From 7240fdf187fe0d007ccceaad76015fbd23b432bc Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Wed, 29 Jul 2015 04:23:42 -0500
Subject: [PATCH] libceph: add support for CMPEXT compare extent requests
References: fate#318836
Patch-mainline: Not yet, SES2 clustered LIO/RBD

This adds support for the CMPEXT request. The request will compare
extent.length bytes and compare them to extent.length bytes at
extent.offset on disk. If there is a miscompare the osd will return
-EILSEQ, the offset in the buffer where it occurred, and the buffer.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Acked-by: David Disseldorp <ddiss@suse.de>
---
 include/linux/ceph/rados.h |    2 ++
 net/ceph/osd_client.c      |   23 ++++++++++++++++++++---
 2 files changed, 22 insertions(+), 3 deletions(-)

--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -212,6 +212,8 @@ extern const char *ceph_osd_state_name(i
 	/* sync */							    \
 	f(SYNC_READ,	__CEPH_OSD_OP(RD, DATA, 11),	"sync_read")	    \
 									    \
+	f(CMPEXT,	__CEPH_OSD_OP(RD, DATA, 31),	"cmpext")	    \
+									    \
 	/* write */							    \
 	f(WRITE,	__CEPH_OSD_OP(WR, DATA, 1),	"write")	    \
 	f(WRITEFULL,	__CEPH_OSD_OP(WR, DATA, 2),	"writefull")	    \
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -194,6 +194,7 @@ void osd_req_op_extent_osd_data_pages(st
 	case CEPH_OSD_OP_READ:
 	case CEPH_OSD_OP_ZERO:
 	case CEPH_OSD_OP_TRUNCATE:
+	case CEPH_OSD_OP_CMPEXT:
 		ceph_osd_data_pages_init(&op->extent.response_data, pages,
 					 length, alignment, pages_from_pool,
 					 own_pages);
@@ -269,6 +270,7 @@ void osd_req_op_extent_osd_data_sg(struc
 				      sgl, init_sg_offset, length);
 		break;
 	case CEPH_OSD_OP_WRITE:
+	case CEPH_OSD_OP_CMPEXT:
 		ceph_osd_data_sg_init(&op->extent.request_data,
 				      sgl, init_sg_offset, length);
 		break;
@@ -372,6 +374,10 @@ static void osd_req_op_data_release(stru
 	case CEPH_OSD_OP_WRITEFULL:
 		ceph_osd_data_release(&op->extent.request_data);
 		break;
+	case CEPH_OSD_OP_CMPEXT:
+		ceph_osd_data_release(&op->extent.response_data);
+		ceph_osd_data_release(&op->extent.request_data);
+		break;
 	case CEPH_OSD_OP_CALL:
 		ceph_osd_data_release(&op->cls.request_info);
 		ceph_osd_data_release(&op->cls.request_data);
@@ -571,13 +577,14 @@ void osd_req_op_extent_init(struct ceph_
 
 	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
 	       opcode != CEPH_OSD_OP_WRITEFULL && opcode != CEPH_OSD_OP_ZERO &&
-	       opcode != CEPH_OSD_OP_TRUNCATE);
+	       opcode != CEPH_OSD_OP_TRUNCATE && opcode != CEPH_OSD_OP_CMPEXT);
 
 	op->extent.offset = offset;
 	op->extent.length = length;
 	op->extent.truncate_size = truncate_size;
 	op->extent.truncate_seq = truncate_seq;
-	if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL)
+	if (opcode == CEPH_OSD_OP_WRITE || opcode == CEPH_OSD_OP_WRITEFULL ||
+	    opcode == CEPH_OSD_OP_CMPEXT)
 		payload_len += length;
 
 	op->payload_len = payload_len;
@@ -762,6 +769,7 @@ static u64 osd_req_encode_op(struct ceph
 	case CEPH_OSD_OP_WRITEFULL:
 	case CEPH_OSD_OP_ZERO:
 	case CEPH_OSD_OP_TRUNCATE:
+	case CEPH_OSD_OP_CMPEXT:
 		dst->extent.offset = cpu_to_le64(src->extent.offset);
 		dst->extent.length = cpu_to_le64(src->extent.length);
 		dst->extent.truncate_size =
@@ -774,6 +782,14 @@ static u64 osd_req_encode_op(struct ceph
 			ceph_osdc_msg_data_add(req->r_request, osd_data);
 
 			request_data_len = src->extent.length;
+		} else if (src->op == CEPH_OSD_OP_CMPEXT) {
+			osd_data = &src->extent.request_data;
+			ceph_osdc_msg_data_add(req->r_request, osd_data);
+
+			osd_data = &src->extent.response_data;
+			ceph_osdc_msg_data_add(req->r_reply, osd_data);
+
+			request_data_len = src->extent.length;
 		} else {
 			osd_data = &src->extent.response_data;
 			ceph_osdc_msg_data_add(req->r_reply, osd_data);
@@ -871,7 +887,8 @@ struct ceph_osd_request *ceph_osdc_new_r
 
 	BUG_ON(opcode != CEPH_OSD_OP_READ && opcode != CEPH_OSD_OP_WRITE &&
 	       opcode != CEPH_OSD_OP_ZERO && opcode != CEPH_OSD_OP_TRUNCATE &&
-	       opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE);
+	       opcode != CEPH_OSD_OP_CREATE && opcode != CEPH_OSD_OP_DELETE &&
+	       opcode != CEPH_OSD_OP_CMPEXT);
 
 	req = ceph_osdc_alloc_request(osdc, snapc, num_ops, use_mempool,
 					GFP_NOFS);