blob: 920ede2829d6c5e467e177ac43a3e97e9f550aac [file] [log] [blame]
/*
drbd.c
This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
Copyright (C) 2001-2008, LINBIT Information Technologies GmbH.
Copyright (C) 1999-2008, Philipp Reisner <philipp.reisner@linbit.com>.
Copyright (C) 2002-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
Thanks to Carter Burden, Bart Grantham and Gennadiy Nerubayev
from Logicworks, Inc. for making SDP replication support possible.
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
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
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.
*/
#include <linux/module.h>
#include <linux/drbd.h>
#include <asm/uaccess.h>
#include <asm/types.h>
#include <net/sock.h>
#include <linux/ctype.h>
#include <linux/mutex.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/reboot.h>
#include <linux/notifier.h>
#include <linux/kthread.h>
#define __KERNEL_SYSCALLS__
#include <linux/unistd.h>
#include <linux/vmalloc.h>
#include <linux/drbd_limits.h>
#include "drbd_int.h"
#include "drbd_req.h" /* only for _req_mod in tl_release and tl_clear */
#include "drbd_vli.h"
struct after_state_chg_work {
struct drbd_work w;
union drbd_state os;
union drbd_state ns;
enum chg_state_flags flags;
struct completion *done;
};
static DEFINE_MUTEX(drbd_main_mutex);
int drbdd_init(struct drbd_thread *);
int drbd_worker(struct drbd_thread *);
int drbd_asender(struct drbd_thread *);
int drbd_init(void);
static int drbd_open(struct block_device *bdev, fmode_t mode);
static int drbd_release(struct gendisk *gd, fmode_t mode);
static int w_after_state_ch(struct drbd_conf *mdev, struct drbd_work *w, int unused);
static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
union drbd_state ns, enum chg_state_flags flags);
static int w_md_sync(struct drbd_conf *mdev, struct drbd_work *w, int unused);
static void md_sync_timer_fn(unsigned long data);
static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused);
static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused);
MODULE_AUTHOR("Philipp Reisner <phil@linbit.com>, "
"Lars Ellenberg <lars@linbit.com>");
MODULE_DESCRIPTION("drbd - Distributed Replicated Block Device v" REL_VERSION);
MODULE_VERSION(REL_VERSION);
MODULE_LICENSE("GPL");
MODULE_PARM_DESC(minor_count, "Maximum number of drbd devices ("
__stringify(DRBD_MINOR_COUNT_MIN) "-" __stringify(DRBD_MINOR_COUNT_MAX) ")");
MODULE_ALIAS_BLOCKDEV_MAJOR(DRBD_MAJOR);
#include <linux/moduleparam.h>
/* allow_open_on_secondary */
MODULE_PARM_DESC(allow_oos, "DONT USE!");
/* thanks to these macros, if compiled into the kernel (not-module),
* this becomes the boot parameter drbd.minor_count */
module_param(minor_count, uint, 0444);
module_param(disable_sendpage, bool, 0644);
module_param(allow_oos, bool, 0);
module_param(cn_idx, uint, 0444);
module_param(proc_details, int, 0644);
#ifdef CONFIG_DRBD_FAULT_INJECTION
int enable_faults;
int fault_rate;
static int fault_count;
int fault_devs;
/* bitmap of enabled faults */
module_param(enable_faults, int, 0664);
/* fault rate % value - applies to all enabled faults */
module_param(fault_rate, int, 0664);
/* count of faults inserted */
module_param(fault_count, int, 0664);
/* bitmap of devices to insert faults on */
module_param(fault_devs, int, 0644);
#endif
/* module parameter, defined */
unsigned int minor_count = DRBD_MINOR_COUNT_DEF;
bool disable_sendpage;
bool allow_oos;
unsigned int cn_idx = CN_IDX_DRBD;
int proc_details; /* Detail level in proc drbd*/
/* Module parameter for setting the user mode helper program
* to run. Default is /sbin/drbdadm */
char usermode_helper[80] = "/sbin/drbdadm";
module_param_string(usermode_helper, usermode_helper, sizeof(usermode_helper), 0644);
/* in 2.6.x, our device mapping and config info contains our virtual gendisks
* as member "struct gendisk *vdisk;"
*/
struct drbd_conf **minor_table;
struct kmem_cache *drbd_request_cache;
struct kmem_cache *drbd_ee_cache; /* epoch entries */
struct kmem_cache *drbd_bm_ext_cache; /* bitmap extents */
struct kmem_cache *drbd_al_ext_cache; /* activity log extents */
mempool_t *drbd_request_mempool;
mempool_t *drbd_ee_mempool;
mempool_t *drbd_md_io_page_pool;
struct bio_set *drbd_md_io_bio_set;
/* I do not use a standard mempool, because:
1) I want to hand out the pre-allocated objects first.
2) I want to be able to interrupt sleeping allocation with a signal.
Note: This is a single linked list, the next pointer is the private
member of struct page.
*/
struct page *drbd_pp_pool;
spinlock_t drbd_pp_lock;
int drbd_pp_vacant;
wait_queue_head_t drbd_pp_wait;
DEFINE_RATELIMIT_STATE(drbd_ratelimit_state, 5 * HZ, 5);
static const struct block_device_operations drbd_ops = {
.owner = THIS_MODULE,
.open = drbd_open,
.release = drbd_release,
};
static void bio_destructor_drbd(struct bio *bio)
{
bio_free(bio, drbd_md_io_bio_set);
}
struct bio *bio_alloc_drbd(gfp_t gfp_mask)
{
struct bio *bio;
if (!drbd_md_io_bio_set)
return bio_alloc(gfp_mask, 1);
bio = bio_alloc_bioset(gfp_mask, 1, drbd_md_io_bio_set);
if (!bio)
return NULL;
bio->bi_destructor = bio_destructor_drbd;
return bio;
}
#ifdef __CHECKER__
/* When checking with sparse, and this is an inline function, sparse will
give tons of false positives. When this is a real functions sparse works.
*/
int _get_ldev_if_state(struct drbd_conf *mdev, enum drbd_disk_state mins)
{
int io_allowed;
atomic_inc(&mdev->local_cnt);
io_allowed = (mdev->state.disk >= mins);
if (!io_allowed) {
if (atomic_dec_and_test(&mdev->local_cnt))
wake_up(&mdev->misc_wait);
}
return io_allowed;
}
#endif
/**
* DOC: The transfer log
*
* The transfer log is a single linked list of &struct drbd_tl_epoch objects.
* mdev->newest_tle points to the head, mdev->oldest_tle points to the tail
* of the list. There is always at least one &struct drbd_tl_epoch object.
*
* Each &struct drbd_tl_epoch has a circular double linked list of requests
* attached.
*/
static int tl_init(struct drbd_conf *mdev)
{
struct drbd_tl_epoch *b;
/* during device minor initialization, we may well use GFP_KERNEL */
b = kmalloc(sizeof(struct drbd_tl_epoch), GFP_KERNEL);
if (!b)
return 0;
INIT_LIST_HEAD(&b->requests);
INIT_LIST_HEAD(&b->w.list);
b->next = NULL;
b->br_number = 4711;
b->n_writes = 0;
b->w.cb = NULL; /* if this is != NULL, we need to dec_ap_pending in tl_clear */
mdev->oldest_tle = b;
mdev->newest_tle = b;
INIT_LIST_HEAD(&mdev->out_of_sequence_requests);
INIT_LIST_HEAD(&mdev->barrier_acked_requests);
mdev->tl_hash = NULL;
mdev->tl_hash_s = 0;
return 1;
}
static void tl_cleanup(struct drbd_conf *mdev)
{
D_ASSERT(mdev->oldest_tle == mdev->newest_tle);
D_ASSERT(list_empty(&mdev->out_of_sequence_requests));
kfree(mdev->oldest_tle);
mdev->oldest_tle = NULL;
kfree(mdev->unused_spare_tle);
mdev->unused_spare_tle = NULL;
kfree(mdev->tl_hash);
mdev->tl_hash = NULL;
mdev->tl_hash_s = 0;
}
/**
* _tl_add_barrier() - Adds a barrier to the transfer log
* @mdev: DRBD device.
* @new: Barrier to be added before the current head of the TL.
*
* The caller must hold the req_lock.
*/
void _tl_add_barrier(struct drbd_conf *mdev, struct drbd_tl_epoch *new)
{
struct drbd_tl_epoch *newest_before;
INIT_LIST_HEAD(&new->requests);
INIT_LIST_HEAD(&new->w.list);
new->w.cb = NULL; /* if this is != NULL, we need to dec_ap_pending in tl_clear */
new->next = NULL;
new->n_writes = 0;
newest_before = mdev->newest_tle;
new->br_number = newest_before->br_number+1;
if (mdev->newest_tle != new) {
mdev->newest_tle->next = new;
mdev->newest_tle = new;
}
}
/**
* tl_release() - Free or recycle the oldest &struct drbd_tl_epoch object of the TL
* @mdev: DRBD device.
* @barrier_nr: Expected identifier of the DRBD write barrier packet.
* @set_size: Expected number of requests before that barrier.
*
* In case the passed barrier_nr or set_size does not match the oldest
* &struct drbd_tl_epoch objects this function will cause a termination
* of the connection.
*/
void tl_release(struct drbd_conf *mdev, unsigned int barrier_nr,
unsigned int set_size)
{
struct drbd_tl_epoch *b, *nob; /* next old barrier */
struct list_head *le, *tle;
struct drbd_request *r;
spin_lock_irq(&mdev->req_lock);
b = mdev->oldest_tle;
/* first some paranoia code */
if (b == NULL) {
dev_err(DEV, "BAD! BarrierAck #%u received, but no epoch in tl!?\n",
barrier_nr);
goto bail;
}
if (b->br_number != barrier_nr) {
dev_err(DEV, "BAD! BarrierAck #%u received, expected #%u!\n",
barrier_nr, b->br_number);
goto bail;
}
if (b->n_writes != set_size) {
dev_err(DEV, "BAD! BarrierAck #%u received with n_writes=%u, expected n_writes=%u!\n",
barrier_nr, set_size, b->n_writes);
goto bail;
}
/* Clean up list of requests processed during current epoch */
list_for_each_safe(le, tle, &b->requests) {
r = list_entry(le, struct drbd_request, tl_requests);
_req_mod(r, barrier_acked);
}
/* There could be requests on the list waiting for completion
of the write to the local disk. To avoid corruptions of
slab's data structures we have to remove the lists head.
Also there could have been a barrier ack out of sequence, overtaking
the write acks - which would be a bug and violating write ordering.
To not deadlock in case we lose connection while such requests are
still pending, we need some way to find them for the
_req_mode(connection_lost_while_pending).
These have been list_move'd to the out_of_sequence_requests list in
_req_mod(, barrier_acked) above.
*/
list_splice_init(&b->requests, &mdev->barrier_acked_requests);
nob = b->next;
if (test_and_clear_bit(CREATE_BARRIER, &mdev->flags)) {
_tl_add_barrier(mdev, b);
if (nob)
mdev->oldest_tle = nob;
/* if nob == NULL b was the only barrier, and becomes the new
barrier. Therefore mdev->oldest_tle points already to b */
} else {
D_ASSERT(nob != NULL);
mdev->oldest_tle = nob;
kfree(b);
}
spin_unlock_irq(&mdev->req_lock);
dec_ap_pending(mdev);
return;
bail:
spin_unlock_irq(&mdev->req_lock);
drbd_force_state(mdev, NS(conn, C_PROTOCOL_ERROR));
}
/**
* _tl_restart() - Walks the transfer log, and applies an action to all requests
* @mdev: DRBD device.
* @what: The action/event to perform with all request objects
*
* @what might be one of connection_lost_while_pending, resend, fail_frozen_disk_io,
* restart_frozen_disk_io.
