CRED: Fix regression in cap_capable() as shown up by sys_faccessat() [ver #3]

Fix a regression in cap_capable() due to:

	commit 3b11a1decef07c19443d24ae926982bc8ec9f4c0
	Author: David Howells <dhowells@redhat.com>
	Date:   Fri Nov 14 10:39:26 2008 +1100

	    CRED: Differentiate objective and effective subjective credentials on a task

The problem is that the above patch allows a process to have two sets of
credentials, and for the most part uses the subjective credentials when
accessing current's creds.

There is, however, one exception: cap_capable(), and thus capable(), uses the
real/objective credentials of the target task, whether or not it is the current
task.

Ordinarily this doesn't matter, since usually the two cred pointers in current
point to the same set of creds.  However, sys_faccessat() makes use of this
facility to override the credentials of the calling process to make its test,
without affecting the creds as seen from other processes.

One of the things sys_faccessat() does is to make an adjustment to the
effective capabilities mask, which cap_capable(), as it stands, then ignores.

The affected capability check is in generic_permission():

	if (!(mask & MAY_EXEC) || execute_ok(inode))
		if (capable(CAP_DAC_OVERRIDE))
			return 0;

This change passes the set of credentials to be tested down into the commoncap
and SELinux code.  The security functions called by capable() and
has_capability() select the appropriate set of credentials from the process
being checked.

This can be tested by compiling the following program from the XFS testsuite:

/*
 *  t_access_root.c - trivial test program to show permission bug.
 *
 *  Written by Michael Kerrisk - copyright ownership not pursued.
 *  Sourced from: http://linux.derkeiler.com/Mailing-Lists/Kernel/2003-10/6030.html
 */
#include <limits.h>
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/stat.h>

#define UID 500
#define GID 100
#define PERM 0
#define TESTPATH "/tmp/t_access"

static void
errExit(char *msg)
{
    perror(msg);
    exit(EXIT_FAILURE);
} /* errExit */

static void
accessTest(char *file, int mask, char *mstr)
{
    printf("access(%s, %s) returns %d\n", file, mstr, access(file, mask));
} /* accessTest */

int
main(int argc, char *argv[])
{
    int fd, perm, uid, gid;
    char *testpath;
    char cmd[PATH_MAX + 20];

    testpath = (argc > 1) ? argv[1] : TESTPATH;
    perm = (argc > 2) ? strtoul(argv[2], NULL, 8) : PERM;
    uid = (argc > 3) ? atoi(argv[3]) : UID;
    gid = (argc > 4) ? atoi(argv[4]) : GID;

    unlink(testpath);

    fd = open(testpath, O_RDWR | O_CREAT, 0);
    if (fd == -1) errExit("open");

    if (fchown(fd, uid, gid) == -1) errExit("fchown");
    if (fchmod(fd, perm) == -1) errExit("fchmod");
    close(fd);

    snprintf(cmd, sizeof(cmd), "ls -l %s", testpath);
    system(cmd);

    if (seteuid(uid) == -1) errExit("seteuid");

    accessTest(testpath, 0, "0");
    accessTest(testpath, R_OK, "R_OK");
    accessTest(testpath, W_OK, "W_OK");
    accessTest(testpath, X_OK, "X_OK");
    accessTest(testpath, R_OK | W_OK, "R_OK | W_OK");
    accessTest(testpath, R_OK | X_OK, "R_OK | X_OK");
    accessTest(testpath, W_OK | X_OK, "W_OK | X_OK");
    accessTest(testpath, R_OK | W_OK | X_OK, "R_OK | W_OK | X_OK");

    exit(EXIT_SUCCESS);
} /* main */

This can be run against an Ext3 filesystem as well as against an XFS
filesystem.  If successful, it will show:

	[root@andromeda src]# ./t_access_root /tmp/xxx 0 4043 4043
	---------- 1 dhowells dhowells 0 2008-12-31 03:00 /tmp/xxx
	access(/tmp/xxx, 0) returns 0
	access(/tmp/xxx, R_OK) returns 0
	access(/tmp/xxx, W_OK) returns 0
	access(/tmp/xxx, X_OK) returns -1
	access(/tmp/xxx, R_OK | W_OK) returns 0
	access(/tmp/xxx, R_OK | X_OK) returns -1
	access(/tmp/xxx, W_OK | X_OK) returns -1
	access(/tmp/xxx, R_OK | W_OK | X_OK) returns -1

