From 95099d4622f8cb224d94e314c7a8e0df60b13f87 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 09 Dec 2023 08:38:01 +0000
Subject: [PATCH] enable docker ppp
---
kernel/drivers/md/bcache/journal.c | 509 +++++++++++++++++++++++++++++++++++--------------------
1 files changed, 321 insertions(+), 188 deletions(-)
diff --git a/kernel/drivers/md/bcache/journal.c b/kernel/drivers/md/bcache/journal.c
index 182c2b7..aea4833 100644
--- a/kernel/drivers/md/bcache/journal.c
+++ b/kernel/drivers/md/bcache/journal.c
@@ -47,7 +47,7 @@
closure_init_stack(&cl);
- pr_debug("reading %u", bucket_index);
+ pr_debug("reading %u\n", bucket_index);
while (offset < ca->sb.bucket_size) {
reread: left = ca->sb.bucket_size - offset;
@@ -78,13 +78,13 @@
size_t blocks, bytes = set_bytes(j);
if (j->magic != jset_magic(&ca->sb)) {
- pr_debug("%u: bad magic", bucket_index);
+ pr_debug("%u: bad magic\n", bucket_index);
return ret;
}
if (bytes > left << 9 ||
bytes > PAGE_SIZE << JSET_BITS) {
- pr_info("%u: too big, %zu bytes, offset %u",
+ pr_info("%u: too big, %zu bytes, offset %u\n",
bucket_index, bytes, offset);
return ret;
}
@@ -93,13 +93,27 @@
goto reread;
if (j->csum != csum_set(j)) {
- pr_info("%u: bad csum, %zu bytes, offset %u",
+ pr_info("%u: bad csum, %zu bytes, offset %u\n",
bucket_index, bytes, offset);
return ret;
}
- blocks = set_blocks(j, block_bytes(ca->set));
+ blocks = set_blocks(j, block_bytes(ca));
+ /*
+ * Nodes in 'list' are in linear increasing order of
+ * i->j.seq, the node on head has the smallest (oldest)
+ * journal seq, the node on tail has the biggest
+ * (latest) journal seq.
+ */
+
+ /*
+ * Check from the oldest jset for last_seq. If
+ * i->j.seq < j->last_seq, it means the oldest jset
+ * in list is expired and useless, remove it from
+ * this list. Otherwise, j is a condidate jset for
+ * further following checks.
+ */
while (!list_empty(list)) {
i = list_first_entry(list,
struct journal_replay, list);
@@ -109,13 +123,22 @@
kfree(i);
}
+ /* iterate list in reverse order (from latest jset) */
list_for_each_entry_reverse(i, list, list) {
if (j->seq == i->j.seq)
goto next_set;
+ /*
+ * if j->seq is less than any i->j.last_seq
+ * in list, j is an expired and useless jset.
+ */
if (j->seq < i->j.last_seq)
goto next_set;
+ /*
+ * 'where' points to first jset in list which
+ * is elder then j.
