1 files changed, 113 insertions, 38 deletions

diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 8adb9cc267f9..ca2b00e9d558 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -33,11 +33,14 @@
 #include <xen/features.h>
 #include <xen/page.h>
 #include <xen/xen-ops.h>
+#include <xen/balloon.h>
 
 #include "privcmd.h"
 
 MODULE_LICENSE("GPL");
 
+#define PRIV_VMA_LOCKED ((void *)1)
+
 #ifndef HAVE_ARCH_PRIVCMD_MMAP
 static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma);
 #endif
@@ -178,7 +181,7 @@ static int mmap_mfn_range(void *data, void *state)
 					msg->va & PAGE_MASK,
 					msg->mfn, msg->npages,
 					vma->vm_page_prot,
-					st->domain);
+					st->domain, NULL);
 	if (rc < 0)
 		return rc;
 
@@ -196,8 +199,9 @@ static long privcmd_ioctl_mmap(void __user *udata)
 	LIST_HEAD(pagelist);
 	struct mmap_mfn_state state;
 
-	if (!xen_initial_domain())
-		return -EPERM;
+	/* We only support privcmd_ioctl_mmap_batch for auto translated. */
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return -ENOSYS;
 
 	if (copy_from_user(&mmapcmd, udata, sizeof(mmapcmd)))
 		return -EFAULT;
@@ -246,6 +250,7 @@ struct mmap_batch_state {
 	domid_t domain;
 	unsigned long va;
 	struct vm_area_struct *vma;
+	int index;
 	/* A tristate:
 	 *      0 for no errors
 	 *      1 if at least one error has happened (and no
@@ -253,24 +258,47 @@ struct mmap_batch_state {
 	 *      -ENOENT if at least 1 -ENOENT has happened.
 	 */
 	int global_error;
-	/* An array for individual errors */
-	int *err;
+	int version;
 
 	/* User-space mfn array to store errors in the second pass for V1. */
 	xen_pfn_t __user *user_mfn;
+	/* User-space int array to store errors in the second pass for V2. */
+	int __user *user_err;
 };
 
+/* auto translated dom0 note: if domU being created is PV, then mfn is
+ * mfn(addr on bus). If it's auto xlated, then mfn is pfn (input to HAP).
+ */
 static int mmap_batch_fn(void *data, void *state)
 {
 	xen_pfn_t *mfnp = data;
 	struct mmap_batch_state *st = state;
+	struct vm_area_struct *vma = st->vma;
+	struct page **pages = vma->vm_private_data;
+	struct page *cur_page = NULL;
 	int ret;
 
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		cur_page = pages[st->index++];
+
 	ret = xen_remap_domain_mfn_range(st->vma, st->va & PAGE_MASK, *mfnp, 1,
-					 st->vma->vm_page_prot, st->domain);
+					 st->vma->vm_page_prot, st->domain,
+					 &cur_page);
 
 	/* Store error code for second pass. */
-	*(st->err++) = ret;
+	if (st->version == 1) {
+		if (ret < 0) {
+			/*
+			 * V1 encodes the error codes in the 32bit top nibble of the
+			 * mfn (with its known limitations vis-a-vis 64 bit callers).
+			 */
+			*mfnp |= (ret == -ENOENT) ?
+						PRIVCMD_MMAPBATCH_PAGED_ERROR :
+						PRIVCMD_MMAPBATCH_MFN_ERROR;
+		}
+	} else { /* st->version == 2 */
+		*((int *) mfnp) = ret;
+	}
 
 	/* And see if it affects the global_error. */
 	if (ret < 0) {
@@ -287,20 +315,51 @@ static int mmap_batch_fn(void *data, void *state)
 	return 0;
 }
 
-static int mmap_return_errors_v1(void *data, void *state)
+static int mmap_return_errors(void *data, void *state)
 {
-	xen_pfn_t *mfnp = data;
 	struct mmap_batch_state *st = state;
-	int err = *(st->err++);
 
-	/*
-	 * V1 encodes the error codes in the 32bit top nibble of the
-	 * mfn (with its known limitations vis-a-vis 64 bit callers).
-	 */
-	*mfnp |= (err == -ENOENT) ?
-				PRIVCMD_MMAPBATCH_PAGED_ERROR :
-				PRIVCMD_MMAPBATCH_MFN_ERROR;
-	return __put_user(*mfnp, st->user_mfn++);
+	if (st->version == 1) {
+		xen_pfn_t mfnp = *((xen_pfn_t *) data);
+		if (mfnp & PRIVCMD_MMAPBATCH_MFN_ERROR)
+			return __put_user(mfnp, st->user_mfn++);
+		else
+			st->user_mfn++;
+	} else { /* st->version == 2 */
+		int err = *((int *) data);
+		if (err)
+			return __put_user(err, st->user_err++);
+		else
+			st->user_err++;
+	}
+
+	return 0;
+}
+
+/* Allocate pfns that are then mapped with gmfns from foreign domid. Update
+ * the vma with the page info to use later.
+ * Returns: 0 if success, otherwise -errno
+ */
+static int alloc_empty_pages(struct vm_area_struct *vma, int numpgs)
+{
+	int rc;
+	struct page **pages;
+
+	pages = kcalloc(numpgs, sizeof(pages[0]), GFP_KERNEL);
+	if (pages == NULL)
+		return -ENOMEM;
+
+	rc = alloc_xenballooned_pages(numpgs, pages, 0);
+	if (rc != 0) {
+		pr_warn("%s Could not alloc %d pfns rc:%d\n", __func__,
+			numpgs, rc);
+		kfree(pages);
+		return -ENOMEM;
+	}
+	BUG_ON(vma->vm_private_data != PRIV_VMA_LOCKED);
+	vma->vm_private_data = pages;
+
+	return 0;
 }
 
