capability: just use a 'u64' instead of a 'u32[2]' array

Back in 2008 we extended the capability bits from 32 to 64, and we did
it by extending the single 32-bit capability word from one word to an
array of two words.  It was then obfuscated by hiding the "2" behind two
macro expansions, with the reasoning being that maybe it gets extended
further some day.

That reasoning may have been valid at the time, but the last thing we
want to do is to extend the capability set any more.  And the array of
values not only causes source code oddities (with loops to deal with
it), but also results in worse code generation.  It's a lose-lose
situation.

So just change the 'u32[2]' into a 'u64' and be done with it.

We still have to deal with the fact that the user space interface is
designed around an array of these 32-bit values, but that was the case
before too, since the array layouts were different (ie user space
doesn't use an array of 32-bit values for individual capability masks,
but an array of 32-bit slices of multiple masks).

So that marshalling of data is actually simplified too, even if it does
remain somewhat obscure and odd.

This was all triggered by my reaction to the new "cap_isidentical()"
introduced recently.  By just using a saner data structure, it went from

	unsigned __capi;
	CAP_FOR_EACH_U32(__capi) {
		if (a.cap[__capi] != b.cap[__capi])
			return false;
	}
	return true;

to just being

	return a.val == b.val;

instead.  Which is rather more obvious both to humans and to compilers.

Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Cc: Serge Hallyn <serge@hallyn.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Paul Moore <paul@paul-moore.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 22 insertions, 27 deletions

diff --git a/security/commoncap.c b/security/commoncap.c
index aec62db55271..5bb7d1e96277 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -589,7 +589,6 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
 					  bool *has_fcap)
 {
 	struct cred *new = bprm->cred;
-	unsigned i;
 	int ret = 0;
 
 	if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE)
@@ -598,22 +597,17 @@ static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps,
 	if (caps->magic_etc & VFS_CAP_REVISION_MASK)
 		*has_fcap = true;
 
-	CAP_FOR_EACH_U32(i) {
-		__u32 permitted = caps->permitted.cap[i];
-		__u32 inheritable = caps->inheritable.cap[i];
-
-		/*
-		 * pP' = (X & fP) | (pI & fI)
-		 * The addition of pA' is handled later.
-		 */
-		new->cap_permitted.cap[i] =
-			(new->cap_bset.cap[i] & permitted) |
-			(new->cap_inheritable.cap[i] & inheritable);
+	/*
+	 * pP' = (X & fP) | (pI & fI)
+	 * The addition of pA' is handled later.
+	 */
+	new->cap_permitted.val =
+		(new->cap_bset.val & caps->permitted.val) |
+		(new->cap_inheritable.val & caps->inheritable.val);
 
-		if (permitted & ~new->cap_permitted.cap[i])
-			/* insufficient to execute correctly */
-			ret = -EPERM;
-	}
+	if (caps->permitted.val & ~new->cap_permitted.val)
+		/* insufficient to execute correctly */
+		ret = -EPERM;
 
 	/*
 	 * For legacy apps, with no internal support for recognizing they
@@ -644,7 +638,6 @@ int get_vfs_caps_from_disk(struct mnt_idmap *idmap,
 {
 	struct inode *inode = d_backing_inode(dentry);
 	__u32 magic_etc;
-	unsigned tocopy, i;
 	int size;
 	struct vfs_ns_cap_data data, *nscaps = &data;
 	struct vfs_cap_data *caps = (struct vfs_cap_data *) &data;
@@ -677,17 +670,14 @@ int get_vfs_caps_from_disk(struct mnt_idmap *idmap,
 	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;
 	case VFS_CAP_REVISION_3:
 		if (size != XATTR_CAPS_SZ_3)
 			return -EINVAL;
-		tocopy = VFS_CAP_U32_3;
 		rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid));
 		break;
 
@@ -705,15 +695,20 @@ int get_vfs_caps_from_disk(struct mnt_idmap *idmap,
 	if (!rootid_owns_currentns(rootvfsuid))
 		return -ENODATA;
 
-	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.val = le32_to_cpu(caps->data[0].permitted);
+	cpu_caps->inheritable.val = le32_to_cpu(caps->data[0].inheritable);
+
+	/*
+	 * Rev1 had just a single 32-bit word, later expanded
+	 * to a second one for the high bits
+	 */
+	if ((magic_etc & VFS_CAP_REVISION_MASK) != VFS_CAP_REVISION_1) {
+		cpu_caps->permitted.val += (u64)le32_to_cpu(caps->data[1].permitted) << 32;
+		cpu_caps->inheritable.val += (u64)le32_to_cpu(caps->data[1].inheritable) << 32;
 	}
 
-	cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
-	cpu_caps->inheritable.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK;
+	cpu_caps->permitted.val &= CAP_VALID_MASK;
+	cpu_caps->inheritable.val &= CAP_VALID_MASK;
 
 	cpu_caps->rootid = vfsuid_into_kuid(rootvfsuid);