Merge branch 'linus' into stackprotector

Conflicts:
	arch/x86/include/asm/pda.h
	kernel/fork.c

28 files changed, 2034 insertions, 1546 deletions

diff --git a/security/capability.c b/security/capability.c
index 24587481903..2dce66fcb99 100644
--- a/security/capability.c
+++ b/security/capability.c
@@ -32,24 +32,19 @@ static int cap_quota_on(struct dentry *dentry)
 	return 0;
 }
 
-static int cap_bprm_alloc_security(struct linux_binprm *bprm)
+static int cap_bprm_check_security (struct linux_binprm *bprm)
 {
 	return 0;
 }
 
-static void cap_bprm_free_security(struct linux_binprm *bprm)
+static void cap_bprm_committing_creds(struct linux_binprm *bprm)
 {
 }
 
-static void cap_bprm_post_apply_creds(struct linux_binprm *bprm)
+static void cap_bprm_committed_creds(struct linux_binprm *bprm)
 {
 }
 
-static int cap_bprm_check_security(struct linux_binprm *bprm)
-{
-	return 0;
-}
-
 static int cap_sb_alloc_security(struct super_block *sb)
 {
 	return 0;
@@ -64,7 +59,7 @@ static int cap_sb_copy_data(char *orig, char *copy)
 	return 0;
 }
 
-static int cap_sb_kern_mount(struct super_block *sb, void *data)
+static int cap_sb_kern_mount(struct super_block *sb, int flags, void *data)
 {
 	return 0;
 }
@@ -330,7 +325,7 @@ static int cap_file_receive(struct file *file)
 	return 0;
 }
 
-static int cap_dentry_open(struct file *file)
+static int cap_dentry_open(struct file *file, const struct cred *cred)
 {
 	return 0;
 }
@@ -340,15 +335,29 @@ static int cap_task_create(unsigned long clone_flags)
 	return 0;
 }
 
-static int cap_task_alloc_security(struct task_struct *p)
+static void cap_cred_free(struct cred *cred)
+{
+}
+
+static int cap_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp)
 {
 	return 0;
 }
 
-static void cap_task_free_security(struct task_struct *p)
+static void cap_cred_commit(struct cred *new, const struct cred *old)
 {
 }
 
+static int cap_kernel_act_as(struct cred *new, u32 secid)
+{
+	return 0;
+}
+
+static int cap_kernel_create_files_as(struct cred *new, struct inode *inode)
+{
+	return 0;
+}
+
 static int cap_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags)
 {
 	return 0;
@@ -750,7 +759,7 @@ static void cap_release_secctx(char *secdata, u32 seclen)
 }
 
 #ifdef CONFIG_KEYS
-static int cap_key_alloc(struct key *key, struct task_struct *ctx,
+static int cap_key_alloc(struct key *key, const struct cred *cred,
 			 unsigned long flags)
 {
 	return 0;
@@ -760,7 +769,7 @@ static void cap_key_free(struct key *key)
 {
 }
 
