Merge Capsicum overhaul:

- Capability is no longer separate descriptor type. Now every descriptor
  has set of its own capability rights.

- The cap_new(2) system call is left, but it is no longer documented and
  should not be used in new code.

- The new syscall cap_rights_limit(2) should be used instead of
  cap_new(2), which limits capability rights of the given descriptor
  without creating a new one.

- The cap_getrights(2) syscall is renamed to cap_rights_get(2).

- If CAP_IOCTL capability right is present we can further reduce allowed
  ioctls list with the new cap_ioctls_limit(2) syscall. List of allowed
  ioctls can be retrived with cap_ioctls_get(2) syscall.

- If CAP_FCNTL capability right is present we can further reduce fcntls
  that can be used with the new cap_fcntls_limit(2) syscall and retrive
  them with cap_fcntls_get(2).

- To support ioctl and fcntl white-listing the filedesc structure was
  heavly modified.

- The audit subsystem, kdump and procstat tools were updated to
  recognize new syscalls.

- Capability rights were revised and eventhough I tried hard to provide
  backward API and ABI compatibility there are some incompatible changes
  that are described in detail below:

	CAP_CREATE old behaviour:
	- Allow for openat(2)+O_CREAT.
	- Allow for linkat(2).
	- Allow for symlinkat(2).
	CAP_CREATE new behaviour:
	- Allow for openat(2)+O_CREAT.

	Added CAP_LINKAT:
	- Allow for linkat(2). ABI: Reuses CAP_RMDIR bit.
	- Allow to be target for renameat(2).

	Added CAP_SYMLINKAT:
	- Allow for symlinkat(2).

	Removed CAP_DELETE. Old behaviour:
	- Allow for unlinkat(2) when removing non-directory object.
	- Allow to be source for renameat(2).

	Removed CAP_RMDIR. Old behaviour:
	- Allow for unlinkat(2) when removing directory.

	Added CAP_RENAMEAT:
	- Required for source directory for the renameat(2) syscall.

	Added CAP_UNLINKAT (effectively it replaces CAP_DELETE and CAP_RMDIR):
	- Allow for unlinkat(2) on any object.
	- Required if target of renameat(2) exists and will be removed by this
	  call.

	Removed CAP_MAPEXEC.

	CAP_MMAP old behaviour:
	- Allow for mmap(2) with any combination of PROT_NONE, PROT_READ and
	  PROT_WRITE.
	CAP_MMAP new behaviour:
	- Allow for mmap(2)+PROT_NONE.

	Added CAP_MMAP_R:
	- Allow for mmap(PROT_READ).
	Added CAP_MMAP_W:
	- Allow for mmap(PROT_WRITE).
	Added CAP_MMAP_X:
	- Allow for mmap(PROT_EXEC).
	Added CAP_MMAP_RW:
	- Allow for mmap(PROT_READ | PROT_WRITE).
	Added CAP_MMAP_RX:
	- Allow for mmap(PROT_READ | PROT_EXEC).
	Added CAP_MMAP_WX:
	- Allow for mmap(PROT_WRITE | PROT_EXEC).
	Added CAP_MMAP_RWX:
	- Allow for mmap(PROT_READ | PROT_WRITE | PROT_EXEC).

	Renamed CAP_MKDIR to CAP_MKDIRAT.
	Renamed CAP_MKFIFO to CAP_MKFIFOAT.
	Renamed CAP_MKNODE to CAP_MKNODEAT.

	CAP_READ old behaviour:
	- Allow pread(2).
	- Disallow read(2), readv(2) (if there is no CAP_SEEK).
	CAP_READ new behaviour:
	- Allow read(2), readv(2).
	- Disallow pread(2) (CAP_SEEK was also required).

	CAP_WRITE old behaviour:
	- Allow pwrite(2).
	- Disallow write(2), writev(2) (if there is no CAP_SEEK).
	CAP_WRITE new behaviour:
	- Allow write(2), writev(2).
	- Disallow pwrite(2) (CAP_SEEK was also required).