+ */
if (j->seq > i->j.seq) {
where = &i->list;
goto add;
@@ -129,10 +152,12 @@
if (!i)
return -ENOMEM;
memcpy(&i->j, j, bytes);
+ /* Add to the location after 'where' points to */
list_add(&i->list, where);
ret = 1;
- ja->seq[bucket_index] = j->seq;
+ if (j->seq > ja->seq[bucket_index])
+ ja->seq[bucket_index] = j->seq;
next_set:
offset += blocks * ca->sb.block_size;
len -= blocks * ca->sb.block_size;
@@ -147,121 +172,116 @@
{
#define read_bucket(b) \
({ \
- int ret = journal_read_bucket(ca, list, b); \
+ ret = journal_read_bucket(ca, list, b); \
__set_bit(b, bitmap); \
if (ret < 0) \
return ret; \
ret; \
})
- struct cache *ca;
- unsigned int iter;
+ struct cache *ca = c->cache;
+ int ret = 0;
+ struct journal_device *ja = &ca->journal;
+ DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS);
+ unsigned int i, l, r, m;
+ uint64_t seq;
- for_each_cache(ca, c, iter) {
- struct journal_device *ja = &ca->journal;
- DECLARE_BITMAP(bitmap, SB_JOURNAL_BUCKETS);
- unsigned int i, l, r, m;
- uint64_t seq;
+ bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
+ pr_debug("%u journal buckets\n", ca->sb.njournal_buckets);
- bitmap_zero(bitmap, SB_JOURNAL_BUCKETS);
- pr_debug("%u journal buckets", ca->sb.njournal_buckets);
-
+ /*
+ * Read journal buckets ordered by golden ratio hash to quickly
+ * find a sequence of buckets with valid journal entries
+ */
+ for (i = 0; i < ca->sb.njournal_buckets; i++) {
/*
- * Read journal buckets ordered by golden ratio hash to quickly
- * find a sequence of buckets with valid journal entries
+ * We must try the index l with ZERO first for
+ * correctness due to the scenario that the journal
+ * bucket is circular buffer which might have wrapped
*/
- for (i = 0; i < ca->sb.njournal_buckets; i++) {
- /*
- * We must try the index l with ZERO first for
- * correctness due to the scenario that the journal
- * bucket is circular buffer which might have wrapped
- */
- l = (i * 2654435769U) % ca->sb.njournal_buckets;
+ l = (i * 2654435769U) % ca->sb.njournal_buckets;
- if (test_bit(l, bitmap))
- break;
+ if (test_bit(l, bitmap))
+ break;
- if (read_bucket(l))
- goto bsearch;
- }
-
- /*
- * If that fails, check all the buckets we haven't checked
- * already
- */
- pr_debug("falling back to linear search");
-
- for (l = find_first_zero_bit(bitmap, ca->sb.njournal_buckets);
- l < ca->sb.njournal_buckets;
- l = find_next_zero_bit(bitmap, ca->sb.njournal_buckets,
- l + 1))
- if (read_bucket(l))
- goto bsearch;
-
- /* no journal entries on this device? */
- if (l == ca->sb.njournal_buckets)
- continue;
-bsearch:
- BUG_ON(list_empty(list));
-
- /* Binary search */
- m = l;
- r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
- pr_debug("starting binary search, l %u r %u", l, r);
-
- while (l + 1 < r) {
- seq = list_entry(list->prev, struct journal_replay,
- list)->j.seq;
-
- m = (l + r) >> 1;
- read_bucket(m);
-
- if (seq != list_entry(list->prev, struct journal_replay,
- list)->j.seq)
- l = m;
- else
- r = m;
- }
-
- /*
- * Read buckets in reverse order until we stop finding more
- * journal entries
- */
- pr_debug("finishing up: m %u njournal_buckets %u",
- m, ca->sb.njournal_buckets);
- l = m;
-
- while (1) {
- if (!l--)
- l = ca->sb.njournal_buckets - 1;
-
- if (l == m)
- break;
-
- if (test_bit(l, bitmap))
- continue;
-
- if (!read_bucket(l))
- break;
- }
-
- seq = 0;
-
- for (i = 0; i < ca->sb.njournal_buckets; i++)
- if (ja->seq[i] > seq) {
- seq = ja->seq[i];
- /*
- * When journal_reclaim() goes to allocate for
- * the first time, it'll use the bucket after
- * ja->cur_idx
- */
- ja->cur_idx = i;
- ja->last_idx = ja->discard_idx = (i + 1) %
- ca->sb.njournal_buckets;
-
- }
+ if (read_bucket(l))
+ goto bsearch;
}
+ /*
+ * If that fails, check all the buckets we haven't checked
+ * already
+ */
+ pr_debug("falling back to linear search\n");
+
+ for_each_clear_bit(l, bitmap, ca->sb.njournal_buckets)
+ if (read_bucket(l))
+ goto bsearch;
+
+ /* no journal entries on this device? */
+ if (l == ca->sb.njournal_buckets)
+ goto out;
+bsearch:
+ BUG_ON(list_empty(list));
+
+ /* Binary search */
+ m = l;
+ r = find_next_bit(bitmap, ca->sb.njournal_buckets, l + 1);
+ pr_debug("starting binary search, l %u r %u\n", l, r);
+
+ while (l + 1 < r) {
+ seq = list_entry(list->prev, struct journal_replay,
+ list)->j.seq;
+
+ m = (l + r) >> 1;
+ read_bucket(m);
+
+ if (seq != list_entry(list->prev, struct journal_replay,
+ list)->j.seq)
+ l = m;
+ else
+ r = m;
+ }
+
+ /*
+ * Read buckets in reverse order until we stop finding more
+ * journal entries
+ */
+ pr_debug("finishing up: m %u njournal_buckets %u\n",
+ m, ca->sb.njournal_buckets);
+ l = m;
+
+ while (1) {
+ if (!l--)
+ l = ca->sb.njournal_buckets - 1;
+
+ if (l == m)
+ break;
+
+ if (test_bit(l, bitmap))
+ continue;
+
+ if (!read_bucket(l))
+ break;
+ }
+
+ seq = 0;
+
+ for (i = 0; i < ca->sb.njournal_buckets; i++)
+ if (ja->seq[i] > seq) {
+ seq = ja->seq[i];
+ /*
+ * When journal_reclaim() goes to allocate for
+ * the first time, it'll use the bucket after
+ * ja->cur_idx
+ */
+ ja->cur_idx = i;
+ ja->last_idx = ja->discard_idx = (i + 1) %
+ ca->sb.njournal_buckets;
+
+ }
+
+out:
if (!list_empty(list))
c->journal.seq = list_entry(list->prev,
struct journal_replay,
@@ -317,14 +337,12 @@
}
}
-bool is_discard_enabled(struct cache_set *s)
+static bool is_discard_enabled(struct cache_set *s)
{
- struct cache *ca;
- unsigned int i;
+ struct cache *ca = s->cache;
- for_each_cache(ca, s, i)
- if (ca->discard)
- return true;
+ if (ca->discard)
+ return true;
return false;
}
@@ -344,10 +362,10 @@
if (n != i->j.seq) {
if (n == start && is_discard_enabled(s))
- pr_info("bcache: journal entries %llu-%llu may be discarded! (replaying %llu-%llu)",
+ pr_info("journal entries %llu-%llu may be discarded! (replaying %llu-%llu)\n",
n, i->j.seq - 1, start, end);
else {
- pr_err("bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)",
+ pr_err("journal entries %llu-%llu missing! (replaying %llu-%llu)\n",
n, i->j.seq - 1, start, end);
ret = -EIO;
goto err;
@@ -377,7 +395,7 @@
entries++;
}
- pr_info("journal replay done, %i keys in %i entries, seq %llu",
+ pr_info("journal replay done, %i keys in %i entries, seq %llu\n",
keys, entries, end);
err:
while (!list_empty(list)) {
@@ -389,52 +407,164 @@
return ret;
}
+void bch_journal_space_reserve(struct journal *j)
+{
+ j->do_reserve = true;
+}
+
/* Journalling */
static void btree_flush_write(struct cache_set *c)
{
- /*
- * Try to find the btree node with that references the oldest journal
- * entry, best is our current candidate and is locked if non NULL:
- */
- struct btree *b, *best;
- unsigned int i;
+ struct btree *b, *t, *btree_nodes[BTREE_FLUSH_NR];
+ unsigned int i, nr;
+ int ref_nr;
+ atomic_t *fifo_front_p, *now_fifo_front_p;
+ size_t mask;
+ if (c->journal.btree_flushing)
+ return;
+
+ spin_lock(&c->journal.flush_write_lock);
+ if (c->journal.btree_flushing) {
+ spin_unlock(&c->journal.flush_write_lock);
+ return;
+ }
+ c->journal.btree_flushing = true;
+ spin_unlock(&c->journal.flush_write_lock);
+
+ /* get the oldest journal entry and check its refcount */
+ spin_lock(&c->journal.lock);
+ fifo_front_p = &fifo_front(&c->journal.pin);
+ ref_nr = atomic_read(fifo_front_p);
+ if (ref_nr <= 0) {
+ /*
+ * do nothing if no btree node references
+ * the oldest journal entry
+ */
+ spin_unlock(&c->journal.lock);
+ goto out;
+ }
+ spin_unlock(&c->journal.lock);
+
+ mask = c->journal.pin.mask;
+ nr = 0;
atomic_long_inc(&c->flush_write);
-retry:
- best = NULL;
+ memset(btree_nodes, 0, sizeof(btree_nodes));
mutex_lock(&c->bucket_lock);
- for_each_cached_btree(b, c, i)
- if (btree_current_write(b)->journal) {
- if (!best)
- best = b;
- else if (journal_pin_cmp(c,
- btree_current_write(best)->journal,
- btree_current_write(b)->journal)) {
- best = b;
- }
+ list_for_each_entry_safe_reverse(b, t, &c->btree_cache, list) {
+ /*
+ * It is safe to get now_fifo_front_p without holding
+ * c->journal.lock here, because we don't need to know
+ * the exactly accurate value, just check whether the
+ * front pointer of c->journal.pin is changed.
