xen/privcmd: Add IOCTL_PRIVCMD_DM_OP

Recently a new dm_op[1] hypercall was added to Xen to provide a mechanism
for restricting device emulators (such as QEMU) to a limited set of
hypervisor operations, and being able to audit those operations in the
kernel of the domain in which they run.

This patch adds IOCTL_PRIVCMD_DM_OP as gateway for __HYPERVISOR_dm_op.

NOTE: There is no requirement for user-space code to bounce data through
      locked memory buffers (as with IOCTL_PRIVCMD_HYPERCALL) since
      privcmd has enough information to lock the original buffers
      directly.

[1] http://xenbits.xen.org/gitweb/?p=xen.git;a=commit;h=524a98c2

Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
This commit is contained in:
Paul Durrant 2017-02-13 17:03:23 +00:00 committed by Boris Ostrovsky
parent dc9eab6fd9
commit ab520be8cd
9 changed files with 196 additions and 0 deletions

View File

@ -457,4 +457,5 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op);
EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op);
EXPORT_SYMBOL_GPL(privcmd_call);

View File

@ -92,6 +92,7 @@ HYPERCALL1(tmem_op);
HYPERCALL1(platform_op_raw);
HYPERCALL2(multicall);
HYPERCALL2(vm_assist);
HYPERCALL3(dm_op);
ENTRY(privcmd_call)
stmdb sp!, {r4}

View File

@ -84,6 +84,7 @@ HYPERCALL1(tmem_op);
HYPERCALL1(platform_op_raw);
HYPERCALL2(multicall);
HYPERCALL2(vm_assist);
HYPERCALL3(dm_op);
ENTRY(privcmd_call)
mov x16, x0

View File

@ -472,6 +472,13 @@ HYPERVISOR_xenpmu_op(unsigned int op, void *arg)
return _hypercall2(int, xenpmu_op, op, arg);
}
static inline int
HYPERVISOR_dm_op(
domid_t dom, unsigned int nr_bufs, void *bufs)
{
return _hypercall3(int, dm_op, dom, nr_bufs, bufs);
}
static inline void
MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
{

View File

@ -22,6 +22,7 @@
#include <linux/pagemap.h>
#include <linux/seq_file.h>
#include <linux/miscdevice.h>
#include <linux/moduleparam.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
@ -32,6 +33,7 @@
#include <xen/xen.h>
#include <xen/privcmd.h>
#include <xen/interface/xen.h>
#include <xen/interface/hvm/dm_op.h>
#include <xen/features.h>
#include <xen/page.h>
#include <xen/xen-ops.h>
@ -43,6 +45,17 @@ MODULE_LICENSE("GPL");
#define PRIV_VMA_LOCKED ((void *)1)
static unsigned int privcmd_dm_op_max_num = 16;
module_param_named(dm_op_max_nr_bufs, privcmd_dm_op_max_num, uint, 0644);
MODULE_PARM_DESC(dm_op_max_nr_bufs,
"Maximum number of buffers per dm_op hypercall");
static unsigned int privcmd_dm_op_buf_max_size = 4096;
module_param_named(dm_op_buf_max_size, privcmd_dm_op_buf_max_size, uint,
0644);
MODULE_PARM_DESC(dm_op_buf_max_size,
"Maximum size of a dm_op hypercall buffer");
static int privcmd_vma_range_is_mapped(
struct vm_area_struct *vma,
unsigned long addr,
@ -548,6 +561,128 @@ out_unlock:
goto out;
}
static int lock_pages(
struct privcmd_dm_op_buf kbufs[], unsigned int num,
struct page *pages[], unsigned int nr_pages)
{
unsigned int i;
for (i = 0; i < num; i++) {
unsigned int requested;
int pinned;
requested = DIV_ROUND_UP(
offset_in_page(kbufs[i].uptr) + kbufs[i].size,
PAGE_SIZE);
if (requested > nr_pages)
return -ENOSPC;
pinned = get_user_pages_fast(
(unsigned long) kbufs[i].uptr,
requested, FOLL_WRITE, pages);
if (pinned < 0)
return pinned;
nr_pages -= pinned;
pages += pinned;
}
return 0;
}
static void unlock_pages(struct page *pages[], unsigned int nr_pages)
{
unsigned int i;
if (!pages)
return;
for (i = 0; i < nr_pages; i++) {
if (pages[i])
put_page(pages[i]);
}
}
static long privcmd_ioctl_dm_op(void __user *udata)
{
struct privcmd_dm_op kdata;
struct privcmd_dm_op_buf *kbufs;
unsigned int nr_pages = 0;
struct page **pages = NULL;
struct xen_dm_op_buf *xbufs = NULL;
unsigned int i;
long rc;
if (copy_from_user(&kdata, udata, sizeof(kdata)))
return -EFAULT;
if (kdata.num == 0)
return 0;
if (kdata.num > privcmd_dm_op_max_num)
return -E2BIG;
kbufs = kcalloc(kdata.num, sizeof(*kbufs), GFP_KERNEL);
if (!kbufs)
return -ENOMEM;
if (copy_from_user(kbufs, kdata.ubufs,
sizeof(*kbufs) * kdata.num)) {
rc = -EFAULT;
goto out;
}
for (i = 0; i < kdata.num; i++) {
if (kbufs[i].size > privcmd_dm_op_buf_max_size) {
rc = -E2BIG;
goto out;
}
if (!access_ok(VERIFY_WRITE, kbufs[i].uptr,
kbufs[i].size)) {
rc = -EFAULT;
goto out;
}
nr_pages += DIV_ROUND_UP(
offset_in_page(kbufs[i].uptr) + kbufs[i].size,
PAGE_SIZE);
}
pages = kcalloc(nr_pages, sizeof(*pages), GFP_KERNEL);
if (!pages) {
rc = -ENOMEM;
goto out;
}
xbufs = kcalloc(kdata.num, sizeof(*xbufs), GFP_KERNEL);
if (!xbufs) {
rc = -ENOMEM;
goto out;
}
rc = lock_pages(kbufs, kdata.num, pages, nr_pages);
if (rc)
goto out;
for (i = 0; i < kdata.num; i++) {
set_xen_guest_handle(xbufs[i].h, kbufs[i].uptr);
xbufs[i].size = kbufs[i].size;
}
xen_preemptible_hcall_begin();
rc = HYPERVISOR_dm_op(kdata.dom, kdata.num, xbufs);
xen_preemptible_hcall_end();
out:
unlock_pages(pages, nr_pages);
kfree(xbufs);
kfree(pages);
kfree(kbufs);
return rc;
}
static long privcmd_ioctl(struct file *file,
unsigned int cmd, unsigned long data)
{
@ -571,6 +706,10 @@ static long privcmd_ioctl(struct file *file,
ret = privcmd_ioctl_mmap_batch(udata, 2);
break;
case IOCTL_PRIVCMD_DM_OP:
ret = privcmd_ioctl_dm_op(udata);
break;
default:
break;
}