-static int cap_key_permission(key_ref_t key_ref, struct task_struct *context,
+static int cap_key_permission(key_ref_t key_ref, const struct cred *cred,
 			      key_perm_t perm)
 {
 	return 0;
@@ -814,8 +823,7 @@ void security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, ptrace_may_access);
 	set_to_cap_if_null(ops, ptrace_traceme);
 	set_to_cap_if_null(ops, capget);
-	set_to_cap_if_null(ops, capset_check);
-	set_to_cap_if_null(ops, capset_set);
+	set_to_cap_if_null(ops, capset);
 	set_to_cap_if_null(ops, acct);
 	set_to_cap_if_null(ops, capable);
 	set_to_cap_if_null(ops, quotactl);
@@ -824,11 +832,9 @@ void security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, syslog);
 	set_to_cap_if_null(ops, settime);
 	set_to_cap_if_null(ops, vm_enough_memory);
-	set_to_cap_if_null(ops, bprm_alloc_security);
-	set_to_cap_if_null(ops, bprm_free_security);
-	set_to_cap_if_null(ops, bprm_apply_creds);
-	set_to_cap_if_null(ops, bprm_post_apply_creds);
-	set_to_cap_if_null(ops, bprm_set_security);
+	set_to_cap_if_null(ops, bprm_set_creds);
+	set_to_cap_if_null(ops, bprm_committing_creds);
+	set_to_cap_if_null(ops, bprm_committed_creds);
 	set_to_cap_if_null(ops, bprm_check_security);
 	set_to_cap_if_null(ops, bprm_secureexec);
 	set_to_cap_if_null(ops, sb_alloc_security);
@@ -890,10 +896,13 @@ void security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, file_receive);
 	set_to_cap_if_null(ops, dentry_open);
 	set_to_cap_if_null(ops, task_create);
-	set_to_cap_if_null(ops, task_alloc_security);
-	set_to_cap_if_null(ops, task_free_security);
+	set_to_cap_if_null(ops, cred_free);
+	set_to_cap_if_null(ops, cred_prepare);
+	set_to_cap_if_null(ops, cred_commit);
+	set_to_cap_if_null(ops, kernel_act_as);
+	set_to_cap_if_null(ops, kernel_create_files_as);
 	set_to_cap_if_null(ops, task_setuid);
-	set_to_cap_if_null(ops, task_post_setuid);
+	set_to_cap_if_null(ops, task_fix_setuid);
 	set_to_cap_if_null(ops, task_setgid);
 	set_to_cap_if_null(ops, task_setpgid);
 	set_to_cap_if_null(ops, task_getpgid);
@@ -910,7 +919,6 @@ void security_fixup_ops(struct security_operations *ops)
 	set_to_cap_if_null(ops, task_wait);
 	set_to_cap_if_null(ops, task_kill);
 	set_to_cap_if_null(ops, task_prctl);
-	set_to_cap_if_null(ops, task_reparent_to_init);
 	set_to_cap_if_null(ops, task_to_inode);
 	set_to_cap_if_null(ops, ipc_permission);
 	set_to_cap_if_null(ops, ipc_getsecid);
diff --git a/security/commoncap.c b/security/commoncap.c
index 399bfdb9e2d..79713545cd6 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/capability.h>
+#include <linux/audit.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -29,7 +30,7 @@
 
 int cap_netlink_send(struct sock *sk, struct sk_buff *skb)
 {
-	NETLINK_CB(skb).eff_cap = current->cap_effective;
+	NETLINK_CB(skb).eff_cap = current_cap();
 	return 0;
 }
 
@@ -39,23 +40,41 @@ int cap_netlink_recv(struct sk_buff *skb, int cap)
 		return -EPERM;
 	return 0;
 }
-
 EXPORT_SYMBOL(cap_netlink_recv);
 
-/*
+/**
+ * cap_capable - Determine whether a task has a particular effective capability
+ * @tsk: The task to query
+ * @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_capable() cannot be used like the kernel's capable()
- * function.  That is, it has the reverse semantics: cap_capable()
- * returns 0 when a task has a capability, but the kernel's capable()
- * returns 1 for this case.
+ * function.  That is, it has the reverse semantics: cap_capable() returns 0
+ * when a task has a capability, but the kernel's capable() returns 1 for this
+ * case.
  */
-int cap_capable (struct task_struct *tsk, int cap)
+int cap_capable(struct task_struct *tsk, int cap, int audit)
 {
+	__u32 cap_raised;
+
 	/* Derived from include/linux/sched.h:capable. */
-	if (cap_raised(tsk->cap_effective, cap))
-		return 0;
-	return -EPERM;
+	rcu_read_lock();
+	cap_raised = cap_raised(__task_cred(tsk)->cap_effective, cap);
+	rcu_read_unlock();
+	return cap_raised ? 0 : -EPERM;
 }
 
+/**
+ * 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(struct timespec *ts, struct timezone *tz)
 {
 	if (!capable(CAP_SYS_TIME))
@@ -63,121 +82,157 @@ int cap_settime(struct timespec *ts, struct timezone *tz)
 	return 0;
 }
 
+/**
+ * cap_ptrace_may_access - Determine whether the current process may access
+ *			   another
+ * @child: The process to be accessed
+ * @mode: The mode of attachment.
+ *
+ * Determine whether a process may access another, returning 0 if permission
+ * granted, -ve if denied.
+ */
 int cap_ptrace_may_access(struct task_struct *child, unsigned int mode)
 {
-	/* Derived from arch/i386/kernel/ptrace.c:sys_ptrace. */
-	if (cap_issubset(child->cap_permitted, current->cap_permitted))
-		return 0;
-	if (capable(CAP_SYS_PTRACE))
-		return 0;
-	return -EPERM;
+	int ret = 0;
+
+	rcu_read_lock();
+	if (!cap_issubset(__task_cred(child)->cap_permitted,
+			  current_cred()->cap_permitted) &&
+	    !capable(CAP_SYS_PTRACE))
+		ret = -EPERM;
+	rcu_read_unlock();
+	return ret;
 }
 
