
+	}
+
+	if (!ima_appraise)
+		ima_policy_flag &= ~IMA_APPRAISE;
+}
+
+/**
+ * ima_init_policy - initialize the default measure rules.
+ *
+ * ima_rules points to either the ima_default_rules or the
+ * the new ima_policy_rules.
+ */
+void __init ima_init_policy(void)
+{
+	int i, measure_entries, appraise_entries;
+
+	/* if !ima_use_tcb set entries = 0 so we load NO default rules */
+	measure_entries = ima_use_tcb ? ARRAY_SIZE(default_rules) : 0;
+	appraise_entries = ima_use_appraise_tcb ?
+			 ARRAY_SIZE(default_appraise_rules) : 0;
+
+	for (i = 0; i < measure_entries + appraise_entries; i++) {
+		if (i < measure_entries)
+			list_add_tail(&default_rules[i].list,
+				      &ima_default_rules);
+		else {
+			int j = i - measure_entries;
+
+			list_add_tail(&default_appraise_rules[j].list,
+				      &ima_default_rules);
+		}
+	}
+
+	ima_rules = &ima_default_rules;
+}
+
+/**
+ * ima_update_policy - update default_rules with new measure rules
+ *
+ * Called on file .release to update the default rules with a complete new
+ * policy.  Once updated, the policy is locked, no additional rules can be
+ * added to the policy.
+ */
+void ima_update_policy(void)
+{
+	static const char op[] = "policy_update";
+	const char *cause = "already-exists";
+	int result = 1;
+	int audit_info = 0;
+
+	if (ima_rules == &ima_default_rules) {
+		ima_rules = &ima_policy_rules;
+		ima_update_policy_flag();
+		cause = "complete";
+		result = 0;
+	}
+	integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL,
+			    NULL, op, cause, result, audit_info);
+}
+
+enum {
+	Opt_err = -1,
+	Opt_measure = 1, Opt_dont_measure,
+	Opt_appraise, Opt_dont_appraise,
+	Opt_audit,
+	Opt_obj_user, Opt_obj_role, Opt_obj_type,
+	Opt_subj_user, Opt_subj_role, Opt_subj_type,
+	Opt_func, Opt_mask, Opt_fsmagic, Opt_uid, Opt_fowner,
+	Opt_appraise_type, Opt_fsuuid, Opt_permit_directio
+};
+
+static match_table_t policy_tokens = {
+	{Opt_measure, "measure"},
+	{Opt_dont_measure, "dont_measure"},
+	{Opt_appraise, "appraise"},
+	{Opt_dont_appraise, "dont_appraise"},
+	{Opt_audit, "audit"},
+	{Opt_obj_user, "obj_user=%s"},
+	{Opt_obj_role, "obj_role=%s"},
+	{Opt_obj_type, "obj_type=%s"},
+	{Opt_subj_user, "subj_user=%s"},
+	{Opt_subj_role, "subj_role=%s"},
+	{Opt_subj_type, "subj_type=%s"},
+	{Opt_func, "func=%s"},
+	{Opt_mask, "mask=%s"},
+	{Opt_fsmagic, "fsmagic=%s"},
+	{Opt_fsuuid, "fsuuid=%s"},
+	{Opt_uid, "uid=%s"},
+	{Opt_fowner, "fowner=%s"},
+	{Opt_appraise_type, "appraise_type=%s"},
+	{Opt_permit_directio, "permit_directio"},
+	{Opt_err, NULL}
+};
+
+static int ima_lsm_rule_init(struct ima_rule_entry *entry,
+			     substring_t *args, int lsm_rule, int audit_type)
+{
+	int result;
+
+	if (entry->lsm[lsm_rule].rule)
+		return -EINVAL;
+
+	entry->lsm[lsm_rule].args_p = match_strdup(args);
+	if (!entry->lsm[lsm_rule].args_p)
+		return -ENOMEM;
+
+	entry->lsm[lsm_rule].type = audit_type;
+	result = security_filter_rule_init(entry->lsm[lsm_rule].type,
+					   Audit_equal,
+					   entry->lsm[lsm_rule].args_p,
+					   &entry->lsm[lsm_rule].rule);
+	if (!entry->lsm[lsm_rule].rule) {
+		kfree(entry->lsm[lsm_rule].args_p);
+		return -EINVAL;
+	}
+
+	return result;
+}
+
+static void ima_log_string(struct audit_buffer *ab, char *key, char *value)
+{
+	audit_log_format(ab, "%s=", key);
+	audit_log_untrustedstring(ab, value);
+	audit_log_format(ab, " ");
+}
+
+static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
+{
+	struct audit_buffer *ab;
+	char *p;
+	int result = 0;
+
+	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_INTEGRITY_RULE);
+
+	entry->uid = INVALID_UID;
+	entry->fowner = INVALID_UID;
+	entry->action = UNKNOWN;
+	while ((p = strsep(&rule, " \t")) != NULL) {
+		substring_t args[MAX_OPT_ARGS];
+		int token;
+		unsigned long lnum;
+
+		if (result < 0)
+			break;
+		if ((*p == '\0') || (*p == ' ') || (*p == '\t'))
+			continue;
+		token = match_token(p, policy_tokens, args);
+		switch (token) {
+		case Opt_measure:
+			ima_log_string(ab, "action", "measure");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = MEASURE;
+			break;
+		case Opt_dont_measure:
+			ima_log_string(ab, "action", "dont_measure");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = DONT_MEASURE;
+			break;
+		case Opt_appraise:
+			ima_log_string(ab, "action", "appraise");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = APPRAISE;
+			break;
+		case Opt_dont_appraise:
+			ima_log_string(ab, "action", "dont_appraise");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = DONT_APPRAISE;
+			break;
+		case Opt_audit:
+			ima_log_string(ab, "action", "audit");
+
+			if (entry->action != UNKNOWN)
+				result = -EINVAL;
+
+			entry->action = AUDIT;
+			break;
+		case Opt_func:
+			ima_log_string(ab, "func", args[0].from);
+
+			if (entry->func)
+				result = -EINVAL;
+
+			if (strcmp(args[0].from, "FILE_CHECK") == 0)
+				entry->func = FILE_CHECK;
+			/* PATH_CHECK is for backwards compat */
+			else if (strcmp(args[0].from, "PATH_CHECK") == 0)
+				entry->func = FILE_CHECK;
+			else if (strcmp(args[0].from, "MODULE_CHECK") == 0)
+				entry->func = MODULE_CHECK;
+			else if (strcmp(args[0].from, "FIRMWARE_CHECK") == 0)
+				entry->func = FIRMWARE_CHECK;
+			else if ((strcmp(args[0].from, "FILE_MMAP") == 0)
+				|| (strcmp(args[0].from, "MMAP_CHECK") == 0))
+				entry->func = MMAP_CHECK;
+			else if (strcmp(args[0].from, "BPRM_CHECK") == 0)
+				entry->func = BPRM_CHECK;
+			else
+				result = -EINVAL;
+			if (!result)
+				entry->flags |= IMA_FUNC;
+			break;
+		case Opt_mask:
+			ima_log_string(ab, "mask", args[0].from);
+
+			if (entry->mask)
+				result = -EINVAL;
+
+			if ((strcmp(args[0].from, "MAY_EXEC")) == 0)
+				entry->mask = MAY_EXEC;
+			else if (strcmp(args[0].from, "MAY_WRITE") == 0)
+				entry->mask = MAY_WRITE;
+			else if (strcmp(args[0].from, "MAY_READ") == 0)
+				entry->mask = MAY_READ;
+			else if (strcmp(args[0].from, "MAY_APPEND") == 0)
+				entry->mask = MAY_APPEND;
+			else
+				result = -EINVAL;
+			if (!result)
+				entry->flags |= IMA_MASK;
+			break;
+		case Opt_fsmagic:
+			ima_log_string(ab, "fsmagic", args[0].from);
+
+			if (entry->fsmagic) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = kstrtoul(args[0].from, 16, &entry->fsmagic);
+			if (!result)
+				entry->flags |= IMA_FSMAGIC;
+			break;
+		case Opt_fsuuid:
+			ima_log_string(ab, "fsuuid", args[0].from);
+
+			if (memchr_inv(entry->fsuuid, 0x00,
+				       sizeof(entry->fsuuid))) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = blk_part_pack_uuid(args[0].from,
+						    entry->fsuuid);
+			if (!result)
+				entry->flags |= IMA_FSUUID;
+			break;
+		case Opt_uid:
+			ima_log_string(ab, "uid", args[0].from);
+
+			if (uid_valid(entry->uid)) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = kstrtoul(args[0].from, 10, &lnum);
+			if (!result) {
+				entry->uid = make_kuid(current_user_ns(), (uid_t)lnum);
+				if (!uid_valid(entry->uid) || (((uid_t)lnum) != lnum))
+					result = -EINVAL;
+				else
+					entry->flags |= IMA_UID;
+			}
+			break;
+		case Opt_fowner:
+			ima_log_string(ab, "fowner", args[0].from);
+
+			if (uid_valid(entry->fowner)) {
+				result = -EINVAL;
+				break;
+			}
+
+			result = kstrtoul(args[0].from, 10, &lnum);
+			if (!result) {
+				entry->fowner = make_kuid(current_user_ns(), (uid_t)lnum);
+				if (!uid_valid(entry->fowner) || (((uid_t)lnum) != lnum))
+					result = -EINVAL;
+				else
+					entry->flags |= IMA_FOWNER;
+			}
+			break;
+		case Opt_obj_user:
+			ima_log_string(ab, "obj_user", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_OBJ_USER,
+						   AUDIT_OBJ_USER);
+			break;
+		case Opt_obj_role:
+			ima_log_string(ab, "obj_role", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_OBJ_ROLE,
+						   AUDIT_OBJ_ROLE);
+			break;
+		case Opt_obj_type:
+			ima_log_string(ab, "obj_type", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_OBJ_TYPE,
+						   AUDIT_OBJ_TYPE);
+			break;
+		case Opt_subj_user:
+			ima_log_string(ab, "subj_user", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_SUBJ_USER,
+						   AUDIT_SUBJ_USER);
+			break;
+		case Opt_subj_role:
+			ima_log_string(ab, "subj_role", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_SUBJ_ROLE,
+						   AUDIT_SUBJ_ROLE);
+			break;
+		case Opt_subj_type:
+			ima_log_string(ab, "subj_type", args[0].from);
+			result = ima_lsm_rule_init(entry, args,
+						   LSM_SUBJ_TYPE,
+						   AUDIT_SUBJ_TYPE);
+			break;
+		case Opt_appraise_type:
+			if (entry->action != APPRAISE) {
+				result = -EINVAL;
+				break;
+			}
+
+			ima_log_string(ab, "appraise_type", args[0].from);
+			if ((strcmp(args[0].from, "imasig")) == 0)
+				entry->flags |= IMA_DIGSIG_REQUIRED;
+			else
+				result = -EINVAL;
+			break;
+		case Opt_permit_directio:
+			entry->flags |= IMA_PERMIT_DIRECTIO;
+			break;
+		case Opt_err:
+			ima_log_string(ab, "UNKNOWN", p);
+			result = -EINVAL;
+			break;
+		}
+	}
+	if (!result && (entry->action == UNKNOWN))
+		result = -EINVAL;
+	else if (entry->func == MODULE_CHECK)
+		ima_appraise |= IMA_APPRAISE_MODULES;
+	else if (entry->func == FIRMWARE_CHECK)
+		ima_appraise |= IMA_APPRAISE_FIRMWARE;
+	audit_log_format(ab, "res=%d", !result);
+	audit_log_end(ab);
+	return result;
+}
+
+/**
+ * ima_parse_add_rule - add a rule to ima_policy_rules
+ * @rule - ima measurement policy rule
+ *
+ * Uses a mutex to protect the policy list from multiple concurrent writers.
+ * Returns the length of the rule parsed, an error code on failure
+ */
+ssize_t ima_parse_add_rule(char *rule)
+{
+	static const char op[] = "update_policy";
+	char *p;
+	struct ima_rule_entry *entry;
+	ssize_t result, len;
+	int audit_info = 0;
+
+	/* Prevent installed policy from changing */
+	if (ima_rules != &ima_default_rules) {
+		integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL,
+				    NULL, op, "already-exists",
+				    -EACCES, audit_info);
+		return -EACCES;
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry) {
+		integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL,
+				    NULL, op, "-ENOMEM", -ENOMEM, audit_info);
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&entry->list);
+
+	p = strsep(&rule, "\n");
+	len = strlen(p) + 1;
+
+	if (*p == '#') {
+		kfree(entry);
+		return len;
+	}
+
+	result = ima_parse_rule(p, entry);
+	if (result) {
+		kfree(entry);
+		integrity_audit_msg(AUDIT_INTEGRITY_STATUS, NULL,
+				    NULL, op, "invalid-policy", result,
+				    audit_info);
+		return result;
+	}
+
+	mutex_lock(&ima_rules_mutex);
+	list_add_tail(&entry->list, &ima_policy_rules);
+	mutex_unlock(&ima_rules_mutex);
+
+	return len;
+}
+
+/* ima_delete_rules called to cleanup invalid policy */
+void ima_delete_rules(void)
+{
+	struct ima_rule_entry *entry, *tmp;
+	int i;
+
+	mutex_lock(&ima_rules_mutex);
+	list_for_each_entry_safe(entry, tmp, &ima_policy_rules, list) {
+		for (i = 0; i < MAX_LSM_RULES; i++)
+			kfree(entry->lsm[i].args_p);
+
+		list_del(&entry->list);
+		kfree(entry);
+	}
+	mutex_unlock(&ima_rules_mutex);
+}

security/integrity/ima/ima_queue.c

@@ -0,0 +1,150 @@
+/*
+ * Copyright (C) 2005,2006,2007,2008 IBM Corporation
+ *
+ * Authors:
+ * Serge Hallyn <serue@us.ibm.com>
+ * Reiner Sailer <sailer@watson.ibm.com>
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_queue.c
+ *       Implements queues that store template measurements and
+ *       maintains aggregate over the stored measurements
+ *       in the pre-configured TPM PCR (if available).
+ *       The measurement list is append-only. No entry is
+ *       ever removed or changed during the boot-cycle.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/rculist.h>
+#include <linux/slab.h>
+#include "ima.h"
+
+#define AUDIT_CAUSE_LEN_MAX 32
+
+LIST_HEAD(ima_measurements);	/* list of all measurements */
+
+/* key: inode (before secure-hashing a file) */
+struct ima_h_table ima_htable = {
+	.len = ATOMIC_LONG_INIT(0),
+	.violations = ATOMIC_LONG_INIT(0),
+	.queue[0 ... IMA_MEASURE_HTABLE_SIZE - 1] = HLIST_HEAD_INIT
+};
+
+/* mutex protects atomicity of extending measurement list
+ * and extending the TPM PCR aggregate. Since tpm_extend can take
+ * long (and the tpm driver uses a mutex), we can't use the spinlock.
+ */
+static DEFINE_MUTEX(ima_extend_list_mutex);
+
+/* lookup up the digest value in the hash table, and return the entry */
+static struct ima_queue_entry *ima_lookup_digest_entry(u8 *digest_value)
+{
+	struct ima_queue_entry *qe, *ret = NULL;
+	unsigned int key;
+	int rc;
+
+	key = ima_hash_key(digest_value);
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(qe, &ima_htable.queue[key], hnext) {
+		rc = memcmp(qe->entry->digest, digest_value, TPM_DIGEST_SIZE);
+		if (rc == 0) {
+			ret = qe;
+			break;
+		}
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
+/* ima_add_template_entry helper function:
+ * - Add template entry to measurement list and hash table.
+ *
+ * (Called with ima_extend_list_mutex held.)
+ */
+static int ima_add_digest_entry(struct ima_template_entry *entry)
+{
+	struct ima_queue_entry *qe;
+	unsigned int key;
+
+	qe = kmalloc(sizeof(*qe), GFP_KERNEL);
+	if (qe == NULL) {
+		pr_err("OUT OF MEMORY ERROR creating queue entry\n");
+		return -ENOMEM;
+	}
+	qe->entry = entry;
+
+	INIT_LIST_HEAD(&qe->later);
+	list_add_tail_rcu(&qe->later, &ima_measurements);
+
+	atomic_long_inc(&ima_htable.len);
+	key = ima_hash_key(entry->digest);
+	hlist_add_head_rcu(&qe->hnext, &ima_htable.queue[key]);
+	return 0;
+}
+
+static int ima_pcr_extend(const u8 *hash)
+{
+	int result = 0;
+
+	if (!ima_used_chip)
+		return result;
+
+	result = tpm_pcr_extend(TPM_ANY_NUM, CONFIG_IMA_MEASURE_PCR_IDX, hash);
+	if (result != 0)
+		pr_err("Error Communicating to TPM chip, result: %d\n", result);
+	return result;
+}
+
+/* Add template entry to the measurement list and hash table,
+ * and extend the pcr.
+ */
+int ima_add_template_entry(struct ima_template_entry *entry, int violation,
+			   const char *op, struct inode *inode,
+			   const unsigned char *filename)
+{
+	u8 digest[TPM_DIGEST_SIZE];
+	const char *audit_cause = "hash_added";
+	char tpm_audit_cause[AUDIT_CAUSE_LEN_MAX];
+	int audit_info = 1;
+	int result = 0, tpmresult = 0;
+
+	mutex_lock(&ima_extend_list_mutex);
+	if (!violation) {
+		memcpy(digest, entry->digest, sizeof(digest));
+		if (ima_lookup_digest_entry(digest)) {
+			audit_cause = "hash_exists";
+			result = -EEXIST;
+			goto out;
+		}
+	}
+
+	result = ima_add_digest_entry(entry);
+	if (result < 0) {
+		audit_cause = "ENOMEM";
+		audit_info = 0;
+		goto out;
+	}
+
+	if (violation)		/* invalidate pcr */
+		memset(digest, 0xff, sizeof(digest));
+
+	tpmresult = ima_pcr_extend(digest);
+	if (tpmresult != 0) {
+		snprintf(tpm_audit_cause, AUDIT_CAUSE_LEN_MAX, "TPM_error(%d)",
+			 tpmresult);
+		audit_cause = tpm_audit_cause;
+		audit_info = 0;
+	}
+out:
+	mutex_unlock(&ima_extend_list_mutex);
+	integrity_audit_msg(AUDIT_INTEGRITY_PCR, inode, filename,
+			    op, audit_cause, result, audit_info);
+	return result;
+}

security/integrity/ima/ima_template.c

@@ -0,0 +1,170 @@
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ *                    TORSEC group -- http://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_template.c
+ *      Helpers to manage template descriptors.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <crypto/hash_info.h>
+
+#include "ima.h"
+#include "ima_template_lib.h"
+
+static struct ima_template_desc defined_templates[] = {
+	{.name = IMA_TEMPLATE_IMA_NAME, .fmt = IMA_TEMPLATE_IMA_FMT},
+	{.name = "ima-ng", .fmt = "d-ng|n-ng"},
+	{.name = "ima-sig", .fmt = "d-ng|n-ng|sig"},
+};
+
+static struct ima_template_field supported_fields[] = {
+	{.field_id = "d", .field_init = ima_eventdigest_init,
+	 .field_show = ima_show_template_digest},
+	{.field_id = "n", .field_init = ima_eventname_init,
+	 .field_show = ima_show_template_string},
+	{.field_id = "d-ng", .field_init = ima_eventdigest_ng_init,
+	 .field_show = ima_show_template_digest_ng},
+	{.field_id = "n-ng", .field_init = ima_eventname_ng_init,
+	 .field_show = ima_show_template_string},
+	{.field_id = "sig", .field_init = ima_eventsig_init,
+	 .field_show = ima_show_template_sig},
+};
+
+static struct ima_template_desc *ima_template;
+static struct ima_template_desc *lookup_template_desc(const char *name);
+
+static int __init ima_template_setup(char *str)
+{
+	struct ima_template_desc *template_desc;
+	int template_len = strlen(str);
+
+	/*
+	 * Verify that a template with the supplied name exists.
+	 * If not, use CONFIG_IMA_DEFAULT_TEMPLATE.
+	 */
+	template_desc = lookup_template_desc(str);
+	if (!template_desc)
+		return 1;
+
+	/*
+	 * Verify whether the current hash algorithm is supported
+	 * by the 'ima' template.
+	 */
+	if (template_len == 3 && strcmp(str, IMA_TEMPLATE_IMA_NAME) == 0 &&
+	    ima_hash_algo != HASH_ALGO_SHA1 && ima_hash_algo != HASH_ALGO_MD5) {
+		pr_err("template does not support hash alg\n");
+		return 1;
+	}
+
+	ima_template = template_desc;
+	return 1;
+}
+__setup("ima_template=", ima_template_setup);
+
+static struct ima_template_desc *lookup_template_desc(const char *name)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(defined_templates); i++) {
+		if (strcmp(defined_templates[i].name, name) == 0)
+			return defined_templates + i;
+	}
+
+	return NULL;
+}
+
+static struct ima_template_field *lookup_template_field(const char *field_id)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(supported_fields); i++)
+		if (strncmp(supported_fields[i].field_id, field_id,
+			    IMA_TEMPLATE_FIELD_ID_MAX_LEN) == 0)
+			return &supported_fields[i];
+	return NULL;
+}
+
+static int template_fmt_size(const char *template_fmt)
+{
+	char c;
+	int template_fmt_len = strlen(template_fmt);
+	int i = 0, j = 0;
+
+	while (i < template_fmt_len) {
+		c = template_fmt[i];
+		if (c == '|')
+			j++;
+		i++;
+	}
+
+	return j + 1;
+}
+
+static int template_desc_init_fields(const char *template_fmt,
+				     struct ima_template_field ***fields,
+				     int *num_fields)
+{
+	char *c, *template_fmt_copy, *template_fmt_ptr;
+	int template_num_fields = template_fmt_size(template_fmt);
+	int i, result = 0;
+
+	if (template_num_fields > IMA_TEMPLATE_NUM_FIELDS_MAX)
+		return -EINVAL;
+
+	/* copying is needed as strsep() modifies the original buffer */
+	template_fmt_copy = kstrdup(template_fmt, GFP_KERNEL);
+	if (template_fmt_copy == NULL)
+		return -ENOMEM;
+
+	*fields = kzalloc(template_num_fields * sizeof(*fields), GFP_KERNEL);
+	if (*fields == NULL) {
+		result = -ENOMEM;
+		goto out;
+	}
+
+	template_fmt_ptr = template_fmt_copy;
+	for (i = 0; (c = strsep(&template_fmt_ptr, "|")) != NULL &&
+	     i < template_num_fields; i++) {
+		struct ima_template_field *f = lookup_template_field(c);
+
+		if (!f) {
+			result = -ENOENT;
+			goto out;
+		}
+		(*fields)[i] = f;
+	}
+	*num_fields = i;
+out:
+	if (result < 0) {
+		kfree(*fields);
+		*fields = NULL;
+	}
+	kfree(template_fmt_copy);
+	return result;
+}
+
+struct ima_template_desc *ima_template_desc_current(void)
+{
+	if (!ima_template)
+		ima_template =
+		    lookup_template_desc(CONFIG_IMA_DEFAULT_TEMPLATE);
+	return ima_template;
+}
+
+int __init ima_init_template(void)
+{
+	struct ima_template_desc *template = ima_template_desc_current();
+
+	return template_desc_init_fields(template->fmt,
+					 &(template->fields),
+					 &(template->num_fields));
+}