*/
static void _tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
{
struct drbd_tl_epoch *b, *tmp, **pn;
struct list_head *le, *tle, carry_reads;
struct drbd_request *req;
int rv, n_writes, n_reads;
b = mdev->oldest_tle;
pn = &mdev->oldest_tle;
while (b) {
n_writes = 0;
n_reads = 0;
INIT_LIST_HEAD(&carry_reads);
list_for_each_safe(le, tle, &b->requests) {
req = list_entry(le, struct drbd_request, tl_requests);
rv = _req_mod(req, what);
n_writes += (rv & MR_WRITE) >> MR_WRITE_SHIFT;
n_reads += (rv & MR_READ) >> MR_READ_SHIFT;
}
tmp = b->next;
if (n_writes) {
if (what == resend) {
b->n_writes = n_writes;
if (b->w.cb == NULL) {
b->w.cb = w_send_barrier;
inc_ap_pending(mdev);
set_bit(CREATE_BARRIER, &mdev->flags);
}
drbd_queue_work(&mdev->data.work, &b->w);
}
pn = &b->next;
} else {
if (n_reads)
list_add(&carry_reads, &b->requests);
/* there could still be requests on that ring list,
* in case local io is still pending */
list_del(&b->requests);
/* dec_ap_pending corresponding to queue_barrier.
* the newest barrier may not have been queued yet,
* in which case w.cb is still NULL. */
if (b->w.cb != NULL)
dec_ap_pending(mdev);
if (b == mdev->newest_tle) {
/* recycle, but reinit! */
D_ASSERT(tmp == NULL);
INIT_LIST_HEAD(&b->requests);
list_splice(&carry_reads, &b->requests);
INIT_LIST_HEAD(&b->w.list);
b->w.cb = NULL;
b->br_number = net_random();
b->n_writes = 0;
*pn = b;
break;
}
*pn = tmp;
kfree(b);
}
b = tmp;
list_splice(&carry_reads, &b->requests);
}
/* Actions operating on the disk state, also want to work on
requests that got barrier acked. */
switch (what) {
case fail_frozen_disk_io:
case restart_frozen_disk_io:
list_for_each_safe(le, tle, &mdev->barrier_acked_requests) {
req = list_entry(le, struct drbd_request, tl_requests);
_req_mod(req, what);
}
case connection_lost_while_pending:
case resend:
break;
default:
dev_err(DEV, "what = %d in _tl_restart()\n", what);
}
}
/**
* tl_clear() - Clears all requests and &struct drbd_tl_epoch objects out of the TL
* @mdev: DRBD device.
*
* This is called after the connection to the peer was lost. The storage covered
* by the requests on the transfer gets marked as our of sync. Called from the
* receiver thread and the worker thread.
*/
void tl_clear(struct drbd_conf *mdev)
{
struct list_head *le, *tle;
struct drbd_request *r;
spin_lock_irq(&mdev->req_lock);
_tl_restart(mdev, connection_lost_while_pending);
/* we expect this list to be empty. */
D_ASSERT(list_empty(&mdev->out_of_sequence_requests));
/* but just in case, clean it up anyways! */
list_for_each_safe(le, tle, &mdev->out_of_sequence_requests) {
r = list_entry(le, struct drbd_request, tl_requests);
/* It would be nice to complete outside of spinlock.
* But this is easier for now. */
_req_mod(r, connection_lost_while_pending);
}
/* ensure bit indicating barrier is required is clear */
clear_bit(CREATE_BARRIER, &mdev->flags);
memset(mdev->app_reads_hash, 0, APP_R_HSIZE*sizeof(void *));
spin_unlock_irq(&mdev->req_lock);
}
void tl_restart(struct drbd_conf *mdev, enum drbd_req_event what)
{
spin_lock_irq(&mdev->req_lock);
_tl_restart(mdev, what);
spin_unlock_irq(&mdev->req_lock);
}
/**
* tl_abort_disk_io() - Abort disk I/O for all requests for a certain mdev in the TL
* @mdev: DRBD device.
*/
void tl_abort_disk_io(struct drbd_conf *mdev)
{
struct drbd_tl_epoch *b;
struct list_head *le, *tle;
struct drbd_request *req;
spin_lock_irq(&mdev->req_lock);
b = mdev->oldest_tle;
while (b) {
list_for_each_safe(le, tle, &b->requests) {
req = list_entry(le, struct drbd_request, tl_requests);
if (!(req->rq_state & RQ_LOCAL_PENDING))
continue;
_req_mod(req, abort_disk_io);
}
b = b->next;
}
list_for_each_safe(le, tle, &mdev->barrier_acked_requests) {
req = list_entry(le, struct drbd_request, tl_requests);
if (!(req->rq_state & RQ_LOCAL_PENDING))
continue;
_req_mod(req, abort_disk_io);
}
spin_unlock_irq(&mdev->req_lock);
}
/**
* cl_wide_st_chg() - true if the state change is a cluster wide one
* @mdev: DRBD device.
* @os: old (current) state.
* @ns: new (wanted) state.
*/
static int cl_wide_st_chg(struct drbd_conf *mdev,
union drbd_state os, union drbd_state ns)
{
return (os.conn >= C_CONNECTED && ns.conn >= C_CONNECTED &&
((os.role != R_PRIMARY && ns.role == R_PRIMARY) ||
(os.conn != C_STARTING_SYNC_T && ns.conn == C_STARTING_SYNC_T) ||
(os.conn != C_STARTING_SYNC_S && ns.conn == C_STARTING_SYNC_S) ||
(os.disk != D_FAILED && ns.disk == D_FAILED))) ||
(os.conn >= C_CONNECTED && ns.conn == C_DISCONNECTING) ||
(os.conn == C_CONNECTED && ns.conn == C_VERIFY_S);
}
enum drbd_state_rv
drbd_change_state(struct drbd_conf *mdev, enum chg_state_flags f,
union drbd_state mask, union drbd_state val)
{
unsigned long flags;
union drbd_state os, ns;
enum drbd_state_rv rv;
spin_lock_irqsave(&mdev->req_lock, flags);
os = mdev->state;
ns.i = (os.i & ~mask.i) | val.i;
rv = _drbd_set_state(mdev, ns, f, NULL);
ns = mdev->state;
spin_unlock_irqrestore(&mdev->req_lock, flags);
return rv;
}
/**
* drbd_force_state() - Impose a change which happens outside our control on our state
* @mdev: DRBD device.
* @mask: mask of state bits to change.
* @val: value of new state bits.
*/
void drbd_force_state(struct drbd_conf *mdev,
union drbd_state mask, union drbd_state val)
{
drbd_change_state(mdev, CS_HARD, mask, val);
}
static enum drbd_state_rv is_valid_state(struct drbd_conf *, union drbd_state);
static enum drbd_state_rv is_valid_state_transition(struct drbd_conf *,
union drbd_state,
union drbd_state);
enum sanitize_state_warnings {
NO_WARNING,
ABORTED_ONLINE_VERIFY,
ABORTED_RESYNC,
CONNECTION_LOST_NEGOTIATING,
IMPLICITLY_UPGRADED_DISK,
IMPLICITLY_UPGRADED_PDSK,
};
static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state os,
union drbd_state ns, enum sanitize_state_warnings *warn);
int drbd_send_state_req(struct drbd_conf *,
union drbd_state, union drbd_state);
static enum drbd_state_rv
_req_st_cond(struct drbd_conf *mdev, union drbd_state mask,
union drbd_state val)
{
union drbd_state os, ns;
unsigned long flags;
enum drbd_state_rv rv;
if (test_and_clear_bit(CL_ST_CHG_SUCCESS, &mdev->flags))
return SS_CW_SUCCESS;
if (test_and_clear_bit(CL_ST_CHG_FAIL, &mdev->flags))
return SS_CW_FAILED_BY_PEER;
rv = 0;
spin_lock_irqsave(&mdev->req_lock, flags);
os = mdev->state;
ns.i = (os.i & ~mask.i) | val.i;
ns = sanitize_state(mdev, os, ns, NULL);
if (!cl_wide_st_chg(mdev, os, ns))
rv = SS_CW_NO_NEED;
if (!rv) {
rv = is_valid_state(mdev, ns);
if (rv == SS_SUCCESS) {
rv = is_valid_state_transition(mdev, ns, os);
if (rv == SS_SUCCESS)
rv = SS_UNKNOWN_ERROR; /* cont waiting, otherwise fail. */
}
}
spin_unlock_irqrestore(&mdev->req_lock, flags);
return rv;
}
/**
* drbd_req_state() - Perform an eventually cluster wide state change
* @mdev: DRBD device.
* @mask: mask of state bits to change.
* @val: value of new state bits.
* @f: flags
*
* Should not be called directly, use drbd_request_state() or
* _drbd_request_state().
*/
static enum drbd_state_rv
drbd_req_state(struct drbd_conf *mdev, union drbd_state mask,
union drbd_state val, enum chg_state_flags f)
{
struct completion done;
unsigned long flags;
union drbd_state os, ns;
enum drbd_state_rv rv;
init_completion(&done);
if (f & CS_SERIALIZE)
mutex_lock(&mdev->state_mutex);
spin_lock_irqsave(&mdev->req_lock, flags);
os = mdev->state;
ns.i = (os.i & ~mask.i) | val.i;
ns = sanitize_state(mdev, os, ns, NULL);
if (cl_wide_st_chg(mdev, os, ns)) {
rv = is_valid_state(mdev, ns);
if (rv == SS_SUCCESS)
rv = is_valid_state_transition(mdev, ns, os);
spin_unlock_irqrestore(&mdev->req_lock, flags);
if (rv < SS_SUCCESS) {
if (f & CS_VERBOSE)
print_st_err(mdev, os, ns, rv);
goto abort;
}
drbd_state_lock(mdev);
if (!drbd_send_state_req(mdev, mask, val)) {
drbd_state_unlock(mdev);
rv = SS_CW_FAILED_BY_PEER;
if (f & CS_VERBOSE)
print_st_err(mdev, os, ns, rv);
goto abort;
}
wait_event(mdev->state_wait,
(rv = _req_st_cond(mdev, mask, val)));
if (rv < SS_SUCCESS) {
drbd_state_unlock(mdev);
if (f & CS_VERBOSE)
print_st_err(mdev, os, ns, rv);
goto abort;
}
spin_lock_irqsave(&mdev->req_lock, flags);
os = mdev->state;
ns.i = (os.i & ~mask.i) | val.i;
rv = _drbd_set_state(mdev, ns, f, &done);
drbd_state_unlock(mdev);
} else {
rv = _drbd_set_state(mdev, ns, f, &done);
}
spin_unlock_irqrestore(&mdev->req_lock, flags);
if (f & CS_WAIT_COMPLETE && rv == SS_SUCCESS) {
D_ASSERT(current != mdev->worker.task);
wait_for_completion(&done);
}
abort:
if (f & CS_SERIALIZE)
mutex_unlock(&mdev->state_mutex);
return rv;
}
/**
* _drbd_request_state() - Request a state change (with flags)
* @mdev: DRBD device.
* @mask: mask of state bits to change.
* @val: value of new state bits.
* @f: flags
*
* Cousin of drbd_request_state(), useful with the CS_WAIT_COMPLETE
* flag, or when logging of failed state change requests is not desired.
