Update Linux to v5.10.157
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.157.tar.xz
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
Change-Id: I7b30d9e98d8c465d6b44de8e7433b4a40b3289ba
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 3c74996..3aa73da 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -119,6 +119,53 @@
dc->writeback_rate_target = target;
}
+static bool idle_counter_exceeded(struct cache_set *c)
+{
+ int counter, dev_nr;
+
+ /*
+ * If c->idle_counter is overflow (idel for really long time),
+ * reset as 0 and not set maximum rate this time for code
+ * simplicity.
+ */
+ counter = atomic_inc_return(&c->idle_counter);
+ if (counter <= 0) {
+ atomic_set(&c->idle_counter, 0);
+ return false;
+ }
+
+ dev_nr = atomic_read(&c->attached_dev_nr);
+ if (dev_nr == 0)
+ return false;
+
+ /*
+ * c->idle_counter is increased by writeback thread of all
+ * attached backing devices, in order to represent a rough
+ * time period, counter should be divided by dev_nr.
+ * Otherwise the idle time cannot be larger with more backing
+ * device attached.
+ * The following calculation equals to checking
+ * (counter / dev_nr) < (dev_nr * 6)
+ */
+ if (counter < (dev_nr * dev_nr * 6))
+ return false;
+
+ return true;
+}
+
+/*
+ * Idle_counter is increased every time when update_writeback_rate() is
+ * called. If all backing devices attached to the same cache set have
+ * identical dc->writeback_rate_update_seconds values, it is about 6
+ * rounds of update_writeback_rate() on each backing device before
+ * c->at_max_writeback_rate is set to 1, and then max wrteback rate set
+ * to each dc->writeback_rate.rate.
+ * In order to avoid extra locking cost for counting exact dirty cached
+ * devices number, c->attached_dev_nr is used to calculate the idle
+ * throushold. It might be bigger if not all cached device are in write-
+ * back mode, but it still works well with limited extra rounds of
+ * update_writeback_rate().
+ */
static bool set_at_max_writeback_rate(struct cache_set *c,
struct cached_dev *dc)
{
@@ -129,21 +176,8 @@
/* Don't set max writeback rate if gc is running */
if (!c->gc_mark_valid)
return false;
- /*
- * Idle_counter is increased everytime when update_writeback_rate() is
- * called. If all backing devices attached to the same cache set have
- * identical dc->writeback_rate_update_seconds values, it is about 6
- * rounds of update_writeback_rate() on each backing device before
- * c->at_max_writeback_rate is set to 1, and then max wrteback rate set
- * to each dc->writeback_rate.rate.
- * In order to avoid extra locking cost for counting exact dirty cached
- * devices number, c->attached_dev_nr is used to calculate the idle
- * throushold. It might be bigger if not all cached device are in write-
- * back mode, but it still works well with limited extra rounds of
- * update_writeback_rate().
- */
- if (atomic_inc_return(&c->idle_counter) <
- atomic_read(&c->attached_dev_nr) * 6)
+
+ if (!idle_counter_exceeded(c))
return false;
if (atomic_read(&c->at_max_writeback_rate) != 1)
@@ -157,13 +191,10 @@
dc->writeback_rate_change = 0;
/*
- * Check c->idle_counter and c->at_max_writeback_rate agagain in case
- * new I/O arrives during before set_at_max_writeback_rate() returns.
- * Then the writeback rate is set to 1, and its new value should be
- * decided via __update_writeback_rate().
+ * In case new I/O arrives during before
+ * set_at_max_writeback_rate() returns.
