STATIC int w_update_odbm(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
struct update_odbm_work *udw = container_of(w, struct update_odbm_work, w);
if (!get_ldev(mdev)) {
if (DRBD_ratelimit(5*HZ, 5))
dev_warn(DEV, "Can not update on disk bitmap, local IO disabled.\n");
kfree(udw);
return 1;
}
drbd_bm_write_page(mdev, rs_extent_to_bm_page(udw->enr));
put_ldev(mdev);
kfree(udw);
if (drbd_bm_total_weight(mdev) <= mdev->rs_failed) {
switch (mdev->state.conn) {
case C_SYNC_SOURCE: case C_SYNC_TARGET:
case C_PAUSED_SYNC_S: case C_PAUSED_SYNC_T:
drbd_resync_finished(mdev);
default:
/* nothing to do */
break;
}
}
drbd_bcast_sync_progress(mdev);
return 1;
}
static void atodb_endio(struct bio *bio, int error)
{
struct drbd_atodb_wait *wc = bio->bi_private;
struct drbd_conf *mdev = wc->mdev;
struct page *page;
int uptodate = bio_flagged(bio, BIO_UPTODATE);
/* strange behavior of some lower level drivers...
* fail the request by clearing the uptodate flag,
* but do not return any error?! */
if (!error && !uptodate)
error = -EIO;
drbd_chk_io_error(mdev, error, TRUE);
if (error && wc->error == 0)
wc->error = error;
if (atomic_dec_and_test(&wc->count))
complete(&wc->io_done);
page = bio->bi_io_vec[0].bv_page;
put_page(page);
bio_put(bio);
mdev->bm_writ_cnt++;
put_ldev(mdev);
}
static void _req_is_done(struct drbd_conf *mdev, struct drbd_request *req, const int rw)
{
const unsigned long s = req->rq_state;
/* remove it from the transfer log.
* well, only if it had been there in the first
* place... if it had not (local only or conflicting
* and never sent), it should still be "empty" as
* initialized in drbd_req_new(), so we can list_del() it
* here unconditionally */
list_del(&req->tl_requests);
/* if it was a write, we may have to set the corresponding
* bit(s) out-of-sync first. If it had a local part, we need to
* release the reference to the activity log. */
if (rw == WRITE) {
/* Set out-of-sync unless both OK flags are set
* (local only or remote failed).
* Other places where we set out-of-sync:
* READ with local io-error */
if (!(s & RQ_NET_OK) || !(s & RQ_LOCAL_OK))
drbd_set_out_of_sync(mdev, req->sector, req->size);
if ((s & RQ_NET_OK) && (s & RQ_LOCAL_OK) && (s & RQ_NET_SIS))
drbd_set_in_sync(mdev, req->sector, req->size);
/* one might be tempted to move the drbd_al_complete_io
* to the local io completion callback drbd_endio_pri.
* but, if this was a mirror write, we may only
* drbd_al_complete_io after this is RQ_NET_DONE,
* otherwise the extent could be dropped from the al
* before it has actually been written on the peer.
* if we crash before our peer knows about the request,
* but after the extent has been dropped from the al,
* we would forget to resync the corresponding extent.
*/
if (s & RQ_LOCAL_MASK) {
if (get_ldev_if_state(mdev, D_FAILED)) {
if (s & RQ_IN_ACT_LOG)
drbd_al_complete_io(mdev, req->sector);
put_ldev(mdev);
} else if (__ratelimit(&drbd_ratelimit_state)) {
dev_warn(DEV, "Should have called drbd_al_complete_io(, %llu), "
"but my Disk seems to have failed :(\n",
(unsigned long long) req->sector);
}
}
}
drbd_req_free(req);
}
static void _req_is_done(struct drbd_conf *mdev, struct drbd_request *req, const int rw)
{
const unsigned long s = req->rq_state;
list_del(&req->tl_requests);
if (rw == WRITE) {
if (!(s & RQ_NET_OK) || !(s & RQ_LOCAL_OK))
drbd_set_out_of_sync(mdev, req->sector, req->size);
if ((s & RQ_NET_OK) && (s & RQ_LOCAL_OK) && (s & RQ_NET_SIS))
drbd_set_in_sync(mdev, req->sector, req->size);
/* one might be tempted to move the drbd_al_complete_io
* to the local io completion callback drbd_endio_pri.
* but, if this was a mirror write, we may only
* drbd_al_complete_io after this is RQ_NET_DONE,
* otherwise the extent could be dropped from the al
* before it has actually been written on the peer.
* if we crash before our peer knows about the request,
* but after the extent has been dropped from the al,
* we would forget to resync the corresponding extent.