*/
enum drbd_state_rv
_drbd_request_state(struct drbd_conf *mdev, union drbd_state mask,
union drbd_state val, enum chg_state_flags f)
{
enum drbd_state_rv rv;
wait_event(mdev->state_wait,
(rv = drbd_req_state(mdev, mask, val, f)) != SS_IN_TRANSIENT_STATE);
return rv;
}
static void print_st(struct drbd_conf *mdev, char *name, union drbd_state ns)
{
dev_err(DEV, " %s = { cs:%s ro:%s/%s ds:%s/%s %c%c%c%c }\n",
name,
drbd_conn_str(ns.conn),
drbd_role_str(ns.role),
drbd_role_str(ns.peer),
drbd_disk_str(ns.disk),
drbd_disk_str(ns.pdsk),
is_susp(ns) ? 's' : 'r',
ns.aftr_isp ? 'a' : '-',
ns.peer_isp ? 'p' : '-',
ns.user_isp ? 'u' : '-'
);
}
void print_st_err(struct drbd_conf *mdev, union drbd_state os,
union drbd_state ns, enum drbd_state_rv err)
{
if (err == SS_IN_TRANSIENT_STATE)
return;
dev_err(DEV, "State change failed: %s\n", drbd_set_st_err_str(err));
print_st(mdev, " state", os);
print_st(mdev, "wanted", ns);
}
/**
* is_valid_state() - Returns an SS_ error code if ns is not valid
* @mdev: DRBD device.
* @ns: State to consider.
*/
static enum drbd_state_rv
is_valid_state(struct drbd_conf *mdev, union drbd_state ns)
{
/* See drbd_state_sw_errors in drbd_strings.c */
enum drbd_fencing_p fp;
enum drbd_state_rv rv = SS_SUCCESS;
fp = FP_DONT_CARE;
if (get_ldev(mdev)) {
fp = mdev->ldev->dc.fencing;
put_ldev(mdev);
}
if (get_net_conf(mdev)) {
if (!mdev->net_conf->two_primaries &&
ns.role == R_PRIMARY && ns.peer == R_PRIMARY)
rv = SS_TWO_PRIMARIES;
put_net_conf(mdev);
}
if (rv <= 0)
/* already found a reason to abort */;
else if (ns.role == R_SECONDARY && mdev->open_cnt)
rv = SS_DEVICE_IN_USE;
else if (ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.disk < D_UP_TO_DATE)
rv = SS_NO_UP_TO_DATE_DISK;
else if (fp >= FP_RESOURCE &&
ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk >= D_UNKNOWN)
rv = SS_PRIMARY_NOP;
else if (ns.role == R_PRIMARY && ns.disk <= D_INCONSISTENT && ns.pdsk <= D_INCONSISTENT)
rv = SS_NO_UP_TO_DATE_DISK;
else if (ns.conn > C_CONNECTED && ns.disk < D_INCONSISTENT)
rv = SS_NO_LOCAL_DISK;
else if (ns.conn > C_CONNECTED && ns.pdsk < D_INCONSISTENT)
rv = SS_NO_REMOTE_DISK;
else if (ns.conn > C_CONNECTED && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE)
rv = SS_NO_UP_TO_DATE_DISK;
else if ((ns.conn == C_CONNECTED ||
ns.conn == C_WF_BITMAP_S ||
ns.conn == C_SYNC_SOURCE ||
ns.conn == C_PAUSED_SYNC_S) &&
ns.disk == D_OUTDATED)
rv = SS_CONNECTED_OUTDATES;
else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
(mdev->sync_conf.verify_alg[0] == 0))
rv = SS_NO_VERIFY_ALG;
else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
mdev->agreed_pro_version < 88)
rv = SS_NOT_SUPPORTED;
else if (ns.conn >= C_CONNECTED && ns.pdsk == D_UNKNOWN)
rv = SS_CONNECTED_OUTDATES;
return rv;
}
/**
* is_valid_state_transition() - Returns an SS_ error code if the state transition is not possible
* @mdev: DRBD device.
* @ns: new state.
* @os: old state.
*/
static enum drbd_state_rv
is_valid_state_transition(struct drbd_conf *mdev, union drbd_state ns,
union drbd_state os)
{
enum drbd_state_rv rv = SS_SUCCESS;
if ((ns.conn == C_STARTING_SYNC_T || ns.conn == C_STARTING_SYNC_S) &&
os.conn > C_CONNECTED)
rv = SS_RESYNC_RUNNING;
if (ns.conn == C_DISCONNECTING && os.conn == C_STANDALONE)
rv = SS_ALREADY_STANDALONE;
if (ns.disk > D_ATTACHING && os.disk == D_DISKLESS)
rv = SS_IS_DISKLESS;
if (ns.conn == C_WF_CONNECTION && os.conn < C_UNCONNECTED)
rv = SS_NO_NET_CONFIG;
if (ns.disk == D_OUTDATED && os.disk < D_OUTDATED && os.disk != D_ATTACHING)
rv = SS_LOWER_THAN_OUTDATED;
if (ns.conn == C_DISCONNECTING && os.conn == C_UNCONNECTED)
rv = SS_IN_TRANSIENT_STATE;
if (ns.conn == os.conn && ns.conn == C_WF_REPORT_PARAMS)
rv = SS_IN_TRANSIENT_STATE;
/* While establishing a connection only allow cstate to change.
Delay/refuse role changes, detach attach etc... */
if (test_bit(STATE_SENT, &mdev->flags) &&
!(os.conn == C_WF_REPORT_PARAMS ||
(ns.conn == C_WF_REPORT_PARAMS && os.conn == C_WF_CONNECTION)))
rv = SS_IN_TRANSIENT_STATE;
if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && os.conn < C_CONNECTED)
rv = SS_NEED_CONNECTION;
if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
ns.conn != os.conn && os.conn > C_CONNECTED)
rv = SS_RESYNC_RUNNING;
if ((ns.conn == C_STARTING_SYNC_S || ns.conn == C_STARTING_SYNC_T) &&
os.conn < C_CONNECTED)
rv = SS_NEED_CONNECTION;
if ((ns.conn == C_SYNC_TARGET || ns.conn == C_SYNC_SOURCE)
&& os.conn < C_WF_REPORT_PARAMS)
rv = SS_NEED_CONNECTION; /* No NetworkFailure -> SyncTarget etc... */
return rv;
}
static void print_sanitize_warnings(struct drbd_conf *mdev, enum sanitize_state_warnings warn)
{
static const char *msg_table[] = {
[NO_WARNING] = "",
[ABORTED_ONLINE_VERIFY] = "Online-verify aborted.",
[ABORTED_RESYNC] = "Resync aborted.",
[CONNECTION_LOST_NEGOTIATING] = "Connection lost while negotiating, no data!",
[IMPLICITLY_UPGRADED_DISK] = "Implicitly upgraded disk",
[IMPLICITLY_UPGRADED_PDSK] = "Implicitly upgraded pdsk",
};
if (warn != NO_WARNING)
dev_warn(DEV, "%s\n", msg_table[warn]);
}
/**
* sanitize_state() - Resolves implicitly necessary additional changes to a state transition
* @mdev: DRBD device.
* @os: old state.
* @ns: new state.
* @warn_sync_abort:
*
* When we loose connection, we have to set the state of the peers disk (pdsk)
* to D_UNKNOWN. This rule and many more along those lines are in this function.
*/
static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state os,
union drbd_state ns, enum sanitize_state_warnings *warn)
{
enum drbd_fencing_p fp;
enum drbd_disk_state disk_min, disk_max, pdsk_min, pdsk_max;
if (warn)
*warn = NO_WARNING;
fp = FP_DONT_CARE;
if (get_ldev(mdev)) {
fp = mdev->ldev->dc.fencing;
put_ldev(mdev);
}
/* Disallow Network errors to configure a device's network part */
if ((ns.conn >= C_TIMEOUT && ns.conn <= C_TEAR_DOWN) &&
os.conn <= C_DISCONNECTING)
ns.conn = os.conn;
/* After a network error (+C_TEAR_DOWN) only C_UNCONNECTED or C_DISCONNECTING can follow.
* If you try to go into some Sync* state, that shall fail (elsewhere). */
if (os.conn >= C_TIMEOUT && os.conn <= C_TEAR_DOWN &&
ns.conn != C_UNCONNECTED && ns.conn != C_DISCONNECTING && ns.conn <= C_CONNECTED)
ns.conn = os.conn;
/* we cannot fail (again) if we already detached */
if (ns.disk == D_FAILED && os.disk == D_DISKLESS)
ns.disk = D_DISKLESS;
/* After C_DISCONNECTING only C_STANDALONE may follow */
if (os.conn == C_DISCONNECTING && ns.conn != C_STANDALONE)
ns.conn = os.conn;
if (ns.conn < C_CONNECTED) {
ns.peer_isp = 0;
ns.peer = R_UNKNOWN;
if (ns.pdsk > D_UNKNOWN || ns.pdsk < D_INCONSISTENT)
ns.pdsk = D_UNKNOWN;
}
/* Clear the aftr_isp when becoming unconfigured */
if (ns.conn == C_STANDALONE && ns.disk == D_DISKLESS && ns.role == R_SECONDARY)
ns.aftr_isp = 0;
/* Abort resync if a disk fails/detaches */
if (os.conn > C_CONNECTED && ns.conn > C_CONNECTED &&
(ns.disk <= D_FAILED || ns.pdsk <= D_FAILED)) {
if (warn)
*warn = os.conn == C_VERIFY_S || os.conn == C_VERIFY_T ?