security/integrity/ima/ima_template_lib.c

@@ -0,0 +1,342 @@
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ *                    TORSEC group -- http://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_template_lib.c
+ *      Library of supported template fields.
+ */
+#include <crypto/hash_info.h>
+
+#include "ima_template_lib.h"
+
+static bool ima_template_hash_algo_allowed(u8 algo)
+{
+	if (algo == HASH_ALGO_SHA1 || algo == HASH_ALGO_MD5)
+		return true;
+
+	return false;
+}
+
+enum data_formats {
+	DATA_FMT_DIGEST = 0,
+	DATA_FMT_DIGEST_WITH_ALGO,
+	DATA_FMT_STRING,
+	DATA_FMT_HEX
+};
+
+static int ima_write_template_field_data(const void *data, const u32 datalen,
+					 enum data_formats datafmt,
+					 struct ima_field_data *field_data)
+{
+	u8 *buf, *buf_ptr;
+	u32 buflen = datalen;
+
+	if (datafmt == DATA_FMT_STRING)
+		buflen = datalen + 1;
+
+	buf = kzalloc(buflen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, data, datalen);
+
+	/*
+	 * Replace all space characters with underscore for event names and
+	 * strings. This avoid that, during the parsing of a measurements list,
+	 * filenames with spaces or that end with the suffix ' (deleted)' are
+	 * split into multiple template fields (the space is the delimitator
+	 * character for measurements lists in ASCII format).
+	 */
+	if (datafmt == DATA_FMT_STRING) {
+		for (buf_ptr = buf; buf_ptr - buf < datalen; buf_ptr++)
+			if (*buf_ptr == ' ')
+				*buf_ptr = '_';
+	}
+
+	field_data->data = buf;
+	field_data->len = buflen;
+	return 0;
+}
+
+static void ima_show_template_data_ascii(struct seq_file *m,
+					 enum ima_show_type show,
+					 enum data_formats datafmt,
+					 struct ima_field_data *field_data)
+{
+	u8 *buf_ptr = field_data->data, buflen = field_data->len;
+
+	switch (datafmt) {
+	case DATA_FMT_DIGEST_WITH_ALGO:
+		buf_ptr = strnchr(field_data->data, buflen, ':');
+		if (buf_ptr != field_data->data)
+			seq_printf(m, "%s", field_data->data);
+
+		/* skip ':' and '\0' */
+		buf_ptr += 2;
+		buflen -= buf_ptr - field_data->data;
+	case DATA_FMT_DIGEST:
+	case DATA_FMT_HEX:
+		if (!buflen)
+			break;
+		ima_print_digest(m, buf_ptr, buflen);
+		break;
+	case DATA_FMT_STRING:
+		seq_printf(m, "%s", buf_ptr);
+		break;
+	default:
+		break;
+	}
+}
+
+static void ima_show_template_data_binary(struct seq_file *m,
+					  enum ima_show_type show,
+					  enum data_formats datafmt,
+					  struct ima_field_data *field_data)
+{
+	u32 len = (show == IMA_SHOW_BINARY_OLD_STRING_FMT) ?
+	    strlen(field_data->data) : field_data->len;
+
+	if (show != IMA_SHOW_BINARY_NO_FIELD_LEN)
+		ima_putc(m, &len, sizeof(len));
+
+	if (!len)
+		return;
+
+	ima_putc(m, field_data->data, len);
+}
+
+static void ima_show_template_field_data(struct seq_file *m,
+					 enum ima_show_type show,
+					 enum data_formats datafmt,
+					 struct ima_field_data *field_data)
+{
+	switch (show) {
+	case IMA_SHOW_ASCII:
+		ima_show_template_data_ascii(m, show, datafmt, field_data);
+		break;
+	case IMA_SHOW_BINARY:
+	case IMA_SHOW_BINARY_NO_FIELD_LEN:
+	case IMA_SHOW_BINARY_OLD_STRING_FMT:
+		ima_show_template_data_binary(m, show, datafmt, field_data);
+		break;
+	default:
+		break;
+	}
+}
+
+void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_DIGEST, field_data);
+}
+
+void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show,
+				 struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_DIGEST_WITH_ALGO,
+				     field_data);
+}
+
+void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_STRING, field_data);
+}
+
+void ima_show_template_sig(struct seq_file *m, enum ima_show_type show,
+			   struct ima_field_data *field_data)
+{
+	ima_show_template_field_data(m, show, DATA_FMT_HEX, field_data);
+}
+
+static int ima_eventdigest_init_common(u8 *digest, u32 digestsize, u8 hash_algo,
+				       struct ima_field_data *field_data)
+{
+	/*
+	 * digest formats:
+	 *  - DATA_FMT_DIGEST: digest
+	 *  - DATA_FMT_DIGEST_WITH_ALGO: [<hash algo>] + ':' + '\0' + digest,
+	 *    where <hash algo> is provided if the hash algoritm is not
+	 *    SHA1 or MD5
+	 */
+	u8 buffer[CRYPTO_MAX_ALG_NAME + 2 + IMA_MAX_DIGEST_SIZE] = { 0 };
+	enum data_formats fmt = DATA_FMT_DIGEST;
+	u32 offset = 0;
+
+	if (hash_algo < HASH_ALGO__LAST) {
+		fmt = DATA_FMT_DIGEST_WITH_ALGO;
+		offset += snprintf(buffer, CRYPTO_MAX_ALG_NAME + 1, "%s",
+				   hash_algo_name[hash_algo]);
+		buffer[offset] = ':';
+		offset += 2;
+	}
+
+	if (digest)
+		memcpy(buffer + offset, digest, digestsize);
+	else
+		/*
+		 * If digest is NULL, the event being recorded is a violation.
+		 * Make room for the digest by increasing the offset of
+		 * IMA_DIGEST_SIZE.
+		 */
+		offset += IMA_DIGEST_SIZE;
+
+	return ima_write_template_field_data(buffer, offset + digestsize,
+					     fmt, field_data);
+}
+
+/*
+ * This function writes the digest of an event (with size limit).
+ */
+int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
+			 const unsigned char *filename,
+			 struct evm_ima_xattr_data *xattr_value, int xattr_len,
+			 struct ima_field_data *field_data)
+{
+	struct {
+		struct ima_digest_data hdr;
+		char digest[IMA_MAX_DIGEST_SIZE];
+	} hash;
+	u8 *cur_digest = NULL;
+	u32 cur_digestsize = 0;
+	struct inode *inode;
+	int result;
+
+	memset(&hash, 0, sizeof(hash));
+
+	if (!iint)		/* recording a violation. */
+		goto out;
+
+	if (ima_template_hash_algo_allowed(iint->ima_hash->algo)) {
+		cur_digest = iint->ima_hash->digest;
+		cur_digestsize = iint->ima_hash->length;
+		goto out;
+	}
+
+	if (!file)		/* missing info to re-calculate the digest */
+		return -EINVAL;
+
+	inode = file_inode(file);
+	hash.hdr.algo = ima_template_hash_algo_allowed(ima_hash_algo) ?
+	    ima_hash_algo : HASH_ALGO_SHA1;
+	result = ima_calc_file_hash(file, &hash.hdr);
+	if (result) {
+		integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
+				    filename, "collect_data",
+				    "failed", result, 0);
+		return result;
+	}
+	cur_digest = hash.hdr.digest;
+	cur_digestsize = hash.hdr.length;
+out:
+	return ima_eventdigest_init_common(cur_digest, cur_digestsize,
+					   HASH_ALGO__LAST, field_data);
+}
+
+/*
+ * This function writes the digest of an event (without size limit).
+ */
+int ima_eventdigest_ng_init(struct integrity_iint_cache *iint,
+			    struct file *file, const unsigned char *filename,
+			    struct evm_ima_xattr_data *xattr_value,
+			    int xattr_len, struct ima_field_data *field_data)
+{
+	u8 *cur_digest = NULL, hash_algo = HASH_ALGO_SHA1;
+	u32 cur_digestsize = 0;
+
+	/* If iint is NULL, we are recording a violation. */
+	if (!iint)
+		goto out;
+
+	cur_digest = iint->ima_hash->digest;
+	cur_digestsize = iint->ima_hash->length;
+
+	hash_algo = iint->ima_hash->algo;
+out:
+	return ima_eventdigest_init_common(cur_digest, cur_digestsize,
+					   hash_algo, field_data);
+}
+
+static int ima_eventname_init_common(struct integrity_iint_cache *iint,
+				     struct file *file,
+				     const unsigned char *filename,
+				     struct ima_field_data *field_data,
+				     bool size_limit)
+{
+	const char *cur_filename = NULL;
+	u32 cur_filename_len = 0;
+
+	BUG_ON(filename == NULL && file == NULL);
+
+	if (filename) {
+		cur_filename = filename;
+		cur_filename_len = strlen(filename);
+
+		if (!size_limit || cur_filename_len <= IMA_EVENT_NAME_LEN_MAX)
+			goto out;
+	}
+
+	if (file) {
+		cur_filename = file->f_dentry->d_name.name;
+		cur_filename_len = strlen(cur_filename);
+	} else
+		/*
+		 * Truncate filename if the latter is too long and
+		 * the file descriptor is not available.
+		 */
+		cur_filename_len = IMA_EVENT_NAME_LEN_MAX;
+out:
+	return ima_write_template_field_data(cur_filename, cur_filename_len,
+					     DATA_FMT_STRING, field_data);
+}
+
+/*
+ * This function writes the name of an event (with size limit).
+ */
+int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
+		       const unsigned char *filename,
+		       struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		       struct ima_field_data *field_data)
+{
+	return ima_eventname_init_common(iint, file, filename,
+					 field_data, true);
+}
+
+/*
+ * This function writes the name of an event (without size limit).
+ */
+int ima_eventname_ng_init(struct integrity_iint_cache *iint, struct file *file,
+			  const unsigned char *filename,
+			  struct evm_ima_xattr_data *xattr_value, int xattr_len,
+			  struct ima_field_data *field_data)
+{
+	return ima_eventname_init_common(iint, file, filename,
+					 field_data, false);
+}
+
+/*
+ *  ima_eventsig_init - include the file signature as part of the template data
+ */
+int ima_eventsig_init(struct integrity_iint_cache *iint, struct file *file,
+		      const unsigned char *filename,
+		      struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		      struct ima_field_data *field_data)
+{
+	enum data_formats fmt = DATA_FMT_HEX;
+	int rc = 0;
+
+	if ((!xattr_value) || (xattr_value->type != EVM_IMA_XATTR_DIGSIG))
+		goto out;
+
+	rc = ima_write_template_field_data(xattr_value, xattr_len, fmt,
+					   field_data);
+out:
+	return rc;
+}

security/integrity/ima/ima_template_lib.h

@@ -0,0 +1,49 @@
+/*
+ * Copyright (C) 2013 Politecnico di Torino, Italy
+ *                    TORSEC group -- http://security.polito.it
+ *
+ * Author: Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ * File: ima_template_lib.h
+ *      Header for the library of supported template fields.
+ */
+#ifndef __LINUX_IMA_TEMPLATE_LIB_H
+#define __LINUX_IMA_TEMPLATE_LIB_H
+
+#include <linux/seq_file.h>
+#include "ima.h"
+
+void ima_show_template_digest(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data);
+void ima_show_template_digest_ng(struct seq_file *m, enum ima_show_type show,
+				 struct ima_field_data *field_data);
+void ima_show_template_string(struct seq_file *m, enum ima_show_type show,
+			      struct ima_field_data *field_data);
+void ima_show_template_sig(struct seq_file *m, enum ima_show_type show,
+			   struct ima_field_data *field_data);
+int ima_eventdigest_init(struct integrity_iint_cache *iint, struct file *file,
+			 const unsigned char *filename,
+			 struct evm_ima_xattr_data *xattr_value, int xattr_len,
+			 struct ima_field_data *field_data);
+int ima_eventname_init(struct integrity_iint_cache *iint, struct file *file,
+		       const unsigned char *filename,
+		       struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		       struct ima_field_data *field_data);
+int ima_eventdigest_ng_init(struct integrity_iint_cache *iint,
+			    struct file *file, const unsigned char *filename,
+			    struct evm_ima_xattr_data *xattr_value,
+			    int xattr_len, struct ima_field_data *field_data);
+int ima_eventname_ng_init(struct integrity_iint_cache *iint, struct file *file,
+			  const unsigned char *filename,
+			  struct evm_ima_xattr_data *xattr_value, int xattr_len,
+			  struct ima_field_data *field_data);
+int ima_eventsig_init(struct integrity_iint_cache *iint, struct file *file,
+		      const unsigned char *filename,
+		      struct evm_ima_xattr_data *xattr_value, int xattr_len,
+		      struct ima_field_data *field_data);
+#endif /* __LINUX_IMA_TEMPLATE_LIB_H */

security/integrity/integrity.h

@@ -0,0 +1,175 @@
+/*
+ * Copyright (C) 2009-2010 IBM Corporation
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the
+ * License.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/integrity.h>
+#include <crypto/sha.h>
+#include <linux/key.h>
+
+/* iint action cache flags */
+#define IMA_MEASURE		0x00000001
+#define IMA_MEASURED		0x00000002
+#define IMA_APPRAISE		0x00000004
+#define IMA_APPRAISED		0x00000008
+/*#define IMA_COLLECT		0x00000010  do not use this flag */
+#define IMA_COLLECTED		0x00000020
+#define IMA_AUDIT		0x00000040
+#define IMA_AUDITED		0x00000080
+
+/* iint cache flags */
+#define IMA_ACTION_FLAGS	0xff000000
+#define IMA_DIGSIG		0x01000000
+#define IMA_DIGSIG_REQUIRED	0x02000000
+#define IMA_PERMIT_DIRECTIO	0x04000000
+#define IMA_NEW_FILE		0x08000000
+
+#define IMA_DO_MASK		(IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \
+				 IMA_APPRAISE_SUBMASK)
+#define IMA_DONE_MASK		(IMA_MEASURED | IMA_APPRAISED | IMA_AUDITED | \
+				 IMA_COLLECTED | IMA_APPRAISED_SUBMASK)
+
+/* iint subaction appraise cache flags */
+#define IMA_FILE_APPRAISE	0x00000100
+#define IMA_FILE_APPRAISED	0x00000200
+#define IMA_MMAP_APPRAISE	0x00000400
+#define IMA_MMAP_APPRAISED	0x00000800
+#define IMA_BPRM_APPRAISE	0x00001000
+#define IMA_BPRM_APPRAISED	0x00002000
+#define IMA_MODULE_APPRAISE	0x00004000
+#define IMA_MODULE_APPRAISED	0x00008000
+#define IMA_FIRMWARE_APPRAISE	0x00010000
+#define IMA_FIRMWARE_APPRAISED	0x00020000
+#define IMA_APPRAISE_SUBMASK	(IMA_FILE_APPRAISE | IMA_MMAP_APPRAISE | \
+				 IMA_BPRM_APPRAISE | IMA_MODULE_APPRAISE | \
+				 IMA_FIRMWARE_APPRAISE)
+#define IMA_APPRAISED_SUBMASK	(IMA_FILE_APPRAISED | IMA_MMAP_APPRAISED | \
+				 IMA_BPRM_APPRAISED | IMA_MODULE_APPRAISED | \
+				 IMA_FIRMWARE_APPRAISED)
+
+enum evm_ima_xattr_type {
+	IMA_XATTR_DIGEST = 0x01,
+	EVM_XATTR_HMAC,
+	EVM_IMA_XATTR_DIGSIG,
+	IMA_XATTR_DIGEST_NG,
+	IMA_XATTR_LAST
+};
+
+struct evm_ima_xattr_data {
+	u8 type;
+	u8 digest[SHA1_DIGEST_SIZE];
+} __packed;
+
+#define IMA_MAX_DIGEST_SIZE	64
+
+struct ima_digest_data {
+	u8 algo;
+	u8 length;
+	union {
+		struct {
+			u8 unused;
+			u8 type;
+		} sha1;
+		struct {
+			u8 type;
+			u8 algo;
+		} ng;
+		u8 data[2];
+	} xattr;
+	u8 digest[0];
+} __packed;
+
+/*
+ * signature format v2 - for using with asymmetric keys
+ */
+struct signature_v2_hdr {
+	uint8_t type;		/* xattr type */
+	uint8_t version;	/* signature format version */
+	uint8_t	hash_algo;	/* Digest algorithm [enum pkey_hash_algo] */
+	uint32_t keyid;		/* IMA key identifier - not X509/PGP specific */
+	uint16_t sig_size;	/* signature size */
+	uint8_t sig[0];		/* signature payload */
+} __packed;
+
+/* integrity data associated with an inode */
+struct integrity_iint_cache {
+	struct rb_node rb_node;	/* rooted in integrity_iint_tree */
+	struct inode *inode;	/* back pointer to inode in question */
+	u64 version;		/* track inode changes */
+	unsigned long flags;
+	enum integrity_status ima_file_status:4;
+	enum integrity_status ima_mmap_status:4;
+	enum integrity_status ima_bprm_status:4;
+	enum integrity_status ima_module_status:4;
+	enum integrity_status ima_firmware_status:4;
+	enum integrity_status evm_status:4;
+	struct ima_digest_data *ima_hash;
+};
+
+/* rbtree tree calls to lookup, insert, delete
+ * integrity data associated with an inode.
+ */
+struct integrity_iint_cache *integrity_iint_find(struct inode *inode);
+
+#define INTEGRITY_KEYRING_EVM		0
+#define INTEGRITY_KEYRING_MODULE	1
+#define INTEGRITY_KEYRING_IMA		2
+#define INTEGRITY_KEYRING_MAX		3
+
+#ifdef CONFIG_INTEGRITY_SIGNATURE
+
+int integrity_digsig_verify(const unsigned int id, const char *sig, int siglen,
+			    const char *digest, int digestlen);
+
+int integrity_init_keyring(const unsigned int id);
+#else
+
+static inline int integrity_digsig_verify(const unsigned int id,
+					  const char *sig, int siglen,
+					  const char *digest, int digestlen)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int integrity_init_keyring(const unsigned int id)
+{
+	return 0;
+}
+#endif /* CONFIG_INTEGRITY_SIGNATURE */
+
+#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
+int asymmetric_verify(struct key *keyring, const char *sig,
+		      int siglen, const char *data, int datalen);
+#else
+static inline int asymmetric_verify(struct key *keyring, const char *sig,
+				    int siglen, const char *data, int datalen)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#ifdef CONFIG_INTEGRITY_AUDIT
+/* declarations */
+void integrity_audit_msg(int audit_msgno, struct inode *inode,
+			 const unsigned char *fname, const char *op,
+			 const char *cause, int result, int info);
+#else
+static inline void integrity_audit_msg(int audit_msgno, struct inode *inode,
+				       const unsigned char *fname,
+				       const char *op, const char *cause,
+				       int result, int info)
+{
+}
+#endif
+
+/* set during initialization */
+extern int iint_initialized;

security/integrity/integrity_audit.c

@@ -0,0 +1,65 @@
+/*
+ * Copyright (C) 2008 IBM Corporation
+ * Author: Mimi Zohar <zohar@us.ibm.com>
+ *
+ * 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, version 2 of the License.
+ *
+ * File: integrity_audit.c
+ *	Audit calls for the integrity subsystem
+ */
+
+#include <linux/fs.h>
+#include <linux/gfp.h>
+#include <linux/audit.h>
+#include "integrity.h"
+
+static int integrity_audit_info;
+
+/* ima_audit_setup - enable informational auditing messages */
+static int __init integrity_audit_setup(char *str)
+{
+	unsigned long audit;
+
+	if (!kstrtoul(str, 0, &audit))
+		integrity_audit_info = audit ? 1 : 0;
+	return 1;
+}
+__setup("integrity_audit=", integrity_audit_setup);
+
+void integrity_audit_msg(int audit_msgno, struct inode *inode,
+			 const unsigned char *fname, const char *op,
+			 const char *cause, int result, int audit_info)
+{
+	struct audit_buffer *ab;
+	char name[TASK_COMM_LEN];
+
+	if (!integrity_audit_info && audit_info == 1)	/* Skip info messages */
+		return;
+
+	ab = audit_log_start(current->audit_context, GFP_KERNEL, audit_msgno);
+	audit_log_format(ab, "pid=%d uid=%u auid=%u ses=%u",
+			 task_pid_nr(current),
+			 from_kuid(&init_user_ns, current_cred()->uid),
+			 from_kuid(&init_user_ns, audit_get_loginuid(current)),
+			 audit_get_sessionid(current));
+	audit_log_task_context(ab);
+	audit_log_format(ab, " op=");
+	audit_log_string(ab, op);
+	audit_log_format(ab, " cause=");
+	audit_log_string(ab, cause);
+	audit_log_format(ab, " comm=");
+	audit_log_untrustedstring(ab, get_task_comm(name, current));
+	if (fname) {
+		audit_log_format(ab, " name=");
+		audit_log_untrustedstring(ab, fname);
+	}
+	if (inode) {
+		audit_log_format(ab, " dev=");
+		audit_log_untrustedstring(ab, inode->i_sb->s_id);
+		audit_log_format(ab, " ino=%lu", inode->i_ino);
+	}
+	audit_log_format(ab, " res=%d", !result);
+	audit_log_end(ab);
+}

security/keys/Kconfig

@@ -0,0 +1,100 @@
+#
+# Key management configuration
+#
+
+config KEYS
+	bool "Enable access key retention support"
+	select ASSOCIATIVE_ARRAY
+	help
+	  This option provides support for retaining authentication tokens and
+	  access keys in the kernel.
+
+	  It also includes provision of methods by which such keys might be
+	  associated with a process so that network filesystems, encryption
+	  support and the like can find them.
+
+	  Furthermore, a special type of key is available that acts as keyring:
+	  a searchable sequence of keys. Each process is equipped with access
+	  to five standard keyrings: UID-specific, GID-specific, session,
+	  process and thread.
+
+	  If you are unsure as to whether this is required, answer N.
+
+config PERSISTENT_KEYRINGS
+	bool "Enable register of persistent per-UID keyrings"
+	depends on KEYS
+	help
+	  This option provides a register of persistent per-UID keyrings,
+	  primarily aimed at Kerberos key storage.  The keyrings are persistent
+	  in the sense that they stay around after all processes of that UID
+	  have exited, not that they survive the machine being rebooted.
+
+	  A particular keyring may be accessed by either the user whose keyring
+	  it is or by a process with administrative privileges.  The active
+	  LSMs gets to rule on which admin-level processes get to access the
+	  cache.
+
+	  Keyrings are created and added into the register upon demand and get
+	  removed if they expire (a default timeout is set upon creation).
+
+config BIG_KEYS
+	bool "Large payload keys"
+	depends on KEYS
+	depends on TMPFS
+	help
+	  This option provides support for holding large keys within the kernel
+	  (for example Kerberos ticket caches).  The data may be stored out to
+	  swapspace by tmpfs.
+
+	  If you are unsure as to whether this is required, answer N.
+
+config TRUSTED_KEYS
+	tristate "TRUSTED KEYS"
+	depends on KEYS && TCG_TPM
+	select CRYPTO
+	select CRYPTO_HMAC
+	select CRYPTO_SHA1
+	help
+	  This option provides support for creating, sealing, and unsealing
+	  keys in the kernel. Trusted keys are random number symmetric keys,
+	  generated and RSA-sealed by the TPM. The TPM only unseals the keys,
+	  if the boot PCRs and other criteria match.  Userspace will only ever
+	  see encrypted blobs.
+
+	  If you are unsure as to whether this is required, answer N.
+
+config ENCRYPTED_KEYS
+	tristate "ENCRYPTED KEYS"
+	depends on KEYS
+	select CRYPTO
+	select CRYPTO_HMAC
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	select CRYPTO_SHA256
+	select CRYPTO_RNG
+	help
+	  This option provides support for create/encrypting/decrypting keys
+	  in the kernel.  Encrypted keys are kernel generated random numbers,
+	  which are encrypted/decrypted with a 'master' symmetric key. The
+	  'master' key can be either a trusted-key or user-key type.
+	  Userspace only ever sees/stores encrypted blobs.
+
+	  If you are unsure as to whether this is required, answer N.
+
+config KEYS_DEBUG_PROC_KEYS
+	bool "Enable the /proc/keys file by which keys may be viewed"
+	depends on KEYS
+	help
+	  This option turns on support for the /proc/keys file - through which
+	  can be listed all the keys on the system that are viewable by the
+	  reading process.
+
+	  The only keys included in the list are those that grant View
+	  permission to the reading process whether or not it possesses them.
+	  Note that LSM security checks are still performed, and may further
+	  filter out keys that the current process is not authorised to view.
+
+	  Only key attributes are listed here; key payloads are not included in
+	  the resulting table.
+
+	  If you are unsure as to whether this is required, answer N.