*/
if (s & RQ_LOCAL_MASK) {
if (get_ldev_if_state(mdev, D_FAILED)) {
if (s & RQ_IN_ACT_LOG)
drbd_al_complete_io(mdev, req->sector);
put_ldev(mdev);
} else if (__ratelimit(&drbd_ratelimit_state)) {
dev_warn(DEV, "Should have called drbd_al_complete_io(, %llu), "
"but my Disk seems to have failed :(\n",
(unsigned long long) req->sector);
}
}
}
drbd_req_free(req);
}
int
w_al_write_transaction(struct drbd_conf *mdev, struct drbd_work *w, int unused)
{
struct update_al_work *aw = container_of(w, struct update_al_work, w);
struct lc_element *updated = aw->al_ext;
const unsigned int new_enr = aw->enr;
const unsigned int evicted = aw->old_enr;
struct al_transaction *buffer;
sector_t sector;
int i, n, mx;
unsigned int extent_nr;
u32 xor_sum = 0;
if (!get_ldev(mdev)) {
dev_err(DEV,
"disk is %s, cannot start al transaction (-%d +%d)\n",
drbd_disk_str(mdev->state.disk), evicted, new_enr);
complete(&((struct update_al_work *)w)->event);
return 1;
}
/* do we have to do a bitmap write, first?
* TODO reduce maximum latency:
* submit both bios, then wait for both,
* instead of doing two synchronous sector writes.
* For now, we must not write the transaction,
* if we cannot write out the bitmap of the evicted extent. */
if (mdev->state.conn < C_CONNECTED && evicted != LC_FREE)
drbd_bm_write_page(mdev, al_extent_to_bm_page(evicted));
/* The bitmap write may have failed, causing a state change. */
if (mdev->state.disk < D_INCONSISTENT) {
dev_err(DEV,
"disk is %s, cannot write al transaction (-%d +%d)\n",
drbd_disk_str(mdev->state.disk), evicted, new_enr);
complete(&((struct update_al_work *)w)->event);
put_ldev(mdev);
return 1;
}
mutex_lock(&mdev->md_io_mutex); /* protects md_io_buffer, al_tr_cycle, ... */
buffer = (struct al_transaction *)page_address(mdev->md_io_page);
buffer->magic = __constant_cpu_to_be32(DRBD_MAGIC);
buffer->tr_number = cpu_to_be32(mdev->al_tr_number);
n = lc_index_of(mdev->act_log, updated);
buffer->updates[0].pos = cpu_to_be32(n);
buffer->updates[0].extent = cpu_to_be32(new_enr);
xor_sum ^= new_enr;
mx = min_t(int, AL_EXTENTS_PT,
mdev->act_log->nr_elements - mdev->al_tr_cycle);
for (i = 0; i < mx; i++) {
unsigned idx = mdev->al_tr_cycle + i;
extent_nr = lc_element_by_index(mdev->act_log, idx)->lc_number;
buffer->updates[i+1].pos = cpu_to_be32(idx);
buffer->updates[i+1].extent = cpu_to_be32(extent_nr);
xor_sum ^= extent_nr;
}
for (; i < AL_EXTENTS_PT; i++) {
buffer->updates[i+1].pos = __constant_cpu_to_be32(-1);
buffer->updates[i+1].extent = __constant_cpu_to_be32(LC_FREE);
xor_sum ^= LC_FREE;
}
mdev->al_tr_cycle += AL_EXTENTS_PT;
if (mdev->al_tr_cycle >= mdev->act_log->nr_elements)
mdev->al_tr_cycle = 0;
buffer->xor_sum = cpu_to_be32(xor_sum);
sector = mdev->ldev->md.md_offset
+ mdev->ldev->md.al_offset + mdev->al_tr_pos;
if (!drbd_md_sync_page_io(mdev, mdev->ldev, sector, WRITE))
drbd_chk_io_error(mdev, 1, true);
if (++mdev->al_tr_pos >
div_ceil(mdev->act_log->nr_elements, AL_EXTENTS_PT))
mdev->al_tr_pos = 0;
D_ASSERT(mdev->al_tr_pos < MD_AL_MAX_SIZE);
mdev->al_tr_number++;
mutex_unlock(&mdev->md_io_mutex);
complete(&((struct update_al_work *)w)->event);
put_ldev(mdev);
return 1;
}
/**
* drbd_al_to_on_disk_bm() - * Writes bitmap parts covered by active AL extents
* @mdev: DRBD device.
*
* Called when we detach (unconfigure) local storage,
* or when we go from R_PRIMARY to R_SECONDARY role.