ABORTED_ONLINE_VERIFY : ABORTED_RESYNC;
ns.conn = C_CONNECTED;
}
/* Connection breaks down before we finished "Negotiating" */
if (ns.conn < C_CONNECTED && ns.disk == D_NEGOTIATING &&
get_ldev_if_state(mdev, D_NEGOTIATING)) {
if (mdev->ed_uuid == mdev->ldev->md.uuid[UI_CURRENT]) {
ns.disk = mdev->new_state_tmp.disk;
ns.pdsk = mdev->new_state_tmp.pdsk;
} else {
if (warn)
*warn = CONNECTION_LOST_NEGOTIATING;
ns.disk = D_DISKLESS;
ns.pdsk = D_UNKNOWN;
}
put_ldev(mdev);
}
/* D_CONSISTENT and D_OUTDATED vanish when we get connected */
if (ns.conn >= C_CONNECTED && ns.conn < C_AHEAD) {
if (ns.disk == D_CONSISTENT || ns.disk == D_OUTDATED)
ns.disk = D_UP_TO_DATE;
if (ns.pdsk == D_CONSISTENT || ns.pdsk == D_OUTDATED)
ns.pdsk = D_UP_TO_DATE;
}
/* Implications of the connection stat on the disk states */
disk_min = D_DISKLESS;
disk_max = D_UP_TO_DATE;
pdsk_min = D_INCONSISTENT;
pdsk_max = D_UNKNOWN;
switch ((enum drbd_conns)ns.conn) {
case C_WF_BITMAP_T:
case C_PAUSED_SYNC_T:
case C_STARTING_SYNC_T:
case C_WF_SYNC_UUID:
case C_BEHIND:
disk_min = D_INCONSISTENT;
disk_max = D_OUTDATED;
pdsk_min = D_UP_TO_DATE;
pdsk_max = D_UP_TO_DATE;
break;
case C_VERIFY_S:
case C_VERIFY_T:
disk_min = D_UP_TO_DATE;
disk_max = D_UP_TO_DATE;
pdsk_min = D_UP_TO_DATE;
pdsk_max = D_UP_TO_DATE;
break;
case C_CONNECTED:
disk_min = D_DISKLESS;
disk_max = D_UP_TO_DATE;
pdsk_min = D_DISKLESS;
pdsk_max = D_UP_TO_DATE;
break;
case C_WF_BITMAP_S:
case C_PAUSED_SYNC_S:
case C_STARTING_SYNC_S:
case C_AHEAD:
disk_min = D_UP_TO_DATE;
disk_max = D_UP_TO_DATE;
pdsk_min = D_INCONSISTENT;
pdsk_max = D_CONSISTENT; /* D_OUTDATED would be nice. But explicit outdate necessary*/
break;
case C_SYNC_TARGET:
disk_min = D_INCONSISTENT;
disk_max = D_INCONSISTENT;
pdsk_min = D_UP_TO_DATE;
pdsk_max = D_UP_TO_DATE;
break;
case C_SYNC_SOURCE:
disk_min = D_UP_TO_DATE;
disk_max = D_UP_TO_DATE;
pdsk_min = D_INCONSISTENT;
pdsk_max = D_INCONSISTENT;
break;
case C_STANDALONE:
case C_DISCONNECTING:
case C_UNCONNECTED:
case C_TIMEOUT:
case C_BROKEN_PIPE:
case C_NETWORK_FAILURE:
case C_PROTOCOL_ERROR:
case C_TEAR_DOWN:
case C_WF_CONNECTION:
case C_WF_REPORT_PARAMS:
case C_MASK:
break;
}
if (ns.disk > disk_max)
ns.disk = disk_max;
if (ns.disk < disk_min) {
if (warn)
*warn = IMPLICITLY_UPGRADED_DISK;
ns.disk = disk_min;
}
if (ns.pdsk > pdsk_max)
ns.pdsk = pdsk_max;
if (ns.pdsk < pdsk_min) {
if (warn)
*warn = IMPLICITLY_UPGRADED_PDSK;
ns.pdsk = pdsk_min;
}
if (fp == FP_STONITH &&
(ns.role == R_PRIMARY && ns.conn < C_CONNECTED && ns.pdsk > D_OUTDATED) &&
!(os.role == R_PRIMARY && os.conn < C_CONNECTED && os.pdsk > D_OUTDATED))
ns.susp_fen = 1; /* Suspend IO while fence-peer handler runs (peer lost) */
if (mdev->sync_conf.on_no_data == OND_SUSPEND_IO &&
(ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE) &&
!(os.role == R_PRIMARY && os.disk < D_UP_TO_DATE && os.pdsk < D_UP_TO_DATE))
ns.susp_nod = 1; /* Suspend IO while no data available (no accessible data available) */
if (ns.aftr_isp || ns.peer_isp || ns.user_isp) {
if (ns.conn == C_SYNC_SOURCE)
ns.conn = C_PAUSED_SYNC_S;
if (ns.conn == C_SYNC_TARGET)
ns.conn = C_PAUSED_SYNC_T;
} else {
if (ns.conn == C_PAUSED_SYNC_S)
ns.conn = C_SYNC_SOURCE;
if (ns.conn == C_PAUSED_SYNC_T)
ns.conn = C_SYNC_TARGET;
}
return ns;
}
/* helper for __drbd_set_state */
static void set_ov_position(struct drbd_conf *mdev, enum drbd_conns cs)
{
if (mdev->agreed_pro_version < 90)
mdev->ov_start_sector = 0;
mdev->rs_total = drbd_bm_bits(mdev);
mdev->ov_position = 0;
if (cs == C_VERIFY_T) {
/* starting online verify from an arbitrary position
* does not fit well into the existing protocol.
* on C_VERIFY_T, we initialize ov_left and friends
* implicitly in receive_DataRequest once the
* first P_OV_REQUEST is received */
mdev->ov_start_sector = ~(sector_t)0;
} else {
unsigned long bit = BM_SECT_TO_BIT(mdev->ov_start_sector);
if (bit >= mdev->rs_total) {
mdev->ov_start_sector =
BM_BIT_TO_SECT(mdev->rs_total - 1);
mdev->rs_total = 1;
} else
mdev->rs_total -= bit;
mdev->ov_position = mdev->ov_start_sector;
}
mdev->ov_left = mdev->rs_total;
}
static void drbd_resume_al(struct drbd_conf *mdev)
{
if (test_and_clear_bit(AL_SUSPENDED, &mdev->flags))
dev_info(DEV, "Resumed AL updates\n");
}
/**
* __drbd_set_state() - Set a new DRBD state
* @mdev: DRBD device.
* @ns: new state.
* @flags: Flags
* @done: Optional completion, that will get completed after the after_state_ch() finished
*
* Caller needs to hold req_lock, and global_state_lock. Do not call directly.
*/
enum drbd_state_rv
__drbd_set_state(struct drbd_conf *mdev, union drbd_state ns,
enum chg_state_flags flags, struct completion *done)
{
union drbd_state os;
enum drbd_state_rv rv = SS_SUCCESS;
enum sanitize_state_warnings ssw;
struct after_state_chg_work *ascw;
os = mdev->state;
ns = sanitize_state(mdev, os, ns, &ssw);
if (ns.i == os.i)
return SS_NOTHING_TO_DO;
if (!(flags & CS_HARD)) {
/* pre-state-change checks ; only look at ns */
/* See drbd_state_sw_errors in drbd_strings.c */
rv = is_valid_state(mdev, ns);
if (rv < SS_SUCCESS) {
/* If the old state was illegal as well, then let
this happen...*/
if (is_valid_state(mdev, os) == rv)
rv = is_valid_state_transition(mdev, ns, os);
} else
rv = is_valid_state_transition(mdev, ns, os);
}
if (rv < SS_SUCCESS) {
if (flags & CS_VERBOSE)
print_st_err(mdev, os, ns, rv);
return rv;
}
print_sanitize_warnings(mdev, ssw);
{
char *pbp, pb[300];
pbp = pb;
*pbp = 0;
if (ns.role != os.role)
pbp += sprintf(pbp, "role( %s -> %s ) ",
drbd_role_str(os.role),
drbd_role_str(ns.role));
if (ns.peer != os.peer)
pbp += sprintf(pbp, "peer( %s -> %s ) ",
drbd_role_str(os.peer),
drbd_role_str(ns.peer));
if (ns.conn != os.conn)
pbp += sprintf(pbp, "conn( %s -> %s ) ",
drbd_conn_str(os.conn),
drbd_conn_str(ns.conn));
if (ns.disk != os.disk)
pbp += sprintf(pbp, "disk( %s -> %s ) ",
drbd_disk_str(os.disk),
drbd_disk_str(ns.disk));
if (ns.pdsk != os.pdsk)
pbp += sprintf(pbp, "pdsk( %s -> %s ) ",
drbd_disk_str(os.pdsk),
drbd_disk_str(ns.pdsk));
if (is_susp(ns) != is_susp(os))
pbp += sprintf(pbp, "susp( %d -> %d ) ",
is_susp(os),
is_susp(ns));
if (ns.aftr_isp != os.aftr_isp)
pbp += sprintf(pbp, "aftr_isp( %d -> %d ) ",
os.aftr_isp,
ns.aftr_isp);
if (ns.peer_isp != os.peer_isp)
pbp += sprintf(pbp, "peer_isp( %d -> %d ) ",
os.peer_isp,
ns.peer_isp);
if (ns.user_isp != os.user_isp)
pbp += sprintf(pbp, "user_isp( %d -> %d ) ",
os.user_isp,
ns.user_isp);
dev_info(DEV, "%s\n", pb);
}
/* solve the race between becoming unconfigured,
* worker doing the cleanup, and
* admin reconfiguring us:
* on (re)configure, first set CONFIG_PENDING,
* then wait for a potentially exiting worker,
* start the worker, and schedule one no_op.
* then proceed with configuration.
*/
if (ns.disk == D_DISKLESS &&
ns.conn == C_STANDALONE &&
ns.role == R_SECONDARY &&
!test_and_set_bit(CONFIG_PENDING, &mdev->flags))
set_bit(DEVICE_DYING, &mdev->flags);
/* if we are going -> D_FAILED or D_DISKLESS, grab one extra reference
* on the ldev here, to be sure the transition -> D_DISKLESS resp.
* drbd_ldev_destroy() won't happen before our corresponding
* after_state_ch works run, where we put_ldev again. */
if ((os.disk != D_FAILED && ns.disk == D_FAILED) ||
(os.disk != D_DISKLESS && ns.disk == D_DISKLESS))
atomic_inc(&mdev->local_cnt);
mdev->state = ns;
if (os.disk == D_ATTACHING && ns.disk >= D_NEGOTIATING)
drbd_print_uuids(mdev, "attached to UUIDs");
wake_up(&mdev->misc_wait);
wake_up(&mdev->state_wait);
/* aborted verify run. log the last position */
if ((os.conn == C_VERIFY_S || os.conn == C_VERIFY_T) &&
ns.conn < C_CONNECTED) {
mdev->ov_start_sector =
BM_BIT_TO_SECT(drbd_bm_bits(mdev) - mdev->ov_left);
dev_info(DEV, "Online Verify reached sector %llu\n",
(unsigned long long)mdev->ov_start_sector);
}
if ((os.conn == C_PAUSED_SYNC_T || os.conn == C_PAUSED_SYNC_S) &&
(ns.conn == C_SYNC_TARGET || ns.conn == C_SYNC_SOURCE)) {
dev_info(DEV, "Syncer continues.\n");
mdev->rs_paused += (long)jiffies
-(long)mdev->rs_mark_time[mdev->rs_last_mark];
if (ns.conn == C_SYNC_TARGET)
mod_timer(&mdev->resync_timer, jiffies);
}
if ((os.conn == C_SYNC_TARGET || os.conn == C_SYNC_SOURCE) &&
(ns.conn == C_PAUSED_SYNC_T || ns.conn == C_PAUSED_SYNC_S)) {
dev_info(DEV, "Resync suspended\n");
mdev->rs_mark_time[mdev->rs_last_mark] = jiffies;
}
if (os.conn == C_CONNECTED &&
(ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T)) {
unsigned long now = jiffies;
int i;
set_ov_position(mdev, ns.conn);
mdev->rs_start = now;
mdev->rs_last_events = 0;
mdev->rs_last_sect_ev = 0;
mdev->ov_last_oos_size = 0;
mdev->ov_last_oos_start = 0;
for (i = 0; i < DRBD_SYNC_MARKS; i++) {
mdev->rs_mark_left[i] = mdev->ov_left;
mdev->rs_mark_time[i] = now;
}
drbd_rs_controller_reset(mdev);
if (ns.conn == C_VERIFY_S) {
dev_info(DEV, "Starting Online Verify from sector %llu\n",
(unsigned long long)mdev->ov_position);
mod_timer(&mdev->resync_timer, jiffies);
}
}
if (get_ldev(mdev)) {
u32 mdf = mdev->ldev->md.flags & ~(MDF_CONSISTENT|MDF_PRIMARY_IND|
MDF_CONNECTED_IND|MDF_WAS_UP_TO_DATE|
MDF_PEER_OUT_DATED|MDF_CRASHED_PRIMARY);
if (test_bit(CRASHED_PRIMARY, &mdev->flags))
mdf |= MDF_CRASHED_PRIMARY;
if (mdev->state.role == R_PRIMARY ||
(mdev->state.pdsk < D_INCONSISTENT && mdev->state.peer == R_PRIMARY))
mdf |= MDF_PRIMARY_IND;
if (mdev->state.conn > C_WF_REPORT_PARAMS)
mdf |= MDF_CONNECTED_IND;
if (mdev->state.disk > D_INCONSISTENT)
mdf |= MDF_CONSISTENT;
if (mdev->state.disk > D_OUTDATED)
mdf |= MDF_WAS_UP_TO_DATE;
