Merge tag 'iter-ubuf.2-2023-04-21' of git://git.kernel.dk/linux

Pull ITER_UBUF updates from Jens Axboe:
 "This turns singe vector imports into ITER_UBUF, rather than
  ITER_IOVEC.

  The former is more trivial to iterate and advance, and hence a bit
  more efficient. From some very unscientific testing, ~60% of all iovec
  imports are single vector"

* tag 'iter-ubuf.2-2023-04-21' of git://git.kernel.dk/linux:
  iov_iter: Mark copy_compat_iovec_from_user() noinline
  iov_iter: import single vector iovecs as ITER_UBUF
  iov_iter: convert import_single_range() to ITER_UBUF
  iov_iter: overlay struct iovec and ubuf/len
  iov_iter: set nr_segs = 1 for ITER_UBUF
  iov_iter: remove iov_iter_iovec()
  iov_iter: add iter_iov_addr() and iter_iov_len() helpers
  ALSA: pcm: check for user backed iterator, not specific iterator type
  IB/qib: check for user backed iterator, not specific iterator type
  IB/hfi1: check for user backed iterator, not specific iterator type
  iov_iter: add iter_iovec() helper
  block: ensure bio_alloc_map_data() deals with ITER_UBUF correctly

block/blk-map.c

@@ -29,10 +29,11 @@ static struct bio_map_data *bio_alloc_map_data(struct iov_iter *data,
 	bmd = kmalloc(struct_size(bmd, iov, data->nr_segs), gfp_mask);
 	if (!bmd)
 		return NULL;
-	memcpy(bmd->iov, data->iov, sizeof(struct iovec) * data->nr_segs);
 	bmd->iter = *data;
-	if (iter_is_iovec(data))
-		bmd->iter.iov = bmd->iov;
+	if (iter_is_iovec(data)) {
+		memcpy(bmd->iov, iter_iov(data), sizeof(struct iovec) * data->nr_segs);
+		bmd->iter.__iov = bmd->iov;
+	}
 	return bmd;
 }
 

drivers/infiniband/hw/hfi1/file_ops.c

@@ -267,18 +267,15 @@ static ssize_t hfi1_write_iter(struct kiocb *kiocb, struct iov_iter *from)
 
 	if (!HFI1_CAP_IS_KSET(SDMA))
 		return -EINVAL;
+	if (!from->user_backed)
+		return -EINVAL;
 	idx = srcu_read_lock(&fd->pq_srcu);
 	pq = srcu_dereference(fd->pq, &fd->pq_srcu);
 	if (!cq || !pq) {
 		srcu_read_unlock(&fd->pq_srcu, idx);
 		return -EIO;
 	}
 
-	if (!iter_is_iovec(from) || !dim) {
-		srcu_read_unlock(&fd->pq_srcu, idx);
-		return -EINVAL;
-	}
-
 	trace_hfi1_sdma_request(fd->dd, fd->uctxt->ctxt, fd->subctxt, dim);
 
 	if (atomic_read(&pq->n_reqs) == pq->n_max_reqs) {
@@ -287,11 +284,12 @@ static ssize_t hfi1_write_iter(struct kiocb *kiocb, struct iov_iter *from)
 	}
 
 	while (dim) {
+		const struct iovec *iov = iter_iov(from);
 		int ret;
 		unsigned long count = 0;
 
 		ret = hfi1_user_sdma_process_request(
-			fd, (struct iovec *)(from->iov + done),
+			fd, (struct iovec *)(iov + done),
 			dim, &count);
 		if (ret) {
 			reqs = ret;

drivers/infiniband/hw/qib/qib_file_ops.c

@@ -2245,10 +2245,10 @@ static ssize_t qib_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct qib_ctxtdata *rcd = ctxt_fp(iocb->ki_filp);
 	struct qib_user_sdma_queue *pq = fp->pq;
 
-	if (!iter_is_iovec(from) || !from->nr_segs || !pq)
+	if (!from->user_backed || !from->nr_segs || !pq)
 		return -EINVAL;
 
-	return qib_user_sdma_writev(rcd, pq, from->iov, from->nr_segs);
+	return qib_user_sdma_writev(rcd, pq, iter_iov(from), from->nr_segs);
 }
 
 static struct class *qib_class;

drivers/net/tun.c

@@ -1486,7 +1486,8 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile,
 	skb->truesize += skb->data_len;
 
 	for (i = 1; i < it->nr_segs; i++) {
-		size_t fragsz = it->iov[i].iov_len;
+		const struct iovec *iov = iter_iov(it);
+		size_t fragsz = iov->iov_len;
 		struct page *page;
 		void *frag;
 

drivers/vhost/scsi.c

@@ -665,7 +665,7 @@ vhost_scsi_calc_sgls(struct iov_iter *iter, size_t bytes, int max_sgls)
 {
 	int sgl_count = 0;
 