+/**
+ * cap_ptrace_traceme - Determine whether another process may trace the current
+ * @parent: The task proposed to be the tracer
+ *
+ * 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)
 {
-	/* Derived from arch/i386/kernel/ptrace.c:sys_ptrace. */
-	if (cap_issubset(current->cap_permitted, parent->cap_permitted))
-		return 0;
-	if (has_capability(parent, CAP_SYS_PTRACE))
-		return 0;
-	return -EPERM;
+	int ret = 0;
+
+	rcu_read_lock();
+	if (!cap_issubset(current_cred()->cap_permitted,
+			  __task_cred(parent)->cap_permitted) &&
+	    !has_capability(parent, CAP_SYS_PTRACE))
+		ret = -EPERM;
+	rcu_read_unlock();
+	return ret;
 }
 
-int cap_capget (struct task_struct *target, kernel_cap_t *effective,
-		kernel_cap_t *inheritable, kernel_cap_t *permitted)
+/**
+ * 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. */
-	*effective = target->cap_effective;
-	*inheritable = target->cap_inheritable;
-	*permitted = target->cap_permitted;
+	rcu_read_lock();
+	cred = __task_cred(target);
+	*effective   = cred->cap_effective;
+	*inheritable = cred->cap_inheritable;
+	*permitted   = cred->cap_permitted;
+	rcu_read_unlock();
 	return 0;
 }
 
-#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
-
-static inline int cap_block_setpcap(struct task_struct *target)
-{
-	/*
-	 * No support for remote process capability manipulation with
-	 * filesystem capability support.
-	 */
-	return (target != current);
-}
-
+/*
+ * 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)
 {
-	/*
-	 * Return 1 if changes to the inheritable set are limited
-	 * to the old permitted set. That is, if the current task
-	 * does *not* possess the CAP_SETPCAP capability.
-	 */
-	return (cap_capable(current, CAP_SETPCAP) != 0);
-}
-
-static inline int cap_limit_ptraced_target(void) { return 1; }
-
-#else /* ie., ndef CONFIG_SECURITY_FILE_CAPABILITIES */
+#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
 
-static inline int cap_block_setpcap(struct task_struct *t) { return 0; }
-static inline int cap_inh_is_capped(void) { return 1; }
-static inline int cap_limit_ptraced_target(void)
-{
-	return !capable(CAP_SETPCAP);
+	/* they are so limited unless the current task has the CAP_SETPCAP
+	 * capability
+	 */
+	if (cap_capable(current, CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0)
+		return 0;
+#endif
+	return 1;
 }
 
-#endif /* def CONFIG_SECURITY_FILE_CAPABILITIES */
-
-int cap_capset_check (struct task_struct *target, kernel_cap_t *effective,
-		      kernel_cap_t *inheritable, kernel_cap_t *permitted)
-{
-	if (cap_block_setpcap(target)) {
-		return -EPERM;
-	}
-	if (cap_inh_is_capped()
-	    && !cap_issubset(*inheritable,
-			     cap_combine(target->cap_inheritable,
-					 current->cap_permitted))) {
+/**
+ * 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(target->cap_inheritable,
-				       current->cap_bset))) {
+			  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,
-			   cap_combine (target->cap_permitted,
-					current->cap_permitted))) {
+	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)) {
+	if (!cap_issubset(*effective, *permitted))
 		return -EPERM;
-	}
 
+	new->cap_effective   = *effective;
+	new->cap_inheritable = *inheritable;
+	new->cap_permitted   = *permitted;
 	return 0;
 }
 
-void cap_capset_set (struct task_struct *target, kernel_cap_t *effective,
-		     kernel_cap_t *inheritable, kernel_cap_t *permitted)
-{
-	target->cap_effective = *effective;
-	target->cap_inheritable = *inheritable;
-	target->cap_permitted = *permitted;
-}
-
+/*
+ * Clear proposed capability sets for execve().
+ */
 static inline void bprm_clear_caps(struct linux_binprm *bprm)
 {
-	cap_clear(bprm->cap_post_exec_permitted);
+	cap_clear(bprm->cred->cap_permitted);
 	bprm->cap_effective = false;
 }
 
 #ifdef CONFIG_SECURITY_FILE_CAPABILITIES
 
+/**
+ * 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;
@@ -192,6 +247,14 @@ int cap_inode_need_killpriv(struct dentry *dentry)
 	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;
@@ -202,19 +265,75 @@ int cap_inode_killpriv(struct dentry *dentry)
 	return inode->i_op->removexattr(dentry, XATTR_NAME_CAPS);
 }
 