security/keys/Makefile

@@ -0,0 +1,28 @@
+#
+# Makefile for key management
+#
+
+#
+# Core
+#
+obj-y := \
+	gc.o \
+	key.o \
+	keyring.o \
+	keyctl.o \
+	permission.o \
+	process_keys.o \
+	request_key.o \
+	request_key_auth.o \
+	user_defined.o
+obj-$(CONFIG_KEYS_COMPAT) += compat.o
+obj-$(CONFIG_PROC_FS) += proc.o
+obj-$(CONFIG_SYSCTL) += sysctl.o
+obj-$(CONFIG_PERSISTENT_KEYRINGS) += persistent.o
+
+#
+# Key types
+#
+obj-$(CONFIG_BIG_KEYS) += big_key.o
+obj-$(CONFIG_TRUSTED_KEYS) += trusted.o
+obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys/

security/keys/big_key.c

@@ -0,0 +1,214 @@
+/* Large capacity key type
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/seq_file.h>
+#include <linux/file.h>
+#include <linux/shmem_fs.h>
+#include <linux/err.h>
+#include <keys/user-type.h>
+#include <keys/big_key-type.h>
+
+MODULE_LICENSE("GPL");
+
+/*
+ * If the data is under this limit, there's no point creating a shm file to
+ * hold it as the permanently resident metadata for the shmem fs will be at
+ * least as large as the data.
+ */
+#define BIG_KEY_FILE_THRESHOLD (sizeof(struct inode) + sizeof(struct dentry))
+
+/*
+ * big_key defined keys take an arbitrary string as the description and an
+ * arbitrary blob of data as the payload
+ */
+struct key_type key_type_big_key = {
+	.name			= "big_key",
+	.preparse		= big_key_preparse,
+	.free_preparse		= big_key_free_preparse,
+	.instantiate		= generic_key_instantiate,
+	.revoke			= big_key_revoke,
+	.destroy		= big_key_destroy,
+	.describe		= big_key_describe,
+	.read			= big_key_read,
+};
+
+/*
+ * Preparse a big key
+ */
+int big_key_preparse(struct key_preparsed_payload *prep)
+{
+	struct path *path = (struct path *)&prep->payload;
+	struct file *file;
+	ssize_t written;
+	size_t datalen = prep->datalen;
+	int ret;
+
+	ret = -EINVAL;
+	if (datalen <= 0 || datalen > 1024 * 1024 || !prep->data)
+		goto error;
+
+	/* Set an arbitrary quota */
+	prep->quotalen = 16;
+
+	prep->type_data[1] = (void *)(unsigned long)datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		/* Create a shmem file to store the data in.  This will permit the data
+		 * to be swapped out if needed.
+		 *
+		 * TODO: Encrypt the stored data with a temporary key.
+		 */
+		file = shmem_kernel_file_setup("", datalen, 0);
+		if (IS_ERR(file)) {
+			ret = PTR_ERR(file);
+			goto error;
+		}
+
+		written = kernel_write(file, prep->data, prep->datalen, 0);
+		if (written != datalen) {
+			ret = written;
+			if (written >= 0)
+				ret = -ENOMEM;
+			goto err_fput;
+		}
+
+		/* Pin the mount and dentry to the key so that we can open it again
+		 * later
+		 */
+		*path = file->f_path;
+		path_get(path);
+		fput(file);
+	} else {
+		/* Just store the data in a buffer */
+		void *data = kmalloc(datalen, GFP_KERNEL);
+		if (!data)
+			return -ENOMEM;
+
+		prep->payload[0] = memcpy(data, prep->data, prep->datalen);
+	}
+	return 0;
+
+err_fput:
+	fput(file);
+error:
+	return ret;
+}
+
+/*
+ * Clear preparsement.
+ */
+void big_key_free_preparse(struct key_preparsed_payload *prep)
+{
+	if (prep->datalen > BIG_KEY_FILE_THRESHOLD) {
+		struct path *path = (struct path *)&prep->payload;
+		path_put(path);
+	} else {
+		kfree(prep->payload[0]);
+	}
+}
+
+/*
+ * dispose of the links from a revoked keyring
+ * - called with the key sem write-locked
+ */
+void big_key_revoke(struct key *key)
+{
+	struct path *path = (struct path *)&key->payload.data2;
+
+	/* clear the quota */
+	key_payload_reserve(key, 0);
+	if (key_is_instantiated(key) && key->type_data.x[1] > BIG_KEY_FILE_THRESHOLD)
+		vfs_truncate(path, 0);
+}
+
+/*
+ * dispose of the data dangling from the corpse of a big_key key
+ */
+void big_key_destroy(struct key *key)
+{
+	if (key->type_data.x[1] > BIG_KEY_FILE_THRESHOLD) {
+		struct path *path = (struct path *)&key->payload.data2;
+		path_put(path);
+		path->mnt = NULL;
+		path->dentry = NULL;
+	} else {
+		kfree(key->payload.data);
+		key->payload.data = NULL;
+	}
+}
+
+/*
+ * describe the big_key key
+ */
+void big_key_describe(const struct key *key, struct seq_file *m)
+{
+	unsigned long datalen = key->type_data.x[1];
+
+	seq_puts(m, key->description);
+
+	if (key_is_instantiated(key))
+		seq_printf(m, ": %lu [%s]",
+			   datalen,
+			   datalen > BIG_KEY_FILE_THRESHOLD ? "file" : "buff");
+}
+
+/*
+ * read the key data
+ * - the key's semaphore is read-locked
+ */
+long big_key_read(const struct key *key, char __user *buffer, size_t buflen)
+{
+	unsigned long datalen = key->type_data.x[1];
+	long ret;
+
+	if (!buffer || buflen < datalen)
+		return datalen;
+
+	if (datalen > BIG_KEY_FILE_THRESHOLD) {
+		struct path *path = (struct path *)&key->payload.data2;
+		struct file *file;
+		loff_t pos;
+
+		file = dentry_open(path, O_RDONLY, current_cred());
+		if (IS_ERR(file))
+			return PTR_ERR(file);
+
+		pos = 0;
+		ret = vfs_read(file, buffer, datalen, &pos);
+		fput(file);
+		if (ret >= 0 && ret != datalen)
+			ret = -EIO;
+	} else {
+		ret = datalen;
+		if (copy_to_user(buffer, key->payload.data, datalen) != 0)
+			ret = -EFAULT;
+	}
+
+	return ret;
+}
+
+/*
+ * Module stuff
+ */
+static int __init big_key_init(void)
+{
+	return register_key_type(&key_type_big_key);
+}
+
+static void __exit big_key_cleanup(void)
+{
+	unregister_key_type(&key_type_big_key);
+}
+
+module_init(big_key_init);
+module_exit(big_key_cleanup);

security/keys/compat.c

@@ -0,0 +1,147 @@
+/* 32-bit compatibility syscall for 64-bit systems
+ *
+ * Copyright (C) 2004-5 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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.
+ */
+
+#include <linux/syscalls.h>
+#include <linux/keyctl.h>
+#include <linux/compat.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+/*
+ * Instantiate a key with the specified compatibility multipart payload and
+ * link the key into the destination keyring if one is given.
+ *
+ * The caller must have the appropriate instantiation permit set for this to
+ * work (see keyctl_assume_authority).  No other permissions are required.
+ *
+ * If successful, 0 will be returned.
+ */
+static long compat_keyctl_instantiate_key_iov(
+	key_serial_t id,
+	const struct compat_iovec __user *_payload_iov,
+	unsigned ioc,
+	key_serial_t ringid)
+{
+	struct iovec iovstack[UIO_FASTIOV], *iov = iovstack;
+	long ret;
+
+	if (!_payload_iov || !ioc)
+		goto no_payload;
+
+	ret = compat_rw_copy_check_uvector(WRITE, _payload_iov, ioc,
+					   ARRAY_SIZE(iovstack),
+					   iovstack, &iov);
+	if (ret < 0)
+		goto err;
+	if (ret == 0)
+		goto no_payload_free;
+
+	ret = keyctl_instantiate_key_common(id, iov, ioc, ret, ringid);
+err:
+	if (iov != iovstack)
+		kfree(iov);
+	return ret;
+
+no_payload_free:
+	if (iov != iovstack)
+		kfree(iov);
+no_payload:
+	return keyctl_instantiate_key_common(id, NULL, 0, 0, ringid);
+}
+
+/*
+ * The key control system call, 32-bit compatibility version for 64-bit archs
+ *
+ * This should only be called if the 64-bit arch uses weird pointers in 32-bit
+ * mode or doesn't guarantee that the top 32-bits of the argument registers on
+ * taking a 32-bit syscall are zero.  If you can, you should call sys_keyctl()
+ * directly.
+ */
+COMPAT_SYSCALL_DEFINE5(keyctl, u32, option,
+		       u32, arg2, u32, arg3, u32, arg4, u32, arg5)
+{
+	switch (option) {
+	case KEYCTL_GET_KEYRING_ID:
+		return keyctl_get_keyring_ID(arg2, arg3);
+
+	case KEYCTL_JOIN_SESSION_KEYRING:
+		return keyctl_join_session_keyring(compat_ptr(arg2));
+
+	case KEYCTL_UPDATE:
+		return keyctl_update_key(arg2, compat_ptr(arg3), arg4);
+
+	case KEYCTL_REVOKE:
+		return keyctl_revoke_key(arg2);
+
+	case KEYCTL_DESCRIBE:
+		return keyctl_describe_key(arg2, compat_ptr(arg3), arg4);
+
+	case KEYCTL_CLEAR:
+		return keyctl_keyring_clear(arg2);
+
+	case KEYCTL_LINK:
+		return keyctl_keyring_link(arg2, arg3);
+
+	case KEYCTL_UNLINK:
+		return keyctl_keyring_unlink(arg2, arg3);
+
+	case KEYCTL_SEARCH:
+		return keyctl_keyring_search(arg2, compat_ptr(arg3),
+					     compat_ptr(arg4), arg5);
+
+	case KEYCTL_READ:
+		return keyctl_read_key(arg2, compat_ptr(arg3), arg4);
+
+	case KEYCTL_CHOWN:
+		return keyctl_chown_key(arg2, arg3, arg4);
+
+	case KEYCTL_SETPERM:
+		return keyctl_setperm_key(arg2, arg3);
+
+	case KEYCTL_INSTANTIATE:
+		return keyctl_instantiate_key(arg2, compat_ptr(arg3), arg4,
+					      arg5);
+
+	case KEYCTL_NEGATE:
+		return keyctl_negate_key(arg2, arg3, arg4);
+
+	case KEYCTL_SET_REQKEY_KEYRING:
+		return keyctl_set_reqkey_keyring(arg2);
+
+	case KEYCTL_SET_TIMEOUT:
+		return keyctl_set_timeout(arg2, arg3);
+
+	case KEYCTL_ASSUME_AUTHORITY:
+		return keyctl_assume_authority(arg2);
+
+	case KEYCTL_GET_SECURITY:
+		return keyctl_get_security(arg2, compat_ptr(arg3), arg4);
+
+	case KEYCTL_SESSION_TO_PARENT:
+		return keyctl_session_to_parent();
+
+	case KEYCTL_REJECT:
+		return keyctl_reject_key(arg2, arg3, arg4, arg5);
+
+	case KEYCTL_INSTANTIATE_IOV:
+		return compat_keyctl_instantiate_key_iov(
+			arg2, compat_ptr(arg3), arg4, arg5);
+
+	case KEYCTL_INVALIDATE:
+		return keyctl_invalidate_key(arg2);
+
+	case KEYCTL_GET_PERSISTENT:
+		return keyctl_get_persistent(arg2, arg3);
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}

security/keys/encrypted-keys/Makefile

@@ -0,0 +1,10 @@
+#
+# Makefile for encrypted keys
+#
+
+obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys.o
+
+encrypted-keys-y := encrypted.o ecryptfs_format.o
+masterkey-$(CONFIG_TRUSTED_KEYS) := masterkey_trusted.o
+masterkey-$(CONFIG_TRUSTED_KEYS)-$(CONFIG_ENCRYPTED_KEYS) := masterkey_trusted.o
+encrypted-keys-y += $(masterkey-y) $(masterkey-m-m)

security/keys/encrypted-keys/ecryptfs_format.c

@@ -0,0 +1,81 @@
+/*
+ * ecryptfs_format.c: helper functions for the encrypted key type
+ *
+ * Copyright (C) 2006 International Business Machines Corp.
+ * Copyright (C) 2010 Politecnico di Torino, Italy
+ *                    TORSEC group -- http://security.polito.it
+ *
+ * Authors:
+ * Michael A. Halcrow <mahalcro@us.ibm.com>
+ * Tyler Hicks <tyhicks@ou.edu>
+ * Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * 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, version 2 of the License.
+ */
+
+#include <linux/module.h>
+#include "ecryptfs_format.h"
+
+u8 *ecryptfs_get_auth_tok_key(struct ecryptfs_auth_tok *auth_tok)
+{
+	return auth_tok->token.password.session_key_encryption_key;
+}
+EXPORT_SYMBOL(ecryptfs_get_auth_tok_key);
+
+/*
+ * ecryptfs_get_versions()
+ *
+ * Source code taken from the software 'ecryptfs-utils' version 83.
+ *
+ */
+void ecryptfs_get_versions(int *major, int *minor, int *file_version)
+{
+	*major = ECRYPTFS_VERSION_MAJOR;
+	*minor = ECRYPTFS_VERSION_MINOR;
+	if (file_version)
+		*file_version = ECRYPTFS_SUPPORTED_FILE_VERSION;
+}
+EXPORT_SYMBOL(ecryptfs_get_versions);
+
+/*
+ * ecryptfs_fill_auth_tok - fill the ecryptfs_auth_tok structure
+ *
+ * Fill the ecryptfs_auth_tok structure with required ecryptfs data.
+ * The source code is inspired to the original function generate_payload()
+ * shipped with the software 'ecryptfs-utils' version 83.
+ *
+ */
+int ecryptfs_fill_auth_tok(struct ecryptfs_auth_tok *auth_tok,
+			   const char *key_desc)
+{
+	int major, minor;
+
+	ecryptfs_get_versions(&major, &minor, NULL);
+	auth_tok->version = (((uint16_t)(major << 8) & 0xFF00)
+			     | ((uint16_t)minor & 0x00FF));
+	auth_tok->token_type = ECRYPTFS_PASSWORD;
+	strncpy((char *)auth_tok->token.password.signature, key_desc,
+		ECRYPTFS_PASSWORD_SIG_SIZE);
+	auth_tok->token.password.session_key_encryption_key_bytes =
+		ECRYPTFS_MAX_KEY_BYTES;
+	/*
+	 * Removed auth_tok->token.password.salt and
+	 * auth_tok->token.password.session_key_encryption_key
+	 * initialization from the original code
+	 */
+	/* TODO: Make the hash parameterizable via policy */
+	auth_tok->token.password.flags |=
+		ECRYPTFS_SESSION_KEY_ENCRYPTION_KEY_SET;
+	/* The kernel code will encrypt the session key. */
+	auth_tok->session_key.encrypted_key[0] = 0;
+	auth_tok->session_key.encrypted_key_size = 0;
+	/* Default; subject to change by kernel eCryptfs */
+	auth_tok->token.password.hash_algo = PGP_DIGEST_ALGO_SHA512;
+	auth_tok->token.password.flags &= ~(ECRYPTFS_PERSISTENT_PASSWORD);
+	return 0;
+}
+EXPORT_SYMBOL(ecryptfs_fill_auth_tok);
+
+MODULE_LICENSE("GPL");

security/keys/encrypted-keys/ecryptfs_format.h

@@ -0,0 +1,30 @@
+/*
+ * ecryptfs_format.h: helper functions for the encrypted key type
+ *
+ * Copyright (C) 2006 International Business Machines Corp.
+ * Copyright (C) 2010 Politecnico di Torino, Italy
+ *                    TORSEC group -- http://security.polito.it
+ *
+ * Authors:
+ * Michael A. Halcrow <mahalcro@us.ibm.com>
+ * Tyler Hicks <tyhicks@ou.edu>
+ * Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * 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, version 2 of the License.
+ */
+
+#ifndef __KEYS_ECRYPTFS_H
+#define __KEYS_ECRYPTFS_H
+
+#include <linux/ecryptfs.h>
+
+#define PGP_DIGEST_ALGO_SHA512   10
+
+u8 *ecryptfs_get_auth_tok_key(struct ecryptfs_auth_tok *auth_tok);
+void ecryptfs_get_versions(int *major, int *minor, int *file_version);
+int ecryptfs_fill_auth_tok(struct ecryptfs_auth_tok *auth_tok,
+			   const char *key_desc);
+
+#endif /* __KEYS_ECRYPTFS_H */

security/keys/encrypted-keys/encrypted.h

@@ -0,0 +1,66 @@
+#ifndef __ENCRYPTED_KEY_H
+#define __ENCRYPTED_KEY_H
+
+#define ENCRYPTED_DEBUG 0
+#if defined(CONFIG_TRUSTED_KEYS) || \
+  (defined(CONFIG_TRUSTED_KEYS_MODULE) && defined(CONFIG_ENCRYPTED_KEYS_MODULE))
+extern struct key *request_trusted_key(const char *trusted_desc,
+				       u8 **master_key, size_t *master_keylen);
+#else
+static inline struct key *request_trusted_key(const char *trusted_desc,
+					      u8 **master_key,
+					      size_t *master_keylen)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+#endif
+
+#if ENCRYPTED_DEBUG
+static inline void dump_master_key(const u8 *master_key, size_t master_keylen)
+{
+	print_hex_dump(KERN_ERR, "master key: ", DUMP_PREFIX_NONE, 32, 1,
+		       master_key, master_keylen, 0);
+}
+
+static inline void dump_decrypted_data(struct encrypted_key_payload *epayload)
+{
+	print_hex_dump(KERN_ERR, "decrypted data: ", DUMP_PREFIX_NONE, 32, 1,
+		       epayload->decrypted_data,
+		       epayload->decrypted_datalen, 0);
+}
+
+static inline void dump_encrypted_data(struct encrypted_key_payload *epayload,
+				       unsigned int encrypted_datalen)
+{
+	print_hex_dump(KERN_ERR, "encrypted data: ", DUMP_PREFIX_NONE, 32, 1,
+		       epayload->encrypted_data, encrypted_datalen, 0);
+}
+
+static inline void dump_hmac(const char *str, const u8 *digest,
+			     unsigned int hmac_size)
+{
+	if (str)
+		pr_info("encrypted_key: %s", str);
+	print_hex_dump(KERN_ERR, "hmac: ", DUMP_PREFIX_NONE, 32, 1, digest,
+		       hmac_size, 0);
+}
+#else
+static inline void dump_master_key(const u8 *master_key, size_t master_keylen)
+{
+}
+
+static inline void dump_decrypted_data(struct encrypted_key_payload *epayload)
+{
+}
+
+static inline void dump_encrypted_data(struct encrypted_key_payload *epayload,
+				       unsigned int encrypted_datalen)
+{
+}
+
+static inline void dump_hmac(const char *str, const u8 *digest,
+			     unsigned int hmac_size)
+{
+}
+#endif
+#endif

security/keys/encrypted-keys/masterkey_trusted.c

@@ -0,0 +1,47 @@
+/*
+ * Copyright (C) 2010 IBM Corporation
+ * Copyright (C) 2010 Politecnico di Torino, Italy
+ *                    TORSEC group -- http://security.polito.it
+ *
+ * Authors:
+ * Mimi Zohar <zohar@us.ibm.com>
+ * Roberto Sassu <roberto.sassu@polito.it>
+ *
+ * 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, version 2 of the License.
+ *
+ * See Documentation/security/keys-trusted-encrypted.txt
+ */
+
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/err.h>
+#include <keys/trusted-type.h>
+#include <keys/encrypted-type.h>
+#include "encrypted.h"
+
+/*
+ * request_trusted_key - request the trusted key
+ *
+ * Trusted keys are sealed to PCRs and other metadata. Although userspace
+ * manages both trusted/encrypted key-types, like the encrypted key type
+ * data, trusted key type data is not visible decrypted from userspace.
+ */
+struct key *request_trusted_key(const char *trusted_desc,
+				u8 **master_key, size_t *master_keylen)
+{
+	struct trusted_key_payload *tpayload;
+	struct key *tkey;
+
+	tkey = request_key(&key_type_trusted, trusted_desc, NULL);
+	if (IS_ERR(tkey))
+		goto error;
+
+	down_read(&tkey->sem);
+	tpayload = tkey->payload.data;
+	*master_key = tpayload->key;
+	*master_keylen = tpayload->key_len;
+error:
+	return tkey;
+}

