/**
* lc_set - associate index with label
* @lc: the lru cache to operate on
* @enr: the label to set
* @index: the element index to associate label with.
*
* Used to initialize the active set to some previously recorded state.
*/
void lc_set(struct lru_cache *lc, unsigned int enr, int index)
{
struct lc_element *e;
if (index < 0 || index >= lc->nr_elements)
return;
e = lc_element_by_index(lc, index);
e->lc_number = enr;
hlist_del_init(&e->colision);
hlist_add_head(&e->colision, lc_hash_slot(lc, enr));
list_move(&e->list, e->refcnt ? &lc->in_use : &lc->lru);
}
/**
* drbd_al_shrink() - Removes all active extents form the activity log
* @mdev: DRBD device.
*
* Removes all active extents form the activity log, waiting until
* the reference count of each entry dropped to 0 first, of course.
*
* You need to lock mdev->act_log with lc_try_lock() / lc_unlock()
*/
void drbd_al_shrink(struct drbd_conf *mdev)
{
struct lc_element *al_ext;
int i;
D_ASSERT(test_bit(__LC_DIRTY, &mdev->act_log->flags));
for (i = 0; i < mdev->act_log->nr_elements; i++) {
al_ext = lc_element_by_index(mdev->act_log, i);
if (al_ext->lc_number == LC_FREE)
continue;
wait_event(mdev->al_wait, _try_lc_del(mdev, al_ext));
}
wake_up(&mdev->al_wait);
}
/**
* lc_dump - Dump a complete LRU cache to seq in textual form.
* @lc: the lru cache to operate on
* @seq: the &struct seq_file pointer to seq_printf into
* @utext: user supplied "heading" or other info
* @detail: function pointer the user may provide to dump further details
* of the object the lc_element is embedded in.
*/
void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext,
void (*detail) (struct seq_file *, struct lc_element *))
{
unsigned int nr_elements = lc->nr_elements;
struct lc_element *e;
int i;
seq_printf(seq, "\tnn: lc_number refcnt %s\n ", utext);
for (i = 0; i < nr_elements; i++) {
e = lc_element_by_index(lc, i);
if (e->lc_number == LC_FREE) {
seq_printf(seq, "\t%2d: FREE\n", i);
} else {
seq_printf(seq, "\t%2d: %4u %4u ", i,
e->lc_number, e->refcnt);
detail(seq, e);
}
}
}
/**
* drbd_al_apply_to_bm() - Sets the bitmap to diry(1) where covered ba active AL extents
* @mdev: DRBD device.
*/
void drbd_al_apply_to_bm(struct drbd_conf *mdev)
{
unsigned int enr;
unsigned long add = 0;
char ppb[10];
int i;
wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
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;
add += drbd_bm_ALe_set_all(mdev, enr);
}
lc_unlock(mdev->act_log);
wake_up(&mdev->al_wait);
dev_info(DEV, "Marked additional %s as out-of-sync based on AL.\n",
ppsize(ppb, Bit2KB(add)));
}
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);
}