if (mdev->state.pdsk <= D_OUTDATED && mdev->state.pdsk >= D_INCONSISTENT)
mdf |= MDF_PEER_OUT_DATED;
if (mdf != mdev->ldev->md.flags) {
mdev->ldev->md.flags = mdf;
drbd_md_mark_dirty(mdev);
}
if (os.disk < D_CONSISTENT && ns.disk >= D_CONSISTENT)
drbd_set_ed_uuid(mdev, mdev->ldev->md.uuid[UI_CURRENT]);
put_ldev(mdev);
}
/* Peer was forced D_UP_TO_DATE & R_PRIMARY, consider to resync */
if (os.disk == D_INCONSISTENT && os.pdsk == D_INCONSISTENT &&
os.peer == R_SECONDARY && ns.peer == R_PRIMARY)
set_bit(CONSIDER_RESYNC, &mdev->flags);
/* Receiver should clean up itself */
if (os.conn != C_DISCONNECTING && ns.conn == C_DISCONNECTING)
drbd_thread_stop_nowait(&mdev->receiver);
/* Now the receiver finished cleaning up itself, it should die */
if (os.conn != C_STANDALONE && ns.conn == C_STANDALONE)
drbd_thread_stop_nowait(&mdev->receiver);
/* Upon network failure, we need to restart the receiver. */
if (os.conn > C_WF_CONNECTION &&
ns.conn <= C_TEAR_DOWN && ns.conn >= C_TIMEOUT)
drbd_thread_restart_nowait(&mdev->receiver);
/* Resume AL writing if we get a connection */
if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED)
drbd_resume_al(mdev);
/* remember last connect and attach times so request_timer_fn() won't
* kill newly established sessions while we are still trying to thaw
* previously frozen IO */
if (os.conn != C_WF_REPORT_PARAMS && ns.conn == C_WF_REPORT_PARAMS)
mdev->last_reconnect_jif = jiffies;
if ((os.disk == D_ATTACHING || os.disk == D_NEGOTIATING) &&
ns.disk > D_NEGOTIATING)
mdev->last_reattach_jif = jiffies;
ascw = kmalloc(sizeof(*ascw), GFP_ATOMIC);
if (ascw) {
ascw->os = os;
ascw->ns = ns;
ascw->flags = flags;
ascw->w.cb = w_after_state_ch;
ascw->done = done;
drbd_queue_work(&mdev->data.work, &ascw->w);
} else {
dev_warn(DEV, "Could not kmalloc an ascw\n");
}
return rv;
}
static int w_after_state_ch(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
struct after_state_chg_work *ascw =
container_of(w, struct after_state_chg_work, w);
after_state_ch(mdev, ascw->os, ascw->ns, ascw->flags);
if (ascw->flags & CS_WAIT_COMPLETE) {
D_ASSERT(ascw->done != NULL);
complete(ascw->done);
}
kfree(ascw);
return 1;
}
static void abw_start_sync(struct drbd_conf *mdev, int rv)
{
if (rv) {
dev_err(DEV, "Writing the bitmap failed not starting resync.\n");
_drbd_request_state(mdev, NS(conn, C_CONNECTED), CS_VERBOSE);
return;
}
switch (mdev->state.conn) {
case C_STARTING_SYNC_T:
_drbd_request_state(mdev, NS(conn, C_WF_SYNC_UUID), CS_VERBOSE);
break;
case C_STARTING_SYNC_S:
drbd_start_resync(mdev, C_SYNC_SOURCE);
break;
}
}
int drbd_bitmap_io_from_worker(struct drbd_conf *mdev,
int (*io_fn)(struct drbd_conf *),
char *why, enum bm_flag flags)
{
int rv;
D_ASSERT(current == mdev->worker.task);
/* open coded non-blocking drbd_suspend_io(mdev); */
set_bit(SUSPEND_IO, &mdev->flags);
drbd_bm_lock(mdev, why, flags);
rv = io_fn(mdev);
drbd_bm_unlock(mdev);
drbd_resume_io(mdev);
return rv;
}
/**
* after_state_ch() - Perform after state change actions that may sleep
* @mdev: DRBD device.
* @os: old state.
* @ns: new state.
* @flags: Flags
*/
static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
union drbd_state ns, enum chg_state_flags flags)
{
enum drbd_fencing_p fp;
enum drbd_req_event what = nothing;
union drbd_state nsm = (union drbd_state){ .i = -1 };
if (os.conn != C_CONNECTED && ns.conn == C_CONNECTED) {
clear_bit(CRASHED_PRIMARY, &mdev->flags);
if (mdev->p_uuid)
mdev->p_uuid[UI_FLAGS] &= ~((u64)2);
}
fp = FP_DONT_CARE;
if (get_ldev(mdev)) {
fp = mdev->ldev->dc.fencing;
put_ldev(mdev);
}
/* Inform userspace about the change... */
drbd_bcast_state(mdev, ns);
if (!(os.role == R_PRIMARY && os.disk < D_UP_TO_DATE && os.pdsk < D_UP_TO_DATE) &&
(ns.role == R_PRIMARY && ns.disk < D_UP_TO_DATE && ns.pdsk < D_UP_TO_DATE))
drbd_khelper(mdev, "pri-on-incon-degr");
/* Here we have the actions that are performed after a
state change. This function might sleep */
if (os.disk <= D_NEGOTIATING && ns.disk > D_NEGOTIATING)
mod_timer(&mdev->request_timer, jiffies + HZ);
nsm.i = -1;
if (ns.susp_nod) {
if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED)
what = resend;
if ((os.disk == D_ATTACHING || os.disk == D_NEGOTIATING) &&
ns.disk > D_NEGOTIATING)
what = restart_frozen_disk_io;
if (what != nothing)
nsm.susp_nod = 0;
}
if (ns.susp_fen) {
/* case1: The outdate peer handler is successful: */
if (os.pdsk > D_OUTDATED && ns.pdsk <= D_OUTDATED) {
tl_clear(mdev);
if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
drbd_uuid_new_current(mdev);
clear_bit(NEW_CUR_UUID, &mdev->flags);
}
spin_lock_irq(&mdev->req_lock);
_drbd_set_state(_NS(mdev, susp_fen, 0), CS_VERBOSE, NULL);
spin_unlock_irq(&mdev->req_lock);
}
/* case2: The connection was established again: */
if (os.conn < C_CONNECTED && ns.conn >= C_CONNECTED) {
clear_bit(NEW_CUR_UUID, &mdev->flags);
what = resend;
nsm.susp_fen = 0;
}
}
if (what != nothing) {
spin_lock_irq(&mdev->req_lock);
_tl_restart(mdev, what);
nsm.i &= mdev->state.i;
_drbd_set_state(mdev, nsm, CS_VERBOSE, NULL);
spin_unlock_irq(&mdev->req_lock);
}
/* Became sync source. With protocol >= 96, we still need to send out
* the sync uuid now. Need to do that before any drbd_send_state, or
* the other side may go "paused sync" before receiving the sync uuids,
* which is unexpected. */
if ((os.conn != C_SYNC_SOURCE && os.conn != C_PAUSED_SYNC_S) &&
(ns.conn == C_SYNC_SOURCE || ns.conn == C_PAUSED_SYNC_S) &&
mdev->agreed_pro_version >= 96 && get_ldev(mdev)) {
drbd_gen_and_send_sync_uuid(mdev);
put_ldev(mdev);
}
/* Do not change the order of the if above and the two below... */
if (os.pdsk == D_DISKLESS && ns.pdsk > D_DISKLESS) { /* attach on the peer */
drbd_send_uuids(mdev);
drbd_send_state(mdev, ns);
}
/* No point in queuing send_bitmap if we don't have a connection
* anymore, so check also the _current_ state, not only the new state
* at the time this work was queued. */
if (os.conn != C_WF_BITMAP_S && ns.conn == C_WF_BITMAP_S &&
mdev->state.conn == C_WF_BITMAP_S)
drbd_queue_bitmap_io(mdev, &drbd_send_bitmap, NULL,
"send_bitmap (WFBitMapS)",
BM_LOCKED_TEST_ALLOWED);
/* Lost contact to peer's copy of the data */
if ((os.pdsk >= D_INCONSISTENT &&
os.pdsk != D_UNKNOWN &&
os.pdsk != D_OUTDATED)
&& (ns.pdsk < D_INCONSISTENT ||
ns.pdsk == D_UNKNOWN ||
ns.pdsk == D_OUTDATED)) {
if (get_ldev(mdev)) {
if ((ns.role == R_PRIMARY || ns.peer == R_PRIMARY) &&
mdev->ldev->md.uuid[UI_BITMAP] == 0 && ns.disk >= D_UP_TO_DATE) {
if (is_susp(mdev->state)) {
set_bit(NEW_CUR_UUID, &mdev->flags);
} else {
drbd_uuid_new_current(mdev);
drbd_send_uuids(mdev);
}
}
put_ldev(mdev);
}
}
if (ns.pdsk < D_INCONSISTENT && get_ldev(mdev)) {
if (os.peer == R_SECONDARY && ns.peer == R_PRIMARY &&
mdev->ldev->md.uuid[UI_BITMAP] == 0 && ns.disk >= D_UP_TO_DATE) {
drbd_uuid_new_current(mdev);
drbd_send_uuids(mdev);
}
/* D_DISKLESS Peer becomes secondary */
if (os.peer == R_PRIMARY && ns.peer == R_SECONDARY)
/* We may still be Primary ourselves.
* No harm done if the bitmap still changes,
* redirtied pages will follow later. */
drbd_bitmap_io_from_worker(mdev, &drbd_bm_write,
"demote diskless peer", BM_LOCKED_SET_ALLOWED);
put_ldev(mdev);
}
/* Write out all changed bits on demote.
* Though, no need to da that just yet
* if there is a resync going on still */
if (os.role == R_PRIMARY && ns.role == R_SECONDARY &&
mdev->state.conn <= C_CONNECTED && get_ldev(mdev)) {
/* No changes to the bitmap expected this time, so assert that,
* even though no harm was done if it did change. */
drbd_bitmap_io_from_worker(mdev, &drbd_bm_write,
"demote", BM_LOCKED_TEST_ALLOWED);
put_ldev(mdev);
}
/* Last part of the attaching process ... */
if (ns.conn >= C_CONNECTED &&
os.disk == D_ATTACHING && ns.disk == D_NEGOTIATING) {
drbd_send_sizes(mdev, 0, 0); /* to start sync... */
drbd_send_uuids(mdev);
drbd_send_state(mdev, ns);
}
/* We want to pause/continue resync, tell peer. */
if (ns.conn >= C_CONNECTED &&
((os.aftr_isp != ns.aftr_isp) ||
(os.user_isp != ns.user_isp)))
drbd_send_state(mdev, ns);
/* In case one of the isp bits got set, suspend other devices. */
if ((!os.aftr_isp && !os.peer_isp && !os.user_isp) &&
(ns.aftr_isp || ns.peer_isp || ns.user_isp))
suspend_other_sg(mdev);
/* Make sure the peer gets informed about eventual state
changes (ISP bits) while we were in WFReportParams. */
if (os.conn == C_WF_REPORT_PARAMS && ns.conn >= C_CONNECTED)
drbd_send_state(mdev, ns);
if (os.conn != C_AHEAD && ns.conn == C_AHEAD)
drbd_send_state(mdev, ns);
/* We are in the progress to start a full sync... */
if ((os.conn != C_STARTING_SYNC_T && ns.conn == C_STARTING_SYNC_T) ||
(os.conn != C_STARTING_SYNC_S && ns.conn == C_STARTING_SYNC_S))
/* no other bitmap changes expected during this phase */
drbd_queue_bitmap_io(mdev,
&drbd_bmio_set_n_write, &abw_start_sync,
"set_n_write from StartingSync", BM_LOCKED_TEST_ALLOWED);
/* We are invalidating our self... */
if (os.conn < C_CONNECTED && ns.conn < C_CONNECTED &&
os.disk > D_INCONSISTENT && ns.disk == D_INCONSISTENT)
/* other bitmap operation expected during this phase */
drbd_queue_bitmap_io(mdev, &drbd_bmio_set_n_write, NULL,
"set_n_write from invalidate", BM_LOCKED_MASK);
/* first half of local IO error, failure to attach,
* or administrative detach */
if (os.disk != D_FAILED && ns.disk == D_FAILED) {
enum drbd_io_error_p eh = EP_PASS_ON;
int was_io_error = 0;
/* corresponding get_ldev was in __drbd_set_state, to serialize
* our cleanup here with the transition to D_DISKLESS.