security/keys/gc.c

@@ -0,0 +1,358 @@
+/* Key garbage collector
+ *
+ * Copyright (C) 2009-2011 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <keys/keyring-type.h>
+#include "internal.h"
+
+/*
+ * Delay between key revocation/expiry in seconds
+ */
+unsigned key_gc_delay = 5 * 60;
+
+/*
+ * Reaper for unused keys.
+ */
+static void key_garbage_collector(struct work_struct *work);
+DECLARE_WORK(key_gc_work, key_garbage_collector);
+
+/*
+ * Reaper for links from keyrings to dead keys.
+ */
+static void key_gc_timer_func(unsigned long);
+static DEFINE_TIMER(key_gc_timer, key_gc_timer_func, 0, 0);
+
+static time_t key_gc_next_run = LONG_MAX;
+static struct key_type *key_gc_dead_keytype;
+
+static unsigned long key_gc_flags;
+#define KEY_GC_KEY_EXPIRED	0	/* A key expired and needs unlinking */
+#define KEY_GC_REAP_KEYTYPE	1	/* A keytype is being unregistered */
+#define KEY_GC_REAPING_KEYTYPE	2	/* Cleared when keytype reaped */
+
+
+/*
+ * Any key whose type gets unregistered will be re-typed to this if it can't be
+ * immediately unlinked.
+ */
+struct key_type key_type_dead = {
+	.name = "dead",
+};
+
+/*
+ * Schedule a garbage collection run.
+ * - time precision isn't particularly important
+ */
+void key_schedule_gc(time_t gc_at)
+{
+	unsigned long expires;
+	time_t now = current_kernel_time().tv_sec;
+
+	kenter("%ld", gc_at - now);
+
+	if (gc_at <= now || test_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags)) {
+		kdebug("IMMEDIATE");
+		schedule_work(&key_gc_work);
+	} else if (gc_at < key_gc_next_run) {
+		kdebug("DEFERRED");
+		key_gc_next_run = gc_at;
+		expires = jiffies + (gc_at - now) * HZ;
+		mod_timer(&key_gc_timer, expires);
+	}
+}
+
+/*
+ * Schedule a dead links collection run.
+ */
+void key_schedule_gc_links(void)
+{
+	set_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags);
+	schedule_work(&key_gc_work);
+}
+
+/*
+ * Some key's cleanup time was met after it expired, so we need to get the
+ * reaper to go through a cycle finding expired keys.
+ */
+static void key_gc_timer_func(unsigned long data)
+{
+	kenter("");
+	key_gc_next_run = LONG_MAX;
+	key_schedule_gc_links();
+}
+
+/*
+ * Reap keys of dead type.
+ *
+ * We use three flags to make sure we see three complete cycles of the garbage
+ * collector: the first to mark keys of that type as being dead, the second to
+ * collect dead links and the third to clean up the dead keys.  We have to be
+ * careful as there may already be a cycle in progress.
+ *
+ * The caller must be holding key_types_sem.
+ */
+void key_gc_keytype(struct key_type *ktype)
+{
+	kenter("%s", ktype->name);
+
+	key_gc_dead_keytype = ktype;
+	set_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags);
+	smp_mb();
+	set_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags);
+
+	kdebug("schedule");
+	schedule_work(&key_gc_work);
+
+	kdebug("sleep");
+	wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE,
+		    TASK_UNINTERRUPTIBLE);
+
+	key_gc_dead_keytype = NULL;
+	kleave("");
+}
+
+/*
+ * Garbage collect a list of unreferenced, detached keys
+ */
+static noinline void key_gc_unused_keys(struct list_head *keys)
+{
+	while (!list_empty(keys)) {
+		struct key *key =
+			list_entry(keys->next, struct key, graveyard_link);
+		list_del(&key->graveyard_link);
+
+		kdebug("- %u", key->serial);
+		key_check(key);
+
+		security_key_free(key);
+
+		/* deal with the user's key tracking and quota */
+		if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) {
+			spin_lock(&key->user->lock);
+			key->user->qnkeys--;
+			key->user->qnbytes -= key->quotalen;
+			spin_unlock(&key->user->lock);
+		}
+
+		atomic_dec(&key->user->nkeys);
+		if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
+			atomic_dec(&key->user->nikeys);
+
+		/* now throw away the key memory */
+		if (key->type->destroy)
+			key->type->destroy(key);
+
+		key_user_put(key->user);
+
+		kfree(key->description);
+
+#ifdef KEY_DEBUGGING
+		key->magic = KEY_DEBUG_MAGIC_X;
+#endif
+		kmem_cache_free(key_jar, key);
+	}
+}
+
+/*
+ * Garbage collector for unused keys.
+ *
+ * This is done in process context so that we don't have to disable interrupts
+ * all over the place.  key_put() schedules this rather than trying to do the
+ * cleanup itself, which means key_put() doesn't have to sleep.
+ */
+static void key_garbage_collector(struct work_struct *work)
+{
+	static LIST_HEAD(graveyard);
+	static u8 gc_state;		/* Internal persistent state */
+#define KEY_GC_REAP_AGAIN	0x01	/* - Need another cycle */
+#define KEY_GC_REAPING_LINKS	0x02	/* - We need to reap links */
+#define KEY_GC_SET_TIMER	0x04	/* - We need to restart the timer */
+#define KEY_GC_REAPING_DEAD_1	0x10	/* - We need to mark dead keys */
+#define KEY_GC_REAPING_DEAD_2	0x20	/* - We need to reap dead key links */
+#define KEY_GC_REAPING_DEAD_3	0x40	/* - We need to reap dead keys */
+#define KEY_GC_FOUND_DEAD_KEY	0x80	/* - We found at least one dead key */
+
+	struct rb_node *cursor;
+	struct key *key;
+	time_t new_timer, limit;
+
+	kenter("[%lx,%x]", key_gc_flags, gc_state);
+
+	limit = current_kernel_time().tv_sec;
+	if (limit > key_gc_delay)
+		limit -= key_gc_delay;
+	else
+		limit = key_gc_delay;
+
+	/* Work out what we're going to be doing in this pass */
+	gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2;
+	gc_state <<= 1;
+	if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags))
+		gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER;
+
+	if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags))
+		gc_state |= KEY_GC_REAPING_DEAD_1;
+	kdebug("new pass %x", gc_state);
+
+	new_timer = LONG_MAX;
+
+	/* As only this function is permitted to remove things from the key
+	 * serial tree, if cursor is non-NULL then it will always point to a
+	 * valid node in the tree - even if lock got dropped.
+	 */
+	spin_lock(&key_serial_lock);
+	cursor = rb_first(&key_serial_tree);
+
+continue_scanning:
+	while (cursor) {
+		key = rb_entry(cursor, struct key, serial_node);
+		cursor = rb_next(cursor);
+
+		if (atomic_read(&key->usage) == 0)
+			goto found_unreferenced_key;
+
+		if (unlikely(gc_state & KEY_GC_REAPING_DEAD_1)) {
+			if (key->type == key_gc_dead_keytype) {
+				gc_state |= KEY_GC_FOUND_DEAD_KEY;
+				set_bit(KEY_FLAG_DEAD, &key->flags);
+				key->perm = 0;
+				goto skip_dead_key;
+			}
+		}
+
+		if (gc_state & KEY_GC_SET_TIMER) {
+			if (key->expiry > limit && key->expiry < new_timer) {
+				kdebug("will expire %x in %ld",
+				       key_serial(key), key->expiry - limit);
+				new_timer = key->expiry;
+			}
+		}
+
+		if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2))
+			if (key->type == key_gc_dead_keytype)
+				gc_state |= KEY_GC_FOUND_DEAD_KEY;
+
+		if ((gc_state & KEY_GC_REAPING_LINKS) ||
+		    unlikely(gc_state & KEY_GC_REAPING_DEAD_2)) {
+			if (key->type == &key_type_keyring)
+				goto found_keyring;
+		}
+
+		if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3))
+			if (key->type == key_gc_dead_keytype)
+				goto destroy_dead_key;
+
+	skip_dead_key:
+		if (spin_is_contended(&key_serial_lock) || need_resched())
+			goto contended;
+	}
+
+contended:
+	spin_unlock(&key_serial_lock);
+
+maybe_resched:
+	if (cursor) {
+		cond_resched();
+		spin_lock(&key_serial_lock);
+		goto continue_scanning;
+	}
+
+	/* We've completed the pass.  Set the timer if we need to and queue a
+	 * new cycle if necessary.  We keep executing cycles until we find one
+	 * where we didn't reap any keys.
+	 */
+	kdebug("pass complete");
+
+	if (gc_state & KEY_GC_SET_TIMER && new_timer != (time_t)LONG_MAX) {
+		new_timer += key_gc_delay;
+		key_schedule_gc(new_timer);
+	}
+
+	if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2) ||
+	    !list_empty(&graveyard)) {
+		/* Make sure that all pending keyring payload destructions are
+		 * fulfilled and that people aren't now looking at dead or
+		 * dying keys that they don't have a reference upon or a link
+		 * to.
+		 */
+		kdebug("gc sync");
+		synchronize_rcu();
+	}
+
+	if (!list_empty(&graveyard)) {
+		kdebug("gc keys");
+		key_gc_unused_keys(&graveyard);
+	}
+
+	if (unlikely(gc_state & (KEY_GC_REAPING_DEAD_1 |
+				 KEY_GC_REAPING_DEAD_2))) {
+		if (!(gc_state & KEY_GC_FOUND_DEAD_KEY)) {
+			/* No remaining dead keys: short circuit the remaining
+			 * keytype reap cycles.
+			 */
+			kdebug("dead short");
+			gc_state &= ~(KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2);
+			gc_state |= KEY_GC_REAPING_DEAD_3;
+		} else {
+			gc_state |= KEY_GC_REAP_AGAIN;
+		}
+	}
+
+	if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3)) {
+		kdebug("dead wake");
+		smp_mb();
+		clear_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags);
+		wake_up_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE);
+	}
+
+	if (gc_state & KEY_GC_REAP_AGAIN)
+		schedule_work(&key_gc_work);
+	kleave(" [end %x]", gc_state);
+	return;
+
+	/* We found an unreferenced key - once we've removed it from the tree,
+	 * we can safely drop the lock.
+	 */
+found_unreferenced_key:
+	kdebug("unrefd key %d", key->serial);
+	rb_erase(&key->serial_node, &key_serial_tree);
+	spin_unlock(&key_serial_lock);
+
+	list_add_tail(&key->graveyard_link, &graveyard);
+	gc_state |= KEY_GC_REAP_AGAIN;
+	goto maybe_resched;
+
+	/* We found a keyring and we need to check the payload for links to
+	 * dead or expired keys.  We don't flag another reap immediately as we
+	 * have to wait for the old payload to be destroyed by RCU before we
+	 * can reap the keys to which it refers.
+	 */
+found_keyring:
+	spin_unlock(&key_serial_lock);
+	keyring_gc(key, limit);
+	goto maybe_resched;
+
+	/* We found a dead key that is still referenced.  Reset its type and
+	 * destroy its payload with its semaphore held.
+	 */
+destroy_dead_key:
+	spin_unlock(&key_serial_lock);
+	kdebug("destroy key %d", key->serial);
+	down_write(&key->sem);
+	key->type = &key_type_dead;
+	if (key_gc_dead_keytype->destroy)
+		key_gc_dead_keytype->destroy(key);
+	memset(&key->payload, KEY_DESTROY, sizeof(key->payload));
+	up_write(&key->sem);
+	goto maybe_resched;
+}

security/keys/internal.h

@@ -0,0 +1,277 @@
+/* Authentication token and access key management internal defs
+ *
+ * Copyright (C) 2003-5, 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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.
+ */
+
+#ifndef _INTERNAL_H
+#define _INTERNAL_H
+
+#include <linux/sched.h>
+#include <linux/key-type.h>
+#include <linux/task_work.h>
+
+struct iovec;
+
+#ifdef __KDEBUG
+#define kenter(FMT, ...) \
+	printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+	printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+	printk(KERN_DEBUG "   "FMT"\n", ##__VA_ARGS__)
+#else
+#define kenter(FMT, ...) \
+	no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+	no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+	no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__)
+#endif
+
+extern struct key_type key_type_dead;
+extern struct key_type key_type_user;
+extern struct key_type key_type_logon;
+
+/*****************************************************************************/
+/*
+ * Keep track of keys for a user.
+ *
+ * This needs to be separate to user_struct to avoid a refcount-loop
+ * (user_struct pins some keyrings which pin this struct).
+ *
+ * We also keep track of keys under request from userspace for this UID here.
+ */
+struct key_user {
+	struct rb_node		node;
+	struct mutex		cons_lock;	/* construction initiation lock */
+	spinlock_t		lock;
+	atomic_t		usage;		/* for accessing qnkeys & qnbytes */
+	atomic_t		nkeys;		/* number of keys */
+	atomic_t		nikeys;		/* number of instantiated keys */
+	kuid_t			uid;
+	int			qnkeys;		/* number of keys allocated to this user */
+	int			qnbytes;	/* number of bytes allocated to this user */
+};
+
+extern struct rb_root	key_user_tree;
+extern spinlock_t	key_user_lock;
+extern struct key_user	root_key_user;
+
+extern struct key_user *key_user_lookup(kuid_t uid);
+extern void key_user_put(struct key_user *user);
+
+/*
+ * Key quota limits.
+ * - root has its own separate limits to everyone else
+ */
+extern unsigned key_quota_root_maxkeys;
+extern unsigned key_quota_root_maxbytes;
+extern unsigned key_quota_maxkeys;
+extern unsigned key_quota_maxbytes;
+
+#define KEYQUOTA_LINK_BYTES	4		/* a link in a keyring is worth 4 bytes */
+
+
+extern struct kmem_cache *key_jar;
+extern struct rb_root key_serial_tree;
+extern spinlock_t key_serial_lock;
+extern struct mutex key_construction_mutex;
+extern wait_queue_head_t request_key_conswq;
+
+
+extern struct key_type *key_type_lookup(const char *type);
+extern void key_type_put(struct key_type *ktype);
+
+extern int __key_link_begin(struct key *keyring,
+			    const struct keyring_index_key *index_key,
+			    struct assoc_array_edit **_edit);
+extern int __key_link_check_live_key(struct key *keyring, struct key *key);
+extern void __key_link(struct key *key, struct assoc_array_edit **_edit);
+extern void __key_link_end(struct key *keyring,
+			   const struct keyring_index_key *index_key,
+			   struct assoc_array_edit *edit);
+
+extern key_ref_t find_key_to_update(key_ref_t keyring_ref,
+				    const struct keyring_index_key *index_key);
+
+extern struct key *keyring_search_instkey(struct key *keyring,
+					  key_serial_t target_id);
+
+extern int iterate_over_keyring(const struct key *keyring,
+				int (*func)(const struct key *key, void *data),
+				void *data);
+
+struct keyring_search_context {
+	struct keyring_index_key index_key;
+	const struct cred	*cred;
+	struct key_match_data	match_data;
+	unsigned		flags;
+#define KEYRING_SEARCH_NO_STATE_CHECK	0x0001	/* Skip state checks */
+#define KEYRING_SEARCH_DO_STATE_CHECK	0x0002	/* Override NO_STATE_CHECK */
+#define KEYRING_SEARCH_NO_UPDATE_TIME	0x0004	/* Don't update times */
+#define KEYRING_SEARCH_NO_CHECK_PERM	0x0008	/* Don't check permissions */
+#define KEYRING_SEARCH_DETECT_TOO_DEEP	0x0010	/* Give an error on excessive depth */
+#define KEYRING_SEARCH_SKIP_EXPIRED	0x0020	/* Ignore expired keys (intention to replace) */
+
+	int (*iterator)(const void *object, void *iterator_data);
+
+	/* Internal stuff */
+	int			skipped_ret;
+	bool			possessed;
+	key_ref_t		result;
+	struct timespec		now;
+};
+
+extern bool key_default_cmp(const struct key *key,
+			    const struct key_match_data *match_data);
+extern key_ref_t keyring_search_aux(key_ref_t keyring_ref,
+				    struct keyring_search_context *ctx);
+
+extern key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx);
+extern key_ref_t search_process_keyrings(struct keyring_search_context *ctx);
+
+extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check);
+
+extern int install_user_keyrings(void);
+extern int install_thread_keyring_to_cred(struct cred *);
+extern int install_process_keyring_to_cred(struct cred *);
+extern int install_session_keyring_to_cred(struct cred *, struct key *);
+
+extern struct key *request_key_and_link(struct key_type *type,
+					const char *description,
+					const void *callout_info,
+					size_t callout_len,
+					void *aux,
+					struct key *dest_keyring,
+					unsigned long flags);
+
+extern bool lookup_user_key_possessed(const struct key *key,
+				      const struct key_match_data *match_data);
+extern key_ref_t lookup_user_key(key_serial_t id, unsigned long flags,
+				 key_perm_t perm);
+#define KEY_LOOKUP_CREATE	0x01
+#define KEY_LOOKUP_PARTIAL	0x02
+#define KEY_LOOKUP_FOR_UNLINK	0x04
+
+extern long join_session_keyring(const char *name);
+extern void key_change_session_keyring(struct callback_head *twork);
+
+extern struct work_struct key_gc_work;
+extern unsigned key_gc_delay;
+extern void keyring_gc(struct key *keyring, time_t limit);
+extern void key_schedule_gc(time_t gc_at);
+extern void key_schedule_gc_links(void);
+extern void key_gc_keytype(struct key_type *ktype);
+
+extern int key_task_permission(const key_ref_t key_ref,
+			       const struct cred *cred,
+			       key_perm_t perm);
+
+/*
+ * Check to see whether permission is granted to use a key in the desired way.
+ */
+static inline int key_permission(const key_ref_t key_ref, unsigned perm)
+{
+	return key_task_permission(key_ref, current_cred(), perm);
+}
+
+/*
+ * Authorisation record for request_key().
+ */
+struct request_key_auth {
+	struct key		*target_key;
+	struct key		*dest_keyring;
+	const struct cred	*cred;
+	void			*callout_info;
+	size_t			callout_len;
+	pid_t			pid;
+};
+
+extern struct key_type key_type_request_key_auth;
+extern struct key *request_key_auth_new(struct key *target,
+					const void *callout_info,
+					size_t callout_len,
+					struct key *dest_keyring);
+
+extern struct key *key_get_instantiation_authkey(key_serial_t target_id);
+
+/*
+ * Determine whether a key is dead.
+ */
+static inline bool key_is_dead(const struct key *key, time_t limit)
+{
+	return
+		key->flags & ((1 << KEY_FLAG_DEAD) |
+			      (1 << KEY_FLAG_INVALIDATED)) ||
+		(key->expiry > 0 && key->expiry <= limit);
+}
+
+/*
+ * keyctl() functions
+ */
+extern long keyctl_get_keyring_ID(key_serial_t, int);
+extern long keyctl_join_session_keyring(const char __user *);
+extern long keyctl_update_key(key_serial_t, const void __user *, size_t);
+extern long keyctl_revoke_key(key_serial_t);
+extern long keyctl_keyring_clear(key_serial_t);
+extern long keyctl_keyring_link(key_serial_t, key_serial_t);
+extern long keyctl_keyring_unlink(key_serial_t, key_serial_t);
+extern long keyctl_describe_key(key_serial_t, char __user *, size_t);
+extern long keyctl_keyring_search(key_serial_t, const char __user *,
+				  const char __user *, key_serial_t);
+extern long keyctl_read_key(key_serial_t, char __user *, size_t);
+extern long keyctl_chown_key(key_serial_t, uid_t, gid_t);
+extern long keyctl_setperm_key(key_serial_t, key_perm_t);
+extern long keyctl_instantiate_key(key_serial_t, const void __user *,
+				   size_t, key_serial_t);
+extern long keyctl_negate_key(key_serial_t, unsigned, key_serial_t);
+extern long keyctl_set_reqkey_keyring(int);
+extern long keyctl_set_timeout(key_serial_t, unsigned);
+extern long keyctl_assume_authority(key_serial_t);
+extern long keyctl_get_security(key_serial_t keyid, char __user *buffer,
+				size_t buflen);
+extern long keyctl_session_to_parent(void);
+extern long keyctl_reject_key(key_serial_t, unsigned, unsigned, key_serial_t);
+extern long keyctl_instantiate_key_iov(key_serial_t,
+				       const struct iovec __user *,
+				       unsigned, key_serial_t);
+extern long keyctl_invalidate_key(key_serial_t);
+
+extern long keyctl_instantiate_key_common(key_serial_t,
+					  const struct iovec *,
+					  unsigned, size_t, key_serial_t);
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+extern long keyctl_get_persistent(uid_t, key_serial_t);
+extern unsigned persistent_keyring_expiry;
+#else
+static inline long keyctl_get_persistent(uid_t uid, key_serial_t destring)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+/*
+ * Debugging key validation
+ */
+#ifdef KEY_DEBUGGING
+extern void __key_check(const struct key *);
+
+static inline void key_check(const struct key *key)
+{
+	if (key && (IS_ERR(key) || key->magic != KEY_DEBUG_MAGIC))
+		__key_check(key);
+}
+
+#else
+
+#define key_check(key) do {} while(0)
+
+#endif
+
+#endif /* _INTERNAL_H */

security/keys/permission.c

@@ -0,0 +1,110 @@
+/* Key permission checking
+ *
+ * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/security.h>
+#include "internal.h"
+
+/**
+ * key_task_permission - Check a key can be used
+ * @key_ref: The key to check.
+ * @cred: The credentials to use.
+ * @perm: The permissions to check for.
+ *
+ * Check to see whether permission is granted to use a key in the desired way,
+ * but permit the security modules to override.
+ *
+ * The caller must hold either a ref on cred or must hold the RCU readlock.
+ *
+ * Returns 0 if successful, -EACCES if access is denied based on the
+ * permissions bits or the LSM check.
+ */
+int key_task_permission(const key_ref_t key_ref, const struct cred *cred,
+			unsigned perm)
+{
+	struct key *key;
+	key_perm_t kperm;
+	int ret;
+
+	key = key_ref_to_ptr(key_ref);
+
+	/* use the second 8-bits of permissions for keys the caller owns */
+	if (uid_eq(key->uid, cred->fsuid)) {
+		kperm = key->perm >> 16;
+		goto use_these_perms;
+	}
+
+	/* use the third 8-bits of permissions for keys the caller has a group
+	 * membership in common with */
+	if (gid_valid(key->gid) && key->perm & KEY_GRP_ALL) {
+		if (gid_eq(key->gid, cred->fsgid)) {
+			kperm = key->perm >> 8;
+			goto use_these_perms;
+		}
+
+		ret = groups_search(cred->group_info, key->gid);
+		if (ret) {
+			kperm = key->perm >> 8;
+			goto use_these_perms;
+		}
+	}
+
+	/* otherwise use the least-significant 8-bits */
+	kperm = key->perm;
+
+use_these_perms:
+
+	/* use the top 8-bits of permissions for keys the caller possesses
+	 * - possessor permissions are additive with other permissions
+	 */
+	if (is_key_possessed(key_ref))
+		kperm |= key->perm >> 24;
+
+	kperm = kperm & perm & KEY_NEED_ALL;
+
+	if (kperm != perm)
+		return -EACCES;
+
+	/* let LSM be the final arbiter */
+	return security_key_permission(key_ref, cred, perm);
+}
+EXPORT_SYMBOL(key_task_permission);
+
+/**
+ * key_validate - Validate a key.
+ * @key: The key to be validated.
+ *
+ * Check that a key is valid, returning 0 if the key is okay, -ENOKEY if the
+ * key is invalidated, -EKEYREVOKED if the key's type has been removed or if
+ * the key has been revoked or -EKEYEXPIRED if the key has expired.
+ */
+int key_validate(const struct key *key)
+{
+	unsigned long flags = key->flags;
+
+	if (flags & (1 << KEY_FLAG_INVALIDATED))
+		return -ENOKEY;
+
+	/* check it's still accessible */
+	if (flags & ((1 << KEY_FLAG_REVOKED) |
+		     (1 << KEY_FLAG_DEAD)))
+		return -EKEYREVOKED;
+
+	/* check it hasn't expired */
+	if (key->expiry) {
+		struct timespec now = current_kernel_time();
+		if (now.tv_sec >= key->expiry)
+			return -EKEYEXPIRED;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(key_validate);

security/keys/persistent.c

@@ -0,0 +1,167 @@
+/* General persistent per-UID keyrings register
+ *
+ * Copyright (C) 2013 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/user_namespace.h>
+#include "internal.h"
+
+unsigned persistent_keyring_expiry = 3 * 24 * 3600; /* Expire after 3 days of non-use */
+
+/*
+ * Create the persistent keyring register for the current user namespace.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static int key_create_persistent_register(struct user_namespace *ns)
+{
+	struct key *reg = keyring_alloc(".persistent_register",
+					KUIDT_INIT(0), KGIDT_INIT(0),
+					current_cred(),
+					((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+					 KEY_USR_VIEW | KEY_USR_READ),
+					KEY_ALLOC_NOT_IN_QUOTA, NULL);
+	if (IS_ERR(reg))
+		return PTR_ERR(reg);
+
+	ns->persistent_keyring_register = reg;
+	return 0;
+}
+
+/*
+ * Create the persistent keyring for the specified user.
+ *
+ * Called with the namespace's sem locked for writing.
+ */
+static key_ref_t key_create_persistent(struct user_namespace *ns, kuid_t uid,
+				       struct keyring_index_key *index_key)
+{
+	struct key *persistent;
+	key_ref_t reg_ref, persistent_ref;
+
+	if (!ns->persistent_keyring_register) {
+		long err = key_create_persistent_register(ns);
+		if (err < 0)
+			return ERR_PTR(err);
+	} else {
+		reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+		persistent_ref = find_key_to_update(reg_ref, index_key);
+		if (persistent_ref)
+			return persistent_ref;
+	}
+
+	persistent = keyring_alloc(index_key->description,
+				   uid, INVALID_GID, current_cred(),
+				   ((KEY_POS_ALL & ~KEY_POS_SETATTR) |
+				    KEY_USR_VIEW | KEY_USR_READ),
+				   KEY_ALLOC_NOT_IN_QUOTA,
+				   ns->persistent_keyring_register);
+	if (IS_ERR(persistent))
+		return ERR_CAST(persistent);
+
+	return make_key_ref(persistent, true);
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+static long key_get_persistent(struct user_namespace *ns, kuid_t uid,
+			       key_ref_t dest_ref)
+{
+	struct keyring_index_key index_key;
+	struct key *persistent;
+	key_ref_t reg_ref, persistent_ref;
+	char buf[32];
+	long ret;
+
+	/* Look in the register if it exists */
+	index_key.type = &key_type_keyring;
+	index_key.description = buf;
+	index_key.desc_len = sprintf(buf, "_persistent.%u", from_kuid(ns, uid));
+
+	if (ns->persistent_keyring_register) {
+		reg_ref = make_key_ref(ns->persistent_keyring_register, true);
+		down_read(&ns->persistent_keyring_register_sem);
+		persistent_ref = find_key_to_update(reg_ref, &index_key);
+		up_read(&ns->persistent_keyring_register_sem);
+
+		if (persistent_ref)
+			goto found;
+	}
+
+	/* It wasn't in the register, so we'll need to create it.  We might
+	 * also need to create the register.
+	 */
+	down_write(&ns->persistent_keyring_register_sem);
+	persistent_ref = key_create_persistent(ns, uid, &index_key);
+	up_write(&ns->persistent_keyring_register_sem);
+	if (!IS_ERR(persistent_ref))
+		goto found;
+
+	return PTR_ERR(persistent_ref);
+
+found:
+	ret = key_task_permission(persistent_ref, current_cred(), KEY_NEED_LINK);
+	if (ret == 0) {
+		persistent = key_ref_to_ptr(persistent_ref);
+		ret = key_link(key_ref_to_ptr(dest_ref), persistent);
+		if (ret == 0) {
+			key_set_timeout(persistent, persistent_keyring_expiry);
+			ret = persistent->serial;		
+		}
+	}
+
+	key_ref_put(persistent_ref);
+	return ret;
+}
+
+/*
+ * Get the persistent keyring for a specific UID and link it to the nominated
+ * keyring.
+ */
+long keyctl_get_persistent(uid_t _uid, key_serial_t destid)
+{
+	struct user_namespace *ns = current_user_ns();
+	key_ref_t dest_ref;
+	kuid_t uid;
+	long ret;
+
+	/* -1 indicates the current user */
+	if (_uid == (uid_t)-1) {
+		uid = current_uid();
+	} else {
+		uid = make_kuid(ns, _uid);
+		if (!uid_valid(uid))
+			return -EINVAL;
+
+		/* You can only see your own persistent cache if you're not
+		 * sufficiently privileged.
+		 */
+		if (!uid_eq(uid, current_uid()) &&
+		    !uid_eq(uid, current_euid()) &&
+		    !ns_capable(ns, CAP_SETUID))
+			return -EPERM;
+	}
+
+	/* There must be a destination keyring */
+	dest_ref = lookup_user_key(destid, KEY_LOOKUP_CREATE, KEY_NEED_WRITE);
+	if (IS_ERR(dest_ref))
+		return PTR_ERR(dest_ref);
+	if (key_ref_to_ptr(dest_ref)->type != &key_type_keyring) {
+		ret = -ENOTDIR;
+		goto out_put_dest;
+	}
+
+	ret = key_get_persistent(ns, uid, dest_ref);
+
+out_put_dest:
+	key_ref_put(dest_ref);
+	return ret;
+}