If unsuccessful, it will show:

	[root@andromeda src]# ./t_access_root /tmp/xxx 0 4043 4043
	---------- 1 dhowells dhowells 0 2008-12-31 02:56 /tmp/xxx
	access(/tmp/xxx, 0) returns 0
	access(/tmp/xxx, R_OK) returns -1
	access(/tmp/xxx, W_OK) returns -1
	access(/tmp/xxx, X_OK) returns -1
	access(/tmp/xxx, R_OK | W_OK) returns -1
	access(/tmp/xxx, R_OK | X_OK) returns -1
	access(/tmp/xxx, W_OK | X_OK) returns -1
	access(/tmp/xxx, R_OK | W_OK | X_OK) returns -1

I've also tested the fix with the SELinux and syscalls LTP testsuites.

Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: J. Bruce Fields <bfields@citi.umich.edu>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: James Morris <jmorris@namei.org>

6 files changed, 94 insertions, 37 deletions

diff --git a/include/linux/capability.h b/include/linux/capability.h
index e22f48c2a46f..02bdb768d43b 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -529,8 +529,21 @@ extern const kernel_cap_t __cap_init_eff_set;
  *
  * Note that this does not set PF_SUPERPRIV on the task.
  */
-#define has_capability(t, cap) (security_capable((t), (cap)) == 0)
-#define has_capability_noaudit(t, cap) (security_capable_noaudit((t), (cap)) == 0)
+#define has_capability(t, cap) (security_real_capable((t), (cap)) == 0)
+
+/**
+ * has_capability_noaudit - Determine if a task has a superior capability available (unaudited)
+ * @t: The task in question
+ * @cap: The capability to be tested for
+ *
+ * Return true if the specified task has the given superior capability
+ * currently in effect, false if not, but don't write an audit message for the
+ * check.
+ *
+ * Note that this does not set PF_SUPERPRIV on the task.
+ */
+#define has_capability_noaudit(t, cap) \
+	(security_real_capable_noaudit((t), (cap)) == 0)
 
 extern int capable(int cap);
 
diff --git a/include/linux/security.h b/include/linux/security.h
index 3416cb85e77b..f9c390494f18 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -48,7 +48,8 @@ struct audit_krule;
  * These functions are in security/capability.c and are used
  * as the default capabilities functions
  */
-extern int cap_capable(struct task_struct *tsk, int cap, int audit);
+extern int cap_capable(struct task_struct *tsk, const struct cred *cred,
+		       int cap, int audit);
 extern int cap_settime(struct timespec *ts, struct timezone *tz);
 extern int cap_ptrace_may_access(struct task_struct *child, unsigned int mode);
 extern int cap_ptrace_traceme(struct task_struct *parent);
@@ -1195,9 +1196,12 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
  *	@permitted contains the permitted capability set.
  *	Return 0 and update @new if permission is granted.
  * @capable:
- *	Check whether the @tsk process has the @cap capability.
+ *	Check whether the @tsk process has the @cap capability in the indicated
+ *	credentials.
  *	@tsk contains the task_struct for the process.
+ *	@cred contains the credentials to use.
  *	@cap contains the capability <include/linux/capability.h>.
+ *	@audit: Whether to write an audit message or not
  *	Return 0 if the capability is granted for @tsk.
  * @acct:
  *	Check permission before enabling or disabling process accounting.  If
@@ -1290,7 +1294,8 @@ struct security_operations {
 		       const kernel_cap_t *effective,
 		       const kernel_cap_t *inheritable,
 		       const kernel_cap_t *permitted);
-	int (*capable) (struct task_struct *tsk, int cap, int audit);
+	int (*capable) (struct task_struct *tsk, const struct cred *cred,
+			int cap, int audit);
 	int (*acct) (struct file *file);
 	int (*sysctl) (struct ctl_table *table, int op);
 	int (*quotactl) (int cmds, int type, int id, struct super_block *sb);
@@ -1556,8 +1561,9 @@ int security_capset(struct cred *new, const struct cred *old,
 		    const kernel_cap_t *effective,
 		    const kernel_cap_t *inheritable,
 		    const kernel_cap_t *permitted);
-int security_capable(struct task_struct *tsk, int cap);
-int security_capable_noaudit(struct task_struct *tsk, int cap);
+int security_capable(int cap);
+int security_real_capable(struct task_struct *tsk, int cap);
+int security_real_capable_noaudit(struct task_struct *tsk, int cap);
 int security_acct(struct file *file);
 int security_sysctl(struct ctl_table *table, int op);
 int security_quotactl(int cmds, int type, int id, struct super_block *sb);
@@ -1754,14 +1760,31 @@ static inline int security_capset(struct cred *new,
 	return cap_capset(new, old, effective, inheritable, permitted);
 }
 
