@@ -1244,9 +1244,9 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access)
}
static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
- struct vring_desc __user *desc,
- struct vring_avail __user *avail,
- struct vring_used __user *used)
+ vring_desc_t __user *desc,
+ vring_avail_t __user *avail,
+ vring_used_t __user *used)
{
return access_ok(desc, vhost_get_desc_size(vq, num)) &&
@@ -2301,7 +2301,7 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
struct vring_used_elem *heads,
unsigned count)
{
- struct vring_used_elem __user *used;
+ vring_used_t __user *used;
u16 old, new;
int start;
@@ -67,9 +67,9 @@ struct vhost_virtqueue {
/* The actual ring of buffers. */
struct mutex mutex;
unsigned int num;
- struct vring_desc __user *desc;
- struct vring_avail __user *avail;
- struct vring_used __user *used;
+ vring_desc_t __user *desc;
+ vring_avail_t __user *avail;
+ vring_used_t __user *used;
const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS];
struct file *kick;
struct eventfd_ctx *call_ctx;
@@ -620,9 +620,9 @@ static inline int xfer_to_user(const struct vringh *vrh,
*/
int vringh_init_user(struct vringh *vrh, u64 features,
unsigned int num, bool weak_barriers,
- struct vring_desc __user *desc,
- struct vring_avail __user *avail,
- struct vring_used __user *used)
+ vring_desc_t __user *desc,
+ vring_avail_t __user *avail,
+ vring_used_t __user *used)
{
/* Sane power of 2 please! */
if (!num || num > 0xffff || (num & (num - 1))) {
@@ -105,9 +105,9 @@ struct vringh_kiov {
/* Helpers for userspace vrings. */
int vringh_init_user(struct vringh *vrh, u64 features,
unsigned int num, bool weak_barriers,
- struct vring_desc __user *desc,
- struct vring_avail __user *avail,
- struct vring_used __user *used);
+ vring_desc_t __user *desc,
+ vring_avail_t __user *avail,
+ vring_used_t __user *used);
static inline void vringh_iov_init(struct vringh_iov *iov,
struct iovec *iovec, unsigned num)
@@ -118,16 +118,6 @@ struct vring_used {
struct vring_used_elem ring[];
};
-struct vring {
- unsigned int num;
-
- struct vring_desc *desc;
-
- struct vring_avail *avail;
-
- struct vring_used *used;
-};
-
/* Alignment requirements for vring elements.
* When using pre-virtio 1.0 layout, these fall out naturally.
*/
@@ -135,6 +125,34 @@ struct vring {
#define VRING_USED_ALIGN_SIZE 4
#define VRING_DESC_ALIGN_SIZE 16
+/*
+ * The ring element addresses are passed between components with different
+ * alignments assumptions. Thus, we might need to decrease the compiler-selected
+ * alignment, and so must use a typedef to make sure the __aligned attribute
+ * actually takes hold:
+ *
+ * https://gcc.gnu.org/onlinedocs//gcc/Common-Type-Attributes.html#Common-Type-Attributes
+ *
+ * When used on a struct, or struct member, the aligned attribute can only
+ * increase the alignment; in order to decrease it, the packed attribute must
+ * be specified as well. When used as part of a typedef, the aligned attribute
+ * can both increase and decrease alignment, and specifying the packed
+ * attribute generates a warning.
+ */
+typedef struct vring_desc __aligned(VRING_DESC_ALIGN_SIZE) vring_desc_t;
+typedef struct vring_avail __aligned(VRING_AVAIL_ALIGN_SIZE) vring_avail_t;
+typedef struct vring_used __aligned(VRING_USED_ALIGN_SIZE) vring_used_t;
+
+struct vring {
+ unsigned int num;
+
+ vring_desc_t *desc;
+
+ vring_avail_t *avail;
+
+ vring_used_t *used;
+};
+
#ifndef VIRTIO_RING_NO_LEGACY
/* The standard layout for the ring is a continuous chunk of memory which looks
The ring element addresses are passed between components with different alignments assumptions. Thus, if guest/userspace selects a pointer and host then gets and dereferences it, we might need to decrease the compiler-selected alignment to prevent compiler on the host from assuming pointer is aligned. This actually triggers on ARM with -mabi=apcs-gnu - which is a deprecated configuration, but it seems safer to handle this generally. Note that userspace that allocates the memory is actually OK and does not need to be fixed, but userspace that gets it from guest or another process does need to be fixed. The later doesn't generally talk to the kernel so while it might be buggy it's not talking to the kernel in the buggy way - it's just using the header in the buggy way - so fixing header and asking userspace to recompile is the best we can do. I verified that the produced kernel binary on x86 is exactly identical before and after the change. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> --- Changes from v1: update vhost, vringh pointers to use the new typedefs drivers/vhost/vhost.c | 8 +++---- drivers/vhost/vhost.h | 6 ++--- drivers/vhost/vringh.c | 6 ++--- include/linux/vringh.h | 6 ++--- include/uapi/linux/virtio_ring.h | 38 +++++++++++++++++++++++--------- 5 files changed, 41 insertions(+), 23 deletions(-)