blob: a2254f825601890fad999d9f7876b704b4a43c4d [file] [log] [blame]
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2006-2008, LINBIT Information Technologies GmbH.
Copyright (C) 2006-2008, Lars Ellenberg <>.
Copyright (C) 2006-2008, Philipp Reisner <>.
DRBD is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
DRBD is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with drbd; see the file COPYING. If not, write to
the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
#ifndef _DRBD_REQ_H
#define _DRBD_REQ_H
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/drbd.h>
#include "drbd_int.h"
/* The request callbacks will be called in irq context by the IDE drivers,
and in Softirqs/Tasklets/BH context by the SCSI drivers,
and by the receiver and worker in kernel-thread context.
Try to get the locking right :) */
* Objects of type struct drbd_request do only exist on a R_PRIMARY node, and are
* associated with IO requests originating from the block layer above us.
* There are quite a few things that may happen to a drbd request
* during its lifetime.
* It will be created.
* It will be marked with the intention to be
* submitted to local disk and/or
* send via the network.
* It has to be placed on the transfer log and other housekeeping lists,
* In case we have a network connection.
* It may be identified as a concurrent (write) request
* and be handled accordingly.
* It may me handed over to the local disk subsystem.
* It may be completed by the local disk subsystem,
* either successfully or with io-error.
* In case it is a READ request, and it failed locally,
* it may be retried remotely.
* It may be queued for sending.
* It may be handed over to the network stack,
* which may fail.
* It may be acknowledged by the "peer" according to the wire_protocol in use.
* this may be a negative ack.
* It may receive a faked ack when the network connection is lost and the
* transfer log is cleaned up.
* Sending may be canceled due to network connection loss.
* When it finally has outlived its time,
* corresponding dirty bits in the resync-bitmap may be cleared or set,
* it will be destroyed,
* and completion will be signalled to the originator,
* with or without "success".
enum drbd_req_event {
/* XXX yes, now I am inconsistent...
* these are not "events" but "actions"
* oh, well... */
/* An empty flush is queued as P_BARRIER,
* which will cause it to complete "successfully",
* even if the local disk flush failed.
* Just like "real" requests, empty flushes (blkdev_issue_flush()) will
* only see an error if neither local nor remote data is reachable. */
WRITE_ACKED_BY_PEER_AND_SIS, /* and set_in_sync */
BARRIER_ACKED, /* in protocol A and B */
DATA_RECEIVED, /* (remote read) */
/* encoding of request states for now. we don't actually need that many bits.
* we don't need to do atomic bit operations either, since most of the time we
* need to look at the connection state and/or manipulate some lists at the
* same time, so we should hold the request lock anyways.
enum drbd_req_state_bits {
/* 3210
* 0000: no local possible
* 0001: to be submitted
* UNUSED, we could map: 011: submitted, completion still pending
* 0110: completed ok
* 0010: completed with error
* 1001: Aborted (before completion)
* 1x10: Aborted and completed -> free
/* 87654
* 00000: no network possible
* 00001: to be send
* 00011: to be send, on worker queue
* 00101: sent, expecting recv_ack (B) or write_ack (C)
* 11101: sent,
* recv_ack (B) or implicit "ack" (A),
* still waiting for the barrier ack.
* master_bio may already be completed and invalidated.
* 11100: write acked (C),
* data received (for remote read, any protocol)
* or finally the barrier ack has arrived (B,A)...
* request can be freed
* 01100: neg-acked (write, protocol C)
* or neg-d-acked (read, any protocol)
* or killed from the transfer log
* during cleanup after connection loss
* request can be freed
* 01000: canceled or send failed...
* request can be freed
/* if "SENT" is not set, yet, this can still fail or be canceled.
* if "SENT" is set already, we still wait for an Ack packet.
* when cleared, the master_bio may be completed.
* in (B,A) the request object may still linger on the transaction log
* until the corresponding barrier ack comes in */
/* If it is QUEUED, and it is a WRITE, it is also registered in the
* transfer log. Currently we need this flag to avoid conflicts between
* worker canceling the request and tl_clear_barrier killing it from
* transfer log. We should restructure the code so this conflict does
* no longer occur. */
/* well, actually only "handed over to the network stack".