security/keys/proc.c

@@ -0,0 +1,360 @@
+/* procfs files for key database enumeration
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <asm/errno.h>
+#include "internal.h"
+
+#ifdef CONFIG_KEYS_DEBUG_PROC_KEYS
+static int proc_keys_open(struct inode *inode, struct file *file);
+static void *proc_keys_start(struct seq_file *p, loff_t *_pos);
+static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos);
+static void proc_keys_stop(struct seq_file *p, void *v);
+static int proc_keys_show(struct seq_file *m, void *v);
+
+static const struct seq_operations proc_keys_ops = {
+	.start	= proc_keys_start,
+	.next	= proc_keys_next,
+	.stop	= proc_keys_stop,
+	.show	= proc_keys_show,
+};
+
+static const struct file_operations proc_keys_fops = {
+	.open		= proc_keys_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+#endif
+
+static int proc_key_users_open(struct inode *inode, struct file *file);
+static void *proc_key_users_start(struct seq_file *p, loff_t *_pos);
+static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos);
+static void proc_key_users_stop(struct seq_file *p, void *v);
+static int proc_key_users_show(struct seq_file *m, void *v);
+
+static const struct seq_operations proc_key_users_ops = {
+	.start	= proc_key_users_start,
+	.next	= proc_key_users_next,
+	.stop	= proc_key_users_stop,
+	.show	= proc_key_users_show,
+};
+
+static const struct file_operations proc_key_users_fops = {
+	.open		= proc_key_users_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/*
+ * Declare the /proc files.
+ */
+static int __init key_proc_init(void)
+{
+	struct proc_dir_entry *p;
+
+#ifdef CONFIG_KEYS_DEBUG_PROC_KEYS
+	p = proc_create("keys", 0, NULL, &proc_keys_fops);
+	if (!p)
+		panic("Cannot create /proc/keys\n");
+#endif
+
+	p = proc_create("key-users", 0, NULL, &proc_key_users_fops);
+	if (!p)
+		panic("Cannot create /proc/key-users\n");
+
+	return 0;
+}
+
+__initcall(key_proc_init);
+
+/*
+ * Implement "/proc/keys" to provide a list of the keys on the system that
+ * grant View permission to the caller.
+ */
+#ifdef CONFIG_KEYS_DEBUG_PROC_KEYS
+
+static struct rb_node *key_serial_next(struct seq_file *p, struct rb_node *n)
+{
+	struct user_namespace *user_ns = seq_user_ns(p);
+
+	n = rb_next(n);
+	while (n) {
+		struct key *key = rb_entry(n, struct key, serial_node);
+		if (kuid_has_mapping(user_ns, key->user->uid))
+			break;
+		n = rb_next(n);
+	}
+	return n;
+}
+
+static int proc_keys_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &proc_keys_ops);
+}
+
+static struct key *find_ge_key(struct seq_file *p, key_serial_t id)
+{
+	struct user_namespace *user_ns = seq_user_ns(p);
+	struct rb_node *n = key_serial_tree.rb_node;
+	struct key *minkey = NULL;
+
+	while (n) {
+		struct key *key = rb_entry(n, struct key, serial_node);
+		if (id < key->serial) {
+			if (!minkey || minkey->serial > key->serial)
+				minkey = key;
+			n = n->rb_left;
+		} else if (id > key->serial) {
+			n = n->rb_right;
+		} else {
+			minkey = key;
+			break;
+		}
+		key = NULL;
+	}
+
+	if (!minkey)
+		return NULL;
+
+	for (;;) {
+		if (kuid_has_mapping(user_ns, minkey->user->uid))
+			return minkey;
+		n = rb_next(&minkey->serial_node);
+		if (!n)
+			return NULL;
+		minkey = rb_entry(n, struct key, serial_node);
+	}
+}
+
+static void *proc_keys_start(struct seq_file *p, loff_t *_pos)
+	__acquires(key_serial_lock)
+{
+	key_serial_t pos = *_pos;
+	struct key *key;
+
+	spin_lock(&key_serial_lock);
+
+	if (*_pos > INT_MAX)
+		return NULL;
+	key = find_ge_key(p, pos);
+	if (!key)
+		return NULL;
+	*_pos = key->serial;
+	return &key->serial_node;
+}
+
+static inline key_serial_t key_node_serial(struct rb_node *n)
+{
+	struct key *key = rb_entry(n, struct key, serial_node);
+	return key->serial;
+}
+
+static void *proc_keys_next(struct seq_file *p, void *v, loff_t *_pos)
+{
+	struct rb_node *n;
+
+	n = key_serial_next(p, v);
+	if (n)
+		*_pos = key_node_serial(n);
+	return n;
+}
+
+static void proc_keys_stop(struct seq_file *p, void *v)
+	__releases(key_serial_lock)
+{
+	spin_unlock(&key_serial_lock);
+}
+
+static int proc_keys_show(struct seq_file *m, void *v)
+{
+	struct rb_node *_p = v;
+	struct key *key = rb_entry(_p, struct key, serial_node);
+	struct timespec now;
+	unsigned long timo;
+	key_ref_t key_ref, skey_ref;
+	char xbuf[12];
+	int rc;
+
+	struct keyring_search_context ctx = {
+		.index_key.type		= key->type,
+		.index_key.description	= key->description,
+		.cred			= current_cred(),
+		.match_data.cmp		= lookup_user_key_possessed,
+		.match_data.raw_data	= key,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_NO_STATE_CHECK,
+	};
+
+	key_ref = make_key_ref(key, 0);
+
+	/* determine if the key is possessed by this process (a test we can
+	 * skip if the key does not indicate the possessor can view it
+	 */
+	if (key->perm & KEY_POS_VIEW) {
+		skey_ref = search_my_process_keyrings(&ctx);
+		if (!IS_ERR(skey_ref)) {
+			key_ref_put(skey_ref);
+			key_ref = make_key_ref(key, 1);
+		}
+	}
+
+	/* check whether the current task is allowed to view the key (assuming
+	 * non-possession)
+	 * - the caller holds a spinlock, and thus the RCU read lock, making our
+	 *   access to __current_cred() safe
+	 */
+	rc = key_task_permission(key_ref, ctx.cred, KEY_NEED_VIEW);
+	if (rc < 0)
+		return 0;
+
+	now = current_kernel_time();
+
+	rcu_read_lock();
+
+	/* come up with a suitable timeout value */
+	if (key->expiry == 0) {
+		memcpy(xbuf, "perm", 5);
+	} else if (now.tv_sec >= key->expiry) {
+		memcpy(xbuf, "expd", 5);
+	} else {
+		timo = key->expiry - now.tv_sec;
+
+		if (timo < 60)
+			sprintf(xbuf, "%lus", timo);
+		else if (timo < 60*60)
+			sprintf(xbuf, "%lum", timo / 60);
+		else if (timo < 60*60*24)
+			sprintf(xbuf, "%luh", timo / (60*60));
+		else if (timo < 60*60*24*7)
+			sprintf(xbuf, "%lud", timo / (60*60*24));
+		else
+			sprintf(xbuf, "%luw", timo / (60*60*24*7));
+	}
+
+#define showflag(KEY, LETTER, FLAG) \
+	(test_bit(FLAG,	&(KEY)->flags) ? LETTER : '-')
+
+	seq_printf(m, "%08x %c%c%c%c%c%c%c %5d %4s %08x %5d %5d %-9.9s ",
+		   key->serial,
+		   showflag(key, 'I', KEY_FLAG_INSTANTIATED),
+		   showflag(key, 'R', KEY_FLAG_REVOKED),
+		   showflag(key, 'D', KEY_FLAG_DEAD),
+		   showflag(key, 'Q', KEY_FLAG_IN_QUOTA),
+		   showflag(key, 'U', KEY_FLAG_USER_CONSTRUCT),
+		   showflag(key, 'N', KEY_FLAG_NEGATIVE),
+		   showflag(key, 'i', KEY_FLAG_INVALIDATED),
+		   atomic_read(&key->usage),
+		   xbuf,
+		   key->perm,
+		   from_kuid_munged(seq_user_ns(m), key->uid),
+		   from_kgid_munged(seq_user_ns(m), key->gid),
+		   key->type->name);
+
+#undef showflag
+
+	if (key->type->describe)
+		key->type->describe(key, m);
+	seq_putc(m, '\n');
+
+	rcu_read_unlock();
+	return 0;
+}
+
+#endif /* CONFIG_KEYS_DEBUG_PROC_KEYS */
+
+static struct rb_node *__key_user_next(struct user_namespace *user_ns, struct rb_node *n)
+{
+	while (n) {
+		struct key_user *user = rb_entry(n, struct key_user, node);
+		if (kuid_has_mapping(user_ns, user->uid))
+			break;
+		n = rb_next(n);
+	}
+	return n;
+}
+
+static struct rb_node *key_user_next(struct user_namespace *user_ns, struct rb_node *n)
+{
+	return __key_user_next(user_ns, rb_next(n));
+}
+
+static struct rb_node *key_user_first(struct user_namespace *user_ns, struct rb_root *r)
+{
+	struct rb_node *n = rb_first(r);
+	return __key_user_next(user_ns, n);
+}
+
+/*
+ * Implement "/proc/key-users" to provides a list of the key users and their
+ * quotas.
+ */
+static int proc_key_users_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &proc_key_users_ops);
+}
+
+static void *proc_key_users_start(struct seq_file *p, loff_t *_pos)
+	__acquires(key_user_lock)
+{
+	struct rb_node *_p;
+	loff_t pos = *_pos;
+
+	spin_lock(&key_user_lock);
+
+	_p = key_user_first(seq_user_ns(p), &key_user_tree);
+	while (pos > 0 && _p) {
+		pos--;
+		_p = key_user_next(seq_user_ns(p), _p);
+	}
+
+	return _p;
+}
+
+static void *proc_key_users_next(struct seq_file *p, void *v, loff_t *_pos)
+{
+	(*_pos)++;
+	return key_user_next(seq_user_ns(p), (struct rb_node *)v);
+}
+
+static void proc_key_users_stop(struct seq_file *p, void *v)
+	__releases(key_user_lock)
+{
+	spin_unlock(&key_user_lock);
+}
+
+static int proc_key_users_show(struct seq_file *m, void *v)
+{
+	struct rb_node *_p = v;
+	struct key_user *user = rb_entry(_p, struct key_user, node);
+	unsigned maxkeys = uid_eq(user->uid, GLOBAL_ROOT_UID) ?
+		key_quota_root_maxkeys : key_quota_maxkeys;
+	unsigned maxbytes = uid_eq(user->uid, GLOBAL_ROOT_UID) ?
+		key_quota_root_maxbytes : key_quota_maxbytes;
+
+	seq_printf(m, "%5u: %5d %d/%d %d/%d %d/%d\n",
+		   from_kuid_munged(seq_user_ns(m), user->uid),
+		   atomic_read(&user->usage),
+		   atomic_read(&user->nkeys),
+		   atomic_read(&user->nikeys),
+		   user->qnkeys,
+		   maxkeys,
+		   user->qnbytes,
+		   maxbytes);
+
+	return 0;
+}

security/keys/process_keys.c

@@ -0,0 +1,870 @@
+/* Manage a process's keyrings
+ *
+ * Copyright (C) 2004-2005, 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/keyctl.h>
+#include <linux/fs.h>
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/security.h>
+#include <linux/user_namespace.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+/* Session keyring create vs join semaphore */
+static DEFINE_MUTEX(key_session_mutex);
+
+/* User keyring creation semaphore */
+static DEFINE_MUTEX(key_user_keyring_mutex);
+
+/* The root user's tracking struct */
+struct key_user root_key_user = {
+	.usage		= ATOMIC_INIT(3),
+	.cons_lock	= __MUTEX_INITIALIZER(root_key_user.cons_lock),
+	.lock		= __SPIN_LOCK_UNLOCKED(root_key_user.lock),
+	.nkeys		= ATOMIC_INIT(2),
+	.nikeys		= ATOMIC_INIT(2),
+	.uid		= GLOBAL_ROOT_UID,
+};
+
+/*
+ * Install the user and user session keyrings for the current process's UID.
+ */
+int install_user_keyrings(void)
+{
+	struct user_struct *user;
+	const struct cred *cred;
+	struct key *uid_keyring, *session_keyring;
+	key_perm_t user_keyring_perm;
+	char buf[20];
+	int ret;
+	uid_t uid;
+
+	user_keyring_perm = (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_ALL;
+	cred = current_cred();
+	user = cred->user;
+	uid = from_kuid(cred->user_ns, user->uid);
+
+	kenter("%p{%u}", user, uid);
+
+	if (user->uid_keyring && user->session_keyring) {
+		kleave(" = 0 [exist]");
+		return 0;
+	}
+
+	mutex_lock(&key_user_keyring_mutex);
+	ret = 0;
+
+	if (!user->uid_keyring) {
+		/* get the UID-specific keyring
+		 * - there may be one in existence already as it may have been
+		 *   pinned by a session, but the user_struct pointing to it
+		 *   may have been destroyed by setuid */
+		sprintf(buf, "_uid.%u", uid);
+
+		uid_keyring = find_keyring_by_name(buf, true);
+		if (IS_ERR(uid_keyring)) {
+			uid_keyring = keyring_alloc(buf, user->uid, INVALID_GID,
+						    cred, user_keyring_perm,
+						    KEY_ALLOC_IN_QUOTA, NULL);
+			if (IS_ERR(uid_keyring)) {
+				ret = PTR_ERR(uid_keyring);
+				goto error;
+			}
+		}
+
+		/* get a default session keyring (which might also exist
+		 * already) */
+		sprintf(buf, "_uid_ses.%u", uid);
+
+		session_keyring = find_keyring_by_name(buf, true);
+		if (IS_ERR(session_keyring)) {
+			session_keyring =
+				keyring_alloc(buf, user->uid, INVALID_GID,
+					      cred, user_keyring_perm,
+					      KEY_ALLOC_IN_QUOTA, NULL);
+			if (IS_ERR(session_keyring)) {
+				ret = PTR_ERR(session_keyring);
+				goto error_release;
+			}
+
+			/* we install a link from the user session keyring to
+			 * the user keyring */
+			ret = key_link(session_keyring, uid_keyring);
+			if (ret < 0)
+				goto error_release_both;
+		}
+
+		/* install the keyrings */
+		user->uid_keyring = uid_keyring;
+		user->session_keyring = session_keyring;
+	}
+
+	mutex_unlock(&key_user_keyring_mutex);
+	kleave(" = 0");
+	return 0;
+
+error_release_both:
+	key_put(session_keyring);
+error_release:
+	key_put(uid_keyring);
+error:
+	mutex_unlock(&key_user_keyring_mutex);
+	kleave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Install a fresh thread keyring directly to new credentials.  This keyring is
+ * allowed to overrun the quota.
+ */
+int install_thread_keyring_to_cred(struct cred *new)
+{
+	struct key *keyring;
+
+	keyring = keyring_alloc("_tid", new->uid, new->gid, new,
+				KEY_POS_ALL | KEY_USR_VIEW,
+				KEY_ALLOC_QUOTA_OVERRUN, NULL);
+	if (IS_ERR(keyring))
+		return PTR_ERR(keyring);
+
+	new->thread_keyring = keyring;
+	return 0;
+}
+
+/*
+ * Install a fresh thread keyring, discarding the old one.
+ */
+static int install_thread_keyring(void)
+{
+	struct cred *new;
+	int ret;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	BUG_ON(new->thread_keyring);
+
+	ret = install_thread_keyring_to_cred(new);
+	if (ret < 0) {
+		abort_creds(new);
+		return ret;
+	}
+
+	return commit_creds(new);
+}
+
+/*
+ * Install a process keyring directly to a credentials struct.
+ *
+ * Returns -EEXIST if there was already a process keyring, 0 if one installed,
+ * and other value on any other error
+ */
+int install_process_keyring_to_cred(struct cred *new)
+{
+	struct key *keyring;
+
+	if (new->process_keyring)
+		return -EEXIST;
+
+	keyring = keyring_alloc("_pid", new->uid, new->gid, new,
+				KEY_POS_ALL | KEY_USR_VIEW,
+				KEY_ALLOC_QUOTA_OVERRUN, NULL);
+	if (IS_ERR(keyring))
+		return PTR_ERR(keyring);
+
+	new->process_keyring = keyring;
+	return 0;
+}
+
+/*
+ * Make sure a process keyring is installed for the current process.  The
+ * existing process keyring is not replaced.
+ *
+ * Returns 0 if there is a process keyring by the end of this function, some
+ * error otherwise.
+ */
+static int install_process_keyring(void)
+{
+	struct cred *new;
+	int ret;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	ret = install_process_keyring_to_cred(new);
+	if (ret < 0) {
+		abort_creds(new);
+		return ret != -EEXIST ? ret : 0;
+	}
+
+	return commit_creds(new);
+}
+
+/*
+ * Install a session keyring directly to a credentials struct.
+ */
+int install_session_keyring_to_cred(struct cred *cred, struct key *keyring)
+{
+	unsigned long flags;
+	struct key *old;
+
+	might_sleep();
+
+	/* create an empty session keyring */
+	if (!keyring) {
+		flags = KEY_ALLOC_QUOTA_OVERRUN;
+		if (cred->session_keyring)
+			flags = KEY_ALLOC_IN_QUOTA;
+
+		keyring = keyring_alloc("_ses", cred->uid, cred->gid, cred,
+					KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ,
+					flags, NULL);
+		if (IS_ERR(keyring))
+			return PTR_ERR(keyring);
+	} else {
+		__key_get(keyring);
+	}
+
+	/* install the keyring */
+	old = cred->session_keyring;
+	rcu_assign_pointer(cred->session_keyring, keyring);
+
+	if (old)
+		key_put(old);
+
+	return 0;
+}
+
+/*
+ * Install a session keyring, discarding the old one.  If a keyring is not
+ * supplied, an empty one is invented.
+ */
+static int install_session_keyring(struct key *keyring)
+{
+	struct cred *new;
+	int ret;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	ret = install_session_keyring_to_cred(new, keyring);
+	if (ret < 0) {
+		abort_creds(new);
+		return ret;
+	}
+
+	return commit_creds(new);
+}
+
+/*
+ * Handle the fsuid changing.
+ */
+void key_fsuid_changed(struct task_struct *tsk)
+{
+	/* update the ownership of the thread keyring */
+	BUG_ON(!tsk->cred);
+	if (tsk->cred->thread_keyring) {
+		down_write(&tsk->cred->thread_keyring->sem);
+		tsk->cred->thread_keyring->uid = tsk->cred->fsuid;
+		up_write(&tsk->cred->thread_keyring->sem);
+	}
+}
+
+/*
+ * Handle the fsgid changing.
+ */
+void key_fsgid_changed(struct task_struct *tsk)
+{
+	/* update the ownership of the thread keyring */
+	BUG_ON(!tsk->cred);
+	if (tsk->cred->thread_keyring) {
+		down_write(&tsk->cred->thread_keyring->sem);
+		tsk->cred->thread_keyring->gid = tsk->cred->fsgid;
+		up_write(&tsk->cred->thread_keyring->sem);
+	}
+}
+
+/*
+ * Search the process keyrings attached to the supplied cred for the first
+ * matching key.
+ *
+ * The search criteria are the type and the match function.  The description is
+ * given to the match function as a parameter, but doesn't otherwise influence
+ * the search.  Typically the match function will compare the description
+ * parameter to the key's description.
+ *
+ * This can only search keyrings that grant Search permission to the supplied
+ * credentials.  Keyrings linked to searched keyrings will also be searched if
+ * they grant Search permission too.  Keys can only be found if they grant
+ * Search permission to the credentials.
+ *
+ * Returns a pointer to the key with the key usage count incremented if
+ * successful, -EAGAIN if we didn't find any matching key or -ENOKEY if we only
+ * matched negative keys.
+ *
+ * In the case of a successful return, the possession attribute is set on the
+ * returned key reference.
+ */
+key_ref_t search_my_process_keyrings(struct keyring_search_context *ctx)
+{
+	key_ref_t key_ref, ret, err;
+
+	/* we want to return -EAGAIN or -ENOKEY if any of the keyrings were
+	 * searchable, but we failed to find a key or we found a negative key;
+	 * otherwise we want to return a sample error (probably -EACCES) if
+	 * none of the keyrings were searchable
+	 *
+	 * in terms of priority: success > -ENOKEY > -EAGAIN > other error
+	 */
+	key_ref = NULL;
+	ret = NULL;
+	err = ERR_PTR(-EAGAIN);
+
+	/* search the thread keyring first */
+	if (ctx->cred->thread_keyring) {
+		key_ref = keyring_search_aux(
+			make_key_ref(ctx->cred->thread_keyring, 1), ctx);
+		if (!IS_ERR(key_ref))
+			goto found;
+
+		switch (PTR_ERR(key_ref)) {
+		case -EAGAIN: /* no key */
+		case -ENOKEY: /* negative key */
+			ret = key_ref;
+			break;
+		default:
+			err = key_ref;
+			break;
+		}
+	}
+
+	/* search the process keyring second */
+	if (ctx->cred->process_keyring) {
+		key_ref = keyring_search_aux(
+			make_key_ref(ctx->cred->process_keyring, 1), ctx);
+		if (!IS_ERR(key_ref))
+			goto found;
+
+		switch (PTR_ERR(key_ref)) {
+		case -EAGAIN: /* no key */
+			if (ret)
+				break;
+		case -ENOKEY: /* negative key */
+			ret = key_ref;
+			break;
+		default:
+			err = key_ref;
+			break;
+		}
+	}
+
+	/* search the session keyring */
+	if (ctx->cred->session_keyring) {
+		rcu_read_lock();
+		key_ref = keyring_search_aux(
+			make_key_ref(rcu_dereference(ctx->cred->session_keyring), 1),
+			ctx);
+		rcu_read_unlock();
+
+		if (!IS_ERR(key_ref))
+			goto found;
+
+		switch (PTR_ERR(key_ref)) {
+		case -EAGAIN: /* no key */
+			if (ret)
+				break;
+		case -ENOKEY: /* negative key */
+			ret = key_ref;
+			break;
+		default:
+			err = key_ref;
+			break;
+		}
+	}
+	/* or search the user-session keyring */
+	else if (ctx->cred->user->session_keyring) {
+		key_ref = keyring_search_aux(
+			make_key_ref(ctx->cred->user->session_keyring, 1),
+			ctx);
+		if (!IS_ERR(key_ref))
+			goto found;
+
+		switch (PTR_ERR(key_ref)) {
+		case -EAGAIN: /* no key */
+			if (ret)
+				break;
+		case -ENOKEY: /* negative key */
+			ret = key_ref;
+			break;
+		default:
+			err = key_ref;
+			break;
+		}
+	}
+
+	/* no key - decide on the error we're going to go for */
+	key_ref = ret ? ret : err;
+
+found:
+	return key_ref;
+}
+
+/*
+ * Search the process keyrings attached to the supplied cred for the first
+ * matching key in the manner of search_my_process_keyrings(), but also search
+ * the keys attached to the assumed authorisation key using its credentials if
+ * one is available.
+ *
+ * Return same as search_my_process_keyrings().
+ */
+key_ref_t search_process_keyrings(struct keyring_search_context *ctx)
+{
+	struct request_key_auth *rka;
+	key_ref_t key_ref, ret = ERR_PTR(-EACCES), err;
+
+	might_sleep();
+
+	key_ref = search_my_process_keyrings(ctx);
+	if (!IS_ERR(key_ref))
+		goto found;
+	err = key_ref;
+
+	/* if this process has an instantiation authorisation key, then we also
+	 * search the keyrings of the process mentioned there
+	 * - we don't permit access to request_key auth keys via this method
+	 */
+	if (ctx->cred->request_key_auth &&
+	    ctx->cred == current_cred() &&
+	    ctx->index_key.type != &key_type_request_key_auth
+	    ) {
+		const struct cred *cred = ctx->cred;
+
+		/* defend against the auth key being revoked */
+		down_read(&cred->request_key_auth->sem);
+
+		if (key_validate(ctx->cred->request_key_auth) == 0) {
+			rka = ctx->cred->request_key_auth->payload.data;
+
+			ctx->cred = rka->cred;
+			key_ref = search_process_keyrings(ctx);
+			ctx->cred = cred;
+
+			up_read(&cred->request_key_auth->sem);
+
+			if (!IS_ERR(key_ref))
+				goto found;
+
+			ret = key_ref;
+		} else {
+			up_read(&cred->request_key_auth->sem);
+		}
+	}
+
+	/* no key - decide on the error we're going to go for */
+	if (err == ERR_PTR(-ENOKEY) || ret == ERR_PTR(-ENOKEY))
+		key_ref = ERR_PTR(-ENOKEY);
+	else if (err == ERR_PTR(-EACCES))
+		key_ref = ret;
+	else
+		key_ref = err;
+
+found:
+	return key_ref;
+}
+
+/*
+ * See if the key we're looking at is the target key.
+ */
+bool lookup_user_key_possessed(const struct key *key,
+			       const struct key_match_data *match_data)
+{
+	return key == match_data->raw_data;
+}
+
+/*
+ * Look up a key ID given us by userspace with a given permissions mask to get
+ * the key it refers to.
+ *
+ * Flags can be passed to request that special keyrings be created if referred
+ * to directly, to permit partially constructed keys to be found and to skip
+ * validity and permission checks on the found key.
+ *
+ * Returns a pointer to the key with an incremented usage count if successful;
+ * -EINVAL if the key ID is invalid; -ENOKEY if the key ID does not correspond
+ * to a key or the best found key was a negative key; -EKEYREVOKED or
+ * -EKEYEXPIRED if the best found key was revoked or expired; -EACCES if the
+ * found key doesn't grant the requested permit or the LSM denied access to it;
+ * or -ENOMEM if a special keyring couldn't be created.
+ *
+ * In the case of a successful return, the possession attribute is set on the
+ * returned key reference.
+ */
+key_ref_t lookup_user_key(key_serial_t id, unsigned long lflags,
+			  key_perm_t perm)
+{
+	struct keyring_search_context ctx = {
+		.match_data.cmp		= lookup_user_key_possessed,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_NO_STATE_CHECK,
+	};
+	struct request_key_auth *rka;
+	struct key *key;
+	key_ref_t key_ref, skey_ref;
+	int ret;
+
+try_again:
+	ctx.cred = get_current_cred();
+	key_ref = ERR_PTR(-ENOKEY);
+
+	switch (id) {
+	case KEY_SPEC_THREAD_KEYRING:
+		if (!ctx.cred->thread_keyring) {
+			if (!(lflags & KEY_LOOKUP_CREATE))
+				goto error;
+
+			ret = install_thread_keyring();
+			if (ret < 0) {
+				key_ref = ERR_PTR(ret);
+				goto error;
+			}
+			goto reget_creds;
+		}
+
+		key = ctx.cred->thread_keyring;
+		__key_get(key);
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_PROCESS_KEYRING:
+		if (!ctx.cred->process_keyring) {
+			if (!(lflags & KEY_LOOKUP_CREATE))
+				goto error;
+
+			ret = install_process_keyring();
+			if (ret < 0) {
+				key_ref = ERR_PTR(ret);
+				goto error;
+			}
+			goto reget_creds;
+		}
+
+		key = ctx.cred->process_keyring;
+		__key_get(key);
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_SESSION_KEYRING:
+		if (!ctx.cred->session_keyring) {
+			/* always install a session keyring upon access if one
+			 * doesn't exist yet */
+			ret = install_user_keyrings();
+			if (ret < 0)
+				goto error;
+			if (lflags & KEY_LOOKUP_CREATE)
+				ret = join_session_keyring(NULL);
+			else
+				ret = install_session_keyring(
+					ctx.cred->user->session_keyring);
+
+			if (ret < 0)
+				goto error;
+			goto reget_creds;
+		} else if (ctx.cred->session_keyring ==
+			   ctx.cred->user->session_keyring &&
+			   lflags & KEY_LOOKUP_CREATE) {
+			ret = join_session_keyring(NULL);
+			if (ret < 0)
+				goto error;
+			goto reget_creds;
+		}
+
+		rcu_read_lock();
+		key = rcu_dereference(ctx.cred->session_keyring);
+		__key_get(key);
+		rcu_read_unlock();
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_USER_KEYRING:
+		if (!ctx.cred->user->uid_keyring) {
+			ret = install_user_keyrings();
+			if (ret < 0)
+				goto error;
+		}
+
+		key = ctx.cred->user->uid_keyring;
+		__key_get(key);
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_USER_SESSION_KEYRING:
+		if (!ctx.cred->user->session_keyring) {
+			ret = install_user_keyrings();
+			if (ret < 0)
+				goto error;
+		}
+
+		key = ctx.cred->user->session_keyring;
+		__key_get(key);
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_GROUP_KEYRING:
+		/* group keyrings are not yet supported */
+		key_ref = ERR_PTR(-EINVAL);
+		goto error;
+
+	case KEY_SPEC_REQKEY_AUTH_KEY:
+		key = ctx.cred->request_key_auth;
+		if (!key)
+			goto error;
+
+		__key_get(key);
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	case KEY_SPEC_REQUESTOR_KEYRING:
+		if (!ctx.cred->request_key_auth)
+			goto error;
+
+		down_read(&ctx.cred->request_key_auth->sem);
+		if (test_bit(KEY_FLAG_REVOKED,
+			     &ctx.cred->request_key_auth->flags)) {
+			key_ref = ERR_PTR(-EKEYREVOKED);
+			key = NULL;
+		} else {
+			rka = ctx.cred->request_key_auth->payload.data;
+			key = rka->dest_keyring;
+			__key_get(key);
+		}
+		up_read(&ctx.cred->request_key_auth->sem);
+		if (!key)
+			goto error;
+		key_ref = make_key_ref(key, 1);
+		break;
+
+	default:
+		key_ref = ERR_PTR(-EINVAL);
+		if (id < 1)
+			goto error;
+
+		key = key_lookup(id);
+		if (IS_ERR(key)) {
+			key_ref = ERR_CAST(key);
+			goto error;
+		}
+
+		key_ref = make_key_ref(key, 0);
+
+		/* check to see if we possess the key */
+		ctx.index_key.type		= key->type;
+		ctx.index_key.description	= key->description;
+		ctx.index_key.desc_len		= strlen(key->description);
+		ctx.match_data.raw_data		= key;
+		kdebug("check possessed");
+		skey_ref = search_process_keyrings(&ctx);
+		kdebug("possessed=%p", skey_ref);
+
+		if (!IS_ERR(skey_ref)) {
+			key_put(key);
+			key_ref = skey_ref;
+		}
+
+		break;
+	}
+
+	/* unlink does not use the nominated key in any way, so can skip all
+	 * the permission checks as it is only concerned with the keyring */
+	if (lflags & KEY_LOOKUP_FOR_UNLINK) {
+		ret = 0;
+		goto error;
+	}
+
+	if (!(lflags & KEY_LOOKUP_PARTIAL)) {
+		ret = wait_for_key_construction(key, true);
+		switch (ret) {
+		case -ERESTARTSYS:
+			goto invalid_key;
+		default:
+			if (perm)
+				goto invalid_key;
+		case 0:
+			break;
+		}
+	} else if (perm) {
+		ret = key_validate(key);
+		if (ret < 0)
+			goto invalid_key;
+	}
+
+	ret = -EIO;
+	if (!(lflags & KEY_LOOKUP_PARTIAL) &&
+	    !test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
+		goto invalid_key;
+
+	/* check the permissions */
+	ret = key_task_permission(key_ref, ctx.cred, perm);
+	if (ret < 0)
+		goto invalid_key;
+
+	key->last_used_at = current_kernel_time().tv_sec;
+
+error:
+	put_cred(ctx.cred);
+	return key_ref;
+
+invalid_key:
+	key_ref_put(key_ref);
+	key_ref = ERR_PTR(ret);
+	goto error;
+
+	/* if we attempted to install a keyring, then it may have caused new
+	 * creds to be installed */
+reget_creds:
+	put_cred(ctx.cred);
+	goto try_again;
+}
+
+/*
+ * Join the named keyring as the session keyring if possible else attempt to
+ * create a new one of that name and join that.
+ *
+ * If the name is NULL, an empty anonymous keyring will be installed as the
+ * session keyring.
+ *
+ * Named session keyrings are joined with a semaphore held to prevent the
+ * keyrings from going away whilst the attempt is made to going them and also
+ * to prevent a race in creating compatible session keyrings.
+ */
+long join_session_keyring(const char *name)
+{
+	const struct cred *old;
+	struct cred *new;
+	struct key *keyring;
+	long ret, serial;
+
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+	old = current_cred();
+
+	/* if no name is provided, install an anonymous keyring */
+	if (!name) {
+		ret = install_session_keyring_to_cred(new, NULL);
+		if (ret < 0)
+			goto error;
+
+		serial = new->session_keyring->serial;
+		ret = commit_creds(new);
+		if (ret == 0)
+			ret = serial;
+		goto okay;
+	}
+
+	/* allow the user to join or create a named keyring */
+	mutex_lock(&key_session_mutex);
+
+	/* look for an existing keyring of this name */
+	keyring = find_keyring_by_name(name, false);
+	if (PTR_ERR(keyring) == -ENOKEY) {
+		/* not found - try and create a new one */
+		keyring = keyring_alloc(
+			name, old->uid, old->gid, old,
+			KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_LINK,
+			KEY_ALLOC_IN_QUOTA, NULL);
+		if (IS_ERR(keyring)) {
+			ret = PTR_ERR(keyring);
+			goto error2;
+		}
+	} else if (IS_ERR(keyring)) {
+		ret = PTR_ERR(keyring);
+		goto error2;
+	} else if (keyring == new->session_keyring) {
+		ret = 0;
+		goto error2;
+	}
+
+	/* we've got a keyring - now to install it */
+	ret = install_session_keyring_to_cred(new, keyring);
+	if (ret < 0)
+		goto error2;
+
+	commit_creds(new);
+	mutex_unlock(&key_session_mutex);
+
+	ret = keyring->serial;
+	key_put(keyring);
+okay:
+	return ret;
+
+error2:
+	mutex_unlock(&key_session_mutex);
+error:
+	abort_creds(new);
+	return ret;
+}
+
+/*
+ * Replace a process's session keyring on behalf of one of its children when
+ * the target  process is about to resume userspace execution.
+ */
+void key_change_session_keyring(struct callback_head *twork)
+{
+	const struct cred *old = current_cred();
+	struct cred *new = container_of(twork, struct cred, rcu);
+
+	if (unlikely(current->flags & PF_EXITING)) {
+		put_cred(new);
+		return;
+	}
+
+	new->  uid	= old->  uid;
+	new-> euid	= old-> euid;
+	new-> suid	= old-> suid;
+	new->fsuid	= old->fsuid;
+	new->  gid	= old->  gid;
+	new-> egid	= old-> egid;
+	new-> sgid	= old-> sgid;
+	new->fsgid	= old->fsgid;
+	new->user	= get_uid(old->user);
+	new->user_ns	= get_user_ns(old->user_ns);
+	new->group_info	= get_group_info(old->group_info);
+
+	new->securebits	= old->securebits;
+	new->cap_inheritable	= old->cap_inheritable;
+	new->cap_permitted	= old->cap_permitted;
+	new->cap_effective	= old->cap_effective;
+	new->cap_bset		= old->cap_bset;
+
+	new->jit_keyring	= old->jit_keyring;
+	new->thread_keyring	= key_get(old->thread_keyring);
+	new->process_keyring	= key_get(old->process_keyring);
+
+	security_transfer_creds(new, old);
+
+	commit_creds(new);
+}
+
+/*
+ * Make sure that root's user and user-session keyrings exist.
+ */
+static int __init init_root_keyring(void)
+{
+	return install_user_keyrings();
+}
+
+late_initcall(init_root_keyring);