* But is is still not save to dreference ldev here, since
* we might come from an failed Attach before ldev was set. */
if (mdev->ldev) {
eh = mdev->ldev->dc.on_io_error;
was_io_error = test_and_clear_bit(WAS_IO_ERROR, &mdev->flags);
/* Immediately allow completion of all application IO, that waits
for completion from the local disk. */
tl_abort_disk_io(mdev);
/* current state still has to be D_FAILED,
* there is only one way out: to D_DISKLESS,
* and that may only happen after our put_ldev below. */
if (mdev->state.disk != D_FAILED)
dev_err(DEV,
"ASSERT FAILED: disk is %s during detach\n",
drbd_disk_str(mdev->state.disk));
if (ns.conn >= C_CONNECTED)
drbd_send_state(mdev, ns);
drbd_rs_cancel_all(mdev);
/* In case we want to get something to stable storage still,
* this may be the last chance.
* Following put_ldev may transition to D_DISKLESS. */
drbd_md_sync(mdev);
}
put_ldev(mdev);
if (was_io_error && eh == EP_CALL_HELPER)
drbd_khelper(mdev, "local-io-error");
}
/* second half of local IO error, failure to attach,
* or administrative detach,
* after local_cnt references have reached zero again */
if (os.disk != D_DISKLESS && ns.disk == D_DISKLESS) {
/* We must still be diskless,
* re-attach has to be serialized with this! */
if (mdev->state.disk != D_DISKLESS)
dev_err(DEV,
"ASSERT FAILED: disk is %s while going diskless\n",
drbd_disk_str(mdev->state.disk));
mdev->rs_total = 0;
mdev->rs_failed = 0;
atomic_set(&mdev->rs_pending_cnt, 0);
if (ns.conn >= C_CONNECTED)
drbd_send_state(mdev, ns);
/* corresponding get_ldev in __drbd_set_state
* this may finally trigger drbd_ldev_destroy. */
put_ldev(mdev);
}
/* Notify peer that I had a local IO error, and did not detached.. */
if (os.disk == D_UP_TO_DATE && ns.disk == D_INCONSISTENT && ns.conn >= C_CONNECTED)
drbd_send_state(mdev, ns);
/* Disks got bigger while they were detached */
if (ns.disk > D_NEGOTIATING && ns.pdsk > D_NEGOTIATING &&
test_and_clear_bit(RESYNC_AFTER_NEG, &mdev->flags)) {
if (ns.conn == C_CONNECTED)
resync_after_online_grow(mdev);
}
/* A resync finished or aborted, wake paused devices... */
if ((os.conn > C_CONNECTED && ns.conn <= C_CONNECTED) ||
(os.peer_isp && !ns.peer_isp) ||
(os.user_isp && !ns.user_isp))
resume_next_sg(mdev);
/* sync target done with resync. Explicitly notify peer, even though
* it should (at least for non-empty resyncs) already know itself. */
if (os.disk < D_UP_TO_DATE && os.conn >= C_SYNC_SOURCE && ns.conn == C_CONNECTED)
drbd_send_state(mdev, ns);
/* Wake up role changes, that were delayed because of connection establishing */
if (os.conn == C_WF_REPORT_PARAMS && ns.conn != C_WF_REPORT_PARAMS) {
clear_bit(STATE_SENT, &mdev->flags);
wake_up(&mdev->state_wait);
}
/* This triggers bitmap writeout of potentially still unwritten pages
* if the resync finished cleanly, or aborted because of peer disk
* failure, or because of connection loss.
* For resync aborted because of local disk failure, we cannot do
* any bitmap writeout anymore.
* No harm done if some bits change during this phase.
*/
if (os.conn > C_CONNECTED && ns.conn <= C_CONNECTED && get_ldev(mdev)) {
drbd_queue_bitmap_io(mdev, &drbd_bm_write_copy_pages, NULL,
"write from resync_finished", BM_LOCKED_CHANGE_ALLOWED);
put_ldev(mdev);
}
/* free tl_hash if we Got thawed and are C_STANDALONE */
if (ns.conn == C_STANDALONE && !is_susp(ns) && mdev->tl_hash)
drbd_free_tl_hash(mdev);
/* Upon network connection, we need to start the receiver */
if (os.conn == C_STANDALONE && ns.conn == C_UNCONNECTED)
drbd_thread_start(&mdev->receiver);
/* Terminate worker thread if we are unconfigured - it will be
restarted as needed... */
if (ns.disk == D_DISKLESS &&
ns.conn == C_STANDALONE &&
ns.role == R_SECONDARY) {
if (os.aftr_isp != ns.aftr_isp)
resume_next_sg(mdev);
/* set in __drbd_set_state, unless CONFIG_PENDING was set */
if (test_bit(DEVICE_DYING, &mdev->flags))
drbd_thread_stop_nowait(&mdev->worker);
}
drbd_md_sync(mdev);
}
static int drbd_thread_setup(void *arg)
{
struct drbd_thread *thi = (struct drbd_thread *) arg;
struct drbd_conf *mdev = thi->mdev;
unsigned long flags;
int retval;
restart:
retval = thi->function(thi);
spin_lock_irqsave(&thi->t_lock, flags);
/* if the receiver has been "Exiting", the last thing it did
* was set the conn state to "StandAlone",
* if now a re-connect request comes in, conn state goes C_UNCONNECTED,
* and receiver thread will be "started".
* drbd_thread_start needs to set "Restarting" in that case.
* t_state check and assignment needs to be within the same spinlock,
* so either thread_start sees Exiting, and can remap to Restarting,
* or thread_start see None, and can proceed as normal.
*/
if (thi->t_state == Restarting) {
dev_info(DEV, "Restarting %s\n", current->comm);
thi->t_state = Running;
spin_unlock_irqrestore(&thi->t_lock, flags);
goto restart;
}
thi->task = NULL;
thi->t_state = None;
smp_mb();
complete(&thi->stop);
spin_unlock_irqrestore(&thi->t_lock, flags);
dev_info(DEV, "Terminating %s\n", current->comm);
/* Release mod reference taken when thread was started */
module_put(THIS_MODULE);
return retval;
}
static void drbd_thread_init(struct drbd_conf *mdev, struct drbd_thread *thi,
int (*func) (struct drbd_thread *))
{
spin_lock_init(&thi->t_lock);
thi->task = NULL;
thi->t_state = None;
thi->function = func;
thi->mdev = mdev;
}
int drbd_thread_start(struct drbd_thread *thi)
{
struct drbd_conf *mdev = thi->mdev;
struct task_struct *nt;
unsigned long flags;
const char *me =
thi == &mdev->receiver ? "receiver" :
thi == &mdev->asender ? "asender" :
thi == &mdev->worker ? "worker" : "NONSENSE";
/* is used from state engine doing drbd_thread_stop_nowait,
* while holding the req lock irqsave */
spin_lock_irqsave(&thi->t_lock, flags);
switch (thi->t_state) {
case None:
dev_info(DEV, "Starting %s thread (from %s [%d])\n",
me, current->comm, current->pid);
/* Get ref on module for thread - this is released when thread exits */
if (!try_module_get(THIS_MODULE)) {
dev_err(DEV, "Failed to get module reference in drbd_thread_start\n");
spin_unlock_irqrestore(&thi->t_lock, flags);
return false;
}
init_completion(&thi->stop);
D_ASSERT(thi->task == NULL);
thi->reset_cpu_mask = 1;
thi->t_state = Running;
spin_unlock_irqrestore(&thi->t_lock, flags);
flush_signals(current); /* otherw. may get -ERESTARTNOINTR */
nt = kthread_create(drbd_thread_setup, (void *) thi,
"drbd%d_%s", mdev_to_minor(mdev), me);
if (IS_ERR(nt)) {
dev_err(DEV, "Couldn't start thread\n");
module_put(THIS_MODULE);
return false;
}
spin_lock_irqsave(&thi->t_lock, flags);
thi->task = nt;
thi->t_state = Running;
spin_unlock_irqrestore(&thi->t_lock, flags);
wake_up_process(nt);
break;
case Exiting:
thi->t_state = Restarting;
dev_info(DEV, "Restarting %s thread (from %s [%d])\n",
me, current->comm, current->pid);
/* fall through */
case Running:
case Restarting:
default:
spin_unlock_irqrestore(&thi->t_lock, flags);
break;
}
return true;
}
void _drbd_thread_stop(struct drbd_thread *thi, int restart, int wait)
{
unsigned long flags;
enum drbd_thread_state ns = restart ? Restarting : Exiting;
/* may be called from state engine, holding the req lock irqsave */
spin_lock_irqsave(&thi->t_lock, flags);
if (thi->t_state == None) {
spin_unlock_irqrestore(&thi->t_lock, flags);
if (restart)
drbd_thread_start(thi);
return;
}
if (thi->t_state != ns) {
if (thi->task == NULL) {
spin_unlock_irqrestore(&thi->t_lock, flags);
return;
}
thi->t_state = ns;
smp_mb();
init_completion(&thi->stop);
if (thi->task != current)
force_sig(DRBD_SIGKILL, thi->task);
}
spin_unlock_irqrestore(&thi->t_lock, flags);
if (wait)
wait_for_completion(&thi->stop);
}
#ifdef CONFIG_SMP
/**
* drbd_calc_cpu_mask() - Generate CPU masks, spread over all CPUs
* @mdev: DRBD device.
*
* Forces all threads of a device onto the same CPU. This is beneficial for
* DRBD's performance. May be overwritten by user's configuration.
*/
void drbd_calc_cpu_mask(struct drbd_conf *mdev)
{
int ord, cpu;
/* user override. */
if (cpumask_weight(mdev->cpu_mask))
return;
ord = mdev_to_minor(mdev) % cpumask_weight(cpu_online_mask);
for_each_online_cpu(cpu) {
if (ord-- == 0) {
cpumask_set_cpu(cpu, mdev->cpu_mask);
return;
}
}
/* should not be reached */
cpumask_setall(mdev->cpu_mask);
}
/**
* drbd_thread_current_set_cpu() - modifies the cpu mask of the _current_ thread
* @mdev: DRBD device.
*
* call in the "main loop" of _all_ threads, no need for any mutex, current won't die
* prematurely.
*/
void drbd_thread_current_set_cpu(struct drbd_conf *mdev)
{
struct task_struct *p = current;
struct drbd_thread *thi =
p == mdev->asender.task ? &mdev->asender :
p == mdev->receiver.task ? &mdev->receiver :
p == mdev->worker.task ? &mdev->worker :
NULL;
ERR_IF(thi == NULL)
return;
if (!thi->reset_cpu_mask)
return;
thi->reset_cpu_mask = 0;
set_cpus_allowed_ptr(p, mdev->cpu_mask);
}
#endif
/* the appropriate socket mutex must be held already */
int _drbd_send_cmd(struct drbd_conf *mdev, struct socket *sock,
enum drbd_packets cmd, struct p_header80 *h,
size_t size, unsigned msg_flags)
{
int sent, ok;
ERR_IF(!h) return false;
ERR_IF(!size) return false;
h->magic = BE_DRBD_MAGIC;
h->command = cpu_to_be16(cmd);
h->length = cpu_to_be16(size-sizeof(struct p_header80));
sent = drbd_send(mdev, sock, h, size, msg_flags);
ok = (sent == size);
if (!ok && !signal_pending(current))
dev_warn(DEV, "short sent %s size=%d sent=%d\n",
cmdname(cmd), (int)size, sent);
return ok;
}
/* don't pass the socket. we may only look at it
* when we hold the appropriate socket mutex.