* TODO can potentially be dropped because of the similar meaning
* however it is not exactly the same. before we drop it
* we must ensure that we can tell a request with network part
* from a request without, regardless of what happens to it. */
/* when set, the request may be freed (if RQ_NET_QUEUED is clear).
* basically this means the corresponding P_BARRIER_ACK was received */
/* whether or not we know (C) or pretend (B,A) that the write
* was successfully written on the peer.
/* peer called drbd_set_in_sync() for this write */
/* keep this last, its for the RQ_NET_MASK */
/* Set when this is a write, clear for a read */
/* Should call drbd_al_complete_io() for this request... */
/* This was the most recent request during some blk_finish_plug()
* or its implicit from-schedule equivalent.
* We may use it as hint to send a P_UNPLUG_REMOTE */
/* The peer has sent a retry ACK */
/* would have been completed,
* but was not, because of drbd_suspended() */
/* We expect a receive ACK (wire proto B) */
/* We expect a write ACK (wite proto C) */
/* waiting for a barrier ack, did an extra kref_get */
#define RQ_LOCAL_OK (1UL << __RQ_LOCAL_OK)
#define RQ_NET_SENT (1UL << __RQ_NET_SENT)
#define RQ_NET_DONE (1UL << __RQ_NET_DONE)
#define RQ_NET_OK (1UL << __RQ_NET_OK)
#define RQ_NET_SIS (1UL << __RQ_NET_SIS)
#define RQ_NET_MASK (((1UL << __RQ_NET_MAX)-1) & ~RQ_LOCAL_MASK)
#define RQ_WRITE (1UL << __RQ_WRITE)
#define RQ_WSAME (1UL << __RQ_WSAME)
#define RQ_UNMAP (1UL << __RQ_UNMAP)
#define RQ_IN_ACT_LOG (1UL << __RQ_IN_ACT_LOG)
#define RQ_UNPLUG (1UL << __RQ_UNPLUG)
/* For waking up the frozen transfer log mod_req() has to return if the request
should be counted in the epoch object*/
#define MR_WRITE 1
#define MR_READ 2
static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src)
struct bio *bio;
bio = bio_clone_fast(bio_src, GFP_NOIO, drbd_io_bio_set);
req->private_bio = bio;
bio->bi_private = req;
bio->bi_end_io = drbd_request_endio;
bio->bi_next = NULL;
/* Short lived temporary struct on the stack.
* We could squirrel the error to be returned into
* bio->bi_iter.bi_size, or similar. But that would be too ugly. */
struct bio_and_error {
struct bio *bio;
int error;
extern void start_new_tl_epoch(struct drbd_connection *connection);
extern void drbd_req_destroy(struct kref *kref);
extern void _req_may_be_done(struct drbd_request *req,
struct bio_and_error *m);
extern int __req_mod(struct drbd_request *req, enum drbd_req_event what,
struct bio_and_error *m);
extern void complete_master_bio(struct drbd_device *device,
struct bio_and_error *m);
extern void request_timer_fn(unsigned long data);
extern void tl_restart(struct drbd_connection *connection, enum drbd_req_event what);
extern void _tl_restart(struct drbd_connection *connection, enum drbd_req_event what);
extern void tl_abort_disk_io(struct drbd_device *device);
/* this is in drbd_main.c */
extern void drbd_restart_request(struct drbd_request *req);
/* use this if you don't want to deal with calling complete_master_bio()
* outside the spinlock, e.g. when walking some list on cleanup. */
static inline int _req_mod(struct drbd_request *req, enum drbd_req_event what)
struct drbd_device *device = req->device;
struct bio_and_error m;
int rv;
/* __req_mod possibly frees req, do not touch req after that! */
rv = __req_mod(req, what, &m);
if (
complete_master_bio(device, &m);
return rv;
/* completion of master bio is outside of our spinlock.
* We still may or may not be inside some irqs disabled section
* of the lower level driver completion callback, so we need to
* spin_lock_irqsave here. */
static inline int req_mod(struct drbd_request *req,
enum drbd_req_event what)
unsigned long flags;
struct drbd_device *device = req->device;
struct bio_and_error m;
int rv;
spin_lock_irqsave(&device->resource->req_lock, flags);
rv = __req_mod(req, what, &m);
spin_unlock_irqrestore(&device->resource->req_lock, flags);
if (
complete_master_bio(device, &m);
return rv;
extern bool drbd_should_do_remote(union drbd_dev_state);