[RFC PATCH v1 7/8] nfs: allow LOCALIO for P2PDMA pages only as aligned direct I/O

[Pranjal Shrivastava]

LOCALIO hands READs and WRITEs to the local filesystem, which can take
P2PDMA pages only if its disk can DMA to them. Use LOCALIO for such I/O
only if the filesystem's block device supports P2PDMA. Otherwise send a
regular READ or WRITE RPC, as if LOCALIO were off.

When the I/O is not a single DIO-aligned segment, LOCALIO falls back to
buffered I/O, which copies the payload through the page cache via CPU
accesses. Fail such I/O with -EINVAL instead.

Signed-off-by: Pranjal Shrivastava <praan@xxxxxxxxxx>
---
 fs/nfs/internal.h |  8 ++++++++
 fs/nfs/localio.c  | 40 ++++++++++++++++++++++++++++++++++++++++
 fs/nfs/pagelist.c |  3 +++
 3 files changed, 51 insertions(+)

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index d6ea41a3f9b4..9338b5e0896a 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -476,6 +476,7 @@ extern struct nfsd_file *nfs_local_open_fh(struct nfs_client *,
 					   struct nfs_fh *,
 					   struct nfs_file_localio *,
 					   const fmode_t);
+struct nfsd_file *nfs_local_p2pdma_check(struct nfsd_file *localio);
 extern int nfs_local_doio(struct nfs_client *,
 			  struct nfsd_file *,
 			  struct nfs_pgio_header *,
@@ -495,6 +496,13 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 {
 	return NULL;
 }
+
+static inline struct nfsd_file *
+nfs_local_p2pdma_check(struct nfsd_file *localio)
+{
+	return NULL;
+}
+
 static inline int nfs_local_doio(struct nfs_client *clp,
 				 struct nfsd_file *localio,
 				 struct nfs_pgio_header *hdr,
diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c
index f42b6112a613..6c8f2d393c35 100644
--- a/fs/nfs/localio.c
+++ b/fs/nfs/localio.c
@@ -19,6 +19,7 @@
 #include <linux/nfs_common.h>
 #include <linux/nfslocalio.h>
 #include <linux/bvec.h>
+#include <linux/blkdev.h>
 
 #include <linux/nfs.h>
 #include <linux/nfs_fs.h>
@@ -290,6 +291,22 @@ nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred,
 }
 EXPORT_SYMBOL_GPL(nfs_local_open_fh);
 
+/*
+ * LOCALIO moves P2PDMA pages only by DMA to and from the local disk.
+ * If that disk cannot do P2PDMA, put @localio and return NULL so the
+ * I/O is sent as a regular RPC instead.
+ */
+struct nfsd_file *nfs_local_p2pdma_check(struct nfsd_file *localio)
+{
+	struct file *file = nfs_to->nfsd_file_file(localio);
+	struct block_device *bdev = file_inode(file)->i_sb->s_bdev;
+
+	if (bdev && blk_queue_pci_p2pdma(bdev_get_queue(bdev)))
+		return localio;
+	nfs_local_file_put(localio);
+	return NULL;
+}
+
 /*
  * Ensure all page cache allocations are done from GFP_NOFS context to
  * prevent direct reclaim recursion back into NFS via nfs_writepages.
@@ -511,6 +528,17 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw)
 	iov_iter_bvec(&iocb->iters[0], rw, iocb->bvec, v, len);
 }
 
+/*
+ * P2PDMA payloads move only by DMA, never through the page cache, so the
+ * whole I/O must be a single DIO-aligned segment.
+ */
+static bool nfs_local_p2pdma_misaligned(struct nfs_local_kiocb *iocb)
+{
+	return iocb->hdr->args.p2pdma &&
+	       (atomic_read(&iocb->n_iters) != 1 ||
+		!iocb->iter_is_dio_aligned[0]);
+}
+
 static void
 nfs_local_hdr_release(struct nfs_pgio_header *hdr,
 		const struct rpc_call_ops *call_ops)
@@ -732,6 +760,12 @@ static void nfs_local_do_read(struct nfs_local_kiocb *iocb,
 	nfs_local_pgio_init(hdr, call_ops);
 	hdr->res.eof = false;
 
+	if (nfs_local_p2pdma_misaligned(iocb)) {
+		nfs_local_pgio_done(iocb, -EINVAL);
+		nfs_local_pgio_release(iocb);
+		return;
+	}
+
 	INIT_WORK(&iocb->work, nfs_local_call_read);
 	if (nfs_local_defer_io())
 		queue_work(nfslocaliod_workqueue, &iocb->work);
@@ -953,6 +987,12 @@ static void nfs_local_do_write(struct nfs_local_kiocb *iocb,
 
 	nfs_set_local_verifier(hdr->inode, hdr->res.verf, hdr->args.stable);
 
+	if (nfs_local_p2pdma_misaligned(iocb)) {
+		nfs_local_pgio_done(iocb, -EINVAL);
+		nfs_local_pgio_release(iocb);
+		return;
+	}
+
 	INIT_WORK(&iocb->work, nfs_local_call_write);
 	if (nfs_local_defer_io())
 		queue_work(nfslocaliod_workqueue, &iocb->work);
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index ec535ed3051d..2d1d07c460fd 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -1023,6 +1023,9 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
 					  &hdr->args.context->nfl,
 					  hdr->args.context->mode);
 
+		if (localio && hdr->args.p2pdma)
+			localio = nfs_local_p2pdma_check(localio);
+
 		if (NFS_SERVER(hdr->inode)->nfs_client->cl_minorversion)
 			task_flags = RPC_TASK_MOVEABLE;
 		ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
-- 
2.56.0.rc1.315.gc6ed9934b7-goog