nfs/localio: refactor iocb initialization

The goal of this commit's various refactoring is to have LOCALIO's per
IO initialization occur in process context so that we don't get into a
situation where IO fails to be issued from workqueue (e.g. due to lack
of memory, etc). Better to have LOCALIO's iocb initialization fail
early.

There isn't immediate need but this commit makes it possible for
LOCALIO to fallback to NFS pagelist code in process context to allow
for immediate retry over RPC.

Signed-off-by: Mike Snitzer <[email protected]>
Signed-off-by: Anna Schumaker <[email protected]>

Author: Mike Snitzer

fs/nfs/localio.c

@@ -36,6 +36,7 @@ struct nfs_local_kiocb {
 	struct nfs_pgio_header	*hdr;
 	struct work_struct	work;
 	void (*aio_complete_work)(struct work_struct *);
+	struct iov_iter		iter ____cacheline_aligned;
 	struct nfsd_file	*localio;
 };
 
@@ -411,13 +412,19 @@ nfs_local_pgio_done(struct nfs_pgio_header *hdr, long status)
 	}
 }
 
+static void
+nfs_local_iocb_release(struct nfs_local_kiocb *iocb)
+{
+	nfs_local_file_put(iocb->localio);
+	nfs_local_iocb_free(iocb);
+}
+
 static void
 nfs_local_pgio_release(struct nfs_local_kiocb *iocb)
 {
 	struct nfs_pgio_header *hdr = iocb->hdr;
 
-	nfs_local_file_put(iocb->localio);
-	nfs_local_iocb_free(iocb);
+	nfs_local_iocb_release(iocb);
 	nfs_local_hdr_release(hdr, hdr->task.tk_ops);
 }
 
@@ -483,18 +490,16 @@ static void nfs_local_call_read(struct work_struct *work)
 		container_of(work, struct nfs_local_kiocb, work);
 	struct file *filp = iocb->kiocb.ki_filp;
 	const struct cred *save_cred;
-	struct iov_iter iter;
 	ssize_t status;
 
 	save_cred = override_creds(filp->f_cred);
 
-	nfs_local_iter_init(&iter, iocb, ITER_DEST);
 	if (iocb->kiocb.ki_flags & IOCB_DIRECT) {
 		iocb->kiocb.ki_complete = nfs_local_read_aio_complete;
 		iocb->aio_complete_work = nfs_local_read_aio_complete_work;
 	}
 
-	status = filp->f_op->read_iter(&iocb->kiocb, &iter);
+	status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iter);
 
 	revert_creds(save_cred);
 
@@ -505,25 +510,14 @@ static void nfs_local_call_read(struct work_struct *work)
 }
 
 static int
-nfs_do_local_read(struct nfs_pgio_header *hdr,
-		  struct nfsd_file *localio,
+nfs_local_do_read(struct nfs_local_kiocb *iocb,
 		  const struct rpc_call_ops *call_ops)
 {
-	struct nfs_local_kiocb *iocb;
-	struct file *file = nfs_to->nfsd_file_file(localio);
-
-	/* Don't support filesystems without read_iter */
-	if (!file->f_op->read_iter)
-		return -EAGAIN;
+	struct nfs_pgio_header *hdr = iocb->hdr;
 
 	dprintk("%s: vfs_read count=%u pos=%llu\n",
 		__func__, hdr->args.count, hdr->args.offset);
 
-	iocb = nfs_local_iocb_alloc(hdr, file, GFP_KERNEL);
-	if (iocb == NULL)
-		return -ENOMEM;
-	iocb->localio = localio;
-
 	nfs_local_pgio_init(hdr, call_ops);
 	hdr->res.eof = false;
 
@@ -680,20 +674,18 @@ static void nfs_local_call_write(struct work_struct *work)
 	struct file *filp = iocb->kiocb.ki_filp;
 	unsigned long old_flags = current->flags;
 	const struct cred *save_cred;
-	struct iov_iter iter;
 	ssize_t status;
 
 	current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO;
 	save_cred = override_creds(filp->f_cred);
 