security/keys/request_key.c

@@ -0,0 +1,722 @@
+/* Request a key from userspace
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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.
+ *
+ * See Documentation/security/keys-request-key.txt
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/kmod.h>
+#include <linux/err.h>
+#include <linux/keyctl.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+#define key_negative_timeout	60	/* default timeout on a negative key's existence */
+
+/**
+ * complete_request_key - Complete the construction of a key.
+ * @cons: The key construction record.
+ * @error: The success or failute of the construction.
+ *
+ * Complete the attempt to construct a key.  The key will be negated
+ * if an error is indicated.  The authorisation key will be revoked
+ * unconditionally.
+ */
+void complete_request_key(struct key_construction *cons, int error)
+{
+	kenter("{%d,%d},%d", cons->key->serial, cons->authkey->serial, error);
+
+	if (error < 0)
+		key_negate_and_link(cons->key, key_negative_timeout, NULL,
+				    cons->authkey);
+	else
+		key_revoke(cons->authkey);
+
+	key_put(cons->key);
+	key_put(cons->authkey);
+	kfree(cons);
+}
+EXPORT_SYMBOL(complete_request_key);
+
+/*
+ * Initialise a usermode helper that is going to have a specific session
+ * keyring.
+ *
+ * This is called in context of freshly forked kthread before kernel_execve(),
+ * so we can simply install the desired session_keyring at this point.
+ */
+static int umh_keys_init(struct subprocess_info *info, struct cred *cred)
+{
+	struct key *keyring = info->data;
+
+	return install_session_keyring_to_cred(cred, keyring);
+}
+
+/*
+ * Clean up a usermode helper with session keyring.
+ */
+static void umh_keys_cleanup(struct subprocess_info *info)
+{
+	struct key *keyring = info->data;
+	key_put(keyring);
+}
+
+/*
+ * Call a usermode helper with a specific session keyring.
+ */
+static int call_usermodehelper_keys(char *path, char **argv, char **envp,
+					struct key *session_keyring, int wait)
+{
+	struct subprocess_info *info;
+
+	info = call_usermodehelper_setup(path, argv, envp, GFP_KERNEL,
+					  umh_keys_init, umh_keys_cleanup,
+					  session_keyring);
+	if (!info)
+		return -ENOMEM;
+
+	key_get(session_keyring);
+	return call_usermodehelper_exec(info, wait);
+}
+
+/*
+ * Request userspace finish the construction of a key
+ * - execute "/sbin/request-key <op> <key> <uid> <gid> <keyring> <keyring> <keyring>"
+ */
+static int call_sbin_request_key(struct key_construction *cons,
+				 const char *op,
+				 void *aux)
+{
+	const struct cred *cred = current_cred();
+	key_serial_t prkey, sskey;
+	struct key *key = cons->key, *authkey = cons->authkey, *keyring,
+		*session;
+	char *argv[9], *envp[3], uid_str[12], gid_str[12];
+	char key_str[12], keyring_str[3][12];
+	char desc[20];
+	int ret, i;
+
+	kenter("{%d},{%d},%s", key->serial, authkey->serial, op);
+
+	ret = install_user_keyrings();
+	if (ret < 0)
+		goto error_alloc;
+
+	/* allocate a new session keyring */
+	sprintf(desc, "_req.%u", key->serial);
+
+	cred = get_current_cred();
+	keyring = keyring_alloc(desc, cred->fsuid, cred->fsgid, cred,
+				KEY_POS_ALL | KEY_USR_VIEW | KEY_USR_READ,
+				KEY_ALLOC_QUOTA_OVERRUN, NULL);
+	put_cred(cred);
+	if (IS_ERR(keyring)) {
+		ret = PTR_ERR(keyring);
+		goto error_alloc;
+	}
+
+	/* attach the auth key to the session keyring */
+	ret = key_link(keyring, authkey);
+	if (ret < 0)
+		goto error_link;
+
+	/* record the UID and GID */
+	sprintf(uid_str, "%d", from_kuid(&init_user_ns, cred->fsuid));
+	sprintf(gid_str, "%d", from_kgid(&init_user_ns, cred->fsgid));
+
+	/* we say which key is under construction */
+	sprintf(key_str, "%d", key->serial);
+
+	/* we specify the process's default keyrings */
+	sprintf(keyring_str[0], "%d",
+		cred->thread_keyring ? cred->thread_keyring->serial : 0);
+
+	prkey = 0;
+	if (cred->process_keyring)
+		prkey = cred->process_keyring->serial;
+	sprintf(keyring_str[1], "%d", prkey);
+
+	rcu_read_lock();
+	session = rcu_dereference(cred->session_keyring);
+	if (!session)
+		session = cred->user->session_keyring;
+	sskey = session->serial;
+	rcu_read_unlock();
+
+	sprintf(keyring_str[2], "%d", sskey);
+
+	/* set up a minimal environment */
+	i = 0;
+	envp[i++] = "HOME=/";
+	envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+	envp[i] = NULL;
+
+	/* set up the argument list */
+	i = 0;
+	argv[i++] = "/sbin/request-key";
+	argv[i++] = (char *) op;
+	argv[i++] = key_str;
+	argv[i++] = uid_str;
+	argv[i++] = gid_str;
+	argv[i++] = keyring_str[0];
+	argv[i++] = keyring_str[1];
+	argv[i++] = keyring_str[2];
+	argv[i] = NULL;
+
+	/* do it */
+	ret = call_usermodehelper_keys(argv[0], argv, envp, keyring,
+				       UMH_WAIT_PROC);
+	kdebug("usermode -> 0x%x", ret);
+	if (ret >= 0) {
+		/* ret is the exit/wait code */
+		if (test_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags) ||
+		    key_validate(key) < 0)
+			ret = -ENOKEY;
+		else
+			/* ignore any errors from userspace if the key was
+			 * instantiated */
+			ret = 0;
+	}
+
+error_link:
+	key_put(keyring);
+
+error_alloc:
+	complete_request_key(cons, ret);
+	kleave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Call out to userspace for key construction.
+ *
+ * Program failure is ignored in favour of key status.
+ */
+static int construct_key(struct key *key, const void *callout_info,
+			 size_t callout_len, void *aux,
+			 struct key *dest_keyring)
+{
+	struct key_construction *cons;
+	request_key_actor_t actor;
+	struct key *authkey;
+	int ret;
+
+	kenter("%d,%p,%zu,%p", key->serial, callout_info, callout_len, aux);
+
+	cons = kmalloc(sizeof(*cons), GFP_KERNEL);
+	if (!cons)
+		return -ENOMEM;
+
+	/* allocate an authorisation key */
+	authkey = request_key_auth_new(key, callout_info, callout_len,
+				       dest_keyring);
+	if (IS_ERR(authkey)) {
+		kfree(cons);
+		ret = PTR_ERR(authkey);
+		authkey = NULL;
+	} else {
+		cons->authkey = key_get(authkey);
+		cons->key = key_get(key);
+
+		/* make the call */
+		actor = call_sbin_request_key;
+		if (key->type->request_key)
+			actor = key->type->request_key;
+
+		ret = actor(cons, "create", aux);
+
+		/* check that the actor called complete_request_key() prior to
+		 * returning an error */
+		WARN_ON(ret < 0 &&
+			!test_bit(KEY_FLAG_REVOKED, &authkey->flags));
+		key_put(authkey);
+	}
+
+	kleave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * Get the appropriate destination keyring for the request.
+ *
+ * The keyring selected is returned with an extra reference upon it which the
+ * caller must release.
+ */
+static void construct_get_dest_keyring(struct key **_dest_keyring)
+{
+	struct request_key_auth *rka;
+	const struct cred *cred = current_cred();
+	struct key *dest_keyring = *_dest_keyring, *authkey;
+
+	kenter("%p", dest_keyring);
+
+	/* find the appropriate keyring */
+	if (dest_keyring) {
+		/* the caller supplied one */
+		key_get(dest_keyring);
+	} else {
+		/* use a default keyring; falling through the cases until we
+		 * find one that we actually have */
+		switch (cred->jit_keyring) {
+		case KEY_REQKEY_DEFL_DEFAULT:
+		case KEY_REQKEY_DEFL_REQUESTOR_KEYRING:
+			if (cred->request_key_auth) {
+				authkey = cred->request_key_auth;
+				down_read(&authkey->sem);
+				rka = authkey->payload.data;
+				if (!test_bit(KEY_FLAG_REVOKED,
+					      &authkey->flags))
+					dest_keyring =
+						key_get(rka->dest_keyring);
+				up_read(&authkey->sem);
+				if (dest_keyring)
+					break;
+			}
+
+		case KEY_REQKEY_DEFL_THREAD_KEYRING:
+			dest_keyring = key_get(cred->thread_keyring);
+			if (dest_keyring)
+				break;
+
+		case KEY_REQKEY_DEFL_PROCESS_KEYRING:
+			dest_keyring = key_get(cred->process_keyring);
+			if (dest_keyring)
+				break;
+
+		case KEY_REQKEY_DEFL_SESSION_KEYRING:
+			rcu_read_lock();
+			dest_keyring = key_get(
+				rcu_dereference(cred->session_keyring));
+			rcu_read_unlock();
+
+			if (dest_keyring)
+				break;
+
+		case KEY_REQKEY_DEFL_USER_SESSION_KEYRING:
+			dest_keyring =
+				key_get(cred->user->session_keyring);
+			break;
+
+		case KEY_REQKEY_DEFL_USER_KEYRING:
+			dest_keyring = key_get(cred->user->uid_keyring);
+			break;
+
+		case KEY_REQKEY_DEFL_GROUP_KEYRING:
+		default:
+			BUG();
+		}
+	}
+
+	*_dest_keyring = dest_keyring;
+	kleave(" [dk %d]", key_serial(dest_keyring));
+	return;
+}
+
+/*
+ * Allocate a new key in under-construction state and attempt to link it in to
+ * the requested keyring.
+ *
+ * May return a key that's already under construction instead if there was a
+ * race between two thread calling request_key().
+ */
+static int construct_alloc_key(struct keyring_search_context *ctx,
+			       struct key *dest_keyring,
+			       unsigned long flags,
+			       struct key_user *user,
+			       struct key **_key)
+{
+	struct assoc_array_edit *edit;
+	struct key *key;
+	key_perm_t perm;
+	key_ref_t key_ref;
+	int ret;
+
+	kenter("%s,%s,,,",
+	       ctx->index_key.type->name, ctx->index_key.description);
+
+	*_key = NULL;
+	mutex_lock(&user->cons_lock);
+
+	perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR;
+	perm |= KEY_USR_VIEW;
+	if (ctx->index_key.type->read)
+		perm |= KEY_POS_READ;
+	if (ctx->index_key.type == &key_type_keyring ||
+	    ctx->index_key.type->update)
+		perm |= KEY_POS_WRITE;
+
+	key = key_alloc(ctx->index_key.type, ctx->index_key.description,
+			ctx->cred->fsuid, ctx->cred->fsgid, ctx->cred,
+			perm, flags);
+	if (IS_ERR(key))
+		goto alloc_failed;
+
+	set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags);
+
+	if (dest_keyring) {
+		ret = __key_link_begin(dest_keyring, &ctx->index_key, &edit);
+		if (ret < 0)
+			goto link_prealloc_failed;
+	}
+
+	/* attach the key to the destination keyring under lock, but we do need
+	 * to do another check just in case someone beat us to it whilst we
+	 * waited for locks */
+	mutex_lock(&key_construction_mutex);
+
+	key_ref = search_process_keyrings(ctx);
+	if (!IS_ERR(key_ref))
+		goto key_already_present;
+
+	if (dest_keyring)
+		__key_link(key, &edit);
+
+	mutex_unlock(&key_construction_mutex);
+	if (dest_keyring)
+		__key_link_end(dest_keyring, &ctx->index_key, edit);
+	mutex_unlock(&user->cons_lock);
+	*_key = key;
+	kleave(" = 0 [%d]", key_serial(key));
+	return 0;
+
+	/* the key is now present - we tell the caller that we found it by
+	 * returning -EINPROGRESS  */
+key_already_present:
+	key_put(key);
+	mutex_unlock(&key_construction_mutex);
+	key = key_ref_to_ptr(key_ref);
+	if (dest_keyring) {
+		ret = __key_link_check_live_key(dest_keyring, key);
+		if (ret == 0)
+			__key_link(key, &edit);
+		__key_link_end(dest_keyring, &ctx->index_key, edit);
+		if (ret < 0)
+			goto link_check_failed;
+	}
+	mutex_unlock(&user->cons_lock);
+	*_key = key;
+	kleave(" = -EINPROGRESS [%d]", key_serial(key));
+	return -EINPROGRESS;
+
+link_check_failed:
+	mutex_unlock(&user->cons_lock);
+	key_put(key);
+	kleave(" = %d [linkcheck]", ret);
+	return ret;
+
+link_prealloc_failed:
+	mutex_unlock(&user->cons_lock);
+	kleave(" = %d [prelink]", ret);
+	return ret;
+
+alloc_failed:
+	mutex_unlock(&user->cons_lock);
+	kleave(" = %ld", PTR_ERR(key));
+	return PTR_ERR(key);
+}
+
+/*
+ * Commence key construction.
+ */
+static struct key *construct_key_and_link(struct keyring_search_context *ctx,
+					  const char *callout_info,
+					  size_t callout_len,
+					  void *aux,
+					  struct key *dest_keyring,
+					  unsigned long flags)
+{
+	struct key_user *user;
+	struct key *key;
+	int ret;
+
+	kenter("");
+
+	user = key_user_lookup(current_fsuid());
+	if (!user)
+		return ERR_PTR(-ENOMEM);
+
+	construct_get_dest_keyring(&dest_keyring);
+
+	ret = construct_alloc_key(ctx, dest_keyring, flags, user, &key);
+	key_user_put(user);
+
+	if (ret == 0) {
+		ret = construct_key(key, callout_info, callout_len, aux,
+				    dest_keyring);
+		if (ret < 0) {
+			kdebug("cons failed");
+			goto construction_failed;
+		}
+	} else if (ret == -EINPROGRESS) {
+		ret = 0;
+	} else {
+		goto couldnt_alloc_key;
+	}
+
+	key_put(dest_keyring);
+	kleave(" = key %d", key_serial(key));
+	return key;
+
+construction_failed:
+	key_negate_and_link(key, key_negative_timeout, NULL, NULL);
+	key_put(key);
+couldnt_alloc_key:
+	key_put(dest_keyring);
+	kleave(" = %d", ret);
+	return ERR_PTR(ret);
+}
+
+/**
+ * request_key_and_link - Request a key and cache it in a keyring.
+ * @type: The type of key we want.
+ * @description: The searchable description of the key.
+ * @callout_info: The data to pass to the instantiation upcall (or NULL).
+ * @callout_len: The length of callout_info.
+ * @aux: Auxiliary data for the upcall.
+ * @dest_keyring: Where to cache the key.
+ * @flags: Flags to key_alloc().
+ *
+ * A key matching the specified criteria is searched for in the process's
+ * keyrings and returned with its usage count incremented if found.  Otherwise,
+ * if callout_info is not NULL, a key will be allocated and some service
+ * (probably in userspace) will be asked to instantiate it.
+ *
+ * If successfully found or created, the key will be linked to the destination
+ * keyring if one is provided.
+ *
+ * Returns a pointer to the key if successful; -EACCES, -ENOKEY, -EKEYREVOKED
+ * or -EKEYEXPIRED if an inaccessible, negative, revoked or expired key was
+ * found; -ENOKEY if no key was found and no @callout_info was given; -EDQUOT
+ * if insufficient key quota was available to create a new key; or -ENOMEM if
+ * insufficient memory was available.
+ *
+ * If the returned key was created, then it may still be under construction,
+ * and wait_for_key_construction() should be used to wait for that to complete.
+ */
+struct key *request_key_and_link(struct key_type *type,
+				 const char *description,
+				 const void *callout_info,
+				 size_t callout_len,
+				 void *aux,
+				 struct key *dest_keyring,
+				 unsigned long flags)
+{
+	struct keyring_search_context ctx = {
+		.index_key.type		= type,
+		.index_key.description	= description,
+		.cred			= current_cred(),
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= (KEYRING_SEARCH_DO_STATE_CHECK |
+					   KEYRING_SEARCH_SKIP_EXPIRED),
+	};
+	struct key *key;
+	key_ref_t key_ref;
+	int ret;
+
+	kenter("%s,%s,%p,%zu,%p,%p,%lx",
+	       ctx.index_key.type->name, ctx.index_key.description,
+	       callout_info, callout_len, aux, dest_keyring, flags);
+
+	if (type->match_preparse) {
+		ret = type->match_preparse(&ctx.match_data);
+		if (ret < 0) {
+			key = ERR_PTR(ret);
+			goto error;
+		}
+	}
+
+	/* search all the process keyrings for a key */
+	key_ref = search_process_keyrings(&ctx);
+
+	if (!IS_ERR(key_ref)) {
+		key = key_ref_to_ptr(key_ref);
+		if (dest_keyring) {
+			construct_get_dest_keyring(&dest_keyring);
+			ret = key_link(dest_keyring, key);
+			key_put(dest_keyring);
+			if (ret < 0) {
+				key_put(key);
+				key = ERR_PTR(ret);
+				goto error_free;
+			}
+		}
+	} else if (PTR_ERR(key_ref) != -EAGAIN) {
+		key = ERR_CAST(key_ref);
+	} else  {
+		/* the search failed, but the keyrings were searchable, so we
+		 * should consult userspace if we can */
+		key = ERR_PTR(-ENOKEY);
+		if (!callout_info)
+			goto error_free;
+
+		key = construct_key_and_link(&ctx, callout_info, callout_len,
+					     aux, dest_keyring, flags);
+	}
+
+error_free:
+	if (type->match_free)
+		type->match_free(&ctx.match_data);
+error:
+	kleave(" = %p", key);
+	return key;
+}
+
+/**
+ * wait_for_key_construction - Wait for construction of a key to complete
+ * @key: The key being waited for.
+ * @intr: Whether to wait interruptibly.
+ *
+ * Wait for a key to finish being constructed.
+ *
+ * Returns 0 if successful; -ERESTARTSYS if the wait was interrupted; -ENOKEY
+ * if the key was negated; or -EKEYREVOKED or -EKEYEXPIRED if the key was
+ * revoked or expired.
+ */
+int wait_for_key_construction(struct key *key, bool intr)
+{
+	int ret;
+
+	ret = wait_on_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT,
+			  intr ? TASK_INTERRUPTIBLE : TASK_UNINTERRUPTIBLE);
+	if (ret)
+		return -ERESTARTSYS;
+	if (test_bit(KEY_FLAG_NEGATIVE, &key->flags)) {
+		smp_rmb();
+		return key->type_data.reject_error;
+	}
+	return key_validate(key);
+}
+EXPORT_SYMBOL(wait_for_key_construction);
+
+/**
+ * request_key - Request a key and wait for construction
+ * @type: Type of key.
+ * @description: The searchable description of the key.
+ * @callout_info: The data to pass to the instantiation upcall (or NULL).
+ *
+ * As for request_key_and_link() except that it does not add the returned key
+ * to a keyring if found, new keys are always allocated in the user's quota,
+ * the callout_info must be a NUL-terminated string and no auxiliary data can
+ * be passed.
+ *
+ * Furthermore, it then works as wait_for_key_construction() to wait for the
+ * completion of keys undergoing construction with a non-interruptible wait.
+ */
+struct key *request_key(struct key_type *type,
+			const char *description,
+			const char *callout_info)
+{
+	struct key *key;
+	size_t callout_len = 0;
+	int ret;
+
+	if (callout_info)
+		callout_len = strlen(callout_info);
+	key = request_key_and_link(type, description, callout_info, callout_len,
+				   NULL, NULL, KEY_ALLOC_IN_QUOTA);
+	if (!IS_ERR(key)) {
+		ret = wait_for_key_construction(key, false);
+		if (ret < 0) {
+			key_put(key);
+			return ERR_PTR(ret);
+		}
+	}
+	return key;
+}
+EXPORT_SYMBOL(request_key);
+
+/**
+ * request_key_with_auxdata - Request a key with auxiliary data for the upcaller
+ * @type: The type of key we want.
+ * @description: The searchable description of the key.
+ * @callout_info: The data to pass to the instantiation upcall (or NULL).
+ * @callout_len: The length of callout_info.
+ * @aux: Auxiliary data for the upcall.
+ *
+ * As for request_key_and_link() except that it does not add the returned key
+ * to a keyring if found and new keys are always allocated in the user's quota.
+ *
+ * Furthermore, it then works as wait_for_key_construction() to wait for the
+ * completion of keys undergoing construction with a non-interruptible wait.
+ */
+struct key *request_key_with_auxdata(struct key_type *type,
+				     const char *description,
+				     const void *callout_info,
+				     size_t callout_len,
+				     void *aux)
+{
+	struct key *key;
+	int ret;
+
+	key = request_key_and_link(type, description, callout_info, callout_len,
+				   aux, NULL, KEY_ALLOC_IN_QUOTA);
+	if (!IS_ERR(key)) {
+		ret = wait_for_key_construction(key, false);
+		if (ret < 0) {
+			key_put(key);
+			return ERR_PTR(ret);
+		}
+	}
+	return key;
+}
+EXPORT_SYMBOL(request_key_with_auxdata);
+
+/*
+ * request_key_async - Request a key (allow async construction)
+ * @type: Type of key.
+ * @description: The searchable description of the key.
+ * @callout_info: The data to pass to the instantiation upcall (or NULL).
+ * @callout_len: The length of callout_info.
+ *
+ * As for request_key_and_link() except that it does not add the returned key
+ * to a keyring if found, new keys are always allocated in the user's quota and
+ * no auxiliary data can be passed.
+ *
+ * The caller should call wait_for_key_construction() to wait for the
+ * completion of the returned key if it is still undergoing construction.
+ */
+struct key *request_key_async(struct key_type *type,
+			      const char *description,
+			      const void *callout_info,
+			      size_t callout_len)
+{
+	return request_key_and_link(type, description, callout_info,
+				    callout_len, NULL, NULL,
+				    KEY_ALLOC_IN_QUOTA);
+}
+EXPORT_SYMBOL(request_key_async);
+
+/*
+ * request a key with auxiliary data for the upcaller (allow async construction)
+ * @type: Type of key.
+ * @description: The searchable description of the key.
+ * @callout_info: The data to pass to the instantiation upcall (or NULL).
+ * @callout_len: The length of callout_info.
+ * @aux: Auxiliary data for the upcall.
+ *
+ * As for request_key_and_link() except that it does not add the returned key
+ * to a keyring if found and new keys are always allocated in the user's quota.
+ *
+ * The caller should call wait_for_key_construction() to wait for the
+ * completion of the returned key if it is still undergoing construction.
+ */
+struct key *request_key_async_with_auxdata(struct key_type *type,
+					   const char *description,
+					   const void *callout_info,
+					   size_t callout_len,
+					   void *aux)
+{
+	return request_key_and_link(type, description, callout_info,
+				    callout_len, aux, NULL, KEY_ALLOC_IN_QUOTA);
+}
+EXPORT_SYMBOL(request_key_async_with_auxdata);

