CRED: Fix regression in cap_capable() as shown up by sys_faccessat() [ver #2]

Fix a regression in cap_capable() due to:

	commit 5ff7711e635b32f0a1e558227d030c7e45b4a465
	Author: David Howells <dhowells@redhat.com>
	Date:   Wed Dec 31 02:52:28 2008 +0000

	    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 splits capable() from has_capability() down into the commoncap and
SELinux code.  The capable() security op now only deals with the current
process, and uses the current process's subjective creds.  A new security op -
task_capable() - is introduced that can check any task's objective creds.

strictly the capable() security op is superfluous with the presence of the
task_capable() op, however it should be faster to call the capable() op since
two fewer arguments need be passed down through the various layers.

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>
Signed-off-by: James Morris <jmorris@namei.org>

2 files changed, 55 insertions, 11 deletions

diff --git a/include/linux/capability.h b/include/linux/capability.h
index e22f48c2a46..5b8a1321445 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_task_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_task_capable_noaudit((t), (cap)) == 0)
 
 extern int capable(int cap);
 
diff --git a/include/linux/security.h b/include/linux/security.h
index 3416cb85e77..76989b8bc34 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -48,7 +48,9 @@ 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(int cap, int audit);
+extern int cap_task_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 +1197,18 @@ 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 current process has the @cap capability in its
+ *      subjective/effective credentials.
+ *	@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.
+ * @task_capable:
+ *	Check whether the @tsk process has the @cap capability in its
+ *      objective/real 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 +1301,9 @@ 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) (int cap, int audit);
+	int (*task_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 +1569,9 @@ 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_task_capable(struct task_struct *tsk, int cap);
+int security_task_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 +1768,31 @@ 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(cap, SECURITY_CAP_AUDIT);
 }
 
-static inline int security_capable_noaudit(struct task_struct *tsk, int cap)
+static inline int security_task_capable(struct task_struct *tsk, int cap)
 {
-	return cap_capable(tsk, cap, SECURITY_CAP_NOAUDIT);
+	int ret;
+
+	rcu_read_lock();
+	ret = cap_task_capable(tsk, __task_cred(tsk), cap, SECURITY_CAP_AUDIT);
+	rcu_read_unlock();
+	return ret;
+}
+
+static inline
+int security_task_capable_noaudit(struct task_struct *tsk, int cap)
+{
+	int ret;
+
+	rcu_read_lock();
+	ret = cap_task_capable(tsk, __task_cred(tsk), cap,
+			       SECURITY_CAP_NOAUDIT);
+	rcu_read_unlock();
+	return ret;
 }
 
 static inline int security_acct(struct file *file)