[Patch v4 21/22] CIFS: SMBD: Upper layer performs SMB read via RDMA write through memory registration

[Long Li <longli-Lp/cVzEoVyZiJJESP9tAQJZ3qXmFLfmx@public.gmane.org>]

From: Long Li <longli-0li6OtcxBFHby3iVrkZq2A@public.gmane.org>

If I/O size is larger than rdma_readwrite_threshold, use RDMA write for
SMB read by specifying channel SMB2_CHANNEL_RDMA_V1 or
SMB2_CHANNEL_RDMA_V1_INVALIDATE in the SMB packet, depending on SMB dialect
used. Append a smbd_buffer_descriptor_v1 to the end of the SMB packet and fill
in other values to indicate this SMB read uses RDMA write.

There is no need to read from the transport for incoming payload. At the time
SMB read response comes back, the data is already transfered and placed in the
pages by RDMA hardware.

When SMB read is finished, deregister the memory regions if RDMA write is used
for this SMB read. smbd_deregister_mr may need to do local invalidation and
sleep, if server remote invalidation is not used.

There are situations where the MID may not be created on I/O failure, under
which memory region is deregistered when read data context is released.

Signed-off-by: Long Li <longli-0li6OtcxBFHby3iVrkZq2A@public.gmane.org>
---
 fs/cifs/cifsglob.h |  1 +
 fs/cifs/file.c     | 10 ++++++++++
 fs/cifs/smb2pdu.c  | 43 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 54 insertions(+)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index f851b50..30b99a5 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1152,6 +1152,7 @@ struct cifs_readdata {
 				struct cifs_readdata *rdata,
 				struct iov_iter *iter);
 	struct kvec			iov[2];
+	struct smbd_mr			*mr;
 	unsigned int			pagesz;
 	unsigned int			tailsz;
 	unsigned int			credits;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0786f19..8396f1e 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -42,6 +42,7 @@
 #include "cifs_debug.h"
 #include "cifs_fs_sb.h"
 #include "fscache.h"
+#include "smbdirect.h"
 
 
 static inline int cifs_convert_flags(unsigned int flags)
@@ -2909,6 +2910,11 @@ cifs_readdata_release(struct kref *refcount)
 	struct cifs_readdata *rdata = container_of(refcount,
 					struct cifs_readdata, refcount);
 
+	if (rdata->mr) {
+		smbd_deregister_mr(rdata->mr);
+		rdata->mr = NULL;
+	}
+
 	if (rdata->cfile)
 		cifsFileInfo_put(rdata->cfile);
 
@@ -3037,6 +3043,8 @@ uncached_fill_pages(struct TCP_Server_Info *server,
 		}
 		if (iter)
 			result = copy_page_from_iter(page, 0, n, iter);
+		else if (rdata->mr)
+			result = n;
 		else
 			result = cifs_read_page_from_socket(server, page, n);
 		if (result < 0)
@@ -3606,6 +3614,8 @@ readpages_fill_pages(struct TCP_Server_Info *server,
 
 		if (iter)
 			result = copy_page_from_iter(page, 0, n, iter);
+		else if (rdata->mr)
+			result = n;
 		else
 			result = cifs_read_page_from_socket(server, page, n);
 		if (result < 0)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 7053db9..31dcee0 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2380,6 +2380,39 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
 	req->Length = cpu_to_le32(io_parms->length);
 	req->Offset = cpu_to_le64(io_parms->offset);
 
+	/*
+	 * If we want to do a RDMA write, fill in and append
+	 * smbd_buffer_descriptor_v1 to the end of read request
+	 */
+	if (server->rdma && rdata &&
+		rdata->bytes >= server->smbd_conn->rdma_readwrite_threshold) {
+
+		struct smbd_buffer_descriptor_v1 *v1;
+		bool need_invalidate =
+			io_parms->tcon->ses->server->dialect == SMB30_PROT_ID;
+
+		rdata->mr = smbd_register_mr(
+				server->smbd_conn, rdata->pages,
+				rdata->nr_pages, rdata->tailsz,
+				true, need_invalidate);
+		if (!rdata->mr)
+			return -ENOBUFS;
+
+		req->Channel = SMB2_CHANNEL_RDMA_V1_INVALIDATE;
+		if (need_invalidate)
+			req->Channel = SMB2_CHANNEL_RDMA_V1;
+		req->ReadChannelInfoOffset =
+			offsetof(struct smb2_read_plain_req, Buffer);
+		req->ReadChannelInfoLength =
+			sizeof(struct smbd_buffer_descriptor_v1);
+		v1 = (struct smbd_buffer_descriptor_v1 *) &req->Buffer[0];
+		v1->offset = rdata->mr->mr->iova;
+		v1->token = rdata->mr->mr->rkey;
+		v1->length = rdata->mr->mr->length;
+
+		*total_len += sizeof(*v1) - 1;
+	}
+
 	if (request_type & CHAINED_REQUEST) {
 		if (!(request_type & END_OF_CHAIN)) {
 			/* next 8-byte aligned request */
@@ -2459,6 +2492,16 @@ smb2_readv_callback(struct mid_q_entry *mid)
 			rdata->result = -EIO;
 	}
 
+	/*
+	 * If this rdata has a memmory registered, the MR can be freed
+	 * MR needs to be freed as soon as I/O finishes to prevent deadlock
+	 * because they have limited number and are used for future I/Os
+	 */
+	if (rdata->mr) {
+		smbd_deregister_mr(rdata->mr);
+		rdata->mr = NULL;
+	}
+
 	if (rdata->result)
 		cifs_stats_fail_inc(tcon, SMB2_READ_HE);
 
-- 
2.7.4

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html