+ */
+ now_fifo_front_p = &fifo_front(&c->journal.pin);
+ /*
+ * If the oldest journal entry is reclaimed and front
+ * pointer of c->journal.pin changes, it is unnecessary
+ * to scan c->btree_cache anymore, just quit the loop and
+ * flush out what we have already.
+ */
+ if (now_fifo_front_p != fifo_front_p)
+ break;
+ /*
+ * quit this loop if all matching btree nodes are
+ * scanned and record in btree_nodes[] already.
+ */
+ ref_nr = atomic_read(fifo_front_p);
+ if (nr >= ref_nr)
+ break;
+
+ if (btree_node_journal_flush(b))
+ pr_err("BUG: flush_write bit should not be set here!\n");
+
+ mutex_lock(&b->write_lock);
+
+ if (!btree_node_dirty(b)) {
+ mutex_unlock(&b->write_lock);
+ continue;
}
- b = best;
- if (b)
+ if (!btree_current_write(b)->journal) {
+ mutex_unlock(&b->write_lock);
+ continue;
+ }
+
+ /*
+ * Only select the btree node which exactly references
+ * the oldest journal entry.
+ *
+ * If the journal entry pointed by fifo_front_p is
+ * reclaimed in parallel, don't worry:
+ * - the list_for_each_xxx loop will quit when checking
+ * next now_fifo_front_p.
+ * - If there are matched nodes recorded in btree_nodes[],
+ * they are clean now (this is why and how the oldest
+ * journal entry can be reclaimed). These selected nodes
+ * will be ignored and skipped in the folowing for-loop.
+ */
+ if (((btree_current_write(b)->journal - fifo_front_p) &
+ mask) != 0) {
+ mutex_unlock(&b->write_lock);
+ continue;
+ }
+
set_btree_node_journal_flush(b);
+
+ mutex_unlock(&b->write_lock);
+
+ btree_nodes[nr++] = b;
+ /*
+ * To avoid holding c->bucket_lock too long time,
+ * only scan for BTREE_FLUSH_NR matched btree nodes
+ * at most. If there are more btree nodes reference
+ * the oldest journal entry, try to flush them next
+ * time when btree_flush_write() is called.
