Second-to-last commit implementing Capsicum capabilities in the FreeBSD

kernel for FreeBSD 9.0:

Add a new capability mask argument to fget(9) and friends, allowing system
call code to declare what capabilities are required when an integer file
descriptor is converted into an in-kernel struct file *.  With options
CAPABILITIES compiled into the kernel, this enforces capability
protection; without, this change is effectively a no-op.

Some cases require special handling, such as mmap(2), which must preserve
information about the maximum rights at the time of mapping in the memory
map so that they can later be enforced in mprotect(2) -- this is done by
narrowing the rights in the existing max_protection field used for similar
purposes with file permissions.

In namei(9), we assert that the code is not reached from within capability
mode, as we're not yet ready to enforce namespace capabilities there.
This will follow in a later commit.

Update two capability names: CAP_EVENT and CAP_KEVENT become
CAP_POST_KEVENT and CAP_POLL_KEVENT to more accurately indicate what they
represent.

Approved by:	re (bz)
Submitted by:	jonathan
Sponsored by:	Google Inc

1 files changed, 19 insertions, 10 deletions

diff --git a/sys/kern/vfs_aio.c b/sys/kern/vfs_aio.c
index 69b4e0a..aedbdd0 100644
--- a/sys/kern/vfs_aio.c
+++ b/sys/kern/vfs_aio.c
@@ -28,6 +28,7 @@ __FBSDID("$FreeBSD$");
 #include <sys/malloc.h>
 #include <sys/bio.h>
 #include <sys/buf.h>
+#include <sys/capability.h>
 #include <sys/eventhandler.h>
 #include <sys/sysproto.h>
 #include <sys/filedesc.h>
@@ -1577,17 +1578,30 @@ aio_aqueue(struct thread *td, struct aiocb *job, struct aioliojob *lj,
 		aiocbe->uaiocb.aio_lio_opcode = type;
 	opcode = aiocbe->uaiocb.aio_lio_opcode;
 
-	/* Fetch the file object for the specified file descriptor. */
+	/*
+	 * Validate the opcode and fetch the file object for the specified
+	 * file descriptor.
+	 *
+	 * XXXRW: Moved the opcode validation up here so that we don't
+	 * retrieve a file descriptor without knowing what the capabiltity
+	 * should be.
+	 */
 	fd = aiocbe->uaiocb.aio_fildes;
 	switch (opcode) {
 	case LIO_WRITE:
-		error = fget_write(td, fd, &fp);
+		error = fget_write(td, fd, CAP_WRITE | CAP_SEEK, &fp);
 		break;
 	case LIO_READ:
-		error = fget_read(td, fd, &fp);
+		error = fget_read(td, fd, CAP_READ | CAP_SEEK, &fp);
+		break;
+	case LIO_SYNC:
+		error = fget(td, fd, CAP_FSYNC, &fp);
+		break;
+	case LIO_NOP:
+		error = fget(td, fd, 0, &fp);
 		break;
 	default:
-		error = fget(td, fd, &fp);
+		error = EINVAL;
 	}
 	if (error) {
 		uma_zfree(aiocb_zone, aiocbe);
@@ -1623,11 +1637,6 @@ aio_aqueue(struct thread *td, struct aiocb *job, struct aioliojob *lj,
 		uma_zfree(aiocb_zone, aiocbe);
 		return (0);
 	}
-	if ((opcode != LIO_READ) && (opcode != LIO_WRITE) &&
-	    (opcode != LIO_SYNC)) {
-		error = EINVAL;
-		goto aqueue_fail;
-	}
 
 	if (aiocbe->uaiocb.aio_sigevent.sigev_notify != SIGEV_KEVENT)
 		goto no_kqueue;
@@ -1971,7 +1980,7 @@ aio_cancel(struct thread *td, struct aio_cancel_args *uap)
 	struct vnode *vp;
 
 	/* Lookup file object. */
-	error = fget(td, uap->fd, &fp);
+	error = fget(td, uap->fd, 0, &fp);
 	if (error)
 		return (error);