-static inline int security_capable(struct task_struct *tsk, int cap)
+static inline int security_capable(int cap)
 {
-	return cap_capable(tsk, cap, SECURITY_CAP_AUDIT);
+	return cap_capable(current, current_cred(), cap, SECURITY_CAP_AUDIT);
 }
 
-static inline int security_capable_noaudit(struct task_struct *tsk, int cap)
+static inline int security_real_capable(struct task_struct *tsk, int cap)
 {
-	return cap_capable(tsk, cap, SECURITY_CAP_NOAUDIT);
+	int ret;
+
+	rcu_read_lock();
+	ret = cap_capable(tsk, __task_cred(tsk), cap, SECURITY_CAP_AUDIT);
+	rcu_read_unlock();
+	return ret;
+}
+
+static inline
+int security_real_capable_noaudit(struct task_struct *tsk, int cap)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = cap_capable(tsk, __task_cred(tsk), cap,
+			       SECURITY_CAP_NOAUDIT);
+	rcu_read_unlock();
+	return ret;
 }
 
 static inline int security_acct(struct file *file)
diff --git a/kernel/capability.c b/kernel/capability.c
index 36b4b4daebec..df62f53f84ac 100644
--- a/kernel/capability.c
+++ b/kernel/capability.c
@@ -308,7 +308,7 @@ int capable(int cap)
 		BUG();
 	}
 
-	if (has_capability(current, cap)) {
+	if (security_capable(cap) == 0) {
 		current->flags |= PF_SUPERPRIV;
 		return 1;
 	}
diff --git a/security/commoncap.c b/security/commoncap.c
index 79713545cd63..f0e671dcfff0 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -45,26 +45,22 @@ EXPORT_SYMBOL(cap_netlink_recv);
 /**
  * cap_capable - Determine whether a task has a particular effective capability
  * @tsk: The task to query
+ * @cred: The credentials to use
  * @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.
+ * 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(struct task_struct *tsk, int cap, int audit)
+int cap_capable(struct task_struct *tsk, const struct cred *cred, int cap,
+		int audit)
 {
-	__u32 cap_raised;
-
-	/* Derived from include/linux/sched.h:capable. */
-	rcu_read_lock();
-	cap_raised = cap_raised(__task_cred(tsk)->cap_effective, cap);
-	rcu_read_unlock();
-	return cap_raised ? 0 : -EPERM;
+	return cap_raised(cred->cap_effective, cap) ? 0 : -EPERM;
 }
 
 /**
@@ -160,7 +156,8 @@ 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, CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0)
+	if (cap_capable(current, current_cred(), CAP_SETPCAP,
+			SECURITY_CAP_AUDIT) == 0)
 		return 0;
 #endif
 	return 1;
@@ -869,7 +866,8 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 		     & (new->securebits ^ arg2))			/*[1]*/
 		    || ((new->securebits & SECURE_ALL_LOCKS & ~arg2))	/*[2]*/
 		    || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS))	/*[3]*/
-		    || (cap_capable(current, CAP_SETPCAP, SECURITY_CAP_AUDIT) != 0) /*[4]*/
+		    || (cap_capable(current, current_cred(), CAP_SETPCAP,
+				    SECURITY_CAP_AUDIT) != 0)		/*[4]*/
 			/*
 			 * [1] no changing of bits that are locked
 			 * [2] no unlocking of locks
@@ -950,7 +948,8 @@ int cap_vm_enough_memory(struct mm_struct *mm, long pages)
 {
 	int cap_sys_admin = 0;
 
