Note that the only other callers that use iov_iter_bvec and asynchronous
read/write are loop, target and nvme-target, so this should actually
be pretty simple.  Out of these only target needs something like this
trivial change to keep the bvec available over the duration of the I/O,
the other two should be fine already:

---
From 581a8eabbb1759e3dcfee4b1d2e419f814a8cb80 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 9 Dec 2020 10:05:04 +0100
Subject: target/file: allocate the bvec array as part of struct target_core_file_cmd

This saves one memory allocation, and ensures the bvecs aren't freed
before the AIO completion.  This will allow the lower level code to be
optimized so that it can avoid allocating another bvec array.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/target/target_core_file.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c
index 7143d03f0e027e..ed0c39a1f7c649 100644
--- a/drivers/target/target_core_file.c
+++ b/drivers/target/target_core_file.c

@@ -241,6 +241,7 @@ struct target_core_file_cmd {
 	unsigned long	len;
 	struct se_cmd	*cmd;
 	struct kiocb	iocb;
+	struct bio_vec	bvecs[];
 };
 
 static void cmd_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)

@@ -268,29 +269,22 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	struct target_core_file_cmd *aio_cmd;
 	struct iov_iter iter = {};
 	struct scatterlist *sg;
-	struct bio_vec *bvec;
 	ssize_t len = 0;
 	int ret = 0, i;
 
-	aio_cmd = kmalloc(sizeof(struct target_core_file_cmd), GFP_KERNEL);
+	aio_cmd = kmalloc(struct_size(aio_cmd, bvecs, sgl_nents), GFP_KERNEL);
 	if (!aio_cmd)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
-	bvec = kcalloc(sgl_nents, sizeof(struct bio_vec), GFP_KERNEL);
-	if (!bvec) {
-		kfree(aio_cmd);
-		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
-	}
-
 	for_each_sg(sgl, sg, sgl_nents, i) {
-		bvec[i].bv_page = sg_page(sg);
-		bvec[i].bv_len = sg->length;
-		bvec[i].bv_offset = sg->offset;
+		aio_cmd->bvecs[i].bv_page = sg_page(sg);
+		aio_cmd->bvecs[i].bv_len = sg->length;
+		aio_cmd->bvecs[i].bv_offset = sg->offset;
 
 		len += sg->length;
 	}
 
-	iov_iter_bvec(&iter, is_write, bvec, sgl_nents, len);
+	iov_iter_bvec(&iter, is_write, aio_cmd->bvecs, sgl_nents, len);
 
 	aio_cmd->cmd = cmd;
 	aio_cmd->len = len;

@@ -307,8 +301,6 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
 	else
 		ret = call_read_iter(file, &aio_cmd->iocb, &iter);
 
-	kfree(bvec);
-
 	if (ret != -EIOCBQUEUED)
 		cmd_rw_aio_complete(&aio_cmd->iocb, ret, 0);