	Added convinient defines:

	#define	CAP_PREAD		(CAP_SEEK | CAP_READ)
	#define	CAP_PWRITE		(CAP_SEEK | CAP_WRITE)
	#define	CAP_MMAP_R		(CAP_MMAP | CAP_SEEK | CAP_READ)
	#define	CAP_MMAP_W		(CAP_MMAP | CAP_SEEK | CAP_WRITE)
	#define	CAP_MMAP_X		(CAP_MMAP | CAP_SEEK | 0x0000000000000008ULL)
	#define	CAP_MMAP_RW		(CAP_MMAP_R | CAP_MMAP_W)
	#define	CAP_MMAP_RX		(CAP_MMAP_R | CAP_MMAP_X)
	#define	CAP_MMAP_WX		(CAP_MMAP_W | CAP_MMAP_X)
	#define	CAP_MMAP_RWX		(CAP_MMAP_R | CAP_MMAP_W | CAP_MMAP_X)
	#define	CAP_RECV		CAP_READ
	#define	CAP_SEND		CAP_WRITE

	#define	CAP_SOCK_CLIENT \
		(CAP_CONNECT | CAP_GETPEERNAME | CAP_GETSOCKNAME | CAP_GETSOCKOPT | \
		 CAP_PEELOFF | CAP_RECV | CAP_SEND | CAP_SETSOCKOPT | CAP_SHUTDOWN)
	#define	CAP_SOCK_SERVER \
		(CAP_ACCEPT | CAP_BIND | CAP_GETPEERNAME | CAP_GETSOCKNAME | \
		 CAP_GETSOCKOPT | CAP_LISTEN | CAP_PEELOFF | CAP_RECV | CAP_SEND | \
		 CAP_SETSOCKOPT | CAP_SHUTDOWN)

	Added defines for backward API compatibility:

	#define	CAP_MAPEXEC		CAP_MMAP_X
	#define	CAP_DELETE		CAP_UNLINKAT
	#define	CAP_MKDIR		CAP_MKDIRAT
	#define	CAP_RMDIR		CAP_UNLINKAT
	#define	CAP_MKFIFO		CAP_MKFIFOAT
	#define	CAP_MKNOD		CAP_MKNODAT
	#define	CAP_SOCK_ALL		(CAP_SOCK_CLIENT | CAP_SOCK_SERVER)

Sponsored by:	The FreeBSD Foundation
Reviewed by:	Christoph Mallon <christoph.mallon@gmx.de>
Many aspects discussed with:	rwatson, benl, jonathan
ABI compatibility discussed with:	kib

1 files changed, 16 insertions, 30 deletions

diff --git a/sys/kern/uipc_syscalls.c b/sys/kern/uipc_syscalls.c
index 665eb6d..847db35 100644
--- a/sys/kern/uipc_syscalls.c
+++ b/sys/kern/uipc_syscalls.c
@@ -121,38 +121,20 @@ SYSCTL_INT(_kern_ipc, OID_AUTO, nsfbufsused, CTLFLAG_RD, &nsfbufsused, 0,
     "Number of sendfile(2) sf_bufs in use");
 
 /*
- * Convert a user file descriptor to a kernel file entry and check that, if
- * it is a capability, the right rights are present. A reference on the file
- * entry is held upon returning.
+ * Convert a user file descriptor to a kernel file entry and check if required
+ * capability rights are present.
+ * A reference on the file entry is held upon returning.
  */
 static int
 getsock_cap(struct filedesc *fdp, int fd, cap_rights_t rights,
     struct file **fpp, u_int *fflagp)
 {
 	struct file *fp;
-#ifdef CAPABILITIES
-	struct file *fp_fromcap;
 	int error;
-#endif
 