-static inline int cap_from_disk(struct vfs_cap_data *caps,
-				struct linux_binprm *bprm, unsigned size)
+/*
+ * 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)
 {
+	struct cred *new = bprm->cred;
+	unsigned i;
+	int ret = 0;
+
+	if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE)
+		*effective = 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 ret;
+	int size;
+	struct vfs_cap_data caps;
+
+	memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data));
+
+	if (!inode || !inode->i_op || !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;
 
-	magic_etc = le32_to_cpu(caps->magic_etc);
+	cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps.magic_etc);
 
-	switch ((magic_etc & VFS_CAP_REVISION_MASK)) {
+	switch (magic_etc & VFS_CAP_REVISION_MASK) {
 	case VFS_CAP_REVISION_1:
 		if (size != XATTR_CAPS_SZ_1)
 			return -EINVAL;
@@ -229,77 +348,48 @@ static inline int cap_from_disk(struct vfs_cap_data *caps,
 		return -EINVAL;
 	}
 
-	if (magic_etc & VFS_CAP_FLAGS_EFFECTIVE) {
-		bprm->cap_effective = true;
-	} else {
-		bprm->cap_effective = false;
-	}
-
-	ret = 0;
-
 	CAP_FOR_EACH_U32(i) {
-		__u32 value_cpu;
-
-		if (i >= tocopy) {
-			/*
-			 * Legacy capability sets have no upper bits
-			 */
-			bprm->cap_post_exec_permitted.cap[i] = 0;
-			continue;
-		}
-		/*
-		 * pP' = (X & fP) | (pI & fI)
-		 */
-		value_cpu = le32_to_cpu(caps->data[i].permitted);
-		bprm->cap_post_exec_permitted.cap[i] =
-			(current->cap_bset.cap[i] & value_cpu) |
-			(current->cap_inheritable.cap[i] &
-				le32_to_cpu(caps->data[i].inheritable));
-		if (value_cpu & ~bprm->cap_post_exec_permitted.cap[i]) {
-			/*
-			 * insufficient to execute correctly
-			 */
-			ret = -EPERM;
-		}
+		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);
 	}
 
-	/*
-	 * 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 bprm->cap_effective ? ret : 0;
+	return 0;
 }
 
-/* Locate any VFS capabilities: */
-static int get_file_caps(struct linux_binprm *bprm)
+/*
+ * 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)
 {
 	struct dentry *dentry;
 	int rc = 0;
-	struct vfs_cap_data vcaps;
-	struct inode *inode;
+	struct cpu_vfs_cap_data vcaps;
 
-	if (bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID) {
-		bprm_clear_caps(bprm);
+	bprm_clear_caps(bprm);
+
+	if (!file_caps_enabled)
+		return 0;
+
+	if (bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID)
 		return 0;
-	}
 
 	dentry = dget(bprm->file->f_dentry);
-	inode = dentry->d_inode;
-	if (!inode->i_op || !inode->i_op->getxattr)
-		goto out;
 
-	rc = inode->i_op->getxattr(dentry, XATTR_NAME_CAPS, &vcaps,
-				   XATTR_CAPS_SZ);
-	if (rc == -ENODATA || rc == -EOPNOTSUPP) {
-		/* no data, that's ok */
-		rc = 0;
+	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;
 	}
-	if (rc < 0)
-		goto out;
 
-	rc = cap_from_disk(&vcaps, bprm, rc);
+	rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective);
 	if (rc == -EINVAL)
 		printk(KERN_NOTICE "%s: cap_from_disk returned %d for %s\n",
 		       __func__, rc, bprm->filename);
@@ -323,18 +413,57 @@ int cap_inode_killpriv(struct dentry *dentry)
 	return 0;
 }
 
-static inline int get_file_caps(struct linux_binprm *bprm)
+int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps)
+{
+	memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data));
+ 	return -ENODATA;
+}
+
+static inline int get_file_caps(struct linux_binprm *bprm, bool *effective)
 {
 	bprm_clear_caps(bprm);
 	return 0;
 }
 #endif
 
-int cap_bprm_set_security (struct linux_binprm *bprm)
+/*
+ * Determine whether a exec'ing process's new permitted capabilities should be
+ * limited to just what it already has.
+ *
+ * This prevents processes that are being ptraced from gaining access to
+ * CAP_SETPCAP, unless the process they're tracing already has it, and the
+ * binary they're executing has filecaps that elevate it.
+ *
+ *  Returns 1 if they should be limited, 0 if they are not.
+ */
+static inline int cap_limit_ptraced_target(void)
 {
+#ifndef CONFIG_SECURITY_FILE_CAPABILITIES
+	if (capable(CAP_SETPCAP))
+		return 0;
+#endif
+	return 1;
+}
+
+/**
+ * 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;
 	int ret;
 