security/keys/request_key_auth.c

@@ -0,0 +1,276 @@
+/* Request key authorisation token key definition.
+ *
+ * Copyright (C) 2005 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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.
+ *
+ * See Documentation/security/keys-request-key.txt
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+#include <keys/user-type.h>
+
+static int request_key_auth_preparse(struct key_preparsed_payload *);
+static void request_key_auth_free_preparse(struct key_preparsed_payload *);
+static int request_key_auth_instantiate(struct key *,
+					struct key_preparsed_payload *);
+static void request_key_auth_describe(const struct key *, struct seq_file *);
+static void request_key_auth_revoke(struct key *);
+static void request_key_auth_destroy(struct key *);
+static long request_key_auth_read(const struct key *, char __user *, size_t);
+
+/*
+ * The request-key authorisation key type definition.
+ */
+struct key_type key_type_request_key_auth = {
+	.name		= ".request_key_auth",
+	.def_datalen	= sizeof(struct request_key_auth),
+	.preparse	= request_key_auth_preparse,
+	.free_preparse	= request_key_auth_free_preparse,
+	.instantiate	= request_key_auth_instantiate,
+	.describe	= request_key_auth_describe,
+	.revoke		= request_key_auth_revoke,
+	.destroy	= request_key_auth_destroy,
+	.read		= request_key_auth_read,
+};
+
+static int request_key_auth_preparse(struct key_preparsed_payload *prep)
+{
+	return 0;
+}
+
+static void request_key_auth_free_preparse(struct key_preparsed_payload *prep)
+{
+}
+
+/*
+ * Instantiate a request-key authorisation key.
+ */
+static int request_key_auth_instantiate(struct key *key,
+					struct key_preparsed_payload *prep)
+{
+	key->payload.data = (struct request_key_auth *)prep->data;
+	return 0;
+}
+
+/*
+ * Describe an authorisation token.
+ */
+static void request_key_auth_describe(const struct key *key,
+				      struct seq_file *m)
+{
+	struct request_key_auth *rka = key->payload.data;
+
+	seq_puts(m, "key:");
+	seq_puts(m, key->description);
+	if (key_is_instantiated(key))
+		seq_printf(m, " pid:%d ci:%zu", rka->pid, rka->callout_len);
+}
+
+/*
+ * Read the callout_info data (retrieves the callout information).
+ * - the key's semaphore is read-locked
+ */
+static long request_key_auth_read(const struct key *key,
+				  char __user *buffer, size_t buflen)
+{
+	struct request_key_auth *rka = key->payload.data;
+	size_t datalen;
+	long ret;
+
+	datalen = rka->callout_len;
+	ret = datalen;
+
+	/* we can return the data as is */
+	if (buffer && buflen > 0) {
+		if (buflen > datalen)
+			buflen = datalen;
+
+		if (copy_to_user(buffer, rka->callout_info, buflen) != 0)
+			ret = -EFAULT;
+	}
+
+	return ret;
+}
+
+/*
+ * Handle revocation of an authorisation token key.
+ *
+ * Called with the key sem write-locked.
+ */
+static void request_key_auth_revoke(struct key *key)
+{
+	struct request_key_auth *rka = key->payload.data;
+
+	kenter("{%d}", key->serial);
+
+	if (rka->cred) {
+		put_cred(rka->cred);
+		rka->cred = NULL;
+	}
+}
+
+/*
+ * Destroy an instantiation authorisation token key.
+ */
+static void request_key_auth_destroy(struct key *key)
+{
+	struct request_key_auth *rka = key->payload.data;
+
+	kenter("{%d}", key->serial);
+
+	if (rka->cred) {
+		put_cred(rka->cred);
+		rka->cred = NULL;
+	}
+
+	key_put(rka->target_key);
+	key_put(rka->dest_keyring);
+	kfree(rka->callout_info);
+	kfree(rka);
+}
+
+/*
+ * Create an authorisation token for /sbin/request-key or whoever to gain
+ * access to the caller's security data.
+ */
+struct key *request_key_auth_new(struct key *target, const void *callout_info,
+				 size_t callout_len, struct key *dest_keyring)
+{
+	struct request_key_auth *rka, *irka;
+	const struct cred *cred = current->cred;
+	struct key *authkey = NULL;
+	char desc[20];
+	int ret;
+
+	kenter("%d,", target->serial);
+
+	/* allocate a auth record */
+	rka = kmalloc(sizeof(*rka), GFP_KERNEL);
+	if (!rka) {
+		kleave(" = -ENOMEM");
+		return ERR_PTR(-ENOMEM);
+	}
+	rka->callout_info = kmalloc(callout_len, GFP_KERNEL);
+	if (!rka->callout_info) {
+		kleave(" = -ENOMEM");
+		kfree(rka);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* see if the calling process is already servicing the key request of
+	 * another process */
+	if (cred->request_key_auth) {
+		/* it is - use that instantiation context here too */
+		down_read(&cred->request_key_auth->sem);
+
+		/* if the auth key has been revoked, then the key we're
+		 * servicing is already instantiated */
+		if (test_bit(KEY_FLAG_REVOKED, &cred->request_key_auth->flags))
+			goto auth_key_revoked;
+
+		irka = cred->request_key_auth->payload.data;
+		rka->cred = get_cred(irka->cred);
+		rka->pid = irka->pid;
+
+		up_read(&cred->request_key_auth->sem);
+	}
+	else {
+		/* it isn't - use this process as the context */
+		rka->cred = get_cred(cred);
+		rka->pid = current->pid;
+	}
+
+	rka->target_key = key_get(target);
+	rka->dest_keyring = key_get(dest_keyring);
+	memcpy(rka->callout_info, callout_info, callout_len);
+	rka->callout_len = callout_len;
+
+	/* allocate the auth key */
+	sprintf(desc, "%x", target->serial);
+
+	authkey = key_alloc(&key_type_request_key_auth, desc,
+			    cred->fsuid, cred->fsgid, cred,
+			    KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH |
+			    KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA);
+	if (IS_ERR(authkey)) {
+		ret = PTR_ERR(authkey);
+		goto error_alloc;
+	}
+
+	/* construct the auth key */
+	ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL);
+	if (ret < 0)
+		goto error_inst;
+
+	kleave(" = {%d,%d}", authkey->serial, atomic_read(&authkey->usage));
+	return authkey;
+
+auth_key_revoked:
+	up_read(&cred->request_key_auth->sem);
+	kfree(rka->callout_info);
+	kfree(rka);
+	kleave("= -EKEYREVOKED");
+	return ERR_PTR(-EKEYREVOKED);
+
+error_inst:
+	key_revoke(authkey);
+	key_put(authkey);
+error_alloc:
+	key_put(rka->target_key);
+	key_put(rka->dest_keyring);
+	kfree(rka->callout_info);
+	kfree(rka);
+	kleave("= %d", ret);
+	return ERR_PTR(ret);
+}
+
+/*
+ * Search the current process's keyrings for the authorisation key for
+ * instantiation of a key.
+ */
+struct key *key_get_instantiation_authkey(key_serial_t target_id)
+{
+	char description[16];
+	struct keyring_search_context ctx = {
+		.index_key.type		= &key_type_request_key_auth,
+		.index_key.description	= description,
+		.cred			= current_cred(),
+		.match_data.cmp		= key_default_cmp,
+		.match_data.raw_data	= description,
+		.match_data.lookup_type	= KEYRING_SEARCH_LOOKUP_DIRECT,
+		.flags			= KEYRING_SEARCH_DO_STATE_CHECK,
+	};
+	struct key *authkey;
+	key_ref_t authkey_ref;
+
+	sprintf(description, "%x", target_id);
+
+	authkey_ref = search_process_keyrings(&ctx);
+
+	if (IS_ERR(authkey_ref)) {
+		authkey = ERR_CAST(authkey_ref);
+		if (authkey == ERR_PTR(-EAGAIN))
+			authkey = ERR_PTR(-ENOKEY);
+		goto error;
+	}
+
+	authkey = key_ref_to_ptr(authkey_ref);
+	if (test_bit(KEY_FLAG_REVOKED, &authkey->flags)) {
+		key_put(authkey);
+		authkey = ERR_PTR(-EKEYREVOKED);
+	}
+
+error:
+	return authkey;
+}

security/keys/sysctl.c

@@ -0,0 +1,76 @@
+/* Key management controls
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/key.h>
+#include <linux/sysctl.h>
+#include "internal.h"
+
+static const int zero, one = 1, max = INT_MAX;
+
+struct ctl_table key_sysctls[] = {
+	{
+		.procname = "maxkeys",
+		.data = &key_quota_maxkeys,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) &one,
+		.extra2 = (void *) &max,
+	},
+	{
+		.procname = "maxbytes",
+		.data = &key_quota_maxbytes,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) &one,
+		.extra2 = (void *) &max,
+	},
+	{
+		.procname = "root_maxkeys",
+		.data = &key_quota_root_maxkeys,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) &one,
+		.extra2 = (void *) &max,
+	},
+	{
+		.procname = "root_maxbytes",
+		.data = &key_quota_root_maxbytes,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) &one,
+		.extra2 = (void *) &max,
+	},
+	{
+		.procname = "gc_delay",
+		.data = &key_gc_delay,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) &zero,
+		.extra2 = (void *) &max,
+	},
+#ifdef CONFIG_PERSISTENT_KEYRINGS
+	{
+		.procname = "persistent_keyring_expiry",
+		.data = &persistent_keyring_expiry,
+		.maxlen = sizeof(unsigned),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_minmax,
+		.extra1 = (void *) &zero,
+		.extra2 = (void *) &max,
+	},
+#endif
+	{ }
+};

security/keys/trusted.h

@@ -0,0 +1,134 @@
+#ifndef __TRUSTED_KEY_H
+#define __TRUSTED_KEY_H
+
+/* implementation specific TPM constants */
+#define MAX_PCRINFO_SIZE		64
+#define MAX_BUF_SIZE			512
+#define TPM_GETRANDOM_SIZE		14
+#define TPM_OSAP_SIZE			36
+#define TPM_OIAP_SIZE			10
+#define TPM_SEAL_SIZE			87
+#define TPM_UNSEAL_SIZE			104
+#define TPM_SIZE_OFFSET			2
+#define TPM_RETURN_OFFSET		6
+#define TPM_DATA_OFFSET			10
+
+#define LOAD32(buffer, offset)	(ntohl(*(uint32_t *)&buffer[offset]))
+#define LOAD32N(buffer, offset)	(*(uint32_t *)&buffer[offset])
+#define LOAD16(buffer, offset)	(ntohs(*(uint16_t *)&buffer[offset]))
+
+struct tpm_buf {
+	int len;
+	unsigned char data[MAX_BUF_SIZE];
+};
+
+#define INIT_BUF(tb) (tb->len = 0)
+
+struct osapsess {
+	uint32_t handle;
+	unsigned char secret[SHA1_DIGEST_SIZE];
+	unsigned char enonce[TPM_NONCE_SIZE];
+};
+
+/* discrete values, but have to store in uint16_t for TPM use */
+enum {
+	SEAL_keytype = 1,
+	SRK_keytype = 4
+};
+
+struct trusted_key_options {
+	uint16_t keytype;
+	uint32_t keyhandle;
+	unsigned char keyauth[SHA1_DIGEST_SIZE];
+	unsigned char blobauth[SHA1_DIGEST_SIZE];
+	uint32_t pcrinfo_len;
+	unsigned char pcrinfo[MAX_PCRINFO_SIZE];
+	int pcrlock;
+};
+
+#define TPM_DEBUG 0
+
+#if TPM_DEBUG
+static inline void dump_options(struct trusted_key_options *o)
+{
+	pr_info("trusted_key: sealing key type %d\n", o->keytype);
+	pr_info("trusted_key: sealing key handle %0X\n", o->keyhandle);
+	pr_info("trusted_key: pcrlock %d\n", o->pcrlock);
+	pr_info("trusted_key: pcrinfo %d\n", o->pcrinfo_len);
+	print_hex_dump(KERN_INFO, "pcrinfo ", DUMP_PREFIX_NONE,
+		       16, 1, o->pcrinfo, o->pcrinfo_len, 0);
+}
+
+static inline void dump_payload(struct trusted_key_payload *p)
+{
+	pr_info("trusted_key: key_len %d\n", p->key_len);
+	print_hex_dump(KERN_INFO, "key ", DUMP_PREFIX_NONE,
+		       16, 1, p->key, p->key_len, 0);
+	pr_info("trusted_key: bloblen %d\n", p->blob_len);
+	print_hex_dump(KERN_INFO, "blob ", DUMP_PREFIX_NONE,
+		       16, 1, p->blob, p->blob_len, 0);
+	pr_info("trusted_key: migratable %d\n", p->migratable);
+}
+
+static inline void dump_sess(struct osapsess *s)
+{
+	print_hex_dump(KERN_INFO, "trusted-key: handle ", DUMP_PREFIX_NONE,
+		       16, 1, &s->handle, 4, 0);
+	pr_info("trusted-key: secret:\n");
+	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE,
+		       16, 1, &s->secret, SHA1_DIGEST_SIZE, 0);
+	pr_info("trusted-key: enonce:\n");
+	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE,
+		       16, 1, &s->enonce, SHA1_DIGEST_SIZE, 0);
+}
+
+static inline void dump_tpm_buf(unsigned char *buf)
+{
+	int len;
+
+	pr_info("\ntrusted-key: tpm buffer\n");
+	len = LOAD32(buf, TPM_SIZE_OFFSET);
+	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_NONE, 16, 1, buf, len, 0);
+}
+#else
+static inline void dump_options(struct trusted_key_options *o)
+{
+}
+
+static inline void dump_payload(struct trusted_key_payload *p)
+{
+}
+
+static inline void dump_sess(struct osapsess *s)
+{
+}
+
+static inline void dump_tpm_buf(unsigned char *buf)
+{
+}
+#endif
+
+static inline void store8(struct tpm_buf *buf, const unsigned char value)
+{
+	buf->data[buf->len++] = value;
+}
+
+static inline void store16(struct tpm_buf *buf, const uint16_t value)
+{
+	*(uint16_t *) & buf->data[buf->len] = htons(value);
+	buf->len += sizeof value;
+}
+
+static inline void store32(struct tpm_buf *buf, const uint32_t value)
+{
+	*(uint32_t *) & buf->data[buf->len] = htonl(value);
+	buf->len += sizeof value;
+}
+
+static inline void storebytes(struct tpm_buf *buf, const unsigned char *in,
+			      const int len)
+{
+	memcpy(buf->data + buf->len, in, len);
+	buf->len += len;
+}
+#endif

