Change the cap_rights_t type from uint64_t to a structure that we can extend

in the future in a backward compatible (API and ABI) way.

The cap_rights_t represents capability rights. We used to use one bit to
represent one right, but we are running out of spare bits. Currently the new
structure provides place for 114 rights (so 50 more than the previous
cap_rights_t), but it is possible to grow the structure to hold at least 285
rights, although we can make it even larger if 285 rights won't be enough.

The structure definition looks like this:

	struct cap_rights {
		uint64_t	cr_rights[CAP_RIGHTS_VERSION + 2];
	};

The initial CAP_RIGHTS_VERSION is 0.

The top two bits in the first element of the cr_rights[] array contain total
number of elements in the array - 2. This means if those two bits are equal to
0, we have 2 array elements.

The top two bits in all remaining array elements should be 0.
The next five bits in all array elements contain array index. Only one bit is
used and bit position in this five-bits range defines array index. This means
there can be at most five array elements in the future.

To define new right the CAPRIGHT() macro must be used. The macro takes two
arguments - an array index and a bit to set, eg.

	#define	CAP_PDKILL	CAPRIGHT(1, 0x0000000000000800ULL)

We still support aliases that combine few rights, but the rights have to belong
to the same array element, eg:

	#define	CAP_LOOKUP	CAPRIGHT(0, 0x0000000000000400ULL)
	#define	CAP_FCHMOD	CAPRIGHT(0, 0x0000000000002000ULL)

	#define	CAP_FCHMODAT	(CAP_FCHMOD | CAP_LOOKUP)

There is new API to manage the new cap_rights_t structure:

	cap_rights_t *cap_rights_init(cap_rights_t *rights, ...);
	void cap_rights_set(cap_rights_t *rights, ...);
	void cap_rights_clear(cap_rights_t *rights, ...);
	bool cap_rights_is_set(const cap_rights_t *rights, ...);

	bool cap_rights_is_valid(const cap_rights_t *rights);
	void cap_rights_merge(cap_rights_t *dst, const cap_rights_t *src);
	void cap_rights_remove(cap_rights_t *dst, const cap_rights_t *src);
	bool cap_rights_contains(const cap_rights_t *big, const cap_rights_t *little);

Capability rights to the cap_rights_init(), cap_rights_set(),
cap_rights_clear() and cap_rights_is_set() functions are provided by
separating them with commas, eg:

	cap_rights_t rights;

	cap_rights_init(&rights, CAP_READ, CAP_WRITE, CAP_FSTAT);

There is no need to terminate the list of rights, as those functions are
actually macros that take care of the termination, eg:

	#define	cap_rights_set(rights, ...)				\
		__cap_rights_set((rights), __VA_ARGS__, 0ULL)
	void __cap_rights_set(cap_rights_t *rights, ...);

Thanks to using one bit as an array index we can assert in those functions that
there are no two rights belonging to different array elements provided
together. For example this is illegal and will be detected, because CAP_LOOKUP
belongs to element 0 and CAP_PDKILL to element 1:

	cap_rights_init(&rights, CAP_LOOKUP | CAP_PDKILL);

Providing several rights that belongs to the same array's element this way is
correct, but is not advised. It should only be used for aliases definition.

This commit also breaks compatibility with some existing Capsicum system calls,
but I see no other way to do that. This should be fine as Capsicum is still
experimental and this change is not going to 9.x.