*/
void drbd_al_to_on_disk_bm(struct drbd_conf *mdev)
{
int i, nr_elements;
unsigned int enr;
struct bio **bios;
struct drbd_atodb_wait wc;
ERR_IF (!get_ldev_if_state(mdev, D_ATTACHING))
return; /* sorry, I don't have any act_log etc... */
wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
nr_elements = mdev->act_log->nr_elements;
/* GFP_KERNEL, we are not in anyone's write-out path */
bios = kzalloc(sizeof(struct bio *) * nr_elements, GFP_KERNEL);
if (!bios)
goto submit_one_by_one;
atomic_set(&wc.count, 0);
init_completion(&wc.io_done);
wc.mdev = mdev;
wc.error = 0;
for (i = 0; i < nr_elements; i++) {
enr = lc_element_by_index(mdev->act_log, i)->lc_number;
if (enr == LC_FREE)
continue;
/* next statement also does atomic_inc wc.count and local_cnt */
if (atodb_prepare_unless_covered(mdev, bios,
enr/AL_EXT_PER_BM_SECT,
&wc))
goto free_bios_submit_one_by_one;
}
/* unnecessary optimization? */
lc_unlock(mdev->act_log);
wake_up(&mdev->al_wait);
/* all prepared, submit them */
for (i = 0; i < nr_elements; i++) {
if (bios[i] == NULL)
break;
if (FAULT_ACTIVE(mdev, DRBD_FAULT_MD_WR)) {
bios[i]->bi_rw = WRITE;
bio_endio(bios[i], -EIO);
} else {
submit_bio(WRITE, bios[i]);
}
}
drbd_blk_run_queue(bdev_get_queue(mdev->ldev->md_bdev));
/* always (try to) flush bitmap to stable storage */
drbd_md_flush(mdev);
/* In case we did not submit a single IO do not wait for
* them to complete. ( Because we would wait forever here. )
*
* In case we had IOs and they are already complete, there
* is not point in waiting anyways.
* Therefore this if () ... */
if (atomic_read(&wc.count))
wait_for_completion(&wc.io_done);
put_ldev(mdev);
kfree(bios);
return;
free_bios_submit_one_by_one:
/* free everything by calling the endio callback directly. */
for (i = 0; i < nr_elements && bios[i]; i++)
bio_endio(bios[i], 0);
kfree(bios);
submit_one_by_one:
dev_warn(DEV, "Using the slow drbd_al_to_on_disk_bm()\n");
for (i = 0; i < mdev->act_log->nr_elements; i++) {
enr = lc_element_by_index(mdev->act_log, i)->lc_number;
if (enr == LC_FREE)
continue;
/* Really slow: if we have al-extents 16..19 active,
* sector 4 will be written four times! Synchronous! */
drbd_bm_write_sect(mdev, enr/AL_EXT_PER_BM_SECT);
}
lc_unlock(mdev->act_log);
wake_up(&mdev->al_wait);
put_ldev(mdev);
}
void drbd_req_destroy(struct kref *kref)
{
struct drbd_request *req = container_of(kref, struct drbd_request, kref);
struct drbd_conf *mdev = req->w.mdev;
const unsigned s = req->rq_state;
if ((req->master_bio && !(s & RQ_POSTPONED)) ||
atomic_read(&req->completion_ref) ||
(s & RQ_LOCAL_PENDING) ||
((s & RQ_NET_MASK) && !(s & RQ_NET_DONE))) {
dev_err(DEV, "drbd_req_destroy: Logic BUG rq_state = 0x%x, completion_ref = %d\n",
s, atomic_read(&req->completion_ref));
return;
}
/* remove it from the transfer log.
* well, only if it had been there in the first
* place... if it had not (local only or conflicting
* and never sent), it should still be "empty" as
* initialized in drbd_req_new(), so we can list_del() it
* here unconditionally */
list_del_init(&req->tl_requests);
/* if it was a write, we may have to set the corresponding
* bit(s) out-of-sync first. If it had a local part, we need to
* release the reference to the activity log. */
if (s & RQ_WRITE) {
/* Set out-of-sync unless both OK flags are set
* (local only or remote failed).
* Other places where we set out-of-sync:
* READ with local io-error */
/* There is a special case:
* we may notice late that IO was suspended,
* and postpone, or schedule for retry, a write,
* before it even was submitted or sent.
* In that case we do not want to touch the bitmap at all.
*/
if ((s & (RQ_POSTPONED|RQ_LOCAL_MASK|RQ_NET_MASK)) != RQ_POSTPONED) {
if (!(s & RQ_NET_OK) || !(s & RQ_LOCAL_OK))
drbd_set_out_of_sync(mdev, req->i.sector, req->i.size);
if ((s & RQ_NET_OK) && (s & RQ_LOCAL_OK) && (s & RQ_NET_SIS))
drbd_set_in_sync(mdev, req->i.sector, req->i.size);
}
/* one might be tempted to move the drbd_al_complete_io
* to the local io completion callback drbd_request_endio.
* but, if this was a mirror write, we may only
* drbd_al_complete_io after this is RQ_NET_DONE,
* otherwise the extent could be dropped from the al
* before it has actually been written on the peer.
* if we crash before our peer knows about the request,
* but after the extent has been dropped from the al,
* we would forget to resync the corresponding extent.
*/
if (s & RQ_IN_ACT_LOG) {
if (get_ldev_if_state(mdev, D_FAILED)) {
drbd_al_complete_io(mdev, &req->i);
put_ldev(mdev);
} else if (__ratelimit(&drbd_ratelimit_state)) {
dev_warn(DEV, "Should have called drbd_al_complete_io(, %llu, %u), "
"but my Disk seems to have failed :(\n",
(unsigned long long) req->i.sector, req->i.size);
}
}
}
mempool_free(req, drbd_request_mempool);
}