*/
int drbd_send_cmd(struct drbd_conf *mdev, int use_data_socket,
enum drbd_packets cmd, struct p_header80 *h, size_t size)
{
int ok = 0;
struct socket *sock;
if (use_data_socket) {
mutex_lock(&mdev->data.mutex);
sock = mdev->data.socket;
} else {
mutex_lock(&mdev->meta.mutex);
sock = mdev->meta.socket;
}
/* drbd_disconnect() could have called drbd_free_sock()
* while we were waiting in down()... */
if (likely(sock != NULL))
ok = _drbd_send_cmd(mdev, sock, cmd, h, size, 0);
if (use_data_socket)
mutex_unlock(&mdev->data.mutex);
else
mutex_unlock(&mdev->meta.mutex);
return ok;
}
int drbd_send_cmd2(struct drbd_conf *mdev, enum drbd_packets cmd, char *data,
size_t size)
{
struct p_header80 h;
int ok;
h.magic = BE_DRBD_MAGIC;
h.command = cpu_to_be16(cmd);
h.length = cpu_to_be16(size);
if (!drbd_get_data_sock(mdev))
return 0;
ok = (sizeof(h) ==
drbd_send(mdev, mdev->data.socket, &h, sizeof(h), 0));
ok = ok && (size ==
drbd_send(mdev, mdev->data.socket, data, size, 0));
drbd_put_data_sock(mdev);
return ok;
}
int drbd_send_sync_param(struct drbd_conf *mdev, struct syncer_conf *sc)
{
struct p_rs_param_95 *p;
struct socket *sock;
int size, rv;
const int apv = mdev->agreed_pro_version;
size = apv <= 87 ? sizeof(struct p_rs_param)
: apv == 88 ? sizeof(struct p_rs_param)
+ strlen(mdev->sync_conf.verify_alg) + 1
: apv <= 94 ? sizeof(struct p_rs_param_89)
: /* apv >= 95 */ sizeof(struct p_rs_param_95);
/* used from admin command context and receiver/worker context.
* to avoid kmalloc, grab the socket right here,
* then use the pre-allocated sbuf there */
mutex_lock(&mdev->data.mutex);
sock = mdev->data.socket;
if (likely(sock != NULL)) {
enum drbd_packets cmd = apv >= 89 ? P_SYNC_PARAM89 : P_SYNC_PARAM;
p = &mdev->data.sbuf.rs_param_95;
/* initialize verify_alg and csums_alg */
memset(p->verify_alg, 0, 2 * SHARED_SECRET_MAX);
p->rate = cpu_to_be32(sc->rate);
p->c_plan_ahead = cpu_to_be32(sc->c_plan_ahead);
p->c_delay_target = cpu_to_be32(sc->c_delay_target);
p->c_fill_target = cpu_to_be32(sc->c_fill_target);
p->c_max_rate = cpu_to_be32(sc->c_max_rate);
if (apv >= 88)
strcpy(p->verify_alg, mdev->sync_conf.verify_alg);
if (apv >= 89)
strcpy(p->csums_alg, mdev->sync_conf.csums_alg);
rv = _drbd_send_cmd(mdev, sock, cmd, &p->head, size, 0);
} else
rv = 0; /* not ok */
mutex_unlock(&mdev->data.mutex);
return rv;
}
int drbd_send_protocol(struct drbd_conf *mdev)
{
struct p_protocol *p;
int size, cf, rv;
size = sizeof(struct p_protocol);
if (mdev->agreed_pro_version >= 87)
size += strlen(mdev->net_conf->integrity_alg) + 1;
/* we must not recurse into our own queue,
* as that is blocked during handshake */
p = kmalloc(size, GFP_NOIO);
if (p == NULL)
return 0;
p->protocol = cpu_to_be32(mdev->net_conf->wire_protocol);
p->after_sb_0p = cpu_to_be32(mdev->net_conf->after_sb_0p);
p->after_sb_1p = cpu_to_be32(mdev->net_conf->after_sb_1p);
p->after_sb_2p = cpu_to_be32(mdev->net_conf->after_sb_2p);
p->two_primaries = cpu_to_be32(mdev->net_conf->two_primaries);
cf = 0;
if (mdev->net_conf->want_lose)
cf |= CF_WANT_LOSE;
if (mdev->net_conf->dry_run) {
if (mdev->agreed_pro_version >= 92)
cf |= CF_DRY_RUN;
else {
dev_err(DEV, "--dry-run is not supported by peer");
kfree(p);
return -1;
}
}
p->conn_flags = cpu_to_be32(cf);
if (mdev->agreed_pro_version >= 87)
strcpy(p->integrity_alg, mdev->net_conf->integrity_alg);
rv = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_PROTOCOL,
(struct p_header80 *)p, size);
kfree(p);
return rv;
}
int _drbd_send_uuids(struct drbd_conf *mdev, u64 uuid_flags)
{
struct p_uuids p;
int i;
if (!get_ldev_if_state(mdev, D_NEGOTIATING))
return 1;
for (i = UI_CURRENT; i < UI_SIZE; i++)
p.uuid[i] = mdev->ldev ? cpu_to_be64(mdev->ldev->md.uuid[i]) : 0;
mdev->comm_bm_set = drbd_bm_total_weight(mdev);
p.uuid[UI_SIZE] = cpu_to_be64(mdev->comm_bm_set);
uuid_flags |= mdev->net_conf->want_lose ? 1 : 0;
uuid_flags |= test_bit(CRASHED_PRIMARY, &mdev->flags) ? 2 : 0;
uuid_flags |= mdev->new_state_tmp.disk == D_INCONSISTENT ? 4 : 0;
p.uuid[UI_FLAGS] = cpu_to_be64(uuid_flags);
put_ldev(mdev);
return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_UUIDS,
(struct p_header80 *)&p, sizeof(p));
}
int drbd_send_uuids(struct drbd_conf *mdev)
{
return _drbd_send_uuids(mdev, 0);
}
int drbd_send_uuids_skip_initial_sync(struct drbd_conf *mdev)
{
return _drbd_send_uuids(mdev, 8);
}
void drbd_print_uuids(struct drbd_conf *mdev, const char *text)
{
if (get_ldev_if_state(mdev, D_NEGOTIATING)) {
u64 *uuid = mdev->ldev->md.uuid;
dev_info(DEV, "%s %016llX:%016llX:%016llX:%016llX\n",
text,
(unsigned long long)uuid[UI_CURRENT],
(unsigned long long)uuid[UI_BITMAP],
(unsigned long long)uuid[UI_HISTORY_START],
(unsigned long long)uuid[UI_HISTORY_END]);
put_ldev(mdev);
} else {
dev_info(DEV, "%s effective data uuid: %016llX\n",
text,
(unsigned long long)mdev->ed_uuid);
}
}
int drbd_gen_and_send_sync_uuid(struct drbd_conf *mdev)
{
struct p_rs_uuid p;
u64 uuid;
D_ASSERT(mdev->state.disk == D_UP_TO_DATE);
uuid = mdev->ldev->md.uuid[UI_BITMAP];
if (uuid && uuid != UUID_JUST_CREATED)
uuid = uuid + UUID_NEW_BM_OFFSET;
else
get_random_bytes(&uuid, sizeof(u64));
drbd_uuid_set(mdev, UI_BITMAP, uuid);
drbd_print_uuids(mdev, "updated sync UUID");
drbd_md_sync(mdev);
p.uuid = cpu_to_be64(uuid);
return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_SYNC_UUID,
(struct p_header80 *)&p, sizeof(p));
}
int drbd_send_sizes(struct drbd_conf *mdev, int trigger_reply, enum dds_flags flags)
{
struct p_sizes p;
sector_t d_size, u_size;
int q_order_type, max_bio_size;
int ok;
if (get_ldev_if_state(mdev, D_NEGOTIATING)) {
D_ASSERT(mdev->ldev->backing_bdev);
d_size = drbd_get_max_capacity(mdev->ldev);
u_size = mdev->ldev->dc.disk_size;
q_order_type = drbd_queue_order_type(mdev);
max_bio_size = queue_max_hw_sectors(mdev->ldev->backing_bdev->bd_disk->queue) << 9;
max_bio_size = min_t(int, max_bio_size, DRBD_MAX_BIO_SIZE);
put_ldev(mdev);
} else {
d_size = 0;
u_size = 0;
q_order_type = QUEUE_ORDERED_NONE;
max_bio_size = DRBD_MAX_BIO_SIZE; /* ... multiple BIOs per peer_request */
}
/* Never allow old drbd (up to 8.3.7) to see more than 32KiB */
if (mdev->agreed_pro_version <= 94)
max_bio_size = min_t(int, max_bio_size, DRBD_MAX_SIZE_H80_PACKET);
p.d_size = cpu_to_be64(d_size);
p.u_size = cpu_to_be64(u_size);
p.c_size = cpu_to_be64(trigger_reply ? 0 : drbd_get_capacity(mdev->this_bdev));
p.max_bio_size = cpu_to_be32(max_bio_size);
p.queue_order_type = cpu_to_be16(q_order_type);
p.dds_flags = cpu_to_be16(flags);
ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_SIZES,
(struct p_header80 *)&p, sizeof(p));
return ok;
}
/**
* drbd_send_current_state() - Sends the drbd state to the peer
* @mdev: DRBD device.
*/
int drbd_send_current_state(struct drbd_conf *mdev)
{
struct socket *sock;
struct p_state p;
int ok = 0;
/* Grab state lock so we wont send state if we're in the middle
* of a cluster wide state change on another thread */
drbd_state_lock(mdev);
mutex_lock(&mdev->data.mutex);
p.state = cpu_to_be32(mdev->state.i); /* Within the send mutex */
sock = mdev->data.socket;
if (likely(sock != NULL)) {
ok = _drbd_send_cmd(mdev, sock, P_STATE,
(struct p_header80 *)&p, sizeof(p), 0);
}
mutex_unlock(&mdev->data.mutex);
drbd_state_unlock(mdev);
return ok;
}
/**
* drbd_send_state() - After a state change, sends the new state to the peer
* @mdev: DRBD device.
* @state: the state to send, not necessarily the current state.
*
* Each state change queues an "after_state_ch" work, which will eventually
* send the resulting new state to the peer. If more state changes happen
* between queuing and processing of the after_state_ch work, we still
* want to send each intermediary state in the order it occurred.