-	if (fdp == NULL || (fp = fget_unlocked(fdp, fd)) == NULL)
-		return (EBADF);
-#ifdef CAPABILITIES
-	/*
-	 * If the file descriptor is for a capability, test rights and use
-	 * the file descriptor referenced by the capability.
-	 */
-	error = cap_funwrap(fp, rights, &fp_fromcap);
-	if (error) {
-		fdrop(fp, curthread);
+	error = fget_unlocked(fdp, fd, rights, 0, &fp, NULL);
+	if (error != 0)
 		return (error);
-	}
-	if (fp != fp_fromcap) {
-		fhold(fp_fromcap);
-		fdrop(fp, curthread);
-		fp = fp_fromcap;
-	}
-#endif /* CAPABILITIES */
 	if (fp->f_type != DTYPE_SOCKET) {
 		fdrop(fp, curthread);
 		return (ENOTSOCK);
@@ -765,7 +747,7 @@ kern_sendit(td, s, mp, flags, control, segflg)
 #endif
 
 	AUDIT_ARG_FD(s);
-	rights = CAP_WRITE;
+	rights = CAP_SEND;
 	if (mp->msg_name != NULL) {
 		AUDIT_ARG_SOCKADDR(td, mp->msg_name);
 		rights |= CAP_CONNECT;
@@ -974,7 +956,7 @@ kern_recvit(td, s, mp, fromseg, controlp)
 		*controlp = NULL;
 
 	AUDIT_ARG_FD(s);
-	error = getsock_cap(td->td_proc->p_fd, s, CAP_READ, &fp, NULL);
+	error = getsock_cap(td->td_proc->p_fd, s, CAP_RECV, &fp, NULL);
 	if (error)
 		return (error);
 	so = fp->f_data;
@@ -1850,7 +1832,11 @@ kern_sendfile(struct thread *td, struct sendfile_args *uap,
 	 * we send only the header/trailer and no payload data.
 	 */
 	AUDIT_ARG_FD(uap->fd);
-	if ((error = fgetvp_read(td, uap->fd, CAP_READ, &vp)) != 0)
+	/*
+	 * sendfile(2) can start at any offset within a file so we require
+	 * CAP_READ+CAP_SEEK = CAP_PREAD.
+	 */
+	if ((error = fgetvp_read(td, uap->fd, CAP_PREAD, &vp)) != 0)
 		goto out;
 	vn_lock(vp, LK_SHARED | LK_RETRY);
 	if (vp->v_type == VREG) {
@@ -1886,7 +1872,7 @@ kern_sendfile(struct thread *td, struct sendfile_args *uap,
 	 * The socket must be a stream socket and connected.
 	 * Remember if it a blocking or non-blocking socket.
 	 */
-	if ((error = getsock_cap(td->td_proc->p_fd, uap->s, CAP_WRITE,
+	if ((error = getsock_cap(td->td_proc->p_fd, uap->s, CAP_SEND,
 	    &sock_fp, NULL)) != 0)
 		goto out;
 	so = sock_fp->f_data;
@@ -2423,7 +2409,7 @@ sys_sctp_generic_sendmsg (td, uap)
 		u_sinfo = &sinfo;
 	}
 
-	rights = CAP_WRITE;
+	rights = CAP_SEND;
 	if (uap->tolen) {
 		error = getsockaddr(&to, uap->to, uap->tolen);
 		if (error) {
@@ -2534,7 +2520,7 @@ sys_sctp_generic_sendmsg_iov(td, uap)
 			return (error);
 		u_sinfo = &sinfo;
 	}
-	rights = CAP_WRITE;
+	rights = CAP_SEND;
 	if (uap->tolen) {
 		error = getsockaddr(&to, uap->to, uap->tolen);
 		if (error) {
@@ -2658,7 +2644,7 @@ sys_sctp_generic_recvmsg(td, uap)
 #endif
 
 	AUDIT_ARG_FD(uap->sd);
-	error = getsock_cap(td->td_proc->p_fd, uap->sd, CAP_READ, &fp, NULL);
+	error = getsock_cap(td->td_proc->p_fd, uap->sd, CAP_RECV, &fp, NULL);
 	if (error) {
 		return (error);
 	}