-	if (!iter || !iter->iov) {
+	if (!iter || !iter_iov(iter)) {
 		pr_err("%s: iter->iov is NULL, but expected bytes: %zu"
 		       " present\n", __func__, bytes);
 		return -EINVAL;

fs/btrfs/file.c

@@ -3730,10 +3730,15 @@ static int check_direct_read(struct btrfs_fs_info *fs_info,
 	if (!iter_is_iovec(iter))
 		return 0;
 
-	for (seg = 0; seg < iter->nr_segs; seg++)
-		for (i = seg + 1; i < iter->nr_segs; i++)
-			if (iter->iov[seg].iov_base == iter->iov[i].iov_base)
+	for (seg = 0; seg < iter->nr_segs; seg++) {
+		for (i = seg + 1; i < iter->nr_segs; i++) {
+			const struct iovec *iov1 = iter_iov(iter) + seg;
+			const struct iovec *iov2 = iter_iov(iter) + i;
+
+			if (iov1->iov_base == iov2->iov_base)
 				return -EINVAL;
+		}
+	}
 	return 0;
 }
 

fs/fuse/file.c

@@ -1419,7 +1419,7 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 static inline unsigned long fuse_get_user_addr(const struct iov_iter *ii)
 {
-	return (unsigned long)ii->iov->iov_base + ii->iov_offset;
+	return (unsigned long)iter_iov(ii)->iov_base + ii->iov_offset;
 }
 
 static inline size_t fuse_get_frag_size(const struct iov_iter *ii,

fs/read_write.c

@@ -749,15 +749,14 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
 		return -EOPNOTSUPP;
 
 	while (iov_iter_count(iter)) {
-		struct iovec iovec = iov_iter_iovec(iter);
 		ssize_t nr;
 
 		if (type == READ) {
-			nr = filp->f_op->read(filp, iovec.iov_base,
-					      iovec.iov_len, ppos);
+			nr = filp->f_op->read(filp, iter_iov_addr(iter),
+						iter_iov_len(iter), ppos);
 		} else {
-			nr = filp->f_op->write(filp, iovec.iov_base,
-					       iovec.iov_len, ppos);
+			nr = filp->f_op->write(filp, iter_iov_addr(iter),
+						iter_iov_len(iter), ppos);
 		}
 
 		if (nr < 0) {
@@ -766,7 +765,7 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
 			break;
 		}
 		ret += nr;
-		if (nr != iovec.iov_len)
+		if (nr != iter_iov_len(iter))
 			break;
 		iov_iter_advance(iter, nr);
 	}

include/linux/uio.h

@@ -49,14 +49,35 @@ struct iov_iter {
 		size_t iov_offset;
 		int last_offset;
 	};
-	size_t count;
+	/*
+	 * Hack alert: overlay ubuf_iovec with iovec + count, so
+	 * that the members resolve correctly regardless of the type
+	 * of iterator used. This means that you can use:
+	 *
+	 * &iter->__ubuf_iovec or iter->__iov
+	 *
+	 * interchangably for the user_backed cases, hence simplifying
+	 * some of the cases that need to deal with both.
+	 */
 	union {
-		const struct iovec *iov;
-		const struct kvec *kvec;
-		const struct bio_vec *bvec;
-		struct xarray *xarray;
-		struct pipe_inode_info *pipe;
-		void __user *ubuf;
+		/*
+		 * This really should be a const, but we cannot do that without
+		 * also modifying any of the zero-filling iter init functions.
+		 * Leave it non-const for now, but it should be treated as such.
+		 */
+		struct iovec __ubuf_iovec;
+		struct {
+			union {
+				/* use iter_iov() to get the current vec */
+				const struct iovec *__iov;
+				const struct kvec *kvec;
+				const struct bio_vec *bvec;
+				struct xarray *xarray;
+				struct pipe_inode_info *pipe;
+				void __user *ubuf;
+			};
+			size_t count;
+		};
 	};
 	union {
 		unsigned long nr_segs;
@@ -68,6 +89,16 @@ struct iov_iter {
 	};
 };
 