security/keys/user_defined.c

@@ -0,0 +1,227 @@
+/* user_defined.c: user defined key type
+ *
+ * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * 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.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/seq_file.h>
+#include <linux/err.h>
+#include <keys/user-type.h>
+#include <asm/uaccess.h>
+#include "internal.h"
+
+static int logon_vet_description(const char *desc);
+
+/*
+ * user defined keys take an arbitrary string as the description and an
+ * arbitrary blob of data as the payload
+ */
+struct key_type key_type_user = {
+	.name			= "user",
+	.preparse		= user_preparse,
+	.free_preparse		= user_free_preparse,
+	.instantiate		= generic_key_instantiate,
+	.update			= user_update,
+	.revoke			= user_revoke,
+	.destroy		= user_destroy,
+	.describe		= user_describe,
+	.read			= user_read,
+};
+
+EXPORT_SYMBOL_GPL(key_type_user);
+
+/*
+ * This key type is essentially the same as key_type_user, but it does
+ * not define a .read op. This is suitable for storing username and
+ * password pairs in the keyring that you do not want to be readable
+ * from userspace.
+ */
+struct key_type key_type_logon = {
+	.name			= "logon",
+	.preparse		= user_preparse,
+	.free_preparse		= user_free_preparse,
+	.instantiate		= generic_key_instantiate,
+	.update			= user_update,
+	.revoke			= user_revoke,
+	.destroy		= user_destroy,
+	.describe		= user_describe,
+	.vet_description	= logon_vet_description,
+};
+EXPORT_SYMBOL_GPL(key_type_logon);
+
+/*
+ * Preparse a user defined key payload
+ */
+int user_preparse(struct key_preparsed_payload *prep)
+{
+	struct user_key_payload *upayload;
+	size_t datalen = prep->datalen;
+
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
+		return -EINVAL;
+
+	upayload = kmalloc(sizeof(*upayload) + datalen, GFP_KERNEL);
+	if (!upayload)
+		return -ENOMEM;
+
+	/* attach the data */
+	prep->quotalen = datalen;
+	prep->payload[0] = upayload;
+	upayload->datalen = datalen;
+	memcpy(upayload->data, prep->data, datalen);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(user_preparse);
+
+/*
+ * Free a preparse of a user defined key payload
+ */
+void user_free_preparse(struct key_preparsed_payload *prep)
+{
+	kfree(prep->payload[0]);
+}
+EXPORT_SYMBOL_GPL(user_free_preparse);
+
+/*
+ * update a user defined key
+ * - the key's semaphore is write-locked
+ */
+int user_update(struct key *key, struct key_preparsed_payload *prep)
+{
+	struct user_key_payload *upayload, *zap;
+	size_t datalen = prep->datalen;
+	int ret;
+
+	ret = -EINVAL;
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
+		goto error;
+
+	/* construct a replacement payload */
+	ret = -ENOMEM;
+	upayload = kmalloc(sizeof(*upayload) + datalen, GFP_KERNEL);
+	if (!upayload)
+		goto error;
+
+	upayload->datalen = datalen;
+	memcpy(upayload->data, prep->data, datalen);
+
+	/* check the quota and attach the new data */
+	zap = upayload;
+
+	ret = key_payload_reserve(key, datalen);
+
+	if (ret == 0) {
+		/* attach the new data, displacing the old */
+		zap = key->payload.data;
+		rcu_assign_keypointer(key, upayload);
+		key->expiry = 0;
+	}
+
+	if (zap)
+		kfree_rcu(zap, rcu);
+
+error:
+	return ret;
+}
+
+EXPORT_SYMBOL_GPL(user_update);
+
+/*
+ * dispose of the links from a revoked keyring
+ * - called with the key sem write-locked
+ */
+void user_revoke(struct key *key)
+{
+	struct user_key_payload *upayload = key->payload.data;
+
+	/* clear the quota */
+	key_payload_reserve(key, 0);
+
+	if (upayload) {
+		rcu_assign_keypointer(key, NULL);
+		kfree_rcu(upayload, rcu);
+	}
+}
+
+EXPORT_SYMBOL(user_revoke);
+
+/*
+ * dispose of the data dangling from the corpse of a user key
+ */
+void user_destroy(struct key *key)
+{
+	struct user_key_payload *upayload = key->payload.data;
+
+#ifdef CONFIG_CRYPTO_FIPS
+	if(upayload)
+	{
+		memset(upayload->data, 0, upayload->datalen);
+	}
+#endif
+	kfree(upayload);
+}
+
+EXPORT_SYMBOL_GPL(user_destroy);
+
+/*
+ * describe the user key
+ */
+void user_describe(const struct key *key, struct seq_file *m)
+{
+	seq_puts(m, key->description);
+	if (key_is_instantiated(key))
+		seq_printf(m, ": %u", key->datalen);
+}
+
+EXPORT_SYMBOL_GPL(user_describe);
+
+/*
+ * read the key data
+ * - the key's semaphore is read-locked
+ */
+long user_read(const struct key *key, char __user *buffer, size_t buflen)
+{
+	struct user_key_payload *upayload;
+	long ret;
+
+	upayload = rcu_dereference_key(key);
+	ret = upayload->datalen;
+
+	/* we can return the data as is */
+	if (buffer && buflen > 0) {
+		if (buflen > upayload->datalen)
+			buflen = upayload->datalen;
+
+		if (copy_to_user(buffer, upayload->data, buflen) != 0)
+			ret = -EFAULT;
+	}
+
+	return ret;
+}
+
+EXPORT_SYMBOL_GPL(user_read);
+
+/* Vet the description for a "logon" key */
+static int logon_vet_description(const char *desc)
+{
+	char *p;
+
+	/* require a "qualified" description string */
+	p = strchr(desc, ':');
+	if (!p)
+		return -EINVAL;
+
+	/* also reject description with ':' as first char */
+	if (p == desc)
+		return -EINVAL;
+
+	return 0;
+}

security/lsm_audit.c

@@ -0,0 +1,433 @@
+/*
+ * common LSM auditing functions
+ *
+ * Based on code written for SELinux by :
+ *			Stephen Smalley, <sds@epoch.ncsc.mil>
+ * 			James Morris <jmorris@redhat.com>
+ * Author : Etienne Basset, <etienne.basset@ensta.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2,
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <net/sock.h>
+#include <linux/un.h>
+#include <net/af_unix.h>
+#include <linux/audit.h>
+#include <linux/ipv6.h>
+#include <linux/ip.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/dccp.h>
+#include <linux/sctp.h>
+#include <linux/lsm_audit.h>
+
+/**
+ * ipv4_skb_to_auditdata : fill auditdata from skb
+ * @skb : the skb
+ * @ad : the audit data to fill
+ * @proto : the layer 4 protocol
+ *
+ * return  0 on success
+ */
+int ipv4_skb_to_auditdata(struct sk_buff *skb,
+		struct common_audit_data *ad, u8 *proto)
+{
+	int ret = 0;
+	struct iphdr *ih;
+
+	ih = ip_hdr(skb);
+	if (ih == NULL)
+		return -EINVAL;
+
+	ad->u.net->v4info.saddr = ih->saddr;
+	ad->u.net->v4info.daddr = ih->daddr;
+
+	if (proto)
+		*proto = ih->protocol;
+	/* non initial fragment */
+	if (ntohs(ih->frag_off) & IP_OFFSET)
+		return 0;
+
+	switch (ih->protocol) {
+	case IPPROTO_TCP: {
+		struct tcphdr *th = tcp_hdr(skb);
+		if (th == NULL)
+			break;
+
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
+		break;
+	}
+	case IPPROTO_UDP: {
+		struct udphdr *uh = udp_hdr(skb);
+		if (uh == NULL)
+			break;
+
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
+		break;
+	}
+	case IPPROTO_DCCP: {
+		struct dccp_hdr *dh = dccp_hdr(skb);
+		if (dh == NULL)
+			break;
+
+		ad->u.net->sport = dh->dccph_sport;
+		ad->u.net->dport = dh->dccph_dport;
+		break;
+	}
+	case IPPROTO_SCTP: {
+		struct sctphdr *sh = sctp_hdr(skb);
+		if (sh == NULL)
+			break;
+		ad->u.net->sport = sh->source;
+		ad->u.net->dport = sh->dest;
+		break;
+	}
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+/**
+ * ipv6_skb_to_auditdata : fill auditdata from skb
+ * @skb : the skb
+ * @ad : the audit data to fill
+ * @proto : the layer 4 protocol
+ *
+ * return  0 on success
+ */
+int ipv6_skb_to_auditdata(struct sk_buff *skb,
+		struct common_audit_data *ad, u8 *proto)
+{
+	int offset, ret = 0;
+	struct ipv6hdr *ip6;
+	u8 nexthdr;
+	__be16 frag_off;
+
+	ip6 = ipv6_hdr(skb);
+	if (ip6 == NULL)
+		return -EINVAL;
+	ad->u.net->v6info.saddr = ip6->saddr;
+	ad->u.net->v6info.daddr = ip6->daddr;
+	ret = 0;
+	/* IPv6 can have several extension header before the Transport header
+	 * skip them */
+	offset = skb_network_offset(skb);
+	offset += sizeof(*ip6);
+	nexthdr = ip6->nexthdr;
+	offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
+	if (offset < 0)
+		return 0;
+	if (proto)
+		*proto = nexthdr;
+	switch (nexthdr) {
+	case IPPROTO_TCP: {
+		struct tcphdr _tcph, *th;
+
+		th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
+		if (th == NULL)
+			break;
+
+		ad->u.net->sport = th->source;
+		ad->u.net->dport = th->dest;
+		break;
+	}
+	case IPPROTO_UDP: {
+		struct udphdr _udph, *uh;
+
+		uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
+		if (uh == NULL)
+			break;
+
+		ad->u.net->sport = uh->source;
+		ad->u.net->dport = uh->dest;
+		break;
+	}
+	case IPPROTO_DCCP: {
+		struct dccp_hdr _dccph, *dh;
+
+		dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph);
+		if (dh == NULL)
+			break;
+
+		ad->u.net->sport = dh->dccph_sport;
+		ad->u.net->dport = dh->dccph_dport;
+		break;
+	}
+	case IPPROTO_SCTP: {
+		struct sctphdr _sctph, *sh;
+
+		sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph);
+		if (sh == NULL)
+			break;
+		ad->u.net->sport = sh->source;
+		ad->u.net->dport = sh->dest;
+		break;
+	}
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
+}
+#endif
+
+
+static inline void print_ipv6_addr(struct audit_buffer *ab,
+				   struct in6_addr *addr, __be16 port,
+				   char *name1, char *name2)
+{
+	if (!ipv6_addr_any(addr))
+		audit_log_format(ab, " %s=%pI6c", name1, addr);
+	if (port)
+		audit_log_format(ab, " %s=%d", name2, ntohs(port));
+}
+
+static inline void print_ipv4_addr(struct audit_buffer *ab, __be32 addr,
+				   __be16 port, char *name1, char *name2)
+{
+	if (addr)
+		audit_log_format(ab, " %s=%pI4", name1, &addr);
+	if (port)
+		audit_log_format(ab, " %s=%d", name2, ntohs(port));
+}
+
+/**
+ * dump_common_audit_data - helper to dump common audit data
+ * @a : common audit data
+ *
+ */
+static void dump_common_audit_data(struct audit_buffer *ab,
+				   struct common_audit_data *a)
+{
+	struct task_struct *tsk = current;
+
+	/*
+	 * To keep stack sizes in check force programers to notice if they
+	 * start making this union too large!  See struct lsm_network_audit
+	 * as an example of how to deal with large data.
+	 */
+	BUILD_BUG_ON(sizeof(a->u) > sizeof(void *)*2);
+
+	audit_log_format(ab, " pid=%d comm=", task_pid_nr(tsk));
+	audit_log_untrustedstring(ab, tsk->comm);
+
+	switch (a->type) {
+	case LSM_AUDIT_DATA_NONE:
+		return;
+	case LSM_AUDIT_DATA_IPC:
+		audit_log_format(ab, " key=%d ", a->u.ipc_id);
+		break;
+	case LSM_AUDIT_DATA_CAP:
+		audit_log_format(ab, " capability=%d ", a->u.cap);
+		break;
+	case LSM_AUDIT_DATA_PATH: {
+		struct inode *inode;
+
+		audit_log_d_path(ab, " path=", &a->u.path);
+
+		inode = a->u.path.dentry->d_inode;
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%lu", inode->i_ino);
+		}
+		break;
+	}
+	case LSM_AUDIT_DATA_IOCTL_OP: {
+		struct inode *inode;
+
+		audit_log_d_path(ab, " path=", &a->u.op->path);
+
+		inode = a->u.op->path.dentry->d_inode;
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%lu", inode->i_ino);
+		}
+
+		audit_log_format(ab, " ioctlcmd=%hx", a->u.op->cmd);
+		break;
+	}
+	case LSM_AUDIT_DATA_DENTRY: {
+		struct inode *inode;
+
+		audit_log_format(ab, " name=");
+		audit_log_untrustedstring(ab, a->u.dentry->d_name.name);
+
+		inode = a->u.dentry->d_inode;
+		if (inode) {
+			audit_log_format(ab, " dev=");
+			audit_log_untrustedstring(ab, inode->i_sb->s_id);
+			audit_log_format(ab, " ino=%lu", inode->i_ino);
+		}
+		break;
+	}
+	case LSM_AUDIT_DATA_INODE: {
+		struct dentry *dentry;
+		struct inode *inode;
+
+		inode = a->u.inode;
+		dentry = d_find_alias(inode);
+		if (dentry) {
+			audit_log_format(ab, " name=");
+			audit_log_untrustedstring(ab,
+					 dentry->d_name.name);
+			dput(dentry);
+		}
+		audit_log_format(ab, " dev=");
+		audit_log_untrustedstring(ab, inode->i_sb->s_id);
+		audit_log_format(ab, " ino=%lu", inode->i_ino);
+		break;
+	}
+	case LSM_AUDIT_DATA_TASK:
+		tsk = a->u.tsk;
+		if (tsk) {
+			pid_t pid = task_pid_nr(tsk);
+			if (pid) {
+				audit_log_format(ab, " pid=%d comm=", pid);
+				audit_log_untrustedstring(ab, tsk->comm);
+			}
+		}
+		break;
+	case LSM_AUDIT_DATA_NET:
+		if (a->u.net->sk) {
+			struct sock *sk = a->u.net->sk;
+			struct unix_sock *u;
+			int len = 0;
+			char *p = NULL;
+
+			switch (sk->sk_family) {
+			case AF_INET: {
+				struct inet_sock *inet = inet_sk(sk);
+
+				print_ipv4_addr(ab, inet->inet_rcv_saddr,
+						inet->inet_sport,
+						"laddr", "lport");
+				print_ipv4_addr(ab, inet->inet_daddr,
+						inet->inet_dport,
+						"faddr", "fport");
+				break;
+			}
+#if IS_ENABLED(CONFIG_IPV6)
+			case AF_INET6: {
+				struct inet_sock *inet = inet_sk(sk);
+
+				print_ipv6_addr(ab, &sk->sk_v6_rcv_saddr,
+						inet->inet_sport,
+						"laddr", "lport");
+				print_ipv6_addr(ab, &sk->sk_v6_daddr,
+						inet->inet_dport,
+						"faddr", "fport");
+				break;
+			}
+#endif
+			case AF_UNIX:
+				u = unix_sk(sk);
+				if (u->path.dentry) {
+					audit_log_d_path(ab, " path=", &u->path);
+					break;
+				}
+				if (!u->addr)
+					break;
+				len = u->addr->len-sizeof(short);
+				p = &u->addr->name->sun_path[0];
+				audit_log_format(ab, " path=");
+				if (*p)
+					audit_log_untrustedstring(ab, p);
+				else
+					audit_log_n_hex(ab, p, len);
+				break;
+			}
+		}
+
+		switch (a->u.net->family) {
+		case AF_INET:
+			print_ipv4_addr(ab, a->u.net->v4info.saddr,
+					a->u.net->sport,
+					"saddr", "src");
+			print_ipv4_addr(ab, a->u.net->v4info.daddr,
+					a->u.net->dport,
+					"daddr", "dest");
+			break;
+		case AF_INET6:
+			print_ipv6_addr(ab, &a->u.net->v6info.saddr,
+					a->u.net->sport,
+					"saddr", "src");
+			print_ipv6_addr(ab, &a->u.net->v6info.daddr,
+					a->u.net->dport,
+					"daddr", "dest");
+			break;
+		}
+		if (a->u.net->netif > 0) {
+			struct net_device *dev;
+
+			/* NOTE: we always use init's namespace */
+			dev = dev_get_by_index(&init_net, a->u.net->netif);
+			if (dev) {
+				audit_log_format(ab, " netif=%s", dev->name);
+				dev_put(dev);
+			}
+		}
+		break;
+#ifdef CONFIG_KEYS
+	case LSM_AUDIT_DATA_KEY:
+		audit_log_format(ab, " key_serial=%u", a->u.key_struct.key);
+		if (a->u.key_struct.key_desc) {
+			audit_log_format(ab, " key_desc=");
+			audit_log_untrustedstring(ab, a->u.key_struct.key_desc);
+		}
+		break;
+#endif
+	case LSM_AUDIT_DATA_KMOD:
+		audit_log_format(ab, " kmod=");
+		audit_log_untrustedstring(ab, a->u.kmod_name);
+		break;
+	} /* switch (a->type) */
+}
+
+/**
+ * common_lsm_audit - generic LSM auditing function
+ * @a:  auxiliary audit data
+ * @pre_audit: lsm-specific pre-audit callback
+ * @post_audit: lsm-specific post-audit callback
+ *
+ * setup the audit buffer for common security information
+ * uses callback to print LSM specific information
+ */
+void common_lsm_audit(struct common_audit_data *a,
+	void (*pre_audit)(struct audit_buffer *, void *),
+	void (*post_audit)(struct audit_buffer *, void *))
+{
+	struct audit_buffer *ab;
+
+	if (a == NULL)
+		return;
+	/* we use GFP_ATOMIC so we won't sleep */
+	ab = audit_log_start(current->audit_context, GFP_ATOMIC | __GFP_NOWARN,
+			     AUDIT_AVC);
+
+	if (ab == NULL)
+		return;
+
+	if (pre_audit)
+		pre_audit(ab, a);
+
+	dump_common_audit_data(ab, a);
+
+	if (post_audit)
+		post_audit(ab, a);
+
+	audit_log_end(ab);
+}

security/min_addr.c

@@ -0,0 +1,52 @@
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/security.h>
+#include <linux/sysctl.h>
+
+/* amount of vm to protect from userspace access by both DAC and the LSM*/
+unsigned long mmap_min_addr;
+/* amount of vm to protect from userspace using CAP_SYS_RAWIO (DAC) */
+unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+/* amount of vm to protect from userspace using the LSM = CONFIG_LSM_MMAP_MIN_ADDR */
+
+/*
+ * Update mmap_min_addr = max(dac_mmap_min_addr, CONFIG_LSM_MMAP_MIN_ADDR)
+ */
+static void update_mmap_min_addr(void)
+{
+#ifdef CONFIG_LSM_MMAP_MIN_ADDR
+	if (dac_mmap_min_addr > CONFIG_LSM_MMAP_MIN_ADDR)
+		mmap_min_addr = dac_mmap_min_addr;
+	else
+		mmap_min_addr = CONFIG_LSM_MMAP_MIN_ADDR;
+#else
+	mmap_min_addr = dac_mmap_min_addr;
+#endif
+}
+
+/*
+ * sysctl handler which just sets dac_mmap_min_addr = the new value and then
+ * calls update_mmap_min_addr() so non MAP_FIXED hints get rounded properly
+ */
+int mmap_min_addr_handler(struct ctl_table *table, int write,
+			  void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	if (write && !capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
+	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
+
+	update_mmap_min_addr();
+
+	return ret;
+}
+
+static int __init init_mmap_min_addr(void)
+{
+	update_mmap_min_addr();
+
+	return 0;
+}
+pure_initcall(init_mmap_min_addr);

security/sdp/Makefile

@@ -0,0 +1,7 @@
+#
+# Makefile for DEK and DLP modules
+#
+
+obj-$(CONFIG_SDP) += dek.o dek_aes.o sdp_mm.o pub_crypto_emul.o dek_sysfs.o cache_cleanup.o kek_pack.o fs_handler.o 
+obj-$(CONFIG_DLP) += sdp_dlp.o
+

security/sdp/cache_cleanup.c

@@ -0,0 +1,70 @@
+/*
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ *
+ * Sensitive Data Protection
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <sdp/common.h>
+#include <sdp/cache_cleanup.h>
+
+#if SDP_CACHE_CLEANUP_DEBUG
+static void sdp_page_dump(unsigned char *buf, int len, const char* str)
+{
+    unsigned int i;
+    char s[512];
+
+    s[0] = 0;
+    for(i=0;i<len && i<32;++i) {
+        char tmp[8];
+        sprintf(tmp, " %02x", buf[i]);
+        strcat(s, tmp);
+    }
+
+    if (len > 32) {
+        char tmp[8];
+        sprintf(tmp, " ...");
+        strcat(s, tmp);
+    }
+
+    printk("%s [%s len=%d]\n", s, str, len);
+}
+#else
+static void sdp_page_dump(unsigned char *buf, int len, const char* str) {
+    return;
+}
+#endif
+
+void sdp_page_cleanup(struct page *page)
+{
+    if(page && page->mapping) {
+        if(mapping_sensitive(page->mapping)) {
+            void *d;
+
+#if SDP_CACHE_CLEANUP_DEBUG
+            printk("%s : deleting [%s] sensitive page.\n",
+                    __func__, page->mapping->host->i_sb->s_type->name);
+            //dump_stack();
+#endif
+            d = kmap_atomic(page);
+            if(d) {
+                sdp_page_dump((unsigned char *)d, PAGE_SIZE, "freeing");
+                clear_page(d);
+                sdp_page_dump((unsigned char *)d, PAGE_SIZE, "freed");
+                kunmap_atomic(d);
+            }
+        }
+    }
+}

security/sdp/dek_aes.c

@@ -0,0 +1,107 @@
+/*
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd.
+ *
+ * Sensitive Data Protection
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+ 
+#include <linux/err.h>
+#include <sdp/dek_common.h>
+#include <sdp/dek_aes.h>
+
+static struct crypto_blkcipher *dek_aes_key_setup(kek_t *kek)
+{
+	struct crypto_blkcipher *tfm = NULL;
+
+	tfm = crypto_alloc_blkcipher("cbc(aes)", 0, CRYPTO_ALG_ASYNC);
+	if (!IS_ERR(tfm)) {
+		crypto_blkcipher_setkey(tfm, kek->buf, kek->len);
+	} else {
+		printk("dek: failed to alloc blkcipher\n");
+	}
+	return tfm;
+}
+
+
+static void dek_aes_key_free(struct crypto_blkcipher *tfm)
+{
+	crypto_free_blkcipher(tfm);
+}
+
+static int __dek_aes_encrypt(struct crypto_blkcipher *tfm, char *src, char *dst, int len) {
+	struct blkcipher_desc desc;
+	struct scatterlist src_sg, dst_sg;
+	int bsize = crypto_blkcipher_ivsize(tfm);
+	u8 iv[bsize];
+
+	memset(&iv, 0, sizeof(iv));
+	desc.tfm = tfm;
+	desc.info = iv;
+	desc.flags = 0;
+
+	sg_init_one(&src_sg, src, len);
+	sg_init_one(&dst_sg, dst, len);
+
+	return crypto_blkcipher_encrypt_iv(&desc, &dst_sg, &src_sg, len);
+}
+
+static int __dek_aes_decrypt(struct crypto_blkcipher *tfm, char *src, char *dst, int len) {
+	struct blkcipher_desc desc;
+	struct scatterlist src_sg, dst_sg;
+	int bsize = crypto_blkcipher_ivsize(tfm);
+	u8 iv[bsize];
+
+	memset(&iv, 0, sizeof(iv));
+	desc.tfm = tfm;
+	desc.info = iv;
+	desc.flags = 0;
+
+	sg_init_one(&src_sg, src, len);
+	sg_init_one(&dst_sg, dst, len);
+
+	return crypto_blkcipher_decrypt_iv(&desc, &dst_sg, &src_sg, len);
+}
+
+int dek_aes_encrypt(kek_t *kek, char *src, char *dst, int len) {
+	int rc;
+	struct crypto_blkcipher *tfm;
+
+	if(kek == NULL) return -EINVAL;
+
+	tfm = dek_aes_key_setup(kek);
+
+	if(tfm) {
+		rc = __dek_aes_encrypt(tfm, src, dst, len);
+		dek_aes_key_free(tfm);
+		return rc;
+	} else
+		return -ENOMEM;
+}
+
+int dek_aes_decrypt(kek_t *kek, char *src, char *dst, int len) {
+	int rc;
+	struct crypto_blkcipher *tfm;
+
+	if(kek == NULL) return -EINVAL;
+
+	tfm = dek_aes_key_setup(kek);
+
+	if(tfm) {
+		rc = __dek_aes_decrypt(tfm, src, dst, len);
+		dek_aes_key_free(tfm);
+		return rc;
+	} else
+		return -ENOMEM;
+}