*/
int drbd_send_state(struct drbd_conf *mdev, union drbd_state state)
{
struct socket *sock;
struct p_state p;
int ok = 0;
mutex_lock(&mdev->data.mutex);
p.state = cpu_to_be32(state.i);
sock = mdev->data.socket;
if (likely(sock != NULL)) {
ok = _drbd_send_cmd(mdev, sock, P_STATE,
(struct p_header80 *)&p, sizeof(p), 0);
}
mutex_unlock(&mdev->data.mutex);
return ok;
}
int drbd_send_state_req(struct drbd_conf *mdev,
union drbd_state mask, union drbd_state val)
{
struct p_req_state p;
p.mask = cpu_to_be32(mask.i);
p.val = cpu_to_be32(val.i);
return drbd_send_cmd(mdev, USE_DATA_SOCKET, P_STATE_CHG_REQ,
(struct p_header80 *)&p, sizeof(p));
}
int drbd_send_sr_reply(struct drbd_conf *mdev, enum drbd_state_rv retcode)
{
struct p_req_state_reply p;
p.retcode = cpu_to_be32(retcode);
return drbd_send_cmd(mdev, USE_META_SOCKET, P_STATE_CHG_REPLY,
(struct p_header80 *)&p, sizeof(p));
}
int fill_bitmap_rle_bits(struct drbd_conf *mdev,
struct p_compressed_bm *p,
struct bm_xfer_ctx *c)
{
struct bitstream bs;
unsigned long plain_bits;
unsigned long tmp;
unsigned long rl;
unsigned len;
unsigned toggle;
int bits;
/* may we use this feature? */
if ((mdev->sync_conf.use_rle == 0) ||
(mdev->agreed_pro_version < 90))
return 0;
if (c->bit_offset >= c->bm_bits)
return 0; /* nothing to do. */
/* use at most thus many bytes */
bitstream_init(&bs, p->code, BM_PACKET_VLI_BYTES_MAX, 0);
memset(p->code, 0, BM_PACKET_VLI_BYTES_MAX);
/* plain bits covered in this code string */
plain_bits = 0;
/* p->encoding & 0x80 stores whether the first run length is set.
* bit offset is implicit.
* start with toggle == 2 to be able to tell the first iteration */
toggle = 2;
/* see how much plain bits we can stuff into one packet
* using RLE and VLI. */
do {
tmp = (toggle == 0) ? _drbd_bm_find_next_zero(mdev, c->bit_offset)
: _drbd_bm_find_next(mdev, c->bit_offset);
if (tmp == -1UL)
tmp = c->bm_bits;
rl = tmp - c->bit_offset;
if (toggle == 2) { /* first iteration */
if (rl == 0) {
/* the first checked bit was set,
* store start value, */
DCBP_set_start(p, 1);
/* but skip encoding of zero run length */
toggle = !toggle;
continue;
}
DCBP_set_start(p, 0);
}
/* paranoia: catch zero runlength.
* can only happen if bitmap is modified while we scan it. */
if (rl == 0) {
dev_err(DEV, "unexpected zero runlength while encoding bitmap "
"t:%u bo:%lu\n", toggle, c->bit_offset);
return -1;
}
bits = vli_encode_bits(&bs, rl);
if (bits == -ENOBUFS) /* buffer full */
break;
if (bits <= 0) {
dev_err(DEV, "error while encoding bitmap: %d\n", bits);
return 0;
}
toggle = !toggle;
plain_bits += rl;
c->bit_offset = tmp;
} while (c->bit_offset < c->bm_bits);
len = bs.cur.b - p->code + !!bs.cur.bit;
if (plain_bits < (len << 3)) {
/* incompressible with this method.
* we need to rewind both word and bit position. */
c->bit_offset -= plain_bits;
bm_xfer_ctx_bit_to_word_offset(c);
c->bit_offset = c->word_offset * BITS_PER_LONG;
return 0;
}
/* RLE + VLI was able to compress it just fine.
* update c->word_offset. */
bm_xfer_ctx_bit_to_word_offset(c);
/* store pad_bits */
DCBP_set_pad_bits(p, (8 - bs.cur.bit) & 0x7);
return len;
}
/**
* send_bitmap_rle_or_plain
*
* Return 0 when done, 1 when another iteration is needed, and a negative error
* code upon failure.
*/
static int
send_bitmap_rle_or_plain(struct drbd_conf *mdev,
struct p_header80 *h, struct bm_xfer_ctx *c)
{
struct p_compressed_bm *p = (void*)h;
unsigned long num_words;
int len;
int ok;
len = fill_bitmap_rle_bits(mdev, p, c);
if (len < 0)
return -EIO;
if (len) {
DCBP_set_code(p, RLE_VLI_Bits);
ok = _drbd_send_cmd(mdev, mdev->data.socket, P_COMPRESSED_BITMAP, h,
sizeof(*p) + len, 0);
c->packets[0]++;
c->bytes[0] += sizeof(*p) + len;
if (c->bit_offset >= c->bm_bits)
len = 0; /* DONE */
} else {
/* was not compressible.
* send a buffer full of plain text bits instead. */
num_words = min_t(size_t, BM_PACKET_WORDS, c->bm_words - c->word_offset);
len = num_words * sizeof(long);
if (len)
drbd_bm_get_lel(mdev, c->word_offset, num_words, (unsigned long*)h->payload);
ok = _drbd_send_cmd(mdev, mdev->data.socket, P_BITMAP,
h, sizeof(struct p_header80) + len, 0);
c->word_offset += num_words;
c->bit_offset = c->word_offset * BITS_PER_LONG;
c->packets[1]++;
c->bytes[1] += sizeof(struct p_header80) + len;
if (c->bit_offset > c->bm_bits)
c->bit_offset = c->bm_bits;
}
if (ok) {
if (len == 0) {
INFO_bm_xfer_stats(mdev, "send", c);
return 0;
} else
return 1;
}
return -EIO;
}
/* See the comment at receive_bitmap() */
int _drbd_send_bitmap(struct drbd_conf *mdev)
{
struct bm_xfer_ctx c;
struct p_header80 *p;
int err;
ERR_IF(!mdev->bitmap) return false;
/* maybe we should use some per thread scratch page,
* and allocate that during initial device creation? */
p = (struct p_header80 *) __get_free_page(GFP_NOIO);
if (!p) {
dev_err(DEV, "failed to allocate one page buffer in %s\n", __func__);
return false;
}
if (get_ldev(mdev)) {
if (drbd_md_test_flag(mdev->ldev, MDF_FULL_SYNC)) {
dev_info(DEV, "Writing the whole bitmap, MDF_FullSync was set.\n");
drbd_bm_set_all(mdev);
if (drbd_bm_write(mdev)) {
/* write_bm did fail! Leave full sync flag set in Meta P_DATA
* but otherwise process as per normal - need to tell other
* side that a full resync is required! */
dev_err(DEV, "Failed to write bitmap to disk!\n");
} else {
drbd_md_clear_flag(mdev, MDF_FULL_SYNC);
drbd_md_sync(mdev);
}
}
put_ldev(mdev);
}
c = (struct bm_xfer_ctx) {
.bm_bits = drbd_bm_bits(mdev),
.bm_words = drbd_bm_words(mdev),
};
do {
err = send_bitmap_rle_or_plain(mdev, p, &c);
} while (err > 0);
free_page((unsigned long) p);
return err == 0;
}
int drbd_send_bitmap(struct drbd_conf *mdev)
{
int err;
if (!drbd_get_data_sock(mdev))
return -1;
err = !_drbd_send_bitmap(mdev);
drbd_put_data_sock(mdev);
return err;
}
int drbd_send_b_ack(struct drbd_conf *mdev, u32 barrier_nr, u32 set_size)
{
int ok;
struct p_barrier_ack p;
p.barrier = barrier_nr;
p.set_size = cpu_to_be32(set_size);
if (mdev->state.conn < C_CONNECTED)
return false;
ok = drbd_send_cmd(mdev, USE_META_SOCKET, P_BARRIER_ACK,
(struct p_header80 *)&p, sizeof(p));
return ok;
}
/**
* _drbd_send_ack() - Sends an ack packet
* @mdev: DRBD device.
* @cmd: Packet command code.
* @sector: sector, needs to be in big endian byte order
* @blksize: size in byte, needs to be in big endian byte order
* @block_id: Id, big endian byte order
*/
static int _drbd_send_ack(struct drbd_conf *mdev, enum drbd_packets cmd,
u64 sector,
u32 blksize,
u64 block_id)
{
int ok;
struct p_block_ack p;
p.sector = sector;
p.block_id = block_id;
p.blksize = blksize;
p.seq_num = cpu_to_be32(atomic_add_return(1, &mdev->packet_seq));
if (!mdev->meta.socket || mdev->state.conn < C_CONNECTED)
return false;
ok = drbd_send_cmd(mdev, USE_META_SOCKET, cmd,
(struct p_header80 *)&p, sizeof(p));
return ok;
}
/* dp->sector and dp->block_id already/still in network byte order,
* data_size is payload size according to dp->head,
* and may need to be corrected for digest size. */
int drbd_send_ack_dp(struct drbd_conf *mdev, enum drbd_packets cmd,
struct p_data *dp, int data_size)
{
data_size -= (mdev->agreed_pro_version >= 87 && mdev->integrity_r_tfm) ?
crypto_hash_digestsize(mdev->integrity_r_tfm) : 0;
return _drbd_send_ack(mdev, cmd, dp->sector, cpu_to_be32(data_size),
dp->block_id);
}
int drbd_send_ack_rp(struct drbd_conf *mdev, enum drbd_packets cmd,
struct p_block_req *rp)
{
return _drbd_send_ack(mdev, cmd, rp->sector, rp->blksize, rp->block_id);
}
/**
* drbd_send_ack() - Sends an ack packet
* @mdev: DRBD device.
* @cmd: Packet command code.
* @e: Epoch entry.
*/
int drbd_send_ack(struct drbd_conf *mdev,
enum drbd_packets cmd, struct drbd_epoch_entry *e)
{
return _drbd_send_ack(mdev, cmd,
cpu_to_be64(e->sector),
cpu_to_be32(e->size),
e->block_id);
}
/* This function misuses the block_id field to signal if the blocks
* are is sync or not. */
int drbd_send_ack_ex(struct drbd_conf *mdev, enum drbd_packets cmd,
sector_t sector, int blksize, u64 block_id)
{
return _drbd_send_ack(mdev, cmd,
cpu_to_be64(sector),
cpu_to_be32(blksize),
cpu_to_be64(block_id));
}
int drbd_send_drequest(struct drbd_conf *mdev, int cmd,
sector_t sector, int size, u64 block_id)
{
int ok;
struct p_block_req p;
p.sector = cpu_to_be64(sector);
p.block_id = block_id;
p.blksize = cpu_to_be32(size);
ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, cmd,
(struct p_header80 *)&p, sizeof(p));
return ok;
}
int drbd_send_drequest_csum(struct drbd_conf *mdev,
sector_t sector, int size,
void *digest, int digest_size,
enum drbd_packets cmd)
{
int ok;
struct p_block_req p;
p.sector = cpu_to_be64(sector);
p.block_id = BE_DRBD_MAGIC + 0xbeef;
p.blksize = cpu_to_be32(size);
p.head.magic = BE_DRBD_MAGIC;
p.head.command = cpu_to_be16(cmd);
p.head.length = cpu_to_be16(sizeof(p) - sizeof(struct p_header80) + digest_size);
mutex_lock(&mdev->data.mutex);
ok = (sizeof(p) == drbd_send(mdev, mdev->data.socket, &p, sizeof(p), 0));
ok = ok && (digest_size == drbd_send(mdev, mdev->data.socket, digest, digest_size, 0));
mutex_unlock(&mdev->data.mutex);
return ok;
}
int drbd_send_ov_request(struct drbd_conf *mdev, sector_t sector, int size)
{
int ok;
struct p_block_req p;
p.sector = cpu_to_be64(sector);
p.block_id = BE_DRBD_MAGIC + 0xbabe;
p.blksize = cpu_to_be32(size);
ok = drbd_send_cmd(mdev, USE_DATA_SOCKET, P_OV_REQUEST,
(struct p_header80 *)&p, sizeof(p));
return ok;
}
/* called on sndtimeo
* returns false if we should retry,
* true if we think connection is dead
*/
static int we_should_drop_the_connection(struct drbd_conf *mdev, struct socket *sock)
{
int drop_it;
/* long elapsed = (long)(jiffies - mdev->last_received); */
drop_it = mdev->meta.socket == sock
|| !mdev->asender.task
|| get_t_state(&mdev->asender) != Running
|| mdev->state.conn < C_CONNECTED;
if (drop_it)
return true;
drop_it = !--mdev