+ */
+ if (nr == BTREE_FLUSH_NR)
+ break;
+ }
mutex_unlock(&c->bucket_lock);
- if (b) {
+ for (i = 0; i < nr; i++) {
+ b = btree_nodes[i];
+ if (!b) {
+ pr_err("BUG: btree_nodes[%d] is NULL\n", i);
+ continue;
+ }
+
+ /* safe to check without holding b->write_lock */
+ if (!btree_node_journal_flush(b)) {
+ pr_err("BUG: bnode %p: journal_flush bit cleaned\n", b);
+ continue;
+ }
+
mutex_lock(&b->write_lock);
if (!btree_current_write(b)->journal) {
clear_bit(BTREE_NODE_journal_flush, &b->flags);
mutex_unlock(&b->write_lock);
- /* We raced */
- atomic_long_inc(&c->retry_flush_write);
- goto retry;
+ pr_debug("bnode %p: written by others\n", b);
+ continue;
+ }
+
+ if (!btree_node_dirty(b)) {
+ clear_bit(BTREE_NODE_journal_flush, &b->flags);
+ mutex_unlock(&b->write_lock);
+ pr_debug("bnode %p: dirty bit cleaned by others\n", b);
+ continue;
}
__bch_btree_node_write(b, NULL);
clear_bit(BTREE_NODE_journal_flush, &b->flags);
mutex_unlock(&b->write_lock);
}
+
+out:
+ spin_lock(&c->journal.flush_write_lock);
+ c->journal.btree_flushing = false;
+ spin_unlock(&c->journal.flush_write_lock);
}
#define last_seq(j) ((j)->seq - fifo_used(&(j)->pin) + 1)
@@ -478,7 +608,7 @@
ca->sb.njournal_buckets;
atomic_set(&ja->discard_in_flight, DISCARD_READY);
- /* fallthrough */
+ fallthrough;
case DISCARD_READY:
if (ja->discard_idx == ja->last_idx)
@@ -500,12 +630,31 @@
}
}
+static unsigned int free_journal_buckets(struct cache_set *c)
+{
+ struct journal *j = &c->journal;
+ struct cache *ca = c->cache;
+ struct journal_device *ja = &c->cache->journal;
+ unsigned int n;
+
+ /* In case njournal_buckets is not power of 2 */
+ if (ja->cur_idx >= ja->discard_idx)
+ n = ca->sb.njournal_buckets + ja->discard_idx - ja->cur_idx;
+ else
+ n = ja->discard_idx - ja->cur_idx;
+
+ if (n > (1 + j->do_reserve))
+ return n - (1 + j->do_reserve);
+
+ return 0;
+}
+
static void journal_reclaim(struct cache_set *c)
{
struct bkey *k = &c->journal.key;
- struct cache *ca;
+ struct cache *ca = c->cache;
uint64_t last_seq;
- unsigned int iter, n = 0;
+ struct journal_device *ja = &ca->journal;
atomic_t p __maybe_unused;
atomic_long_inc(&c->reclaim);
@@ -517,45 +666,29 @@
/* Update last_idx */
- for_each_cache(ca, c, iter) {
- struct journal_device *ja = &ca->journal;
+ while (ja->last_idx != ja->cur_idx &&
+ ja->seq[ja->last_idx] < last_seq)
+ ja->last_idx = (ja->last_idx + 1) %
+ ca->sb.njournal_buckets;
- while (ja->last_idx != ja->cur_idx &&
- ja->seq[ja->last_idx] < last_seq)
- ja->last_idx = (ja->last_idx + 1) %
- ca->sb.njournal_buckets;
- }
-
- for_each_cache(ca, c, iter)
- do_journal_discard(ca);
+ do_journal_discard(ca);
if (c->journal.blocks_free)
goto out;
- /*
- * Allocate:
- * XXX: Sort by free journal space
- */
+ if (!free_journal_buckets(c))
+ goto out;
- for_each_cache(ca, c, iter) {
- struct journal_device *ja = &ca->journal;
- unsigned int next = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
+ ja->cur_idx = (ja->cur_idx + 1) % ca->sb.njournal_buckets;
+ k->ptr[0] = MAKE_PTR(0,
+ bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
+ ca->sb.nr_this_dev);
+ atomic_long_inc(&c->reclaimed_journal_buckets);
- /* No space available on this device */
- if (next == ja->discard_idx)
- continue;
+ bkey_init(k);