Sponsored by:	The FreeBSD Foundation

7 files changed, 39 insertions, 7 deletions

diff --git a/lib/libc/Makefile b/lib/libc/Makefile
index cf2d2aa..2806cc7 100644
--- a/lib/libc/Makefile
+++ b/lib/libc/Makefile
@@ -100,6 +100,7 @@ NOASM=
 CFLAGS+= -DYP
 .include "${.CURDIR}/yp/Makefile.inc"
 .endif
+.include "${.CURDIR}/capability/Makefile.inc"
 .if ${MK_HESIOD} != "no"
 CFLAGS+= -DHESIOD
 .endif
diff --git a/lib/libc/capability/Makefile.inc b/lib/libc/capability/Makefile.inc
new file mode 100644
index 0000000..934fc8b
--- /dev/null
+++ b/lib/libc/capability/Makefile.inc
@@ -0,0 +1,19 @@
+# $FreeBSD$
+
+# capability sources
+.PATH: ${.CURDIR}/../../sys/kern
+
+SRCS+=	subr_capability.c
+
+SYM_MAPS+=	${.CURDIR}/capability/Symbol.map
+
+#MAN+=	cap_rights_init.3
+
+#MLINKS+=cap_rights_init.3 cap_rights_set.3
+#MLINKS+=cap_rights_init.3 cap_rights_clear.3
+#MLINKS+=cap_rights_init.3 cap_rights_is_set.3
+#MLINKS+=cap_rights_init.3 cap_rights_is_valid.3
+#MLINKS+=cap_rights_init.3 cap_rights_merge.3
+#MLINKS+=cap_rights_init.3 cap_rights_remove.3
+#MLINKS+=cap_rights_init.3 cap_rights_contains.3
+
diff --git a/lib/libc/capability/Symbol.map b/lib/libc/capability/Symbol.map
new file mode 100644
index 0000000..c5c18c2
--- /dev/null
+++ b/lib/libc/capability/Symbol.map
@@ -0,0 +1,14 @@
+/*
+ * $FreeBSD$
+ */
+
+FBSD_1.3 {
+	__cap_rights_clear;
+	cap_rights_contains;
+	__cap_rights_init;
+	__cap_rights_is_set;
+	cap_rights_is_valid;
+	cap_rights_merge;
+	cap_rights_remove;
+	__cap_rights_set;
+};
diff --git a/lib/libc/include/compat.h b/lib/libc/include/compat.h
index 3739fe1..7694540 100644
--- a/lib/libc/include/compat.h
+++ b/lib/libc/include/compat.h
@@ -42,8 +42,6 @@ __sym_compat(__semctl, freebsd7___semctl, FBSD_1.0);
 __sym_compat(msgctl, freebsd7_msgctl, FBSD_1.0);
 __sym_compat(shmctl, freebsd7_shmctl, FBSD_1.0);
 
-__sym_compat(cap_getrights, cap_rights_get, FBSD_1.2);
-
 #undef __sym_compat
 
 #endif	/* __LIBC_COMPAT_H__ */
diff --git a/lib/libc/sys/Symbol.map b/lib/libc/sys/Symbol.map
index 4f1104e..222f5f0 100644
--- a/lib/libc/sys/Symbol.map
+++ b/lib/libc/sys/Symbol.map
@@ -363,7 +363,6 @@ FBSD_1.1 {
 FBSD_1.2 {
 	cap_enter;
 	cap_getmode;
-	cap_new;
 	getloginclass;
 	pdfork;
 	pdgetpid;
@@ -385,7 +384,7 @@ FBSD_1.3 {
 	cap_fcntls_limit;
 	cap_ioctls_get;
 	cap_ioctls_limit;
-	cap_rights_get;
+	__cap_rights_get;
 	cap_rights_limit;
 	cap_sandboxed;
 	chflagsat;
diff --git a/lib/libprocstat/libprocstat.c b/lib/libprocstat/libprocstat.c
index dfb5ed3..9056151 100644
--- a/lib/libprocstat/libprocstat.c
+++ b/lib/libprocstat/libprocstat.c
@@ -378,7 +378,7 @@ procstat_freefiles(struct procstat *procstat, struct filestat_list *head)
 
 static struct filestat *
 filestat_new_entry(void *typedep, int type, int fd, int fflags, int uflags,
-    int refcount, off_t offset, char *path, cap_rights_t cap_rights)
+    int refcount, off_t offset, char *path, cap_rights_t *cap_rightsp)
 {
 	struct filestat *entry;
 
@@ -395,7 +395,7 @@ filestat_new_entry(void *typedep, int type, int fd, int fflags, int uflags,
 	entry->fs_ref_count = refcount;
 	entry->fs_offset = offset;
 	entry->fs_path = path;
-	entry->fs_cap_rights = cap_rights;
+	entry->fs_cap_rights = *cap_rightsp;
 	return (entry);
 }
 
@@ -851,7 +851,7 @@ procstat_getfiles_sysctl(struct procstat *procstat, struct kinfo_proc *kp,
 		 * Create filestat entry.
 		 */
 		entry = filestat_new_entry(kif, type, fd, fflags, uflags,
-		    refcount, offset, path, cap_rights);
+		    refcount, offset, path, &cap_rights);
 		if (entry != NULL)
 			STAILQ_INSERT_TAIL(head, entry, next);
 	}
diff --git a/lib/libprocstat/libprocstat.h b/lib/libprocstat/libprocstat.h
index 65a5eb9..7af6ccb 100644
--- a/lib/libprocstat/libprocstat.h
+++ b/lib/libprocstat/libprocstat.h
@@ -36,6 +36,7 @@
 #ifndef ZFS
 #include <sys/elf.h>
 #endif
+#include <sys/caprights.h>
 
 /*
  * Vnode types.