From: Long Li <lon...@microsoft.com>

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, depending on SMB dialect used. When RDMA write 
is used, 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.

Signed-off-by: Long Li <lon...@microsoft.com>
---
 fs/cifs/file.c    |  5 +++++
 fs/cifs/smb2pdu.c | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index dec70b3..41460a5 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)
@@ -3037,6 +3038,8 @@ 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 +3609,8 @@ 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 fbad987..1f08c75 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2392,6 +2392,39 @@ 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 */
-- 
2.7.4

Reply via email to