Add a new file operations hook for mmap operations. File type-specific

logic is now placed in the mmap hook implementation rather than requiring
it to be placed in sys/vm/vm_mmap.c.  This hook allows new file types to
support mmap() as well as potentially allowing mmap() for existing file
types that do not currently support any mapping.

The vm_mmap() function is now split up into two functions.  A new
vm_mmap_object() function handles the "back half" of vm_mmap() and accepts
a referenced VM object to map rather than a (handle, handle_type) tuple.
vm_mmap() is now reduced to converting a (handle, handle_type) tuple to a
a VM object and then calling vm_mmap_object() to handle the actual mapping.
The vm_mmap() function remains for use by other parts of the kernel
(e.g. device drivers and exec) but now only supports mapping vnodes,
character devices, and anonymous memory.

The mmap() system call invokes vm_mmap_object() directly with a NULL object
for anonymous mappings.  For mappings using a file descriptor, the
descriptors fo_mmap() hook is invoked instead.  The fo_mmap() hook is
responsible for performing type-specific checks and adjustments to
arguments as well as possibly modifying mapping parameters such as flags
or the object offset.  The fo_mmap() hook routines then call
vm_mmap_object() to handle the actual mapping.

The fo_mmap() hook is optional.  If it is not set, then fo_mmap() will
fail with ENODEV.  A fo_mmap() hook is implemented for regular files,
character devices, and shared memory objects (created via shm_open()).

While here, consistently use the VM_PROT_* constants for the vm_prot_t
type for the 'prot' variable passed to vm_mmap() and vm_mmap_object()
as well as the vm_mmap_vnode() and vm_mmap_cdev() helper routines.
Previously some places were using the mmap()-specific PROT_* constants
instead.  While this happens to work because PROT_xx == VM_PROT_xx,
using VM_PROT_* is more correct.

Differential Revision:	https://reviews.freebsd.org/D2658
Reviewed by:	alc (glanced over), kib
MFC after:	1 month
Sponsored by:	Chelsio

1 files changed, 65 insertions, 0 deletions

diff --git a/sys/fs/devfs/devfs_vnops.c b/sys/fs/devfs/devfs_vnops.c
index 552ddd2..fe8e9ef 100644
--- a/sys/fs/devfs/devfs_vnops.c
+++ b/sys/fs/devfs/devfs_vnops.c
@@ -51,6 +51,7 @@
 #include <sys/kernel.h>
 #include <sys/lock.h>
 #include <sys/malloc.h>
+#include <sys/mman.h>
 #include <sys/mount.h>
 #include <sys/namei.h>
 #include <sys/priv.h>
@@ -71,6 +72,10 @@ static struct fileops devfs_ops_f;
 
 #include <security/mac/mac_framework.h>
 
+#include <vm/vm.h>
+#include <vm/vm_extern.h>
+#include <vm/vm_object.h>
+
 static MALLOC_DEFINE(M_CDEVPDATA, "DEVFSP", "Metainfo for cdev-fp data");
 
 struct mtx	devfs_de_interlock;
@@ -1738,6 +1743,65 @@ devfs_write_f(struct file *fp, struct uio *uio, struct ucred *cred,
 	return (error);
 }
 
+static int
+devfs_mmap_f(struct file *fp, vm_map_t map, vm_offset_t *addr, vm_size_t size,
+    vm_prot_t prot, vm_prot_t cap_maxprot, int flags, vm_ooffset_t foff,
+    struct thread *td)
+{
+	struct cdev *dev;
+	struct cdevsw *dsw;
+	struct mount *mp;
+	struct vnode *vp;
+	struct file *fpop;
+	vm_object_t object;
+	vm_prot_t maxprot;
+	int error, ref;
+
+	vp = fp->f_vnode;
+
+	/*
+	 * Ensure that file and memory protections are
+	 * compatible.
+	 */
+	mp = vp->v_mount;
+	if (mp != NULL && (mp->mnt_flag & MNT_NOEXEC) != 0)
+		maxprot = VM_PROT_NONE;
+	else
+		maxprot = VM_PROT_EXECUTE;
+	if ((fp->f_flag & FREAD) != 0)
+		maxprot |= VM_PROT_READ;
+	else if ((prot & VM_PROT_READ) != 0)
+		return (EACCES);
+
+	/*
+	 * Character devices always share mappings, so
+	 * require a writable fd for writable mappings.
+	 */
+	if ((fp->f_flag & FWRITE) != 0)
+		maxprot |= VM_PROT_WRITE;
+	else if ((prot & VM_PROT_WRITE) != 0)
+		return (EACCES);
+	maxprot &= cap_maxprot;
+
+	fpop = td->td_fpop;
+	error = devfs_fp_check(fp, &dev, &dsw, &ref);
+	if (error != 0)
+		return (error);
+
+	error = vm_mmap_cdev(td, size, prot, &maxprot, &flags, dev, dsw, &foff,
+	    &object);
+	td->td_fpop = fpop;
+	dev_relthread(dev, ref);
+	if (error != 0)
+		return (error);
+
+	error = vm_mmap_object(map, addr, size, prot, maxprot, flags, object,
+	    foff, FALSE, td);
+	if (error != 0)
+		vm_object_deallocate(object);
+	return (error);
+}
+
 dev_t
 dev2udev(struct cdev *x)
 {
@@ -1760,6 +1824,7 @@ static struct fileops devfs_ops_f = {
 	.fo_sendfile =	vn_sendfile,
 	.fo_seek =	vn_seek,
 	.fo_fill_kinfo = vn_fill_kinfo,
+	.fo_mmap =	devfs_mmap_f,
 	.fo_flags =	DFLAG_PASSABLE | DFLAG_SEEKABLE
 };