-	nfs_local_iter_init(&iter, iocb, ITER_SOURCE);
 	if (iocb->kiocb.ki_flags & IOCB_DIRECT) {
 		iocb->kiocb.ki_complete = nfs_local_write_aio_complete;
 		iocb->aio_complete_work = nfs_local_write_aio_complete_work;
 	}
 
 	file_start_write(filp);
-	status = filp->f_op->write_iter(&iocb->kiocb, &iter);
+	status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iter);
 	file_end_write(filp);
 
 	revert_creds(save_cred);
@@ -707,26 +699,15 @@ static void nfs_local_call_write(struct work_struct *work)
 }
 
 static int
-nfs_do_local_write(struct nfs_pgio_header *hdr,
-		   struct nfsd_file *localio,
+nfs_local_do_write(struct nfs_local_kiocb *iocb,
 		   const struct rpc_call_ops *call_ops)
 {
-	struct nfs_local_kiocb *iocb;
-	struct file *file = nfs_to->nfsd_file_file(localio);
-
-	/* Don't support filesystems without write_iter */
-	if (!file->f_op->write_iter)
-		return -EAGAIN;
+	struct nfs_pgio_header *hdr = iocb->hdr;
 
 	dprintk("%s: vfs_write count=%u pos=%llu %s\n",
 		__func__, hdr->args.count, hdr->args.offset,
 		(hdr->args.stable == NFS_UNSTABLE) ?  "unstable" : "stable");
 
-	iocb = nfs_local_iocb_alloc(hdr, file, GFP_NOIO);
-	if (iocb == NULL)
-		return -ENOMEM;
-	iocb->localio = localio;
-
 	switch (hdr->args.stable) {
 	default:
 		break;
@@ -747,32 +728,68 @@ nfs_do_local_write(struct nfs_pgio_header *hdr,
 	return 0;
 }
 
+static struct nfs_local_kiocb *
+nfs_local_iocb_init(struct nfs_pgio_header *hdr, struct nfsd_file *localio)
+{
+	struct file *file = nfs_to->nfsd_file_file(localio);
+	struct nfs_local_kiocb *iocb;
+	gfp_t gfp_mask;
+	int rw;
+
+	if (hdr->rw_mode & FMODE_READ) {
+		if (!file->f_op->read_iter)
+			return ERR_PTR(-EOPNOTSUPP);
+		gfp_mask = GFP_KERNEL;
+		rw = ITER_DEST;
+	} else {
+		if (!file->f_op->write_iter)
+			return ERR_PTR(-EOPNOTSUPP);
+		gfp_mask = GFP_NOIO;
+		rw = ITER_SOURCE;
+	}
+
+	iocb = nfs_local_iocb_alloc(hdr, file, gfp_mask);
+	if (iocb == NULL)
+		return ERR_PTR(-ENOMEM);
+	iocb->hdr = hdr;
+	iocb->localio = localio;
+
+	nfs_local_iter_init(&iocb->iter, iocb, rw);
+
+	return iocb;
+}
+
 int nfs_local_doio(struct nfs_client *clp, struct nfsd_file *localio,
 		   struct nfs_pgio_header *hdr,
 		   const struct rpc_call_ops *call_ops)
 {
+	struct nfs_local_kiocb *iocb;
 	int status = 0;
 
 	if (!hdr->args.count)
 		return 0;
 
+	iocb = nfs_local_iocb_init(hdr, localio);
+	if (IS_ERR(iocb))
+		return PTR_ERR(iocb);
+
 	switch (hdr->rw_mode) {
 	case FMODE_READ:
-		status = nfs_do_local_read(hdr, localio, call_ops);
+		status = nfs_local_do_read(iocb, call_ops);
 		break;
 	case FMODE_WRITE:
-		status = nfs_do_local_write(hdr, localio, call_ops);
+		status = nfs_local_do_write(iocb, call_ops);
 		break;
 	default:
 		dprintk("%s: invalid mode: %d\n", __func__,
 			hdr->rw_mode);
-		status = -EINVAL;
+		status = -EOPNOTSUPP;
 	}
 
 	if (status != 0) {
 		if (status == -EAGAIN)
 			nfs_localio_disable_client(clp);
-		nfs_local_file_put(localio);
+		nfs_local_iocb_release(iocb);
 		hdr->task.tk_status = status;
 		nfs_local_hdr_release(hdr, call_ops);
 	}