View File

@ -77,6 +77,17 @@ struct privcmd_mmapbatch_v2 {
int __user *err; /* array of error codes */
};
struct privcmd_dm_op_buf {
void __user *uptr;
size_t size;
};
struct privcmd_dm_op {
domid_t dom;
__u16 num;
const struct privcmd_dm_op_buf __user *ubufs;
};
/*
* @cmd: IOCTL_PRIVCMD_HYPERCALL
* @arg: &privcmd_hypercall_t
@ -98,5 +109,7 @@ struct privcmd_mmapbatch_v2 {
_IOC(_IOC_NONE, 'P', 3, sizeof(struct privcmd_mmapbatch))
#define IOCTL_PRIVCMD_MMAPBATCH_V2 \
_IOC(_IOC_NONE, 'P', 4, sizeof(struct privcmd_mmapbatch_v2))
#define IOCTL_PRIVCMD_DM_OP \
_IOC(_IOC_NONE, 'P', 5, sizeof(struct privcmd_dm_op))
#endif /* __LINUX_PUBLIC_PRIVCMD_H__ */

View File

@ -53,6 +53,7 @@ int HYPERVISOR_physdev_op(int cmd, void *arg);
int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args);
int HYPERVISOR_tmem_op(void *arg);
int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type);
int HYPERVISOR_dm_op(domid_t domid, unsigned int nr_bufs, void *bufs);
int HYPERVISOR_platform_op_raw(void *arg);
static inline int HYPERVISOR_platform_op(struct xen_platform_op *op)
{

View File

@ -0,0 +1,32 @@
/*
* Copyright (c) 2016, Citrix Systems Inc
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*/
#ifndef __XEN_PUBLIC_HVM_DM_OP_H__
#define __XEN_PUBLIC_HVM_DM_OP_H__
struct xen_dm_op_buf {
GUEST_HANDLE(void) h;
xen_ulong_t size;
};
DEFINE_GUEST_HANDLE_STRUCT(xen_dm_op_buf);
#endif /* __XEN_PUBLIC_HVM_DM_OP_H__ */

View File

@ -81,6 +81,7 @@
#define __HYPERVISOR_tmem_op 38
#define __HYPERVISOR_xc_reserved_op 39 /* reserved for XenClient */
#define __HYPERVISOR_xenpmu_op 40
#define __HYPERVISOR_dm_op 41
/* Architecture-specific hypercall definitions. */
#define __HYPERVISOR_arch_0 48