 static struct vm_operations_struct privcmd_vm_ops;
@@ -313,12 +372,8 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
 	struct vm_area_struct *vma;
 	unsigned long nr_pages;
 	LIST_HEAD(pagelist);
-	int *err_array = NULL;
 	struct mmap_batch_state state;
 
-	if (!xen_initial_domain())
-		return -EPERM;
-
 	switch (version) {
 	case 1:
 		if (copy_from_user(&m, udata, sizeof(struct privcmd_mmapbatch)))
@@ -352,30 +407,40 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
 		goto out;
 	}
 
-	err_array = kcalloc(m.num, sizeof(int), GFP_KERNEL);
-	if (err_array == NULL) {
-		ret = -ENOMEM;
-		goto out;
+	if (version == 2) {
+		/* Zero error array now to only copy back actual errors. */
+		if (clear_user(m.err, sizeof(int) * m.num)) {
+			ret = -EFAULT;
+			goto out;
+		}
 	}
 
 	down_write(&mm->mmap_sem);
 
 	vma = find_vma(mm, m.addr);
-	ret = -EINVAL;
 	if (!vma ||
 	    vma->vm_ops != &privcmd_vm_ops ||
 	    (m.addr != vma->vm_start) ||
 	    ((m.addr + (nr_pages << PAGE_SHIFT)) != vma->vm_end) ||
 	    !privcmd_enforce_singleshot_mapping(vma)) {
 		up_write(&mm->mmap_sem);
+		ret = -EINVAL;
 		goto out;
 	}
+	if (xen_feature(XENFEAT_auto_translated_physmap)) {
+		ret = alloc_empty_pages(vma, m.num);
+		if (ret < 0) {
+			up_write(&mm->mmap_sem);
+			goto out;
+		}
+	}
 
 	state.domain        = m.dom;
 	state.vma           = vma;
 	state.va            = m.addr;
+	state.index         = 0;
 	state.global_error  = 0;
-	state.err           = err_array;
+	state.version       = version;
 
 	/* mmap_batch_fn guarantees ret == 0 */
 	BUG_ON(traverse_pages(m.num, sizeof(xen_pfn_t),
@@ -383,17 +448,14 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
 
 	up_write(&mm->mmap_sem);
 
-	if (state.global_error && (version == 1)) {
+	if (state.global_error) {
 		/* Write back errors in second pass. */
 		state.user_mfn = (xen_pfn_t *)m.arr;
-		state.err      = err_array;
+		state.user_err = m.err;
 		ret = traverse_pages(m.num, sizeof(xen_pfn_t),
-				     &pagelist, mmap_return_errors_v1, &state);
-	} else if (version == 2) {
-		ret = __copy_to_user(m.err, err_array, m.num * sizeof(int));
-		if (ret)
-			ret = -EFAULT;
-	}
+							 &pagelist, mmap_return_errors, &state);
+	} else
+		ret = 0;
 
 	/* If we have not had any EFAULT-like global errors then set the global
 	 * error to -ENOENT if necessary. */
@@ -401,7 +463,6 @@ static long privcmd_ioctl_mmap_batch(void __user *udata, int version)
 		ret = -ENOENT;
 
 out:
-	kfree(err_array);
 	free_page_list(&pagelist);
 
 	return ret;
@@ -438,6 +499,19 @@ static long privcmd_ioctl(struct file *file,
 	return ret;
 }
 
+static void privcmd_close(struct vm_area_struct *vma)
+{
+	struct page **pages = vma->vm_private_data;
+	int numpgs = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+
+	if (!xen_feature(XENFEAT_auto_translated_physmap || !numpgs || !pages))
+		return;
+
+	xen_unmap_domain_mfn_range(vma, numpgs, pages);
+	free_xenballooned_pages(numpgs, pages);
+	kfree(pages);
+}
+
 static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	printk(KERN_DEBUG "privcmd_fault: vma=%p %lx-%lx, pgoff=%lx, uv=%p\n",
@@ -448,6 +522,7 @@ static int privcmd_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 }
 
 static struct vm_operations_struct privcmd_vm_ops = {
+	.close = privcmd_close,
 	.fault = privcmd_fault
 };
 
@@ -465,7 +540,7 @@ static int privcmd_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int privcmd_enforce_singleshot_mapping(struct vm_area_struct *vma)
 {
-	return (xchg(&vma->vm_private_data, (void *)1) == NULL);
+	return !cmpxchg(&vma->vm_private_data, NULL, PRIV_VMA_LOCKED);
 }
 
 const struct file_operations xen_privcmd_fops = {