+ SET_KEY_PTRS(k, 1);
+ c->journal.blocks_free = ca->sb.bucket_size >> c->block_bits;
- ja->cur_idx = next;
- k->ptr[n++] = MAKE_PTR(0,
- bucket_to_sector(c, ca->sb.d[ja->cur_idx]),
- ca->sb.nr_this_dev);
- }
-
- if (n) {
- bkey_init(k);
- SET_KEY_PTRS(k, n);
- c->journal.blocks_free = c->sb.bucket_size >> c->block_bits;
- }
out:
if (!journal_full(&c->journal))
__closure_wake_up(&c->journal.wait);
@@ -582,7 +715,7 @@
j->cur->data->keys = 0;
if (fifo_full(&j->pin))
- pr_debug("journal_pin full (%zu)", fifo_used(&j->pin));
+ pr_debug("journal_pin full (%zu)\n", fifo_used(&j->pin));
}
static void journal_write_endio(struct bio *bio)
@@ -619,11 +752,11 @@
__releases(c->journal.lock)
{
struct cache_set *c = container_of(cl, struct cache_set, journal.io);
- struct cache *ca;
+ struct cache *ca = c->cache;
struct journal_write *w = c->journal.cur;
struct bkey *k = &c->journal.key;
- unsigned int i, sectors = set_blocks(w->data, block_bytes(c)) *
- c->sb.block_size;
+ unsigned int i, sectors = set_blocks(w->data, block_bytes(ca)) *
+ ca->sb.block_size;
struct bio *bio;
struct bio_list list;
@@ -642,17 +775,15 @@
return;
}
- c->journal.blocks_free -= set_blocks(w->data, block_bytes(c));
+ c->journal.blocks_free -= set_blocks(w->data, block_bytes(ca));
w->data->btree_level = c->root->level;
bkey_copy(&w->data->btree_root, &c->root->key);
bkey_copy(&w->data->uuid_bucket, &c->uuid_bucket);
- for_each_cache(ca, c, i)
- w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
-
- w->data->magic = jset_magic(&c->sb);
+ w->data->prio_bucket[ca->sb.nr_this_dev] = ca->prio_buckets[0];
+ w->data->magic = jset_magic(&ca->sb);
w->data->version = BCACHE_JSET_VERSION;
w->data->last_seq = last_seq(&c->journal);
w->data->csum = csum_set(w->data);
@@ -674,7 +805,7 @@
REQ_SYNC|REQ_META|REQ_PREFLUSH|REQ_FUA);
bch_bio_map(bio, w->data);
- trace_bcache_journal_write(bio);
+ trace_bcache_journal_write(bio, w->data->keys);
bio_list_add(&list, bio);
SET_PTR_OFFSET(k, i, PTR_OFFSET(k, i) + sectors);
@@ -728,6 +859,7 @@
size_t sectors;
struct closure cl;
bool wait = false;
+ struct cache *ca = c->cache;
closure_init_stack(&cl);
@@ -737,10 +869,10 @@
struct journal_write *w = c->journal.cur;
sectors = __set_blocks(w->data, w->data->keys + nkeys,
- block_bytes(c)) * c->sb.block_size;
+ block_bytes(ca)) * ca->sb.block_size;
if (sectors <= min_t(size_t,
- c->journal.blocks_free * c->sb.block_size,
+ c->journal.blocks_free * ca->sb.block_size,
PAGE_SECTORS << JSET_BITS))
return w;
@@ -805,7 +937,7 @@
if (unlikely(test_bit(CACHE_SET_IO_DISABLE, &c->flags)))
return NULL;
- if (!CACHE_SYNC(&c->sb))
+ if (!CACHE_SYNC(&c->cache->sb))
return NULL;
w = journal_wait_for_write(c, bch_keylist_nkeys(keys));
@@ -821,8 +953,8 @@
journal_try_write(c);
} else if (!w->dirty) {
w->dirty = true;
- schedule_delayed_work(&c->journal.work,
- msecs_to_jiffies(c->journal_delay_ms));
+ queue_delayed_work(bch_flush_wq, &c->journal.work,
+ msecs_to_jiffies(c->journal_delay_ms));
spin_unlock(&c->journal.lock);
} else {
spin_unlock(&c->journal.lock);
@@ -856,6 +988,7 @@
struct journal *j = &c->journal;
spin_lock_init(&j->lock);
+ spin_lock_init(&j->flush_write_lock);
INIT_DELAYED_WORK(&j->work, journal_write_work);
c->journal_delay_ms = 100;
--
Gitblit v1.6.2