-	ret = get_file_caps(bprm);
+	effective = false;
+	ret = get_file_caps(bprm, &effective);
+	if (ret < 0)
+		return ret;
 
 	if (!issecure(SECURE_NOROOT)) {
 		/*
@@ -342,75 +471,113 @@ int cap_bprm_set_security (struct linux_binprm *bprm)
 		 * 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 only the real uid is 0, we do not set the effective bit.
 		 */
-		if (bprm->e_uid == 0 || current->uid == 0) {
+		if (new->euid == 0 || new->uid == 0) {
 			/* pP' = (cap_bset & ~0) | (pI & ~0) */
-			bprm->cap_post_exec_permitted = cap_combine(
-				current->cap_bset, current->cap_inheritable
-				);
-			bprm->cap_effective = (bprm->e_uid == 0);
-			ret = 0;
+			new->cap_permitted = cap_combine(old->cap_bset,
+							 old->cap_inheritable);
 		}
+		if (new->euid == 0)
+			effective = true;
 	}
 
-	return ret;
-}
-
-void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe)
-{
-	if (bprm->e_uid != current->uid || bprm->e_gid != current->gid ||
-	    !cap_issubset(bprm->cap_post_exec_permitted,
-			  current->cap_permitted)) {
-		set_dumpable(current->mm, suid_dumpable);
-		current->pdeath_signal = 0;
-
-		if (unsafe & ~LSM_UNSAFE_PTRACE_CAP) {
-			if (!capable(CAP_SETUID)) {
-				bprm->e_uid = current->uid;
-				bprm->e_gid = current->gid;
-			}
-			if (cap_limit_ptraced_target()) {
-				bprm->cap_post_exec_permitted = cap_intersect(
-					bprm->cap_post_exec_permitted,
-					current->cap_permitted);
-			}
+	/* Don't let someone trace a set[ug]id/setpcap binary with the revised
+	 * credentials unless they have the appropriate permit
+	 */
+	if ((new->euid != old->uid ||
+	     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)) {
+			new->euid = new->uid;
+			new->egid = new->gid;
 		}
+		if (cap_limit_ptraced_target())
+			new->cap_permitted = cap_intersect(new->cap_permitted,
+							   old->cap_permitted);
 	}
 
-	current->suid = current->euid = current->fsuid = bprm->e_uid;
-	current->sgid = current->egid = current->fsgid = bprm->e_gid;
+	new->suid = new->fsuid = new->euid;
+	new->sgid = new->fsgid = new->egid;
 
-	/* For init, we want to retain the capabilities set
-	 * in the init_task struct. Thus we skip the usual
-	 * capability rules */
+	/* For init, we want to retain the capabilities set in the initial
+	 * task.  Thus we skip the usual capability rules
+	 */
 	if (!is_global_init(current)) {
-		current->cap_permitted = bprm->cap_post_exec_permitted;
-		if (bprm->cap_effective)
-			current->cap_effective = bprm->cap_post_exec_permitted;
+		if (effective)
+			new->cap_effective = new->cap_permitted;
 		else
-			cap_clear(current->cap_effective);
+			cap_clear(new->cap_effective);
 	}
+	bprm->cap_effective = effective;
 
-	/* AUD: Audit candidate if current->cap_effective is set */
+	/*
+	 * 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) ||
+		    new->euid != 0 || new->uid != 0 ||
+		    issecure(SECURE_NOROOT)) {
+			ret = audit_log_bprm_fcaps(bprm, new, old);
+			if (ret < 0)
+				return ret;
+		}
+	}
 
-	current->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
+	new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS);
+	return 0;
 }
 
-int cap_bprm_secureexec (struct linux_binprm *bprm)
+/**
+ * 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)
 {
-	if (current->uid != 0) {
+	const struct cred *cred = current_cred();
+
+	if (cred->uid != 0) {
 		if (bprm->cap_effective)
 			return 1;
-		if (!cap_isclear(bprm->cap_post_exec_permitted))
+		if (!cap_isclear(cred->cap_permitted))
 			return 1;
 	}
 
-	return (current->euid != current->uid ||
-		current->egid != current->gid);
+	return (cred->euid != cred->uid ||
+		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)
 {
@@ -418,28 +585,42 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name,