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>

drivers/xen/privcmd.c

@@ -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;
 	}