+static inline const struct iovec *iter_iov(const struct iov_iter *iter)
+{
+	if (iter->iter_type == ITER_UBUF)
+		return (const struct iovec *) &iter->__ubuf_iovec;
+	return iter->__iov;
+}
+
+#define iter_iov_addr(iter)	(iter_iov(iter)->iov_base + (iter)->iov_offset)
+#define iter_iov_len(iter)	(iter_iov(iter)->iov_len - (iter)->iov_offset)
+
 static inline enum iter_type iov_iter_type(const struct iov_iter *i)
 {
 	return i->iter_type;
@@ -143,15 +174,6 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
 	return ret;
 }
 
-static inline struct iovec iov_iter_iovec(const struct iov_iter *iter)
-{
-	return (struct iovec) {
-		.iov_base = iter->iov->iov_base + iter->iov_offset,
-		.iov_len = min(iter->count,
-			       iter->iov->iov_len - iter->iov_offset),
-	};
-}
-
 size_t copy_page_from_iter_atomic(struct page *page, unsigned offset,
 				  size_t bytes, struct iov_iter *i);
 void iov_iter_advance(struct iov_iter *i, size_t bytes);
@@ -359,7 +381,8 @@ static inline void iov_iter_ubuf(struct iov_iter *i, unsigned int direction,
 		.user_backed = true,
 		.data_source = direction,
 		.ubuf = buf,
-		.count = count
+		.count = count,
+		.nr_segs = 1
 	};
 }
 /* Flags for iov_iter_get/extract_pages*() */

io_uring/net.c

@@ -184,8 +184,8 @@ static int io_setup_async_msg(struct io_kiocb *req,
 		async_msg->msg.msg_name = &async_msg->addr;
 	/* if were using fast_iov, set it to the new one */
 	if (iter_is_iovec(&kmsg->msg.msg_iter) && !kmsg->free_iov) {
-		size_t fast_idx = kmsg->msg.msg_iter.iov - kmsg->fast_iov;
-		async_msg->msg.msg_iter.iov = &async_msg->fast_iov[fast_idx];
+		size_t fast_idx = iter_iov(&kmsg->msg.msg_iter) - kmsg->fast_iov;
+		async_msg->msg.msg_iter.__iov = &async_msg->fast_iov[fast_idx];
 	}
 
 	return -EAGAIN;

io_uring/rw.c

@@ -447,26 +447,25 @@ static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
 	ppos = io_kiocb_ppos(kiocb);
 
 	while (iov_iter_count(iter)) {
-		struct iovec iovec;
+		void __user *addr;
+		size_t len;
 		ssize_t nr;
 
 		if (iter_is_ubuf(iter)) {
-			iovec.iov_base = iter->ubuf + iter->iov_offset;
-			iovec.iov_len = iov_iter_count(iter);
+			addr = iter->ubuf + iter->iov_offset;
+			len = iov_iter_count(iter);
 		} else if (!iov_iter_is_bvec(iter)) {
-			iovec = iov_iter_iovec(iter);
+			addr = iter_iov_addr(iter);
+			len = iter_iov_len(iter);
 		} else {
-			iovec.iov_base = u64_to_user_ptr(rw->addr);
-			iovec.iov_len = rw->len;
+			addr = u64_to_user_ptr(rw->addr);
+			len = rw->len;
 		}
 
-		if (ddir == READ) {
-			nr = file->f_op->read(file, iovec.iov_base,
-					      iovec.iov_len, ppos);
-		} else {
-			nr = file->f_op->write(file, iovec.iov_base,
-					       iovec.iov_len, ppos);
-		}
+		if (ddir == READ)
+			nr = file->f_op->read(file, addr, len, ppos);
+		else
+			nr = file->f_op->write(file, addr, len, ppos);
 
 		if (nr < 0) {
 			if (!ret)
@@ -482,7 +481,7 @@ static ssize_t loop_rw_iter(int ddir, struct io_rw *rw, struct iov_iter *iter)
 			if (!rw->len)
 				break;
 		}
-		if (nr != iovec.iov_len)
+		if (nr != len)
 			break;
 	}
 
@@ -503,10 +502,10 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
 	if (!iovec) {
 		unsigned iov_off = 0;
 
-		io->s.iter.iov = io->s.fast_iov;
-		if (iter->iov != fast_iov) {
-			iov_off = iter->iov - fast_iov;
-			io->s.iter.iov += iov_off;
+		io->s.iter.__iov = io->s.fast_iov;
+		if (iter->__iov != fast_iov) {
+			iov_off = iter_iov(iter) - fast_iov;
+			io->s.iter.__iov += iov_off;
 		}
 		if (io->s.fast_iov != fast_iov)
 			memcpy(io->s.fast_iov + iov_off, fast_iov + iov_off,