[Xen-devel] [PATCH v2 2/3] xen/privcmd: Add IOCTL_PRIVCMD_DM_OP

[Paul Durrant <paul.durrant@xxxxxxxxxx>]

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,
bouncing the callers buffers through kernel memory to allow the address
ranges to be audited (and negating the need to bounce through locked
memory in user-space).

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

Signed-off-by: Paul Durrant <paul.durrant@xxxxxxxxxx>
---
Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Cc: Juergen Gross <jgross@xxxxxxxx>

v2:
- Lock the user pages rather than bouncing through kernel memory
---
 arch/x86/include/asm/xen/hypercall.h |   7 ++
 drivers/xen/privcmd.c                | 138 +++++++++++++++++++++++++++++++++++
 include/uapi/xen/privcmd.h           |  13 ++++
 include/xen/interface/hvm/dm_op.h    |  32 ++++++++
 include/xen/interface/xen.h          |   1 +
 5 files changed, 191 insertions(+)
 create mode 100644 include/xen/interface/hvm/dm_op.h

diff --git a/arch/x86/include/asm/xen/hypercall.h 
b/arch/x86/include/asm/xen/hypercall.h
index a12a047..f6d20f6 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -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)
 {
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 5e5c7ae..d5cf042 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -32,6 +32,7 @@
 #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>
@@ -548,6 +549,139 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, 
int version)
        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;
+
+       /*
+        * Set a tolerable upper limit on the number of buffers
+        * without being overly restrictive, since we can't easily
+        * predict what future dm_ops may require.
+        */
+       if (kdata.num * sizeof(*kbufs) > PAGE_SIZE)
+               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 (!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);
+       }
+
+       /*
+        * Again, set a tolerable upper limit on the number of pages
+        * needed to lock all the buffers without being overly
+        * restrictive, since we can't easily predict the size of
+        * buffers future dm_ops may use.
+        */
+       if (nr_pages * sizeof(*pages) > PAGE_SIZE) {
+               rc = -E2BIG;
+               goto out;
+       }
+
+       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 +705,10 @@ 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;
        }
diff --git a/include/uapi/xen/privcmd.h b/include/uapi/xen/privcmd.h
index 7ddeeda..f8c5d75 100644
--- a/include/uapi/xen/privcmd.h
+++ b/include/uapi/xen/privcmd.h
@@ -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__ */
diff --git a/include/xen/interface/hvm/dm_op.h 
b/include/xen/interface/hvm/dm_op.h
new file mode 100644
index 0000000..ee9e480
--- /dev/null
+++ b/include/xen/interface/hvm/dm_op.h
@@ -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__ */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 1b0d189..4f4830e 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -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
-- 
2.1.4


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
https://lists.xen.org/xen-devel