vringh: iterate on iotlb_translate to handle large translations

iotlb_translate() can return -ENOBUFS if the bio_vec is not big enough
to contain all the ranges for translation.
This can happen for example if the VMM maps a large bounce buffer,
without using hugepages, that requires more than 16 ranges to translate
the addresses.

To handle this case, let's extend iotlb_translate() to also return the
number of bytes successfully translated.
In copy_from_iotlb()/copy_to_iotlb() loops by calling iotlb_translate()
several times until we complete the translation.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20220624075656.13997-1-sgarzare@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

1 files changed, 56 insertions, 22 deletions

diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index eab55accf381..11f59dd06a74 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -1095,7 +1095,8 @@ EXPORT_SYMBOL(vringh_need_notify_kern);
 #if IS_REACHABLE(CONFIG_VHOST_IOTLB)
 
 static int iotlb_translate(const struct vringh *vrh,
-			   u64 addr, u64 len, struct bio_vec iov[],
+			   u64 addr, u64 len, u64 *translated,
+			   struct bio_vec iov[],
 			   int iov_size, u32 perm)
 {
 	struct vhost_iotlb_map *map;
@@ -1136,43 +1137,76 @@ static int iotlb_translate(const struct vringh *vrh,
 
 	spin_unlock(vrh->iotlb_lock);
 
+	if (translated)
+		*translated = min(len, s);
+
 	return ret;
 }
 
 static inline int copy_from_iotlb(const struct vringh *vrh, void *dst,
 				  void *src, size_t len)
 {
-	struct iov_iter iter;
-	struct bio_vec iov[16];
-	int ret;
+	u64 total_translated = 0;
 
-	ret = iotlb_translate(vrh, (u64)(uintptr_t)src,
-			      len, iov, 16, VHOST_MAP_RO);
-	if (ret < 0)
-		return ret;
+	while (total_translated < len) {
+		struct bio_vec iov[16];
+		struct iov_iter iter;
+		u64 translated;
+		int ret;
 
-	iov_iter_bvec(&iter, READ, iov, ret, len);
+		ret = iotlb_translate(vrh, (u64)(uintptr_t)src,
+				      len - total_translated, &translated,
+				      iov, ARRAY_SIZE(iov), VHOST_MAP_RO);
+		if (ret == -ENOBUFS)
+			ret = ARRAY_SIZE(iov);
+		else if (ret < 0)
+			return ret;
 
-	ret = copy_from_iter(dst, len, &iter);
+		iov_iter_bvec(&iter, READ, iov, ret, translated);
 
-	return ret;
+		ret = copy_from_iter(dst, translated, &iter);
+		if (ret < 0)
+			return ret;
+
+		src += translated;
+		dst += translated;
+		total_translated += translated;
+	}
+
+	return total_translated;
 }
 
 static inline int copy_to_iotlb(const struct vringh *vrh, void *dst,
 				void *src, size_t len)
 {
-	struct iov_iter iter;
-	struct bio_vec iov[16];
-	int ret;
+	u64 total_translated = 0;
 
-	ret = iotlb_translate(vrh, (u64)(uintptr_t)dst,
-			      len, iov, 16, VHOST_MAP_WO);
-	if (ret < 0)
-		return ret;
+	while (total_translated < len) {
+		struct bio_vec iov[16];
+		struct iov_iter iter;
+		u64 translated;
+		int ret;
+
+		ret = iotlb_translate(vrh, (u64)(uintptr_t)dst,
+				      len - total_translated, &translated,
+				      iov, ARRAY_SIZE(iov), VHOST_MAP_WO);
+		if (ret == -ENOBUFS)
+			ret = ARRAY_SIZE(iov);
+		else if (ret < 0)
+			return ret;
 
-	iov_iter_bvec(&iter, WRITE, iov, ret, len);
+		iov_iter_bvec(&iter, WRITE, iov, ret, translated);
+
+		ret = copy_to_iter(src, translated, &iter);
+		if (ret < 0)
+			return ret;
+
+		src += translated;
+		dst += translated;
+		total_translated += translated;
+	}
 
-	return copy_to_iter(src, len, &iter);
+	return total_translated;
 }
 
 static inline int getu16_iotlb(const struct vringh *vrh,
@@ -1183,7 +1217,7 @@ static inline int getu16_iotlb(const struct vringh *vrh,
 	int ret;
 
 	/* Atomic read is needed for getu16 */
-	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p),
+	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL,
 			      &iov, 1, VHOST_MAP_RO);
 	if (ret < 0)
 		return ret;
@@ -1204,7 +1238,7 @@ static inline int putu16_iotlb(const struct vringh *vrh,
 	int ret;
 
 	/* Atomic write is needed for putu16 */
-	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p),
+	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p), NULL,
 			      &iov, 1, VHOST_MAP_WO);
 	if (ret < 0)
 		return ret;