*/
- if ((atomic_read(&c->idle_counter) <
- atomic_read(&c->attached_dev_nr) * 6) ||
+ if (!idle_counter_exceeded(c) ||
!atomic_read(&c->at_max_writeback_rate))
return false;
@@ -756,13 +787,11 @@
/* Init */
#define INIT_KEYS_EACH_TIME 500000
-#define INIT_KEYS_SLEEP_MS 100
struct sectors_dirty_init {
struct btree_op op;
unsigned int inode;
size_t count;
- struct bkey start;
};
static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
@@ -778,11 +807,8 @@
KEY_START(k), KEY_SIZE(k));
op->count++;
- if (atomic_read(&b->c->search_inflight) &&
- !(op->count % INIT_KEYS_EACH_TIME)) {
- bkey_copy_key(&op->start, k);
- return -EAGAIN;
- }
+ if (!(op->count % INIT_KEYS_EACH_TIME))
+ cond_resched();
return MAP_CONTINUE;
}
@@ -797,24 +823,16 @@
bch_btree_op_init(&op.op, -1);
op.inode = d->id;
op.count = 0;
- op.start = KEY(op.inode, 0, 0);
- do {
- ret = bcache_btree(map_keys_recurse,
- k,
- c->root,
- &op.op,
- &op.start,
- sectors_dirty_init_fn,
- 0);
- if (ret == -EAGAIN)
- schedule_timeout_interruptible(
- msecs_to_jiffies(INIT_KEYS_SLEEP_MS));
- else if (ret < 0) {
- pr_warn("sectors dirty init failed, ret=%d!\n", ret);
- break;
- }
- } while (ret == -EAGAIN);
+ ret = bcache_btree(map_keys_recurse,
+ k,
+ c->root,
+ &op.op,
+ &KEY(op.inode, 0, 0),
+ sectors_dirty_init_fn,
+ 0);
+ if (ret < 0)
+ pr_warn("sectors dirty init failed, ret=%d!\n", ret);
return ret;
}
@@ -858,7 +876,6 @@
goto out;
}
skip_nr--;
- cond_resched();
}
if (p) {
@@ -868,7 +885,6 @@
p = NULL;
prev_idx = cur_idx;
- cond_resched();
}
out:
@@ -899,65 +915,56 @@
struct btree_iter iter;
struct sectors_dirty_init op;
struct cache_set *c = d->c;
- struct bch_dirty_init_state *state;
- char name[32];
+ struct bch_dirty_init_state state;
/* Just count root keys if no leaf node */
+ rw_lock(0, c->root, c->root->level);
if (c->root->level == 0) {
bch_btree_op_init(&op.op, -1);
op.inode = d->id;
op.count = 0;
- op.start = KEY(op.inode, 0, 0);
for_each_key_filter(&c->root->keys,
k, &iter, bch_ptr_invalid)
sectors_dirty_init_fn(&op.op, c->root, k);
+
+ rw_unlock(0, c->root);
return;
}
- state = kzalloc(sizeof(struct bch_dirty_init_state), GFP_KERNEL);
- if (!state) {
- pr_warn("sectors dirty init failed: cannot allocate memory\n");
- return;
- }
+ memset(&state, 0, sizeof(struct bch_dirty_init_state));
+ state.c = c;
+ state.d = d;
+ state.total_threads = bch_btre_dirty_init_thread_nr();
+ state.key_idx = 0;
+ spin_lock_init(&state.idx_lock);
+ atomic_set(&state.started, 0);
+ atomic_set(&state.enough, 0);
+ init_waitqueue_head(&state.wait);
- state->c = c;
- state->d = d;
- state->total_threads = bch_btre_dirty_init_thread_nr();
- state->key_idx = 0;
- spin_lock_init(&state->idx_lock);
- atomic_set(&state->started, 0);
- atomic_set(&state->enough, 0);
- init_waitqueue_head(&state->wait);
-
- for (i = 0; i < state->total_threads; i++) {
- /* Fetch latest state->enough earlier */
+ for (i = 0; i < state.total_threads; i++) {
+ /* Fetch latest state.enough earlier */
smp_mb__before_atomic();
- if (atomic_read(&state->enough))
+ if (atomic_read(&state.enough))
break;
- state->infos[i].state = state;
- atomic_inc(&state->started);
- snprintf(name, sizeof(name), "bch_dirty_init[%d]", i);
-
- state->infos[i].thread =
- kthread_run(bch_dirty_init_thread,
- &state->infos[i],
- name);
- if (IS_ERR(state->infos[i].thread)) {
+ state.infos[i].state = &state;
+ state.infos[i].thread =
+ kthread_run(bch_dirty_init_thread, &state.infos[i],
+ "bch_dirtcnt[%d]", i);
+ if (IS_ERR(state.infos[i].thread)) {
pr_err("fails to run thread bch_dirty_init[%d]\n", i);
for (--i; i >= 0; i--)
- kthread_stop(state->infos[i].thread);
+ kthread_stop(state.infos[i].thread);
goto out;
}
+ atomic_inc(&state.started);
}
- wait_event_interruptible(state->wait,
- atomic_read(&state->started) == 0 ||
- test_bit(CACHE_SET_IO_DISABLE, &c->flags));
-
out:
- kfree(state);
+ /* Must wait for all threads to stop. */
+ wait_event(state.wait, atomic_read(&state.started) == 0);
+ rw_unlock(0, c->root);
}
void bch_cached_dev_writeback_init(struct cached_dev *dc)