-	if (cap_capable(current, CAP_SYS_ADMIN, SECURITY_CAP_NOAUDIT) == 0)
+	if (cap_capable(current, current_cred(), CAP_SYS_ADMIN,
+			SECURITY_CAP_NOAUDIT) == 0)
 		cap_sys_admin = 1;
 	return __vm_enough_memory(mm, pages, cap_sys_admin);
 }
diff --git a/security/security.c b/security/security.c
index d85dbb37c972..a02f243f09c0 100644
--- a/security/security.c
+++ b/security/security.c
@@ -154,14 +154,32 @@ int security_capset(struct cred *new, const struct cred *old,
 				    effective, inheritable, permitted);
 }
 
-int security_capable(struct task_struct *tsk, int cap)
+int security_capable(int cap)
 {
-	return security_ops->capable(tsk, cap, SECURITY_CAP_AUDIT);
+	return security_ops->capable(current, current_cred(), cap,
+				     SECURITY_CAP_AUDIT);
 }
 
-int security_capable_noaudit(struct task_struct *tsk, int cap)
+int security_real_capable(struct task_struct *tsk, int cap)
 {
-	return security_ops->capable(tsk, cap, SECURITY_CAP_NOAUDIT);
+	const struct cred *cred;
+	int ret;
+
+	cred = get_task_cred(tsk);
+	ret = security_ops->capable(tsk, cred, cap, SECURITY_CAP_AUDIT);
+	put_cred(cred);
+	return ret;
+}
+
+int security_real_capable_noaudit(struct task_struct *tsk, int cap)
+{
+	const struct cred *cred;
+	int ret;
+
+	cred = get_task_cred(tsk);
+	ret = security_ops->capable(tsk, cred, cap, SECURITY_CAP_NOAUDIT);
+	put_cred(cred);
+	return ret;
 }
 
 int security_acct(struct file *file)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index df30a7555d8a..00815973d412 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1433,12 +1433,13 @@ static int current_has_perm(const struct task_struct *tsk,
 
 /* Check whether a task is allowed to use a capability. */
 static int task_has_capability(struct task_struct *tsk,
+			       const struct cred *cred,
 			       int cap, int audit)
 {
 	struct avc_audit_data ad;
 	struct av_decision avd;
 	u16 sclass;
-	u32 sid = task_sid(tsk);
+	u32 sid = cred_sid(cred);
 	u32 av = CAP_TO_MASK(cap);
 	int rc;
 
@@ -1865,15 +1866,16 @@ static int selinux_capset(struct cred *new, const struct cred *old,
 	return cred_has_perm(old, new, PROCESS__SETCAP);
 }
 
-static int selinux_capable(struct task_struct *tsk, int cap, int audit)
+static int selinux_capable(struct task_struct *tsk, const struct cred *cred,
+			   int cap, int audit)
 {
 	int rc;
 
-	rc = secondary_ops->capable(tsk, cap, audit);
+	rc = secondary_ops->capable(tsk, cred, cap, audit);
 	if (rc)
 		return rc;
 
-	return task_has_capability(tsk, cap, audit);
+	return task_has_capability(tsk, cred, cap, audit);
 }
 
 static int selinux_sysctl_get_sid(ctl_table *table, u16 tclass, u32 *sid)
@@ -2037,7 +2039,8 @@ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages)
 {
 	int rc, cap_sys_admin = 0;
 
-	rc = selinux_capable(current, CAP_SYS_ADMIN, SECURITY_CAP_NOAUDIT);
+	rc = selinux_capable(current, current_cred(), CAP_SYS_ADMIN,
+			     SECURITY_CAP_NOAUDIT);
 	if (rc == 0)
 		cap_sys_admin = 1;
 
@@ -2880,7 +2883,8 @@ static int selinux_inode_getsecurity(const struct inode *inode, const char *name
 	 * and lack of permission just means that we fall back to the
 	 * in-core context value, not a denial.
 	 */
-	error = selinux_capable(current, CAP_MAC_ADMIN, SECURITY_CAP_NOAUDIT);
+	error = selinux_capable(current, current_cred(), CAP_MAC_ADMIN,
+				SECURITY_CAP_NOAUDIT);
 	if (!error)
 		error = security_sid_to_context_force(isec->sid, &context,
 						      &size);